diff --git a/DEPS b/DEPS
index e803f4066e..7aaea3d4c5 100644
--- a/DEPS
+++ b/DEPS
@@ -9,9 +9,7 @@
 vars = {
   "chromium_git": "https://chromium.googlesource.com",
   "googlesource_git": "https://%s.googlesource.com",
-  "curl_url": "https://github.com/bagder/curl.git",
-  # TODO(kqyang): Replace with an official release.
-  "curl_rev": "26ddc536b0ab5fc62d6503c82c34dd3dbf112dc3",
+  "curl_url": "https://github.com/curl/curl.git",
 }
 
 deps = {
@@ -33,10 +31,10 @@ deps = {
    # Make sure the version matches the one in
    # src/packager/third_party/boringssl, which contains perl generated files.
   "src/packager/third_party/boringssl/src":
-    (Var("googlesource_git") % "boringssl") + "/boringssl@209b2562235f7dab66b8260624e7b3c5b00d14a6",
+    (Var("googlesource_git") % "boringssl") + "/boringssl@3cab5572b1fcf5a8f6018529dc30dc8d21b2a4bd",
 
   "src/packager/third_party/curl/source":
-    Var("curl_url") + "@" + Var("curl_rev"),
+    Var("curl_url") + "@curl-7_50_0",
 
   "src/packager/third_party/gflags":
     Var("chromium_git") + "/external/webrtc/trunk/third_party/gflags@cc7e9a4b374ff7b6a1cae4d76161113ea985b624",
diff --git a/packager/media/base/test/fake_prng.cc b/packager/media/base/test/fake_prng.cc
index c9a284e48d..ab49cbb0e6 100644
--- a/packager/media/base/test/fake_prng.cc
+++ b/packager/media/base/test/fake_prng.cc
@@ -19,7 +19,7 @@ FILE* g_rand_source_fp = NULL;
 const char kFakePrngDataFile[] = "fake_prng_data.bin";
 
 // RAND_bytes and RAND_pseudorand implementation.
-int FakeBytes(uint8_t* buf, int num) {
+int FakeBytes(uint8_t* buf, size_t num) {
   DCHECK(buf);
   DCHECK(g_rand_source_fp);
 
diff --git a/packager/third_party/boringssl/BUILD.generated.gni b/packager/third_party/boringssl/BUILD.generated.gni
new file mode 100644
index 0000000000..cdbe0c95ab
--- /dev/null
+++ b/packager/third_party/boringssl/BUILD.generated.gni
@@ -0,0 +1,459 @@
+# Copyright (c) 2016 The Chromium Authors. All rights reserved.
+# Use of this source code is governed by a BSD-style license that can be
+# found in the LICENSE file.
+
+# This file is created by generate_build_files.py. Do not edit manually.
+
+crypto_sources = [
+  "err_data.c",
+  "src/crypto/aes/aes.c",
+  "src/crypto/aes/mode_wrappers.c",
+  "src/crypto/asn1/a_bitstr.c",
+  "src/crypto/asn1/a_bool.c",
+  "src/crypto/asn1/a_bytes.c",
+  "src/crypto/asn1/a_d2i_fp.c",
+  "src/crypto/asn1/a_dup.c",
+  "src/crypto/asn1/a_enum.c",
+  "src/crypto/asn1/a_gentm.c",
+  "src/crypto/asn1/a_i2d_fp.c",
+  "src/crypto/asn1/a_int.c",
+  "src/crypto/asn1/a_mbstr.c",
+  "src/crypto/asn1/a_object.c",
+  "src/crypto/asn1/a_octet.c",
+  "src/crypto/asn1/a_print.c",
+  "src/crypto/asn1/a_strnid.c",
+  "src/crypto/asn1/a_time.c",
+  "src/crypto/asn1/a_type.c",
+  "src/crypto/asn1/a_utctm.c",
+  "src/crypto/asn1/a_utf8.c",
+  "src/crypto/asn1/asn1_lib.c",
+  "src/crypto/asn1/asn1_par.c",
+  "src/crypto/asn1/asn_pack.c",
+  "src/crypto/asn1/f_enum.c",
+  "src/crypto/asn1/f_int.c",
+  "src/crypto/asn1/f_string.c",
+  "src/crypto/asn1/t_bitst.c",
+  "src/crypto/asn1/tasn_dec.c",
+  "src/crypto/asn1/tasn_enc.c",
+  "src/crypto/asn1/tasn_fre.c",
+  "src/crypto/asn1/tasn_new.c",
+  "src/crypto/asn1/tasn_typ.c",
+  "src/crypto/asn1/tasn_utl.c",
+  "src/crypto/asn1/x_bignum.c",
+  "src/crypto/asn1/x_long.c",
+  "src/crypto/base64/base64.c",
+  "src/crypto/bio/bio.c",
+  "src/crypto/bio/bio_mem.c",
+  "src/crypto/bio/buffer.c",
+  "src/crypto/bio/connect.c",
+  "src/crypto/bio/fd.c",
+  "src/crypto/bio/file.c",
+  "src/crypto/bio/hexdump.c",
+  "src/crypto/bio/pair.c",
+  "src/crypto/bio/printf.c",
+  "src/crypto/bio/socket.c",
+  "src/crypto/bio/socket_helper.c",
+  "src/crypto/bn/add.c",
+  "src/crypto/bn/asm/x86_64-gcc.c",
+  "src/crypto/bn/bn.c",
+  "src/crypto/bn/bn_asn1.c",
+  "src/crypto/bn/cmp.c",
+  "src/crypto/bn/convert.c",
+  "src/crypto/bn/ctx.c",
+  "src/crypto/bn/div.c",
+  "src/crypto/bn/exponentiation.c",
+  "src/crypto/bn/gcd.c",
+  "src/crypto/bn/generic.c",
+  "src/crypto/bn/kronecker.c",
+  "src/crypto/bn/montgomery.c",
+  "src/crypto/bn/mul.c",
+  "src/crypto/bn/prime.c",
+  "src/crypto/bn/random.c",
+  "src/crypto/bn/rsaz_exp.c",
+  "src/crypto/bn/shift.c",
+  "src/crypto/bn/sqrt.c",
+  "src/crypto/buf/buf.c",
+  "src/crypto/bytestring/asn1_compat.c",
+  "src/crypto/bytestring/ber.c",
+  "src/crypto/bytestring/cbb.c",
+  "src/crypto/bytestring/cbs.c",
+  "src/crypto/chacha/chacha.c",
+  "src/crypto/cipher/aead.c",
+  "src/crypto/cipher/cipher.c",
+  "src/crypto/cipher/derive_key.c",
+  "src/crypto/cipher/e_aes.c",
+  "src/crypto/cipher/e_chacha20poly1305.c",
+  "src/crypto/cipher/e_des.c",
+  "src/crypto/cipher/e_null.c",
+  "src/crypto/cipher/e_rc2.c",
+  "src/crypto/cipher/e_rc4.c",
+  "src/crypto/cipher/e_ssl3.c",
+  "src/crypto/cipher/e_tls.c",
+  "src/crypto/cipher/tls_cbc.c",
+  "src/crypto/cmac/cmac.c",
+  "src/crypto/conf/conf.c",
+  "src/crypto/cpu-aarch64-linux.c",
+  "src/crypto/cpu-arm-linux.c",
+  "src/crypto/cpu-arm.c",
+  "src/crypto/cpu-intel.c",
+  "src/crypto/crypto.c",
+  "src/crypto/curve25519/curve25519.c",
+  "src/crypto/curve25519/spake25519.c",
+  "src/crypto/curve25519/x25519-x86_64.c",
+  "src/crypto/des/des.c",
+  "src/crypto/dh/check.c",
+  "src/crypto/dh/dh.c",
+  "src/crypto/dh/dh_asn1.c",
+  "src/crypto/dh/params.c",
+  "src/crypto/digest/digest.c",
+  "src/crypto/digest/digests.c",
+  "src/crypto/dsa/dsa.c",
+  "src/crypto/dsa/dsa_asn1.c",
+  "src/crypto/ec/ec.c",
+  "src/crypto/ec/ec_asn1.c",
+  "src/crypto/ec/ec_key.c",
+  "src/crypto/ec/ec_montgomery.c",
+  "src/crypto/ec/oct.c",
+  "src/crypto/ec/p224-64.c",
+  "src/crypto/ec/p256-64.c",
+  "src/crypto/ec/p256-x86_64.c",
+  "src/crypto/ec/simple.c",
+  "src/crypto/ec/util-64.c",
+  "src/crypto/ec/wnaf.c",
+  "src/crypto/ecdh/ecdh.c",
+  "src/crypto/ecdsa/ecdsa.c",
+  "src/crypto/ecdsa/ecdsa_asn1.c",
+  "src/crypto/engine/engine.c",
+  "src/crypto/err/err.c",
+  "src/crypto/evp/digestsign.c",
+  "src/crypto/evp/evp.c",
+  "src/crypto/evp/evp_asn1.c",
+  "src/crypto/evp/evp_ctx.c",
+  "src/crypto/evp/p_dsa_asn1.c",
+  "src/crypto/evp/p_ec.c",
+  "src/crypto/evp/p_ec_asn1.c",
+  "src/crypto/evp/p_rsa.c",
+  "src/crypto/evp/p_rsa_asn1.c",
+  "src/crypto/evp/pbkdf.c",
+  "src/crypto/evp/print.c",
+  "src/crypto/evp/sign.c",
+  "src/crypto/ex_data.c",
+  "src/crypto/hkdf/hkdf.c",
+  "src/crypto/hmac/hmac.c",
+  "src/crypto/lhash/lhash.c",
+  "src/crypto/md4/md4.c",
+  "src/crypto/md5/md5.c",
+  "src/crypto/mem.c",
+  "src/crypto/modes/cbc.c",
+  "src/crypto/modes/cfb.c",
+  "src/crypto/modes/ctr.c",
+  "src/crypto/modes/gcm.c",
+  "src/crypto/modes/ofb.c",
+  "src/crypto/newhope/error_correction.c",
+  "src/crypto/newhope/newhope.c",
+  "src/crypto/newhope/ntt.c",
+  "src/crypto/newhope/poly.c",
+  "src/crypto/newhope/precomp.c",
+  "src/crypto/newhope/reduce.c",
+  "src/crypto/obj/obj.c",
+  "src/crypto/obj/obj_xref.c",
+  "src/crypto/pem/pem_all.c",
+  "src/crypto/pem/pem_info.c",
+  "src/crypto/pem/pem_lib.c",
+  "src/crypto/pem/pem_oth.c",
+  "src/crypto/pem/pem_pk8.c",
+  "src/crypto/pem/pem_pkey.c",
+  "src/crypto/pem/pem_x509.c",
+  "src/crypto/pem/pem_xaux.c",
+  "src/crypto/pkcs8/p5_pbe.c",
+  "src/crypto/pkcs8/p5_pbev2.c",
+  "src/crypto/pkcs8/p8_pkey.c",
+  "src/crypto/pkcs8/pkcs8.c",
+  "src/crypto/poly1305/poly1305.c",
+  "src/crypto/poly1305/poly1305_arm.c",
+  "src/crypto/poly1305/poly1305_vec.c",
+  "src/crypto/rand/deterministic.c",
+  "src/crypto/rand/rand.c",
+  "src/crypto/rand/urandom.c",
+  "src/crypto/rand/windows.c",
+  "src/crypto/rc4/rc4.c",
+  "src/crypto/refcount_c11.c",
+  "src/crypto/refcount_lock.c",
+  "src/crypto/rsa/blinding.c",
+  "src/crypto/rsa/padding.c",
+  "src/crypto/rsa/rsa.c",
+  "src/crypto/rsa/rsa_asn1.c",
+  "src/crypto/rsa/rsa_impl.c",
+  "src/crypto/sha/sha1.c",
+  "src/crypto/sha/sha256.c",
+  "src/crypto/sha/sha512.c",
+  "src/crypto/stack/stack.c",
+  "src/crypto/thread.c",
+  "src/crypto/thread_none.c",
+  "src/crypto/thread_pthread.c",
+  "src/crypto/thread_win.c",
+  "src/crypto/time_support.c",
+  "src/crypto/x509/a_digest.c",
+  "src/crypto/x509/a_sign.c",
+  "src/crypto/x509/a_strex.c",
+  "src/crypto/x509/a_verify.c",
+  "src/crypto/x509/algorithm.c",
+  "src/crypto/x509/asn1_gen.c",
+  "src/crypto/x509/by_dir.c",
+  "src/crypto/x509/by_file.c",
+  "src/crypto/x509/i2d_pr.c",
+  "src/crypto/x509/pkcs7.c",
+  "src/crypto/x509/rsa_pss.c",
+  "src/crypto/x509/t_crl.c",
+  "src/crypto/x509/t_req.c",
+  "src/crypto/x509/t_x509.c",
+  "src/crypto/x509/t_x509a.c",
+  "src/crypto/x509/x509.c",
+  "src/crypto/x509/x509_att.c",
+  "src/crypto/x509/x509_cmp.c",
+  "src/crypto/x509/x509_d2.c",
+  "src/crypto/x509/x509_def.c",
+  "src/crypto/x509/x509_ext.c",
+  "src/crypto/x509/x509_lu.c",
+  "src/crypto/x509/x509_obj.c",
+  "src/crypto/x509/x509_r2x.c",
+  "src/crypto/x509/x509_req.c",
+  "src/crypto/x509/x509_set.c",
+  "src/crypto/x509/x509_trs.c",
+  "src/crypto/x509/x509_txt.c",
+  "src/crypto/x509/x509_v3.c",
+  "src/crypto/x509/x509_vfy.c",
+  "src/crypto/x509/x509_vpm.c",
+  "src/crypto/x509/x509cset.c",
+  "src/crypto/x509/x509name.c",
+  "src/crypto/x509/x509rset.c",
+  "src/crypto/x509/x509spki.c",
+  "src/crypto/x509/x509type.c",
+  "src/crypto/x509/x_algor.c",
+  "src/crypto/x509/x_all.c",
+  "src/crypto/x509/x_attrib.c",
+  "src/crypto/x509/x_crl.c",
+  "src/crypto/x509/x_exten.c",
+  "src/crypto/x509/x_info.c",
+  "src/crypto/x509/x_name.c",
+  "src/crypto/x509/x_pkey.c",
+  "src/crypto/x509/x_pubkey.c",
+  "src/crypto/x509/x_req.c",
+  "src/crypto/x509/x_sig.c",
+  "src/crypto/x509/x_spki.c",
+  "src/crypto/x509/x_val.c",
+  "src/crypto/x509/x_x509.c",
+  "src/crypto/x509/x_x509a.c",
+  "src/crypto/x509v3/pcy_cache.c",
+  "src/crypto/x509v3/pcy_data.c",
+  "src/crypto/x509v3/pcy_lib.c",
+  "src/crypto/x509v3/pcy_map.c",
+  "src/crypto/x509v3/pcy_node.c",
+  "src/crypto/x509v3/pcy_tree.c",
+  "src/crypto/x509v3/v3_akey.c",
+  "src/crypto/x509v3/v3_akeya.c",
+  "src/crypto/x509v3/v3_alt.c",
+  "src/crypto/x509v3/v3_bcons.c",
+  "src/crypto/x509v3/v3_bitst.c",
+  "src/crypto/x509v3/v3_conf.c",
+  "src/crypto/x509v3/v3_cpols.c",
+  "src/crypto/x509v3/v3_crld.c",
+  "src/crypto/x509v3/v3_enum.c",
+  "src/crypto/x509v3/v3_extku.c",
+  "src/crypto/x509v3/v3_genn.c",
+  "src/crypto/x509v3/v3_ia5.c",
+  "src/crypto/x509v3/v3_info.c",
+  "src/crypto/x509v3/v3_int.c",
+  "src/crypto/x509v3/v3_lib.c",
+  "src/crypto/x509v3/v3_ncons.c",
+  "src/crypto/x509v3/v3_pci.c",
+  "src/crypto/x509v3/v3_pcia.c",
+  "src/crypto/x509v3/v3_pcons.c",
+  "src/crypto/x509v3/v3_pku.c",
+  "src/crypto/x509v3/v3_pmaps.c",
+  "src/crypto/x509v3/v3_prn.c",
+  "src/crypto/x509v3/v3_purp.c",
+  "src/crypto/x509v3/v3_skey.c",
+  "src/crypto/x509v3/v3_sxnet.c",
+  "src/crypto/x509v3/v3_utl.c",
+]
+
+ssl_sources = [
+  "src/ssl/custom_extensions.c",
+  "src/ssl/d1_both.c",
+  "src/ssl/d1_lib.c",
+  "src/ssl/d1_meth.c",
+  "src/ssl/d1_pkt.c",
+  "src/ssl/d1_srtp.c",
+  "src/ssl/dtls_record.c",
+  "src/ssl/handshake_client.c",
+  "src/ssl/handshake_server.c",
+  "src/ssl/pqueue/pqueue.c",
+  "src/ssl/s3_both.c",
+  "src/ssl/s3_enc.c",
+  "src/ssl/s3_lib.c",
+  "src/ssl/s3_meth.c",
+  "src/ssl/s3_pkt.c",
+  "src/ssl/ssl_aead_ctx.c",
+  "src/ssl/ssl_asn1.c",
+  "src/ssl/ssl_buffer.c",
+  "src/ssl/ssl_cert.c",
+  "src/ssl/ssl_cipher.c",
+  "src/ssl/ssl_ecdh.c",
+  "src/ssl/ssl_file.c",
+  "src/ssl/ssl_lib.c",
+  "src/ssl/ssl_rsa.c",
+  "src/ssl/ssl_session.c",
+  "src/ssl/ssl_stat.c",
+  "src/ssl/t1_enc.c",
+  "src/ssl/t1_lib.c",
+  "src/ssl/tls_record.c",
+]
+
+crypto_sources_linux_aarch64 = [
+  "linux-aarch64/crypto/aes/aesv8-armx64.S",
+  "linux-aarch64/crypto/bn/armv8-mont.S",
+  "linux-aarch64/crypto/chacha/chacha-armv8.S",
+  "linux-aarch64/crypto/modes/ghashv8-armx64.S",
+  "linux-aarch64/crypto/sha/sha1-armv8.S",
+  "linux-aarch64/crypto/sha/sha256-armv8.S",
+  "linux-aarch64/crypto/sha/sha512-armv8.S",
+]
+
+crypto_sources_linux_arm = [
+  "linux-arm/crypto/aes/aes-armv4.S",
+  "linux-arm/crypto/aes/aesv8-armx32.S",
+  "linux-arm/crypto/aes/bsaes-armv7.S",
+  "linux-arm/crypto/bn/armv4-mont.S",
+  "linux-arm/crypto/chacha/chacha-armv4.S",
+  "linux-arm/crypto/modes/ghash-armv4.S",
+  "linux-arm/crypto/modes/ghashv8-armx32.S",
+  "linux-arm/crypto/sha/sha1-armv4-large.S",
+  "linux-arm/crypto/sha/sha256-armv4.S",
+  "linux-arm/crypto/sha/sha512-armv4.S",
+  "src/crypto/curve25519/asm/x25519-asm-arm.S",
+  "src/crypto/poly1305/poly1305_arm_asm.S",
+]
+
+crypto_sources_linux_x86 = [
+  "linux-x86/crypto/aes/aes-586.S",
+  "linux-x86/crypto/aes/aesni-x86.S",
+  "linux-x86/crypto/aes/vpaes-x86.S",
+  "linux-x86/crypto/bn/bn-586.S",
+  "linux-x86/crypto/bn/co-586.S",
+  "linux-x86/crypto/bn/x86-mont.S",
+  "linux-x86/crypto/chacha/chacha-x86.S",
+  "linux-x86/crypto/md5/md5-586.S",
+  "linux-x86/crypto/modes/ghash-x86.S",
+  "linux-x86/crypto/rc4/rc4-586.S",
+  "linux-x86/crypto/sha/sha1-586.S",
+  "linux-x86/crypto/sha/sha256-586.S",
+  "linux-x86/crypto/sha/sha512-586.S",
+]
+
+crypto_sources_linux_x86_64 = [
+  "linux-x86_64/crypto/aes/aes-x86_64.S",
+  "linux-x86_64/crypto/aes/aesni-x86_64.S",
+  "linux-x86_64/crypto/aes/bsaes-x86_64.S",
+  "linux-x86_64/crypto/aes/vpaes-x86_64.S",
+  "linux-x86_64/crypto/bn/rsaz-avx2.S",
+  "linux-x86_64/crypto/bn/rsaz-x86_64.S",
+  "linux-x86_64/crypto/bn/x86_64-mont.S",
+  "linux-x86_64/crypto/bn/x86_64-mont5.S",
+  "linux-x86_64/crypto/chacha/chacha-x86_64.S",
+  "linux-x86_64/crypto/ec/p256-x86_64-asm.S",
+  "linux-x86_64/crypto/md5/md5-x86_64.S",
+  "linux-x86_64/crypto/modes/aesni-gcm-x86_64.S",
+  "linux-x86_64/crypto/modes/ghash-x86_64.S",
+  "linux-x86_64/crypto/rand/rdrand-x86_64.S",
+  "linux-x86_64/crypto/rc4/rc4-x86_64.S",
+  "linux-x86_64/crypto/sha/sha1-x86_64.S",
+  "linux-x86_64/crypto/sha/sha256-x86_64.S",
+  "linux-x86_64/crypto/sha/sha512-x86_64.S",
+  "src/crypto/curve25519/asm/x25519-asm-x86_64.S",
+]
+
+crypto_sources_mac_x86 = [
+  "mac-x86/crypto/aes/aes-586.S",
+  "mac-x86/crypto/aes/aesni-x86.S",
+  "mac-x86/crypto/aes/vpaes-x86.S",
+  "mac-x86/crypto/bn/bn-586.S",
+  "mac-x86/crypto/bn/co-586.S",
+  "mac-x86/crypto/bn/x86-mont.S",
+  "mac-x86/crypto/chacha/chacha-x86.S",
+  "mac-x86/crypto/md5/md5-586.S",
+  "mac-x86/crypto/modes/ghash-x86.S",
+  "mac-x86/crypto/rc4/rc4-586.S",
+  "mac-x86/crypto/sha/sha1-586.S",
+  "mac-x86/crypto/sha/sha256-586.S",
+  "mac-x86/crypto/sha/sha512-586.S",
+]
+
+crypto_sources_mac_x86_64 = [
+  "mac-x86_64/crypto/aes/aes-x86_64.S",
+  "mac-x86_64/crypto/aes/aesni-x86_64.S",
+  "mac-x86_64/crypto/aes/bsaes-x86_64.S",
+  "mac-x86_64/crypto/aes/vpaes-x86_64.S",
+  "mac-x86_64/crypto/bn/rsaz-avx2.S",
+  "mac-x86_64/crypto/bn/rsaz-x86_64.S",
+  "mac-x86_64/crypto/bn/x86_64-mont.S",
+  "mac-x86_64/crypto/bn/x86_64-mont5.S",
+  "mac-x86_64/crypto/chacha/chacha-x86_64.S",
+  "mac-x86_64/crypto/ec/p256-x86_64-asm.S",
+  "mac-x86_64/crypto/md5/md5-x86_64.S",
+  "mac-x86_64/crypto/modes/aesni-gcm-x86_64.S",
+  "mac-x86_64/crypto/modes/ghash-x86_64.S",
+  "mac-x86_64/crypto/rand/rdrand-x86_64.S",
+  "mac-x86_64/crypto/rc4/rc4-x86_64.S",
+  "mac-x86_64/crypto/sha/sha1-x86_64.S",
+  "mac-x86_64/crypto/sha/sha256-x86_64.S",
+  "mac-x86_64/crypto/sha/sha512-x86_64.S",
+  "src/crypto/curve25519/asm/x25519-asm-x86_64.S",
+]
+
+crypto_sources_win_x86 = [
+  "win-x86/crypto/aes/aes-586.asm",
+  "win-x86/crypto/aes/aesni-x86.asm",
+  "win-x86/crypto/aes/vpaes-x86.asm",
+  "win-x86/crypto/bn/bn-586.asm",
+  "win-x86/crypto/bn/co-586.asm",
+  "win-x86/crypto/bn/x86-mont.asm",
+  "win-x86/crypto/chacha/chacha-x86.asm",
+  "win-x86/crypto/md5/md5-586.asm",
+  "win-x86/crypto/modes/ghash-x86.asm",
+  "win-x86/crypto/rc4/rc4-586.asm",
+  "win-x86/crypto/sha/sha1-586.asm",
+  "win-x86/crypto/sha/sha256-586.asm",
+  "win-x86/crypto/sha/sha512-586.asm",
+]
+
+crypto_sources_win_x86_64 = [
+  "win-x86_64/crypto/aes/aes-x86_64.asm",
+  "win-x86_64/crypto/aes/aesni-x86_64.asm",
+  "win-x86_64/crypto/aes/bsaes-x86_64.asm",
+  "win-x86_64/crypto/aes/vpaes-x86_64.asm",
+  "win-x86_64/crypto/bn/rsaz-avx2.asm",
+  "win-x86_64/crypto/bn/rsaz-x86_64.asm",
+  "win-x86_64/crypto/bn/x86_64-mont.asm",
+  "win-x86_64/crypto/bn/x86_64-mont5.asm",
+  "win-x86_64/crypto/chacha/chacha-x86_64.asm",
+  "win-x86_64/crypto/ec/p256-x86_64-asm.asm",
+  "win-x86_64/crypto/md5/md5-x86_64.asm",
+  "win-x86_64/crypto/modes/aesni-gcm-x86_64.asm",
+  "win-x86_64/crypto/modes/ghash-x86_64.asm",
+  "win-x86_64/crypto/rand/rdrand-x86_64.asm",
+  "win-x86_64/crypto/rc4/rc4-x86_64.asm",
+  "win-x86_64/crypto/sha/sha1-x86_64.asm",
+  "win-x86_64/crypto/sha/sha256-x86_64.asm",
+  "win-x86_64/crypto/sha/sha512-x86_64.asm",
+]
+
+fuzzers = [
+  "cert",
+  "client",
+  "pkcs8",
+  "privkey",
+  "read_pem",
+  "server",
+  "spki",
+]
diff --git a/packager/third_party/boringssl/BUILD.generated_tests.gni b/packager/third_party/boringssl/BUILD.generated_tests.gni
new file mode 100644
index 0000000000..8b7ea3cc59
--- /dev/null
+++ b/packager/third_party/boringssl/BUILD.generated_tests.gni
@@ -0,0 +1,597 @@
+# Copyright (c) 2016 The Chromium Authors. All rights reserved.
+# Use of this source code is governed by a BSD-style license that can be
+# found in the LICENSE file.
+
+# This file is created by generate_build_files.py. Do not edit manually.
+
+_test_support_sources = [
+  "src/crypto/test/file_test.cc",
+  "src/crypto/test/file_test.h",
+  "src/crypto/test/malloc.cc",
+  "src/crypto/test/scoped_types.h",
+  "src/crypto/test/test_util.cc",
+  "src/crypto/test/test_util.h",
+  "src/ssl/test/async_bio.h",
+  "src/ssl/test/packeted_bio.h",
+  "src/ssl/test/scoped_types.h",
+  "src/ssl/test/test_config.h",
+]
+
+template("create_tests") {
+  executable("boringssl_aes_test") {
+    sources = [
+      "src/crypto/aes/aes_test.cc",
+    ]
+    sources += _test_support_sources
+    if (defined(invoker.configs_exclude)) {
+      configs -= invoker.configs_exclude
+    }
+    configs += invoker.configs
+    deps = invoker.deps
+  }
+
+  executable("boringssl_asn1_test") {
+    sources = [
+      "src/crypto/asn1/asn1_test.cc",
+    ]
+    sources += _test_support_sources
+    if (defined(invoker.configs_exclude)) {
+      configs -= invoker.configs_exclude
+    }
+    configs += invoker.configs
+    deps = invoker.deps
+  }
+
+  executable("boringssl_base64_test") {
+    sources = [
+      "src/crypto/base64/base64_test.cc",
+    ]
+    sources += _test_support_sources
+    if (defined(invoker.configs_exclude)) {
+      configs -= invoker.configs_exclude
+    }
+    configs += invoker.configs
+    deps = invoker.deps
+  }
+
+  executable("boringssl_bio_test") {
+    sources = [
+      "src/crypto/bio/bio_test.cc",
+    ]
+    sources += _test_support_sources
+    if (defined(invoker.configs_exclude)) {
+      configs -= invoker.configs_exclude
+    }
+    configs += invoker.configs
+    deps = invoker.deps
+  }
+
+  executable("boringssl_bn_test") {
+    sources = [
+      "src/crypto/bn/bn_test.cc",
+    ]
+    sources += _test_support_sources
+    if (defined(invoker.configs_exclude)) {
+      configs -= invoker.configs_exclude
+    }
+    configs += invoker.configs
+    deps = invoker.deps
+  }
+
+  executable("boringssl_bytestring_test") {
+    sources = [
+      "src/crypto/bytestring/bytestring_test.cc",
+    ]
+    sources += _test_support_sources
+    if (defined(invoker.configs_exclude)) {
+      configs -= invoker.configs_exclude
+    }
+    configs += invoker.configs
+    deps = invoker.deps
+  }
+
+  executable("boringssl_chacha_test") {
+    sources = [
+      "src/crypto/chacha/chacha_test.cc",
+    ]
+    sources += _test_support_sources
+    if (defined(invoker.configs_exclude)) {
+      configs -= invoker.configs_exclude
+    }
+    configs += invoker.configs
+    deps = invoker.deps
+  }
+
+  executable("boringssl_aead_test") {
+    sources = [
+      "src/crypto/cipher/aead_test.cc",
+    ]
+    sources += _test_support_sources
+    if (defined(invoker.configs_exclude)) {
+      configs -= invoker.configs_exclude
+    }
+    configs += invoker.configs
+    deps = invoker.deps
+  }
+
+  executable("boringssl_cipher_test") {
+    sources = [
+      "src/crypto/cipher/cipher_test.cc",
+    ]
+    sources += _test_support_sources
+    if (defined(invoker.configs_exclude)) {
+      configs -= invoker.configs_exclude
+    }
+    configs += invoker.configs
+    deps = invoker.deps
+  }
+
+  executable("boringssl_cmac_test") {
+    sources = [
+      "src/crypto/cmac/cmac_test.cc",
+    ]
+    sources += _test_support_sources
+    if (defined(invoker.configs_exclude)) {
+      configs -= invoker.configs_exclude
+    }
+    configs += invoker.configs
+    deps = invoker.deps
+  }
+
+  executable("boringssl_constant_time_test") {
+    sources = [
+      "src/crypto/constant_time_test.c",
+    ]
+    sources += _test_support_sources
+    if (defined(invoker.configs_exclude)) {
+      configs -= invoker.configs_exclude
+    }
+    configs += invoker.configs
+    deps = invoker.deps
+  }
+
+  executable("boringssl_ed25519_test") {
+    sources = [
+      "src/crypto/curve25519/ed25519_test.cc",
+    ]
+    sources += _test_support_sources
+    if (defined(invoker.configs_exclude)) {
+      configs -= invoker.configs_exclude
+    }
+    configs += invoker.configs
+    deps = invoker.deps
+  }
+
+  executable("boringssl_spake25519_test") {
+    sources = [
+      "src/crypto/curve25519/spake25519_test.cc",
+    ]
+    sources += _test_support_sources
+    if (defined(invoker.configs_exclude)) {
+      configs -= invoker.configs_exclude
+    }
+    configs += invoker.configs
+    deps = invoker.deps
+  }
+
+  executable("boringssl_x25519_test") {
+    sources = [
+      "src/crypto/curve25519/x25519_test.cc",
+    ]
+    sources += _test_support_sources
+    if (defined(invoker.configs_exclude)) {
+      configs -= invoker.configs_exclude
+    }
+    configs += invoker.configs
+    deps = invoker.deps
+  }
+
+  executable("boringssl_dh_test") {
+    sources = [
+      "src/crypto/dh/dh_test.cc",
+    ]
+    sources += _test_support_sources
+    if (defined(invoker.configs_exclude)) {
+      configs -= invoker.configs_exclude
+    }
+    configs += invoker.configs
+    deps = invoker.deps
+  }
+
+  executable("boringssl_digest_test") {
+    sources = [
+      "src/crypto/digest/digest_test.cc",
+    ]
+    sources += _test_support_sources
+    if (defined(invoker.configs_exclude)) {
+      configs -= invoker.configs_exclude
+    }
+    configs += invoker.configs
+    deps = invoker.deps
+  }
+
+  executable("boringssl_dsa_test") {
+    sources = [
+      "src/crypto/dsa/dsa_test.c",
+    ]
+    sources += _test_support_sources
+    if (defined(invoker.configs_exclude)) {
+      configs -= invoker.configs_exclude
+    }
+    configs += invoker.configs
+    deps = invoker.deps
+  }
+
+  executable("boringssl_ec_test") {
+    sources = [
+      "src/crypto/ec/ec_test.cc",
+    ]
+    sources += _test_support_sources
+    if (defined(invoker.configs_exclude)) {
+      configs -= invoker.configs_exclude
+    }
+    configs += invoker.configs
+    deps = invoker.deps
+  }
+
+  executable("boringssl_example_mul") {
+    sources = [
+      "src/crypto/ec/example_mul.c",
+    ]
+    sources += _test_support_sources
+    if (defined(invoker.configs_exclude)) {
+      configs -= invoker.configs_exclude
+    }
+    configs += invoker.configs
+    deps = invoker.deps
+  }
+
+  executable("boringssl_ecdsa_test") {
+    sources = [
+      "src/crypto/ecdsa/ecdsa_test.cc",
+    ]
+    sources += _test_support_sources
+    if (defined(invoker.configs_exclude)) {
+      configs -= invoker.configs_exclude
+    }
+    configs += invoker.configs
+    deps = invoker.deps
+  }
+
+  executable("boringssl_err_test") {
+    sources = [
+      "src/crypto/err/err_test.cc",
+    ]
+    sources += _test_support_sources
+    if (defined(invoker.configs_exclude)) {
+      configs -= invoker.configs_exclude
+    }
+    configs += invoker.configs
+    deps = invoker.deps
+  }
+
+  executable("boringssl_evp_extra_test") {
+    sources = [
+      "src/crypto/evp/evp_extra_test.cc",
+    ]
+    sources += _test_support_sources
+    if (defined(invoker.configs_exclude)) {
+      configs -= invoker.configs_exclude
+    }
+    configs += invoker.configs
+    deps = invoker.deps
+  }
+
+  executable("boringssl_evp_test") {
+    sources = [
+      "src/crypto/evp/evp_test.cc",
+    ]
+    sources += _test_support_sources
+    if (defined(invoker.configs_exclude)) {
+      configs -= invoker.configs_exclude
+    }
+    configs += invoker.configs
+    deps = invoker.deps
+  }
+
+  executable("boringssl_pbkdf_test") {
+    sources = [
+      "src/crypto/evp/pbkdf_test.cc",
+    ]
+    sources += _test_support_sources
+    if (defined(invoker.configs_exclude)) {
+      configs -= invoker.configs_exclude
+    }
+    configs += invoker.configs
+    deps = invoker.deps
+  }
+
+  executable("boringssl_hkdf_test") {
+    sources = [
+      "src/crypto/hkdf/hkdf_test.c",
+    ]
+    sources += _test_support_sources
+    if (defined(invoker.configs_exclude)) {
+      configs -= invoker.configs_exclude
+    }
+    configs += invoker.configs
+    deps = invoker.deps
+  }
+
+  executable("boringssl_hmac_test") {
+    sources = [
+      "src/crypto/hmac/hmac_test.cc",
+    ]
+    sources += _test_support_sources
+    if (defined(invoker.configs_exclude)) {
+      configs -= invoker.configs_exclude
+    }
+    configs += invoker.configs
+    deps = invoker.deps
+  }
+
+  executable("boringssl_lhash_test") {
+    sources = [
+      "src/crypto/lhash/lhash_test.c",
+    ]
+    sources += _test_support_sources
+    if (defined(invoker.configs_exclude)) {
+      configs -= invoker.configs_exclude
+    }
+    configs += invoker.configs
+    deps = invoker.deps
+  }
+
+  executable("boringssl_gcm_test") {
+    sources = [
+      "src/crypto/modes/gcm_test.c",
+    ]
+    sources += _test_support_sources
+    if (defined(invoker.configs_exclude)) {
+      configs -= invoker.configs_exclude
+    }
+    configs += invoker.configs
+    deps = invoker.deps
+  }
+
+  executable("boringssl_newhope_statistical_test") {
+    sources = [
+      "src/crypto/newhope/newhope_statistical_test.cc",
+    ]
+    sources += _test_support_sources
+    if (defined(invoker.configs_exclude)) {
+      configs -= invoker.configs_exclude
+    }
+    configs += invoker.configs
+    deps = invoker.deps
+  }
+
+  executable("boringssl_newhope_test") {
+    sources = [
+      "src/crypto/newhope/newhope_test.cc",
+    ]
+    sources += _test_support_sources
+    if (defined(invoker.configs_exclude)) {
+      configs -= invoker.configs_exclude
+    }
+    configs += invoker.configs
+    deps = invoker.deps
+  }
+
+  executable("boringssl_newhope_vectors_test") {
+    sources = [
+      "src/crypto/newhope/newhope_vectors_test.cc",
+    ]
+    sources += _test_support_sources
+    if (defined(invoker.configs_exclude)) {
+      configs -= invoker.configs_exclude
+    }
+    configs += invoker.configs
+    deps = invoker.deps
+  }
+
+  executable("boringssl_obj_test") {
+    sources = [
+      "src/crypto/obj/obj_test.cc",
+    ]
+    sources += _test_support_sources
+    if (defined(invoker.configs_exclude)) {
+      configs -= invoker.configs_exclude
+    }
+    configs += invoker.configs
+    deps = invoker.deps
+  }
+
+  executable("boringssl_pkcs12_test") {
+    sources = [
+      "src/crypto/pkcs8/pkcs12_test.cc",
+    ]
+    sources += _test_support_sources
+    if (defined(invoker.configs_exclude)) {
+      configs -= invoker.configs_exclude
+    }
+    configs += invoker.configs
+    deps = invoker.deps
+  }
+
+  executable("boringssl_pkcs8_test") {
+    sources = [
+      "src/crypto/pkcs8/pkcs8_test.cc",
+    ]
+    sources += _test_support_sources
+    if (defined(invoker.configs_exclude)) {
+      configs -= invoker.configs_exclude
+    }
+    configs += invoker.configs
+    deps = invoker.deps
+  }
+
+  executable("boringssl_poly1305_test") {
+    sources = [
+      "src/crypto/poly1305/poly1305_test.cc",
+    ]
+    sources += _test_support_sources
+    if (defined(invoker.configs_exclude)) {
+      configs -= invoker.configs_exclude
+    }
+    configs += invoker.configs
+    deps = invoker.deps
+  }
+
+  executable("boringssl_refcount_test") {
+    sources = [
+      "src/crypto/refcount_test.c",
+    ]
+    sources += _test_support_sources
+    if (defined(invoker.configs_exclude)) {
+      configs -= invoker.configs_exclude
+    }
+    configs += invoker.configs
+    deps = invoker.deps
+  }
+
+  executable("boringssl_rsa_test") {
+    sources = [
+      "src/crypto/rsa/rsa_test.cc",
+    ]
+    sources += _test_support_sources
+    if (defined(invoker.configs_exclude)) {
+      configs -= invoker.configs_exclude
+    }
+    configs += invoker.configs
+    deps = invoker.deps
+  }
+
+  executable("boringssl_thread_test") {
+    sources = [
+      "src/crypto/thread_test.c",
+    ]
+    sources += _test_support_sources
+    if (defined(invoker.configs_exclude)) {
+      configs -= invoker.configs_exclude
+    }
+    configs += invoker.configs
+    deps = invoker.deps
+  }
+
+  executable("boringssl_pkcs7_test") {
+    sources = [
+      "src/crypto/x509/pkcs7_test.c",
+    ]
+    sources += _test_support_sources
+    if (defined(invoker.configs_exclude)) {
+      configs -= invoker.configs_exclude
+    }
+    configs += invoker.configs
+    deps = invoker.deps
+  }
+
+  executable("boringssl_x509_test") {
+    sources = [
+      "src/crypto/x509/x509_test.cc",
+    ]
+    sources += _test_support_sources
+    if (defined(invoker.configs_exclude)) {
+      configs -= invoker.configs_exclude
+    }
+    configs += invoker.configs
+    deps = invoker.deps
+  }
+
+  executable("boringssl_tab_test") {
+    sources = [
+      "src/crypto/x509v3/tab_test.c",
+    ]
+    sources += _test_support_sources
+    if (defined(invoker.configs_exclude)) {
+      configs -= invoker.configs_exclude
+    }
+    configs += invoker.configs
+    deps = invoker.deps
+  }
+
+  executable("boringssl_v3name_test") {
+    sources = [
+      "src/crypto/x509v3/v3name_test.c",
+    ]
+    sources += _test_support_sources
+    if (defined(invoker.configs_exclude)) {
+      configs -= invoker.configs_exclude
+    }
+    configs += invoker.configs
+    deps = invoker.deps
+  }
+
+  executable("boringssl_pqueue_test") {
+    sources = [
+      "src/ssl/pqueue/pqueue_test.c",
+    ]
+    sources += _test_support_sources
+    if (defined(invoker.configs_exclude)) {
+      configs -= invoker.configs_exclude
+    }
+    configs += invoker.configs
+    deps = invoker.deps
+  }
+
+  executable("boringssl_ssl_test") {
+    sources = [
+      "src/ssl/ssl_test.cc",
+    ]
+    sources += _test_support_sources
+    if (defined(invoker.configs_exclude)) {
+      configs -= invoker.configs_exclude
+    }
+    configs += invoker.configs
+    deps = invoker.deps
+  }
+
+  group(target_name) {
+    deps = [
+      ":boringssl_aead_test",
+      ":boringssl_aes_test",
+      ":boringssl_asn1_test",
+      ":boringssl_base64_test",
+      ":boringssl_bio_test",
+      ":boringssl_bn_test",
+      ":boringssl_bytestring_test",
+      ":boringssl_chacha_test",
+      ":boringssl_cipher_test",
+      ":boringssl_cmac_test",
+      ":boringssl_constant_time_test",
+      ":boringssl_dh_test",
+      ":boringssl_digest_test",
+      ":boringssl_dsa_test",
+      ":boringssl_ec_test",
+      ":boringssl_ecdsa_test",
+      ":boringssl_ed25519_test",
+      ":boringssl_err_test",
+      ":boringssl_evp_extra_test",
+      ":boringssl_evp_test",
+      ":boringssl_example_mul",
+      ":boringssl_gcm_test",
+      ":boringssl_hkdf_test",
+      ":boringssl_hmac_test",
+      ":boringssl_lhash_test",
+      ":boringssl_newhope_statistical_test",
+      ":boringssl_newhope_test",
+      ":boringssl_newhope_vectors_test",
+      ":boringssl_obj_test",
+      ":boringssl_pbkdf_test",
+      ":boringssl_pkcs12_test",
+      ":boringssl_pkcs7_test",
+      ":boringssl_pkcs8_test",
+      ":boringssl_poly1305_test",
+      ":boringssl_pqueue_test",
+      ":boringssl_refcount_test",
+      ":boringssl_rsa_test",
+      ":boringssl_spake25519_test",
+      ":boringssl_ssl_test",
+      ":boringssl_tab_test",
+      ":boringssl_thread_test",
+      ":boringssl_v3name_test",
+      ":boringssl_x25519_test",
+      ":boringssl_x509_test",
+    ]
+  }
+}
diff --git a/packager/third_party/boringssl/BUILD.gn b/packager/third_party/boringssl/BUILD.gn
index a8fe16edb9..fd7c960989 100644
--- a/packager/third_party/boringssl/BUILD.gn
+++ b/packager/third_party/boringssl/BUILD.gn
@@ -2,26 +2,51 @@
 # Use of this source code is governed by a BSD-style license that can be
 # found in the LICENSE file.
 
+import("//build/config/android/config.gni")
+import("//build/config/sanitizers/sanitizers.gni")
+import("//build_overrides/build.gni")
+import("//testing/libfuzzer/fuzzer_test.gni")
+import("BUILD.generated.gni")
+import("BUILD.generated_tests.gni")
+
 # Config for us and everybody else depending on BoringSSL.
-config("openssl_config") {
-  include_dirs = []
-  include_dirs += [ "src/include" ]
+config("external_config") {
+  include_dirs = [ "src/include" ]
   if (is_component_build) {
     defines = [ "BORINGSSL_SHARED_LIBRARY" ]
   }
 }
 
-# Config internal to this build file.
-config("openssl_internal_config") {
+# Config internal to this build file, shared by boringssl and boringssl_fuzzer.
+config("internal_config") {
   visibility = [ ":*" ]  # Only targets in this file can depend on this.
+  defines = [
+    "BORINGSSL_IMPLEMENTATION",
+    "BORINGSSL_NO_STATIC_INITIALIZER",
+    "OPENSSL_SMALL",
+  ]
+  configs = [
+    # TODO(davidben): Fix size_t truncations in BoringSSL.
+    # https://crbug.com/429039
+    "//build/config/compiler:no_size_t_to_int_warning",
+  ]
+  if (is_posix) {
+    cflags_c = [ "-std=c99" ]
+    defines += [ "_XOPEN_SOURCE=700" ]
+  }
 }
 
-# The list of BoringSSL files is kept in boringssl.gypi.
-gypi_values =
-    exec_script("//build/gypi_to_gn.py",
-                [ rebase_path("//third_party/boringssl/boringssl.gypi") ],
-                "scope",
-                [ "//third_party/boringssl/boringssl.gypi" ])
+config("no_asm_config") {
+  visibility = [ ":*" ]  # Only targets in this file can depend on this.
+  defines = [ "OPENSSL_NO_ASM" ]
+}
+
+config("fuzzer_config") {
+  visibility = [ ":*" ]  # Only targets in this file can depend on this.
+  defines = [ "BORINGSSL_UNSAFE_FUZZER_MODE" ]
+}
+
+all_sources = crypto_sources + ssl_sources
 
 # Windows' assembly is built with Yasm. The other platforms use the platform
 # assembler.
@@ -29,75 +54,159 @@ if (is_win && !is_msan) {
   import("//third_party/yasm/yasm_assemble.gni")
   yasm_assemble("boringssl_asm") {
     if (current_cpu == "x64") {
-      sources = gypi_values.boringssl_win_x86_64_sources
+      sources = crypto_sources_win_x86_64
     } else if (current_cpu == "x86") {
-      sources = gypi_values.boringssl_win_x86_sources
+      sources = crypto_sources_win_x86
+    }
+  }
+} else {
+  source_set("boringssl_asm") {
+    visibility = [ ":*" ]  # Only targets in this file can depend on this.
+
+    defines = []
+    sources = []
+    asmflags = []
+    include_dirs = [ "src/include" ]
+
+    if ((current_cpu == "arm" || current_cpu == "arm64") && is_clang) {
+      if (current_cpu == "arm") {
+        # TODO(hans) Enable integrated-as (crbug.com/124610).
+        asmflags += [ "-fno-integrated-as" ]
+      }
+      if (is_android) {
+        rebased_android_toolchain_root =
+            rebase_path(android_toolchain_root, root_build_dir)
+
+        # Else /usr/bin/as gets picked up.
+        asmflags += [ "-B${rebased_android_toolchain_root}/bin" ]
+      }
+    }
+
+    if (is_msan) {
+      public_configs = [ ":no_asm_config" ]
+    } else if (current_cpu == "x64") {
+      if (is_mac) {
+        sources += crypto_sources_mac_x86_64
+      } else if (is_linux || is_android) {
+        sources += crypto_sources_linux_x86_64
+      } else {
+        public_configs = [ ":no_asm_config" ]
+      }
+    } else if (current_cpu == "x86") {
+      if (is_mac) {
+        sources += crypto_sources_mac_x86
+      } else if (is_linux || is_android) {
+        sources += crypto_sources_linux_x86
+      } else {
+        public_configs = [ ":no_asm_config" ]
+      }
+    } else if (current_cpu == "arm" && (is_linux || is_android)) {
+      sources += crypto_sources_linux_arm
+    } else if (current_cpu == "arm64" && (is_linux || is_android)) {
+      sources += crypto_sources_linux_aarch64
+
+      # TODO(davidben): Remove explicit arch flag once https://crbug.com/576858
+      # is fixed.
+      asmflags += [ "-march=armv8-a+crypto" ]
+    } else {
+      public_configs = [ ":no_asm_config" ]
     }
   }
 }
 
 component("boringssl") {
-  sources = gypi_values.boringssl_crypto_sources
-  sources += gypi_values.boringssl_ssl_sources
-
-  public_configs = [ ":openssl_config" ]
-
-  cflags = []
-  defines = [
-    "BORINGSSL_IMPLEMENTATION",
-    "BORINGSSL_NO_STATIC_INITIALIZER",
+  sources = all_sources
+  deps = [
+    ":boringssl_asm",
   ]
-  deps = []
-  if (is_component_build) {
-    defines += [ "BORINGSSL_SHARED_LIBRARY" ]
-  }
+
+  public_configs = [ ":external_config" ]
+  configs += [ ":internal_config" ]
 
   configs -= [ "//build/config/compiler:chromium_code" ]
-  configs += [
-    "//build/config/compiler:no_chromium_code",
+  configs += [ "//build/config/compiler:no_chromium_code" ]
 
-    # TODO(davidben): Fix size_t truncations in BoringSSL.
-    # https://crbug.com/429039
-    "//build/config/compiler:no_size_t_to_int_warning",
-  ]
-
-  # Also gets the include dirs from :openssl_config
-  include_dirs = [
-    "src/include",
-
-    # This is for arm_arch.h, which is needed by some asm files. Since the
-    # asm files are generated and kept in a different directory, they
-    # cannot use relative paths to find this file.
-    "src/crypto",
-  ]
-
-  if (is_msan) {
-    defines += [ "OPENSSL_NO_ASM" ]
-  } else if (current_cpu == "x64") {
-    if (is_mac || is_ios) {
-      sources += gypi_values.boringssl_mac_x86_64_sources
-    } else if (is_linux || is_android) {
-      sources += gypi_values.boringssl_linux_x86_64_sources
-    } else if (is_win) {
-      deps += [ ":boringssl_asm" ]
-    } else {
-      defines += [ "OPENSSL_NO_ASM" ]
-    }
-  } else if (current_cpu == "x86") {
-    if (is_mac || is_ios) {
-      sources += gypi_values.boringssl_mac_x86_sources
-    } else if (is_linux || is_android) {
-      sources += gypi_values.boringssl_linux_x86_sources
-    } else if (is_win) {
-      deps += [ ":boringssl_asm" ]
-    } else {
-      defines += [ "OPENSSL_NO_ASM" ]
-    }
-  } else if (current_cpu == "arm" && (is_linux || is_android)) {
-    sources += gypi_values.boringssl_linux_arm_sources
-  } else if (current_cpu == "arm64" && (is_linux || is_android)) {
-    sources += gypi_values.boringssl_linux_aarch64_sources
-  } else {
-    defines += [ "OPENSSL_NO_ASM" ]
+  if (is_nacl) {
+    deps += [ "//native_client_sdk/src/libraries/nacl_io" ]
+  }
+}
+
+if (build_with_chromium) {
+  create_tests("boringssl_tests") {
+    configs_exclude = [ "//build/config/compiler:chromium_code" ]
+    configs = [
+      ":internal_config",
+      "//build/config/compiler:no_chromium_code",
+    ]
+    deps = [
+      ":boringssl",
+      "//build/win:default_exe_manifest",
+    ]
+  }
+
+  if (!is_ios) {
+    test("boringssl_unittests") {
+      deps = [
+        ":boringssl_tests",
+        "//base",
+        "//base/test:run_all_unittests",
+        "//base/test:test_support",
+        "//testing/gtest",
+      ]
+      sources = [
+        "boringssl_unittest.cc",
+      ]
+    }
+  }
+
+  # The same as boringssl, but builds with BORINGSSL_UNSAFE_FUZZER_MODE.
+  component("boringssl_fuzzer") {
+    visibility = [ ":*" ]  # Only targets in this file can depend on this.
+
+    sources = all_sources
+    deps = [
+      ":boringssl_asm",
+    ]
+
+    public_configs = [
+      ":external_config",
+      ":fuzzer_config",
+    ]
+    configs += [ ":internal_config" ]
+
+    configs -= [ "//build/config/compiler:chromium_code" ]
+    configs += [ "//build/config/compiler:no_chromium_code" ]
+
+    if (is_nacl) {
+      deps += [ "//native_client_sdk/src/libraries/nacl_io" ]
+    }
+  }
+
+  foreach(fuzzer, fuzzers) {
+    fuzzer_test("boringssl_${fuzzer}_fuzzer") {
+      sources = [
+        "src/fuzz/${fuzzer}.cc",
+      ]
+      deps = [
+        ":boringssl_fuzzer",
+      ]
+      seed_corpus = "src/fuzz/${fuzzer}_corpus"
+
+      if ("cert" == fuzzer) {
+        libfuzzer_options = [ "max_len=3072" ]
+      } else if ("client" == fuzzer) {
+        libfuzzer_options = [ "max_len=20000" ]
+      } else if ("pkcs8" == fuzzer) {
+        libfuzzer_options = [ "max_len=2048" ]
+      } else if ("privkey" == fuzzer) {
+        libfuzzer_options = [ "max_len=2048" ]
+      } else if ("read_pem" == fuzzer) {
+        libfuzzer_options = [ "max_len=512" ]
+      } else if ("server" == fuzzer) {
+        libfuzzer_options = [ "max_len=4096" ]
+      } else if ("spki" == fuzzer) {
+        libfuzzer_options = [ "max_len=1024" ]
+      }
+    }
   }
 }
diff --git a/packager/third_party/boringssl/README.chromium b/packager/third_party/boringssl/README.chromium
index 8c89faa633..8abcfe695d 100644
--- a/packager/third_party/boringssl/README.chromium
+++ b/packager/third_party/boringssl/README.chromium
@@ -2,7 +2,7 @@ Name: boringssl
 URL: https://boringssl.googlesource.com/boringssl
 Version: git
 License: BSDish
-License File: NOTICE
+License File: src/LICENSE
 License Android Compatible: yes
 Security Critical: yes
 
@@ -13,6 +13,7 @@ https://www.imperialviolet.org/2014/06/20/boringssl.html
 Note: when rolling DEPS forward, remember to run
 
   cd third_party/boringssl
-  python src/util/generate_build_files.py chromium
+  python src/util/generate_build_files.py gn gyp
 
-from a system with both Perl and Go installed.
+from a system with both Perl and Go installed. Alternatively, use the
+roll_boringssl.py script.
diff --git a/packager/third_party/boringssl/boringssl.gyp b/packager/third_party/boringssl/boringssl.gyp
index 5118fc7cc2..75d0829685 100644
--- a/packager/third_party/boringssl/boringssl.gyp
+++ b/packager/third_party/boringssl/boringssl.gyp
@@ -3,21 +3,35 @@
 # found in the LICENSE file.
 
 {
+  'includes': [
+    'boringssl.gypi',
+  ],
+  'target_defaults': {
+    'conditions': [
+      ['os_posix == 1', {
+        'cflags_c': [ '-std=c99' ],
+        'defines': [ '_XOPEN_SOURCE=700' ],
+      }],
+    ],
+  },
   'targets': [
     {
-      'target_name': 'boringssl',
+      'target_name': 'boringssl_nacl_win64',
       'type': '<(component)',
-      'includes': [
-        'boringssl.gypi',
-      ],
       'sources': [
         '<@(boringssl_crypto_sources)',
-        '<@(boringssl_ssl_sources)',
       ],
       'defines': [
         'BORINGSSL_IMPLEMENTATION',
         'BORINGSSL_NO_STATIC_INITIALIZER',
+        'OPENSSL_NO_ASM',
+        'OPENSSL_SMALL',
       ],
+      'configurations': {
+        'Common_Base': {
+          'msvs_target_platform': 'x64',
+        },
+      },
       # TODO(davidben): Fix size_t truncations in BoringSSL.
       # https://crbug.com/429039
       'msvs_disabled_warnings': [ 4267, ],
@@ -27,12 +41,88 @@
             'BORINGSSL_SHARED_LIBRARY',
           ],
         }],
+      ],
+      'include_dirs': [
+        'src/include',
+      ],
+      'direct_dependent_settings': {
+        'include_dirs': [
+          'src/include',
+        ],
+        'conditions': [
+          ['component == "shared_library"', {
+            'defines': [
+              'BORINGSSL_SHARED_LIBRARY',
+            ],
+          }],
+        ],
+      },
+    },
+    {
+      'target_name': 'boringssl',
+      'type': '<(component)',
+      'sources': [
+        '<@(boringssl_crypto_sources)',
+        '<@(boringssl_ssl_sources)',
+      ],
+      'defines': [
+        'BORINGSSL_IMPLEMENTATION',
+        'BORINGSSL_NO_STATIC_INITIALIZER',
+        'OPENSSL_SMALL',
+      ],
+      'dependencies': [ 'boringssl_asm' ],
+      # TODO(davidben): Fix size_t truncations in BoringSSL.
+      # https://crbug.com/429039
+      'msvs_disabled_warnings': [ 4267, ],
+      'conditions': [
+        ['component == "shared_library"', {
+          'defines': [
+            'BORINGSSL_SHARED_LIBRARY',
+          ],
+        }],
+      ],
+      'include_dirs': [
+        'src/include',
+      ],
+      'direct_dependent_settings': {
+        'include_dirs': [
+          'src/include',
+        ],
+        'conditions': [
+          ['component == "shared_library"', {
+            'defines': [
+              'BORINGSSL_SHARED_LIBRARY',
+            ],
+          }],
+        ],
+      },
+    },
+    {
+      # boringssl_asm is a separate target to allow for ASM-specific cflags.
+      'target_name': 'boringssl_asm',
+      'type': 'static_library',
+      'include_dirs': [
+        'src/include',
+      ],
+      'conditions': [
         ['target_arch == "arm" and msan == 0', {
           'conditions': [
             ['OS == "linux" or OS == "android"', {
               'sources': [ '<@(boringssl_linux_arm_sources)' ],
             }, {
-              'defines': [ 'OPENSSL_NO_ASM' ],
+              'direct_dependent_settings': {
+                'defines': [ 'OPENSSL_NO_ASM' ],
+              },
+            }],
+          ],
+        }],
+        ['target_arch == "arm" and clang == 1', {
+          # TODO(hans) Enable integrated-as (crbug.com/124610).
+          'cflags': [ '-fno-integrated-as' ],
+          'conditions': [
+            ['OS == "android"', {
+              # Else /usr/bin/as gets picked up.
+              'cflags': [ '-B<(android_toolchain)' ],
             }],
           ],
         }],
@@ -40,14 +130,19 @@
           'conditions': [
             ['OS == "linux" or OS == "android"', {
               'sources': [ '<@(boringssl_linux_aarch64_sources)' ],
+              # TODO(davidben): Remove explicit arch flag once
+              # https://crbug.com/576858 is fixed.
+              'cflags': [ '-march=armv8-a+crypto' ],
             }, {
-              'defines': [ 'OPENSSL_NO_ASM' ],
+              'direct_dependent_settings': {
+                'defines': [ 'OPENSSL_NO_ASM' ],
+              },
             }],
           ],
         }],
         ['target_arch == "ia32" and msan == 0', {
           'conditions': [
-            ['OS == "mac" or OS == "ios"', {
+            ['OS == "mac"', {
               'sources': [ '<@(boringssl_mac_x86_sources)' ],
             }],
             ['OS == "linux" or OS == "android"', {
@@ -64,14 +159,16 @@
                 '../yasm/yasm_compile.gypi',
               ],
             }],
-            ['OS != "mac" and OS != "ios" and OS != "linux" and OS != "win" and OS != "android"', {
-              'defines': [ 'OPENSSL_NO_ASM' ],
+            ['OS != "mac" and OS != "linux" and OS != "win" and OS != "android"', {
+              'direct_dependent_settings': {
+                'defines': [ 'OPENSSL_NO_ASM' ],
+              },
             }],
           ]
         }],
         ['target_arch == "x64" and msan == 0', {
           'conditions': [
-            ['OS == "mac" or OS == "ios"', {
+            ['OS == "mac"', {
               'sources': [ '<@(boringssl_mac_x86_64_sources)' ],
             }],
             ['OS == "linux" or OS == "android"', {
@@ -88,34 +185,19 @@
                 '../yasm/yasm_compile.gypi',
               ],
             }],
-            ['OS != "mac" and OS != "ios" and OS != "linux" and OS != "win" and OS != "android"', {
-              'defines': [ 'OPENSSL_NO_ASM' ],
+            ['OS != "mac" and OS != "linux" and OS != "win" and OS != "android"', {
+              'direct_dependent_settings': {
+                'defines': [ 'OPENSSL_NO_ASM' ],
+              },
             }],
           ]
         }],
         ['msan == 1 or (target_arch != "arm" and target_arch != "ia32" and target_arch != "x64" and target_arch != "arm64")', {
-          'defines': [ 'OPENSSL_NO_ASM' ],
+          'direct_dependent_settings': {
+            'defines': [ 'OPENSSL_NO_ASM' ],
+          },
         }],
       ],
-      'include_dirs': [
-        'src/include',
-        # This is for arm_arch.h, which is needed by some asm files. Since the
-        # asm files are generated and kept in a different directory, they
-        # cannot use relative paths to find this file.
-        'src/crypto',
-      ],
-      'direct_dependent_settings': {
-        'include_dirs': [
-          'src/include',
-        ],
-        'conditions': [
-          ['component == "shared_library"', {
-            'defines': [
-              'BORINGSSL_SHARED_LIBRARY',
-            ],
-          }],
-        ],
-      },
     },
   ],
 }
diff --git a/packager/third_party/boringssl/boringssl.gypi b/packager/third_party/boringssl/boringssl.gypi
index 1aaade461c..65a483e90e 100644
--- a/packager/third_party/boringssl/boringssl.gypi
+++ b/packager/third_party/boringssl/boringssl.gypi
@@ -1,4 +1,4 @@
-# Copyright (c) 2014 The Chromium Authors. All rights reserved.
+# Copyright (c) 2016 The Chromium Authors. All rights reserved.
 # Use of this source code is governed by a BSD-style license that can be
 # found in the LICENSE file.
 
@@ -7,33 +7,35 @@
 {
   'variables': {
     'boringssl_ssl_sources': [
+      'src/ssl/custom_extensions.c',
       'src/ssl/d1_both.c',
-      'src/ssl/d1_clnt.c',
       'src/ssl/d1_lib.c',
       'src/ssl/d1_meth.c',
       'src/ssl/d1_pkt.c',
       'src/ssl/d1_srtp.c',
-      'src/ssl/d1_srvr.c',
+      'src/ssl/dtls_record.c',
+      'src/ssl/handshake_client.c',
+      'src/ssl/handshake_server.c',
       'src/ssl/pqueue/pqueue.c',
       'src/ssl/s3_both.c',
-      'src/ssl/s3_clnt.c',
       'src/ssl/s3_enc.c',
       'src/ssl/s3_lib.c',
       'src/ssl/s3_meth.c',
       'src/ssl/s3_pkt.c',
-      'src/ssl/s3_srvr.c',
       'src/ssl/ssl_aead_ctx.c',
-      'src/ssl/ssl_algs.c',
       'src/ssl/ssl_asn1.c',
+      'src/ssl/ssl_buffer.c',
       'src/ssl/ssl_cert.c',
       'src/ssl/ssl_cipher.c',
+      'src/ssl/ssl_ecdh.c',
+      'src/ssl/ssl_file.c',
       'src/ssl/ssl_lib.c',
       'src/ssl/ssl_rsa.c',
-      'src/ssl/ssl_sess.c',
+      'src/ssl/ssl_session.c',
       'src/ssl/ssl_stat.c',
-      'src/ssl/ssl_txt.c',
       'src/ssl/t1_enc.c',
       'src/ssl/t1_lib.c',
+      'src/ssl/tls_record.c',
     ],
     'boringssl_crypto_sources': [
       'err_data.c',
@@ -60,18 +62,14 @@
       'src/crypto/asn1/asn1_lib.c',
       'src/crypto/asn1/asn1_par.c',
       'src/crypto/asn1/asn_pack.c',
-      'src/crypto/asn1/bio_asn1.c',
-      'src/crypto/asn1/bio_ndef.c',
       'src/crypto/asn1/f_enum.c',
       'src/crypto/asn1/f_int.c',
       'src/crypto/asn1/f_string.c',
       'src/crypto/asn1/t_bitst.c',
-      'src/crypto/asn1/t_pkey.c',
       'src/crypto/asn1/tasn_dec.c',
       'src/crypto/asn1/tasn_enc.c',
       'src/crypto/asn1/tasn_fre.c',
       'src/crypto/asn1/tasn_new.c',
-      'src/crypto/asn1/tasn_prn.c',
       'src/crypto/asn1/tasn_typ.c',
       'src/crypto/asn1/tasn_utl.c',
       'src/crypto/asn1/x_bignum.c',
@@ -108,11 +106,11 @@
       'src/crypto/bn/shift.c',
       'src/crypto/bn/sqrt.c',
       'src/crypto/buf/buf.c',
+      'src/crypto/bytestring/asn1_compat.c',
       'src/crypto/bytestring/ber.c',
       'src/crypto/bytestring/cbb.c',
       'src/crypto/bytestring/cbs.c',
-      'src/crypto/chacha/chacha_generic.c',
-      'src/crypto/chacha/chacha_vec.c',
+      'src/crypto/chacha/chacha.c',
       'src/crypto/cipher/aead.c',
       'src/crypto/cipher/cipher.c',
       'src/crypto/cipher/derive_key.c',
@@ -127,28 +125,31 @@
       'src/crypto/cipher/tls_cbc.c',
       'src/crypto/cmac/cmac.c',
       'src/crypto/conf/conf.c',
+      'src/crypto/cpu-aarch64-linux.c',
+      'src/crypto/cpu-arm-linux.c',
       'src/crypto/cpu-arm.c',
       'src/crypto/cpu-intel.c',
       'src/crypto/crypto.c',
+      'src/crypto/curve25519/curve25519.c',
+      'src/crypto/curve25519/spake25519.c',
+      'src/crypto/curve25519/x25519-x86_64.c',
       'src/crypto/des/des.c',
       'src/crypto/dh/check.c',
       'src/crypto/dh/dh.c',
       'src/crypto/dh/dh_asn1.c',
-      'src/crypto/dh/dh_impl.c',
       'src/crypto/dh/params.c',
       'src/crypto/digest/digest.c',
       'src/crypto/digest/digests.c',
-      'src/crypto/directory_posix.c',
-      'src/crypto/directory_win.c',
       'src/crypto/dsa/dsa.c',
       'src/crypto/dsa/dsa_asn1.c',
-      'src/crypto/dsa/dsa_impl.c',
       'src/crypto/ec/ec.c',
       'src/crypto/ec/ec_asn1.c',
       'src/crypto/ec/ec_key.c',
       'src/crypto/ec/ec_montgomery.c',
       'src/crypto/ec/oct.c',
+      'src/crypto/ec/p224-64.c',
       'src/crypto/ec/p256-64.c',
+      'src/crypto/ec/p256-x86_64.c',
       'src/crypto/ec/simple.c',
       'src/crypto/ec/util-64.c',
       'src/crypto/ec/wnaf.c',
@@ -157,7 +158,6 @@
       'src/crypto/ecdsa/ecdsa_asn1.c',
       'src/crypto/engine/engine.c',
       'src/crypto/err/err.c',
-      'src/crypto/evp/algorithm.c',
       'src/crypto/evp/digestsign.c',
       'src/crypto/evp/evp.c',
       'src/crypto/evp/evp_asn1.c',
@@ -168,6 +168,7 @@
       'src/crypto/evp/p_rsa.c',
       'src/crypto/evp/p_rsa_asn1.c',
       'src/crypto/evp/pbkdf.c',
+      'src/crypto/evp/print.c',
       'src/crypto/evp/sign.c',
       'src/crypto/ex_data.c',
       'src/crypto/hkdf/hkdf.c',
@@ -181,6 +182,12 @@
       'src/crypto/modes/ctr.c',
       'src/crypto/modes/gcm.c',
       'src/crypto/modes/ofb.c',
+      'src/crypto/newhope/error_correction.c',
+      'src/crypto/newhope/newhope.c',
+      'src/crypto/newhope/ntt.c',
+      'src/crypto/newhope/poly.c',
+      'src/crypto/newhope/precomp.c',
+      'src/crypto/newhope/reduce.c',
       'src/crypto/obj/obj.c',
       'src/crypto/obj/obj_xref.c',
       'src/crypto/pem/pem_all.c',
@@ -198,7 +205,7 @@
       'src/crypto/poly1305/poly1305.c',
       'src/crypto/poly1305/poly1305_arm.c',
       'src/crypto/poly1305/poly1305_vec.c',
-      'src/crypto/rand/hwrand.c',
+      'src/crypto/rand/deterministic.c',
       'src/crypto/rand/rand.c',
       'src/crypto/rand/urandom.c',
       'src/crypto/rand/windows.c',
@@ -223,11 +230,13 @@
       'src/crypto/x509/a_sign.c',
       'src/crypto/x509/a_strex.c',
       'src/crypto/x509/a_verify.c',
+      'src/crypto/x509/algorithm.c',
       'src/crypto/x509/asn1_gen.c',
       'src/crypto/x509/by_dir.c',
       'src/crypto/x509/by_file.c',
       'src/crypto/x509/i2d_pr.c',
       'src/crypto/x509/pkcs7.c',
+      'src/crypto/x509/rsa_pss.c',
       'src/crypto/x509/t_crl.c',
       'src/crypto/x509/t_req.c',
       'src/crypto/x509/t_x509.c',
@@ -303,6 +312,8 @@
     ],
     'boringssl_linux_aarch64_sources': [
       'linux-aarch64/crypto/aes/aesv8-armx64.S',
+      'linux-aarch64/crypto/bn/armv8-mont.S',
+      'linux-aarch64/crypto/chacha/chacha-armv8.S',
       'linux-aarch64/crypto/modes/ghashv8-armx64.S',
       'linux-aarch64/crypto/sha/sha1-armv8.S',
       'linux-aarch64/crypto/sha/sha256-armv8.S',
@@ -313,13 +324,13 @@
       'linux-arm/crypto/aes/aesv8-armx32.S',
       'linux-arm/crypto/aes/bsaes-armv7.S',
       'linux-arm/crypto/bn/armv4-mont.S',
+      'linux-arm/crypto/chacha/chacha-armv4.S',
       'linux-arm/crypto/modes/ghash-armv4.S',
       'linux-arm/crypto/modes/ghashv8-armx32.S',
       'linux-arm/crypto/sha/sha1-armv4-large.S',
       'linux-arm/crypto/sha/sha256-armv4.S',
       'linux-arm/crypto/sha/sha512-armv4.S',
-      'src/crypto/chacha/chacha_vec_arm.S',
-      'src/crypto/cpu-arm-asm.S',
+      'src/crypto/curve25519/asm/x25519-asm-arm.S',
       'src/crypto/poly1305/poly1305_arm_asm.S',
     ],
     'boringssl_linux_x86_sources': [
@@ -329,6 +340,7 @@
       'linux-x86/crypto/bn/bn-586.S',
       'linux-x86/crypto/bn/co-586.S',
       'linux-x86/crypto/bn/x86-mont.S',
+      'linux-x86/crypto/chacha/chacha-x86.S',
       'linux-x86/crypto/md5/md5-586.S',
       'linux-x86/crypto/modes/ghash-x86.S',
       'linux-x86/crypto/rc4/rc4-586.S',
@@ -345,15 +357,17 @@
       'linux-x86_64/crypto/bn/rsaz-x86_64.S',
       'linux-x86_64/crypto/bn/x86_64-mont.S',
       'linux-x86_64/crypto/bn/x86_64-mont5.S',
+      'linux-x86_64/crypto/chacha/chacha-x86_64.S',
+      'linux-x86_64/crypto/ec/p256-x86_64-asm.S',
       'linux-x86_64/crypto/md5/md5-x86_64.S',
       'linux-x86_64/crypto/modes/aesni-gcm-x86_64.S',
       'linux-x86_64/crypto/modes/ghash-x86_64.S',
       'linux-x86_64/crypto/rand/rdrand-x86_64.S',
-      'linux-x86_64/crypto/rc4/rc4-md5-x86_64.S',
       'linux-x86_64/crypto/rc4/rc4-x86_64.S',
       'linux-x86_64/crypto/sha/sha1-x86_64.S',
       'linux-x86_64/crypto/sha/sha256-x86_64.S',
       'linux-x86_64/crypto/sha/sha512-x86_64.S',
+      'src/crypto/curve25519/asm/x25519-asm-x86_64.S',
     ],
     'boringssl_mac_x86_sources': [
       'mac-x86/crypto/aes/aes-586.S',
@@ -362,6 +376,7 @@
       'mac-x86/crypto/bn/bn-586.S',
       'mac-x86/crypto/bn/co-586.S',
       'mac-x86/crypto/bn/x86-mont.S',
+      'mac-x86/crypto/chacha/chacha-x86.S',
       'mac-x86/crypto/md5/md5-586.S',
       'mac-x86/crypto/modes/ghash-x86.S',
       'mac-x86/crypto/rc4/rc4-586.S',
@@ -378,15 +393,17 @@
       'mac-x86_64/crypto/bn/rsaz-x86_64.S',
       'mac-x86_64/crypto/bn/x86_64-mont.S',
       'mac-x86_64/crypto/bn/x86_64-mont5.S',
+      'mac-x86_64/crypto/chacha/chacha-x86_64.S',
+      'mac-x86_64/crypto/ec/p256-x86_64-asm.S',
       'mac-x86_64/crypto/md5/md5-x86_64.S',
       'mac-x86_64/crypto/modes/aesni-gcm-x86_64.S',
       'mac-x86_64/crypto/modes/ghash-x86_64.S',
       'mac-x86_64/crypto/rand/rdrand-x86_64.S',
-      'mac-x86_64/crypto/rc4/rc4-md5-x86_64.S',
       'mac-x86_64/crypto/rc4/rc4-x86_64.S',
       'mac-x86_64/crypto/sha/sha1-x86_64.S',
       'mac-x86_64/crypto/sha/sha256-x86_64.S',
       'mac-x86_64/crypto/sha/sha512-x86_64.S',
+      'src/crypto/curve25519/asm/x25519-asm-x86_64.S',
     ],
     'boringssl_win_x86_sources': [
       'win-x86/crypto/aes/aes-586.asm',
@@ -395,6 +412,7 @@
       'win-x86/crypto/bn/bn-586.asm',
       'win-x86/crypto/bn/co-586.asm',
       'win-x86/crypto/bn/x86-mont.asm',
+      'win-x86/crypto/chacha/chacha-x86.asm',
       'win-x86/crypto/md5/md5-586.asm',
       'win-x86/crypto/modes/ghash-x86.asm',
       'win-x86/crypto/rc4/rc4-586.asm',
@@ -411,11 +429,12 @@
       'win-x86_64/crypto/bn/rsaz-x86_64.asm',
       'win-x86_64/crypto/bn/x86_64-mont.asm',
       'win-x86_64/crypto/bn/x86_64-mont5.asm',
+      'win-x86_64/crypto/chacha/chacha-x86_64.asm',
+      'win-x86_64/crypto/ec/p256-x86_64-asm.asm',
       'win-x86_64/crypto/md5/md5-x86_64.asm',
       'win-x86_64/crypto/modes/aesni-gcm-x86_64.asm',
       'win-x86_64/crypto/modes/ghash-x86_64.asm',
       'win-x86_64/crypto/rand/rdrand-x86_64.asm',
-      'win-x86_64/crypto/rc4/rc4-md5-x86_64.asm',
       'win-x86_64/crypto/rc4/rc4-x86_64.asm',
       'win-x86_64/crypto/sha/sha1-x86_64.asm',
       'win-x86_64/crypto/sha/sha256-x86_64.asm',
diff --git a/packager/third_party/boringssl/boringssl_nacl.gyp b/packager/third_party/boringssl/boringssl_nacl.gyp
index e560c29e9c..b99e00221d 100644
--- a/packager/third_party/boringssl/boringssl_nacl.gyp
+++ b/packager/third_party/boringssl/boringssl_nacl.gyp
@@ -31,10 +31,6 @@
       ],
       'include_dirs': [
         'src/include',
-        # This is for arm_arch.h, which is needed by some asm files. Since the
-        # asm files are generated and kept in a different directory, they
-        # cannot use relative paths to find this file.
-        'src/crypto',
       ],
       'direct_dependent_settings': {
         'include_dirs': [
diff --git a/packager/third_party/boringssl/boringssl_tests.gyp b/packager/third_party/boringssl/boringssl_tests.gyp
index a875bfecd4..a9160315b9 100644
--- a/packager/third_party/boringssl/boringssl_tests.gyp
+++ b/packager/third_party/boringssl/boringssl_tests.gyp
@@ -6,20 +6,24 @@
   'includes': [
     'boringssl_tests.gypi',
   ],
-  'targets': [
-    {
-      'target_name': 'boringssl_unittests',
-      'type': 'executable',
-      'sources': [
-        'boringssl_unittest.cc',
-       ],
-      'dependencies': [
-        '<@(boringssl_test_targets)',
-        '../../base/base.gyp:base',
-        '../../base/base.gyp:run_all_unittests',
-        '../../base/base.gyp:test_support_base',
-        '../../testing/gtest.gyp:gtest',
+  'conditions': [
+    ['OS!="ios"', {
+      'targets': [
+        {
+          'target_name': 'boringssl_unittests',
+          'type': 'executable',
+          'sources': [
+            'boringssl_unittest.cc',
+           ],
+          'dependencies': [
+            '<@(boringssl_test_targets)',
+            '../../base/base.gyp:base',
+            '../../base/base.gyp:run_all_unittests',
+            '../../base/base.gyp:test_support_base',
+            '../../testing/gtest.gyp:gtest',
+          ],
+        },
       ],
-    },
+    }],
   ],
 }
diff --git a/packager/third_party/boringssl/boringssl_tests.gypi b/packager/third_party/boringssl/boringssl_tests.gypi
index 675b913249..8542e5c20a 100644
--- a/packager/third_party/boringssl/boringssl_tests.gypi
+++ b/packager/third_party/boringssl/boringssl_tests.gypi
@@ -1,4 +1,4 @@
-# Copyright (c) 2014 The Chromium Authors. All rights reserved.
+# Copyright (c) 2016 The Chromium Authors. All rights reserved.
 # Use of this source code is governed by a BSD-style license that can be
 # found in the LICENSE file.
 
@@ -20,6 +20,20 @@
       # https://crbug.com/429039
       'msvs_disabled_warnings': [ 4267, ],
     },
+    {
+      'target_name': 'boringssl_asn1_test',
+      'type': 'executable',
+      'dependencies': [
+        'boringssl.gyp:boringssl',
+      ],
+      'sources': [
+        'src/crypto/asn1/asn1_test.cc',
+        '<@(boringssl_test_support_sources)',
+      ],
+      # TODO(davidben): Fix size_t truncations in BoringSSL.
+      # https://crbug.com/429039
+      'msvs_disabled_warnings': [ 4267, ],
+    },
     {
       'target_name': 'boringssl_base64_test',
       'type': 'executable',
@@ -76,6 +90,20 @@
       # https://crbug.com/429039
       'msvs_disabled_warnings': [ 4267, ],
     },
+    {
+      'target_name': 'boringssl_chacha_test',
+      'type': 'executable',
+      'dependencies': [
+        'boringssl.gyp:boringssl',
+      ],
+      'sources': [
+        'src/crypto/chacha/chacha_test.cc',
+        '<@(boringssl_test_support_sources)',
+      ],
+      # TODO(davidben): Fix size_t truncations in BoringSSL.
+      # https://crbug.com/429039
+      'msvs_disabled_warnings': [ 4267, ],
+    },
     {
       'target_name': 'boringssl_aead_test',
       'type': 'executable',
@@ -132,6 +160,48 @@
       # https://crbug.com/429039
       'msvs_disabled_warnings': [ 4267, ],
     },
+    {
+      'target_name': 'boringssl_ed25519_test',
+      'type': 'executable',
+      'dependencies': [
+        'boringssl.gyp:boringssl',
+      ],
+      'sources': [
+        'src/crypto/curve25519/ed25519_test.cc',
+        '<@(boringssl_test_support_sources)',
+      ],
+      # TODO(davidben): Fix size_t truncations in BoringSSL.
+      # https://crbug.com/429039
+      'msvs_disabled_warnings': [ 4267, ],
+    },
+    {
+      'target_name': 'boringssl_spake25519_test',
+      'type': 'executable',
+      'dependencies': [
+        'boringssl.gyp:boringssl',
+      ],
+      'sources': [
+        'src/crypto/curve25519/spake25519_test.cc',
+        '<@(boringssl_test_support_sources)',
+      ],
+      # TODO(davidben): Fix size_t truncations in BoringSSL.
+      # https://crbug.com/429039
+      'msvs_disabled_warnings': [ 4267, ],
+    },
+    {
+      'target_name': 'boringssl_x25519_test',
+      'type': 'executable',
+      'dependencies': [
+        'boringssl.gyp:boringssl',
+      ],
+      'sources': [
+        'src/crypto/curve25519/x25519_test.cc',
+        '<@(boringssl_test_support_sources)',
+      ],
+      # TODO(davidben): Fix size_t truncations in BoringSSL.
+      # https://crbug.com/429039
+      'msvs_disabled_warnings': [ 4267, ],
+    },
     {
       'target_name': 'boringssl_dh_test',
       'type': 'executable',
@@ -328,6 +398,62 @@
       # https://crbug.com/429039
       'msvs_disabled_warnings': [ 4267, ],
     },
+    {
+      'target_name': 'boringssl_newhope_statistical_test',
+      'type': 'executable',
+      'dependencies': [
+        'boringssl.gyp:boringssl',
+      ],
+      'sources': [
+        'src/crypto/newhope/newhope_statistical_test.cc',
+        '<@(boringssl_test_support_sources)',
+      ],
+      # TODO(davidben): Fix size_t truncations in BoringSSL.
+      # https://crbug.com/429039
+      'msvs_disabled_warnings': [ 4267, ],
+    },
+    {
+      'target_name': 'boringssl_newhope_test',
+      'type': 'executable',
+      'dependencies': [
+        'boringssl.gyp:boringssl',
+      ],
+      'sources': [
+        'src/crypto/newhope/newhope_test.cc',
+        '<@(boringssl_test_support_sources)',
+      ],
+      # TODO(davidben): Fix size_t truncations in BoringSSL.
+      # https://crbug.com/429039
+      'msvs_disabled_warnings': [ 4267, ],
+    },
+    {
+      'target_name': 'boringssl_newhope_vectors_test',
+      'type': 'executable',
+      'dependencies': [
+        'boringssl.gyp:boringssl',
+      ],
+      'sources': [
+        'src/crypto/newhope/newhope_vectors_test.cc',
+        '<@(boringssl_test_support_sources)',
+      ],
+      # TODO(davidben): Fix size_t truncations in BoringSSL.
+      # https://crbug.com/429039
+      'msvs_disabled_warnings': [ 4267, ],
+    },
+    {
+      'target_name': 'boringssl_obj_test',
+      'type': 'executable',
+      'dependencies': [
+        'boringssl.gyp:boringssl',
+      ],
+      'sources': [
+        'src/crypto/obj/obj_test.cc',
+        '<@(boringssl_test_support_sources)',
+      ],
+      # TODO(davidben): Fix size_t truncations in BoringSSL.
+      # https://crbug.com/429039
+      'msvs_disabled_warnings': [ 4267, ],
+    },
     {
       'target_name': 'boringssl_pkcs12_test',
       'type': 'executable',
@@ -342,6 +468,20 @@
       # https://crbug.com/429039
       'msvs_disabled_warnings': [ 4267, ],
     },
+    {
+      'target_name': 'boringssl_pkcs8_test',
+      'type': 'executable',
+      'dependencies': [
+        'boringssl.gyp:boringssl',
+      ],
+      'sources': [
+        'src/crypto/pkcs8/pkcs8_test.cc',
+        '<@(boringssl_test_support_sources)',
+      ],
+      # TODO(davidben): Fix size_t truncations in BoringSSL.
+      # https://crbug.com/429039
+      'msvs_disabled_warnings': [ 4267, ],
+    },
     {
       'target_name': 'boringssl_poly1305_test',
       'type': 'executable',
@@ -412,6 +552,20 @@
       # https://crbug.com/429039
       'msvs_disabled_warnings': [ 4267, ],
     },
+    {
+      'target_name': 'boringssl_x509_test',
+      'type': 'executable',
+      'dependencies': [
+        'boringssl.gyp:boringssl',
+      ],
+      'sources': [
+        'src/crypto/x509/x509_test.cc',
+        '<@(boringssl_test_support_sources)',
+      ],
+      # TODO(davidben): Fix size_t truncations in BoringSSL.
+      # https://crbug.com/429039
+      'msvs_disabled_warnings': [ 4267, ],
+    },
     {
       'target_name': 'boringssl_tab_test',
       'type': 'executable',
@@ -472,15 +626,25 @@
   'variables': {
     'boringssl_test_support_sources': [
       'src/crypto/test/file_test.cc',
+      'src/crypto/test/file_test.h',
       'src/crypto/test/malloc.cc',
+      'src/crypto/test/scoped_types.h',
+      'src/crypto/test/test_util.cc',
+      'src/crypto/test/test_util.h',
+      'src/ssl/test/async_bio.h',
+      'src/ssl/test/packeted_bio.h',
+      'src/ssl/test/scoped_types.h',
+      'src/ssl/test/test_config.h',
     ],
     'boringssl_test_targets': [
       'boringssl_aead_test',
       'boringssl_aes_test',
+      'boringssl_asn1_test',
       'boringssl_base64_test',
       'boringssl_bio_test',
       'boringssl_bn_test',
       'boringssl_bytestring_test',
+      'boringssl_chacha_test',
       'boringssl_cipher_test',
       'boringssl_cmac_test',
       'boringssl_constant_time_test',
@@ -489,6 +653,7 @@
       'boringssl_dsa_test',
       'boringssl_ec_test',
       'boringssl_ecdsa_test',
+      'boringssl_ed25519_test',
       'boringssl_err_test',
       'boringssl_evp_extra_test',
       'boringssl_evp_test',
@@ -497,17 +662,25 @@
       'boringssl_hkdf_test',
       'boringssl_hmac_test',
       'boringssl_lhash_test',
+      'boringssl_newhope_statistical_test',
+      'boringssl_newhope_test',
+      'boringssl_newhope_vectors_test',
+      'boringssl_obj_test',
       'boringssl_pbkdf_test',
       'boringssl_pkcs12_test',
       'boringssl_pkcs7_test',
+      'boringssl_pkcs8_test',
       'boringssl_poly1305_test',
       'boringssl_pqueue_test',
       'boringssl_refcount_test',
       'boringssl_rsa_test',
+      'boringssl_spake25519_test',
       'boringssl_ssl_test',
       'boringssl_tab_test',
       'boringssl_thread_test',
       'boringssl_v3name_test',
+      'boringssl_x25519_test',
+      'boringssl_x509_test',
     ],
   }
 }
diff --git a/packager/third_party/boringssl/boringssl_unittest.cc b/packager/third_party/boringssl/boringssl_unittest.cc
index 75b9db80bf..068dafffa6 100644
--- a/packager/third_party/boringssl/boringssl_unittest.cc
+++ b/packager/third_party/boringssl/boringssl_unittest.cc
@@ -161,6 +161,10 @@ TEST(BoringSSL, ByteString) {
   TestSimple("bytestring_test");
 }
 
+TEST(BoringSSL, ChaCha) {
+  TestSimple("chacha_test");
+}
+
 TEST(BoringSSL, Cipher) {
   base::FilePath data_file;
   ASSERT_TRUE(CryptoCipherTestPath(&data_file));
@@ -200,6 +204,19 @@ TEST(BoringSSL, ECDSA) {
   TestSimple("ecdsa_test");
 }
 
+TEST(BoringSSL, ED25519) {
+  base::FilePath data_file;
+  ASSERT_TRUE(BoringSSLPath(&data_file));
+  data_file = data_file.Append(FILE_PATH_LITERAL("crypto"));
+  data_file = data_file.Append(FILE_PATH_LITERAL("curve25519"));
+  data_file = data_file.Append(FILE_PATH_LITERAL("ed25519_tests.txt"));
+
+  std::vector<base::CommandLine::StringType> args;
+  args.push_back(data_file.value());
+
+  TestProcess("ed25519_test", args);
+}
+
 TEST(BoringSSL, ERR) {
   TestSimple("err_test");
 }
@@ -250,6 +267,23 @@ TEST(BoringSSL, LH) {
   TestSimple("lhash_test");
 }
 
+TEST(BoringSSL, NewHope) {
+  TestSimple("newhope_test");
+}
+
+TEST(BoringSSL, NewHopeVectors) {
+  base::FilePath data_file;
+  ASSERT_TRUE(BoringSSLPath(&data_file));
+  data_file = data_file.Append(FILE_PATH_LITERAL("crypto"));
+  data_file = data_file.Append(FILE_PATH_LITERAL("newhope"));
+  data_file = data_file.Append(FILE_PATH_LITERAL("newhope_test.txt"));
+
+  std::vector<base::CommandLine::StringType> args;
+  args.push_back(data_file.value());
+
+  TestProcess("newhope_vectors_test", args);
+}
+
 TEST(BoringSSL, PBKDF) {
   TestSimple("pbkdf_test");
 }
@@ -271,6 +305,10 @@ TEST(BoringSSL, PKCS7) {
   TestSimple("pkcs7_test");
 }
 
+TEST(BoringSSL, PKCS8) {
+  TestSimple("pkcs8_test");
+}
+
 TEST(BoringSSL, PKCS12) {
   TestSimple("pkcs12_test");
 }
@@ -302,3 +340,11 @@ TEST(BoringSSL, Thread) {
 TEST(BoringSSL, V3NameTest) {
   TestSimple("v3name_test");
 }
+
+TEST(BoringSSL, X25519) {
+  TestSimple("x25519_test");
+}
+
+TEST(BoringSSL, X509) {
+  TestSimple("x509_test");
+}
diff --git a/packager/third_party/boringssl/err_data.c b/packager/third_party/boringssl/err_data.c
index 43a4c7e605..32976ad424 100644
--- a/packager/third_party/boringssl/err_data.c
+++ b/packager/third_party/boringssl/err_data.c
@@ -54,178 +54,166 @@ OPENSSL_COMPILE_ASSERT(ERR_LIB_USER == 32, library_values_changed_32);
 OPENSSL_COMPILE_ASSERT(ERR_NUM_LIBS == 33, library_values_changed_num);
 
 const uint32_t kOpenSSLReasonValues[] = {
-    0xc3207ba,
-    0xc3287d4,
-    0xc3307e3,
-    0xc3387f3,
-    0xc340802,
-    0xc34881b,
-    0xc350827,
-    0xc358844,
-    0xc360856,
-    0xc368864,
-    0xc370874,
-    0xc378881,
-    0xc380891,
-    0xc38889c,
-    0xc3908b2,
-    0xc3988c1,
-    0xc3a08d5,
-    0xc3a87c7,
-    0xc3b00b0,
-    0x10321478,
-    0x10329484,
-    0x1033149d,
-    0x103394b0,
-    0x10340de1,
-    0x103494cf,
-    0x103514e4,
-    0x10359516,
-    0x1036152f,
-    0x10369544,
-    0x10371562,
-    0x10379571,
-    0x1038158d,
-    0x103895a8,
-    0x103915b7,
-    0x103995d3,
-    0x103a15ee,
-    0x103a9605,
-    0x103b1616,
-    0x103b962a,
-    0x103c1649,
-    0x103c9658,
-    0x103d166f,
-    0x103d9682,
-    0x103e0b6c,
-    0x103e96b3,
-    0x103f16c6,
-    0x103f96e0,
-    0x104016f0,
-    0x10409704,
-    0x1041171a,
-    0x10419732,
-    0x10421747,
-    0x1042975b,
-    0x1043176d,
-    0x104385d0,
-    0x104408c1,
-    0x10449782,
-    0x10451799,
-    0x104597ae,
-    0x104617bc,
-    0x10469695,
-    0x104714f7,
-    0x104787c7,
-    0x104800b0,
-    0x104894c3,
-    0x14320b4f,
-    0x14328b5d,
-    0x14330b6c,
-    0x14338b7e,
+    0xc320838,
+    0xc328852,
+    0xc330861,
+    0xc338871,
+    0xc340880,
+    0xc348899,
+    0xc3508a5,
+    0xc3588c2,
+    0xc3608d4,
+    0xc3688e2,
+    0xc3708f2,
+    0xc3788ff,
+    0xc38090f,
+    0xc38891a,
+    0xc390930,
+    0xc39893f,
+    0xc3a0953,
+    0xc3a8845,
+    0xc3b00ea,
+    0x10320845,
+    0x1032939a,
+    0x103313a6,
+    0x103393bf,
+    0x103413d2,
+    0x10348e7a,
+    0x10350c19,
+    0x103593e5,
+    0x103613fa,
+    0x1036940d,
+    0x1037142c,
+    0x10379445,
+    0x1038145a,
+    0x10389478,
+    0x10391487,
+    0x103994a3,
+    0x103a14be,
+    0x103a94cd,
+    0x103b14e9,
+    0x103b9504,
+    0x103c151b,
+    0x103c80ea,
+    0x103d152c,
+    0x103d9540,
+    0x103e155f,
+    0x103e956e,
+    0x103f1585,
+    0x103f9598,
+    0x10400bea,
+    0x104095ab,
+    0x104115c9,
+    0x104195dc,
+    0x104215f6,
+    0x10429606,
+    0x1043161a,
+    0x10439630,
+    0x10441648,
+    0x1044965d,
+    0x10451671,
+    0x10459683,
+    0x104605fb,
+    0x1046893f,
+    0x10471698,
+    0x104796af,
+    0x104816c4,
+    0x104896d2,
+    0x14320bcd,
+    0x14328bdb,
+    0x14330bea,
+    0x14338bfc,
+    0x143400ac,
+    0x143480ea,
     0x18320083,
-    0x18328e47,
-    0x18340e75,
-    0x18348e89,
-    0x18358ec0,
-    0x18368eed,
-    0x18370f00,
-    0x18378f14,
-    0x18380f38,
-    0x18388f46,
-    0x18390f5c,
-    0x18398f70,
-    0x183a0f80,
-    0x183b0f90,
-    0x183b8fa5,
-    0x183c8fd0,
-    0x183d0fe4,
-    0x183d8ff4,
-    0x183e0b9b,
-    0x183e9001,
-    0x183f1013,
-    0x183f901e,
-    0x1840102e,
-    0x1840903f,
-    0x18411050,
-    0x18419062,
-    0x1842108b,
-    0x184290bd,
-    0x184310cc,
-    0x18451135,
-    0x1845914b,
-    0x18461166,
-    0x18468ed8,
-    0x184709d9,
-    0x18478094,
-    0x18480fbc,
-    0x18489101,
-    0x18490e5d,
-    0x18498e9e,
-    0x184a119c,
-    0x184a9119,
-    0x184b10e0,
-    0x184b8e37,
-    0x184c10a4,
-    0x184c866b,
-    0x184d1181,
-    0x203211c3,
-    0x243211cf,
-    0x24328907,
-    0x243311e1,
-    0x243391ee,
-    0x243411fb,
-    0x2434920d,
-    0x2435121c,
-    0x24359239,
-    0x24361246,
-    0x24369254,
-    0x24371262,
-    0x24379270,
-    0x24381279,
-    0x24389286,
-    0x24391299,
-    0x28320b8f,
-    0x28328b9b,
-    0x28330b6c,
-    0x28338bae,
-    0x2c322b64,
-    0x2c32ab72,
-    0x2c332b84,
-    0x2c33ab96,
-    0x2c342baa,
-    0x2c34abbc,
-    0x2c352bd7,
-    0x2c35abe9,
-    0x2c362bfc,
-    0x2c3682f3,
-    0x2c372c09,
-    0x2c37ac1b,
-    0x2c382c2e,
-    0x2c38ac3c,
-    0x2c392c4c,
-    0x2c39ac5e,
-    0x2c3a2c72,
-    0x2c3aac83,
-    0x2c3b1359,
-    0x2c3bac94,
-    0x2c3c2ca8,
-    0x2c3cacbe,
-    0x2c3d2cd7,
-    0x2c3dad05,
-    0x2c3e2d13,
-    0x2c3ead2b,
-    0x2c3f2d43,
-    0x2c3fad50,
-    0x2c402d73,
-    0x2c40ad92,
-    0x2c4111c3,
-    0x2c41ada3,
-    0x2c422db6,
-    0x2c429135,
-    0x2c432dc7,
-    0x2c4386a2,
-    0x2c442cf4,
+    0x18328ed0,
+    0x183300ac,
+    0x18338ee6,
+    0x18340efa,
+    0x183480ea,
+    0x18350f0f,
+    0x18358f27,
+    0x18360f3c,
+    0x18368f50,
+    0x18370f74,
+    0x18378f8a,
+    0x18380f9e,
+    0x18388fae,
+    0x18390a57,
+    0x18398fbe,
+    0x183a0fd3,
+    0x183a8fe7,
+    0x183b0c25,
+    0x183b8ff4,
+    0x183c1006,
+    0x183c9011,
+    0x183d1021,
+    0x183d9032,
+    0x183e1043,
+    0x183e9055,
+    0x183f107e,
+    0x183f9097,
+    0x184010af,
+    0x184086d3,
+    0x203210d6,
+    0x243210e2,
+    0x24328985,
+    0x243310f4,
+    0x24339101,
+    0x2434110e,
+    0x24349120,
+    0x2435112f,
+    0x2435914c,
+    0x24361159,
+    0x24369167,
+    0x24371175,
+    0x24379183,
+    0x2438118c,
+    0x24389199,
+    0x243911ac,
+    0x28320c0d,
+    0x28328c25,
+    0x28330bea,
+    0x28338c38,
+    0x28340c19,
+    0x283480ac,
+    0x283500ea,
+    0x2c32274a,
+    0x2c32a758,
+    0x2c33276a,
+    0x2c33a77c,
+    0x2c342790,
+    0x2c34a7a2,
+    0x2c3527bd,
+    0x2c35a7cf,
+    0x2c3627e2,
+    0x2c36832d,
+    0x2c3727ef,
+    0x2c37a801,
+    0x2c382814,
+    0x2c38a82b,
+    0x2c392839,
+    0x2c39a849,
+    0x2c3a285b,
+    0x2c3aa86f,
+    0x2c3b2880,
+    0x2c3ba89f,
+    0x2c3c28b3,
+    0x2c3ca8c9,
+    0x2c3d28e2,
+    0x2c3da8ff,
+    0x2c3e2910,
+    0x2c3ea91e,
+    0x2c3f2936,
+    0x2c3fa94e,
+    0x2c40295b,
+    0x2c4090d6,
+    0x2c41296c,
+    0x2c41a97f,
+    0x2c4210af,
+    0x2c42a990,
+    0x2c430720,
+    0x2c43a891,
     0x30320000,
     0x30328015,
     0x3033001f,
@@ -235,472 +223,449 @@ const uint32_t kOpenSSLReasonValues[] = {
     0x3035006b,
     0x30358083,
     0x30360094,
-    0x303680a1,
-    0x303700b0,
-    0x303780bd,
-    0x303800d0,
-    0x303880eb,
-    0x30390100,
-    0x30398114,
-    0x303a0128,
-    0x303a8139,
-    0x303b0152,
-    0x303b816f,
-    0x303c017d,
-    0x303c8191,
-    0x303d01a1,
-    0x303d81ba,
-    0x303e01ca,
-    0x303e81dd,
-    0x303f01ec,
-    0x303f81f8,
-    0x3040020d,
-    0x3040821d,
-    0x30410234,
-    0x30418241,
-    0x30420254,
-    0x30428263,
-    0x30430278,
-    0x30438299,
-    0x304402ac,
-    0x304482bf,
-    0x304502d8,
-    0x304582f3,
-    0x30460310,
-    0x30468329,
-    0x30470337,
-    0x30478348,
-    0x30480357,
-    0x3048836f,
-    0x30490381,
-    0x30498395,
-    0x304a03b4,
-    0x304a83c7,
-    0x304b03d2,
-    0x304b83e1,
-    0x304c03f2,
-    0x304c83fe,
-    0x304d0414,
-    0x304d8422,
-    0x304e0438,
-    0x304e844a,
-    0x304f045c,
-    0x304f846f,
-    0x30500482,
-    0x30508493,
-    0x305104a3,
-    0x305184bb,
-    0x305204d0,
-    0x305284e8,
-    0x305304fc,
-    0x30538514,
-    0x3054052d,
-    0x30548546,
-    0x30550563,
-    0x3055856e,
-    0x30560586,
-    0x30568596,
-    0x305705a7,
-    0x305785ba,
-    0x305805d0,
-    0x305885d9,
-    0x305905ee,
-    0x30598601,
-    0x305a0610,
-    0x305a8630,
-    0x305b063f,
-    0x305b864b,
-    0x305c066b,
-    0x305c8687,
-    0x305d0698,
-    0x305d86a2,
-    0x34320ac9,
-    0x34328add,
-    0x34330afa,
-    0x34338b0d,
-    0x34340b1c,
-    0x34348b39,
+    0x303680ac,
+    0x303700b9,
+    0x303780c8,
+    0x303800ea,
+    0x303880f7,
+    0x3039010a,
+    0x30398125,
+    0x303a013a,
+    0x303a814e,
+    0x303b0162,
+    0x303b8173,
+    0x303c018c,
+    0x303c81a9,
+    0x303d01b7,
+    0x303d81cb,
+    0x303e01db,
+    0x303e81f4,
+    0x303f0204,
+    0x303f8217,
+    0x30400226,
+    0x30408232,
+    0x30410247,
+    0x30418257,
+    0x3042026e,
+    0x3042827b,
+    0x3043028e,
+    0x3043829d,
+    0x304402b2,
+    0x304482d3,
+    0x304502e6,
+    0x304582f9,
+    0x30460312,
+    0x3046832d,
+    0x3047034a,
+    0x30478363,
+    0x30480371,
+    0x30488382,
+    0x30490391,
+    0x304983a9,
+    0x304a03bb,
+    0x304a83cf,
+    0x304b03ee,
+    0x304b8401,
+    0x304c040c,
+    0x304c841d,
+    0x304d0429,
+    0x304d843f,
+    0x304e044d,
+    0x304e8463,
+    0x304f0475,
+    0x304f8487,
+    0x3050049a,
+    0x305084ad,
+    0x305104be,
+    0x305184ce,
+    0x305204e6,
+    0x305284fb,
+    0x30530513,
+    0x30538527,
+    0x3054053f,
+    0x30548558,
+    0x30550571,
+    0x3055858e,
+    0x30560599,
+    0x305685b1,
+    0x305705c1,
+    0x305785d2,
+    0x305805e5,
+    0x305885fb,
+    0x30590604,
+    0x30598619,
+    0x305a062c,
+    0x305a863b,
+    0x305b065b,
+    0x305b866a,
+    0x305c068b,
+    0x305c86a7,
+    0x305d06b3,
+    0x305d86d3,
+    0x305e06ef,
+    0x305e8700,
+    0x305f0716,
+    0x305f8720,
+    0x34320b47,
+    0x34328b5b,
+    0x34330b78,
+    0x34338b8b,
+    0x34340b9a,
+    0x34348bb7,
     0x3c320083,
-    0x3c328bd8,
-    0x3c330bf1,
-    0x3c338c0c,
-    0x3c340c29,
-    0x3c348c44,
-    0x3c350c5f,
-    0x3c358c74,
-    0x3c360c8d,
-    0x3c368ca5,
-    0x3c370cb6,
-    0x3c378cc4,
-    0x3c380cd1,
-    0x3c388ce5,
-    0x3c390b9b,
-    0x3c398cf9,
-    0x3c3a0d0d,
-    0x3c3a8881,
-    0x3c3b0d1d,
-    0x3c3b8d38,
-    0x3c3c0d4a,
-    0x3c3c8d60,
-    0x3c3d0d6a,
-    0x3c3d8d7e,
-    0x3c3e0d8c,
-    0x3c3e8db1,
-    0x3c3f0bc4,
-    0x3c3f8d9a,
-    0x403217d3,
-    0x403297e9,
-    0x40331817,
-    0x40339821,
-    0x40341838,
-    0x40349856,
-    0x40351866,
-    0x40359878,
-    0x40361885,
-    0x40369891,
-    0x403718a6,
-    0x403798bb,
-    0x403818cd,
-    0x403898d8,
-    0x403918ea,
-    0x40398de1,
-    0x403a18fa,
-    0x403a990d,
-    0x403b192e,
-    0x403b993f,
-    0x403c194f,
-    0x403c8064,
-    0x403d195b,
-    0x403d9977,
-    0x403e198d,
-    0x403e999c,
-    0x403f19af,
-    0x403f99c9,
-    0x404019d7,
-    0x404099ec,
-    0x40411a00,
-    0x40419a1d,
-    0x40421a36,
-    0x40429a51,
-    0x40431a6a,
-    0x40439a7d,
-    0x40441a91,
-    0x40449aa9,
-    0x40451ab9,
-    0x40459ac7,
-    0x40461ae5,
-    0x40468094,
-    0x40471afa,
-    0x40479b0c,
-    0x40481b30,
-    0x40489b50,
-    0x40491b64,
-    0x40499b79,
-    0x404a1b92,
-    0x404a9bcc,
-    0x404b1be6,
-    0x404b9c04,
-    0x404c1c1f,
-    0x404c9c39,
-    0x404d1c50,
-    0x404d9c78,
-    0x404e1c8f,
-    0x404e9cab,
-    0x404f1cc7,
-    0x404f9ce8,
-    0x40501d0a,
-    0x40509d26,
-    0x40511d3a,
-    0x40519d47,
-    0x40521d5e,
-    0x40529d6e,
-    0x40531d7e,
-    0x40539d92,
-    0x40541dad,
-    0x40549dbd,
-    0x40551dd4,
-    0x40559de3,
-    0x40561dfe,
-    0x40569e16,
-    0x40571e32,
-    0x40579e4b,
-    0x40581e5e,
-    0x40589e73,
-    0x40591e96,
-    0x40599ea4,
-    0x405a1eb1,
-    0x405a9eca,
-    0x405b1ee2,
-    0x405b9ef5,
-    0x405c1f0a,
-    0x405c9f1c,
-    0x405d1f31,
-    0x405d9f41,
-    0x405e1f5a,
-    0x405e9f6e,
-    0x405f1f7e,
-    0x405f9f96,
-    0x40601fa7,
-    0x40609fba,
-    0x40611fcb,
-    0x40619fe9,
-    0x40621ffa,
-    0x4062a007,
-    0x4063201e,
-    0x4063a05f,
-    0x40642076,
-    0x4064a083,
-    0x40652091,
-    0x4065a0b3,
-    0x406620db,
-    0x4066a0f0,
-    0x40672107,
-    0x4067a118,
-    0x40682129,
-    0x4068a13a,
-    0x4069214f,
-    0x4069a166,
-    0x406a2177,
-    0x406aa190,
-    0x406b21ab,
-    0x406ba1c2,
-    0x406c222f,
-    0x406ca250,
-    0x406d2263,
-    0x406da284,
-    0x406e229f,
-    0x406ea2e8,
-    0x406f2309,
-    0x406fa32f,
-    0x4070234f,
-    0x4070a36b,
-    0x407124f8,
-    0x4071a51b,
-    0x40722531,
-    0x4072a550,
-    0x40732568,
-    0x4073a588,
-    0x407427b2,
-    0x4074a7d7,
-    0x407527f2,
-    0x4075a811,
-    0x40762840,
-    0x4076a868,
-    0x40772899,
-    0x4077a8b8,
-    0x407828f2,
-    0x4078a909,
-    0x4079291c,
-    0x4079a939,
-    0x407a0782,
-    0x407aa94b,
-    0x407b295e,
-    0x407ba977,
-    0x407c298f,
-    0x407c90bd,
-    0x407d29a3,
-    0x407da9bd,
-    0x407e29ce,
-    0x407ea9e2,
-    0x407f29f0,
-    0x407faa0b,
-    0x40801286,
-    0x4080aa30,
-    0x40812a52,
-    0x4081aa6d,
-    0x40822a82,
-    0x4082aa9a,
-    0x40832ab2,
-    0x4083aac9,
-    0x40842adf,
-    0x4084aaeb,
-    0x40852afe,
-    0x4085ab13,
-    0x40862b25,
-    0x4086ab3a,
-    0x40872b43,
-    0x40879c66,
-    0x40880083,
-    0x4088a03e,
-    0x40890a17,
-    0x4089a1da,
-    0x408a1bb5,
-    0x408aa204,
-    0x408b2881,
-    0x408ba8dd,
-    0x408c22ba,
-    0x41f42423,
-    0x41f924b5,
-    0x41fe23a8,
-    0x41fea5d9,
-    0x41ff26ca,
-    0x4203243c,
-    0x4208245e,
-    0x4208a49a,
-    0x4209238c,
-    0x4209a4d4,
-    0x420a23e3,
-    0x420aa3c3,
-    0x420b2403,
-    0x420ba47c,
-    0x420c26e6,
-    0x420ca5a6,
-    0x420d25c0,
-    0x420da5f7,
-    0x42122611,
-    0x421726ad,
-    0x4217a653,
-    0x421c2675,
-    0x421f2630,
-    0x422126fd,
-    0x42262690,
-    0x422b2796,
-    0x422ba75f,
-    0x422c277e,
-    0x422ca739,
-    0x422d2718,
-    0x443206ad,
-    0x443286bc,
-    0x443306c8,
-    0x443386d6,
-    0x443406e9,
-    0x443486fa,
-    0x44350701,
-    0x4435870b,
-    0x4436071e,
-    0x44368734,
-    0x44370746,
-    0x44378753,
-    0x44380762,
-    0x4438876a,
-    0x44390782,
-    0x44398790,
-    0x443a07a3,
-    0x4c3212b0,
-    0x4c3292c0,
-    0x4c3312d3,
-    0x4c3392f3,
-    0x4c340094,
-    0x4c3480b0,
-    0x4c3512ff,
-    0x4c35930d,
-    0x4c361329,
-    0x4c36933c,
-    0x4c37134b,
-    0x4c379359,
-    0x4c38136e,
-    0x4c38937a,
-    0x4c39139a,
-    0x4c3993c4,
-    0x4c3a13dd,
-    0x4c3a93f6,
-    0x4c3b05d0,
-    0x4c3b940f,
-    0x4c3c1421,
-    0x4c3c9430,
-    0x4c3d10bd,
-    0x4c3d9449,
-    0x4c3e1456,
-    0x50322dd9,
-    0x5032ade8,
-    0x50332df3,
-    0x5033ae03,
-    0x50342e1c,
-    0x5034ae36,
-    0x50352e44,
-    0x5035ae5a,
-    0x50362e6c,
-    0x5036ae82,
-    0x50372e9b,
-    0x5037aeae,
-    0x50382ec6,
-    0x5038aed7,
-    0x50392eec,
-    0x5039af00,
-    0x503a2f20,
-    0x503aaf36,
-    0x503b2f4e,
-    0x503baf60,
-    0x503c2f7c,
-    0x503caf93,
-    0x503d2fac,
-    0x503dafc2,
-    0x503e2fcf,
-    0x503eafe5,
-    0x503f2ff7,
-    0x503f8348,
-    0x5040300a,
-    0x5040b01a,
-    0x50413034,
-    0x5041b043,
-    0x5042305d,
-    0x5042b07a,
-    0x5043308a,
-    0x5043b09a,
-    0x504430a9,
-    0x50448414,
-    0x504530bd,
-    0x5045b0db,
-    0x504630ee,
-    0x5046b104,
-    0x50473116,
-    0x5047b12b,
-    0x50483151,
-    0x5048b15f,
-    0x50493172,
-    0x5049b187,
-    0x504a319d,
-    0x504ab1ad,
-    0x504b31cd,
-    0x504bb1e0,
-    0x504c3203,
-    0x504cb231,
-    0x504d3243,
-    0x504db260,
-    0x504e327b,
-    0x504eb297,
-    0x504f32a9,
-    0x504fb2c0,
-    0x505032cf,
-    0x50508687,
-    0x505132e2,
-    0x58320e1f,
-    0x68320de1,
-    0x68328b9b,
-    0x68330bae,
-    0x68338def,
-    0x68340dff,
-    0x683480b0,
-    0x6c320dbd,
-    0x6c328b7e,
-    0x6c330dc8,
-    0x7432098d,
-    0x783208f2,
-    0x78328907,
-    0x78330913,
+    0x3c328c62,
+    0x3c330c7b,
+    0x3c338c96,
+    0x3c340cb3,
+    0x3c348cdd,
+    0x3c350cf8,
+    0x3c358d0d,
+    0x3c360d26,
+    0x3c368d3e,
+    0x3c370d4f,
+    0x3c378d5d,
+    0x3c380d6a,
+    0x3c388d7e,
+    0x3c390c25,
+    0x3c398d92,
+    0x3c3a0da6,
+    0x3c3a88ff,
+    0x3c3b0db6,
+    0x3c3b8dd1,
+    0x3c3c0de3,
+    0x3c3c8df9,
+    0x3c3d0e03,
+    0x3c3d8e17,
+    0x3c3e0e25,
+    0x3c3e8e4a,
+    0x3c3f0c4e,
+    0x3c3f8e33,
+    0x3c4000ac,
+    0x3c4080ea,
+    0x3c410cce,
+    0x403216e9,
+    0x403296ff,
+    0x4033172d,
+    0x40339737,
+    0x4034174e,
+    0x4034976c,
+    0x4035177c,
+    0x4035978e,
+    0x4036179b,
+    0x403697a7,
+    0x403717bc,
+    0x403797ce,
+    0x403817d9,
+    0x403897eb,
+    0x40390e7a,
+    0x403997fb,
+    0x403a180e,
+    0x403a982f,
+    0x403b1840,
+    0x403b9850,
+    0x403c0064,
+    0x403c8083,
+    0x403d185c,
+    0x403d9872,
+    0x403e1881,
+    0x403e9894,
+    0x403f18ae,
+    0x403f98bc,
+    0x404018d1,
+    0x404098e5,
+    0x40411902,
+    0x4041991d,
+    0x40421936,
+    0x40429949,
+    0x4043195d,
+    0x40439975,
+    0x4044198c,
+    0x404480ac,
+    0x404519a1,
+    0x404599b3,
+    0x404619d7,
+    0x404699f7,
+    0x40471a05,
+    0x40479a19,
+    0x40481a2e,
+    0x40489a47,
+    0x40491a5e,
+    0x40499a78,
+    0x404a1a8f,
+    0x404a9aad,
+    0x404b1ac5,
+    0x404b9adc,
+    0x404c1af2,
+    0x404c9b04,
+    0x404d1b25,
+    0x404d9b47,
+    0x404e1b5b,
+    0x404e9b68,
+    0x404f1b7f,
+    0x404f9b8f,
+    0x40501b9f,
+    0x40509bb3,
+    0x40511bce,
+    0x40519bde,
+    0x40521bf5,
+    0x40529c07,
+    0x40531c1f,
+    0x40539c32,
+    0x40541c47,
+    0x40549c6a,
+    0x40551c78,
+    0x40559c95,
+    0x40561ca2,
+    0x40569cbb,
+    0x40571cd3,
+    0x40579ce6,
+    0x40581cfb,
+    0x40589d0d,
+    0x40591d1d,
+    0x40599d36,
+    0x405a1d4a,
+    0x405a9d5a,
+    0x405b1d72,
+    0x405b9d83,
+    0x405c1d96,
+    0x405c9da7,
+    0x405d1db4,
+    0x405d9dcb,
+    0x405e1deb,
+    0x405e8a95,
+    0x405f1e0c,
+    0x405f9e19,
+    0x40601e27,
+    0x40609e49,
+    0x40611e71,
+    0x40619e86,
+    0x40621e9d,
+    0x40629eae,
+    0x40631ebf,
+    0x40639ed4,
+    0x40641eeb,
+    0x40649efc,
+    0x40651f17,
+    0x40659f2e,
+    0x40661f46,
+    0x40669f70,
+    0x40671f9b,
+    0x40679fbc,
+    0x40681fcf,
+    0x40689ff0,
+    0x40692022,
+    0x4069a050,
+    0x406a2071,
+    0x406aa091,
+    0x406b2219,
+    0x406ba23c,
+    0x406c2252,
+    0x406ca47e,
+    0x406d24ad,
+    0x406da4d5,
+    0x406e24ee,
+    0x406ea506,
+    0x406f2525,
+    0x406fa53a,
+    0x4070254d,
+    0x4070a56a,
+    0x40710800,
+    0x4071a57c,
+    0x4072258f,
+    0x4072a5a8,
+    0x407325c0,
+    0x4073935c,
+    0x407425d4,
+    0x4074a5ee,
+    0x407525ff,
+    0x4075a613,
+    0x40762621,
+    0x40769199,
+    0x40772646,
+    0x4077a668,
+    0x40782683,
+    0x4078a698,
+    0x407926af,
+    0x4079a6c5,
+    0x407a26d1,
+    0x407aa6e4,
+    0x407b26f9,
+    0x407ba70b,
+    0x407c2720,
+    0x407ca729,
+    0x407d200b,
+    0x41f42144,
+    0x41f921d6,
+    0x41fe20c9,
+    0x41fea2a5,
+    0x41ff2396,
+    0x4203215d,
+    0x4208217f,
+    0x4208a1bb,
+    0x420920ad,
+    0x4209a1f5,
+    0x420a2104,
+    0x420aa0e4,
+    0x420b2124,
+    0x420ba19d,
+    0x420c23b2,
+    0x420ca272,
+    0x420d228c,
+    0x420da2c3,
+    0x421222dd,
+    0x42172379,
+    0x4217a31f,
+    0x421c2341,
+    0x421f22fc,
+    0x422123c9,
+    0x4226235c,
+    0x422b2462,
+    0x422ba42b,
+    0x422c244a,
+    0x422ca405,
+    0x422d23e4,
+    0x4432072b,
+    0x4432873a,
+    0x44330746,
+    0x44338754,
+    0x44340767,
+    0x44348778,
+    0x4435077f,
+    0x44358789,
+    0x4436079c,
+    0x443687b2,
+    0x443707c4,
+    0x443787d1,
+    0x443807e0,
+    0x443887e8,
+    0x44390800,
+    0x4439880e,
+    0x443a0821,
+    0x4c3211c3,
+    0x4c3291d3,
+    0x4c3311e6,
+    0x4c339206,
+    0x4c3400ac,
+    0x4c3480ea,
+    0x4c351212,
+    0x4c359220,
+    0x4c36123c,
+    0x4c36924f,
+    0x4c37125e,
+    0x4c37926c,
+    0x4c381281,
+    0x4c38928d,
+    0x4c3912ad,
+    0x4c3992d7,
+    0x4c3a12f0,
+    0x4c3a9309,
+    0x4c3b05fb,
+    0x4c3b9322,
+    0x4c3c1334,
+    0x4c3c9343,
+    0x4c3d135c,
+    0x4c3d936b,
+    0x4c3e1378,
+    0x503229a2,
+    0x5032a9b1,
+    0x503329bc,
+    0x5033a9cc,
+    0x503429e5,
+    0x5034a9ff,
+    0x50352a0d,
+    0x5035aa23,
+    0x50362a35,
+    0x5036aa4b,
+    0x50372a64,
+    0x5037aa77,
+    0x50382a8f,
+    0x5038aaa0,
+    0x50392ab5,
+    0x5039aac9,
+    0x503a2ae9,
+    0x503aaaff,
+    0x503b2b17,
+    0x503bab29,
+    0x503c2b45,
+    0x503cab5c,
+    0x503d2b75,
+    0x503dab8b,
+    0x503e2b98,
+    0x503eabae,
+    0x503f2bc0,
+    0x503f8382,
+    0x50402bd3,
+    0x5040abe3,
+    0x50412bfd,
+    0x5041ac0c,
+    0x50422c26,
+    0x5042ac43,
+    0x50432c53,
+    0x5043ac63,
+    0x50442c72,
+    0x5044843f,
+    0x50452c86,
+    0x5045aca4,
+    0x50462cb7,
+    0x5046accd,
+    0x50472cdf,
+    0x5047acf4,
+    0x50482d1a,
+    0x5048ad28,
+    0x50492d3b,
+    0x5049ad50,
+    0x504a2d66,
+    0x504aad76,
+    0x504b2d96,
+    0x504bada9,
+    0x504c2dcc,
+    0x504cadfa,
+    0x504d2e0c,
+    0x504dae29,
+    0x504e2e44,
+    0x504eae60,
+    0x504f2e72,
+    0x504fae89,
+    0x50502e98,
+    0x505086ef,
+    0x50512eab,
+    0x58320eb8,
+    0x68320e7a,
+    0x68328c25,
+    0x68330c38,
+    0x68338e88,
+    0x68340e98,
+    0x683480ea,
+    0x6c320e56,
+    0x6c328bfc,
+    0x6c330e61,
+    0x74320a0b,
+    0x78320970,
+    0x78328985,
+    0x78330991,
     0x78338083,
-    0x78340922,
-    0x78348937,
-    0x78350956,
-    0x78358978,
-    0x7836098d,
-    0x783689a3,
-    0x783709b3,
-    0x783789c6,
-    0x783809d9,
-    0x783889eb,
-    0x783909f8,
-    0x78398a17,
-    0x783a0a2c,
-    0x783a8a3a,
-    0x783b0a44,
-    0x783b8a58,
-    0x783c0a6f,
-    0x783c8a84,
-    0x783d0a9b,
-    0x783d8ab0,
-    0x783e0a06,
-    0x7c3211b2,
+    0x783409a0,
+    0x783489b5,
+    0x783509d4,
+    0x783589f6,
+    0x78360a0b,
+    0x78368a21,
+    0x78370a31,
+    0x78378a44,
+    0x78380a57,
+    0x78388a69,
+    0x78390a76,
+    0x78398a95,
+    0x783a0aaa,
+    0x783a8ab8,
+    0x783b0ac2,
+    0x783b8ad6,
+    0x783c0aed,
+    0x783c8b02,
+    0x783d0b19,
+    0x783d8b2e,
+    0x783e0a84,
+    0x7c3210c5,
 };
 
 const size_t kOpenSSLReasonValuesLen = sizeof(kOpenSSLReasonValues) / sizeof(kOpenSSLReasonValues[0]);
@@ -714,8 +679,10 @@ const char kOpenSSLReasonStringData[] =
     "BN_LIB\0"
     "BOOLEAN_IS_WRONG_LENGTH\0"
     "BUFFER_TOO_SMALL\0"
+    "CONTEXT_NOT_INITIALISED\0"
     "DECODE_ERROR\0"
     "DEPTH_EXCEEDED\0"
+    "DIGEST_AND_KEY_TYPE_NOT_SUPPORTED\0"
     "ENCODE_ERROR\0"
     "ERROR_GETTING_TIME\0"
     "EXPECTING_AN_ASN1_SEQUENCE\0"
@@ -756,7 +723,6 @@ const char kOpenSSLReasonStringData[] =
     "INVALID_UNIVERSALSTRING_LENGTH\0"
     "INVALID_UTF8STRING\0"
     "LIST_ERROR\0"
-    "MALLOC_FAILURE\0"
     "MISSING_ASN1_EOS\0"
     "MISSING_EOC\0"
     "MISSING_SECOND_NUMBER\0"
@@ -788,10 +754,13 @@ const char kOpenSSLReasonStringData[] =
     "UNEXPECTED_EOC\0"
     "UNIVERSALSTRING_IS_WRONG_LENGTH\0"
     "UNKNOWN_FORMAT\0"
+    "UNKNOWN_MESSAGE_DIGEST_ALGORITHM\0"
+    "UNKNOWN_SIGNATURE_ALGORITHM\0"
     "UNKNOWN_TAG\0"
     "UNSUPPORTED_ANY_DEFINED_BY_TYPE\0"
     "UNSUPPORTED_PUBLIC_KEY_TYPE\0"
     "UNSUPPORTED_TYPE\0"
+    "WRONG_PUBLIC_KEY_TYPE\0"
     "WRONG_TAG\0"
     "WRONG_TYPE\0"
     "BAD_FOPEN_MODE\0"
@@ -864,6 +833,7 @@ const char kOpenSSLReasonStringData[] =
     "MODULUS_TOO_LARGE\0"
     "NO_PRIVATE_VALUE\0"
     "BAD_Q_VALUE\0"
+    "BAD_VERSION\0"
     "MISSING_PARAMETERS\0"
     "NEED_NEW_SETUP_VALUES\0"
     "BIGNUM_OUT_OF_RANGE\0"
@@ -871,6 +841,7 @@ const char kOpenSSLReasonStringData[] =
     "D2I_ECPKPARAMETERS_FAILURE\0"
     "EC_GROUP_NEW_BY_NAME_FAILURE\0"
     "GROUP2PKPARAMETERS_FAILURE\0"
+    "GROUP_MISMATCH\0"
     "I2D_ECPKPARAMETERS_FAILURE\0"
     "INCOMPATIBLE_OBJECTS\0"
     "INVALID_COMPRESSED_POINT\0"
@@ -897,27 +868,19 @@ const char kOpenSSLReasonStringData[] =
     "NOT_IMPLEMENTED\0"
     "RANDOM_NUMBER_GENERATION_FAILED\0"
     "OPERATION_NOT_SUPPORTED\0"
-    "BN_DECODE_ERROR\0"
     "COMMAND_NOT_SUPPORTED\0"
-    "CONTEXT_NOT_INITIALISED\0"
     "DIFFERENT_KEY_TYPES\0"
     "DIFFERENT_PARAMETERS\0"
-    "DIGEST_AND_KEY_TYPE_NOT_SUPPORTED\0"
     "EXPECTING_AN_EC_KEY_KEY\0"
     "EXPECTING_AN_RSA_KEY\0"
-    "EXPECTING_A_DH_KEY\0"
     "EXPECTING_A_DSA_KEY\0"
     "ILLEGAL_OR_UNSUPPORTED_PADDING_MODE\0"
-    "INVALID_CURVE\0"
     "INVALID_DIGEST_LENGTH\0"
     "INVALID_DIGEST_TYPE\0"
     "INVALID_KEYBITS\0"
     "INVALID_MGF1_MD\0"
     "INVALID_PADDING_MODE\0"
-    "INVALID_PSS_PARAMETERS\0"
     "INVALID_PSS_SALTLEN\0"
-    "INVALID_SALT_LENGTH\0"
-    "INVALID_TRAILER\0"
     "KEYS_NOT_SET\0"
     "NO_DEFAULT_DIGEST\0"
     "NO_KEY_SET\0"
@@ -927,17 +890,8 @@ const char kOpenSSLReasonStringData[] =
     "NO_PARAMETERS_SET\0"
     "OPERATION_NOT_SUPPORTED_FOR_THIS_KEYTYPE\0"
     "OPERATON_NOT_INITIALIZED\0"
-    "PARAMETER_ENCODING_ERROR\0"
-    "UNKNOWN_DIGEST\0"
-    "UNKNOWN_MASK_DIGEST\0"
-    "UNKNOWN_MESSAGE_DIGEST_ALGORITHM\0"
     "UNKNOWN_PUBLIC_KEY_TYPE\0"
-    "UNKNOWN_SIGNATURE_ALGORITHM\0"
     "UNSUPPORTED_ALGORITHM\0"
-    "UNSUPPORTED_MASK_ALGORITHM\0"
-    "UNSUPPORTED_MASK_PARAMETER\0"
-    "UNSUPPORTED_SIGNATURE_TYPE\0"
-    "WRONG_PUBLIC_KEY_TYPE\0"
     "OUTPUT_TOO_LARGE\0"
     "UNKNOWN_NID\0"
     "BAD_BASE64_DECODE\0"
@@ -973,13 +927,13 @@ const char kOpenSSLReasonStringData[] =
     "UNKNOWN_ALGORITHM\0"
     "UNKNOWN_CIPHER\0"
     "UNKNOWN_CIPHER_ALGORITHM\0"
+    "UNKNOWN_DIGEST\0"
     "UNKNOWN_HASH\0"
     "UNSUPPORTED_PRIVATE_KEY_ALGORITHM\0"
     "BAD_E_VALUE\0"
     "BAD_FIXED_HEADER_DECRYPT\0"
     "BAD_PAD_BYTE_COUNT\0"
     "BAD_RSA_PARAMETERS\0"
-    "BAD_VERSION\0"
     "BLOCK_TYPE_IS_NOT_01\0"
     "BN_NOT_INITIALIZED\0"
     "CANNOT_RECOVER_MULTI_PRIME_KEY\0"
@@ -1024,7 +978,6 @@ const char kOpenSSLReasonStringData[] =
     "BAD_DIGEST_LENGTH\0"
     "BAD_ECC_CERT\0"
     "BAD_ECPOINT\0"
-    "BAD_HANDSHAKE_LENGTH\0"
     "BAD_HANDSHAKE_RECORD\0"
     "BAD_HELLO_REQUEST\0"
     "BAD_LENGTH\0"
@@ -1035,7 +988,6 @@ const char kOpenSSLReasonStringData[] =
     "BAD_SSL_FILETYPE\0"
     "BAD_WRITE_RETRY\0"
     "BIO_NOT_SET\0"
-    "CANNOT_SERIALIZE_PUBLIC_KEY\0"
     "CA_DN_LENGTH_MISMATCH\0"
     "CA_DN_TOO_LONG\0"
     "CCS_RECEIVED_EARLY\0"
@@ -1044,37 +996,30 @@ const char kOpenSSLReasonStringData[] =
     "CERT_LENGTH_MISMATCH\0"
     "CHANNEL_ID_NOT_P256\0"
     "CHANNEL_ID_SIGNATURE_INVALID\0"
-    "CIPHER_CODE_WRONG_LENGTH\0"
     "CIPHER_OR_HASH_UNAVAILABLE\0"
     "CLIENTHELLO_PARSE_FAILED\0"
     "CLIENTHELLO_TLSEXT\0"
     "CONNECTION_REJECTED\0"
     "CONNECTION_TYPE_NOT_SET\0"
-    "COOKIE_MISMATCH\0"
-    "D2I_ECDSA_SIG\0"
-    "DATA_BETWEEN_CCS_AND_FINISHED\0"
+    "CUSTOM_EXTENSION_ERROR\0"
     "DATA_LENGTH_TOO_LONG\0"
     "DECRYPTION_FAILED\0"
     "DECRYPTION_FAILED_OR_BAD_RECORD_MAC\0"
     "DH_PUBLIC_VALUE_LENGTH_IS_WRONG\0"
+    "DH_P_TOO_LONG\0"
     "DIGEST_CHECK_FAILED\0"
     "DTLS_MESSAGE_TOO_BIG\0"
     "ECC_CERT_NOT_FOR_SIGNING\0"
-    "EMPTY_SRTP_PROTECTION_PROFILE_LIST\0"
     "EMS_STATE_INCONSISTENT\0"
     "ENCRYPTED_LENGTH_TOO_LONG\0"
+    "ERROR_ADDING_EXTENSION\0"
     "ERROR_IN_RECEIVED_CIPHER_LIST\0"
-    "EVP_DIGESTSIGNFINAL_FAILED\0"
-    "EVP_DIGESTSIGNINIT_FAILED\0"
+    "ERROR_PARSING_EXTENSION\0"
     "EXCESSIVE_MESSAGE_SIZE\0"
     "EXTRA_DATA_IN_MESSAGE\0"
     "FRAGMENT_MISMATCH\0"
-    "GOT_A_FIN_BEFORE_A_CCS\0"
-    "GOT_CHANNEL_ID_BEFORE_A_CCS\0"
-    "GOT_NEXT_PROTO_BEFORE_A_CCS\0"
     "GOT_NEXT_PROTO_WITHOUT_EXTENSION\0"
     "HANDSHAKE_FAILURE_ON_CLIENT_HELLO\0"
-    "HANDSHAKE_RECORD_BEFORE_CCS\0"
     "HTTPS_PROXY_REQUEST\0"
     "HTTP_REQUEST\0"
     "INAPPROPRIATE_FALLBACK\0"
@@ -1084,22 +1029,19 @@ const char kOpenSSLReasonStringData[] =
     "INVALID_TICKET_KEYS_LENGTH\0"
     "LENGTH_MISMATCH\0"
     "LIBRARY_HAS_NO_CIPHERS\0"
-    "MISSING_DH_KEY\0"
-    "MISSING_ECDSA_SIGNING_CERT\0"
+    "MISSING_EXTENSION\0"
     "MISSING_RSA_CERTIFICATE\0"
-    "MISSING_RSA_ENCRYPTING_CERT\0"
-    "MISSING_RSA_SIGNING_CERT\0"
     "MISSING_TMP_DH_KEY\0"
     "MISSING_TMP_ECDH_KEY\0"
     "MIXED_SPECIAL_OPERATOR_WITH_GROUPS\0"
     "MTU_TOO_SMALL\0"
+    "NEGOTIATED_BOTH_NPN_AND_ALPN\0"
     "NESTED_GROUP\0"
     "NO_CERTIFICATES_RETURNED\0"
     "NO_CERTIFICATE_ASSIGNED\0"
     "NO_CERTIFICATE_SET\0"
     "NO_CIPHERS_AVAILABLE\0"
     "NO_CIPHERS_PASSED\0"
-    "NO_CIPHERS_SPECIFIED\0"
     "NO_CIPHER_MATCH\0"
     "NO_COMPRESSION_SPECIFIED\0"
     "NO_METHOD_SPECIFIED\0"
@@ -1108,13 +1050,10 @@ const char kOpenSSLReasonStringData[] =
     "NO_RENEGOTIATION\0"
     "NO_REQUIRED_DIGEST\0"
     "NO_SHARED_CIPHER\0"
-    "NO_SHARED_SIGATURE_ALGORITHMS\0"
-    "NO_SRTP_PROFILES\0"
     "NULL_SSL_CTX\0"
     "NULL_SSL_METHOD_PASSED\0"
     "OLD_SESSION_CIPHER_NOT_RETURNED\0"
     "OLD_SESSION_VERSION_NOT_RETURNED\0"
-    "PACKET_LENGTH_TOO_LONG\0"
     "PARSE_TLSEXT\0"
     "PATH_TOO_LONG\0"
     "PEER_DID_NOT_RETURN_A_CERTIFICATE\0"
@@ -1123,11 +1062,9 @@ const char kOpenSSLReasonStringData[] =
     "PSK_IDENTITY_NOT_FOUND\0"
     "PSK_NO_CLIENT_CB\0"
     "PSK_NO_SERVER_CB\0"
-    "READ_BIO_NOT_SET\0"
     "READ_TIMEOUT_EXPIRED\0"
     "RECORD_LENGTH_MISMATCH\0"
     "RECORD_TOO_LARGE\0"
-    "RENEGOTIATE_EXT_TOO_LONG\0"
     "RENEGOTIATION_ENCODING_ERR\0"
     "RENEGOTIATION_MISMATCH\0"
     "REQUIRED_CIPHER_MISSING\0"
@@ -1137,13 +1074,11 @@ const char kOpenSSLReasonStringData[] =
     "SERVERHELLO_TLSEXT\0"
     "SESSION_ID_CONTEXT_UNINITIALIZED\0"
     "SESSION_MAY_NOT_BE_CREATED\0"
-    "SIGNATURE_ALGORITHMS_ERROR\0"
+    "SHUTDOWN_WHILE_IN_INIT\0"
     "SIGNATURE_ALGORITHMS_EXTENSION_SENT_BY_SERVER\0"
     "SRTP_COULD_NOT_ALLOCATE_PROFILES\0"
-    "SRTP_PROTECTION_PROFILE_LIST_TOO_LONG\0"
     "SRTP_UNKNOWN_PROTECTION_PROFILE\0"
     "SSL3_EXT_INVALID_SERVERNAME\0"
-    "SSL3_EXT_INVALID_SERVERNAME_TYPE\0"
     "SSLV3_ALERT_BAD_CERTIFICATE\0"
     "SSLV3_ALERT_BAD_RECORD_MAC\0"
     "SSLV3_ALERT_CERTIFICATE_EXPIRED\0"
@@ -1158,10 +1093,7 @@ const char kOpenSSLReasonStringData[] =
     "SSLV3_ALERT_UNSUPPORTED_CERTIFICATE\0"
     "SSL_CTX_HAS_NO_DEFAULT_SSL_VERSION\0"
     "SSL_HANDSHAKE_FAILURE\0"
-    "SSL_SESSION_ID_CALLBACK_FAILED\0"
-    "SSL_SESSION_ID_CONFLICT\0"
     "SSL_SESSION_ID_CONTEXT_TOO_LONG\0"
-    "SSL_SESSION_ID_HAS_BAD_LENGTH\0"
     "TLSV1_ALERT_ACCESS_DENIED\0"
     "TLSV1_ALERT_DECODE_ERROR\0"
     "TLSV1_ALERT_DECRYPTION_FAILED\0"
@@ -1180,17 +1112,12 @@ const char kOpenSSLReasonStringData[] =
     "TLSV1_CERTIFICATE_UNOBTAINABLE\0"
     "TLSV1_UNRECOGNIZED_NAME\0"
     "TLSV1_UNSUPPORTED_EXTENSION\0"
-    "TLS_CLIENT_CERT_REQ_WITH_ANON_CIPHER\0"
-    "TLS_ILLEGAL_EXPORTER_LABEL\0"
-    "TLS_INVALID_ECPOINTFORMAT_LIST\0"
     "TLS_PEER_DID_NOT_RESPOND_WITH_CERTIFICATE_LIST\0"
     "TLS_RSA_ENCRYPTED_VALUE_LENGTH_IS_WRONG\0"
     "TOO_MANY_EMPTY_FRAGMENTS\0"
     "TOO_MANY_WARNING_ALERTS\0"
     "UNABLE_TO_FIND_ECDH_PARAMETERS\0"
-    "UNABLE_TO_FIND_PUBLIC_KEY_PARAMETERS\0"
     "UNEXPECTED_EXTENSION\0"
-    "UNEXPECTED_GROUP_CLOSE\0"
     "UNEXPECTED_MESSAGE\0"
     "UNEXPECTED_OPERATOR_IN_GROUP\0"
     "UNEXPECTED_RECORD\0"
@@ -1202,13 +1129,10 @@ const char kOpenSSLReasonStringData[] =
     "UNKNOWN_PROTOCOL\0"
     "UNKNOWN_SSL_VERSION\0"
     "UNKNOWN_STATE\0"
-    "UNPROCESSED_HANDSHAKE_DATA\0"
     "UNSAFE_LEGACY_RENEGOTIATION_DISABLED\0"
     "UNSUPPORTED_COMPRESSION_ALGORITHM\0"
     "UNSUPPORTED_ELLIPTIC_CURVE\0"
     "UNSUPPORTED_PROTOCOL\0"
-    "UNSUPPORTED_SSL_VERSION\0"
-    "USE_SRTP_NOT_NEGOTIATED\0"
     "WRONG_CERTIFICATE_TYPE\0"
     "WRONG_CIPHER_RETURNED\0"
     "WRONG_CURVE\0"
@@ -1229,12 +1153,14 @@ const char kOpenSSLReasonStringData[] =
     "IDP_MISMATCH\0"
     "INVALID_DIRECTORY\0"
     "INVALID_FIELD_NAME\0"
+    "INVALID_PSS_PARAMETERS\0"
     "INVALID_TRUST\0"
     "ISSUER_MISMATCH\0"
     "KEY_TYPE_MISMATCH\0"
     "KEY_VALUES_MISMATCH\0"
     "LOADING_CERT_DIR\0"
     "LOADING_DEFAULTS\0"
+    "NAME_TOO_LONG\0"
     "NEWER_CRL_NOT_NEWER\0"
     "NOT_PKCS7_SIGNED_DATA\0"
     "NO_CERTIFICATES_INCLUDED\0"
@@ -1244,8 +1170,6 @@ const char kOpenSSLReasonStringData[] =
     "PUBLIC_KEY_DECODE_ERROR\0"
     "PUBLIC_KEY_ENCODE_ERROR\0"
     "SHOULD_RETRY\0"
-    "UNABLE_TO_FIND_PARAMETERS_IN_CHAIN\0"
-    "UNABLE_TO_GET_CERTS_PUBLIC_KEY\0"
     "UNKNOWN_KEY_TYPE\0"
     "UNKNOWN_PURPOSE_ID\0"
     "UNKNOWN_TRUST_ID\0"
diff --git a/packager/third_party/boringssl/linux-aarch64/crypto/aes/aesv8-armx64.S b/packager/third_party/boringssl/linux-aarch64/crypto/aes/aesv8-armx64.S
index c414476cdf..3e8cb16e01 100644
--- a/packager/third_party/boringssl/linux-aarch64/crypto/aes/aesv8-armx64.S
+++ b/packager/third_party/boringssl/linux-aarch64/crypto/aes/aesv8-armx64.S
@@ -1,5 +1,5 @@
 #if defined(__aarch64__)
-#include "arm_arch.h"
+#include <openssl/arm_arch.h>
 
 #if __ARM_MAX_ARCH__>=7
 .text
@@ -13,6 +13,7 @@
 .long	0x1b,0x1b,0x1b,0x1b
 
 .globl	aes_v8_set_encrypt_key
+.hidden	aes_v8_set_encrypt_key
 .type	aes_v8_set_encrypt_key,%function
 .align	5
 aes_v8_set_encrypt_key:
@@ -180,6 +181,7 @@ aes_v8_set_encrypt_key:
 .size	aes_v8_set_encrypt_key,.-aes_v8_set_encrypt_key
 
 .globl	aes_v8_set_decrypt_key
+.hidden	aes_v8_set_decrypt_key
 .type	aes_v8_set_decrypt_key,%function
 .align	5
 aes_v8_set_decrypt_key:
@@ -219,6 +221,7 @@ aes_v8_set_decrypt_key:
 	ret
 .size	aes_v8_set_decrypt_key,.-aes_v8_set_decrypt_key
 .globl	aes_v8_encrypt
+.hidden	aes_v8_encrypt
 .type	aes_v8_encrypt,%function
 .align	5
 aes_v8_encrypt:
@@ -248,6 +251,7 @@ aes_v8_encrypt:
 	ret
 .size	aes_v8_encrypt,.-aes_v8_encrypt
 .globl	aes_v8_decrypt
+.hidden	aes_v8_decrypt
 .type	aes_v8_decrypt,%function
 .align	5
 aes_v8_decrypt:
@@ -277,6 +281,7 @@ aes_v8_decrypt:
 	ret
 .size	aes_v8_decrypt,.-aes_v8_decrypt
 .globl	aes_v8_cbc_encrypt
+.hidden	aes_v8_cbc_encrypt
 .type	aes_v8_cbc_encrypt,%function
 .align	5
 aes_v8_cbc_encrypt:
@@ -567,6 +572,7 @@ aes_v8_cbc_encrypt:
 	ret
 .size	aes_v8_cbc_encrypt,.-aes_v8_cbc_encrypt
 .globl	aes_v8_ctr32_encrypt_blocks
+.hidden	aes_v8_ctr32_encrypt_blocks
 .type	aes_v8_ctr32_encrypt_blocks,%function
 .align	5
 aes_v8_ctr32_encrypt_blocks:
@@ -748,4 +754,4 @@ aes_v8_ctr32_encrypt_blocks:
 	ret
 .size	aes_v8_ctr32_encrypt_blocks,.-aes_v8_ctr32_encrypt_blocks
 #endif
-#endif
\ No newline at end of file
+#endif
diff --git a/packager/third_party/boringssl/linux-aarch64/crypto/bn/armv8-mont.S b/packager/third_party/boringssl/linux-aarch64/crypto/bn/armv8-mont.S
new file mode 100644
index 0000000000..74702db6aa
--- /dev/null
+++ b/packager/third_party/boringssl/linux-aarch64/crypto/bn/armv8-mont.S
@@ -0,0 +1,1407 @@
+#if defined(__aarch64__)
+.text
+
+.globl	bn_mul_mont
+.hidden	bn_mul_mont
+.type	bn_mul_mont,%function
+.align	5
+bn_mul_mont:
+	tst	x5,#7
+	b.eq	__bn_sqr8x_mont
+	tst	x5,#3
+	b.eq	__bn_mul4x_mont
+.Lmul_mont:
+	stp	x29,x30,[sp,#-64]!
+	add	x29,sp,#0
+	stp	x19,x20,[sp,#16]
+	stp	x21,x22,[sp,#32]
+	stp	x23,x24,[sp,#48]
+
+	ldr	x9,[x2],#8		// bp[0]
+	sub	x22,sp,x5,lsl#3
+	ldp	x7,x8,[x1],#16	// ap[0..1]
+	lsl	x5,x5,#3
+	ldr	x4,[x4]		// *n0
+	and	x22,x22,#-16		// ABI says so
+	ldp	x13,x14,[x3],#16	// np[0..1]
+
+	mul	x6,x7,x9		// ap[0]*bp[0]
+	sub	x21,x5,#16		// j=num-2
+	umulh	x7,x7,x9
+	mul	x10,x8,x9		// ap[1]*bp[0]
+	umulh	x11,x8,x9
+
+	mul	x15,x6,x4		// "tp[0]"*n0
+	mov	sp,x22			// alloca
+
+	// (*)	mul	x12,x13,x15	// np[0]*m1
+	umulh	x13,x13,x15
+	mul	x16,x14,x15		// np[1]*m1
+	// (*)	adds	x12,x12,x6	// discarded
+	// (*)	As for removal of first multiplication and addition
+	//	instructions. The outcome of first addition is
+	//	guaranteed to be zero, which leaves two computationally
+	//	significant outcomes: it either carries or not. Then
+	//	question is when does it carry? Is there alternative
+	//	way to deduce it? If you follow operations, you can
+	//	observe that condition for carry is quite simple:
+	//	x6 being non-zero. So that carry can be calculated
+	//	by adding -1 to x6. That's what next instruction does.
+	subs	xzr,x6,#1		// (*)
+	umulh	x17,x14,x15
+	adc	x13,x13,xzr
+	cbz	x21,.L1st_skip
+
+.L1st:
+	ldr	x8,[x1],#8
+	adds	x6,x10,x7
+	sub	x21,x21,#8		// j--
+	adc	x7,x11,xzr
+
+	ldr	x14,[x3],#8
+	adds	x12,x16,x13
+	mul	x10,x8,x9		// ap[j]*bp[0]
+	adc	x13,x17,xzr
+	umulh	x11,x8,x9
+
+	adds	x12,x12,x6
+	mul	x16,x14,x15		// np[j]*m1
+	adc	x13,x13,xzr
+	umulh	x17,x14,x15
+	str	x12,[x22],#8		// tp[j-1]
+	cbnz	x21,.L1st
+
+.L1st_skip:
+	adds	x6,x10,x7
+	sub	x1,x1,x5		// rewind x1
+	adc	x7,x11,xzr
+
+	adds	x12,x16,x13
+	sub	x3,x3,x5		// rewind x3
+	adc	x13,x17,xzr
+
+	adds	x12,x12,x6
+	sub	x20,x5,#8		// i=num-1
+	adcs	x13,x13,x7
+
+	adc	x19,xzr,xzr		// upmost overflow bit
+	stp	x12,x13,[x22]
+
+.Louter:
+	ldr	x9,[x2],#8		// bp[i]
+	ldp	x7,x8,[x1],#16
+	ldr	x23,[sp]		// tp[0]
+	add	x22,sp,#8
+
+	mul	x6,x7,x9		// ap[0]*bp[i]
+	sub	x21,x5,#16		// j=num-2
+	umulh	x7,x7,x9
+	ldp	x13,x14,[x3],#16
+	mul	x10,x8,x9		// ap[1]*bp[i]
+	adds	x6,x6,x23
+	umulh	x11,x8,x9
+	adc	x7,x7,xzr
+
+	mul	x15,x6,x4
+	sub	x20,x20,#8		// i--
+
+	// (*)	mul	x12,x13,x15	// np[0]*m1
+	umulh	x13,x13,x15
+	mul	x16,x14,x15		// np[1]*m1
+	// (*)	adds	x12,x12,x6
+	subs	xzr,x6,#1		// (*)
+	umulh	x17,x14,x15
+	cbz	x21,.Linner_skip
+
+.Linner:
+	ldr	x8,[x1],#8
+	adc	x13,x13,xzr
+	ldr	x23,[x22],#8		// tp[j]
+	adds	x6,x10,x7
+	sub	x21,x21,#8		// j--
+	adc	x7,x11,xzr
+
+	adds	x12,x16,x13
+	ldr	x14,[x3],#8
+	adc	x13,x17,xzr
+
+	mul	x10,x8,x9		// ap[j]*bp[i]
+	adds	x6,x6,x23
+	umulh	x11,x8,x9
+	adc	x7,x7,xzr
+
+	mul	x16,x14,x15		// np[j]*m1
+	adds	x12,x12,x6
+	umulh	x17,x14,x15
+	str	x12,[x22,#-16]		// tp[j-1]
+	cbnz	x21,.Linner
+
+.Linner_skip:
+	ldr	x23,[x22],#8		// tp[j]
+	adc	x13,x13,xzr
+	adds	x6,x10,x7
+	sub	x1,x1,x5		// rewind x1
+	adc	x7,x11,xzr
+
+	adds	x12,x16,x13
+	sub	x3,x3,x5		// rewind x3
+	adcs	x13,x17,x19
+	adc	x19,xzr,xzr
+
+	adds	x6,x6,x23
+	adc	x7,x7,xzr
+
+	adds	x12,x12,x6
+	adcs	x13,x13,x7
+	adc	x19,x19,xzr		// upmost overflow bit
+	stp	x12,x13,[x22,#-16]
+
+	cbnz	x20,.Louter
+
+	// Final step. We see if result is larger than modulus, and
+	// if it is, subtract the modulus. But comparison implies
+	// subtraction. So we subtract modulus, see if it borrowed,
+	// and conditionally copy original value.
+	ldr	x23,[sp]		// tp[0]
+	add	x22,sp,#8
+	ldr	x14,[x3],#8		// np[0]
+	subs	x21,x5,#8		// j=num-1 and clear borrow
+	mov	x1,x0
+.Lsub:
+	sbcs	x8,x23,x14		// tp[j]-np[j]
+	ldr	x23,[x22],#8
+	sub	x21,x21,#8		// j--
+	ldr	x14,[x3],#8
+	str	x8,[x1],#8		// rp[j]=tp[j]-np[j]
+	cbnz	x21,.Lsub
+
+	sbcs	x8,x23,x14
+	sbcs	x19,x19,xzr		// did it borrow?
+	str	x8,[x1],#8		// rp[num-1]
+
+	ldr	x23,[sp]		// tp[0]
+	add	x22,sp,#8
+	ldr	x8,[x0],#8		// rp[0]
+	sub	x5,x5,#8		// num--
+	nop
+.Lcond_copy:
+	sub	x5,x5,#8		// num--
+	csel	x14,x23,x8,lo		// did it borrow?
+	ldr	x23,[x22],#8
+	ldr	x8,[x0],#8
+	str	xzr,[x22,#-16]		// wipe tp
+	str	x14,[x0,#-16]
+	cbnz	x5,.Lcond_copy
+
+	csel	x14,x23,x8,lo
+	str	xzr,[x22,#-8]		// wipe tp
+	str	x14,[x0,#-8]
+
+	ldp	x19,x20,[x29,#16]
+	mov	sp,x29
+	ldp	x21,x22,[x29,#32]
+	mov	x0,#1
+	ldp	x23,x24,[x29,#48]
+	ldr	x29,[sp],#64
+	ret
+.size	bn_mul_mont,.-bn_mul_mont
+.type	__bn_sqr8x_mont,%function
+.align	5
+__bn_sqr8x_mont:
+	cmp	x1,x2
+	b.ne	__bn_mul4x_mont
+.Lsqr8x_mont:
+	stp	x29,x30,[sp,#-128]!
+	add	x29,sp,#0
+	stp	x19,x20,[sp,#16]
+	stp	x21,x22,[sp,#32]
+	stp	x23,x24,[sp,#48]
+	stp	x25,x26,[sp,#64]
+	stp	x27,x28,[sp,#80]
+	stp	x0,x3,[sp,#96]	// offload rp and np
+
+	ldp	x6,x7,[x1,#8*0]
+	ldp	x8,x9,[x1,#8*2]
+	ldp	x10,x11,[x1,#8*4]
+	ldp	x12,x13,[x1,#8*6]
+
+	sub	x2,sp,x5,lsl#4
+	lsl	x5,x5,#3
+	ldr	x4,[x4]		// *n0
+	mov	sp,x2			// alloca
+	sub	x27,x5,#8*8
+	b	.Lsqr8x_zero_start
+
+.Lsqr8x_zero:
+	sub	x27,x27,#8*8
+	stp	xzr,xzr,[x2,#8*0]
+	stp	xzr,xzr,[x2,#8*2]
+	stp	xzr,xzr,[x2,#8*4]
+	stp	xzr,xzr,[x2,#8*6]
+.Lsqr8x_zero_start:
+	stp	xzr,xzr,[x2,#8*8]
+	stp	xzr,xzr,[x2,#8*10]
+	stp	xzr,xzr,[x2,#8*12]
+	stp	xzr,xzr,[x2,#8*14]
+	add	x2,x2,#8*16
+	cbnz	x27,.Lsqr8x_zero
+
+	add	x3,x1,x5
+	add	x1,x1,#8*8
+	mov	x19,xzr
+	mov	x20,xzr
+	mov	x21,xzr
+	mov	x22,xzr
+	mov	x23,xzr
+	mov	x24,xzr
+	mov	x25,xzr
+	mov	x26,xzr
+	mov	x2,sp
+	str	x4,[x29,#112]		// offload n0
+
+	// Multiply everything but a[i]*a[i]
+.align	4
+.Lsqr8x_outer_loop:
+        //                                                 a[1]a[0]	(i)
+        //                                             a[2]a[0]
+        //                                         a[3]a[0]
+        //                                     a[4]a[0]
+        //                                 a[5]a[0]
+        //                             a[6]a[0]
+        //                         a[7]a[0]
+        //                                         a[2]a[1]		(ii)
+        //                                     a[3]a[1]
+        //                                 a[4]a[1]
+        //                             a[5]a[1]
+        //                         a[6]a[1]
+        //                     a[7]a[1]
+        //                                 a[3]a[2]			(iii)
+        //                             a[4]a[2]
+        //                         a[5]a[2]
+        //                     a[6]a[2]
+        //                 a[7]a[2]
+        //                         a[4]a[3]				(iv)
+        //                     a[5]a[3]
+        //                 a[6]a[3]
+        //             a[7]a[3]
+        //                 a[5]a[4]					(v)
+        //             a[6]a[4]
+        //         a[7]a[4]
+        //         a[6]a[5]						(vi)
+        //     a[7]a[5]
+        // a[7]a[6]							(vii)
+
+	mul	x14,x7,x6		// lo(a[1..7]*a[0])		(i)
+	mul	x15,x8,x6
+	mul	x16,x9,x6
+	mul	x17,x10,x6
+	adds	x20,x20,x14		// t[1]+lo(a[1]*a[0])
+	mul	x14,x11,x6
+	adcs	x21,x21,x15
+	mul	x15,x12,x6
+	adcs	x22,x22,x16
+	mul	x16,x13,x6
+	adcs	x23,x23,x17
+	umulh	x17,x7,x6		// hi(a[1..7]*a[0])
+	adcs	x24,x24,x14
+	umulh	x14,x8,x6
+	adcs	x25,x25,x15
+	umulh	x15,x9,x6
+	adcs	x26,x26,x16
+	umulh	x16,x10,x6
+	stp	x19,x20,[x2],#8*2	// t[0..1]
+	adc	x19,xzr,xzr		// t[8]
+	adds	x21,x21,x17		// t[2]+lo(a[1]*a[0])
+	umulh	x17,x11,x6
+	adcs	x22,x22,x14
+	umulh	x14,x12,x6
+	adcs	x23,x23,x15
+	umulh	x15,x13,x6
+	adcs	x24,x24,x16
+	mul	x16,x8,x7		// lo(a[2..7]*a[1])		(ii)
+	adcs	x25,x25,x17
+	mul	x17,x9,x7
+	adcs	x26,x26,x14
+	mul	x14,x10,x7
+	adc	x19,x19,x15
+
+	mul	x15,x11,x7
+	adds	x22,x22,x16
+	mul	x16,x12,x7
+	adcs	x23,x23,x17
+	mul	x17,x13,x7
+	adcs	x24,x24,x14
+	umulh	x14,x8,x7		// hi(a[2..7]*a[1])
+	adcs	x25,x25,x15
+	umulh	x15,x9,x7
+	adcs	x26,x26,x16
+	umulh	x16,x10,x7
+	adcs	x19,x19,x17
+	umulh	x17,x11,x7
+	stp	x21,x22,[x2],#8*2	// t[2..3]
+	adc	x20,xzr,xzr		// t[9]
+	adds	x23,x23,x14
+	umulh	x14,x12,x7
+	adcs	x24,x24,x15
+	umulh	x15,x13,x7
+	adcs	x25,x25,x16
+	mul	x16,x9,x8		// lo(a[3..7]*a[2])		(iii)
+	adcs	x26,x26,x17
+	mul	x17,x10,x8
+	adcs	x19,x19,x14
+	mul	x14,x11,x8
+	adc	x20,x20,x15
+
+	mul	x15,x12,x8
+	adds	x24,x24,x16
+	mul	x16,x13,x8
+	adcs	x25,x25,x17
+	umulh	x17,x9,x8		// hi(a[3..7]*a[2])
+	adcs	x26,x26,x14
+	umulh	x14,x10,x8
+	adcs	x19,x19,x15
+	umulh	x15,x11,x8
+	adcs	x20,x20,x16
+	umulh	x16,x12,x8
+	stp	x23,x24,[x2],#8*2	// t[4..5]
+	adc	x21,xzr,xzr		// t[10]
+	adds	x25,x25,x17
+	umulh	x17,x13,x8
+	adcs	x26,x26,x14
+	mul	x14,x10,x9		// lo(a[4..7]*a[3])		(iv)
+	adcs	x19,x19,x15
+	mul	x15,x11,x9
+	adcs	x20,x20,x16
+	mul	x16,x12,x9
+	adc	x21,x21,x17
+
+	mul	x17,x13,x9
+	adds	x26,x26,x14
+	umulh	x14,x10,x9		// hi(a[4..7]*a[3])
+	adcs	x19,x19,x15
+	umulh	x15,x11,x9
+	adcs	x20,x20,x16
+	umulh	x16,x12,x9
+	adcs	x21,x21,x17
+	umulh	x17,x13,x9
+	stp	x25,x26,[x2],#8*2	// t[6..7]
+	adc	x22,xzr,xzr		// t[11]
+	adds	x19,x19,x14
+	mul	x14,x11,x10		// lo(a[5..7]*a[4])		(v)
+	adcs	x20,x20,x15
+	mul	x15,x12,x10
+	adcs	x21,x21,x16
+	mul	x16,x13,x10
+	adc	x22,x22,x17
+
+	umulh	x17,x11,x10		// hi(a[5..7]*a[4])
+	adds	x20,x20,x14
+	umulh	x14,x12,x10
+	adcs	x21,x21,x15
+	umulh	x15,x13,x10
+	adcs	x22,x22,x16
+	mul	x16,x12,x11		// lo(a[6..7]*a[5])		(vi)
+	adc	x23,xzr,xzr		// t[12]
+	adds	x21,x21,x17
+	mul	x17,x13,x11
+	adcs	x22,x22,x14
+	umulh	x14,x12,x11		// hi(a[6..7]*a[5])
+	adc	x23,x23,x15
+
+	umulh	x15,x13,x11
+	adds	x22,x22,x16
+	mul	x16,x13,x12		// lo(a[7]*a[6])		(vii)
+	adcs	x23,x23,x17
+	umulh	x17,x13,x12		// hi(a[7]*a[6])
+	adc	x24,xzr,xzr		// t[13]
+	adds	x23,x23,x14
+	sub	x27,x3,x1	// done yet?
+	adc	x24,x24,x15
+
+	adds	x24,x24,x16
+	sub	x14,x3,x5	// rewinded ap
+	adc	x25,xzr,xzr		// t[14]
+	add	x25,x25,x17
+
+	cbz	x27,.Lsqr8x_outer_break
+
+	mov	x4,x6
+	ldp	x6,x7,[x2,#8*0]
+	ldp	x8,x9,[x2,#8*2]
+	ldp	x10,x11,[x2,#8*4]
+	ldp	x12,x13,[x2,#8*6]
+	adds	x19,x19,x6
+	adcs	x20,x20,x7
+	ldp	x6,x7,[x1,#8*0]
+	adcs	x21,x21,x8
+	adcs	x22,x22,x9
+	ldp	x8,x9,[x1,#8*2]
+	adcs	x23,x23,x10
+	adcs	x24,x24,x11
+	ldp	x10,x11,[x1,#8*4]
+	adcs	x25,x25,x12
+	mov	x0,x1
+	adcs	x26,xzr,x13
+	ldp	x12,x13,[x1,#8*6]
+	add	x1,x1,#8*8
+	//adc	x28,xzr,xzr		// moved below
+	mov	x27,#-8*8
+
+	//                                                         a[8]a[0]
+	//                                                     a[9]a[0]
+	//                                                 a[a]a[0]
+	//                                             a[b]a[0]
+	//                                         a[c]a[0]
+	//                                     a[d]a[0]
+	//                                 a[e]a[0]
+	//                             a[f]a[0]
+	//                                                     a[8]a[1]
+	//                         a[f]a[1]........................
+	//                                                 a[8]a[2]
+	//                     a[f]a[2]........................
+	//                                             a[8]a[3]
+	//                 a[f]a[3]........................
+	//                                         a[8]a[4]
+	//             a[f]a[4]........................
+	//                                     a[8]a[5]
+	//         a[f]a[5]........................
+	//                                 a[8]a[6]
+	//     a[f]a[6]........................
+	//                             a[8]a[7]
+	// a[f]a[7]........................
+.Lsqr8x_mul:
+	mul	x14,x6,x4
+	adc	x28,xzr,xzr		// carry bit, modulo-scheduled
+	mul	x15,x7,x4
+	add	x27,x27,#8
+	mul	x16,x8,x4
+	mul	x17,x9,x4
+	adds	x19,x19,x14
+	mul	x14,x10,x4
+	adcs	x20,x20,x15
+	mul	x15,x11,x4
+	adcs	x21,x21,x16
+	mul	x16,x12,x4
+	adcs	x22,x22,x17
+	mul	x17,x13,x4
+	adcs	x23,x23,x14
+	umulh	x14,x6,x4
+	adcs	x24,x24,x15
+	umulh	x15,x7,x4
+	adcs	x25,x25,x16
+	umulh	x16,x8,x4
+	adcs	x26,x26,x17
+	umulh	x17,x9,x4
+	adc	x28,x28,xzr
+	str	x19,[x2],#8
+	adds	x19,x20,x14
+	umulh	x14,x10,x4
+	adcs	x20,x21,x15
+	umulh	x15,x11,x4
+	adcs	x21,x22,x16
+	umulh	x16,x12,x4
+	adcs	x22,x23,x17
+	umulh	x17,x13,x4
+	ldr	x4,[x0,x27]
+	adcs	x23,x24,x14
+	adcs	x24,x25,x15
+	adcs	x25,x26,x16
+	adcs	x26,x28,x17
+	//adc	x28,xzr,xzr		// moved above
+	cbnz	x27,.Lsqr8x_mul
+					// note that carry flag is guaranteed
+					// to be zero at this point
+	cmp	x1,x3		// done yet?
+	b.eq	.Lsqr8x_break
+
+	ldp	x6,x7,[x2,#8*0]
+	ldp	x8,x9,[x2,#8*2]
+	ldp	x10,x11,[x2,#8*4]
+	ldp	x12,x13,[x2,#8*6]
+	adds	x19,x19,x6
+	ldr	x4,[x0,#-8*8]
+	adcs	x20,x20,x7
+	ldp	x6,x7,[x1,#8*0]
+	adcs	x21,x21,x8
+	adcs	x22,x22,x9
+	ldp	x8,x9,[x1,#8*2]
+	adcs	x23,x23,x10
+	adcs	x24,x24,x11
+	ldp	x10,x11,[x1,#8*4]
+	adcs	x25,x25,x12
+	mov	x27,#-8*8
+	adcs	x26,x26,x13
+	ldp	x12,x13,[x1,#8*6]
+	add	x1,x1,#8*8
+	//adc	x28,xzr,xzr		// moved above
+	b	.Lsqr8x_mul
+
+.align	4
+.Lsqr8x_break:
+	ldp	x6,x7,[x0,#8*0]
+	add	x1,x0,#8*8
+	ldp	x8,x9,[x0,#8*2]
+	sub	x14,x3,x1		// is it last iteration?
+	ldp	x10,x11,[x0,#8*4]
+	sub	x15,x2,x14
+	ldp	x12,x13,[x0,#8*6]
+	cbz	x14,.Lsqr8x_outer_loop
+
+	stp	x19,x20,[x2,#8*0]
+	ldp	x19,x20,[x15,#8*0]
+	stp	x21,x22,[x2,#8*2]
+	ldp	x21,x22,[x15,#8*2]
+	stp	x23,x24,[x2,#8*4]
+	ldp	x23,x24,[x15,#8*4]
+	stp	x25,x26,[x2,#8*6]
+	mov	x2,x15
+	ldp	x25,x26,[x15,#8*6]
+	b	.Lsqr8x_outer_loop
+
+.align	4
+.Lsqr8x_outer_break:
+	// Now multiply above result by 2 and add a[n-1]*a[n-1]|...|a[0]*a[0]
+	ldp	x7,x9,[x14,#8*0]	// recall that x14 is &a[0]
+	ldp	x15,x16,[sp,#8*1]
+	ldp	x11,x13,[x14,#8*2]
+	add	x1,x14,#8*4
+	ldp	x17,x14,[sp,#8*3]
+
+	stp	x19,x20,[x2,#8*0]
+	mul	x19,x7,x7
+	stp	x21,x22,[x2,#8*2]
+	umulh	x7,x7,x7
+	stp	x23,x24,[x2,#8*4]
+	mul	x8,x9,x9
+	stp	x25,x26,[x2,#8*6]
+	mov	x2,sp
+	umulh	x9,x9,x9
+	adds	x20,x7,x15,lsl#1
+	extr	x15,x16,x15,#63
+	sub	x27,x5,#8*4
+
+.Lsqr4x_shift_n_add:
+	adcs	x21,x8,x15
+	extr	x16,x17,x16,#63
+	sub	x27,x27,#8*4
+	adcs	x22,x9,x16
+	ldp	x15,x16,[x2,#8*5]
+	mul	x10,x11,x11
+	ldp	x7,x9,[x1],#8*2
+	umulh	x11,x11,x11
+	mul	x12,x13,x13
+	umulh	x13,x13,x13
+	extr	x17,x14,x17,#63
+	stp	x19,x20,[x2,#8*0]
+	adcs	x23,x10,x17
+	extr	x14,x15,x14,#63
+	stp	x21,x22,[x2,#8*2]
+	adcs	x24,x11,x14
+	ldp	x17,x14,[x2,#8*7]
+	extr	x15,x16,x15,#63
+	adcs	x25,x12,x15
+	extr	x16,x17,x16,#63
+	adcs	x26,x13,x16
+	ldp	x15,x16,[x2,#8*9]
+	mul	x6,x7,x7
+	ldp	x11,x13,[x1],#8*2
+	umulh	x7,x7,x7
+	mul	x8,x9,x9
+	umulh	x9,x9,x9
+	stp	x23,x24,[x2,#8*4]
+	extr	x17,x14,x17,#63
+	stp	x25,x26,[x2,#8*6]
+	add	x2,x2,#8*8
+	adcs	x19,x6,x17
+	extr	x14,x15,x14,#63
+	adcs	x20,x7,x14
+	ldp	x17,x14,[x2,#8*3]
+	extr	x15,x16,x15,#63
+	cbnz	x27,.Lsqr4x_shift_n_add
+	ldp	x1,x4,[x29,#104]	// pull np and n0
+
+	adcs	x21,x8,x15
+	extr	x16,x17,x16,#63
+	adcs	x22,x9,x16
+	ldp	x15,x16,[x2,#8*5]
+	mul	x10,x11,x11
+	umulh	x11,x11,x11
+	stp	x19,x20,[x2,#8*0]
+	mul	x12,x13,x13
+	umulh	x13,x13,x13
+	stp	x21,x22,[x2,#8*2]
+	extr	x17,x14,x17,#63
+	adcs	x23,x10,x17
+	extr	x14,x15,x14,#63
+	ldp	x19,x20,[sp,#8*0]
+	adcs	x24,x11,x14
+	extr	x15,x16,x15,#63
+	ldp	x6,x7,[x1,#8*0]
+	adcs	x25,x12,x15
+	extr	x16,xzr,x16,#63
+	ldp	x8,x9,[x1,#8*2]
+	adc	x26,x13,x16
+	ldp	x10,x11,[x1,#8*4]
+
+	// Reduce by 512 bits per iteration
+	mul	x28,x4,x19		// t[0]*n0
+	ldp	x12,x13,[x1,#8*6]
+	add	x3,x1,x5
+	ldp	x21,x22,[sp,#8*2]
+	stp	x23,x24,[x2,#8*4]
+	ldp	x23,x24,[sp,#8*4]
+	stp	x25,x26,[x2,#8*6]
+	ldp	x25,x26,[sp,#8*6]
+	add	x1,x1,#8*8
+	mov	x30,xzr		// initial top-most carry
+	mov	x2,sp
+	mov	x27,#8
+
+.Lsqr8x_reduction:
+	// (*)	mul	x14,x6,x28	// lo(n[0-7])*lo(t[0]*n0)
+	mul	x15,x7,x28
+	sub	x27,x27,#1
+	mul	x16,x8,x28
+	str	x28,[x2],#8		// put aside t[0]*n0 for tail processing
+	mul	x17,x9,x28
+	// (*)	adds	xzr,x19,x14
+	subs	xzr,x19,#1		// (*)
+	mul	x14,x10,x28
+	adcs	x19,x20,x15
+	mul	x15,x11,x28
+	adcs	x20,x21,x16
+	mul	x16,x12,x28
+	adcs	x21,x22,x17
+	mul	x17,x13,x28
+	adcs	x22,x23,x14
+	umulh	x14,x6,x28		// hi(n[0-7])*lo(t[0]*n0)
+	adcs	x23,x24,x15
+	umulh	x15,x7,x28
+	adcs	x24,x25,x16
+	umulh	x16,x8,x28
+	adcs	x25,x26,x17
+	umulh	x17,x9,x28
+	adc	x26,xzr,xzr
+	adds	x19,x19,x14
+	umulh	x14,x10,x28
+	adcs	x20,x20,x15
+	umulh	x15,x11,x28
+	adcs	x21,x21,x16
+	umulh	x16,x12,x28
+	adcs	x22,x22,x17
+	umulh	x17,x13,x28
+	mul	x28,x4,x19		// next t[0]*n0
+	adcs	x23,x23,x14
+	adcs	x24,x24,x15
+	adcs	x25,x25,x16
+	adc	x26,x26,x17
+	cbnz	x27,.Lsqr8x_reduction
+
+	ldp	x14,x15,[x2,#8*0]
+	ldp	x16,x17,[x2,#8*2]
+	mov	x0,x2
+	sub	x27,x3,x1	// done yet?
+	adds	x19,x19,x14
+	adcs	x20,x20,x15
+	ldp	x14,x15,[x2,#8*4]
+	adcs	x21,x21,x16
+	adcs	x22,x22,x17
+	ldp	x16,x17,[x2,#8*6]
+	adcs	x23,x23,x14
+	adcs	x24,x24,x15
+	adcs	x25,x25,x16
+	adcs	x26,x26,x17
+	//adc	x28,xzr,xzr		// moved below
+	cbz	x27,.Lsqr8x8_post_condition
+
+	ldr	x4,[x2,#-8*8]
+	ldp	x6,x7,[x1,#8*0]
+	ldp	x8,x9,[x1,#8*2]
+	ldp	x10,x11,[x1,#8*4]
+	mov	x27,#-8*8
+	ldp	x12,x13,[x1,#8*6]
+	add	x1,x1,#8*8
+
+.Lsqr8x_tail:
+	mul	x14,x6,x4
+	adc	x28,xzr,xzr		// carry bit, modulo-scheduled
+	mul	x15,x7,x4
+	add	x27,x27,#8
+	mul	x16,x8,x4
+	mul	x17,x9,x4
+	adds	x19,x19,x14
+	mul	x14,x10,x4
+	adcs	x20,x20,x15
+	mul	x15,x11,x4
+	adcs	x21,x21,x16
+	mul	x16,x12,x4
+	adcs	x22,x22,x17
+	mul	x17,x13,x4
+	adcs	x23,x23,x14
+	umulh	x14,x6,x4
+	adcs	x24,x24,x15
+	umulh	x15,x7,x4
+	adcs	x25,x25,x16
+	umulh	x16,x8,x4
+	adcs	x26,x26,x17
+	umulh	x17,x9,x4
+	adc	x28,x28,xzr
+	str	x19,[x2],#8
+	adds	x19,x20,x14
+	umulh	x14,x10,x4
+	adcs	x20,x21,x15
+	umulh	x15,x11,x4
+	adcs	x21,x22,x16
+	umulh	x16,x12,x4
+	adcs	x22,x23,x17
+	umulh	x17,x13,x4
+	ldr	x4,[x0,x27]
+	adcs	x23,x24,x14
+	adcs	x24,x25,x15
+	adcs	x25,x26,x16
+	adcs	x26,x28,x17
+	//adc	x28,xzr,xzr		// moved above
+	cbnz	x27,.Lsqr8x_tail
+					// note that carry flag is guaranteed
+					// to be zero at this point
+	ldp	x6,x7,[x2,#8*0]
+	sub	x27,x3,x1	// done yet?
+	sub	x16,x3,x5	// rewinded np
+	ldp	x8,x9,[x2,#8*2]
+	ldp	x10,x11,[x2,#8*4]
+	ldp	x12,x13,[x2,#8*6]
+	cbz	x27,.Lsqr8x_tail_break
+
+	ldr	x4,[x0,#-8*8]
+	adds	x19,x19,x6
+	adcs	x20,x20,x7
+	ldp	x6,x7,[x1,#8*0]
+	adcs	x21,x21,x8
+	adcs	x22,x22,x9
+	ldp	x8,x9,[x1,#8*2]
+	adcs	x23,x23,x10
+	adcs	x24,x24,x11
+	ldp	x10,x11,[x1,#8*4]
+	adcs	x25,x25,x12
+	mov	x27,#-8*8
+	adcs	x26,x26,x13
+	ldp	x12,x13,[x1,#8*6]
+	add	x1,x1,#8*8
+	//adc	x28,xzr,xzr		// moved above
+	b	.Lsqr8x_tail
+
+.align	4
+.Lsqr8x_tail_break:
+	ldr	x4,[x29,#112]		// pull n0
+	add	x27,x2,#8*8		// end of current t[num] window
+
+	subs	xzr,x30,#1		// "move" top-most carry to carry bit
+	adcs	x14,x19,x6
+	adcs	x15,x20,x7
+	ldp	x19,x20,[x0,#8*0]
+	adcs	x21,x21,x8
+	ldp	x6,x7,[x16,#8*0]	// recall that x16 is &n[0]
+	adcs	x22,x22,x9
+	ldp	x8,x9,[x16,#8*2]
+	adcs	x23,x23,x10
+	adcs	x24,x24,x11
+	ldp	x10,x11,[x16,#8*4]
+	adcs	x25,x25,x12
+	adcs	x26,x26,x13
+	ldp	x12,x13,[x16,#8*6]
+	add	x1,x16,#8*8
+	adc	x30,xzr,xzr	// top-most carry
+	mul	x28,x4,x19
+	stp	x14,x15,[x2,#8*0]
+	stp	x21,x22,[x2,#8*2]
+	ldp	x21,x22,[x0,#8*2]
+	stp	x23,x24,[x2,#8*4]
+	ldp	x23,x24,[x0,#8*4]
+	cmp	x27,x29		// did we hit the bottom?
+	stp	x25,x26,[x2,#8*6]
+	mov	x2,x0			// slide the window
+	ldp	x25,x26,[x0,#8*6]
+	mov	x27,#8
+	b.ne	.Lsqr8x_reduction
+
+	// Final step. We see if result is larger than modulus, and
+	// if it is, subtract the modulus. But comparison implies
+	// subtraction. So we subtract modulus, see if it borrowed,
+	// and conditionally copy original value.
+	ldr	x0,[x29,#96]		// pull rp
+	add	x2,x2,#8*8
+	subs	x14,x19,x6
+	sbcs	x15,x20,x7
+	sub	x27,x5,#8*8
+	mov	x3,x0		// x0 copy
+
+.Lsqr8x_sub:
+	sbcs	x16,x21,x8
+	ldp	x6,x7,[x1,#8*0]
+	sbcs	x17,x22,x9
+	stp	x14,x15,[x0,#8*0]
+	sbcs	x14,x23,x10
+	ldp	x8,x9,[x1,#8*2]
+	sbcs	x15,x24,x11
+	stp	x16,x17,[x0,#8*2]
+	sbcs	x16,x25,x12
+	ldp	x10,x11,[x1,#8*4]
+	sbcs	x17,x26,x13
+	ldp	x12,x13,[x1,#8*6]
+	add	x1,x1,#8*8
+	ldp	x19,x20,[x2,#8*0]
+	sub	x27,x27,#8*8
+	ldp	x21,x22,[x2,#8*2]
+	ldp	x23,x24,[x2,#8*4]
+	ldp	x25,x26,[x2,#8*6]
+	add	x2,x2,#8*8
+	stp	x14,x15,[x0,#8*4]
+	sbcs	x14,x19,x6
+	stp	x16,x17,[x0,#8*6]
+	add	x0,x0,#8*8
+	sbcs	x15,x20,x7
+	cbnz	x27,.Lsqr8x_sub
+
+	sbcs	x16,x21,x8
+	mov	x2,sp
+	add	x1,sp,x5
+	ldp	x6,x7,[x3,#8*0]
+	sbcs	x17,x22,x9
+	stp	x14,x15,[x0,#8*0]
+	sbcs	x14,x23,x10
+	ldp	x8,x9,[x3,#8*2]
+	sbcs	x15,x24,x11
+	stp	x16,x17,[x0,#8*2]
+	sbcs	x16,x25,x12
+	ldp	x19,x20,[x1,#8*0]
+	sbcs	x17,x26,x13
+	ldp	x21,x22,[x1,#8*2]
+	sbcs	xzr,x30,xzr	// did it borrow?
+	ldr	x30,[x29,#8]		// pull return address
+	stp	x14,x15,[x0,#8*4]
+	stp	x16,x17,[x0,#8*6]
+
+	sub	x27,x5,#8*4
+.Lsqr4x_cond_copy:
+	sub	x27,x27,#8*4
+	csel	x14,x19,x6,lo
+	stp	xzr,xzr,[x2,#8*0]
+	csel	x15,x20,x7,lo
+	ldp	x6,x7,[x3,#8*4]
+	ldp	x19,x20,[x1,#8*4]
+	csel	x16,x21,x8,lo
+	stp	xzr,xzr,[x2,#8*2]
+	add	x2,x2,#8*4
+	csel	x17,x22,x9,lo
+	ldp	x8,x9,[x3,#8*6]
+	ldp	x21,x22,[x1,#8*6]
+	add	x1,x1,#8*4
+	stp	x14,x15,[x3,#8*0]
+	stp	x16,x17,[x3,#8*2]
+	add	x3,x3,#8*4
+	stp	xzr,xzr,[x1,#8*0]
+	stp	xzr,xzr,[x1,#8*2]
+	cbnz	x27,.Lsqr4x_cond_copy
+
+	csel	x14,x19,x6,lo
+	stp	xzr,xzr,[x2,#8*0]
+	csel	x15,x20,x7,lo
+	stp	xzr,xzr,[x2,#8*2]
+	csel	x16,x21,x8,lo
+	csel	x17,x22,x9,lo
+	stp	x14,x15,[x3,#8*0]
+	stp	x16,x17,[x3,#8*2]
+
+	b	.Lsqr8x_done
+
+.align	4
+.Lsqr8x8_post_condition:
+	adc	x28,xzr,xzr
+	ldr	x30,[x29,#8]		// pull return address
+	// x19-7,x28 hold result, x6-7 hold modulus
+	subs	x6,x19,x6
+	ldr	x1,[x29,#96]		// pull rp
+	sbcs	x7,x20,x7
+	stp	xzr,xzr,[sp,#8*0]
+	sbcs	x8,x21,x8
+	stp	xzr,xzr,[sp,#8*2]
+	sbcs	x9,x22,x9
+	stp	xzr,xzr,[sp,#8*4]
+	sbcs	x10,x23,x10
+	stp	xzr,xzr,[sp,#8*6]
+	sbcs	x11,x24,x11
+	stp	xzr,xzr,[sp,#8*8]
+	sbcs	x12,x25,x12
+	stp	xzr,xzr,[sp,#8*10]
+	sbcs	x13,x26,x13
+	stp	xzr,xzr,[sp,#8*12]
+	sbcs	x28,x28,xzr	// did it borrow?
+	stp	xzr,xzr,[sp,#8*14]
+
+	// x6-7 hold result-modulus
+	csel	x6,x19,x6,lo
+	csel	x7,x20,x7,lo
+	csel	x8,x21,x8,lo
+	csel	x9,x22,x9,lo
+	stp	x6,x7,[x1,#8*0]
+	csel	x10,x23,x10,lo
+	csel	x11,x24,x11,lo
+	stp	x8,x9,[x1,#8*2]
+	csel	x12,x25,x12,lo
+	csel	x13,x26,x13,lo
+	stp	x10,x11,[x1,#8*4]
+	stp	x12,x13,[x1,#8*6]
+
+.Lsqr8x_done:
+	ldp	x19,x20,[x29,#16]
+	mov	sp,x29
+	ldp	x21,x22,[x29,#32]
+	mov	x0,#1
+	ldp	x23,x24,[x29,#48]
+	ldp	x25,x26,[x29,#64]
+	ldp	x27,x28,[x29,#80]
+	ldr	x29,[sp],#128
+	ret
+.size	__bn_sqr8x_mont,.-__bn_sqr8x_mont
+.type	__bn_mul4x_mont,%function
+.align	5
+__bn_mul4x_mont:
+	stp	x29,x30,[sp,#-128]!
+	add	x29,sp,#0
+	stp	x19,x20,[sp,#16]
+	stp	x21,x22,[sp,#32]
+	stp	x23,x24,[sp,#48]
+	stp	x25,x26,[sp,#64]
+	stp	x27,x28,[sp,#80]
+
+	sub	x26,sp,x5,lsl#3
+	lsl	x5,x5,#3
+	ldr	x4,[x4]		// *n0
+	sub	sp,x26,#8*4		// alloca
+
+	add	x10,x2,x5
+	add	x27,x1,x5
+	stp	x0,x10,[x29,#96]	// offload rp and &b[num]
+
+	ldr	x24,[x2,#8*0]		// b[0]
+	ldp	x6,x7,[x1,#8*0]	// a[0..3]
+	ldp	x8,x9,[x1,#8*2]
+	add	x1,x1,#8*4
+	mov	x19,xzr
+	mov	x20,xzr
+	mov	x21,xzr
+	mov	x22,xzr
+	ldp	x14,x15,[x3,#8*0]	// n[0..3]
+	ldp	x16,x17,[x3,#8*2]
+	adds	x3,x3,#8*4		// clear carry bit
+	mov	x0,xzr
+	mov	x28,#0
+	mov	x26,sp
+
+.Loop_mul4x_1st_reduction:
+	mul	x10,x6,x24		// lo(a[0..3]*b[0])
+	adc	x0,x0,xzr	// modulo-scheduled
+	mul	x11,x7,x24
+	add	x28,x28,#8
+	mul	x12,x8,x24
+	and	x28,x28,#31
+	mul	x13,x9,x24
+	adds	x19,x19,x10
+	umulh	x10,x6,x24		// hi(a[0..3]*b[0])
+	adcs	x20,x20,x11
+	mul	x25,x19,x4		// t[0]*n0
+	adcs	x21,x21,x12
+	umulh	x11,x7,x24
+	adcs	x22,x22,x13
+	umulh	x12,x8,x24
+	adc	x23,xzr,xzr
+	umulh	x13,x9,x24
+	ldr	x24,[x2,x28]		// next b[i] (or b[0])
+	adds	x20,x20,x10
+	// (*)	mul	x10,x14,x25	// lo(n[0..3]*t[0]*n0)
+	str	x25,[x26],#8		// put aside t[0]*n0 for tail processing
+	adcs	x21,x21,x11
+	mul	x11,x15,x25
+	adcs	x22,x22,x12
+	mul	x12,x16,x25
+	adc	x23,x23,x13		// can't overflow
+	mul	x13,x17,x25
+	// (*)	adds	xzr,x19,x10
+	subs	xzr,x19,#1		// (*)
+	umulh	x10,x14,x25		// hi(n[0..3]*t[0]*n0)
+	adcs	x19,x20,x11
+	umulh	x11,x15,x25
+	adcs	x20,x21,x12
+	umulh	x12,x16,x25
+	adcs	x21,x22,x13
+	umulh	x13,x17,x25
+	adcs	x22,x23,x0
+	adc	x0,xzr,xzr
+	adds	x19,x19,x10
+	sub	x10,x27,x1
+	adcs	x20,x20,x11
+	adcs	x21,x21,x12
+	adcs	x22,x22,x13
+	//adc	x0,x0,xzr
+	cbnz	x28,.Loop_mul4x_1st_reduction
+
+	cbz	x10,.Lmul4x4_post_condition
+
+	ldp	x6,x7,[x1,#8*0]	// a[4..7]
+	ldp	x8,x9,[x1,#8*2]
+	add	x1,x1,#8*4
+	ldr	x25,[sp]		// a[0]*n0
+	ldp	x14,x15,[x3,#8*0]	// n[4..7]
+	ldp	x16,x17,[x3,#8*2]
+	add	x3,x3,#8*4
+
+.Loop_mul4x_1st_tail:
+	mul	x10,x6,x24		// lo(a[4..7]*b[i])
+	adc	x0,x0,xzr	// modulo-scheduled
+	mul	x11,x7,x24
+	add	x28,x28,#8
+	mul	x12,x8,x24
+	and	x28,x28,#31
+	mul	x13,x9,x24
+	adds	x19,x19,x10
+	umulh	x10,x6,x24		// hi(a[4..7]*b[i])
+	adcs	x20,x20,x11
+	umulh	x11,x7,x24
+	adcs	x21,x21,x12
+	umulh	x12,x8,x24
+	adcs	x22,x22,x13
+	umulh	x13,x9,x24
+	adc	x23,xzr,xzr
+	ldr	x24,[x2,x28]		// next b[i] (or b[0])
+	adds	x20,x20,x10
+	mul	x10,x14,x25		// lo(n[4..7]*a[0]*n0)
+	adcs	x21,x21,x11
+	mul	x11,x15,x25
+	adcs	x22,x22,x12
+	mul	x12,x16,x25
+	adc	x23,x23,x13		// can't overflow
+	mul	x13,x17,x25
+	adds	x19,x19,x10
+	umulh	x10,x14,x25		// hi(n[4..7]*a[0]*n0)
+	adcs	x20,x20,x11
+	umulh	x11,x15,x25
+	adcs	x21,x21,x12
+	umulh	x12,x16,x25
+	adcs	x22,x22,x13
+	adcs	x23,x23,x0
+	umulh	x13,x17,x25
+	adc	x0,xzr,xzr
+	ldr	x25,[sp,x28]		// next t[0]*n0
+	str	x19,[x26],#8		// result!!!
+	adds	x19,x20,x10
+	sub	x10,x27,x1		// done yet?
+	adcs	x20,x21,x11
+	adcs	x21,x22,x12
+	adcs	x22,x23,x13
+	//adc	x0,x0,xzr
+	cbnz	x28,.Loop_mul4x_1st_tail
+
+	sub	x11,x27,x5	// rewinded x1
+	cbz	x10,.Lmul4x_proceed
+
+	ldp	x6,x7,[x1,#8*0]
+	ldp	x8,x9,[x1,#8*2]
+	add	x1,x1,#8*4
+	ldp	x14,x15,[x3,#8*0]
+	ldp	x16,x17,[x3,#8*2]
+	add	x3,x3,#8*4
+	b	.Loop_mul4x_1st_tail
+
+.align	5
+.Lmul4x_proceed:
+	ldr	x24,[x2,#8*4]!		// *++b
+	adc	x30,x0,xzr
+	ldp	x6,x7,[x11,#8*0]	// a[0..3]
+	sub	x3,x3,x5		// rewind np
+	ldp	x8,x9,[x11,#8*2]
+	add	x1,x11,#8*4
+
+	stp	x19,x20,[x26,#8*0]	// result!!!
+	ldp	x19,x20,[sp,#8*4]	// t[0..3]
+	stp	x21,x22,[x26,#8*2]	// result!!!
+	ldp	x21,x22,[sp,#8*6]
+
+	ldp	x14,x15,[x3,#8*0]	// n[0..3]
+	mov	x26,sp
+	ldp	x16,x17,[x3,#8*2]
+	adds	x3,x3,#8*4		// clear carry bit
+	mov	x0,xzr
+
+.align	4
+.Loop_mul4x_reduction:
+	mul	x10,x6,x24		// lo(a[0..3]*b[4])
+	adc	x0,x0,xzr	// modulo-scheduled
+	mul	x11,x7,x24
+	add	x28,x28,#8
+	mul	x12,x8,x24
+	and	x28,x28,#31
+	mul	x13,x9,x24
+	adds	x19,x19,x10
+	umulh	x10,x6,x24		// hi(a[0..3]*b[4])
+	adcs	x20,x20,x11
+	mul	x25,x19,x4		// t[0]*n0
+	adcs	x21,x21,x12
+	umulh	x11,x7,x24
+	adcs	x22,x22,x13
+	umulh	x12,x8,x24
+	adc	x23,xzr,xzr
+	umulh	x13,x9,x24
+	ldr	x24,[x2,x28]		// next b[i]
+	adds	x20,x20,x10
+	// (*)	mul	x10,x14,x25
+	str	x25,[x26],#8		// put aside t[0]*n0 for tail processing
+	adcs	x21,x21,x11
+	mul	x11,x15,x25		// lo(n[0..3]*t[0]*n0
+	adcs	x22,x22,x12
+	mul	x12,x16,x25
+	adc	x23,x23,x13		// can't overflow
+	mul	x13,x17,x25
+	// (*)	adds	xzr,x19,x10
+	subs	xzr,x19,#1		// (*)
+	umulh	x10,x14,x25		// hi(n[0..3]*t[0]*n0
+	adcs	x19,x20,x11
+	umulh	x11,x15,x25
+	adcs	x20,x21,x12
+	umulh	x12,x16,x25
+	adcs	x21,x22,x13
+	umulh	x13,x17,x25
+	adcs	x22,x23,x0
+	adc	x0,xzr,xzr
+	adds	x19,x19,x10
+	adcs	x20,x20,x11
+	adcs	x21,x21,x12
+	adcs	x22,x22,x13
+	//adc	x0,x0,xzr
+	cbnz	x28,.Loop_mul4x_reduction
+
+	adc	x0,x0,xzr
+	ldp	x10,x11,[x26,#8*4]	// t[4..7]
+	ldp	x12,x13,[x26,#8*6]
+	ldp	x6,x7,[x1,#8*0]	// a[4..7]
+	ldp	x8,x9,[x1,#8*2]
+	add	x1,x1,#8*4
+	adds	x19,x19,x10
+	adcs	x20,x20,x11
+	adcs	x21,x21,x12
+	adcs	x22,x22,x13
+	//adc	x0,x0,xzr
+
+	ldr	x25,[sp]		// t[0]*n0
+	ldp	x14,x15,[x3,#8*0]	// n[4..7]
+	ldp	x16,x17,[x3,#8*2]
+	add	x3,x3,#8*4
+
+.align	4
+.Loop_mul4x_tail:
+	mul	x10,x6,x24		// lo(a[4..7]*b[4])
+	adc	x0,x0,xzr	// modulo-scheduled
+	mul	x11,x7,x24
+	add	x28,x28,#8
+	mul	x12,x8,x24
+	and	x28,x28,#31
+	mul	x13,x9,x24
+	adds	x19,x19,x10
+	umulh	x10,x6,x24		// hi(a[4..7]*b[4])
+	adcs	x20,x20,x11
+	umulh	x11,x7,x24
+	adcs	x21,x21,x12
+	umulh	x12,x8,x24
+	adcs	x22,x22,x13
+	umulh	x13,x9,x24
+	adc	x23,xzr,xzr
+	ldr	x24,[x2,x28]		// next b[i]
+	adds	x20,x20,x10
+	mul	x10,x14,x25		// lo(n[4..7]*t[0]*n0)
+	adcs	x21,x21,x11
+	mul	x11,x15,x25
+	adcs	x22,x22,x12
+	mul	x12,x16,x25
+	adc	x23,x23,x13		// can't overflow
+	mul	x13,x17,x25
+	adds	x19,x19,x10
+	umulh	x10,x14,x25		// hi(n[4..7]*t[0]*n0)
+	adcs	x20,x20,x11
+	umulh	x11,x15,x25
+	adcs	x21,x21,x12
+	umulh	x12,x16,x25
+	adcs	x22,x22,x13
+	umulh	x13,x17,x25
+	adcs	x23,x23,x0
+	ldr	x25,[sp,x28]		// next a[0]*n0
+	adc	x0,xzr,xzr
+	str	x19,[x26],#8		// result!!!
+	adds	x19,x20,x10
+	sub	x10,x27,x1		// done yet?
+	adcs	x20,x21,x11
+	adcs	x21,x22,x12
+	adcs	x22,x23,x13
+	//adc	x0,x0,xzr
+	cbnz	x28,.Loop_mul4x_tail
+
+	sub	x11,x3,x5		// rewinded np?
+	adc	x0,x0,xzr
+	cbz	x10,.Loop_mul4x_break
+
+	ldp	x10,x11,[x26,#8*4]
+	ldp	x12,x13,[x26,#8*6]
+	ldp	x6,x7,[x1,#8*0]
+	ldp	x8,x9,[x1,#8*2]
+	add	x1,x1,#8*4
+	adds	x19,x19,x10
+	adcs	x20,x20,x11
+	adcs	x21,x21,x12
+	adcs	x22,x22,x13
+	//adc	x0,x0,xzr
+	ldp	x14,x15,[x3,#8*0]
+	ldp	x16,x17,[x3,#8*2]
+	add	x3,x3,#8*4
+	b	.Loop_mul4x_tail
+
+.align	4
+.Loop_mul4x_break:
+	ldp	x12,x13,[x29,#96]	// pull rp and &b[num]
+	adds	x19,x19,x30
+	add	x2,x2,#8*4		// bp++
+	adcs	x20,x20,xzr
+	sub	x1,x1,x5		// rewind ap
+	adcs	x21,x21,xzr
+	stp	x19,x20,[x26,#8*0]	// result!!!
+	adcs	x22,x22,xzr
+	ldp	x19,x20,[sp,#8*4]	// t[0..3]
+	adc	x30,x0,xzr
+	stp	x21,x22,[x26,#8*2]	// result!!!
+	cmp	x2,x13			// done yet?
+	ldp	x21,x22,[sp,#8*6]
+	ldp	x14,x15,[x11,#8*0]	// n[0..3]
+	ldp	x16,x17,[x11,#8*2]
+	add	x3,x11,#8*4
+	b.eq	.Lmul4x_post
+
+	ldr	x24,[x2]
+	ldp	x6,x7,[x1,#8*0]	// a[0..3]
+	ldp	x8,x9,[x1,#8*2]
+	adds	x1,x1,#8*4		// clear carry bit
+	mov	x0,xzr
+	mov	x26,sp
+	b	.Loop_mul4x_reduction
+
+.align	4
+.Lmul4x_post:
+	// Final step. We see if result is larger than modulus, and
+	// if it is, subtract the modulus. But comparison implies
+	// subtraction. So we subtract modulus, see if it borrowed,
+	// and conditionally copy original value.
+	mov	x0,x12
+	mov	x27,x12		// x0 copy
+	subs	x10,x19,x14
+	add	x26,sp,#8*8
+	sbcs	x11,x20,x15
+	sub	x28,x5,#8*4
+
+.Lmul4x_sub:
+	sbcs	x12,x21,x16
+	ldp	x14,x15,[x3,#8*0]
+	sub	x28,x28,#8*4
+	ldp	x19,x20,[x26,#8*0]
+	sbcs	x13,x22,x17
+	ldp	x16,x17,[x3,#8*2]
+	add	x3,x3,#8*4
+	ldp	x21,x22,[x26,#8*2]
+	add	x26,x26,#8*4
+	stp	x10,x11,[x0,#8*0]
+	sbcs	x10,x19,x14
+	stp	x12,x13,[x0,#8*2]
+	add	x0,x0,#8*4
+	sbcs	x11,x20,x15
+	cbnz	x28,.Lmul4x_sub
+
+	sbcs	x12,x21,x16
+	mov	x26,sp
+	add	x1,sp,#8*4
+	ldp	x6,x7,[x27,#8*0]
+	sbcs	x13,x22,x17
+	stp	x10,x11,[x0,#8*0]
+	ldp	x8,x9,[x27,#8*2]
+	stp	x12,x13,[x0,#8*2]
+	ldp	x19,x20,[x1,#8*0]
+	ldp	x21,x22,[x1,#8*2]
+	sbcs	xzr,x30,xzr	// did it borrow?
+	ldr	x30,[x29,#8]		// pull return address
+
+	sub	x28,x5,#8*4
+.Lmul4x_cond_copy:
+	sub	x28,x28,#8*4
+	csel	x10,x19,x6,lo
+	stp	xzr,xzr,[x26,#8*0]
+	csel	x11,x20,x7,lo
+	ldp	x6,x7,[x27,#8*4]
+	ldp	x19,x20,[x1,#8*4]
+	csel	x12,x21,x8,lo
+	stp	xzr,xzr,[x26,#8*2]
+	add	x26,x26,#8*4
+	csel	x13,x22,x9,lo
+	ldp	x8,x9,[x27,#8*6]
+	ldp	x21,x22,[x1,#8*6]
+	add	x1,x1,#8*4
+	stp	x10,x11,[x27,#8*0]
+	stp	x12,x13,[x27,#8*2]
+	add	x27,x27,#8*4
+	cbnz	x28,.Lmul4x_cond_copy
+
+	csel	x10,x19,x6,lo
+	stp	xzr,xzr,[x26,#8*0]
+	csel	x11,x20,x7,lo
+	stp	xzr,xzr,[x26,#8*2]
+	csel	x12,x21,x8,lo
+	stp	xzr,xzr,[x26,#8*3]
+	csel	x13,x22,x9,lo
+	stp	xzr,xzr,[x26,#8*4]
+	stp	x10,x11,[x27,#8*0]
+	stp	x12,x13,[x27,#8*2]
+
+	b	.Lmul4x_done
+
+.align	4
+.Lmul4x4_post_condition:
+	adc	x0,x0,xzr
+	ldr	x1,[x29,#96]		// pull rp
+	// x19-3,x0 hold result, x14-7 hold modulus
+	subs	x6,x19,x14
+	ldr	x30,[x29,#8]		// pull return address
+	sbcs	x7,x20,x15
+	stp	xzr,xzr,[sp,#8*0]
+	sbcs	x8,x21,x16
+	stp	xzr,xzr,[sp,#8*2]
+	sbcs	x9,x22,x17
+	stp	xzr,xzr,[sp,#8*4]
+	sbcs	xzr,x0,xzr		// did it borrow?
+	stp	xzr,xzr,[sp,#8*6]
+
+	// x6-3 hold result-modulus
+	csel	x6,x19,x6,lo
+	csel	x7,x20,x7,lo
+	csel	x8,x21,x8,lo
+	csel	x9,x22,x9,lo
+	stp	x6,x7,[x1,#8*0]
+	stp	x8,x9,[x1,#8*2]
+
+.Lmul4x_done:
+	ldp	x19,x20,[x29,#16]
+	mov	sp,x29
+	ldp	x21,x22,[x29,#32]
+	mov	x0,#1
+	ldp	x23,x24,[x29,#48]
+	ldp	x25,x26,[x29,#64]
+	ldp	x27,x28,[x29,#80]
+	ldr	x29,[sp],#128
+	ret
+.size	__bn_mul4x_mont,.-__bn_mul4x_mont
+.byte	77,111,110,116,103,111,109,101,114,121,32,77,117,108,116,105,112,108,105,99,97,116,105,111,110,32,102,111,114,32,65,82,77,118,56,44,32,67,82,89,80,84,79,71,65,77,83,32,98,121,32,60,97,112,112,114,111,64,111,112,101,110,115,115,108,46,111,114,103,62,0
+.align	2
+.align	4
+#endif
diff --git a/packager/third_party/boringssl/linux-aarch64/crypto/chacha/chacha-armv8.S b/packager/third_party/boringssl/linux-aarch64/crypto/chacha/chacha-armv8.S
new file mode 100644
index 0000000000..6ff6bffb66
--- /dev/null
+++ b/packager/third_party/boringssl/linux-aarch64/crypto/chacha/chacha-armv8.S
@@ -0,0 +1,1971 @@
+#if defined(__aarch64__)
+#include <openssl/arm_arch.h>
+
+.text
+
+
+
+.align	5
+.Lsigma:
+.quad	0x3320646e61707865,0x6b20657479622d32		// endian-neutral
+.Lone:
+.long	1,0,0,0
+.LOPENSSL_armcap_P:
+#ifdef	__ILP32__
+.long	OPENSSL_armcap_P-.
+#else
+.quad	OPENSSL_armcap_P-.
+#endif
+.byte	67,104,97,67,104,97,50,48,32,102,111,114,32,65,82,77,118,56,44,32,67,82,89,80,84,79,71,65,77,83,32,98,121,32,60,97,112,112,114,111,64,111,112,101,110,115,115,108,46,111,114,103,62,0
+.align	2
+
+.globl	ChaCha20_ctr32
+.hidden	ChaCha20_ctr32
+.type	ChaCha20_ctr32,%function
+.align	5
+ChaCha20_ctr32:
+	cbz	x2,.Labort
+	adr	x5,.LOPENSSL_armcap_P
+	cmp	x2,#192
+	b.lo	.Lshort
+#ifdef	__ILP32__
+	ldrsw	x6,[x5]
+#else
+	ldr	x6,[x5]
+#endif
+	ldr	w17,[x6,x5]
+	tst	w17,#ARMV7_NEON
+	b.ne	ChaCha20_neon
+
+.Lshort:
+	stp	x29,x30,[sp,#-96]!
+	add	x29,sp,#0
+
+	adr	x5,.Lsigma
+	stp	x19,x20,[sp,#16]
+	stp	x21,x22,[sp,#32]
+	stp	x23,x24,[sp,#48]
+	stp	x25,x26,[sp,#64]
+	stp	x27,x28,[sp,#80]
+	sub	sp,sp,#64
+
+	ldp	x22,x23,[x5]		// load sigma
+	ldp	x24,x25,[x3]		// load key
+	ldp	x26,x27,[x3,#16]
+	ldp	x28,x30,[x4]		// load counter
+#ifdef	__ARMEB__
+	ror	x24,x24,#32
+	ror	x25,x25,#32
+	ror	x26,x26,#32
+	ror	x27,x27,#32
+	ror	x28,x28,#32
+	ror	x30,x30,#32
+#endif
+
+.Loop_outer:
+	mov	w5,w22			// unpack key block
+	lsr	x6,x22,#32
+	mov	w7,w23
+	lsr	x8,x23,#32
+	mov	w9,w24
+	lsr	x10,x24,#32
+	mov	w11,w25
+	lsr	x12,x25,#32
+	mov	w13,w26
+	lsr	x14,x26,#32
+	mov	w15,w27
+	lsr	x16,x27,#32
+	mov	w17,w28
+	lsr	x19,x28,#32
+	mov	w20,w30
+	lsr	x21,x30,#32
+
+	mov	x4,#10
+	subs	x2,x2,#64
+.Loop:
+	sub	x4,x4,#1
+	add	w5,w5,w9
+	add	w6,w6,w10
+	add	w7,w7,w11
+	add	w8,w8,w12
+	eor	w17,w17,w5
+	eor	w19,w19,w6
+	eor	w20,w20,w7
+	eor	w21,w21,w8
+	ror	w17,w17,#16
+	ror	w19,w19,#16
+	ror	w20,w20,#16
+	ror	w21,w21,#16
+	add	w13,w13,w17
+	add	w14,w14,w19
+	add	w15,w15,w20
+	add	w16,w16,w21
+	eor	w9,w9,w13
+	eor	w10,w10,w14
+	eor	w11,w11,w15
+	eor	w12,w12,w16
+	ror	w9,w9,#20
+	ror	w10,w10,#20
+	ror	w11,w11,#20
+	ror	w12,w12,#20
+	add	w5,w5,w9
+	add	w6,w6,w10
+	add	w7,w7,w11
+	add	w8,w8,w12
+	eor	w17,w17,w5
+	eor	w19,w19,w6
+	eor	w20,w20,w7
+	eor	w21,w21,w8
+	ror	w17,w17,#24
+	ror	w19,w19,#24
+	ror	w20,w20,#24
+	ror	w21,w21,#24
+	add	w13,w13,w17
+	add	w14,w14,w19
+	add	w15,w15,w20
+	add	w16,w16,w21
+	eor	w9,w9,w13
+	eor	w10,w10,w14
+	eor	w11,w11,w15
+	eor	w12,w12,w16
+	ror	w9,w9,#25
+	ror	w10,w10,#25
+	ror	w11,w11,#25
+	ror	w12,w12,#25
+	add	w5,w5,w10
+	add	w6,w6,w11
+	add	w7,w7,w12
+	add	w8,w8,w9
+	eor	w21,w21,w5
+	eor	w17,w17,w6
+	eor	w19,w19,w7
+	eor	w20,w20,w8
+	ror	w21,w21,#16
+	ror	w17,w17,#16
+	ror	w19,w19,#16
+	ror	w20,w20,#16
+	add	w15,w15,w21
+	add	w16,w16,w17
+	add	w13,w13,w19
+	add	w14,w14,w20
+	eor	w10,w10,w15
+	eor	w11,w11,w16
+	eor	w12,w12,w13
+	eor	w9,w9,w14
+	ror	w10,w10,#20
+	ror	w11,w11,#20
+	ror	w12,w12,#20
+	ror	w9,w9,#20
+	add	w5,w5,w10
+	add	w6,w6,w11
+	add	w7,w7,w12
+	add	w8,w8,w9
+	eor	w21,w21,w5
+	eor	w17,w17,w6
+	eor	w19,w19,w7
+	eor	w20,w20,w8
+	ror	w21,w21,#24
+	ror	w17,w17,#24
+	ror	w19,w19,#24
+	ror	w20,w20,#24
+	add	w15,w15,w21
+	add	w16,w16,w17
+	add	w13,w13,w19
+	add	w14,w14,w20
+	eor	w10,w10,w15
+	eor	w11,w11,w16
+	eor	w12,w12,w13
+	eor	w9,w9,w14
+	ror	w10,w10,#25
+	ror	w11,w11,#25
+	ror	w12,w12,#25
+	ror	w9,w9,#25
+	cbnz	x4,.Loop
+
+	add	w5,w5,w22		// accumulate key block
+	add	x6,x6,x22,lsr#32
+	add	w7,w7,w23
+	add	x8,x8,x23,lsr#32
+	add	w9,w9,w24
+	add	x10,x10,x24,lsr#32
+	add	w11,w11,w25
+	add	x12,x12,x25,lsr#32
+	add	w13,w13,w26
+	add	x14,x14,x26,lsr#32
+	add	w15,w15,w27
+	add	x16,x16,x27,lsr#32
+	add	w17,w17,w28
+	add	x19,x19,x28,lsr#32
+	add	w20,w20,w30
+	add	x21,x21,x30,lsr#32
+
+	b.lo	.Ltail
+
+	add	x5,x5,x6,lsl#32	// pack
+	add	x7,x7,x8,lsl#32
+	ldp	x6,x8,[x1,#0]		// load input
+	add	x9,x9,x10,lsl#32
+	add	x11,x11,x12,lsl#32
+	ldp	x10,x12,[x1,#16]
+	add	x13,x13,x14,lsl#32
+	add	x15,x15,x16,lsl#32
+	ldp	x14,x16,[x1,#32]
+	add	x17,x17,x19,lsl#32
+	add	x20,x20,x21,lsl#32
+	ldp	x19,x21,[x1,#48]
+	add	x1,x1,#64
+#ifdef	__ARMEB__
+	rev	x5,x5
+	rev	x7,x7
+	rev	x9,x9
+	rev	x11,x11
+	rev	x13,x13
+	rev	x15,x15
+	rev	x17,x17
+	rev	x20,x20
+#endif
+	eor	x5,x5,x6
+	eor	x7,x7,x8
+	eor	x9,x9,x10
+	eor	x11,x11,x12
+	eor	x13,x13,x14
+	eor	x15,x15,x16
+	eor	x17,x17,x19
+	eor	x20,x20,x21
+
+	stp	x5,x7,[x0,#0]		// store output
+	add	x28,x28,#1			// increment counter
+	stp	x9,x11,[x0,#16]
+	stp	x13,x15,[x0,#32]
+	stp	x17,x20,[x0,#48]
+	add	x0,x0,#64
+
+	b.hi	.Loop_outer
+
+	ldp	x19,x20,[x29,#16]
+	add	sp,sp,#64
+	ldp	x21,x22,[x29,#32]
+	ldp	x23,x24,[x29,#48]
+	ldp	x25,x26,[x29,#64]
+	ldp	x27,x28,[x29,#80]
+	ldp	x29,x30,[sp],#96
+.Labort:
+	ret
+
+.align	4
+.Ltail:
+	add	x2,x2,#64
+.Less_than_64:
+	sub	x0,x0,#1
+	add	x1,x1,x2
+	add	x0,x0,x2
+	add	x4,sp,x2
+	neg	x2,x2
+
+	add	x5,x5,x6,lsl#32	// pack
+	add	x7,x7,x8,lsl#32
+	add	x9,x9,x10,lsl#32
+	add	x11,x11,x12,lsl#32
+	add	x13,x13,x14,lsl#32
+	add	x15,x15,x16,lsl#32
+	add	x17,x17,x19,lsl#32
+	add	x20,x20,x21,lsl#32
+#ifdef	__ARMEB__
+	rev	x5,x5
+	rev	x7,x7
+	rev	x9,x9
+	rev	x11,x11
+	rev	x13,x13
+	rev	x15,x15
+	rev	x17,x17
+	rev	x20,x20
+#endif
+	stp	x5,x7,[sp,#0]
+	stp	x9,x11,[sp,#16]
+	stp	x13,x15,[sp,#32]
+	stp	x17,x20,[sp,#48]
+
+.Loop_tail:
+	ldrb	w10,[x1,x2]
+	ldrb	w11,[x4,x2]
+	add	x2,x2,#1
+	eor	w10,w10,w11
+	strb	w10,[x0,x2]
+	cbnz	x2,.Loop_tail
+
+	stp	xzr,xzr,[sp,#0]
+	stp	xzr,xzr,[sp,#16]
+	stp	xzr,xzr,[sp,#32]
+	stp	xzr,xzr,[sp,#48]
+
+	ldp	x19,x20,[x29,#16]
+	add	sp,sp,#64
+	ldp	x21,x22,[x29,#32]
+	ldp	x23,x24,[x29,#48]
+	ldp	x25,x26,[x29,#64]
+	ldp	x27,x28,[x29,#80]
+	ldp	x29,x30,[sp],#96
+	ret
+.size	ChaCha20_ctr32,.-ChaCha20_ctr32
+
+.type	ChaCha20_neon,%function
+.align	5
+ChaCha20_neon:
+	stp	x29,x30,[sp,#-96]!
+	add	x29,sp,#0
+
+	adr	x5,.Lsigma
+	stp	x19,x20,[sp,#16]
+	stp	x21,x22,[sp,#32]
+	stp	x23,x24,[sp,#48]
+	stp	x25,x26,[sp,#64]
+	stp	x27,x28,[sp,#80]
+	cmp	x2,#512
+	b.hs	.L512_or_more_neon
+
+	sub	sp,sp,#64
+
+	ldp	x22,x23,[x5]		// load sigma
+	ld1	{v24.4s},[x5],#16
+	ldp	x24,x25,[x3]		// load key
+	ldp	x26,x27,[x3,#16]
+	ld1	{v25.4s,v26.4s},[x3]
+	ldp	x28,x30,[x4]		// load counter
+	ld1	{v27.4s},[x4]
+	ld1	{v31.4s},[x5]
+#ifdef	__ARMEB__
+	rev64	v24.4s,v24.4s
+	ror	x24,x24,#32
+	ror	x25,x25,#32
+	ror	x26,x26,#32
+	ror	x27,x27,#32
+	ror	x28,x28,#32
+	ror	x30,x30,#32
+#endif
+	add	v27.4s,v27.4s,v31.4s		// += 1
+	add	v28.4s,v27.4s,v31.4s
+	add	v29.4s,v28.4s,v31.4s
+	shl	v31.4s,v31.4s,#2			// 1 -> 4
+
+.Loop_outer_neon:
+	mov	w5,w22			// unpack key block
+	lsr	x6,x22,#32
+	mov	v0.16b,v24.16b
+	mov	w7,w23
+	lsr	x8,x23,#32
+	mov	v4.16b,v24.16b
+	mov	w9,w24
+	lsr	x10,x24,#32
+	mov	v16.16b,v24.16b
+	mov	w11,w25
+	mov	v1.16b,v25.16b
+	lsr	x12,x25,#32
+	mov	v5.16b,v25.16b
+	mov	w13,w26
+	mov	v17.16b,v25.16b
+	lsr	x14,x26,#32
+	mov	v3.16b,v27.16b
+	mov	w15,w27
+	mov	v7.16b,v28.16b
+	lsr	x16,x27,#32
+	mov	v19.16b,v29.16b
+	mov	w17,w28
+	mov	v2.16b,v26.16b
+	lsr	x19,x28,#32
+	mov	v6.16b,v26.16b
+	mov	w20,w30
+	mov	v18.16b,v26.16b
+	lsr	x21,x30,#32
+
+	mov	x4,#10
+	subs	x2,x2,#256
+.Loop_neon:
+	sub	x4,x4,#1
+	add	v0.4s,v0.4s,v1.4s
+	add	w5,w5,w9
+	add	v4.4s,v4.4s,v5.4s
+	add	w6,w6,w10
+	add	v16.4s,v16.4s,v17.4s
+	add	w7,w7,w11
+	eor	v3.16b,v3.16b,v0.16b
+	add	w8,w8,w12
+	eor	v7.16b,v7.16b,v4.16b
+	eor	w17,w17,w5
+	eor	v19.16b,v19.16b,v16.16b
+	eor	w19,w19,w6
+	rev32	v3.8h,v3.8h
+	eor	w20,w20,w7
+	rev32	v7.8h,v7.8h
+	eor	w21,w21,w8
+	rev32	v19.8h,v19.8h
+	ror	w17,w17,#16
+	add	v2.4s,v2.4s,v3.4s
+	ror	w19,w19,#16
+	add	v6.4s,v6.4s,v7.4s
+	ror	w20,w20,#16
+	add	v18.4s,v18.4s,v19.4s
+	ror	w21,w21,#16
+	eor	v20.16b,v1.16b,v2.16b
+	add	w13,w13,w17
+	eor	v21.16b,v5.16b,v6.16b
+	add	w14,w14,w19
+	eor	v22.16b,v17.16b,v18.16b
+	add	w15,w15,w20
+	ushr	v1.4s,v20.4s,#20
+	add	w16,w16,w21
+	ushr	v5.4s,v21.4s,#20
+	eor	w9,w9,w13
+	ushr	v17.4s,v22.4s,#20
+	eor	w10,w10,w14
+	sli	v1.4s,v20.4s,#12
+	eor	w11,w11,w15
+	sli	v5.4s,v21.4s,#12
+	eor	w12,w12,w16
+	sli	v17.4s,v22.4s,#12
+	ror	w9,w9,#20
+	add	v0.4s,v0.4s,v1.4s
+	ror	w10,w10,#20
+	add	v4.4s,v4.4s,v5.4s
+	ror	w11,w11,#20
+	add	v16.4s,v16.4s,v17.4s
+	ror	w12,w12,#20
+	eor	v20.16b,v3.16b,v0.16b
+	add	w5,w5,w9
+	eor	v21.16b,v7.16b,v4.16b
+	add	w6,w6,w10
+	eor	v22.16b,v19.16b,v16.16b
+	add	w7,w7,w11
+	ushr	v3.4s,v20.4s,#24
+	add	w8,w8,w12
+	ushr	v7.4s,v21.4s,#24
+	eor	w17,w17,w5
+	ushr	v19.4s,v22.4s,#24
+	eor	w19,w19,w6
+	sli	v3.4s,v20.4s,#8
+	eor	w20,w20,w7
+	sli	v7.4s,v21.4s,#8
+	eor	w21,w21,w8
+	sli	v19.4s,v22.4s,#8
+	ror	w17,w17,#24
+	add	v2.4s,v2.4s,v3.4s
+	ror	w19,w19,#24
+	add	v6.4s,v6.4s,v7.4s
+	ror	w20,w20,#24
+	add	v18.4s,v18.4s,v19.4s
+	ror	w21,w21,#24
+	eor	v20.16b,v1.16b,v2.16b
+	add	w13,w13,w17
+	eor	v21.16b,v5.16b,v6.16b
+	add	w14,w14,w19
+	eor	v22.16b,v17.16b,v18.16b
+	add	w15,w15,w20
+	ushr	v1.4s,v20.4s,#25
+	add	w16,w16,w21
+	ushr	v5.4s,v21.4s,#25
+	eor	w9,w9,w13
+	ushr	v17.4s,v22.4s,#25
+	eor	w10,w10,w14
+	sli	v1.4s,v20.4s,#7
+	eor	w11,w11,w15
+	sli	v5.4s,v21.4s,#7
+	eor	w12,w12,w16
+	sli	v17.4s,v22.4s,#7
+	ror	w9,w9,#25
+	ext	v2.16b,v2.16b,v2.16b,#8
+	ror	w10,w10,#25
+	ext	v6.16b,v6.16b,v6.16b,#8
+	ror	w11,w11,#25
+	ext	v18.16b,v18.16b,v18.16b,#8
+	ror	w12,w12,#25
+	ext	v3.16b,v3.16b,v3.16b,#12
+	ext	v7.16b,v7.16b,v7.16b,#12
+	ext	v19.16b,v19.16b,v19.16b,#12
+	ext	v1.16b,v1.16b,v1.16b,#4
+	ext	v5.16b,v5.16b,v5.16b,#4
+	ext	v17.16b,v17.16b,v17.16b,#4
+	add	v0.4s,v0.4s,v1.4s
+	add	w5,w5,w10
+	add	v4.4s,v4.4s,v5.4s
+	add	w6,w6,w11
+	add	v16.4s,v16.4s,v17.4s
+	add	w7,w7,w12
+	eor	v3.16b,v3.16b,v0.16b
+	add	w8,w8,w9
+	eor	v7.16b,v7.16b,v4.16b
+	eor	w21,w21,w5
+	eor	v19.16b,v19.16b,v16.16b
+	eor	w17,w17,w6
+	rev32	v3.8h,v3.8h
+	eor	w19,w19,w7
+	rev32	v7.8h,v7.8h
+	eor	w20,w20,w8
+	rev32	v19.8h,v19.8h
+	ror	w21,w21,#16
+	add	v2.4s,v2.4s,v3.4s
+	ror	w17,w17,#16
+	add	v6.4s,v6.4s,v7.4s
+	ror	w19,w19,#16
+	add	v18.4s,v18.4s,v19.4s
+	ror	w20,w20,#16
+	eor	v20.16b,v1.16b,v2.16b
+	add	w15,w15,w21
+	eor	v21.16b,v5.16b,v6.16b
+	add	w16,w16,w17
+	eor	v22.16b,v17.16b,v18.16b
+	add	w13,w13,w19
+	ushr	v1.4s,v20.4s,#20
+	add	w14,w14,w20
+	ushr	v5.4s,v21.4s,#20
+	eor	w10,w10,w15
+	ushr	v17.4s,v22.4s,#20
+	eor	w11,w11,w16
+	sli	v1.4s,v20.4s,#12
+	eor	w12,w12,w13
+	sli	v5.4s,v21.4s,#12
+	eor	w9,w9,w14
+	sli	v17.4s,v22.4s,#12
+	ror	w10,w10,#20
+	add	v0.4s,v0.4s,v1.4s
+	ror	w11,w11,#20
+	add	v4.4s,v4.4s,v5.4s
+	ror	w12,w12,#20
+	add	v16.4s,v16.4s,v17.4s
+	ror	w9,w9,#20
+	eor	v20.16b,v3.16b,v0.16b
+	add	w5,w5,w10
+	eor	v21.16b,v7.16b,v4.16b
+	add	w6,w6,w11
+	eor	v22.16b,v19.16b,v16.16b
+	add	w7,w7,w12
+	ushr	v3.4s,v20.4s,#24
+	add	w8,w8,w9
+	ushr	v7.4s,v21.4s,#24
+	eor	w21,w21,w5
+	ushr	v19.4s,v22.4s,#24
+	eor	w17,w17,w6
+	sli	v3.4s,v20.4s,#8
+	eor	w19,w19,w7
+	sli	v7.4s,v21.4s,#8
+	eor	w20,w20,w8
+	sli	v19.4s,v22.4s,#8
+	ror	w21,w21,#24
+	add	v2.4s,v2.4s,v3.4s
+	ror	w17,w17,#24
+	add	v6.4s,v6.4s,v7.4s
+	ror	w19,w19,#24
+	add	v18.4s,v18.4s,v19.4s
+	ror	w20,w20,#24
+	eor	v20.16b,v1.16b,v2.16b
+	add	w15,w15,w21
+	eor	v21.16b,v5.16b,v6.16b
+	add	w16,w16,w17
+	eor	v22.16b,v17.16b,v18.16b
+	add	w13,w13,w19
+	ushr	v1.4s,v20.4s,#25
+	add	w14,w14,w20
+	ushr	v5.4s,v21.4s,#25
+	eor	w10,w10,w15
+	ushr	v17.4s,v22.4s,#25
+	eor	w11,w11,w16
+	sli	v1.4s,v20.4s,#7
+	eor	w12,w12,w13
+	sli	v5.4s,v21.4s,#7
+	eor	w9,w9,w14
+	sli	v17.4s,v22.4s,#7
+	ror	w10,w10,#25
+	ext	v2.16b,v2.16b,v2.16b,#8
+	ror	w11,w11,#25
+	ext	v6.16b,v6.16b,v6.16b,#8
+	ror	w12,w12,#25
+	ext	v18.16b,v18.16b,v18.16b,#8
+	ror	w9,w9,#25
+	ext	v3.16b,v3.16b,v3.16b,#4
+	ext	v7.16b,v7.16b,v7.16b,#4
+	ext	v19.16b,v19.16b,v19.16b,#4
+	ext	v1.16b,v1.16b,v1.16b,#12
+	ext	v5.16b,v5.16b,v5.16b,#12
+	ext	v17.16b,v17.16b,v17.16b,#12
+	cbnz	x4,.Loop_neon
+
+	add	w5,w5,w22		// accumulate key block
+	add	v0.4s,v0.4s,v24.4s
+	add	x6,x6,x22,lsr#32
+	add	v4.4s,v4.4s,v24.4s
+	add	w7,w7,w23
+	add	v16.4s,v16.4s,v24.4s
+	add	x8,x8,x23,lsr#32
+	add	v2.4s,v2.4s,v26.4s
+	add	w9,w9,w24
+	add	v6.4s,v6.4s,v26.4s
+	add	x10,x10,x24,lsr#32
+	add	v18.4s,v18.4s,v26.4s
+	add	w11,w11,w25
+	add	v3.4s,v3.4s,v27.4s
+	add	x12,x12,x25,lsr#32
+	add	w13,w13,w26
+	add	v7.4s,v7.4s,v28.4s
+	add	x14,x14,x26,lsr#32
+	add	w15,w15,w27
+	add	v19.4s,v19.4s,v29.4s
+	add	x16,x16,x27,lsr#32
+	add	w17,w17,w28
+	add	v1.4s,v1.4s,v25.4s
+	add	x19,x19,x28,lsr#32
+	add	w20,w20,w30
+	add	v5.4s,v5.4s,v25.4s
+	add	x21,x21,x30,lsr#32
+	add	v17.4s,v17.4s,v25.4s
+
+	b.lo	.Ltail_neon
+
+	add	x5,x5,x6,lsl#32	// pack
+	add	x7,x7,x8,lsl#32
+	ldp	x6,x8,[x1,#0]		// load input
+	add	x9,x9,x10,lsl#32
+	add	x11,x11,x12,lsl#32
+	ldp	x10,x12,[x1,#16]
+	add	x13,x13,x14,lsl#32
+	add	x15,x15,x16,lsl#32
+	ldp	x14,x16,[x1,#32]
+	add	x17,x17,x19,lsl#32
+	add	x20,x20,x21,lsl#32
+	ldp	x19,x21,[x1,#48]
+	add	x1,x1,#64
+#ifdef	__ARMEB__
+	rev	x5,x5
+	rev	x7,x7
+	rev	x9,x9
+	rev	x11,x11
+	rev	x13,x13
+	rev	x15,x15
+	rev	x17,x17
+	rev	x20,x20
+#endif
+	ld1	{v20.16b,v21.16b,v22.16b,v23.16b},[x1],#64
+	eor	x5,x5,x6
+	eor	x7,x7,x8
+	eor	x9,x9,x10
+	eor	x11,x11,x12
+	eor	x13,x13,x14
+	eor	v0.16b,v0.16b,v20.16b
+	eor	x15,x15,x16
+	eor	v1.16b,v1.16b,v21.16b
+	eor	x17,x17,x19
+	eor	v2.16b,v2.16b,v22.16b
+	eor	x20,x20,x21
+	eor	v3.16b,v3.16b,v23.16b
+	ld1	{v20.16b,v21.16b,v22.16b,v23.16b},[x1],#64
+
+	stp	x5,x7,[x0,#0]		// store output
+	add	x28,x28,#4			// increment counter
+	stp	x9,x11,[x0,#16]
+	add	v27.4s,v27.4s,v31.4s		// += 4
+	stp	x13,x15,[x0,#32]
+	add	v28.4s,v28.4s,v31.4s
+	stp	x17,x20,[x0,#48]
+	add	v29.4s,v29.4s,v31.4s
+	add	x0,x0,#64
+
+	st1	{v0.16b,v1.16b,v2.16b,v3.16b},[x0],#64
+	ld1	{v0.16b,v1.16b,v2.16b,v3.16b},[x1],#64
+
+	eor	v4.16b,v4.16b,v20.16b
+	eor	v5.16b,v5.16b,v21.16b
+	eor	v6.16b,v6.16b,v22.16b
+	eor	v7.16b,v7.16b,v23.16b
+	st1	{v4.16b,v5.16b,v6.16b,v7.16b},[x0],#64
+
+	eor	v16.16b,v16.16b,v0.16b
+	eor	v17.16b,v17.16b,v1.16b
+	eor	v18.16b,v18.16b,v2.16b
+	eor	v19.16b,v19.16b,v3.16b
+	st1	{v16.16b,v17.16b,v18.16b,v19.16b},[x0],#64
+
+	b.hi	.Loop_outer_neon
+
+	ldp	x19,x20,[x29,#16]
+	add	sp,sp,#64
+	ldp	x21,x22,[x29,#32]
+	ldp	x23,x24,[x29,#48]
+	ldp	x25,x26,[x29,#64]
+	ldp	x27,x28,[x29,#80]
+	ldp	x29,x30,[sp],#96
+	ret
+
+.Ltail_neon:
+	add	x2,x2,#256
+	cmp	x2,#64
+	b.lo	.Less_than_64
+
+	add	x5,x5,x6,lsl#32	// pack
+	add	x7,x7,x8,lsl#32
+	ldp	x6,x8,[x1,#0]		// load input
+	add	x9,x9,x10,lsl#32
+	add	x11,x11,x12,lsl#32
+	ldp	x10,x12,[x1,#16]
+	add	x13,x13,x14,lsl#32
+	add	x15,x15,x16,lsl#32
+	ldp	x14,x16,[x1,#32]
+	add	x17,x17,x19,lsl#32
+	add	x20,x20,x21,lsl#32
+	ldp	x19,x21,[x1,#48]
+	add	x1,x1,#64
+#ifdef	__ARMEB__
+	rev	x5,x5
+	rev	x7,x7
+	rev	x9,x9
+	rev	x11,x11
+	rev	x13,x13
+	rev	x15,x15
+	rev	x17,x17
+	rev	x20,x20
+#endif
+	eor	x5,x5,x6
+	eor	x7,x7,x8
+	eor	x9,x9,x10
+	eor	x11,x11,x12
+	eor	x13,x13,x14
+	eor	x15,x15,x16
+	eor	x17,x17,x19
+	eor	x20,x20,x21
+
+	stp	x5,x7,[x0,#0]		// store output
+	add	x28,x28,#4			// increment counter
+	stp	x9,x11,[x0,#16]
+	stp	x13,x15,[x0,#32]
+	stp	x17,x20,[x0,#48]
+	add	x0,x0,#64
+	b.eq	.Ldone_neon
+	sub	x2,x2,#64
+	cmp	x2,#64
+	b.lo	.Less_than_128
+
+	ld1	{v20.16b,v21.16b,v22.16b,v23.16b},[x1],#64
+	eor	v0.16b,v0.16b,v20.16b
+	eor	v1.16b,v1.16b,v21.16b
+	eor	v2.16b,v2.16b,v22.16b
+	eor	v3.16b,v3.16b,v23.16b
+	st1	{v0.16b,v1.16b,v2.16b,v3.16b},[x0],#64
+	b.eq	.Ldone_neon
+	sub	x2,x2,#64
+	cmp	x2,#64
+	b.lo	.Less_than_192
+
+	ld1	{v20.16b,v21.16b,v22.16b,v23.16b},[x1],#64
+	eor	v4.16b,v4.16b,v20.16b
+	eor	v5.16b,v5.16b,v21.16b
+	eor	v6.16b,v6.16b,v22.16b
+	eor	v7.16b,v7.16b,v23.16b
+	st1	{v4.16b,v5.16b,v6.16b,v7.16b},[x0],#64
+	b.eq	.Ldone_neon
+	sub	x2,x2,#64
+
+	st1	{v16.16b,v17.16b,v18.16b,v19.16b},[sp]
+	b	.Last_neon
+
+.Less_than_128:
+	st1	{v0.16b,v1.16b,v2.16b,v3.16b},[sp]
+	b	.Last_neon
+.Less_than_192:
+	st1	{v4.16b,v5.16b,v6.16b,v7.16b},[sp]
+	b	.Last_neon
+
+.align	4
+.Last_neon:
+	sub	x0,x0,#1
+	add	x1,x1,x2
+	add	x0,x0,x2
+	add	x4,sp,x2
+	neg	x2,x2
+
+.Loop_tail_neon:
+	ldrb	w10,[x1,x2]
+	ldrb	w11,[x4,x2]
+	add	x2,x2,#1
+	eor	w10,w10,w11
+	strb	w10,[x0,x2]
+	cbnz	x2,.Loop_tail_neon
+
+	stp	xzr,xzr,[sp,#0]
+	stp	xzr,xzr,[sp,#16]
+	stp	xzr,xzr,[sp,#32]
+	stp	xzr,xzr,[sp,#48]
+
+.Ldone_neon:
+	ldp	x19,x20,[x29,#16]
+	add	sp,sp,#64
+	ldp	x21,x22,[x29,#32]
+	ldp	x23,x24,[x29,#48]
+	ldp	x25,x26,[x29,#64]
+	ldp	x27,x28,[x29,#80]
+	ldp	x29,x30,[sp],#96
+	ret
+.size	ChaCha20_neon,.-ChaCha20_neon
+.type	ChaCha20_512_neon,%function
+.align	5
+ChaCha20_512_neon:
+	stp	x29,x30,[sp,#-96]!
+	add	x29,sp,#0
+
+	adr	x5,.Lsigma
+	stp	x19,x20,[sp,#16]
+	stp	x21,x22,[sp,#32]
+	stp	x23,x24,[sp,#48]
+	stp	x25,x26,[sp,#64]
+	stp	x27,x28,[sp,#80]
+
+.L512_or_more_neon:
+	sub	sp,sp,#128+64
+
+	ldp	x22,x23,[x5]		// load sigma
+	ld1	{v24.4s},[x5],#16
+	ldp	x24,x25,[x3]		// load key
+	ldp	x26,x27,[x3,#16]
+	ld1	{v25.4s,v26.4s},[x3]
+	ldp	x28,x30,[x4]		// load counter
+	ld1	{v27.4s},[x4]
+	ld1	{v31.4s},[x5]
+#ifdef	__ARMEB__
+	rev64	v24.4s,v24.4s
+	ror	x24,x24,#32
+	ror	x25,x25,#32
+	ror	x26,x26,#32
+	ror	x27,x27,#32
+	ror	x28,x28,#32
+	ror	x30,x30,#32
+#endif
+	add	v27.4s,v27.4s,v31.4s		// += 1
+	stp	q24,q25,[sp,#0]		// off-load key block, invariant part
+	add	v27.4s,v27.4s,v31.4s		// not typo
+	str	q26,[sp,#32]
+	add	v28.4s,v27.4s,v31.4s
+	add	v29.4s,v28.4s,v31.4s
+	add	v30.4s,v29.4s,v31.4s
+	shl	v31.4s,v31.4s,#2			// 1 -> 4
+
+	stp	d8,d9,[sp,#128+0]		// meet ABI requirements
+	stp	d10,d11,[sp,#128+16]
+	stp	d12,d13,[sp,#128+32]
+	stp	d14,d15,[sp,#128+48]
+
+	sub	x2,x2,#512			// not typo
+
+.Loop_outer_512_neon:
+	mov	v0.16b,v24.16b
+	mov	v4.16b,v24.16b
+	mov	v8.16b,v24.16b
+	mov	v12.16b,v24.16b
+	mov	v16.16b,v24.16b
+	mov	v20.16b,v24.16b
+	mov	v1.16b,v25.16b
+	mov	w5,w22			// unpack key block
+	mov	v5.16b,v25.16b
+	lsr	x6,x22,#32
+	mov	v9.16b,v25.16b
+	mov	w7,w23
+	mov	v13.16b,v25.16b
+	lsr	x8,x23,#32
+	mov	v17.16b,v25.16b
+	mov	w9,w24
+	mov	v21.16b,v25.16b
+	lsr	x10,x24,#32
+	mov	v3.16b,v27.16b
+	mov	w11,w25
+	mov	v7.16b,v28.16b
+	lsr	x12,x25,#32
+	mov	v11.16b,v29.16b
+	mov	w13,w26
+	mov	v15.16b,v30.16b
+	lsr	x14,x26,#32
+	mov	v2.16b,v26.16b
+	mov	w15,w27
+	mov	v6.16b,v26.16b
+	lsr	x16,x27,#32
+	add	v19.4s,v3.4s,v31.4s			// +4
+	mov	w17,w28
+	add	v23.4s,v7.4s,v31.4s			// +4
+	lsr	x19,x28,#32
+	mov	v10.16b,v26.16b
+	mov	w20,w30
+	mov	v14.16b,v26.16b
+	lsr	x21,x30,#32
+	mov	v18.16b,v26.16b
+	stp	q27,q28,[sp,#48]		// off-load key block, variable part
+	mov	v22.16b,v26.16b
+	str	q29,[sp,#80]
+
+	mov	x4,#5
+	subs	x2,x2,#512
+.Loop_upper_neon:
+	sub	x4,x4,#1
+	add	v0.4s,v0.4s,v1.4s
+	add	w5,w5,w9
+	add	v4.4s,v4.4s,v5.4s
+	add	w6,w6,w10
+	add	v8.4s,v8.4s,v9.4s
+	add	w7,w7,w11
+	add	v12.4s,v12.4s,v13.4s
+	add	w8,w8,w12
+	add	v16.4s,v16.4s,v17.4s
+	eor	w17,w17,w5
+	add	v20.4s,v20.4s,v21.4s
+	eor	w19,w19,w6
+	eor	v3.16b,v3.16b,v0.16b
+	eor	w20,w20,w7
+	eor	v7.16b,v7.16b,v4.16b
+	eor	w21,w21,w8
+	eor	v11.16b,v11.16b,v8.16b
+	ror	w17,w17,#16
+	eor	v15.16b,v15.16b,v12.16b
+	ror	w19,w19,#16
+	eor	v19.16b,v19.16b,v16.16b
+	ror	w20,w20,#16
+	eor	v23.16b,v23.16b,v20.16b
+	ror	w21,w21,#16
+	rev32	v3.8h,v3.8h
+	add	w13,w13,w17
+	rev32	v7.8h,v7.8h
+	add	w14,w14,w19
+	rev32	v11.8h,v11.8h
+	add	w15,w15,w20
+	rev32	v15.8h,v15.8h
+	add	w16,w16,w21
+	rev32	v19.8h,v19.8h
+	eor	w9,w9,w13
+	rev32	v23.8h,v23.8h
+	eor	w10,w10,w14
+	add	v2.4s,v2.4s,v3.4s
+	eor	w11,w11,w15
+	add	v6.4s,v6.4s,v7.4s
+	eor	w12,w12,w16
+	add	v10.4s,v10.4s,v11.4s
+	ror	w9,w9,#20
+	add	v14.4s,v14.4s,v15.4s
+	ror	w10,w10,#20
+	add	v18.4s,v18.4s,v19.4s
+	ror	w11,w11,#20
+	add	v22.4s,v22.4s,v23.4s
+	ror	w12,w12,#20
+	eor	v24.16b,v1.16b,v2.16b
+	add	w5,w5,w9
+	eor	v25.16b,v5.16b,v6.16b
+	add	w6,w6,w10
+	eor	v26.16b,v9.16b,v10.16b
+	add	w7,w7,w11
+	eor	v27.16b,v13.16b,v14.16b
+	add	w8,w8,w12
+	eor	v28.16b,v17.16b,v18.16b
+	eor	w17,w17,w5
+	eor	v29.16b,v21.16b,v22.16b
+	eor	w19,w19,w6
+	ushr	v1.4s,v24.4s,#20
+	eor	w20,w20,w7
+	ushr	v5.4s,v25.4s,#20
+	eor	w21,w21,w8
+	ushr	v9.4s,v26.4s,#20
+	ror	w17,w17,#24
+	ushr	v13.4s,v27.4s,#20
+	ror	w19,w19,#24
+	ushr	v17.4s,v28.4s,#20
+	ror	w20,w20,#24
+	ushr	v21.4s,v29.4s,#20
+	ror	w21,w21,#24
+	sli	v1.4s,v24.4s,#12
+	add	w13,w13,w17
+	sli	v5.4s,v25.4s,#12
+	add	w14,w14,w19
+	sli	v9.4s,v26.4s,#12
+	add	w15,w15,w20
+	sli	v13.4s,v27.4s,#12
+	add	w16,w16,w21
+	sli	v17.4s,v28.4s,#12
+	eor	w9,w9,w13
+	sli	v21.4s,v29.4s,#12
+	eor	w10,w10,w14
+	add	v0.4s,v0.4s,v1.4s
+	eor	w11,w11,w15
+	add	v4.4s,v4.4s,v5.4s
+	eor	w12,w12,w16
+	add	v8.4s,v8.4s,v9.4s
+	ror	w9,w9,#25
+	add	v12.4s,v12.4s,v13.4s
+	ror	w10,w10,#25
+	add	v16.4s,v16.4s,v17.4s
+	ror	w11,w11,#25
+	add	v20.4s,v20.4s,v21.4s
+	ror	w12,w12,#25
+	eor	v24.16b,v3.16b,v0.16b
+	add	w5,w5,w10
+	eor	v25.16b,v7.16b,v4.16b
+	add	w6,w6,w11
+	eor	v26.16b,v11.16b,v8.16b
+	add	w7,w7,w12
+	eor	v27.16b,v15.16b,v12.16b
+	add	w8,w8,w9
+	eor	v28.16b,v19.16b,v16.16b
+	eor	w21,w21,w5
+	eor	v29.16b,v23.16b,v20.16b
+	eor	w17,w17,w6
+	ushr	v3.4s,v24.4s,#24
+	eor	w19,w19,w7
+	ushr	v7.4s,v25.4s,#24
+	eor	w20,w20,w8
+	ushr	v11.4s,v26.4s,#24
+	ror	w21,w21,#16
+	ushr	v15.4s,v27.4s,#24
+	ror	w17,w17,#16
+	ushr	v19.4s,v28.4s,#24
+	ror	w19,w19,#16
+	ushr	v23.4s,v29.4s,#24
+	ror	w20,w20,#16
+	sli	v3.4s,v24.4s,#8
+	add	w15,w15,w21
+	sli	v7.4s,v25.4s,#8
+	add	w16,w16,w17
+	sli	v11.4s,v26.4s,#8
+	add	w13,w13,w19
+	sli	v15.4s,v27.4s,#8
+	add	w14,w14,w20
+	sli	v19.4s,v28.4s,#8
+	eor	w10,w10,w15
+	sli	v23.4s,v29.4s,#8
+	eor	w11,w11,w16
+	add	v2.4s,v2.4s,v3.4s
+	eor	w12,w12,w13
+	add	v6.4s,v6.4s,v7.4s
+	eor	w9,w9,w14
+	add	v10.4s,v10.4s,v11.4s
+	ror	w10,w10,#20
+	add	v14.4s,v14.4s,v15.4s
+	ror	w11,w11,#20
+	add	v18.4s,v18.4s,v19.4s
+	ror	w12,w12,#20
+	add	v22.4s,v22.4s,v23.4s
+	ror	w9,w9,#20
+	eor	v24.16b,v1.16b,v2.16b
+	add	w5,w5,w10
+	eor	v25.16b,v5.16b,v6.16b
+	add	w6,w6,w11
+	eor	v26.16b,v9.16b,v10.16b
+	add	w7,w7,w12
+	eor	v27.16b,v13.16b,v14.16b
+	add	w8,w8,w9
+	eor	v28.16b,v17.16b,v18.16b
+	eor	w21,w21,w5
+	eor	v29.16b,v21.16b,v22.16b
+	eor	w17,w17,w6
+	ushr	v1.4s,v24.4s,#25
+	eor	w19,w19,w7
+	ushr	v5.4s,v25.4s,#25
+	eor	w20,w20,w8
+	ushr	v9.4s,v26.4s,#25
+	ror	w21,w21,#24
+	ushr	v13.4s,v27.4s,#25
+	ror	w17,w17,#24
+	ushr	v17.4s,v28.4s,#25
+	ror	w19,w19,#24
+	ushr	v21.4s,v29.4s,#25
+	ror	w20,w20,#24
+	sli	v1.4s,v24.4s,#7
+	add	w15,w15,w21
+	sli	v5.4s,v25.4s,#7
+	add	w16,w16,w17
+	sli	v9.4s,v26.4s,#7
+	add	w13,w13,w19
+	sli	v13.4s,v27.4s,#7
+	add	w14,w14,w20
+	sli	v17.4s,v28.4s,#7
+	eor	w10,w10,w15
+	sli	v21.4s,v29.4s,#7
+	eor	w11,w11,w16
+	ext	v2.16b,v2.16b,v2.16b,#8
+	eor	w12,w12,w13
+	ext	v6.16b,v6.16b,v6.16b,#8
+	eor	w9,w9,w14
+	ext	v10.16b,v10.16b,v10.16b,#8
+	ror	w10,w10,#25
+	ext	v14.16b,v14.16b,v14.16b,#8
+	ror	w11,w11,#25
+	ext	v18.16b,v18.16b,v18.16b,#8
+	ror	w12,w12,#25
+	ext	v22.16b,v22.16b,v22.16b,#8
+	ror	w9,w9,#25
+	ext	v3.16b,v3.16b,v3.16b,#12
+	ext	v7.16b,v7.16b,v7.16b,#12
+	ext	v11.16b,v11.16b,v11.16b,#12
+	ext	v15.16b,v15.16b,v15.16b,#12
+	ext	v19.16b,v19.16b,v19.16b,#12
+	ext	v23.16b,v23.16b,v23.16b,#12
+	ext	v1.16b,v1.16b,v1.16b,#4
+	ext	v5.16b,v5.16b,v5.16b,#4
+	ext	v9.16b,v9.16b,v9.16b,#4
+	ext	v13.16b,v13.16b,v13.16b,#4
+	ext	v17.16b,v17.16b,v17.16b,#4
+	ext	v21.16b,v21.16b,v21.16b,#4
+	add	v0.4s,v0.4s,v1.4s
+	add	w5,w5,w9
+	add	v4.4s,v4.4s,v5.4s
+	add	w6,w6,w10
+	add	v8.4s,v8.4s,v9.4s
+	add	w7,w7,w11
+	add	v12.4s,v12.4s,v13.4s
+	add	w8,w8,w12
+	add	v16.4s,v16.4s,v17.4s
+	eor	w17,w17,w5
+	add	v20.4s,v20.4s,v21.4s
+	eor	w19,w19,w6
+	eor	v3.16b,v3.16b,v0.16b
+	eor	w20,w20,w7
+	eor	v7.16b,v7.16b,v4.16b
+	eor	w21,w21,w8
+	eor	v11.16b,v11.16b,v8.16b
+	ror	w17,w17,#16
+	eor	v15.16b,v15.16b,v12.16b
+	ror	w19,w19,#16
+	eor	v19.16b,v19.16b,v16.16b
+	ror	w20,w20,#16
+	eor	v23.16b,v23.16b,v20.16b
+	ror	w21,w21,#16
+	rev32	v3.8h,v3.8h
+	add	w13,w13,w17
+	rev32	v7.8h,v7.8h
+	add	w14,w14,w19
+	rev32	v11.8h,v11.8h
+	add	w15,w15,w20
+	rev32	v15.8h,v15.8h
+	add	w16,w16,w21
+	rev32	v19.8h,v19.8h
+	eor	w9,w9,w13
+	rev32	v23.8h,v23.8h
+	eor	w10,w10,w14
+	add	v2.4s,v2.4s,v3.4s
+	eor	w11,w11,w15
+	add	v6.4s,v6.4s,v7.4s
+	eor	w12,w12,w16
+	add	v10.4s,v10.4s,v11.4s
+	ror	w9,w9,#20
+	add	v14.4s,v14.4s,v15.4s
+	ror	w10,w10,#20
+	add	v18.4s,v18.4s,v19.4s
+	ror	w11,w11,#20
+	add	v22.4s,v22.4s,v23.4s
+	ror	w12,w12,#20
+	eor	v24.16b,v1.16b,v2.16b
+	add	w5,w5,w9
+	eor	v25.16b,v5.16b,v6.16b
+	add	w6,w6,w10
+	eor	v26.16b,v9.16b,v10.16b
+	add	w7,w7,w11
+	eor	v27.16b,v13.16b,v14.16b
+	add	w8,w8,w12
+	eor	v28.16b,v17.16b,v18.16b
+	eor	w17,w17,w5
+	eor	v29.16b,v21.16b,v22.16b
+	eor	w19,w19,w6
+	ushr	v1.4s,v24.4s,#20
+	eor	w20,w20,w7
+	ushr	v5.4s,v25.4s,#20
+	eor	w21,w21,w8
+	ushr	v9.4s,v26.4s,#20
+	ror	w17,w17,#24
+	ushr	v13.4s,v27.4s,#20
+	ror	w19,w19,#24
+	ushr	v17.4s,v28.4s,#20
+	ror	w20,w20,#24
+	ushr	v21.4s,v29.4s,#20
+	ror	w21,w21,#24
+	sli	v1.4s,v24.4s,#12
+	add	w13,w13,w17
+	sli	v5.4s,v25.4s,#12
+	add	w14,w14,w19
+	sli	v9.4s,v26.4s,#12
+	add	w15,w15,w20
+	sli	v13.4s,v27.4s,#12
+	add	w16,w16,w21
+	sli	v17.4s,v28.4s,#12
+	eor	w9,w9,w13
+	sli	v21.4s,v29.4s,#12
+	eor	w10,w10,w14
+	add	v0.4s,v0.4s,v1.4s
+	eor	w11,w11,w15
+	add	v4.4s,v4.4s,v5.4s
+	eor	w12,w12,w16
+	add	v8.4s,v8.4s,v9.4s
+	ror	w9,w9,#25
+	add	v12.4s,v12.4s,v13.4s
+	ror	w10,w10,#25
+	add	v16.4s,v16.4s,v17.4s
+	ror	w11,w11,#25
+	add	v20.4s,v20.4s,v21.4s
+	ror	w12,w12,#25
+	eor	v24.16b,v3.16b,v0.16b
+	add	w5,w5,w10
+	eor	v25.16b,v7.16b,v4.16b
+	add	w6,w6,w11
+	eor	v26.16b,v11.16b,v8.16b
+	add	w7,w7,w12
+	eor	v27.16b,v15.16b,v12.16b
+	add	w8,w8,w9
+	eor	v28.16b,v19.16b,v16.16b
+	eor	w21,w21,w5
+	eor	v29.16b,v23.16b,v20.16b
+	eor	w17,w17,w6
+	ushr	v3.4s,v24.4s,#24
+	eor	w19,w19,w7
+	ushr	v7.4s,v25.4s,#24
+	eor	w20,w20,w8
+	ushr	v11.4s,v26.4s,#24
+	ror	w21,w21,#16
+	ushr	v15.4s,v27.4s,#24
+	ror	w17,w17,#16
+	ushr	v19.4s,v28.4s,#24
+	ror	w19,w19,#16
+	ushr	v23.4s,v29.4s,#24
+	ror	w20,w20,#16
+	sli	v3.4s,v24.4s,#8
+	add	w15,w15,w21
+	sli	v7.4s,v25.4s,#8
+	add	w16,w16,w17
+	sli	v11.4s,v26.4s,#8
+	add	w13,w13,w19
+	sli	v15.4s,v27.4s,#8
+	add	w14,w14,w20
+	sli	v19.4s,v28.4s,#8
+	eor	w10,w10,w15
+	sli	v23.4s,v29.4s,#8
+	eor	w11,w11,w16
+	add	v2.4s,v2.4s,v3.4s
+	eor	w12,w12,w13
+	add	v6.4s,v6.4s,v7.4s
+	eor	w9,w9,w14
+	add	v10.4s,v10.4s,v11.4s
+	ror	w10,w10,#20
+	add	v14.4s,v14.4s,v15.4s
+	ror	w11,w11,#20
+	add	v18.4s,v18.4s,v19.4s
+	ror	w12,w12,#20
+	add	v22.4s,v22.4s,v23.4s
+	ror	w9,w9,#20
+	eor	v24.16b,v1.16b,v2.16b
+	add	w5,w5,w10
+	eor	v25.16b,v5.16b,v6.16b
+	add	w6,w6,w11
+	eor	v26.16b,v9.16b,v10.16b
+	add	w7,w7,w12
+	eor	v27.16b,v13.16b,v14.16b
+	add	w8,w8,w9
+	eor	v28.16b,v17.16b,v18.16b
+	eor	w21,w21,w5
+	eor	v29.16b,v21.16b,v22.16b
+	eor	w17,w17,w6
+	ushr	v1.4s,v24.4s,#25
+	eor	w19,w19,w7
+	ushr	v5.4s,v25.4s,#25
+	eor	w20,w20,w8
+	ushr	v9.4s,v26.4s,#25
+	ror	w21,w21,#24
+	ushr	v13.4s,v27.4s,#25
+	ror	w17,w17,#24
+	ushr	v17.4s,v28.4s,#25
+	ror	w19,w19,#24
+	ushr	v21.4s,v29.4s,#25
+	ror	w20,w20,#24
+	sli	v1.4s,v24.4s,#7
+	add	w15,w15,w21
+	sli	v5.4s,v25.4s,#7
+	add	w16,w16,w17
+	sli	v9.4s,v26.4s,#7
+	add	w13,w13,w19
+	sli	v13.4s,v27.4s,#7
+	add	w14,w14,w20
+	sli	v17.4s,v28.4s,#7
+	eor	w10,w10,w15
+	sli	v21.4s,v29.4s,#7
+	eor	w11,w11,w16
+	ext	v2.16b,v2.16b,v2.16b,#8
+	eor	w12,w12,w13
+	ext	v6.16b,v6.16b,v6.16b,#8
+	eor	w9,w9,w14
+	ext	v10.16b,v10.16b,v10.16b,#8
+	ror	w10,w10,#25
+	ext	v14.16b,v14.16b,v14.16b,#8
+	ror	w11,w11,#25
+	ext	v18.16b,v18.16b,v18.16b,#8
+	ror	w12,w12,#25
+	ext	v22.16b,v22.16b,v22.16b,#8
+	ror	w9,w9,#25
+	ext	v3.16b,v3.16b,v3.16b,#4
+	ext	v7.16b,v7.16b,v7.16b,#4
+	ext	v11.16b,v11.16b,v11.16b,#4
+	ext	v15.16b,v15.16b,v15.16b,#4
+	ext	v19.16b,v19.16b,v19.16b,#4
+	ext	v23.16b,v23.16b,v23.16b,#4
+	ext	v1.16b,v1.16b,v1.16b,#12
+	ext	v5.16b,v5.16b,v5.16b,#12
+	ext	v9.16b,v9.16b,v9.16b,#12
+	ext	v13.16b,v13.16b,v13.16b,#12
+	ext	v17.16b,v17.16b,v17.16b,#12
+	ext	v21.16b,v21.16b,v21.16b,#12
+	cbnz	x4,.Loop_upper_neon
+
+	add	w5,w5,w22		// accumulate key block
+	add	x6,x6,x22,lsr#32
+	add	w7,w7,w23
+	add	x8,x8,x23,lsr#32
+	add	w9,w9,w24
+	add	x10,x10,x24,lsr#32
+	add	w11,w11,w25
+	add	x12,x12,x25,lsr#32
+	add	w13,w13,w26
+	add	x14,x14,x26,lsr#32
+	add	w15,w15,w27
+	add	x16,x16,x27,lsr#32
+	add	w17,w17,w28
+	add	x19,x19,x28,lsr#32
+	add	w20,w20,w30
+	add	x21,x21,x30,lsr#32
+
+	add	x5,x5,x6,lsl#32	// pack
+	add	x7,x7,x8,lsl#32
+	ldp	x6,x8,[x1,#0]		// load input
+	add	x9,x9,x10,lsl#32
+	add	x11,x11,x12,lsl#32
+	ldp	x10,x12,[x1,#16]
+	add	x13,x13,x14,lsl#32
+	add	x15,x15,x16,lsl#32
+	ldp	x14,x16,[x1,#32]
+	add	x17,x17,x19,lsl#32
+	add	x20,x20,x21,lsl#32
+	ldp	x19,x21,[x1,#48]
+	add	x1,x1,#64
+#ifdef	__ARMEB__
+	rev	x5,x5
+	rev	x7,x7
+	rev	x9,x9
+	rev	x11,x11
+	rev	x13,x13
+	rev	x15,x15
+	rev	x17,x17
+	rev	x20,x20
+#endif
+	eor	x5,x5,x6
+	eor	x7,x7,x8
+	eor	x9,x9,x10
+	eor	x11,x11,x12
+	eor	x13,x13,x14
+	eor	x15,x15,x16
+	eor	x17,x17,x19
+	eor	x20,x20,x21
+
+	stp	x5,x7,[x0,#0]		// store output
+	add	x28,x28,#1			// increment counter
+	mov	w5,w22			// unpack key block
+	lsr	x6,x22,#32
+	stp	x9,x11,[x0,#16]
+	mov	w7,w23
+	lsr	x8,x23,#32
+	stp	x13,x15,[x0,#32]
+	mov	w9,w24
+	lsr	x10,x24,#32
+	stp	x17,x20,[x0,#48]
+	add	x0,x0,#64
+	mov	w11,w25
+	lsr	x12,x25,#32
+	mov	w13,w26
+	lsr	x14,x26,#32
+	mov	w15,w27
+	lsr	x16,x27,#32
+	mov	w17,w28
+	lsr	x19,x28,#32
+	mov	w20,w30
+	lsr	x21,x30,#32
+
+	mov	x4,#5
+.Loop_lower_neon:
+	sub	x4,x4,#1
+	add	v0.4s,v0.4s,v1.4s
+	add	w5,w5,w9
+	add	v4.4s,v4.4s,v5.4s
+	add	w6,w6,w10
+	add	v8.4s,v8.4s,v9.4s
+	add	w7,w7,w11
+	add	v12.4s,v12.4s,v13.4s
+	add	w8,w8,w12
+	add	v16.4s,v16.4s,v17.4s
+	eor	w17,w17,w5
+	add	v20.4s,v20.4s,v21.4s
+	eor	w19,w19,w6
+	eor	v3.16b,v3.16b,v0.16b
+	eor	w20,w20,w7
+	eor	v7.16b,v7.16b,v4.16b
+	eor	w21,w21,w8
+	eor	v11.16b,v11.16b,v8.16b
+	ror	w17,w17,#16
+	eor	v15.16b,v15.16b,v12.16b
+	ror	w19,w19,#16
+	eor	v19.16b,v19.16b,v16.16b
+	ror	w20,w20,#16
+	eor	v23.16b,v23.16b,v20.16b
+	ror	w21,w21,#16
+	rev32	v3.8h,v3.8h
+	add	w13,w13,w17
+	rev32	v7.8h,v7.8h
+	add	w14,w14,w19
+	rev32	v11.8h,v11.8h
+	add	w15,w15,w20
+	rev32	v15.8h,v15.8h
+	add	w16,w16,w21
+	rev32	v19.8h,v19.8h
+	eor	w9,w9,w13
+	rev32	v23.8h,v23.8h
+	eor	w10,w10,w14
+	add	v2.4s,v2.4s,v3.4s
+	eor	w11,w11,w15
+	add	v6.4s,v6.4s,v7.4s
+	eor	w12,w12,w16
+	add	v10.4s,v10.4s,v11.4s
+	ror	w9,w9,#20
+	add	v14.4s,v14.4s,v15.4s
+	ror	w10,w10,#20
+	add	v18.4s,v18.4s,v19.4s
+	ror	w11,w11,#20
+	add	v22.4s,v22.4s,v23.4s
+	ror	w12,w12,#20
+	eor	v24.16b,v1.16b,v2.16b
+	add	w5,w5,w9
+	eor	v25.16b,v5.16b,v6.16b
+	add	w6,w6,w10
+	eor	v26.16b,v9.16b,v10.16b
+	add	w7,w7,w11
+	eor	v27.16b,v13.16b,v14.16b
+	add	w8,w8,w12
+	eor	v28.16b,v17.16b,v18.16b
+	eor	w17,w17,w5
+	eor	v29.16b,v21.16b,v22.16b
+	eor	w19,w19,w6
+	ushr	v1.4s,v24.4s,#20
+	eor	w20,w20,w7
+	ushr	v5.4s,v25.4s,#20
+	eor	w21,w21,w8
+	ushr	v9.4s,v26.4s,#20
+	ror	w17,w17,#24
+	ushr	v13.4s,v27.4s,#20
+	ror	w19,w19,#24
+	ushr	v17.4s,v28.4s,#20
+	ror	w20,w20,#24
+	ushr	v21.4s,v29.4s,#20
+	ror	w21,w21,#24
+	sli	v1.4s,v24.4s,#12
+	add	w13,w13,w17
+	sli	v5.4s,v25.4s,#12
+	add	w14,w14,w19
+	sli	v9.4s,v26.4s,#12
+	add	w15,w15,w20
+	sli	v13.4s,v27.4s,#12
+	add	w16,w16,w21
+	sli	v17.4s,v28.4s,#12
+	eor	w9,w9,w13
+	sli	v21.4s,v29.4s,#12
+	eor	w10,w10,w14
+	add	v0.4s,v0.4s,v1.4s
+	eor	w11,w11,w15
+	add	v4.4s,v4.4s,v5.4s
+	eor	w12,w12,w16
+	add	v8.4s,v8.4s,v9.4s
+	ror	w9,w9,#25
+	add	v12.4s,v12.4s,v13.4s
+	ror	w10,w10,#25
+	add	v16.4s,v16.4s,v17.4s
+	ror	w11,w11,#25
+	add	v20.4s,v20.4s,v21.4s
+	ror	w12,w12,#25
+	eor	v24.16b,v3.16b,v0.16b
+	add	w5,w5,w10
+	eor	v25.16b,v7.16b,v4.16b
+	add	w6,w6,w11
+	eor	v26.16b,v11.16b,v8.16b
+	add	w7,w7,w12
+	eor	v27.16b,v15.16b,v12.16b
+	add	w8,w8,w9
+	eor	v28.16b,v19.16b,v16.16b
+	eor	w21,w21,w5
+	eor	v29.16b,v23.16b,v20.16b
+	eor	w17,w17,w6
+	ushr	v3.4s,v24.4s,#24
+	eor	w19,w19,w7
+	ushr	v7.4s,v25.4s,#24
+	eor	w20,w20,w8
+	ushr	v11.4s,v26.4s,#24
+	ror	w21,w21,#16
+	ushr	v15.4s,v27.4s,#24
+	ror	w17,w17,#16
+	ushr	v19.4s,v28.4s,#24
+	ror	w19,w19,#16
+	ushr	v23.4s,v29.4s,#24
+	ror	w20,w20,#16
+	sli	v3.4s,v24.4s,#8
+	add	w15,w15,w21
+	sli	v7.4s,v25.4s,#8
+	add	w16,w16,w17
+	sli	v11.4s,v26.4s,#8
+	add	w13,w13,w19
+	sli	v15.4s,v27.4s,#8
+	add	w14,w14,w20
+	sli	v19.4s,v28.4s,#8
+	eor	w10,w10,w15
+	sli	v23.4s,v29.4s,#8
+	eor	w11,w11,w16
+	add	v2.4s,v2.4s,v3.4s
+	eor	w12,w12,w13
+	add	v6.4s,v6.4s,v7.4s
+	eor	w9,w9,w14
+	add	v10.4s,v10.4s,v11.4s
+	ror	w10,w10,#20
+	add	v14.4s,v14.4s,v15.4s
+	ror	w11,w11,#20
+	add	v18.4s,v18.4s,v19.4s
+	ror	w12,w12,#20
+	add	v22.4s,v22.4s,v23.4s
+	ror	w9,w9,#20
+	eor	v24.16b,v1.16b,v2.16b
+	add	w5,w5,w10
+	eor	v25.16b,v5.16b,v6.16b
+	add	w6,w6,w11
+	eor	v26.16b,v9.16b,v10.16b
+	add	w7,w7,w12
+	eor	v27.16b,v13.16b,v14.16b
+	add	w8,w8,w9
+	eor	v28.16b,v17.16b,v18.16b
+	eor	w21,w21,w5
+	eor	v29.16b,v21.16b,v22.16b
+	eor	w17,w17,w6
+	ushr	v1.4s,v24.4s,#25
+	eor	w19,w19,w7
+	ushr	v5.4s,v25.4s,#25
+	eor	w20,w20,w8
+	ushr	v9.4s,v26.4s,#25
+	ror	w21,w21,#24
+	ushr	v13.4s,v27.4s,#25
+	ror	w17,w17,#24
+	ushr	v17.4s,v28.4s,#25
+	ror	w19,w19,#24
+	ushr	v21.4s,v29.4s,#25
+	ror	w20,w20,#24
+	sli	v1.4s,v24.4s,#7
+	add	w15,w15,w21
+	sli	v5.4s,v25.4s,#7
+	add	w16,w16,w17
+	sli	v9.4s,v26.4s,#7
+	add	w13,w13,w19
+	sli	v13.4s,v27.4s,#7
+	add	w14,w14,w20
+	sli	v17.4s,v28.4s,#7
+	eor	w10,w10,w15
+	sli	v21.4s,v29.4s,#7
+	eor	w11,w11,w16
+	ext	v2.16b,v2.16b,v2.16b,#8
+	eor	w12,w12,w13
+	ext	v6.16b,v6.16b,v6.16b,#8
+	eor	w9,w9,w14
+	ext	v10.16b,v10.16b,v10.16b,#8
+	ror	w10,w10,#25
+	ext	v14.16b,v14.16b,v14.16b,#8
+	ror	w11,w11,#25
+	ext	v18.16b,v18.16b,v18.16b,#8
+	ror	w12,w12,#25
+	ext	v22.16b,v22.16b,v22.16b,#8
+	ror	w9,w9,#25
+	ext	v3.16b,v3.16b,v3.16b,#12
+	ext	v7.16b,v7.16b,v7.16b,#12
+	ext	v11.16b,v11.16b,v11.16b,#12
+	ext	v15.16b,v15.16b,v15.16b,#12
+	ext	v19.16b,v19.16b,v19.16b,#12
+	ext	v23.16b,v23.16b,v23.16b,#12
+	ext	v1.16b,v1.16b,v1.16b,#4
+	ext	v5.16b,v5.16b,v5.16b,#4
+	ext	v9.16b,v9.16b,v9.16b,#4
+	ext	v13.16b,v13.16b,v13.16b,#4
+	ext	v17.16b,v17.16b,v17.16b,#4
+	ext	v21.16b,v21.16b,v21.16b,#4
+	add	v0.4s,v0.4s,v1.4s
+	add	w5,w5,w9
+	add	v4.4s,v4.4s,v5.4s
+	add	w6,w6,w10
+	add	v8.4s,v8.4s,v9.4s
+	add	w7,w7,w11
+	add	v12.4s,v12.4s,v13.4s
+	add	w8,w8,w12
+	add	v16.4s,v16.4s,v17.4s
+	eor	w17,w17,w5
+	add	v20.4s,v20.4s,v21.4s
+	eor	w19,w19,w6
+	eor	v3.16b,v3.16b,v0.16b
+	eor	w20,w20,w7
+	eor	v7.16b,v7.16b,v4.16b
+	eor	w21,w21,w8
+	eor	v11.16b,v11.16b,v8.16b
+	ror	w17,w17,#16
+	eor	v15.16b,v15.16b,v12.16b
+	ror	w19,w19,#16
+	eor	v19.16b,v19.16b,v16.16b
+	ror	w20,w20,#16
+	eor	v23.16b,v23.16b,v20.16b
+	ror	w21,w21,#16
+	rev32	v3.8h,v3.8h
+	add	w13,w13,w17
+	rev32	v7.8h,v7.8h
+	add	w14,w14,w19
+	rev32	v11.8h,v11.8h
+	add	w15,w15,w20
+	rev32	v15.8h,v15.8h
+	add	w16,w16,w21
+	rev32	v19.8h,v19.8h
+	eor	w9,w9,w13
+	rev32	v23.8h,v23.8h
+	eor	w10,w10,w14
+	add	v2.4s,v2.4s,v3.4s
+	eor	w11,w11,w15
+	add	v6.4s,v6.4s,v7.4s
+	eor	w12,w12,w16
+	add	v10.4s,v10.4s,v11.4s
+	ror	w9,w9,#20
+	add	v14.4s,v14.4s,v15.4s
+	ror	w10,w10,#20
+	add	v18.4s,v18.4s,v19.4s
+	ror	w11,w11,#20
+	add	v22.4s,v22.4s,v23.4s
+	ror	w12,w12,#20
+	eor	v24.16b,v1.16b,v2.16b
+	add	w5,w5,w9
+	eor	v25.16b,v5.16b,v6.16b
+	add	w6,w6,w10
+	eor	v26.16b,v9.16b,v10.16b
+	add	w7,w7,w11
+	eor	v27.16b,v13.16b,v14.16b
+	add	w8,w8,w12
+	eor	v28.16b,v17.16b,v18.16b
+	eor	w17,w17,w5
+	eor	v29.16b,v21.16b,v22.16b
+	eor	w19,w19,w6
+	ushr	v1.4s,v24.4s,#20
+	eor	w20,w20,w7
+	ushr	v5.4s,v25.4s,#20
+	eor	w21,w21,w8
+	ushr	v9.4s,v26.4s,#20
+	ror	w17,w17,#24
+	ushr	v13.4s,v27.4s,#20
+	ror	w19,w19,#24
+	ushr	v17.4s,v28.4s,#20
+	ror	w20,w20,#24
+	ushr	v21.4s,v29.4s,#20
+	ror	w21,w21,#24
+	sli	v1.4s,v24.4s,#12
+	add	w13,w13,w17
+	sli	v5.4s,v25.4s,#12
+	add	w14,w14,w19
+	sli	v9.4s,v26.4s,#12
+	add	w15,w15,w20
+	sli	v13.4s,v27.4s,#12
+	add	w16,w16,w21
+	sli	v17.4s,v28.4s,#12
+	eor	w9,w9,w13
+	sli	v21.4s,v29.4s,#12
+	eor	w10,w10,w14
+	add	v0.4s,v0.4s,v1.4s
+	eor	w11,w11,w15
+	add	v4.4s,v4.4s,v5.4s
+	eor	w12,w12,w16
+	add	v8.4s,v8.4s,v9.4s
+	ror	w9,w9,#25
+	add	v12.4s,v12.4s,v13.4s
+	ror	w10,w10,#25
+	add	v16.4s,v16.4s,v17.4s
+	ror	w11,w11,#25
+	add	v20.4s,v20.4s,v21.4s
+	ror	w12,w12,#25
+	eor	v24.16b,v3.16b,v0.16b
+	add	w5,w5,w10
+	eor	v25.16b,v7.16b,v4.16b
+	add	w6,w6,w11
+	eor	v26.16b,v11.16b,v8.16b
+	add	w7,w7,w12
+	eor	v27.16b,v15.16b,v12.16b
+	add	w8,w8,w9
+	eor	v28.16b,v19.16b,v16.16b
+	eor	w21,w21,w5
+	eor	v29.16b,v23.16b,v20.16b
+	eor	w17,w17,w6
+	ushr	v3.4s,v24.4s,#24
+	eor	w19,w19,w7
+	ushr	v7.4s,v25.4s,#24
+	eor	w20,w20,w8
+	ushr	v11.4s,v26.4s,#24
+	ror	w21,w21,#16
+	ushr	v15.4s,v27.4s,#24
+	ror	w17,w17,#16
+	ushr	v19.4s,v28.4s,#24
+	ror	w19,w19,#16
+	ushr	v23.4s,v29.4s,#24
+	ror	w20,w20,#16
+	sli	v3.4s,v24.4s,#8
+	add	w15,w15,w21
+	sli	v7.4s,v25.4s,#8
+	add	w16,w16,w17
+	sli	v11.4s,v26.4s,#8
+	add	w13,w13,w19
+	sli	v15.4s,v27.4s,#8
+	add	w14,w14,w20
+	sli	v19.4s,v28.4s,#8
+	eor	w10,w10,w15
+	sli	v23.4s,v29.4s,#8
+	eor	w11,w11,w16
+	add	v2.4s,v2.4s,v3.4s
+	eor	w12,w12,w13
+	add	v6.4s,v6.4s,v7.4s
+	eor	w9,w9,w14
+	add	v10.4s,v10.4s,v11.4s
+	ror	w10,w10,#20
+	add	v14.4s,v14.4s,v15.4s
+	ror	w11,w11,#20
+	add	v18.4s,v18.4s,v19.4s
+	ror	w12,w12,#20
+	add	v22.4s,v22.4s,v23.4s
+	ror	w9,w9,#20
+	eor	v24.16b,v1.16b,v2.16b
+	add	w5,w5,w10
+	eor	v25.16b,v5.16b,v6.16b
+	add	w6,w6,w11
+	eor	v26.16b,v9.16b,v10.16b
+	add	w7,w7,w12
+	eor	v27.16b,v13.16b,v14.16b
+	add	w8,w8,w9
+	eor	v28.16b,v17.16b,v18.16b
+	eor	w21,w21,w5
+	eor	v29.16b,v21.16b,v22.16b
+	eor	w17,w17,w6
+	ushr	v1.4s,v24.4s,#25
+	eor	w19,w19,w7
+	ushr	v5.4s,v25.4s,#25
+	eor	w20,w20,w8
+	ushr	v9.4s,v26.4s,#25
+	ror	w21,w21,#24
+	ushr	v13.4s,v27.4s,#25
+	ror	w17,w17,#24
+	ushr	v17.4s,v28.4s,#25
+	ror	w19,w19,#24
+	ushr	v21.4s,v29.4s,#25
+	ror	w20,w20,#24
+	sli	v1.4s,v24.4s,#7
+	add	w15,w15,w21
+	sli	v5.4s,v25.4s,#7
+	add	w16,w16,w17
+	sli	v9.4s,v26.4s,#7
+	add	w13,w13,w19
+	sli	v13.4s,v27.4s,#7
+	add	w14,w14,w20
+	sli	v17.4s,v28.4s,#7
+	eor	w10,w10,w15
+	sli	v21.4s,v29.4s,#7
+	eor	w11,w11,w16
+	ext	v2.16b,v2.16b,v2.16b,#8
+	eor	w12,w12,w13
+	ext	v6.16b,v6.16b,v6.16b,#8
+	eor	w9,w9,w14
+	ext	v10.16b,v10.16b,v10.16b,#8
+	ror	w10,w10,#25
+	ext	v14.16b,v14.16b,v14.16b,#8
+	ror	w11,w11,#25
+	ext	v18.16b,v18.16b,v18.16b,#8
+	ror	w12,w12,#25
+	ext	v22.16b,v22.16b,v22.16b,#8
+	ror	w9,w9,#25
+	ext	v3.16b,v3.16b,v3.16b,#4
+	ext	v7.16b,v7.16b,v7.16b,#4
+	ext	v11.16b,v11.16b,v11.16b,#4
+	ext	v15.16b,v15.16b,v15.16b,#4
+	ext	v19.16b,v19.16b,v19.16b,#4
+	ext	v23.16b,v23.16b,v23.16b,#4
+	ext	v1.16b,v1.16b,v1.16b,#12
+	ext	v5.16b,v5.16b,v5.16b,#12
+	ext	v9.16b,v9.16b,v9.16b,#12
+	ext	v13.16b,v13.16b,v13.16b,#12
+	ext	v17.16b,v17.16b,v17.16b,#12
+	ext	v21.16b,v21.16b,v21.16b,#12
+	cbnz	x4,.Loop_lower_neon
+
+	add	w5,w5,w22		// accumulate key block
+	ldp	q24,q25,[sp,#0]
+	add	x6,x6,x22,lsr#32
+	ldp	q26,q27,[sp,#32]
+	add	w7,w7,w23
+	ldp	q28,q29,[sp,#64]
+	add	x8,x8,x23,lsr#32
+	add	v0.4s,v0.4s,v24.4s
+	add	w9,w9,w24
+	add	v4.4s,v4.4s,v24.4s
+	add	x10,x10,x24,lsr#32
+	add	v8.4s,v8.4s,v24.4s
+	add	w11,w11,w25
+	add	v12.4s,v12.4s,v24.4s
+	add	x12,x12,x25,lsr#32
+	add	v16.4s,v16.4s,v24.4s
+	add	w13,w13,w26
+	add	v20.4s,v20.4s,v24.4s
+	add	x14,x14,x26,lsr#32
+	add	v2.4s,v2.4s,v26.4s
+	add	w15,w15,w27
+	add	v6.4s,v6.4s,v26.4s
+	add	x16,x16,x27,lsr#32
+	add	v10.4s,v10.4s,v26.4s
+	add	w17,w17,w28
+	add	v14.4s,v14.4s,v26.4s
+	add	x19,x19,x28,lsr#32
+	add	v18.4s,v18.4s,v26.4s
+	add	w20,w20,w30
+	add	v22.4s,v22.4s,v26.4s
+	add	x21,x21,x30,lsr#32
+	add	v19.4s,v19.4s,v31.4s			// +4
+	add	x5,x5,x6,lsl#32	// pack
+	add	v23.4s,v23.4s,v31.4s			// +4
+	add	x7,x7,x8,lsl#32
+	add	v3.4s,v3.4s,v27.4s
+	ldp	x6,x8,[x1,#0]		// load input
+	add	v7.4s,v7.4s,v28.4s
+	add	x9,x9,x10,lsl#32
+	add	v11.4s,v11.4s,v29.4s
+	add	x11,x11,x12,lsl#32
+	add	v15.4s,v15.4s,v30.4s
+	ldp	x10,x12,[x1,#16]
+	add	v19.4s,v19.4s,v27.4s
+	add	x13,x13,x14,lsl#32
+	add	v23.4s,v23.4s,v28.4s
+	add	x15,x15,x16,lsl#32
+	add	v1.4s,v1.4s,v25.4s
+	ldp	x14,x16,[x1,#32]
+	add	v5.4s,v5.4s,v25.4s
+	add	x17,x17,x19,lsl#32
+	add	v9.4s,v9.4s,v25.4s
+	add	x20,x20,x21,lsl#32
+	add	v13.4s,v13.4s,v25.4s
+	ldp	x19,x21,[x1,#48]
+	add	v17.4s,v17.4s,v25.4s
+	add	x1,x1,#64
+	add	v21.4s,v21.4s,v25.4s
+
+#ifdef	__ARMEB__
+	rev	x5,x5
+	rev	x7,x7
+	rev	x9,x9
+	rev	x11,x11
+	rev	x13,x13
+	rev	x15,x15
+	rev	x17,x17
+	rev	x20,x20
+#endif
+	ld1	{v24.16b,v25.16b,v26.16b,v27.16b},[x1],#64
+	eor	x5,x5,x6
+	eor	x7,x7,x8
+	eor	x9,x9,x10
+	eor	x11,x11,x12
+	eor	x13,x13,x14
+	eor	v0.16b,v0.16b,v24.16b
+	eor	x15,x15,x16
+	eor	v1.16b,v1.16b,v25.16b
+	eor	x17,x17,x19
+	eor	v2.16b,v2.16b,v26.16b
+	eor	x20,x20,x21
+	eor	v3.16b,v3.16b,v27.16b
+	ld1	{v24.16b,v25.16b,v26.16b,v27.16b},[x1],#64
+
+	stp	x5,x7,[x0,#0]		// store output
+	add	x28,x28,#7			// increment counter
+	stp	x9,x11,[x0,#16]
+	stp	x13,x15,[x0,#32]
+	stp	x17,x20,[x0,#48]
+	add	x0,x0,#64
+	st1	{v0.16b,v1.16b,v2.16b,v3.16b},[x0],#64
+
+	ld1	{v0.16b,v1.16b,v2.16b,v3.16b},[x1],#64
+	eor	v4.16b,v4.16b,v24.16b
+	eor	v5.16b,v5.16b,v25.16b
+	eor	v6.16b,v6.16b,v26.16b
+	eor	v7.16b,v7.16b,v27.16b
+	st1	{v4.16b,v5.16b,v6.16b,v7.16b},[x0],#64
+
+	ld1	{v4.16b,v5.16b,v6.16b,v7.16b},[x1],#64
+	eor	v8.16b,v8.16b,v0.16b
+	ldp	q24,q25,[sp,#0]
+	eor	v9.16b,v9.16b,v1.16b
+	ldp	q26,q27,[sp,#32]
+	eor	v10.16b,v10.16b,v2.16b
+	eor	v11.16b,v11.16b,v3.16b
+	st1	{v8.16b,v9.16b,v10.16b,v11.16b},[x0],#64
+
+	ld1	{v8.16b,v9.16b,v10.16b,v11.16b},[x1],#64
+	eor	v12.16b,v12.16b,v4.16b
+	eor	v13.16b,v13.16b,v5.16b
+	eor	v14.16b,v14.16b,v6.16b
+	eor	v15.16b,v15.16b,v7.16b
+	st1	{v12.16b,v13.16b,v14.16b,v15.16b},[x0],#64
+
+	ld1	{v12.16b,v13.16b,v14.16b,v15.16b},[x1],#64
+	eor	v16.16b,v16.16b,v8.16b
+	eor	v17.16b,v17.16b,v9.16b
+	eor	v18.16b,v18.16b,v10.16b
+	eor	v19.16b,v19.16b,v11.16b
+	st1	{v16.16b,v17.16b,v18.16b,v19.16b},[x0],#64
+
+	shl	v0.4s,v31.4s,#1			// 4 -> 8
+	eor	v20.16b,v20.16b,v12.16b
+	eor	v21.16b,v21.16b,v13.16b
+	eor	v22.16b,v22.16b,v14.16b
+	eor	v23.16b,v23.16b,v15.16b
+	st1	{v20.16b,v21.16b,v22.16b,v23.16b},[x0],#64
+
+	add	v27.4s,v27.4s,v0.4s			// += 8
+	add	v28.4s,v28.4s,v0.4s
+	add	v29.4s,v29.4s,v0.4s
+	add	v30.4s,v30.4s,v0.4s
+
+	b.hs	.Loop_outer_512_neon
+
+	adds	x2,x2,#512
+	ushr	v0.4s,v31.4s,#2			// 4 -> 1
+
+	ldp	d8,d9,[sp,#128+0]		// meet ABI requirements
+	ldp	d10,d11,[sp,#128+16]
+	ldp	d12,d13,[sp,#128+32]
+	ldp	d14,d15,[sp,#128+48]
+
+	stp	q24,q31,[sp,#0]		// wipe off-load area
+	stp	q24,q31,[sp,#32]
+	stp	q24,q31,[sp,#64]
+
+	b.eq	.Ldone_512_neon
+
+	cmp	x2,#192
+	sub	v27.4s,v27.4s,v0.4s			// -= 1
+	sub	v28.4s,v28.4s,v0.4s
+	sub	v29.4s,v29.4s,v0.4s
+	add	sp,sp,#128
+	b.hs	.Loop_outer_neon
+
+	eor	v25.16b,v25.16b,v25.16b
+	eor	v26.16b,v26.16b,v26.16b
+	eor	v27.16b,v27.16b,v27.16b
+	eor	v28.16b,v28.16b,v28.16b
+	eor	v29.16b,v29.16b,v29.16b
+	eor	v30.16b,v30.16b,v30.16b
+	b	.Loop_outer
+
+.Ldone_512_neon:
+	ldp	x19,x20,[x29,#16]
+	add	sp,sp,#128+64
+	ldp	x21,x22,[x29,#32]
+	ldp	x23,x24,[x29,#48]
+	ldp	x25,x26,[x29,#64]
+	ldp	x27,x28,[x29,#80]
+	ldp	x29,x30,[sp],#96
+	ret
+.size	ChaCha20_512_neon,.-ChaCha20_512_neon
+#endif
diff --git a/packager/third_party/boringssl/linux-aarch64/crypto/modes/ghashv8-armx64.S b/packager/third_party/boringssl/linux-aarch64/crypto/modes/ghashv8-armx64.S
index a0a9b6807a..f39f3ba870 100644
--- a/packager/third_party/boringssl/linux-aarch64/crypto/modes/ghashv8-armx64.S
+++ b/packager/third_party/boringssl/linux-aarch64/crypto/modes/ghashv8-armx64.S
@@ -1,11 +1,12 @@
 #if defined(__aarch64__)
-#include "arm_arch.h"
+#include <openssl/arm_arch.h>
 
 .text
 #if !defined(__clang__)
 .arch	armv8-a+crypto
 #endif
 .globl	gcm_init_v8
+.hidden	gcm_init_v8
 .type	gcm_init_v8,%function
 .align	4
 gcm_init_v8:
@@ -56,6 +57,7 @@ gcm_init_v8:
 	ret
 .size	gcm_init_v8,.-gcm_init_v8
 .globl	gcm_gmult_v8
+.hidden	gcm_gmult_v8
 .type	gcm_gmult_v8,%function
 .align	4
 gcm_gmult_v8:
@@ -68,10 +70,10 @@ gcm_gmult_v8:
 #endif
 	ext	v3.16b,v17.16b,v17.16b,#8
 
-	pmull	v0.1q,v20.1d,v3.1d		//H.lo·Xi.lo
+	pmull	v0.1q,v20.1d,v3.1d		//H.lo·Xi.lo
 	eor	v17.16b,v17.16b,v3.16b		//Karatsuba pre-processing
-	pmull2	v2.1q,v20.2d,v3.2d		//H.hi·Xi.hi
-	pmull	v1.1q,v21.1d,v17.1d		//(H.lo+H.hi)·(Xi.lo+Xi.hi)
+	pmull2	v2.1q,v20.2d,v3.2d		//H.hi·Xi.hi
+	pmull	v1.1q,v21.1d,v17.1d		//(H.lo+H.hi)·(Xi.lo+Xi.hi)
 
 	ext	v17.16b,v0.16b,v2.16b,#8		//Karatsuba post-processing
 	eor	v18.16b,v0.16b,v2.16b
@@ -97,6 +99,7 @@ gcm_gmult_v8:
 	ret
 .size	gcm_gmult_v8,.-gcm_gmult_v8
 .globl	gcm_ghash_v8
+.hidden	gcm_ghash_v8
 .type	gcm_ghash_v8,%function
 .align	4
 gcm_ghash_v8:
@@ -135,7 +138,7 @@ gcm_ghash_v8:
 #endif
 	ext	v7.16b,v17.16b,v17.16b,#8
 	eor	v3.16b,v3.16b,v0.16b		//I[i]^=Xi
-	pmull	v4.1q,v20.1d,v7.1d		//H·Ii+1
+	pmull	v4.1q,v20.1d,v7.1d		//H·Ii+1
 	eor	v17.16b,v17.16b,v7.16b		//Karatsuba pre-processing
 	pmull2	v6.1q,v20.2d,v7.2d
 	b	.Loop_mod2x_v8
@@ -144,14 +147,14 @@ gcm_ghash_v8:
 .Loop_mod2x_v8:
 	ext	v18.16b,v3.16b,v3.16b,#8
 	subs	x3,x3,#32		//is there more data?
-	pmull	v0.1q,v22.1d,v3.1d		//H^2.lo·Xi.lo
+	pmull	v0.1q,v22.1d,v3.1d		//H^2.lo·Xi.lo
 	csel	x12,xzr,x12,lo			//is it time to zero x12?
 
 	pmull	v5.1q,v21.1d,v17.1d
 	eor	v18.16b,v18.16b,v3.16b		//Karatsuba pre-processing
-	pmull2	v2.1q,v22.2d,v3.2d		//H^2.hi·Xi.hi
+	pmull2	v2.1q,v22.2d,v3.2d		//H^2.hi·Xi.hi
 	eor	v0.16b,v0.16b,v4.16b		//accumulate
-	pmull2	v1.1q,v21.2d,v18.2d		//(H^2.lo+H^2.hi)·(Xi.lo+Xi.hi)
+	pmull2	v1.1q,v21.2d,v18.2d		//(H^2.lo+H^2.hi)·(Xi.lo+Xi.hi)
 	ld1	{v16.2d},[x2],x12	//load [rotated] I[i+2]
 
 	eor	v2.16b,v2.16b,v6.16b
@@ -176,7 +179,7 @@ gcm_ghash_v8:
 	ext	v7.16b,v17.16b,v17.16b,#8
 	ext	v3.16b,v16.16b,v16.16b,#8
 	eor	v0.16b,v1.16b,v18.16b
-	pmull	v4.1q,v20.1d,v7.1d		//H·Ii+1
+	pmull	v4.1q,v20.1d,v7.1d		//H·Ii+1
 	eor	v3.16b,v3.16b,v2.16b		//accumulate v3.16b early
 
 	ext	v18.16b,v0.16b,v0.16b,#8		//2nd phase of reduction
@@ -197,10 +200,10 @@ gcm_ghash_v8:
 	eor	v3.16b,v3.16b,v0.16b		//inp^=Xi
 	eor	v17.16b,v16.16b,v18.16b		//v17.16b is rotated inp^Xi
 
-	pmull	v0.1q,v20.1d,v3.1d		//H.lo·Xi.lo
+	pmull	v0.1q,v20.1d,v3.1d		//H.lo·Xi.lo
 	eor	v17.16b,v17.16b,v3.16b		//Karatsuba pre-processing
-	pmull2	v2.1q,v20.2d,v3.2d		//H.hi·Xi.hi
-	pmull	v1.1q,v21.1d,v17.1d		//(H.lo+H.hi)·(Xi.lo+Xi.hi)
+	pmull2	v2.1q,v20.2d,v3.2d		//H.hi·Xi.hi
+	pmull	v1.1q,v21.1d,v17.1d		//(H.lo+H.hi)·(Xi.lo+Xi.hi)
 
 	ext	v17.16b,v0.16b,v2.16b,#8		//Karatsuba post-processing
 	eor	v18.16b,v0.16b,v2.16b
@@ -229,4 +232,4 @@ gcm_ghash_v8:
 .byte	71,72,65,83,72,32,102,111,114,32,65,82,77,118,56,44,32,67,82,89,80,84,79,71,65,77,83,32,98,121,32,60,97,112,112,114,111,64,111,112,101,110,115,115,108,46,111,114,103,62,0
 .align	2
 .align	2
-#endif
\ No newline at end of file
+#endif
diff --git a/packager/third_party/boringssl/linux-aarch64/crypto/sha/sha1-armv8.S b/packager/third_party/boringssl/linux-aarch64/crypto/sha/sha1-armv8.S
index 487a497da2..cfb4aa021f 100644
--- a/packager/third_party/boringssl/linux-aarch64/crypto/sha/sha1-armv8.S
+++ b/packager/third_party/boringssl/linux-aarch64/crypto/sha/sha1-armv8.S
@@ -1,10 +1,11 @@
 #if defined(__aarch64__)
-#include "arm_arch.h"
+#include <openssl/arm_arch.h>
 
 .text
 
 
 .globl	sha1_block_data_order
+.hidden	sha1_block_data_order
 .type	sha1_block_data_order,%function
 .align	6
 sha1_block_data_order:
@@ -1212,4 +1213,4 @@ sha1_block_armv8:
 .align	2
 .align	2
 .comm	OPENSSL_armcap_P,4,4
-#endif
\ No newline at end of file
+#endif
diff --git a/packager/third_party/boringssl/linux-aarch64/crypto/sha/sha256-armv8.S b/packager/third_party/boringssl/linux-aarch64/crypto/sha/sha256-armv8.S
index 4834553dc1..bfc552cbf1 100644
--- a/packager/third_party/boringssl/linux-aarch64/crypto/sha/sha256-armv8.S
+++ b/packager/third_party/boringssl/linux-aarch64/crypto/sha/sha256-armv8.S
@@ -1,10 +1,11 @@
 #if defined(__aarch64__)
-#include "arm_arch.h"
+#include <openssl/arm_arch.h>
 
 .text
 
 
 .globl	sha256_block_data_order
+.hidden	sha256_block_data_order
 .type	sha256_block_data_order,%function
 .align	6
 sha256_block_data_order:
@@ -1142,4 +1143,4 @@ sha256_block_armv8:
 	ret
 .size	sha256_block_armv8,.-sha256_block_armv8
 .comm	OPENSSL_armcap_P,4,4
-#endif
\ No newline at end of file
+#endif
diff --git a/packager/third_party/boringssl/linux-aarch64/crypto/sha/sha512-armv8.S b/packager/third_party/boringssl/linux-aarch64/crypto/sha/sha512-armv8.S
index 654c473f27..4645722923 100644
--- a/packager/third_party/boringssl/linux-aarch64/crypto/sha/sha512-armv8.S
+++ b/packager/third_party/boringssl/linux-aarch64/crypto/sha/sha512-armv8.S
@@ -1,10 +1,11 @@
 #if defined(__aarch64__)
-#include "arm_arch.h"
+#include <openssl/arm_arch.h>
 
 .text
 
 
 .globl	sha512_block_data_order
+.hidden	sha512_block_data_order
 .type	sha512_block_data_order,%function
 .align	6
 sha512_block_data_order:
@@ -1022,4 +1023,4 @@ sha512_block_data_order:
 .align	2
 .align	2
 .comm	OPENSSL_armcap_P,4,4
-#endif
\ No newline at end of file
+#endif
diff --git a/packager/third_party/boringssl/linux-arm/crypto/aes/aes-armv4.S b/packager/third_party/boringssl/linux-arm/crypto/aes/aes-armv4.S
index cb94841e02..bc11e3f139 100644
--- a/packager/third_party/boringssl/linux-arm/crypto/aes/aes-armv4.S
+++ b/packager/third_party/boringssl/linux-arm/crypto/aes/aes-armv4.S
@@ -34,7 +34,7 @@
 
 #if defined(__arm__)
 #ifndef __KERNEL__
-# include "arm_arch.h"
+# include <openssl/arm_arch.h>
 #else
 # define __ARM_ARCH__ __LINUX_ARM_ARCH__
 #endif
@@ -1197,4 +1197,4 @@ _armv4_AES_decrypt:
 .align	2
 
 #endif
-#endif
\ No newline at end of file
+#endif
diff --git a/packager/third_party/boringssl/linux-arm/crypto/aes/aesv8-armx32.S b/packager/third_party/boringssl/linux-arm/crypto/aes/aesv8-armx32.S
index 6f0ee7d81d..95a2ea4dc9 100644
--- a/packager/third_party/boringssl/linux-arm/crypto/aes/aesv8-armx32.S
+++ b/packager/third_party/boringssl/linux-arm/crypto/aes/aesv8-armx32.S
@@ -1,5 +1,5 @@
 #if defined(__arm__)
-#include "arm_arch.h"
+#include <openssl/arm_arch.h>
 
 #if __ARM_MAX_ARCH__>=7
 .text
@@ -13,6 +13,7 @@
 .long	0x1b,0x1b,0x1b,0x1b
 
 .globl	aes_v8_set_encrypt_key
+.hidden	aes_v8_set_encrypt_key
 .type	aes_v8_set_encrypt_key,%function
 .align	5
 aes_v8_set_encrypt_key:
@@ -183,6 +184,7 @@ aes_v8_set_encrypt_key:
 .size	aes_v8_set_encrypt_key,.-aes_v8_set_encrypt_key
 
 .globl	aes_v8_set_decrypt_key
+.hidden	aes_v8_set_decrypt_key
 .type	aes_v8_set_decrypt_key,%function
 .align	5
 aes_v8_set_decrypt_key:
@@ -220,6 +222,7 @@ aes_v8_set_decrypt_key:
 	ldmia	sp!,{r4,pc}
 .size	aes_v8_set_decrypt_key,.-aes_v8_set_decrypt_key
 .globl	aes_v8_encrypt
+.hidden	aes_v8_encrypt
 .type	aes_v8_encrypt,%function
 .align	5
 aes_v8_encrypt:
@@ -249,6 +252,7 @@ aes_v8_encrypt:
 	bx	lr
 .size	aes_v8_encrypt,.-aes_v8_encrypt
 .globl	aes_v8_decrypt
+.hidden	aes_v8_decrypt
 .type	aes_v8_decrypt,%function
 .align	5
 aes_v8_decrypt:
@@ -278,6 +282,7 @@ aes_v8_decrypt:
 	bx	lr
 .size	aes_v8_decrypt,.-aes_v8_decrypt
 .globl	aes_v8_cbc_encrypt
+.hidden	aes_v8_cbc_encrypt
 .type	aes_v8_cbc_encrypt,%function
 .align	5
 aes_v8_cbc_encrypt:
@@ -570,6 +575,7 @@ aes_v8_cbc_encrypt:
 	ldmia	sp!,{r4,r5,r6,r7,r8,pc}
 .size	aes_v8_cbc_encrypt,.-aes_v8_cbc_encrypt
 .globl	aes_v8_ctr32_encrypt_blocks
+.hidden	aes_v8_ctr32_encrypt_blocks
 .type	aes_v8_ctr32_encrypt_blocks,%function
 .align	5
 aes_v8_ctr32_encrypt_blocks:
@@ -753,4 +759,4 @@ aes_v8_ctr32_encrypt_blocks:
 	ldmia	sp!,{r4,r5,r6,r7,r8,r9,r10,pc}
 .size	aes_v8_ctr32_encrypt_blocks,.-aes_v8_ctr32_encrypt_blocks
 #endif
-#endif
\ No newline at end of file
+#endif
diff --git a/packager/third_party/boringssl/linux-arm/crypto/aes/bsaes-armv7.S b/packager/third_party/boringssl/linux-arm/crypto/aes/bsaes-armv7.S
index dd84f3589d..abb414d549 100644
--- a/packager/third_party/boringssl/linux-arm/crypto/aes/bsaes-armv7.S
+++ b/packager/third_party/boringssl/linux-arm/crypto/aes/bsaes-armv7.S
@@ -47,9 +47,8 @@
 @
 @					<ard.biesheuvel@linaro.org>
 
-#if defined(__arm__)
 #ifndef __KERNEL__
-# include "arm_arch.h"
+# include <openssl/arm_arch.h>
 
 # define VFP_ABI_PUSH	vstmdb	sp!,{d8-d15}
 # define VFP_ABI_POP	vldmia	sp!,{d8-d15}
@@ -2576,4 +2575,3 @@ bsaes_xts_decrypt:
 .size	bsaes_xts_decrypt,.-bsaes_xts_decrypt
 #endif
 #endif
-#endif
\ No newline at end of file
diff --git a/packager/third_party/boringssl/linux-arm/crypto/bn/armv4-mont.S b/packager/third_party/boringssl/linux-arm/crypto/bn/armv4-mont.S
index 68dfb2c172..e59599f832 100644
--- a/packager/third_party/boringssl/linux-arm/crypto/bn/armv4-mont.S
+++ b/packager/third_party/boringssl/linux-arm/crypto/bn/armv4-mont.S
@@ -1,5 +1,5 @@
 #if defined(__arm__)
-#include "arm_arch.h"
+#include <openssl/arm_arch.h>
 
 .text
 .code	32
@@ -28,7 +28,7 @@ bn_mul_mont:
 #ifdef	__APPLE__
 	ldr	r0,[r0]
 #endif
-	tst	r0,#1			@ NEON available?
+	tst	r0,#ARMV7_NEON		@ NEON available?
 	ldmia	sp, {r0,r2}
 	beq	.Lialu
 	add	sp,sp,#8
@@ -586,4 +586,4 @@ bn_mul8x_mont_neon:
 .comm	OPENSSL_armcap_P,4,4
 .hidden	OPENSSL_armcap_P
 #endif
-#endif
\ No newline at end of file
+#endif
diff --git a/packager/third_party/boringssl/linux-arm/crypto/chacha/chacha-armv4.S b/packager/third_party/boringssl/linux-arm/crypto/chacha/chacha-armv4.S
new file mode 100644
index 0000000000..19a4d2c4ff
--- /dev/null
+++ b/packager/third_party/boringssl/linux-arm/crypto/chacha/chacha-armv4.S
@@ -0,0 +1,1471 @@
+#if defined(__arm__)
+#include <openssl/arm_arch.h>
+
+.text
+#if defined(__thumb2__)
+.syntax	unified
+.thumb
+#else
+.code	32
+#endif
+
+#if defined(__thumb2__) || defined(__clang__)
+#define ldrhsb	ldrbhs
+#endif
+
+.align	5
+.Lsigma:
+.long	0x61707865,0x3320646e,0x79622d32,0x6b206574	@ endian-neutral
+.Lone:
+.long	1,0,0,0
+#if __ARM_MAX_ARCH__>=7
+.LOPENSSL_armcap:
+.word	OPENSSL_armcap_P-.LChaCha20_ctr32
+#else
+.word	-1
+#endif
+
+.globl	ChaCha20_ctr32
+.hidden	ChaCha20_ctr32
+.type	ChaCha20_ctr32,%function
+.align	5
+ChaCha20_ctr32:
+.LChaCha20_ctr32:
+	ldr	r12,[sp,#0]		@ pull pointer to counter and nonce
+	stmdb	sp!,{r0,r1,r2,r4-r11,lr}
+#if __ARM_ARCH__<7 && !defined(__thumb2__)
+	sub	r14,pc,#16		@ ChaCha20_ctr32
+#else
+	adr	r14,.LChaCha20_ctr32
+#endif
+	cmp	r2,#0			@ len==0?
+#ifdef	__thumb2__
+	itt	eq
+#endif
+	addeq	sp,sp,#4*3
+	beq	.Lno_data
+#if __ARM_MAX_ARCH__>=7
+	cmp	r2,#192			@ test len
+	bls	.Lshort
+	ldr	r4,[r14,#-32]
+	ldr	r4,[r14,r4]
+# ifdef	__APPLE__
+	ldr	r4,[r4]
+# endif
+	tst	r4,#ARMV7_NEON
+	bne	.LChaCha20_neon
+.Lshort:
+#endif
+	ldmia	r12,{r4,r5,r6,r7}		@ load counter and nonce
+	sub	sp,sp,#4*(16)		@ off-load area
+	sub	r14,r14,#64		@ .Lsigma
+	stmdb	sp!,{r4,r5,r6,r7}		@ copy counter and nonce
+	ldmia	r3,{r4,r5,r6,r7,r8,r9,r10,r11}		@ load key
+	ldmia	r14,{r0,r1,r2,r3}		@ load sigma
+	stmdb	sp!,{r4,r5,r6,r7,r8,r9,r10,r11}		@ copy key
+	stmdb	sp!,{r0,r1,r2,r3}		@ copy sigma
+	str	r10,[sp,#4*(16+10)]	@ off-load "rx"
+	str	r11,[sp,#4*(16+11)]	@ off-load "rx"
+	b	.Loop_outer_enter
+
+.align	4
+.Loop_outer:
+	ldmia	sp,{r0,r1,r2,r3,r4,r5,r6,r7,r8,r9}		@ load key material
+	str	r11,[sp,#4*(32+2)]	@ save len
+	str	r12,  [sp,#4*(32+1)]	@ save inp
+	str	r14,  [sp,#4*(32+0)]	@ save out
+.Loop_outer_enter:
+	ldr	r11, [sp,#4*(15)]
+	ldr	r12,[sp,#4*(12)]	@ modulo-scheduled load
+	ldr	r10, [sp,#4*(13)]
+	ldr	r14,[sp,#4*(14)]
+	str	r11, [sp,#4*(16+15)]
+	mov	r11,#10
+	b	.Loop
+
+.align	4
+.Loop:
+	subs	r11,r11,#1
+	add	r0,r0,r4
+	mov	r12,r12,ror#16
+	add	r1,r1,r5
+	mov	r10,r10,ror#16
+	eor	r12,r12,r0,ror#16
+	eor	r10,r10,r1,ror#16
+	add	r8,r8,r12
+	mov	r4,r4,ror#20
+	add	r9,r9,r10
+	mov	r5,r5,ror#20
+	eor	r4,r4,r8,ror#20
+	eor	r5,r5,r9,ror#20
+	add	r0,r0,r4
+	mov	r12,r12,ror#24
+	add	r1,r1,r5
+	mov	r10,r10,ror#24
+	eor	r12,r12,r0,ror#24
+	eor	r10,r10,r1,ror#24
+	add	r8,r8,r12
+	mov	r4,r4,ror#25
+	add	r9,r9,r10
+	mov	r5,r5,ror#25
+	str	r10,[sp,#4*(16+13)]
+	ldr	r10,[sp,#4*(16+15)]
+	eor	r4,r4,r8,ror#25
+	eor	r5,r5,r9,ror#25
+	str	r8,[sp,#4*(16+8)]
+	ldr	r8,[sp,#4*(16+10)]
+	add	r2,r2,r6
+	mov	r14,r14,ror#16
+	str	r9,[sp,#4*(16+9)]
+	ldr	r9,[sp,#4*(16+11)]
+	add	r3,r3,r7
+	mov	r10,r10,ror#16
+	eor	r14,r14,r2,ror#16
+	eor	r10,r10,r3,ror#16
+	add	r8,r8,r14
+	mov	r6,r6,ror#20
+	add	r9,r9,r10
+	mov	r7,r7,ror#20
+	eor	r6,r6,r8,ror#20
+	eor	r7,r7,r9,ror#20
+	add	r2,r2,r6
+	mov	r14,r14,ror#24
+	add	r3,r3,r7
+	mov	r10,r10,ror#24
+	eor	r14,r14,r2,ror#24
+	eor	r10,r10,r3,ror#24
+	add	r8,r8,r14
+	mov	r6,r6,ror#25
+	add	r9,r9,r10
+	mov	r7,r7,ror#25
+	eor	r6,r6,r8,ror#25
+	eor	r7,r7,r9,ror#25
+	add	r0,r0,r5
+	mov	r10,r10,ror#16
+	add	r1,r1,r6
+	mov	r12,r12,ror#16
+	eor	r10,r10,r0,ror#16
+	eor	r12,r12,r1,ror#16
+	add	r8,r8,r10
+	mov	r5,r5,ror#20
+	add	r9,r9,r12
+	mov	r6,r6,ror#20
+	eor	r5,r5,r8,ror#20
+	eor	r6,r6,r9,ror#20
+	add	r0,r0,r5
+	mov	r10,r10,ror#24
+	add	r1,r1,r6
+	mov	r12,r12,ror#24
+	eor	r10,r10,r0,ror#24
+	eor	r12,r12,r1,ror#24
+	add	r8,r8,r10
+	mov	r5,r5,ror#25
+	str	r10,[sp,#4*(16+15)]
+	ldr	r10,[sp,#4*(16+13)]
+	add	r9,r9,r12
+	mov	r6,r6,ror#25
+	eor	r5,r5,r8,ror#25
+	eor	r6,r6,r9,ror#25
+	str	r8,[sp,#4*(16+10)]
+	ldr	r8,[sp,#4*(16+8)]
+	add	r2,r2,r7
+	mov	r10,r10,ror#16
+	str	r9,[sp,#4*(16+11)]
+	ldr	r9,[sp,#4*(16+9)]
+	add	r3,r3,r4
+	mov	r14,r14,ror#16
+	eor	r10,r10,r2,ror#16
+	eor	r14,r14,r3,ror#16
+	add	r8,r8,r10
+	mov	r7,r7,ror#20
+	add	r9,r9,r14
+	mov	r4,r4,ror#20
+	eor	r7,r7,r8,ror#20
+	eor	r4,r4,r9,ror#20
+	add	r2,r2,r7
+	mov	r10,r10,ror#24
+	add	r3,r3,r4
+	mov	r14,r14,ror#24
+	eor	r10,r10,r2,ror#24
+	eor	r14,r14,r3,ror#24
+	add	r8,r8,r10
+	mov	r7,r7,ror#25
+	add	r9,r9,r14
+	mov	r4,r4,ror#25
+	eor	r7,r7,r8,ror#25
+	eor	r4,r4,r9,ror#25
+	bne	.Loop
+
+	ldr	r11,[sp,#4*(32+2)]	@ load len
+
+	str	r8, [sp,#4*(16+8)]	@ modulo-scheduled store
+	str	r9, [sp,#4*(16+9)]
+	str	r12,[sp,#4*(16+12)]
+	str	r10, [sp,#4*(16+13)]
+	str	r14,[sp,#4*(16+14)]
+
+	@ at this point we have first half of 512-bit result in
+	@ rx and second half at sp+4*(16+8)
+
+	cmp	r11,#64		@ done yet?
+#ifdef	__thumb2__
+	itete	lo
+#endif
+	addlo	r12,sp,#4*(0)		@ shortcut or ...
+	ldrhs	r12,[sp,#4*(32+1)]	@ ... load inp
+	addlo	r14,sp,#4*(0)		@ shortcut or ...
+	ldrhs	r14,[sp,#4*(32+0)]	@ ... load out
+
+	ldr	r8,[sp,#4*(0)]	@ load key material
+	ldr	r9,[sp,#4*(1)]
+
+#if __ARM_ARCH__>=6 || !defined(__ARMEB__)
+# if __ARM_ARCH__<7
+	orr	r10,r12,r14
+	tst	r10,#3		@ are input and output aligned?
+	ldr	r10,[sp,#4*(2)]
+	bne	.Lunaligned
+	cmp	r11,#64		@ restore flags
+# else
+	ldr	r10,[sp,#4*(2)]
+# endif
+	ldr	r11,[sp,#4*(3)]
+
+	add	r0,r0,r8	@ accumulate key material
+	add	r1,r1,r9
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	ldrhs	r8,[r12],#16		@ load input
+	ldrhs	r9,[r12,#-12]
+
+	add	r2,r2,r10
+	add	r3,r3,r11
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	ldrhs	r10,[r12,#-8]
+	ldrhs	r11,[r12,#-4]
+# if __ARM_ARCH__>=6 && defined(__ARMEB__)
+	rev	r0,r0
+	rev	r1,r1
+	rev	r2,r2
+	rev	r3,r3
+# endif
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	eorhs	r0,r0,r8	@ xor with input
+	eorhs	r1,r1,r9
+	add	r8,sp,#4*(4)
+	str	r0,[r14],#16		@ store output
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	eorhs	r2,r2,r10
+	eorhs	r3,r3,r11
+	ldmia	r8,{r8,r9,r10,r11}	@ load key material
+	str	r1,[r14,#-12]
+	str	r2,[r14,#-8]
+	str	r3,[r14,#-4]
+
+	add	r4,r4,r8	@ accumulate key material
+	add	r5,r5,r9
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	ldrhs	r8,[r12],#16		@ load input
+	ldrhs	r9,[r12,#-12]
+	add	r6,r6,r10
+	add	r7,r7,r11
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	ldrhs	r10,[r12,#-8]
+	ldrhs	r11,[r12,#-4]
+# if __ARM_ARCH__>=6 && defined(__ARMEB__)
+	rev	r4,r4
+	rev	r5,r5
+	rev	r6,r6
+	rev	r7,r7
+# endif
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	eorhs	r4,r4,r8
+	eorhs	r5,r5,r9
+	add	r8,sp,#4*(8)
+	str	r4,[r14],#16		@ store output
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	eorhs	r6,r6,r10
+	eorhs	r7,r7,r11
+	str	r5,[r14,#-12]
+	ldmia	r8,{r8,r9,r10,r11}	@ load key material
+	str	r6,[r14,#-8]
+	add	r0,sp,#4*(16+8)
+	str	r7,[r14,#-4]
+
+	ldmia	r0,{r0,r1,r2,r3,r4,r5,r6,r7}	@ load second half
+
+	add	r0,r0,r8	@ accumulate key material
+	add	r1,r1,r9
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	ldrhs	r8,[r12],#16		@ load input
+	ldrhs	r9,[r12,#-12]
+# ifdef	__thumb2__
+	itt	hi
+# endif
+	strhi	r10,[sp,#4*(16+10)]	@ copy "rx" while at it
+	strhi	r11,[sp,#4*(16+11)]	@ copy "rx" while at it
+	add	r2,r2,r10
+	add	r3,r3,r11
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	ldrhs	r10,[r12,#-8]
+	ldrhs	r11,[r12,#-4]
+# if __ARM_ARCH__>=6 && defined(__ARMEB__)
+	rev	r0,r0
+	rev	r1,r1
+	rev	r2,r2
+	rev	r3,r3
+# endif
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	eorhs	r0,r0,r8
+	eorhs	r1,r1,r9
+	add	r8,sp,#4*(12)
+	str	r0,[r14],#16		@ store output
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	eorhs	r2,r2,r10
+	eorhs	r3,r3,r11
+	str	r1,[r14,#-12]
+	ldmia	r8,{r8,r9,r10,r11}	@ load key material
+	str	r2,[r14,#-8]
+	str	r3,[r14,#-4]
+
+	add	r4,r4,r8	@ accumulate key material
+	add	r5,r5,r9
+# ifdef	__thumb2__
+	itt	hi
+# endif
+	addhi	r8,r8,#1		@ next counter value
+	strhi	r8,[sp,#4*(12)]	@ save next counter value
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	ldrhs	r8,[r12],#16		@ load input
+	ldrhs	r9,[r12,#-12]
+	add	r6,r6,r10
+	add	r7,r7,r11
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	ldrhs	r10,[r12,#-8]
+	ldrhs	r11,[r12,#-4]
+# if __ARM_ARCH__>=6 && defined(__ARMEB__)
+	rev	r4,r4
+	rev	r5,r5
+	rev	r6,r6
+	rev	r7,r7
+# endif
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	eorhs	r4,r4,r8
+	eorhs	r5,r5,r9
+# ifdef	__thumb2__
+	it	ne
+# endif
+	ldrne	r8,[sp,#4*(32+2)]	@ re-load len
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	eorhs	r6,r6,r10
+	eorhs	r7,r7,r11
+	str	r4,[r14],#16		@ store output
+	str	r5,[r14,#-12]
+# ifdef	__thumb2__
+	it	hs
+# endif
+	subhs	r11,r8,#64		@ len-=64
+	str	r6,[r14,#-8]
+	str	r7,[r14,#-4]
+	bhi	.Loop_outer
+
+	beq	.Ldone
+# if __ARM_ARCH__<7
+	b	.Ltail
+
+.align	4
+.Lunaligned:@ unaligned endian-neutral path
+	cmp	r11,#64		@ restore flags
+# endif
+#endif
+#if __ARM_ARCH__<7
+	ldr	r11,[sp,#4*(3)]
+	add	r0,r0,r8		@ accumulate key material
+	add	r1,r1,r9
+	add	r2,r2,r10
+# ifdef	__thumb2__
+	itete	lo
+# endif
+	eorlo	r8,r8,r8		@ zero or ...
+	ldrhsb	r8,[r12],#16			@ ... load input
+	eorlo	r9,r9,r9
+	ldrhsb	r9,[r12,#-12]
+
+	add	r3,r3,r11
+# ifdef	__thumb2__
+	itete	lo
+# endif
+	eorlo	r10,r10,r10
+	ldrhsb	r10,[r12,#-8]
+	eorlo	r11,r11,r11
+	ldrhsb	r11,[r12,#-4]
+
+	eor	r0,r8,r0		@ xor with input (or zero)
+	eor	r1,r9,r1
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	ldrhsb	r8,[r12,#-15]		@ load more input
+	ldrhsb	r9,[r12,#-11]
+	eor	r2,r10,r2
+	strb	r0,[r14],#16		@ store output
+	eor	r3,r11,r3
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	ldrhsb	r10,[r12,#-7]
+	ldrhsb	r11,[r12,#-3]
+	strb	r1,[r14,#-12]
+	eor	r0,r8,r0,lsr#8
+	strb	r2,[r14,#-8]
+	eor	r1,r9,r1,lsr#8
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	ldrhsb	r8,[r12,#-14]		@ load more input
+	ldrhsb	r9,[r12,#-10]
+	strb	r3,[r14,#-4]
+	eor	r2,r10,r2,lsr#8
+	strb	r0,[r14,#-15]
+	eor	r3,r11,r3,lsr#8
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	ldrhsb	r10,[r12,#-6]
+	ldrhsb	r11,[r12,#-2]
+	strb	r1,[r14,#-11]
+	eor	r0,r8,r0,lsr#8
+	strb	r2,[r14,#-7]
+	eor	r1,r9,r1,lsr#8
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	ldrhsb	r8,[r12,#-13]		@ load more input
+	ldrhsb	r9,[r12,#-9]
+	strb	r3,[r14,#-3]
+	eor	r2,r10,r2,lsr#8
+	strb	r0,[r14,#-14]
+	eor	r3,r11,r3,lsr#8
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	ldrhsb	r10,[r12,#-5]
+	ldrhsb	r11,[r12,#-1]
+	strb	r1,[r14,#-10]
+	strb	r2,[r14,#-6]
+	eor	r0,r8,r0,lsr#8
+	strb	r3,[r14,#-2]
+	eor	r1,r9,r1,lsr#8
+	strb	r0,[r14,#-13]
+	eor	r2,r10,r2,lsr#8
+	strb	r1,[r14,#-9]
+	eor	r3,r11,r3,lsr#8
+	strb	r2,[r14,#-5]
+	strb	r3,[r14,#-1]
+	add	r8,sp,#4*(4+0)
+	ldmia	r8,{r8,r9,r10,r11}		@ load key material
+	add	r0,sp,#4*(16+8)
+	add	r4,r4,r8		@ accumulate key material
+	add	r5,r5,r9
+	add	r6,r6,r10
+# ifdef	__thumb2__
+	itete	lo
+# endif
+	eorlo	r8,r8,r8		@ zero or ...
+	ldrhsb	r8,[r12],#16			@ ... load input
+	eorlo	r9,r9,r9
+	ldrhsb	r9,[r12,#-12]
+
+	add	r7,r7,r11
+# ifdef	__thumb2__
+	itete	lo
+# endif
+	eorlo	r10,r10,r10
+	ldrhsb	r10,[r12,#-8]
+	eorlo	r11,r11,r11
+	ldrhsb	r11,[r12,#-4]
+
+	eor	r4,r8,r4		@ xor with input (or zero)
+	eor	r5,r9,r5
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	ldrhsb	r8,[r12,#-15]		@ load more input
+	ldrhsb	r9,[r12,#-11]
+	eor	r6,r10,r6
+	strb	r4,[r14],#16		@ store output
+	eor	r7,r11,r7
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	ldrhsb	r10,[r12,#-7]
+	ldrhsb	r11,[r12,#-3]
+	strb	r5,[r14,#-12]
+	eor	r4,r8,r4,lsr#8
+	strb	r6,[r14,#-8]
+	eor	r5,r9,r5,lsr#8
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	ldrhsb	r8,[r12,#-14]		@ load more input
+	ldrhsb	r9,[r12,#-10]
+	strb	r7,[r14,#-4]
+	eor	r6,r10,r6,lsr#8
+	strb	r4,[r14,#-15]
+	eor	r7,r11,r7,lsr#8
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	ldrhsb	r10,[r12,#-6]
+	ldrhsb	r11,[r12,#-2]
+	strb	r5,[r14,#-11]
+	eor	r4,r8,r4,lsr#8
+	strb	r6,[r14,#-7]
+	eor	r5,r9,r5,lsr#8
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	ldrhsb	r8,[r12,#-13]		@ load more input
+	ldrhsb	r9,[r12,#-9]
+	strb	r7,[r14,#-3]
+	eor	r6,r10,r6,lsr#8
+	strb	r4,[r14,#-14]
+	eor	r7,r11,r7,lsr#8
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	ldrhsb	r10,[r12,#-5]
+	ldrhsb	r11,[r12,#-1]
+	strb	r5,[r14,#-10]
+	strb	r6,[r14,#-6]
+	eor	r4,r8,r4,lsr#8
+	strb	r7,[r14,#-2]
+	eor	r5,r9,r5,lsr#8
+	strb	r4,[r14,#-13]
+	eor	r6,r10,r6,lsr#8
+	strb	r5,[r14,#-9]
+	eor	r7,r11,r7,lsr#8
+	strb	r6,[r14,#-5]
+	strb	r7,[r14,#-1]
+	add	r8,sp,#4*(4+4)
+	ldmia	r8,{r8,r9,r10,r11}		@ load key material
+	ldmia	r0,{r0,r1,r2,r3,r4,r5,r6,r7}		@ load second half
+# ifdef	__thumb2__
+	itt	hi
+# endif
+	strhi	r10,[sp,#4*(16+10)]		@ copy "rx"
+	strhi	r11,[sp,#4*(16+11)]		@ copy "rx"
+	add	r0,r0,r8		@ accumulate key material
+	add	r1,r1,r9
+	add	r2,r2,r10
+# ifdef	__thumb2__
+	itete	lo
+# endif
+	eorlo	r8,r8,r8		@ zero or ...
+	ldrhsb	r8,[r12],#16			@ ... load input
+	eorlo	r9,r9,r9
+	ldrhsb	r9,[r12,#-12]
+
+	add	r3,r3,r11
+# ifdef	__thumb2__
+	itete	lo
+# endif
+	eorlo	r10,r10,r10
+	ldrhsb	r10,[r12,#-8]
+	eorlo	r11,r11,r11
+	ldrhsb	r11,[r12,#-4]
+
+	eor	r0,r8,r0		@ xor with input (or zero)
+	eor	r1,r9,r1
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	ldrhsb	r8,[r12,#-15]		@ load more input
+	ldrhsb	r9,[r12,#-11]
+	eor	r2,r10,r2
+	strb	r0,[r14],#16		@ store output
+	eor	r3,r11,r3
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	ldrhsb	r10,[r12,#-7]
+	ldrhsb	r11,[r12,#-3]
+	strb	r1,[r14,#-12]
+	eor	r0,r8,r0,lsr#8
+	strb	r2,[r14,#-8]
+	eor	r1,r9,r1,lsr#8
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	ldrhsb	r8,[r12,#-14]		@ load more input
+	ldrhsb	r9,[r12,#-10]
+	strb	r3,[r14,#-4]
+	eor	r2,r10,r2,lsr#8
+	strb	r0,[r14,#-15]
+	eor	r3,r11,r3,lsr#8
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	ldrhsb	r10,[r12,#-6]
+	ldrhsb	r11,[r12,#-2]
+	strb	r1,[r14,#-11]
+	eor	r0,r8,r0,lsr#8
+	strb	r2,[r14,#-7]
+	eor	r1,r9,r1,lsr#8
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	ldrhsb	r8,[r12,#-13]		@ load more input
+	ldrhsb	r9,[r12,#-9]
+	strb	r3,[r14,#-3]
+	eor	r2,r10,r2,lsr#8
+	strb	r0,[r14,#-14]
+	eor	r3,r11,r3,lsr#8
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	ldrhsb	r10,[r12,#-5]
+	ldrhsb	r11,[r12,#-1]
+	strb	r1,[r14,#-10]
+	strb	r2,[r14,#-6]
+	eor	r0,r8,r0,lsr#8
+	strb	r3,[r14,#-2]
+	eor	r1,r9,r1,lsr#8
+	strb	r0,[r14,#-13]
+	eor	r2,r10,r2,lsr#8
+	strb	r1,[r14,#-9]
+	eor	r3,r11,r3,lsr#8
+	strb	r2,[r14,#-5]
+	strb	r3,[r14,#-1]
+	add	r8,sp,#4*(4+8)
+	ldmia	r8,{r8,r9,r10,r11}		@ load key material
+	add	r4,r4,r8		@ accumulate key material
+# ifdef	__thumb2__
+	itt	hi
+# endif
+	addhi	r8,r8,#1			@ next counter value
+	strhi	r8,[sp,#4*(12)]		@ save next counter value
+	add	r5,r5,r9
+	add	r6,r6,r10
+# ifdef	__thumb2__
+	itete	lo
+# endif
+	eorlo	r8,r8,r8		@ zero or ...
+	ldrhsb	r8,[r12],#16			@ ... load input
+	eorlo	r9,r9,r9
+	ldrhsb	r9,[r12,#-12]
+
+	add	r7,r7,r11
+# ifdef	__thumb2__
+	itete	lo
+# endif
+	eorlo	r10,r10,r10
+	ldrhsb	r10,[r12,#-8]
+	eorlo	r11,r11,r11
+	ldrhsb	r11,[r12,#-4]
+
+	eor	r4,r8,r4		@ xor with input (or zero)
+	eor	r5,r9,r5
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	ldrhsb	r8,[r12,#-15]		@ load more input
+	ldrhsb	r9,[r12,#-11]
+	eor	r6,r10,r6
+	strb	r4,[r14],#16		@ store output
+	eor	r7,r11,r7
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	ldrhsb	r10,[r12,#-7]
+	ldrhsb	r11,[r12,#-3]
+	strb	r5,[r14,#-12]
+	eor	r4,r8,r4,lsr#8
+	strb	r6,[r14,#-8]
+	eor	r5,r9,r5,lsr#8
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	ldrhsb	r8,[r12,#-14]		@ load more input
+	ldrhsb	r9,[r12,#-10]
+	strb	r7,[r14,#-4]
+	eor	r6,r10,r6,lsr#8
+	strb	r4,[r14,#-15]
+	eor	r7,r11,r7,lsr#8
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	ldrhsb	r10,[r12,#-6]
+	ldrhsb	r11,[r12,#-2]
+	strb	r5,[r14,#-11]
+	eor	r4,r8,r4,lsr#8
+	strb	r6,[r14,#-7]
+	eor	r5,r9,r5,lsr#8
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	ldrhsb	r8,[r12,#-13]		@ load more input
+	ldrhsb	r9,[r12,#-9]
+	strb	r7,[r14,#-3]
+	eor	r6,r10,r6,lsr#8
+	strb	r4,[r14,#-14]
+	eor	r7,r11,r7,lsr#8
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	ldrhsb	r10,[r12,#-5]
+	ldrhsb	r11,[r12,#-1]
+	strb	r5,[r14,#-10]
+	strb	r6,[r14,#-6]
+	eor	r4,r8,r4,lsr#8
+	strb	r7,[r14,#-2]
+	eor	r5,r9,r5,lsr#8
+	strb	r4,[r14,#-13]
+	eor	r6,r10,r6,lsr#8
+	strb	r5,[r14,#-9]
+	eor	r7,r11,r7,lsr#8
+	strb	r6,[r14,#-5]
+	strb	r7,[r14,#-1]
+# ifdef	__thumb2__
+	it	ne
+# endif
+	ldrne	r8,[sp,#4*(32+2)]		@ re-load len
+# ifdef	__thumb2__
+	it	hs
+# endif
+	subhs	r11,r8,#64			@ len-=64
+	bhi	.Loop_outer
+
+	beq	.Ldone
+#endif
+
+.Ltail:
+	ldr	r12,[sp,#4*(32+1)]	@ load inp
+	add	r9,sp,#4*(0)
+	ldr	r14,[sp,#4*(32+0)]	@ load out
+
+.Loop_tail:
+	ldrb	r10,[r9],#1	@ read buffer on stack
+	ldrb	r11,[r12],#1		@ read input
+	subs	r8,r8,#1
+	eor	r11,r11,r10
+	strb	r11,[r14],#1		@ store output
+	bne	.Loop_tail
+
+.Ldone:
+	add	sp,sp,#4*(32+3)
+.Lno_data:
+	ldmia	sp!,{r4,r5,r6,r7,r8,r9,r10,r11,pc}
+.size	ChaCha20_ctr32,.-ChaCha20_ctr32
+#if __ARM_MAX_ARCH__>=7
+.arch	armv7-a
+.fpu	neon
+
+.type	ChaCha20_neon,%function
+.align	5
+ChaCha20_neon:
+	ldr	r12,[sp,#0]		@ pull pointer to counter and nonce
+	stmdb	sp!,{r0,r1,r2,r4-r11,lr}
+.LChaCha20_neon:
+	adr	r14,.Lsigma
+	vstmdb	sp!,{d8,d9,d10,d11,d12,d13,d14,d15}		@ ABI spec says so
+	stmdb	sp!,{r0,r1,r2,r3}
+
+	vld1.32	{q1,q2},[r3]		@ load key
+	ldmia	r3,{r4,r5,r6,r7,r8,r9,r10,r11}		@ load key
+
+	sub	sp,sp,#4*(16+16)
+	vld1.32	{q3},[r12]		@ load counter and nonce
+	add	r12,sp,#4*8
+	ldmia	r14,{r0,r1,r2,r3}		@ load sigma
+	vld1.32	{q0},[r14]!		@ load sigma
+	vld1.32	{q12},[r14]		@ one
+	vst1.32	{q2,q3},[r12]		@ copy 1/2key|counter|nonce
+	vst1.32	{q0,q1},[sp]		@ copy sigma|1/2key
+
+	str	r10,[sp,#4*(16+10)]	@ off-load "rx"
+	str	r11,[sp,#4*(16+11)]	@ off-load "rx"
+	vshl.i32	d26,d24,#1	@ two
+	vstr	d24,[sp,#4*(16+0)]
+	vshl.i32	d28,d24,#2	@ four
+	vstr	d26,[sp,#4*(16+2)]
+	vmov	q4,q0
+	vstr	d28,[sp,#4*(16+4)]
+	vmov	q8,q0
+	vmov	q5,q1
+	vmov	q9,q1
+	b	.Loop_neon_enter
+
+.align	4
+.Loop_neon_outer:
+	ldmia	sp,{r0,r1,r2,r3,r4,r5,r6,r7,r8,r9}		@ load key material
+	cmp	r11,#64*2		@ if len<=64*2
+	bls	.Lbreak_neon		@ switch to integer-only
+	vmov	q4,q0
+	str	r11,[sp,#4*(32+2)]	@ save len
+	vmov	q8,q0
+	str	r12,  [sp,#4*(32+1)]	@ save inp
+	vmov	q5,q1
+	str	r14,  [sp,#4*(32+0)]	@ save out
+	vmov	q9,q1
+.Loop_neon_enter:
+	ldr	r11, [sp,#4*(15)]
+	vadd.i32	q7,q3,q12		@ counter+1
+	ldr	r12,[sp,#4*(12)]	@ modulo-scheduled load
+	vmov	q6,q2
+	ldr	r10, [sp,#4*(13)]
+	vmov	q10,q2
+	ldr	r14,[sp,#4*(14)]
+	vadd.i32	q11,q7,q12		@ counter+2
+	str	r11, [sp,#4*(16+15)]
+	mov	r11,#10
+	add	r12,r12,#3	@ counter+3
+	b	.Loop_neon
+
+.align	4
+.Loop_neon:
+	subs	r11,r11,#1
+	vadd.i32	q0,q0,q1
+	add	r0,r0,r4
+	vadd.i32	q4,q4,q5
+	mov	r12,r12,ror#16
+	vadd.i32	q8,q8,q9
+	add	r1,r1,r5
+	veor	q3,q3,q0
+	mov	r10,r10,ror#16
+	veor	q7,q7,q4
+	eor	r12,r12,r0,ror#16
+	veor	q11,q11,q8
+	eor	r10,r10,r1,ror#16
+	vrev32.16	q3,q3
+	add	r8,r8,r12
+	vrev32.16	q7,q7
+	mov	r4,r4,ror#20
+	vrev32.16	q11,q11
+	add	r9,r9,r10
+	vadd.i32	q2,q2,q3
+	mov	r5,r5,ror#20
+	vadd.i32	q6,q6,q7
+	eor	r4,r4,r8,ror#20
+	vadd.i32	q10,q10,q11
+	eor	r5,r5,r9,ror#20
+	veor	q12,q1,q2
+	add	r0,r0,r4
+	veor	q13,q5,q6
+	mov	r12,r12,ror#24
+	veor	q14,q9,q10
+	add	r1,r1,r5
+	vshr.u32	q1,q12,#20
+	mov	r10,r10,ror#24
+	vshr.u32	q5,q13,#20
+	eor	r12,r12,r0,ror#24
+	vshr.u32	q9,q14,#20
+	eor	r10,r10,r1,ror#24
+	vsli.32	q1,q12,#12
+	add	r8,r8,r12
+	vsli.32	q5,q13,#12
+	mov	r4,r4,ror#25
+	vsli.32	q9,q14,#12
+	add	r9,r9,r10
+	vadd.i32	q0,q0,q1
+	mov	r5,r5,ror#25
+	vadd.i32	q4,q4,q5
+	str	r10,[sp,#4*(16+13)]
+	vadd.i32	q8,q8,q9
+	ldr	r10,[sp,#4*(16+15)]
+	veor	q12,q3,q0
+	eor	r4,r4,r8,ror#25
+	veor	q13,q7,q4
+	eor	r5,r5,r9,ror#25
+	veor	q14,q11,q8
+	str	r8,[sp,#4*(16+8)]
+	vshr.u32	q3,q12,#24
+	ldr	r8,[sp,#4*(16+10)]
+	vshr.u32	q7,q13,#24
+	add	r2,r2,r6
+	vshr.u32	q11,q14,#24
+	mov	r14,r14,ror#16
+	vsli.32	q3,q12,#8
+	str	r9,[sp,#4*(16+9)]
+	vsli.32	q7,q13,#8
+	ldr	r9,[sp,#4*(16+11)]
+	vsli.32	q11,q14,#8
+	add	r3,r3,r7
+	vadd.i32	q2,q2,q3
+	mov	r10,r10,ror#16
+	vadd.i32	q6,q6,q7
+	eor	r14,r14,r2,ror#16
+	vadd.i32	q10,q10,q11
+	eor	r10,r10,r3,ror#16
+	veor	q12,q1,q2
+	add	r8,r8,r14
+	veor	q13,q5,q6
+	mov	r6,r6,ror#20
+	veor	q14,q9,q10
+	add	r9,r9,r10
+	vshr.u32	q1,q12,#25
+	mov	r7,r7,ror#20
+	vshr.u32	q5,q13,#25
+	eor	r6,r6,r8,ror#20
+	vshr.u32	q9,q14,#25
+	eor	r7,r7,r9,ror#20
+	vsli.32	q1,q12,#7
+	add	r2,r2,r6
+	vsli.32	q5,q13,#7
+	mov	r14,r14,ror#24
+	vsli.32	q9,q14,#7
+	add	r3,r3,r7
+	vext.8	q2,q2,q2,#8
+	mov	r10,r10,ror#24
+	vext.8	q6,q6,q6,#8
+	eor	r14,r14,r2,ror#24
+	vext.8	q10,q10,q10,#8
+	eor	r10,r10,r3,ror#24
+	vext.8	q1,q1,q1,#4
+	add	r8,r8,r14
+	vext.8	q5,q5,q5,#4
+	mov	r6,r6,ror#25
+	vext.8	q9,q9,q9,#4
+	add	r9,r9,r10
+	vext.8	q3,q3,q3,#12
+	mov	r7,r7,ror#25
+	vext.8	q7,q7,q7,#12
+	eor	r6,r6,r8,ror#25
+	vext.8	q11,q11,q11,#12
+	eor	r7,r7,r9,ror#25
+	vadd.i32	q0,q0,q1
+	add	r0,r0,r5
+	vadd.i32	q4,q4,q5
+	mov	r10,r10,ror#16
+	vadd.i32	q8,q8,q9
+	add	r1,r1,r6
+	veor	q3,q3,q0
+	mov	r12,r12,ror#16
+	veor	q7,q7,q4
+	eor	r10,r10,r0,ror#16
+	veor	q11,q11,q8
+	eor	r12,r12,r1,ror#16
+	vrev32.16	q3,q3
+	add	r8,r8,r10
+	vrev32.16	q7,q7
+	mov	r5,r5,ror#20
+	vrev32.16	q11,q11
+	add	r9,r9,r12
+	vadd.i32	q2,q2,q3
+	mov	r6,r6,ror#20
+	vadd.i32	q6,q6,q7
+	eor	r5,r5,r8,ror#20
+	vadd.i32	q10,q10,q11
+	eor	r6,r6,r9,ror#20
+	veor	q12,q1,q2
+	add	r0,r0,r5
+	veor	q13,q5,q6
+	mov	r10,r10,ror#24
+	veor	q14,q9,q10
+	add	r1,r1,r6
+	vshr.u32	q1,q12,#20
+	mov	r12,r12,ror#24
+	vshr.u32	q5,q13,#20
+	eor	r10,r10,r0,ror#24
+	vshr.u32	q9,q14,#20
+	eor	r12,r12,r1,ror#24
+	vsli.32	q1,q12,#12
+	add	r8,r8,r10
+	vsli.32	q5,q13,#12
+	mov	r5,r5,ror#25
+	vsli.32	q9,q14,#12
+	str	r10,[sp,#4*(16+15)]
+	vadd.i32	q0,q0,q1
+	ldr	r10,[sp,#4*(16+13)]
+	vadd.i32	q4,q4,q5
+	add	r9,r9,r12
+	vadd.i32	q8,q8,q9
+	mov	r6,r6,ror#25
+	veor	q12,q3,q0
+	eor	r5,r5,r8,ror#25
+	veor	q13,q7,q4
+	eor	r6,r6,r9,ror#25
+	veor	q14,q11,q8
+	str	r8,[sp,#4*(16+10)]
+	vshr.u32	q3,q12,#24
+	ldr	r8,[sp,#4*(16+8)]
+	vshr.u32	q7,q13,#24
+	add	r2,r2,r7
+	vshr.u32	q11,q14,#24
+	mov	r10,r10,ror#16
+	vsli.32	q3,q12,#8
+	str	r9,[sp,#4*(16+11)]
+	vsli.32	q7,q13,#8
+	ldr	r9,[sp,#4*(16+9)]
+	vsli.32	q11,q14,#8
+	add	r3,r3,r4
+	vadd.i32	q2,q2,q3
+	mov	r14,r14,ror#16
+	vadd.i32	q6,q6,q7
+	eor	r10,r10,r2,ror#16
+	vadd.i32	q10,q10,q11
+	eor	r14,r14,r3,ror#16
+	veor	q12,q1,q2
+	add	r8,r8,r10
+	veor	q13,q5,q6
+	mov	r7,r7,ror#20
+	veor	q14,q9,q10
+	add	r9,r9,r14
+	vshr.u32	q1,q12,#25
+	mov	r4,r4,ror#20
+	vshr.u32	q5,q13,#25
+	eor	r7,r7,r8,ror#20
+	vshr.u32	q9,q14,#25
+	eor	r4,r4,r9,ror#20
+	vsli.32	q1,q12,#7
+	add	r2,r2,r7
+	vsli.32	q5,q13,#7
+	mov	r10,r10,ror#24
+	vsli.32	q9,q14,#7
+	add	r3,r3,r4
+	vext.8	q2,q2,q2,#8
+	mov	r14,r14,ror#24
+	vext.8	q6,q6,q6,#8
+	eor	r10,r10,r2,ror#24
+	vext.8	q10,q10,q10,#8
+	eor	r14,r14,r3,ror#24
+	vext.8	q1,q1,q1,#12
+	add	r8,r8,r10
+	vext.8	q5,q5,q5,#12
+	mov	r7,r7,ror#25
+	vext.8	q9,q9,q9,#12
+	add	r9,r9,r14
+	vext.8	q3,q3,q3,#4
+	mov	r4,r4,ror#25
+	vext.8	q7,q7,q7,#4
+	eor	r7,r7,r8,ror#25
+	vext.8	q11,q11,q11,#4
+	eor	r4,r4,r9,ror#25
+	bne	.Loop_neon
+
+	add	r11,sp,#32
+	vld1.32	{q12,q13},[sp]		@ load key material
+	vld1.32	{q14,q15},[r11]
+
+	ldr	r11,[sp,#4*(32+2)]	@ load len
+
+	str	r8, [sp,#4*(16+8)]	@ modulo-scheduled store
+	str	r9, [sp,#4*(16+9)]
+	str	r12,[sp,#4*(16+12)]
+	str	r10, [sp,#4*(16+13)]
+	str	r14,[sp,#4*(16+14)]
+
+	@ at this point we have first half of 512-bit result in
+	@ rx and second half at sp+4*(16+8)
+
+	ldr	r12,[sp,#4*(32+1)]	@ load inp
+	ldr	r14,[sp,#4*(32+0)]	@ load out
+
+	vadd.i32	q0,q0,q12		@ accumulate key material
+	vadd.i32	q4,q4,q12
+	vadd.i32	q8,q8,q12
+	vldr	d24,[sp,#4*(16+0)]	@ one
+
+	vadd.i32	q1,q1,q13
+	vadd.i32	q5,q5,q13
+	vadd.i32	q9,q9,q13
+	vldr	d26,[sp,#4*(16+2)]	@ two
+
+	vadd.i32	q2,q2,q14
+	vadd.i32	q6,q6,q14
+	vadd.i32	q10,q10,q14
+	vadd.i32	d14,d14,d24	@ counter+1
+	vadd.i32	d22,d22,d26	@ counter+2
+
+	vadd.i32	q3,q3,q15
+	vadd.i32	q7,q7,q15
+	vadd.i32	q11,q11,q15
+
+	cmp	r11,#64*4
+	blo	.Ltail_neon
+
+	vld1.8	{q12,q13},[r12]!	@ load input
+	mov	r11,sp
+	vld1.8	{q14,q15},[r12]!
+	veor	q0,q0,q12		@ xor with input
+	veor	q1,q1,q13
+	vld1.8	{q12,q13},[r12]!
+	veor	q2,q2,q14
+	veor	q3,q3,q15
+	vld1.8	{q14,q15},[r12]!
+
+	veor	q4,q4,q12
+	vst1.8	{q0,q1},[r14]!	@ store output
+	veor	q5,q5,q13
+	vld1.8	{q12,q13},[r12]!
+	veor	q6,q6,q14
+	vst1.8	{q2,q3},[r14]!
+	veor	q7,q7,q15
+	vld1.8	{q14,q15},[r12]!
+
+	veor	q8,q8,q12
+	vld1.32	{q0,q1},[r11]!	@ load for next iteration
+	veor	d25,d25,d25
+	vldr	d24,[sp,#4*(16+4)]	@ four
+	veor	q9,q9,q13
+	vld1.32	{q2,q3},[r11]
+	veor	q10,q10,q14
+	vst1.8	{q4,q5},[r14]!
+	veor	q11,q11,q15
+	vst1.8	{q6,q7},[r14]!
+
+	vadd.i32	d6,d6,d24	@ next counter value
+	vldr	d24,[sp,#4*(16+0)]	@ one
+
+	ldmia	sp,{r8,r9,r10,r11}	@ load key material
+	add	r0,r0,r8	@ accumulate key material
+	ldr	r8,[r12],#16		@ load input
+	vst1.8	{q8,q9},[r14]!
+	add	r1,r1,r9
+	ldr	r9,[r12,#-12]
+	vst1.8	{q10,q11},[r14]!
+	add	r2,r2,r10
+	ldr	r10,[r12,#-8]
+	add	r3,r3,r11
+	ldr	r11,[r12,#-4]
+# ifdef	__ARMEB__
+	rev	r0,r0
+	rev	r1,r1
+	rev	r2,r2
+	rev	r3,r3
+# endif
+	eor	r0,r0,r8	@ xor with input
+	add	r8,sp,#4*(4)
+	eor	r1,r1,r9
+	str	r0,[r14],#16		@ store output
+	eor	r2,r2,r10
+	str	r1,[r14,#-12]
+	eor	r3,r3,r11
+	ldmia	r8,{r8,r9,r10,r11}	@ load key material
+	str	r2,[r14,#-8]
+	str	r3,[r14,#-4]
+
+	add	r4,r4,r8	@ accumulate key material
+	ldr	r8,[r12],#16		@ load input
+	add	r5,r5,r9
+	ldr	r9,[r12,#-12]
+	add	r6,r6,r10
+	ldr	r10,[r12,#-8]
+	add	r7,r7,r11
+	ldr	r11,[r12,#-4]
+# ifdef	__ARMEB__
+	rev	r4,r4
+	rev	r5,r5
+	rev	r6,r6
+	rev	r7,r7
+# endif
+	eor	r4,r4,r8
+	add	r8,sp,#4*(8)
+	eor	r5,r5,r9
+	str	r4,[r14],#16		@ store output
+	eor	r6,r6,r10
+	str	r5,[r14,#-12]
+	eor	r7,r7,r11
+	ldmia	r8,{r8,r9,r10,r11}	@ load key material
+	str	r6,[r14,#-8]
+	add	r0,sp,#4*(16+8)
+	str	r7,[r14,#-4]
+
+	ldmia	r0,{r0,r1,r2,r3,r4,r5,r6,r7}	@ load second half
+
+	add	r0,r0,r8	@ accumulate key material
+	ldr	r8,[r12],#16		@ load input
+	add	r1,r1,r9
+	ldr	r9,[r12,#-12]
+# ifdef	__thumb2__
+	it	hi
+# endif
+	strhi	r10,[sp,#4*(16+10)]	@ copy "rx" while at it
+	add	r2,r2,r10
+	ldr	r10,[r12,#-8]
+# ifdef	__thumb2__
+	it	hi
+# endif
+	strhi	r11,[sp,#4*(16+11)]	@ copy "rx" while at it
+	add	r3,r3,r11
+	ldr	r11,[r12,#-4]
+# ifdef	__ARMEB__
+	rev	r0,r0
+	rev	r1,r1
+	rev	r2,r2
+	rev	r3,r3
+# endif
+	eor	r0,r0,r8
+	add	r8,sp,#4*(12)
+	eor	r1,r1,r9
+	str	r0,[r14],#16		@ store output
+	eor	r2,r2,r10
+	str	r1,[r14,#-12]
+	eor	r3,r3,r11
+	ldmia	r8,{r8,r9,r10,r11}	@ load key material
+	str	r2,[r14,#-8]
+	str	r3,[r14,#-4]
+
+	add	r4,r4,r8	@ accumulate key material
+	add	r8,r8,#4		@ next counter value
+	add	r5,r5,r9
+	str	r8,[sp,#4*(12)]	@ save next counter value
+	ldr	r8,[r12],#16		@ load input
+	add	r6,r6,r10
+	add	r4,r4,#3		@ counter+3
+	ldr	r9,[r12,#-12]
+	add	r7,r7,r11
+	ldr	r10,[r12,#-8]
+	ldr	r11,[r12,#-4]
+# ifdef	__ARMEB__
+	rev	r4,r4
+	rev	r5,r5
+	rev	r6,r6
+	rev	r7,r7
+# endif
+	eor	r4,r4,r8
+# ifdef	__thumb2__
+	it	hi
+# endif
+	ldrhi	r8,[sp,#4*(32+2)]	@ re-load len
+	eor	r5,r5,r9
+	eor	r6,r6,r10
+	str	r4,[r14],#16		@ store output
+	eor	r7,r7,r11
+	str	r5,[r14,#-12]
+	sub	r11,r8,#64*4	@ len-=64*4
+	str	r6,[r14,#-8]
+	str	r7,[r14,#-4]
+	bhi	.Loop_neon_outer
+
+	b	.Ldone_neon
+
+.align	4
+.Lbreak_neon:
+	@ harmonize NEON and integer-only stack frames: load data
+	@ from NEON frame, but save to integer-only one; distance
+	@ between the two is 4*(32+4+16-32)=4*(20).
+
+	str	r11, [sp,#4*(20+32+2)]	@ save len
+	add	r11,sp,#4*(32+4)
+	str	r12,   [sp,#4*(20+32+1)]	@ save inp
+	str	r14,   [sp,#4*(20+32+0)]	@ save out
+
+	ldr	r12,[sp,#4*(16+10)]
+	ldr	r14,[sp,#4*(16+11)]
+	vldmia	r11,{d8,d9,d10,d11,d12,d13,d14,d15}			@ fulfill ABI requirement
+	str	r12,[sp,#4*(20+16+10)]	@ copy "rx"
+	str	r14,[sp,#4*(20+16+11)]	@ copy "rx"
+
+	ldr	r11, [sp,#4*(15)]
+	ldr	r12,[sp,#4*(12)]		@ modulo-scheduled load
+	ldr	r10, [sp,#4*(13)]
+	ldr	r14,[sp,#4*(14)]
+	str	r11, [sp,#4*(20+16+15)]
+	add	r11,sp,#4*(20)
+	vst1.32	{q0,q1},[r11]!		@ copy key
+	add	sp,sp,#4*(20)			@ switch frame
+	vst1.32	{q2,q3},[r11]
+	mov	r11,#10
+	b	.Loop				@ go integer-only
+
+.align	4
+.Ltail_neon:
+	cmp	r11,#64*3
+	bhs	.L192_or_more_neon
+	cmp	r11,#64*2
+	bhs	.L128_or_more_neon
+	cmp	r11,#64*1
+	bhs	.L64_or_more_neon
+
+	add	r8,sp,#4*(8)
+	vst1.8	{q0,q1},[sp]
+	add	r10,sp,#4*(0)
+	vst1.8	{q2,q3},[r8]
+	b	.Loop_tail_neon
+
+.align	4
+.L64_or_more_neon:
+	vld1.8	{q12,q13},[r12]!
+	vld1.8	{q14,q15},[r12]!
+	veor	q0,q0,q12
+	veor	q1,q1,q13
+	veor	q2,q2,q14
+	veor	q3,q3,q15
+	vst1.8	{q0,q1},[r14]!
+	vst1.8	{q2,q3},[r14]!
+
+	beq	.Ldone_neon
+
+	add	r8,sp,#4*(8)
+	vst1.8	{q4,q5},[sp]
+	add	r10,sp,#4*(0)
+	vst1.8	{q6,q7},[r8]
+	sub	r11,r11,#64*1	@ len-=64*1
+	b	.Loop_tail_neon
+
+.align	4
+.L128_or_more_neon:
+	vld1.8	{q12,q13},[r12]!
+	vld1.8	{q14,q15},[r12]!
+	veor	q0,q0,q12
+	veor	q1,q1,q13
+	vld1.8	{q12,q13},[r12]!
+	veor	q2,q2,q14
+	veor	q3,q3,q15
+	vld1.8	{q14,q15},[r12]!
+
+	veor	q4,q4,q12
+	veor	q5,q5,q13
+	vst1.8	{q0,q1},[r14]!
+	veor	q6,q6,q14
+	vst1.8	{q2,q3},[r14]!
+	veor	q7,q7,q15
+	vst1.8	{q4,q5},[r14]!
+	vst1.8	{q6,q7},[r14]!
+
+	beq	.Ldone_neon
+
+	add	r8,sp,#4*(8)
+	vst1.8	{q8,q9},[sp]
+	add	r10,sp,#4*(0)
+	vst1.8	{q10,q11},[r8]
+	sub	r11,r11,#64*2	@ len-=64*2
+	b	.Loop_tail_neon
+
+.align	4
+.L192_or_more_neon:
+	vld1.8	{q12,q13},[r12]!
+	vld1.8	{q14,q15},[r12]!
+	veor	q0,q0,q12
+	veor	q1,q1,q13
+	vld1.8	{q12,q13},[r12]!
+	veor	q2,q2,q14
+	veor	q3,q3,q15
+	vld1.8	{q14,q15},[r12]!
+
+	veor	q4,q4,q12
+	veor	q5,q5,q13
+	vld1.8	{q12,q13},[r12]!
+	veor	q6,q6,q14
+	vst1.8	{q0,q1},[r14]!
+	veor	q7,q7,q15
+	vld1.8	{q14,q15},[r12]!
+
+	veor	q8,q8,q12
+	vst1.8	{q2,q3},[r14]!
+	veor	q9,q9,q13
+	vst1.8	{q4,q5},[r14]!
+	veor	q10,q10,q14
+	vst1.8	{q6,q7},[r14]!
+	veor	q11,q11,q15
+	vst1.8	{q8,q9},[r14]!
+	vst1.8	{q10,q11},[r14]!
+
+	beq	.Ldone_neon
+
+	ldmia	sp,{r8,r9,r10,r11}	@ load key material
+	add	r0,r0,r8	@ accumulate key material
+	add	r8,sp,#4*(4)
+	add	r1,r1,r9
+	add	r2,r2,r10
+	add	r3,r3,r11
+	ldmia	r8,{r8,r9,r10,r11}	@ load key material
+
+	add	r4,r4,r8	@ accumulate key material
+	add	r8,sp,#4*(8)
+	add	r5,r5,r9
+	add	r6,r6,r10
+	add	r7,r7,r11
+	ldmia	r8,{r8,r9,r10,r11}	@ load key material
+# ifdef	__ARMEB__
+	rev	r0,r0
+	rev	r1,r1
+	rev	r2,r2
+	rev	r3,r3
+	rev	r4,r4
+	rev	r5,r5
+	rev	r6,r6
+	rev	r7,r7
+# endif
+	stmia	sp,{r0,r1,r2,r3,r4,r5,r6,r7}
+	add	r0,sp,#4*(16+8)
+
+	ldmia	r0,{r0,r1,r2,r3,r4,r5,r6,r7}	@ load second half
+
+	add	r0,r0,r8	@ accumulate key material
+	add	r8,sp,#4*(12)
+	add	r1,r1,r9
+	add	r2,r2,r10
+	add	r3,r3,r11
+	ldmia	r8,{r8,r9,r10,r11}	@ load key material
+
+	add	r4,r4,r8	@ accumulate key material
+	add	r8,sp,#4*(8)
+	add	r5,r5,r9
+	add	r4,r4,#3		@ counter+3
+	add	r6,r6,r10
+	add	r7,r7,r11
+	ldr	r11,[sp,#4*(32+2)]	@ re-load len
+# ifdef	__ARMEB__
+	rev	r0,r0
+	rev	r1,r1
+	rev	r2,r2
+	rev	r3,r3
+	rev	r4,r4
+	rev	r5,r5
+	rev	r6,r6
+	rev	r7,r7
+# endif
+	stmia	r8,{r0,r1,r2,r3,r4,r5,r6,r7}
+	add	r10,sp,#4*(0)
+	sub	r11,r11,#64*3	@ len-=64*3
+
+.Loop_tail_neon:
+	ldrb	r8,[r10],#1	@ read buffer on stack
+	ldrb	r9,[r12],#1		@ read input
+	subs	r11,r11,#1
+	eor	r8,r8,r9
+	strb	r8,[r14],#1		@ store ouput
+	bne	.Loop_tail_neon
+
+.Ldone_neon:
+	add	sp,sp,#4*(32+4)
+	vldmia	sp,{d8,d9,d10,d11,d12,d13,d14,d15}
+	add	sp,sp,#4*(16+3)
+	ldmia	sp!,{r4,r5,r6,r7,r8,r9,r10,r11,pc}
+.size	ChaCha20_neon,.-ChaCha20_neon
+.comm	OPENSSL_armcap_P,4,4
+#endif
+#endif
diff --git a/packager/third_party/boringssl/linux-arm/crypto/modes/ghash-armv4.S b/packager/third_party/boringssl/linux-arm/crypto/modes/ghash-armv4.S
index c6f025d759..791b28906c 100644
--- a/packager/third_party/boringssl/linux-arm/crypto/modes/ghash-armv4.S
+++ b/packager/third_party/boringssl/linux-arm/crypto/modes/ghash-armv4.S
@@ -1,13 +1,12 @@
 #if defined(__arm__)
-#if defined(__arm__)
-#include "arm_arch.h"
+#include <openssl/arm_arch.h>
 
 .syntax	unified
 
 .text
 .code	32
 
-#ifdef  __APPLE__
+#ifdef  __clang__
 #define ldrplb  ldrbpl
 #define ldrneb  ldrbne
 #endif
@@ -536,6 +535,4 @@ gcm_ghash_neon:
 .byte	71,72,65,83,72,32,102,111,114,32,65,82,77,118,52,47,78,69,79,78,44,32,67,82,89,80,84,79,71,65,77,83,32,98,121,32,60,97,112,112,114,111,64,111,112,101,110,115,115,108,46,111,114,103,62,0
 .align	2
 .align	2
-
 #endif
-#endif
\ No newline at end of file
diff --git a/packager/third_party/boringssl/linux-arm/crypto/modes/ghashv8-armx32.S b/packager/third_party/boringssl/linux-arm/crypto/modes/ghashv8-armx32.S
index bdbbae90d4..0e1e631486 100644
--- a/packager/third_party/boringssl/linux-arm/crypto/modes/ghashv8-armx32.S
+++ b/packager/third_party/boringssl/linux-arm/crypto/modes/ghashv8-armx32.S
@@ -1,10 +1,11 @@
 #if defined(__arm__)
-#include "arm_arch.h"
+#include <openssl/arm_arch.h>
 
 .text
 .fpu	neon
 .code	32
 .globl	gcm_init_v8
+.hidden	gcm_init_v8
 .type	gcm_init_v8,%function
 .align	4
 gcm_init_v8:
@@ -55,6 +56,7 @@ gcm_init_v8:
 	bx	lr
 .size	gcm_init_v8,.-gcm_init_v8
 .globl	gcm_gmult_v8
+.hidden	gcm_gmult_v8
 .type	gcm_gmult_v8,%function
 .align	4
 gcm_gmult_v8:
@@ -67,10 +69,10 @@ gcm_gmult_v8:
 #endif
 	vext.8	q3,q9,q9,#8
 
-.byte	0x86,0x0e,0xa8,0xf2	@ pmull q0,q12,q3		@ H.lo·Xi.lo
+.byte	0x86,0x0e,0xa8,0xf2	@ pmull q0,q12,q3		@ H.lo·Xi.lo
 	veor	q9,q9,q3		@ Karatsuba pre-processing
-.byte	0x87,0x4e,0xa9,0xf2	@ pmull2 q2,q12,q3		@ H.hi·Xi.hi
-.byte	0xa2,0x2e,0xaa,0xf2	@ pmull q1,q13,q9		@ (H.lo+H.hi)·(Xi.lo+Xi.hi)
+.byte	0x87,0x4e,0xa9,0xf2	@ pmull2 q2,q12,q3		@ H.hi·Xi.hi
+.byte	0xa2,0x2e,0xaa,0xf2	@ pmull q1,q13,q9		@ (H.lo+H.hi)·(Xi.lo+Xi.hi)
 
 	vext.8	q9,q0,q2,#8		@ Karatsuba post-processing
 	veor	q10,q0,q2
@@ -96,6 +98,7 @@ gcm_gmult_v8:
 	bx	lr
 .size	gcm_gmult_v8,.-gcm_gmult_v8
 .globl	gcm_ghash_v8
+.hidden	gcm_ghash_v8
 .type	gcm_ghash_v8,%function
 .align	4
 gcm_ghash_v8:
@@ -135,7 +138,7 @@ gcm_ghash_v8:
 #endif
 	vext.8	q7,q9,q9,#8
 	veor	q3,q3,q0		@ I[i]^=Xi
-.byte	0x8e,0x8e,0xa8,0xf2	@ pmull q4,q12,q7		@ H·Ii+1
+.byte	0x8e,0x8e,0xa8,0xf2	@ pmull q4,q12,q7		@ H·Ii+1
 	veor	q9,q9,q7		@ Karatsuba pre-processing
 .byte	0x8f,0xce,0xa9,0xf2	@ pmull2 q6,q12,q7
 	b	.Loop_mod2x_v8
@@ -144,14 +147,14 @@ gcm_ghash_v8:
 .Loop_mod2x_v8:
 	vext.8	q10,q3,q3,#8
 	subs	r3,r3,#32		@ is there more data?
-.byte	0x86,0x0e,0xac,0xf2	@ pmull q0,q14,q3		@ H^2.lo·Xi.lo
+.byte	0x86,0x0e,0xac,0xf2	@ pmull q0,q14,q3		@ H^2.lo·Xi.lo
 	movlo	r12,#0			@ is it time to zero r12?
 
 .byte	0xa2,0xae,0xaa,0xf2	@ pmull q5,q13,q9
 	veor	q10,q10,q3		@ Karatsuba pre-processing
-.byte	0x87,0x4e,0xad,0xf2	@ pmull2 q2,q14,q3		@ H^2.hi·Xi.hi
+.byte	0x87,0x4e,0xad,0xf2	@ pmull2 q2,q14,q3		@ H^2.hi·Xi.hi
 	veor	q0,q0,q4		@ accumulate
-.byte	0xa5,0x2e,0xab,0xf2	@ pmull2 q1,q13,q10		@ (H^2.lo+H^2.hi)·(Xi.lo+Xi.hi)
+.byte	0xa5,0x2e,0xab,0xf2	@ pmull2 q1,q13,q10		@ (H^2.lo+H^2.hi)·(Xi.lo+Xi.hi)
 	vld1.64	{q8},[r2],r12	@ load [rotated] I[i+2]
 
 	veor	q2,q2,q6
@@ -176,7 +179,7 @@ gcm_ghash_v8:
 	vext.8	q7,q9,q9,#8
 	vext.8	q3,q8,q8,#8
 	veor	q0,q1,q10
-.byte	0x8e,0x8e,0xa8,0xf2	@ pmull q4,q12,q7		@ H·Ii+1
+.byte	0x8e,0x8e,0xa8,0xf2	@ pmull q4,q12,q7		@ H·Ii+1
 	veor	q3,q3,q2		@ accumulate q3 early
 
 	vext.8	q10,q0,q0,#8		@ 2nd phase of reduction
@@ -197,10 +200,10 @@ gcm_ghash_v8:
 	veor	q3,q3,q0		@ inp^=Xi
 	veor	q9,q8,q10		@ q9 is rotated inp^Xi
 
-.byte	0x86,0x0e,0xa8,0xf2	@ pmull q0,q12,q3		@ H.lo·Xi.lo
+.byte	0x86,0x0e,0xa8,0xf2	@ pmull q0,q12,q3		@ H.lo·Xi.lo
 	veor	q9,q9,q3		@ Karatsuba pre-processing
-.byte	0x87,0x4e,0xa9,0xf2	@ pmull2 q2,q12,q3		@ H.hi·Xi.hi
-.byte	0xa2,0x2e,0xaa,0xf2	@ pmull q1,q13,q9		@ (H.lo+H.hi)·(Xi.lo+Xi.hi)
+.byte	0x87,0x4e,0xa9,0xf2	@ pmull2 q2,q12,q3		@ H.hi·Xi.hi
+.byte	0xa2,0x2e,0xaa,0xf2	@ pmull q1,q13,q9		@ (H.lo+H.hi)·(Xi.lo+Xi.hi)
 
 	vext.8	q9,q0,q2,#8		@ Karatsuba post-processing
 	veor	q10,q0,q2
@@ -230,4 +233,4 @@ gcm_ghash_v8:
 .byte	71,72,65,83,72,32,102,111,114,32,65,82,77,118,56,44,32,67,82,89,80,84,79,71,65,77,83,32,98,121,32,60,97,112,112,114,111,64,111,112,101,110,115,115,108,46,111,114,103,62,0
 .align	2
 .align	2
-#endif
\ No newline at end of file
+#endif
diff --git a/packager/third_party/boringssl/linux-arm/crypto/sha/sha1-armv4-large.S b/packager/third_party/boringssl/linux-arm/crypto/sha/sha1-armv4-large.S
index 4911458b26..36955faf19 100644
--- a/packager/third_party/boringssl/linux-arm/crypto/sha/sha1-armv4-large.S
+++ b/packager/third_party/boringssl/linux-arm/crypto/sha/sha1-armv4-large.S
@@ -1,10 +1,11 @@
 #if defined(__arm__)
-#include "arm_arch.h"
+#include <openssl/arm_arch.h>
 
 .text
 .code	32
 
 .globl	sha1_block_data_order
+.hidden	sha1_block_data_order
 .type	sha1_block_data_order,%function
 
 .align	5
@@ -1459,4 +1460,4 @@ sha1_block_data_order_armv8:
 .comm	OPENSSL_armcap_P,4,4
 .hidden	OPENSSL_armcap_P
 #endif
-#endif
\ No newline at end of file
+#endif
diff --git a/packager/third_party/boringssl/linux-arm/crypto/sha/sha256-armv4.S b/packager/third_party/boringssl/linux-arm/crypto/sha/sha256-armv4.S
index ac9f2f164d..6040041322 100644
--- a/packager/third_party/boringssl/linux-arm/crypto/sha/sha256-armv4.S
+++ b/packager/third_party/boringssl/linux-arm/crypto/sha/sha256-armv4.S
@@ -38,7 +38,7 @@
 @ Add ARMv8 code path performing at 2.0 cpb on Apple A7.
 
 #ifndef __KERNEL__
-# include "arm_arch.h"
+# include <openssl/arm_arch.h>
 #else
 # define __ARM_ARCH__ __LINUX_ARM_ARCH__
 # define __ARM_MAX_ARCH__ 7
@@ -85,6 +85,7 @@ K256:
 .align	5
 
 .globl	sha256_block_data_order
+.hidden	sha256_block_data_order
 .type	sha256_block_data_order,%function
 sha256_block_data_order:
 .Lsha256_block_data_order:
@@ -1875,6 +1876,7 @@ sha256_block_data_order:
 .fpu	neon
 
 .globl	sha256_block_data_order_neon
+.hidden	sha256_block_data_order_neon
 .type	sha256_block_data_order_neon,%function
 .align	4
 sha256_block_data_order_neon:
@@ -2815,4 +2817,4 @@ sha256_block_data_order_armv8:
 .comm	OPENSSL_armcap_P,4,4
 .hidden	OPENSSL_armcap_P
 #endif
-#endif
\ No newline at end of file
+#endif
diff --git a/packager/third_party/boringssl/linux-arm/crypto/sha/sha512-armv4.S b/packager/third_party/boringssl/linux-arm/crypto/sha/sha512-armv4.S
index c794f87fcf..93a7bf8566 100644
--- a/packager/third_party/boringssl/linux-arm/crypto/sha/sha512-armv4.S
+++ b/packager/third_party/boringssl/linux-arm/crypto/sha/sha512-armv4.S
@@ -47,7 +47,7 @@
 @ was reflected in below two parameters as 0 and 4. Now caller is
 @ expected to maintain native byte order for whole 64-bit values.
 #ifndef __KERNEL__
-# include "arm_arch.h"
+# include <openssl/arm_arch.h>
 # define VFP_ABI_PUSH	vstmdb	sp!,{d8-d15}
 # define VFP_ABI_POP	vldmia	sp!,{d8-d15}
 #else
@@ -133,6 +133,7 @@ K512:
 #endif
 
 .globl	sha512_block_data_order
+.hidden	sha512_block_data_order
 .type	sha512_block_data_order,%function
 sha512_block_data_order:
 .Lsha512_block_data_order:
@@ -147,7 +148,7 @@ sha512_block_data_order:
 #ifdef	__APPLE__
 	ldr	r12,[r12]
 #endif
-	tst	r12,#1
+	tst	r12,#ARMV7_NEON
 	bne	.LNEON
 #endif
 	add	r2,r1,r2,lsl#7	@ len to point at the end of inp
@@ -533,6 +534,7 @@ sha512_block_data_order:
 .fpu	neon
 
 .globl	sha512_block_data_order_neon
+.hidden	sha512_block_data_order_neon
 .type	sha512_block_data_order_neon,%function
 .align	4
 sha512_block_data_order_neon:
@@ -1866,4 +1868,4 @@ sha512_block_data_order_neon:
 .comm	OPENSSL_armcap_P,4,4
 .hidden	OPENSSL_armcap_P
 #endif
-#endif
\ No newline at end of file
+#endif
diff --git a/packager/third_party/boringssl/linux-x86/crypto/chacha/chacha-x86.S b/packager/third_party/boringssl/linux-x86/crypto/chacha/chacha-x86.S
new file mode 100644
index 0000000000..d3c39ace9b
--- /dev/null
+++ b/packager/third_party/boringssl/linux-x86/crypto/chacha/chacha-x86.S
@@ -0,0 +1,969 @@
+#if defined(__i386__)
+.file	"chacha-x86.S"
+.text
+.globl	ChaCha20_ctr32
+.hidden	ChaCha20_ctr32
+.type	ChaCha20_ctr32,@function
+.align	16
+ChaCha20_ctr32:
+.L_ChaCha20_ctr32_begin:
+	pushl	%ebp
+	pushl	%ebx
+	pushl	%esi
+	pushl	%edi
+	xorl	%eax,%eax
+	cmpl	28(%esp),%eax
+	je	.L000no_data
+	call	.Lpic_point
+.Lpic_point:
+	popl	%eax
+	leal	OPENSSL_ia32cap_P-.Lpic_point(%eax),%ebp
+	testl	$16777216,(%ebp)
+	jz	.L001x86
+	testl	$512,4(%ebp)
+	jz	.L001x86
+	jmp	.Lssse3_shortcut
+.L001x86:
+	movl	32(%esp),%esi
+	movl	36(%esp),%edi
+	subl	$132,%esp
+	movl	(%esi),%eax
+	movl	4(%esi),%ebx
+	movl	8(%esi),%ecx
+	movl	12(%esi),%edx
+	movl	%eax,80(%esp)
+	movl	%ebx,84(%esp)
+	movl	%ecx,88(%esp)
+	movl	%edx,92(%esp)
+	movl	16(%esi),%eax
+	movl	20(%esi),%ebx
+	movl	24(%esi),%ecx
+	movl	28(%esi),%edx
+	movl	%eax,96(%esp)
+	movl	%ebx,100(%esp)
+	movl	%ecx,104(%esp)
+	movl	%edx,108(%esp)
+	movl	(%edi),%eax
+	movl	4(%edi),%ebx
+	movl	8(%edi),%ecx
+	movl	12(%edi),%edx
+	subl	$1,%eax
+	movl	%eax,112(%esp)
+	movl	%ebx,116(%esp)
+	movl	%ecx,120(%esp)
+	movl	%edx,124(%esp)
+	jmp	.L002entry
+.align	16
+.L003outer_loop:
+	movl	%ebx,156(%esp)
+	movl	%eax,152(%esp)
+	movl	%ecx,160(%esp)
+.L002entry:
+	movl	$1634760805,%eax
+	movl	$857760878,4(%esp)
+	movl	$2036477234,8(%esp)
+	movl	$1797285236,12(%esp)
+	movl	84(%esp),%ebx
+	movl	88(%esp),%ebp
+	movl	104(%esp),%ecx
+	movl	108(%esp),%esi
+	movl	116(%esp),%edx
+	movl	120(%esp),%edi
+	movl	%ebx,20(%esp)
+	movl	%ebp,24(%esp)
+	movl	%ecx,40(%esp)
+	movl	%esi,44(%esp)
+	movl	%edx,52(%esp)
+	movl	%edi,56(%esp)
+	movl	92(%esp),%ebx
+	movl	124(%esp),%edi
+	movl	112(%esp),%edx
+	movl	80(%esp),%ebp
+	movl	96(%esp),%ecx
+	movl	100(%esp),%esi
+	addl	$1,%edx
+	movl	%ebx,28(%esp)
+	movl	%edi,60(%esp)
+	movl	%edx,112(%esp)
+	movl	$10,%ebx
+	jmp	.L004loop
+.align	16
+.L004loop:
+	addl	%ebp,%eax
+	movl	%ebx,128(%esp)
+	movl	%ebp,%ebx
+	xorl	%eax,%edx
+	roll	$16,%edx
+	addl	%edx,%ecx
+	xorl	%ecx,%ebx
+	movl	52(%esp),%edi
+	roll	$12,%ebx
+	movl	20(%esp),%ebp
+	addl	%ebx,%eax
+	xorl	%eax,%edx
+	movl	%eax,(%esp)
+	roll	$8,%edx
+	movl	4(%esp),%eax
+	addl	%edx,%ecx
+	movl	%edx,48(%esp)
+	xorl	%ecx,%ebx
+	addl	%ebp,%eax
+	roll	$7,%ebx
+	xorl	%eax,%edi
+	movl	%ecx,32(%esp)
+	roll	$16,%edi
+	movl	%ebx,16(%esp)
+	addl	%edi,%esi
+	movl	40(%esp),%ecx
+	xorl	%esi,%ebp
+	movl	56(%esp),%edx
+	roll	$12,%ebp
+	movl	24(%esp),%ebx
+	addl	%ebp,%eax
+	xorl	%eax,%edi
+	movl	%eax,4(%esp)
+	roll	$8,%edi
+	movl	8(%esp),%eax
+	addl	%edi,%esi
+	movl	%edi,52(%esp)
+	xorl	%esi,%ebp
+	addl	%ebx,%eax
+	roll	$7,%ebp
+	xorl	%eax,%edx
+	movl	%esi,36(%esp)
+	roll	$16,%edx
+	movl	%ebp,20(%esp)
+	addl	%edx,%ecx
+	movl	44(%esp),%esi
+	xorl	%ecx,%ebx
+	movl	60(%esp),%edi
+	roll	$12,%ebx
+	movl	28(%esp),%ebp
+	addl	%ebx,%eax
+	xorl	%eax,%edx
+	movl	%eax,8(%esp)
+	roll	$8,%edx
+	movl	12(%esp),%eax
+	addl	%edx,%ecx
+	movl	%edx,56(%esp)
+	xorl	%ecx,%ebx
+	addl	%ebp,%eax
+	roll	$7,%ebx
+	xorl	%eax,%edi
+	roll	$16,%edi
+	movl	%ebx,24(%esp)
+	addl	%edi,%esi
+	xorl	%esi,%ebp
+	roll	$12,%ebp
+	movl	20(%esp),%ebx
+	addl	%ebp,%eax
+	xorl	%eax,%edi
+	movl	%eax,12(%esp)
+	roll	$8,%edi
+	movl	(%esp),%eax
+	addl	%edi,%esi
+	movl	%edi,%edx
+	xorl	%esi,%ebp
+	addl	%ebx,%eax
+	roll	$7,%ebp
+	xorl	%eax,%edx
+	roll	$16,%edx
+	movl	%ebp,28(%esp)
+	addl	%edx,%ecx
+	xorl	%ecx,%ebx
+	movl	48(%esp),%edi
+	roll	$12,%ebx
+	movl	24(%esp),%ebp
+	addl	%ebx,%eax
+	xorl	%eax,%edx
+	movl	%eax,(%esp)
+	roll	$8,%edx
+	movl	4(%esp),%eax
+	addl	%edx,%ecx
+	movl	%edx,60(%esp)
+	xorl	%ecx,%ebx
+	addl	%ebp,%eax
+	roll	$7,%ebx
+	xorl	%eax,%edi
+	movl	%ecx,40(%esp)
+	roll	$16,%edi
+	movl	%ebx,20(%esp)
+	addl	%edi,%esi
+	movl	32(%esp),%ecx
+	xorl	%esi,%ebp
+	movl	52(%esp),%edx
+	roll	$12,%ebp
+	movl	28(%esp),%ebx
+	addl	%ebp,%eax
+	xorl	%eax,%edi
+	movl	%eax,4(%esp)
+	roll	$8,%edi
+	movl	8(%esp),%eax
+	addl	%edi,%esi
+	movl	%edi,48(%esp)
+	xorl	%esi,%ebp
+	addl	%ebx,%eax
+	roll	$7,%ebp
+	xorl	%eax,%edx
+	movl	%esi,44(%esp)
+	roll	$16,%edx
+	movl	%ebp,24(%esp)
+	addl	%edx,%ecx
+	movl	36(%esp),%esi
+	xorl	%ecx,%ebx
+	movl	56(%esp),%edi
+	roll	$12,%ebx
+	movl	16(%esp),%ebp
+	addl	%ebx,%eax
+	xorl	%eax,%edx
+	movl	%eax,8(%esp)
+	roll	$8,%edx
+	movl	12(%esp),%eax
+	addl	%edx,%ecx
+	movl	%edx,52(%esp)
+	xorl	%ecx,%ebx
+	addl	%ebp,%eax
+	roll	$7,%ebx
+	xorl	%eax,%edi
+	roll	$16,%edi
+	movl	%ebx,28(%esp)
+	addl	%edi,%esi
+	xorl	%esi,%ebp
+	movl	48(%esp),%edx
+	roll	$12,%ebp
+	movl	128(%esp),%ebx
+	addl	%ebp,%eax
+	xorl	%eax,%edi
+	movl	%eax,12(%esp)
+	roll	$8,%edi
+	movl	(%esp),%eax
+	addl	%edi,%esi
+	movl	%edi,56(%esp)
+	xorl	%esi,%ebp
+	roll	$7,%ebp
+	decl	%ebx
+	jnz	.L004loop
+	movl	160(%esp),%ebx
+	addl	$1634760805,%eax
+	addl	80(%esp),%ebp
+	addl	96(%esp),%ecx
+	addl	100(%esp),%esi
+	cmpl	$64,%ebx
+	jb	.L005tail
+	movl	156(%esp),%ebx
+	addl	112(%esp),%edx
+	addl	120(%esp),%edi
+	xorl	(%ebx),%eax
+	xorl	16(%ebx),%ebp
+	movl	%eax,(%esp)
+	movl	152(%esp),%eax
+	xorl	32(%ebx),%ecx
+	xorl	36(%ebx),%esi
+	xorl	48(%ebx),%edx
+	xorl	56(%ebx),%edi
+	movl	%ebp,16(%eax)
+	movl	%ecx,32(%eax)
+	movl	%esi,36(%eax)
+	movl	%edx,48(%eax)
+	movl	%edi,56(%eax)
+	movl	4(%esp),%ebp
+	movl	8(%esp),%ecx
+	movl	12(%esp),%esi
+	movl	20(%esp),%edx
+	movl	24(%esp),%edi
+	addl	$857760878,%ebp
+	addl	$2036477234,%ecx
+	addl	$1797285236,%esi
+	addl	84(%esp),%edx
+	addl	88(%esp),%edi
+	xorl	4(%ebx),%ebp
+	xorl	8(%ebx),%ecx
+	xorl	12(%ebx),%esi
+	xorl	20(%ebx),%edx
+	xorl	24(%ebx),%edi
+	movl	%ebp,4(%eax)
+	movl	%ecx,8(%eax)
+	movl	%esi,12(%eax)
+	movl	%edx,20(%eax)
+	movl	%edi,24(%eax)
+	movl	28(%esp),%ebp
+	movl	40(%esp),%ecx
+	movl	44(%esp),%esi
+	movl	52(%esp),%edx
+	movl	60(%esp),%edi
+	addl	92(%esp),%ebp
+	addl	104(%esp),%ecx
+	addl	108(%esp),%esi
+	addl	116(%esp),%edx
+	addl	124(%esp),%edi
+	xorl	28(%ebx),%ebp
+	xorl	40(%ebx),%ecx
+	xorl	44(%ebx),%esi
+	xorl	52(%ebx),%edx
+	xorl	60(%ebx),%edi
+	leal	64(%ebx),%ebx
+	movl	%ebp,28(%eax)
+	movl	(%esp),%ebp
+	movl	%ecx,40(%eax)
+	movl	160(%esp),%ecx
+	movl	%esi,44(%eax)
+	movl	%edx,52(%eax)
+	movl	%edi,60(%eax)
+	movl	%ebp,(%eax)
+	leal	64(%eax),%eax
+	subl	$64,%ecx
+	jnz	.L003outer_loop
+	jmp	.L006done
+.L005tail:
+	addl	112(%esp),%edx
+	addl	120(%esp),%edi
+	movl	%eax,(%esp)
+	movl	%ebp,16(%esp)
+	movl	%ecx,32(%esp)
+	movl	%esi,36(%esp)
+	movl	%edx,48(%esp)
+	movl	%edi,56(%esp)
+	movl	4(%esp),%ebp
+	movl	8(%esp),%ecx
+	movl	12(%esp),%esi
+	movl	20(%esp),%edx
+	movl	24(%esp),%edi
+	addl	$857760878,%ebp
+	addl	$2036477234,%ecx
+	addl	$1797285236,%esi
+	addl	84(%esp),%edx
+	addl	88(%esp),%edi
+	movl	%ebp,4(%esp)
+	movl	%ecx,8(%esp)
+	movl	%esi,12(%esp)
+	movl	%edx,20(%esp)
+	movl	%edi,24(%esp)
+	movl	28(%esp),%ebp
+	movl	40(%esp),%ecx
+	movl	44(%esp),%esi
+	movl	52(%esp),%edx
+	movl	60(%esp),%edi
+	addl	92(%esp),%ebp
+	addl	104(%esp),%ecx
+	addl	108(%esp),%esi
+	addl	116(%esp),%edx
+	addl	124(%esp),%edi
+	movl	%ebp,28(%esp)
+	movl	156(%esp),%ebp
+	movl	%ecx,40(%esp)
+	movl	152(%esp),%ecx
+	movl	%esi,44(%esp)
+	xorl	%esi,%esi
+	movl	%edx,52(%esp)
+	movl	%edi,60(%esp)
+	xorl	%eax,%eax
+	xorl	%edx,%edx
+.L007tail_loop:
+	movb	(%esi,%ebp,1),%al
+	movb	(%esp,%esi,1),%dl
+	leal	1(%esi),%esi
+	xorb	%dl,%al
+	movb	%al,-1(%ecx,%esi,1)
+	decl	%ebx
+	jnz	.L007tail_loop
+.L006done:
+	addl	$132,%esp
+.L000no_data:
+	popl	%edi
+	popl	%esi
+	popl	%ebx
+	popl	%ebp
+	ret
+.size	ChaCha20_ctr32,.-.L_ChaCha20_ctr32_begin
+.globl	ChaCha20_ssse3
+.hidden	ChaCha20_ssse3
+.type	ChaCha20_ssse3,@function
+.align	16
+ChaCha20_ssse3:
+.L_ChaCha20_ssse3_begin:
+	pushl	%ebp
+	pushl	%ebx
+	pushl	%esi
+	pushl	%edi
+.Lssse3_shortcut:
+	movl	20(%esp),%edi
+	movl	24(%esp),%esi
+	movl	28(%esp),%ecx
+	movl	32(%esp),%edx
+	movl	36(%esp),%ebx
+	movl	%esp,%ebp
+	subl	$524,%esp
+	andl	$-64,%esp
+	movl	%ebp,512(%esp)
+	leal	.Lssse3_data-.Lpic_point(%eax),%eax
+	movdqu	(%ebx),%xmm3
+	cmpl	$256,%ecx
+	jb	.L0081x
+	movl	%edx,516(%esp)
+	movl	%ebx,520(%esp)
+	subl	$256,%ecx
+	leal	384(%esp),%ebp
+	movdqu	(%edx),%xmm7
+	pshufd	$0,%xmm3,%xmm0
+	pshufd	$85,%xmm3,%xmm1
+	pshufd	$170,%xmm3,%xmm2
+	pshufd	$255,%xmm3,%xmm3
+	paddd	48(%eax),%xmm0
+	pshufd	$0,%xmm7,%xmm4
+	pshufd	$85,%xmm7,%xmm5
+	psubd	64(%eax),%xmm0
+	pshufd	$170,%xmm7,%xmm6
+	pshufd	$255,%xmm7,%xmm7
+	movdqa	%xmm0,64(%ebp)
+	movdqa	%xmm1,80(%ebp)
+	movdqa	%xmm2,96(%ebp)
+	movdqa	%xmm3,112(%ebp)
+	movdqu	16(%edx),%xmm3
+	movdqa	%xmm4,-64(%ebp)
+	movdqa	%xmm5,-48(%ebp)
+	movdqa	%xmm6,-32(%ebp)
+	movdqa	%xmm7,-16(%ebp)
+	movdqa	32(%eax),%xmm7
+	leal	128(%esp),%ebx
+	pshufd	$0,%xmm3,%xmm0
+	pshufd	$85,%xmm3,%xmm1
+	pshufd	$170,%xmm3,%xmm2
+	pshufd	$255,%xmm3,%xmm3
+	pshufd	$0,%xmm7,%xmm4
+	pshufd	$85,%xmm7,%xmm5
+	pshufd	$170,%xmm7,%xmm6
+	pshufd	$255,%xmm7,%xmm7
+	movdqa	%xmm0,(%ebp)
+	movdqa	%xmm1,16(%ebp)
+	movdqa	%xmm2,32(%ebp)
+	movdqa	%xmm3,48(%ebp)
+	movdqa	%xmm4,-128(%ebp)
+	movdqa	%xmm5,-112(%ebp)
+	movdqa	%xmm6,-96(%ebp)
+	movdqa	%xmm7,-80(%ebp)
+	leal	128(%esi),%esi
+	leal	128(%edi),%edi
+	jmp	.L009outer_loop
+.align	16
+.L009outer_loop:
+	movdqa	-112(%ebp),%xmm1
+	movdqa	-96(%ebp),%xmm2
+	movdqa	-80(%ebp),%xmm3
+	movdqa	-48(%ebp),%xmm5
+	movdqa	-32(%ebp),%xmm6
+	movdqa	-16(%ebp),%xmm7
+	movdqa	%xmm1,-112(%ebx)
+	movdqa	%xmm2,-96(%ebx)
+	movdqa	%xmm3,-80(%ebx)
+	movdqa	%xmm5,-48(%ebx)
+	movdqa	%xmm6,-32(%ebx)
+	movdqa	%xmm7,-16(%ebx)
+	movdqa	32(%ebp),%xmm2
+	movdqa	48(%ebp),%xmm3
+	movdqa	64(%ebp),%xmm4
+	movdqa	80(%ebp),%xmm5
+	movdqa	96(%ebp),%xmm6
+	movdqa	112(%ebp),%xmm7
+	paddd	64(%eax),%xmm4
+	movdqa	%xmm2,32(%ebx)
+	movdqa	%xmm3,48(%ebx)
+	movdqa	%xmm4,64(%ebx)
+	movdqa	%xmm5,80(%ebx)
+	movdqa	%xmm6,96(%ebx)
+	movdqa	%xmm7,112(%ebx)
+	movdqa	%xmm4,64(%ebp)
+	movdqa	-128(%ebp),%xmm0
+	movdqa	%xmm4,%xmm6
+	movdqa	-64(%ebp),%xmm3
+	movdqa	(%ebp),%xmm4
+	movdqa	16(%ebp),%xmm5
+	movl	$10,%edx
+	nop
+.align	16
+.L010loop:
+	paddd	%xmm3,%xmm0
+	movdqa	%xmm3,%xmm2
+	pxor	%xmm0,%xmm6
+	pshufb	(%eax),%xmm6
+	paddd	%xmm6,%xmm4
+	pxor	%xmm4,%xmm2
+	movdqa	-48(%ebx),%xmm3
+	movdqa	%xmm2,%xmm1
+	pslld	$12,%xmm2
+	psrld	$20,%xmm1
+	por	%xmm1,%xmm2
+	movdqa	-112(%ebx),%xmm1
+	paddd	%xmm2,%xmm0
+	movdqa	80(%ebx),%xmm7
+	pxor	%xmm0,%xmm6
+	movdqa	%xmm0,-128(%ebx)
+	pshufb	16(%eax),%xmm6
+	paddd	%xmm6,%xmm4
+	movdqa	%xmm6,64(%ebx)
+	pxor	%xmm4,%xmm2
+	paddd	%xmm3,%xmm1
+	movdqa	%xmm2,%xmm0
+	pslld	$7,%xmm2
+	psrld	$25,%xmm0
+	pxor	%xmm1,%xmm7
+	por	%xmm0,%xmm2
+	movdqa	%xmm4,(%ebx)
+	pshufb	(%eax),%xmm7
+	movdqa	%xmm2,-64(%ebx)
+	paddd	%xmm7,%xmm5
+	movdqa	32(%ebx),%xmm4
+	pxor	%xmm5,%xmm3
+	movdqa	-32(%ebx),%xmm2
+	movdqa	%xmm3,%xmm0
+	pslld	$12,%xmm3
+	psrld	$20,%xmm0
+	por	%xmm0,%xmm3
+	movdqa	-96(%ebx),%xmm0
+	paddd	%xmm3,%xmm1
+	movdqa	96(%ebx),%xmm6
+	pxor	%xmm1,%xmm7
+	movdqa	%xmm1,-112(%ebx)
+	pshufb	16(%eax),%xmm7
+	paddd	%xmm7,%xmm5
+	movdqa	%xmm7,80(%ebx)
+	pxor	%xmm5,%xmm3
+	paddd	%xmm2,%xmm0
+	movdqa	%xmm3,%xmm1
+	pslld	$7,%xmm3
+	psrld	$25,%xmm1
+	pxor	%xmm0,%xmm6
+	por	%xmm1,%xmm3
+	movdqa	%xmm5,16(%ebx)
+	pshufb	(%eax),%xmm6
+	movdqa	%xmm3,-48(%ebx)
+	paddd	%xmm6,%xmm4
+	movdqa	48(%ebx),%xmm5
+	pxor	%xmm4,%xmm2
+	movdqa	-16(%ebx),%xmm3
+	movdqa	%xmm2,%xmm1
+	pslld	$12,%xmm2
+	psrld	$20,%xmm1
+	por	%xmm1,%xmm2
+	movdqa	-80(%ebx),%xmm1
+	paddd	%xmm2,%xmm0
+	movdqa	112(%ebx),%xmm7
+	pxor	%xmm0,%xmm6
+	movdqa	%xmm0,-96(%ebx)
+	pshufb	16(%eax),%xmm6
+	paddd	%xmm6,%xmm4
+	movdqa	%xmm6,96(%ebx)
+	pxor	%xmm4,%xmm2
+	paddd	%xmm3,%xmm1
+	movdqa	%xmm2,%xmm0
+	pslld	$7,%xmm2
+	psrld	$25,%xmm0
+	pxor	%xmm1,%xmm7
+	por	%xmm0,%xmm2
+	pshufb	(%eax),%xmm7
+	movdqa	%xmm2,-32(%ebx)
+	paddd	%xmm7,%xmm5
+	pxor	%xmm5,%xmm3
+	movdqa	-48(%ebx),%xmm2
+	movdqa	%xmm3,%xmm0
+	pslld	$12,%xmm3
+	psrld	$20,%xmm0
+	por	%xmm0,%xmm3
+	movdqa	-128(%ebx),%xmm0
+	paddd	%xmm3,%xmm1
+	pxor	%xmm1,%xmm7
+	movdqa	%xmm1,-80(%ebx)
+	pshufb	16(%eax),%xmm7
+	paddd	%xmm7,%xmm5
+	movdqa	%xmm7,%xmm6
+	pxor	%xmm5,%xmm3
+	paddd	%xmm2,%xmm0
+	movdqa	%xmm3,%xmm1
+	pslld	$7,%xmm3
+	psrld	$25,%xmm1
+	pxor	%xmm0,%xmm6
+	por	%xmm1,%xmm3
+	pshufb	(%eax),%xmm6
+	movdqa	%xmm3,-16(%ebx)
+	paddd	%xmm6,%xmm4
+	pxor	%xmm4,%xmm2
+	movdqa	-32(%ebx),%xmm3
+	movdqa	%xmm2,%xmm1
+	pslld	$12,%xmm2
+	psrld	$20,%xmm1
+	por	%xmm1,%xmm2
+	movdqa	-112(%ebx),%xmm1
+	paddd	%xmm2,%xmm0
+	movdqa	64(%ebx),%xmm7
+	pxor	%xmm0,%xmm6
+	movdqa	%xmm0,-128(%ebx)
+	pshufb	16(%eax),%xmm6
+	paddd	%xmm6,%xmm4
+	movdqa	%xmm6,112(%ebx)
+	pxor	%xmm4,%xmm2
+	paddd	%xmm3,%xmm1
+	movdqa	%xmm2,%xmm0
+	pslld	$7,%xmm2
+	psrld	$25,%xmm0
+	pxor	%xmm1,%xmm7
+	por	%xmm0,%xmm2
+	movdqa	%xmm4,32(%ebx)
+	pshufb	(%eax),%xmm7
+	movdqa	%xmm2,-48(%ebx)
+	paddd	%xmm7,%xmm5
+	movdqa	(%ebx),%xmm4
+	pxor	%xmm5,%xmm3
+	movdqa	-16(%ebx),%xmm2
+	movdqa	%xmm3,%xmm0
+	pslld	$12,%xmm3
+	psrld	$20,%xmm0
+	por	%xmm0,%xmm3
+	movdqa	-96(%ebx),%xmm0
+	paddd	%xmm3,%xmm1
+	movdqa	80(%ebx),%xmm6
+	pxor	%xmm1,%xmm7
+	movdqa	%xmm1,-112(%ebx)
+	pshufb	16(%eax),%xmm7
+	paddd	%xmm7,%xmm5
+	movdqa	%xmm7,64(%ebx)
+	pxor	%xmm5,%xmm3
+	paddd	%xmm2,%xmm0
+	movdqa	%xmm3,%xmm1
+	pslld	$7,%xmm3
+	psrld	$25,%xmm1
+	pxor	%xmm0,%xmm6
+	por	%xmm1,%xmm3
+	movdqa	%xmm5,48(%ebx)
+	pshufb	(%eax),%xmm6
+	movdqa	%xmm3,-32(%ebx)
+	paddd	%xmm6,%xmm4
+	movdqa	16(%ebx),%xmm5
+	pxor	%xmm4,%xmm2
+	movdqa	-64(%ebx),%xmm3
+	movdqa	%xmm2,%xmm1
+	pslld	$12,%xmm2
+	psrld	$20,%xmm1
+	por	%xmm1,%xmm2
+	movdqa	-80(%ebx),%xmm1
+	paddd	%xmm2,%xmm0
+	movdqa	96(%ebx),%xmm7
+	pxor	%xmm0,%xmm6
+	movdqa	%xmm0,-96(%ebx)
+	pshufb	16(%eax),%xmm6
+	paddd	%xmm6,%xmm4
+	movdqa	%xmm6,80(%ebx)
+	pxor	%xmm4,%xmm2
+	paddd	%xmm3,%xmm1
+	movdqa	%xmm2,%xmm0
+	pslld	$7,%xmm2
+	psrld	$25,%xmm0
+	pxor	%xmm1,%xmm7
+	por	%xmm0,%xmm2
+	pshufb	(%eax),%xmm7
+	movdqa	%xmm2,-16(%ebx)
+	paddd	%xmm7,%xmm5
+	pxor	%xmm5,%xmm3
+	movdqa	%xmm3,%xmm0
+	pslld	$12,%xmm3
+	psrld	$20,%xmm0
+	por	%xmm0,%xmm3
+	movdqa	-128(%ebx),%xmm0
+	paddd	%xmm3,%xmm1
+	movdqa	64(%ebx),%xmm6
+	pxor	%xmm1,%xmm7
+	movdqa	%xmm1,-80(%ebx)
+	pshufb	16(%eax),%xmm7
+	paddd	%xmm7,%xmm5
+	movdqa	%xmm7,96(%ebx)
+	pxor	%xmm5,%xmm3
+	movdqa	%xmm3,%xmm1
+	pslld	$7,%xmm3
+	psrld	$25,%xmm1
+	por	%xmm1,%xmm3
+	decl	%edx
+	jnz	.L010loop
+	movdqa	%xmm3,-64(%ebx)
+	movdqa	%xmm4,(%ebx)
+	movdqa	%xmm5,16(%ebx)
+	movdqa	%xmm6,64(%ebx)
+	movdqa	%xmm7,96(%ebx)
+	movdqa	-112(%ebx),%xmm1
+	movdqa	-96(%ebx),%xmm2
+	movdqa	-80(%ebx),%xmm3
+	paddd	-128(%ebp),%xmm0
+	paddd	-112(%ebp),%xmm1
+	paddd	-96(%ebp),%xmm2
+	paddd	-80(%ebp),%xmm3
+	movdqa	%xmm0,%xmm6
+	punpckldq	%xmm1,%xmm0
+	movdqa	%xmm2,%xmm7
+	punpckldq	%xmm3,%xmm2
+	punpckhdq	%xmm1,%xmm6
+	punpckhdq	%xmm3,%xmm7
+	movdqa	%xmm0,%xmm1
+	punpcklqdq	%xmm2,%xmm0
+	movdqa	%xmm6,%xmm3
+	punpcklqdq	%xmm7,%xmm6
+	punpckhqdq	%xmm2,%xmm1
+	punpckhqdq	%xmm7,%xmm3
+	movdqu	-128(%esi),%xmm4
+	movdqu	-64(%esi),%xmm5
+	movdqu	(%esi),%xmm2
+	movdqu	64(%esi),%xmm7
+	leal	16(%esi),%esi
+	pxor	%xmm0,%xmm4
+	movdqa	-64(%ebx),%xmm0
+	pxor	%xmm1,%xmm5
+	movdqa	-48(%ebx),%xmm1
+	pxor	%xmm2,%xmm6
+	movdqa	-32(%ebx),%xmm2
+	pxor	%xmm3,%xmm7
+	movdqa	-16(%ebx),%xmm3
+	movdqu	%xmm4,-128(%edi)
+	movdqu	%xmm5,-64(%edi)
+	movdqu	%xmm6,(%edi)
+	movdqu	%xmm7,64(%edi)
+	leal	16(%edi),%edi
+	paddd	-64(%ebp),%xmm0
+	paddd	-48(%ebp),%xmm1
+	paddd	-32(%ebp),%xmm2
+	paddd	-16(%ebp),%xmm3
+	movdqa	%xmm0,%xmm6
+	punpckldq	%xmm1,%xmm0
+	movdqa	%xmm2,%xmm7
+	punpckldq	%xmm3,%xmm2
+	punpckhdq	%xmm1,%xmm6
+	punpckhdq	%xmm3,%xmm7
+	movdqa	%xmm0,%xmm1
+	punpcklqdq	%xmm2,%xmm0
+	movdqa	%xmm6,%xmm3
+	punpcklqdq	%xmm7,%xmm6
+	punpckhqdq	%xmm2,%xmm1
+	punpckhqdq	%xmm7,%xmm3
+	movdqu	-128(%esi),%xmm4
+	movdqu	-64(%esi),%xmm5
+	movdqu	(%esi),%xmm2
+	movdqu	64(%esi),%xmm7
+	leal	16(%esi),%esi
+	pxor	%xmm0,%xmm4
+	movdqa	(%ebx),%xmm0
+	pxor	%xmm1,%xmm5
+	movdqa	16(%ebx),%xmm1
+	pxor	%xmm2,%xmm6
+	movdqa	32(%ebx),%xmm2
+	pxor	%xmm3,%xmm7
+	movdqa	48(%ebx),%xmm3
+	movdqu	%xmm4,-128(%edi)
+	movdqu	%xmm5,-64(%edi)
+	movdqu	%xmm6,(%edi)
+	movdqu	%xmm7,64(%edi)
+	leal	16(%edi),%edi
+	paddd	(%ebp),%xmm0
+	paddd	16(%ebp),%xmm1
+	paddd	32(%ebp),%xmm2
+	paddd	48(%ebp),%xmm3
+	movdqa	%xmm0,%xmm6
+	punpckldq	%xmm1,%xmm0
+	movdqa	%xmm2,%xmm7
+	punpckldq	%xmm3,%xmm2
+	punpckhdq	%xmm1,%xmm6
+	punpckhdq	%xmm3,%xmm7
+	movdqa	%xmm0,%xmm1
+	punpcklqdq	%xmm2,%xmm0
+	movdqa	%xmm6,%xmm3
+	punpcklqdq	%xmm7,%xmm6
+	punpckhqdq	%xmm2,%xmm1
+	punpckhqdq	%xmm7,%xmm3
+	movdqu	-128(%esi),%xmm4
+	movdqu	-64(%esi),%xmm5
+	movdqu	(%esi),%xmm2
+	movdqu	64(%esi),%xmm7
+	leal	16(%esi),%esi
+	pxor	%xmm0,%xmm4
+	movdqa	64(%ebx),%xmm0
+	pxor	%xmm1,%xmm5
+	movdqa	80(%ebx),%xmm1
+	pxor	%xmm2,%xmm6
+	movdqa	96(%ebx),%xmm2
+	pxor	%xmm3,%xmm7
+	movdqa	112(%ebx),%xmm3
+	movdqu	%xmm4,-128(%edi)
+	movdqu	%xmm5,-64(%edi)
+	movdqu	%xmm6,(%edi)
+	movdqu	%xmm7,64(%edi)
+	leal	16(%edi),%edi
+	paddd	64(%ebp),%xmm0
+	paddd	80(%ebp),%xmm1
+	paddd	96(%ebp),%xmm2
+	paddd	112(%ebp),%xmm3
+	movdqa	%xmm0,%xmm6
+	punpckldq	%xmm1,%xmm0
+	movdqa	%xmm2,%xmm7
+	punpckldq	%xmm3,%xmm2
+	punpckhdq	%xmm1,%xmm6
+	punpckhdq	%xmm3,%xmm7
+	movdqa	%xmm0,%xmm1
+	punpcklqdq	%xmm2,%xmm0
+	movdqa	%xmm6,%xmm3
+	punpcklqdq	%xmm7,%xmm6
+	punpckhqdq	%xmm2,%xmm1
+	punpckhqdq	%xmm7,%xmm3
+	movdqu	-128(%esi),%xmm4
+	movdqu	-64(%esi),%xmm5
+	movdqu	(%esi),%xmm2
+	movdqu	64(%esi),%xmm7
+	leal	208(%esi),%esi
+	pxor	%xmm0,%xmm4
+	pxor	%xmm1,%xmm5
+	pxor	%xmm2,%xmm6
+	pxor	%xmm3,%xmm7
+	movdqu	%xmm4,-128(%edi)
+	movdqu	%xmm5,-64(%edi)
+	movdqu	%xmm6,(%edi)
+	movdqu	%xmm7,64(%edi)
+	leal	208(%edi),%edi
+	subl	$256,%ecx
+	jnc	.L009outer_loop
+	addl	$256,%ecx
+	jz	.L011done
+	movl	520(%esp),%ebx
+	leal	-128(%esi),%esi
+	movl	516(%esp),%edx
+	leal	-128(%edi),%edi
+	movd	64(%ebp),%xmm2
+	movdqu	(%ebx),%xmm3
+	paddd	96(%eax),%xmm2
+	pand	112(%eax),%xmm3
+	por	%xmm2,%xmm3
+.L0081x:
+	movdqa	32(%eax),%xmm0
+	movdqu	(%edx),%xmm1
+	movdqu	16(%edx),%xmm2
+	movdqa	(%eax),%xmm6
+	movdqa	16(%eax),%xmm7
+	movl	%ebp,48(%esp)
+	movdqa	%xmm0,(%esp)
+	movdqa	%xmm1,16(%esp)
+	movdqa	%xmm2,32(%esp)
+	movdqa	%xmm3,48(%esp)
+	movl	$10,%edx
+	jmp	.L012loop1x
+.align	16
+.L013outer1x:
+	movdqa	80(%eax),%xmm3
+	movdqa	(%esp),%xmm0
+	movdqa	16(%esp),%xmm1
+	movdqa	32(%esp),%xmm2
+	paddd	48(%esp),%xmm3
+	movl	$10,%edx
+	movdqa	%xmm3,48(%esp)
+	jmp	.L012loop1x
+.align	16
+.L012loop1x:
+	paddd	%xmm1,%xmm0
+	pxor	%xmm0,%xmm3
+.byte	102,15,56,0,222
+	paddd	%xmm3,%xmm2
+	pxor	%xmm2,%xmm1
+	movdqa	%xmm1,%xmm4
+	psrld	$20,%xmm1
+	pslld	$12,%xmm4
+	por	%xmm4,%xmm1
+	paddd	%xmm1,%xmm0
+	pxor	%xmm0,%xmm3
+.byte	102,15,56,0,223
+	paddd	%xmm3,%xmm2
+	pxor	%xmm2,%xmm1
+	movdqa	%xmm1,%xmm4
+	psrld	$25,%xmm1
+	pslld	$7,%xmm4
+	por	%xmm4,%xmm1
+	pshufd	$78,%xmm2,%xmm2
+	pshufd	$57,%xmm1,%xmm1
+	pshufd	$147,%xmm3,%xmm3
+	nop
+	paddd	%xmm1,%xmm0
+	pxor	%xmm0,%xmm3
+.byte	102,15,56,0,222
+	paddd	%xmm3,%xmm2
+	pxor	%xmm2,%xmm1
+	movdqa	%xmm1,%xmm4
+	psrld	$20,%xmm1
+	pslld	$12,%xmm4
+	por	%xmm4,%xmm1
+	paddd	%xmm1,%xmm0
+	pxor	%xmm0,%xmm3
+.byte	102,15,56,0,223
+	paddd	%xmm3,%xmm2
+	pxor	%xmm2,%xmm1
+	movdqa	%xmm1,%xmm4
+	psrld	$25,%xmm1
+	pslld	$7,%xmm4
+	por	%xmm4,%xmm1
+	pshufd	$78,%xmm2,%xmm2
+	pshufd	$147,%xmm1,%xmm1
+	pshufd	$57,%xmm3,%xmm3
+	decl	%edx
+	jnz	.L012loop1x
+	paddd	(%esp),%xmm0
+	paddd	16(%esp),%xmm1
+	paddd	32(%esp),%xmm2
+	paddd	48(%esp),%xmm3
+	cmpl	$64,%ecx
+	jb	.L014tail
+	movdqu	(%esi),%xmm4
+	movdqu	16(%esi),%xmm5
+	pxor	%xmm4,%xmm0
+	movdqu	32(%esi),%xmm4
+	pxor	%xmm5,%xmm1
+	movdqu	48(%esi),%xmm5
+	pxor	%xmm4,%xmm2
+	pxor	%xmm5,%xmm3
+	leal	64(%esi),%esi
+	movdqu	%xmm0,(%edi)
+	movdqu	%xmm1,16(%edi)
+	movdqu	%xmm2,32(%edi)
+	movdqu	%xmm3,48(%edi)
+	leal	64(%edi),%edi
+	subl	$64,%ecx
+	jnz	.L013outer1x
+	jmp	.L011done
+.L014tail:
+	movdqa	%xmm0,(%esp)
+	movdqa	%xmm1,16(%esp)
+	movdqa	%xmm2,32(%esp)
+	movdqa	%xmm3,48(%esp)
+	xorl	%eax,%eax
+	xorl	%edx,%edx
+	xorl	%ebp,%ebp
+.L015tail_loop:
+	movb	(%esp,%ebp,1),%al
+	movb	(%esi,%ebp,1),%dl
+	leal	1(%ebp),%ebp
+	xorb	%dl,%al
+	movb	%al,-1(%edi,%ebp,1)
+	decl	%ecx
+	jnz	.L015tail_loop
+.L011done:
+	movl	512(%esp),%esp
+	popl	%edi
+	popl	%esi
+	popl	%ebx
+	popl	%ebp
+	ret
+.size	ChaCha20_ssse3,.-.L_ChaCha20_ssse3_begin
+.align	64
+.Lssse3_data:
+.byte	2,3,0,1,6,7,4,5,10,11,8,9,14,15,12,13
+.byte	3,0,1,2,7,4,5,6,11,8,9,10,15,12,13,14
+.long	1634760805,857760878,2036477234,1797285236
+.long	0,1,2,3
+.long	4,4,4,4
+.long	1,0,0,0
+.long	4,0,0,0
+.long	0,-1,-1,-1
+.align	64
+.byte	67,104,97,67,104,97,50,48,32,102,111,114,32,120,56,54
+.byte	44,32,67,82,89,80,84,79,71,65,77,83,32,98,121,32
+.byte	60,97,112,112,114,111,64,111,112,101,110,115,115,108,46,111
+.byte	114,103,62,0
+#endif
diff --git a/packager/third_party/boringssl/linux-x86/crypto/rc4/rc4-586.S b/packager/third_party/boringssl/linux-x86/crypto/rc4/rc4-586.S
index a5cce47c09..d245589eca 100644
--- a/packager/third_party/boringssl/linux-x86/crypto/rc4/rc4-586.S
+++ b/packager/third_party/boringssl/linux-x86/crypto/rc4/rc4-586.S
@@ -347,39 +347,4 @@ asm_RC4_set_key:
 	popl	%ebp
 	ret
 .size	asm_RC4_set_key,.-.L_asm_RC4_set_key_begin
-.globl	RC4_options
-.hidden	RC4_options
-.type	RC4_options,@function
-.align	16
-RC4_options:
-.L_RC4_options_begin:
-	call	.L018pic_point
-.L018pic_point:
-	popl	%eax
-	leal	.L019opts-.L018pic_point(%eax),%eax
-	call	.L020PIC_me_up
-.L020PIC_me_up:
-	popl	%edx
-	leal	OPENSSL_ia32cap_P-.L020PIC_me_up(%edx),%edx
-	movl	(%edx),%edx
-	btl	$20,%edx
-	jc	.L0211xchar
-	btl	$26,%edx
-	jnc	.L022ret
-	addl	$25,%eax
-	ret
-.L0211xchar:
-	addl	$12,%eax
-.L022ret:
-	ret
-.align	64
-.L019opts:
-.byte	114,99,52,40,52,120,44,105,110,116,41,0
-.byte	114,99,52,40,49,120,44,99,104,97,114,41,0
-.byte	114,99,52,40,56,120,44,109,109,120,41,0
-.byte	82,67,52,32,102,111,114,32,120,56,54,44,32,67,82,89
-.byte	80,84,79,71,65,77,83,32,98,121,32,60,97,112,112,114
-.byte	111,64,111,112,101,110,115,115,108,46,111,114,103,62,0
-.align	64
-.size	RC4_options,.-.L_RC4_options_begin
 #endif
diff --git a/packager/third_party/boringssl/linux-x86/crypto/sha/sha1-586.S b/packager/third_party/boringssl/linux-x86/crypto/sha/sha1-586.S
index 808ccac517..58d0bc1277 100644
--- a/packager/third_party/boringssl/linux-x86/crypto/sha/sha1-586.S
+++ b/packager/third_party/boringssl/linux-x86/crypto/sha/sha1-586.S
@@ -23,8 +23,11 @@ sha1_block_data_order:
 	movl	8(%esi),%ecx
 	testl	$16777216,%eax
 	jz	.L001x86
-	testl	$536870912,%ecx
-	jnz	.Lshaext_shortcut
+	andl	$268435456,%edx
+	andl	$1073741824,%eax
+	orl	%edx,%eax
+	cmpl	$1342177280,%eax
+	je	.Lavx_shortcut
 	jmp	.Lssse3_shortcut
 .align	16
 .L001x86:
@@ -1393,177 +1396,6 @@ sha1_block_data_order:
 	popl	%ebp
 	ret
 .size	sha1_block_data_order,.-.L_sha1_block_data_order_begin
-.hidden	_sha1_block_data_order_shaext
-.type	_sha1_block_data_order_shaext,@function
-.align	16
-_sha1_block_data_order_shaext:
-	pushl	%ebp
-	pushl	%ebx
-	pushl	%esi
-	pushl	%edi
-	call	.L003pic_point
-.L003pic_point:
-	popl	%ebp
-	leal	.LK_XX_XX-.L003pic_point(%ebp),%ebp
-.Lshaext_shortcut:
-	movl	20(%esp),%edi
-	movl	%esp,%ebx
-	movl	24(%esp),%esi
-	movl	28(%esp),%ecx
-	subl	$32,%esp
-	movdqu	(%edi),%xmm0
-	movd	16(%edi),%xmm1
-	andl	$-32,%esp
-	movdqa	80(%ebp),%xmm3
-	movdqu	(%esi),%xmm4
-	pshufd	$27,%xmm0,%xmm0
-	movdqu	16(%esi),%xmm5
-	pshufd	$27,%xmm1,%xmm1
-	movdqu	32(%esi),%xmm6
-.byte	102,15,56,0,227
-	movdqu	48(%esi),%xmm7
-.byte	102,15,56,0,235
-.byte	102,15,56,0,243
-.byte	102,15,56,0,251
-	jmp	.L004loop_shaext
-.align	16
-.L004loop_shaext:
-	decl	%ecx
-	leal	64(%esi),%eax
-	movdqa	%xmm1,(%esp)
-	paddd	%xmm4,%xmm1
-	cmovnel	%eax,%esi
-	movdqa	%xmm0,16(%esp)
-.byte	15,56,201,229
-	movdqa	%xmm0,%xmm2
-.byte	15,58,204,193,0
-.byte	15,56,200,213
-	pxor	%xmm6,%xmm4
-.byte	15,56,201,238
-.byte	15,56,202,231
-	movdqa	%xmm0,%xmm1
-.byte	15,58,204,194,0
-.byte	15,56,200,206
-	pxor	%xmm7,%xmm5
-.byte	15,56,202,236
-.byte	15,56,201,247
-	movdqa	%xmm0,%xmm2
-.byte	15,58,204,193,0
-.byte	15,56,200,215
-	pxor	%xmm4,%xmm6
-.byte	15,56,201,252
-.byte	15,56,202,245
-	movdqa	%xmm0,%xmm1
-.byte	15,58,204,194,0
-.byte	15,56,200,204
-	pxor	%xmm5,%xmm7
-.byte	15,56,202,254
-.byte	15,56,201,229
-	movdqa	%xmm0,%xmm2
-.byte	15,58,204,193,0
-.byte	15,56,200,213
-	pxor	%xmm6,%xmm4
-.byte	15,56,201,238
-.byte	15,56,202,231
-	movdqa	%xmm0,%xmm1
-.byte	15,58,204,194,1
-.byte	15,56,200,206
-	pxor	%xmm7,%xmm5
-.byte	15,56,202,236
-.byte	15,56,201,247
-	movdqa	%xmm0,%xmm2
-.byte	15,58,204,193,1
-.byte	15,56,200,215
-	pxor	%xmm4,%xmm6
-.byte	15,56,201,252
-.byte	15,56,202,245
-	movdqa	%xmm0,%xmm1
-.byte	15,58,204,194,1
-.byte	15,56,200,204
-	pxor	%xmm5,%xmm7
-.byte	15,56,202,254
-.byte	15,56,201,229
-	movdqa	%xmm0,%xmm2
-.byte	15,58,204,193,1
-.byte	15,56,200,213
-	pxor	%xmm6,%xmm4
-.byte	15,56,201,238
-.byte	15,56,202,231
-	movdqa	%xmm0,%xmm1
-.byte	15,58,204,194,1
-.byte	15,56,200,206
-	pxor	%xmm7,%xmm5
-.byte	15,56,202,236
-.byte	15,56,201,247
-	movdqa	%xmm0,%xmm2
-.byte	15,58,204,193,2
-.byte	15,56,200,215
-	pxor	%xmm4,%xmm6
-.byte	15,56,201,252
-.byte	15,56,202,245
-	movdqa	%xmm0,%xmm1
-.byte	15,58,204,194,2
-.byte	15,56,200,204
-	pxor	%xmm5,%xmm7
-.byte	15,56,202,254
-.byte	15,56,201,229
-	movdqa	%xmm0,%xmm2
-.byte	15,58,204,193,2
-.byte	15,56,200,213
-	pxor	%xmm6,%xmm4
-.byte	15,56,201,238
-.byte	15,56,202,231
-	movdqa	%xmm0,%xmm1
-.byte	15,58,204,194,2
-.byte	15,56,200,206
-	pxor	%xmm7,%xmm5
-.byte	15,56,202,236
-.byte	15,56,201,247
-	movdqa	%xmm0,%xmm2
-.byte	15,58,204,193,2
-.byte	15,56,200,215
-	pxor	%xmm4,%xmm6
-.byte	15,56,201,252
-.byte	15,56,202,245
-	movdqa	%xmm0,%xmm1
-.byte	15,58,204,194,3
-.byte	15,56,200,204
-	pxor	%xmm5,%xmm7
-.byte	15,56,202,254
-	movdqu	(%esi),%xmm4
-	movdqa	%xmm0,%xmm2
-.byte	15,58,204,193,3
-.byte	15,56,200,213
-	movdqu	16(%esi),%xmm5
-.byte	102,15,56,0,227
-	movdqa	%xmm0,%xmm1
-.byte	15,58,204,194,3
-.byte	15,56,200,206
-	movdqu	32(%esi),%xmm6
-.byte	102,15,56,0,235
-	movdqa	%xmm0,%xmm2
-.byte	15,58,204,193,3
-.byte	15,56,200,215
-	movdqu	48(%esi),%xmm7
-.byte	102,15,56,0,243
-	movdqa	%xmm0,%xmm1
-.byte	15,58,204,194,3
-	movdqa	(%esp),%xmm2
-.byte	102,15,56,0,251
-.byte	15,56,200,202
-	paddd	16(%esp),%xmm0
-	jnz	.L004loop_shaext
-	pshufd	$27,%xmm0,%xmm0
-	pshufd	$27,%xmm1,%xmm1
-	movdqu	%xmm0,(%edi)
-	movd	%xmm1,16(%edi)
-	movl	%ebx,%esp
-	popl	%edi
-	popl	%esi
-	popl	%ebx
-	popl	%ebp
-	ret
-.size	_sha1_block_data_order_shaext,.-_sha1_block_data_order_shaext
 .hidden	_sha1_block_data_order_ssse3
 .type	_sha1_block_data_order_ssse3,@function
 .align	16
@@ -1572,10 +1404,10 @@ _sha1_block_data_order_ssse3:
 	pushl	%ebx
 	pushl	%esi
 	pushl	%edi
-	call	.L005pic_point
-.L005pic_point:
+	call	.L003pic_point
+.L003pic_point:
 	popl	%ebp
-	leal	.LK_XX_XX-.L005pic_point(%ebp),%ebp
+	leal	.LK_XX_XX-.L003pic_point(%ebp),%ebp
 .Lssse3_shortcut:
 	movdqa	(%ebp),%xmm7
 	movdqa	16(%ebp),%xmm0
@@ -1628,9 +1460,9 @@ _sha1_block_data_order_ssse3:
 	xorl	%edx,%ebp
 	pshufd	$238,%xmm0,%xmm4
 	andl	%ebp,%esi
-	jmp	.L006loop
+	jmp	.L004loop
 .align	16
-.L006loop:
+.L004loop:
 	rorl	$2,%ebx
 	xorl	%edx,%esi
 	movl	%eax,%ebp
@@ -2533,7 +2365,7 @@ _sha1_block_data_order_ssse3:
 	addl	%edx,%ecx
 	movl	196(%esp),%ebp
 	cmpl	200(%esp),%ebp
-	je	.L007done
+	je	.L005done
 	movdqa	160(%esp),%xmm7
 	movdqa	176(%esp),%xmm6
 	movdqu	(%ebp),%xmm0
@@ -2668,9 +2500,9 @@ _sha1_block_data_order_ssse3:
 	pshufd	$238,%xmm0,%xmm4
 	andl	%ebx,%esi
 	movl	%ebp,%ebx
-	jmp	.L006loop
+	jmp	.L004loop
 .align	16
-.L007done:
+.L005done:
 	addl	16(%esp),%ebx
 	xorl	%edi,%esi
 	movl	%ecx,%ebp
@@ -2784,6 +2616,1177 @@ _sha1_block_data_order_ssse3:
 	popl	%ebp
 	ret
 .size	_sha1_block_data_order_ssse3,.-_sha1_block_data_order_ssse3
+.hidden	_sha1_block_data_order_avx
+.type	_sha1_block_data_order_avx,@function
+.align	16
+_sha1_block_data_order_avx:
+	pushl	%ebp
+	pushl	%ebx
+	pushl	%esi
+	pushl	%edi
+	call	.L006pic_point
+.L006pic_point:
+	popl	%ebp
+	leal	.LK_XX_XX-.L006pic_point(%ebp),%ebp
+.Lavx_shortcut:
+	vzeroall
+	vmovdqa	(%ebp),%xmm7
+	vmovdqa	16(%ebp),%xmm0
+	vmovdqa	32(%ebp),%xmm1
+	vmovdqa	48(%ebp),%xmm2
+	vmovdqa	64(%ebp),%xmm6
+	movl	20(%esp),%edi
+	movl	24(%esp),%ebp
+	movl	28(%esp),%edx
+	movl	%esp,%esi
+	subl	$208,%esp
+	andl	$-64,%esp
+	vmovdqa	%xmm0,112(%esp)
+	vmovdqa	%xmm1,128(%esp)
+	vmovdqa	%xmm2,144(%esp)
+	shll	$6,%edx
+	vmovdqa	%xmm7,160(%esp)
+	addl	%ebp,%edx
+	vmovdqa	%xmm6,176(%esp)
+	addl	$64,%ebp
+	movl	%edi,192(%esp)
+	movl	%ebp,196(%esp)
+	movl	%edx,200(%esp)
+	movl	%esi,204(%esp)
+	movl	(%edi),%eax
+	movl	4(%edi),%ebx
+	movl	8(%edi),%ecx
+	movl	12(%edi),%edx
+	movl	16(%edi),%edi
+	movl	%ebx,%esi
+	vmovdqu	-64(%ebp),%xmm0
+	vmovdqu	-48(%ebp),%xmm1
+	vmovdqu	-32(%ebp),%xmm2
+	vmovdqu	-16(%ebp),%xmm3
+	vpshufb	%xmm6,%xmm0,%xmm0
+	vpshufb	%xmm6,%xmm1,%xmm1
+	vpshufb	%xmm6,%xmm2,%xmm2
+	vmovdqa	%xmm7,96(%esp)
+	vpshufb	%xmm6,%xmm3,%xmm3
+	vpaddd	%xmm7,%xmm0,%xmm4
+	vpaddd	%xmm7,%xmm1,%xmm5
+	vpaddd	%xmm7,%xmm2,%xmm6
+	vmovdqa	%xmm4,(%esp)
+	movl	%ecx,%ebp
+	vmovdqa	%xmm5,16(%esp)
+	xorl	%edx,%ebp
+	vmovdqa	%xmm6,32(%esp)
+	andl	%ebp,%esi
+	jmp	.L007loop
+.align	16
+.L007loop:
+	shrdl	$2,%ebx,%ebx
+	xorl	%edx,%esi
+	vpalignr	$8,%xmm0,%xmm1,%xmm4
+	movl	%eax,%ebp
+	addl	(%esp),%edi
+	vpaddd	%xmm3,%xmm7,%xmm7
+	vmovdqa	%xmm0,64(%esp)
+	xorl	%ecx,%ebx
+	shldl	$5,%eax,%eax
+	vpsrldq	$4,%xmm3,%xmm6
+	addl	%esi,%edi
+	andl	%ebx,%ebp
+	vpxor	%xmm0,%xmm4,%xmm4
+	xorl	%ecx,%ebx
+	addl	%eax,%edi
+	vpxor	%xmm2,%xmm6,%xmm6
+	shrdl	$7,%eax,%eax
+	xorl	%ecx,%ebp
+	vmovdqa	%xmm7,48(%esp)
+	movl	%edi,%esi
+	addl	4(%esp),%edx
+	vpxor	%xmm6,%xmm4,%xmm4
+	xorl	%ebx,%eax
+	shldl	$5,%edi,%edi
+	addl	%ebp,%edx
+	andl	%eax,%esi
+	vpsrld	$31,%xmm4,%xmm6
+	xorl	%ebx,%eax
+	addl	%edi,%edx
+	shrdl	$7,%edi,%edi
+	xorl	%ebx,%esi
+	vpslldq	$12,%xmm4,%xmm0
+	vpaddd	%xmm4,%xmm4,%xmm4
+	movl	%edx,%ebp
+	addl	8(%esp),%ecx
+	xorl	%eax,%edi
+	shldl	$5,%edx,%edx
+	vpsrld	$30,%xmm0,%xmm7
+	vpor	%xmm6,%xmm4,%xmm4
+	addl	%esi,%ecx
+	andl	%edi,%ebp
+	xorl	%eax,%edi
+	addl	%edx,%ecx
+	vpslld	$2,%xmm0,%xmm0
+	shrdl	$7,%edx,%edx
+	xorl	%eax,%ebp
+	vpxor	%xmm7,%xmm4,%xmm4
+	movl	%ecx,%esi
+	addl	12(%esp),%ebx
+	xorl	%edi,%edx
+	shldl	$5,%ecx,%ecx
+	vpxor	%xmm0,%xmm4,%xmm4
+	addl	%ebp,%ebx
+	andl	%edx,%esi
+	vmovdqa	96(%esp),%xmm0
+	xorl	%edi,%edx
+	addl	%ecx,%ebx
+	shrdl	$7,%ecx,%ecx
+	xorl	%edi,%esi
+	vpalignr	$8,%xmm1,%xmm2,%xmm5
+	movl	%ebx,%ebp
+	addl	16(%esp),%eax
+	vpaddd	%xmm4,%xmm0,%xmm0
+	vmovdqa	%xmm1,80(%esp)
+	xorl	%edx,%ecx
+	shldl	$5,%ebx,%ebx
+	vpsrldq	$4,%xmm4,%xmm7
+	addl	%esi,%eax
+	andl	%ecx,%ebp
+	vpxor	%xmm1,%xmm5,%xmm5
+	xorl	%edx,%ecx
+	addl	%ebx,%eax
+	vpxor	%xmm3,%xmm7,%xmm7
+	shrdl	$7,%ebx,%ebx
+	xorl	%edx,%ebp
+	vmovdqa	%xmm0,(%esp)
+	movl	%eax,%esi
+	addl	20(%esp),%edi
+	vpxor	%xmm7,%xmm5,%xmm5
+	xorl	%ecx,%ebx
+	shldl	$5,%eax,%eax
+	addl	%ebp,%edi
+	andl	%ebx,%esi
+	vpsrld	$31,%xmm5,%xmm7
+	xorl	%ecx,%ebx
+	addl	%eax,%edi
+	shrdl	$7,%eax,%eax
+	xorl	%ecx,%esi
+	vpslldq	$12,%xmm5,%xmm1
+	vpaddd	%xmm5,%xmm5,%xmm5
+	movl	%edi,%ebp
+	addl	24(%esp),%edx
+	xorl	%ebx,%eax
+	shldl	$5,%edi,%edi
+	vpsrld	$30,%xmm1,%xmm0
+	vpor	%xmm7,%xmm5,%xmm5
+	addl	%esi,%edx
+	andl	%eax,%ebp
+	xorl	%ebx,%eax
+	addl	%edi,%edx
+	vpslld	$2,%xmm1,%xmm1
+	shrdl	$7,%edi,%edi
+	xorl	%ebx,%ebp
+	vpxor	%xmm0,%xmm5,%xmm5
+	movl	%edx,%esi
+	addl	28(%esp),%ecx
+	xorl	%eax,%edi
+	shldl	$5,%edx,%edx
+	vpxor	%xmm1,%xmm5,%xmm5
+	addl	%ebp,%ecx
+	andl	%edi,%esi
+	vmovdqa	112(%esp),%xmm1
+	xorl	%eax,%edi
+	addl	%edx,%ecx
+	shrdl	$7,%edx,%edx
+	xorl	%eax,%esi
+	vpalignr	$8,%xmm2,%xmm3,%xmm6
+	movl	%ecx,%ebp
+	addl	32(%esp),%ebx
+	vpaddd	%xmm5,%xmm1,%xmm1
+	vmovdqa	%xmm2,96(%esp)
+	xorl	%edi,%edx
+	shldl	$5,%ecx,%ecx
+	vpsrldq	$4,%xmm5,%xmm0
+	addl	%esi,%ebx
+	andl	%edx,%ebp
+	vpxor	%xmm2,%xmm6,%xmm6
+	xorl	%edi,%edx
+	addl	%ecx,%ebx
+	vpxor	%xmm4,%xmm0,%xmm0
+	shrdl	$7,%ecx,%ecx
+	xorl	%edi,%ebp
+	vmovdqa	%xmm1,16(%esp)
+	movl	%ebx,%esi
+	addl	36(%esp),%eax
+	vpxor	%xmm0,%xmm6,%xmm6
+	xorl	%edx,%ecx
+	shldl	$5,%ebx,%ebx
+	addl	%ebp,%eax
+	andl	%ecx,%esi
+	vpsrld	$31,%xmm6,%xmm0
+	xorl	%edx,%ecx
+	addl	%ebx,%eax
+	shrdl	$7,%ebx,%ebx
+	xorl	%edx,%esi
+	vpslldq	$12,%xmm6,%xmm2
+	vpaddd	%xmm6,%xmm6,%xmm6
+	movl	%eax,%ebp
+	addl	40(%esp),%edi
+	xorl	%ecx,%ebx
+	shldl	$5,%eax,%eax
+	vpsrld	$30,%xmm2,%xmm1
+	vpor	%xmm0,%xmm6,%xmm6
+	addl	%esi,%edi
+	andl	%ebx,%ebp
+	xorl	%ecx,%ebx
+	addl	%eax,%edi
+	vpslld	$2,%xmm2,%xmm2
+	vmovdqa	64(%esp),%xmm0
+	shrdl	$7,%eax,%eax
+	xorl	%ecx,%ebp
+	vpxor	%xmm1,%xmm6,%xmm6
+	movl	%edi,%esi
+	addl	44(%esp),%edx
+	xorl	%ebx,%eax
+	shldl	$5,%edi,%edi
+	vpxor	%xmm2,%xmm6,%xmm6
+	addl	%ebp,%edx
+	andl	%eax,%esi
+	vmovdqa	112(%esp),%xmm2
+	xorl	%ebx,%eax
+	addl	%edi,%edx
+	shrdl	$7,%edi,%edi
+	xorl	%ebx,%esi
+	vpalignr	$8,%xmm3,%xmm4,%xmm7
+	movl	%edx,%ebp
+	addl	48(%esp),%ecx
+	vpaddd	%xmm6,%xmm2,%xmm2
+	vmovdqa	%xmm3,64(%esp)
+	xorl	%eax,%edi
+	shldl	$5,%edx,%edx
+	vpsrldq	$4,%xmm6,%xmm1
+	addl	%esi,%ecx
+	andl	%edi,%ebp
+	vpxor	%xmm3,%xmm7,%xmm7
+	xorl	%eax,%edi
+	addl	%edx,%ecx
+	vpxor	%xmm5,%xmm1,%xmm1
+	shrdl	$7,%edx,%edx
+	xorl	%eax,%ebp
+	vmovdqa	%xmm2,32(%esp)
+	movl	%ecx,%esi
+	addl	52(%esp),%ebx
+	vpxor	%xmm1,%xmm7,%xmm7
+	xorl	%edi,%edx
+	shldl	$5,%ecx,%ecx
+	addl	%ebp,%ebx
+	andl	%edx,%esi
+	vpsrld	$31,%xmm7,%xmm1
+	xorl	%edi,%edx
+	addl	%ecx,%ebx
+	shrdl	$7,%ecx,%ecx
+	xorl	%edi,%esi
+	vpslldq	$12,%xmm7,%xmm3
+	vpaddd	%xmm7,%xmm7,%xmm7
+	movl	%ebx,%ebp
+	addl	56(%esp),%eax
+	xorl	%edx,%ecx
+	shldl	$5,%ebx,%ebx
+	vpsrld	$30,%xmm3,%xmm2
+	vpor	%xmm1,%xmm7,%xmm7
+	addl	%esi,%eax
+	andl	%ecx,%ebp
+	xorl	%edx,%ecx
+	addl	%ebx,%eax
+	vpslld	$2,%xmm3,%xmm3
+	vmovdqa	80(%esp),%xmm1
+	shrdl	$7,%ebx,%ebx
+	xorl	%edx,%ebp
+	vpxor	%xmm2,%xmm7,%xmm7
+	movl	%eax,%esi
+	addl	60(%esp),%edi
+	xorl	%ecx,%ebx
+	shldl	$5,%eax,%eax
+	vpxor	%xmm3,%xmm7,%xmm7
+	addl	%ebp,%edi
+	andl	%ebx,%esi
+	vmovdqa	112(%esp),%xmm3
+	xorl	%ecx,%ebx
+	addl	%eax,%edi
+	vpalignr	$8,%xmm6,%xmm7,%xmm2
+	vpxor	%xmm4,%xmm0,%xmm0
+	shrdl	$7,%eax,%eax
+	xorl	%ecx,%esi
+	movl	%edi,%ebp
+	addl	(%esp),%edx
+	vpxor	%xmm1,%xmm0,%xmm0
+	vmovdqa	%xmm4,80(%esp)
+	xorl	%ebx,%eax
+	shldl	$5,%edi,%edi
+	vmovdqa	%xmm3,%xmm4
+	vpaddd	%xmm7,%xmm3,%xmm3
+	addl	%esi,%edx
+	andl	%eax,%ebp
+	vpxor	%xmm2,%xmm0,%xmm0
+	xorl	%ebx,%eax
+	addl	%edi,%edx
+	shrdl	$7,%edi,%edi
+	xorl	%ebx,%ebp
+	vpsrld	$30,%xmm0,%xmm2
+	vmovdqa	%xmm3,48(%esp)
+	movl	%edx,%esi
+	addl	4(%esp),%ecx
+	xorl	%eax,%edi
+	shldl	$5,%edx,%edx
+	vpslld	$2,%xmm0,%xmm0
+	addl	%ebp,%ecx
+	andl	%edi,%esi
+	xorl	%eax,%edi
+	addl	%edx,%ecx
+	shrdl	$7,%edx,%edx
+	xorl	%eax,%esi
+	movl	%ecx,%ebp
+	addl	8(%esp),%ebx
+	vpor	%xmm2,%xmm0,%xmm0
+	xorl	%edi,%edx
+	shldl	$5,%ecx,%ecx
+	vmovdqa	96(%esp),%xmm2
+	addl	%esi,%ebx
+	andl	%edx,%ebp
+	xorl	%edi,%edx
+	addl	%ecx,%ebx
+	addl	12(%esp),%eax
+	xorl	%edi,%ebp
+	movl	%ebx,%esi
+	shldl	$5,%ebx,%ebx
+	addl	%ebp,%eax
+	xorl	%edx,%esi
+	shrdl	$7,%ecx,%ecx
+	addl	%ebx,%eax
+	vpalignr	$8,%xmm7,%xmm0,%xmm3
+	vpxor	%xmm5,%xmm1,%xmm1
+	addl	16(%esp),%edi
+	xorl	%ecx,%esi
+	movl	%eax,%ebp
+	shldl	$5,%eax,%eax
+	vpxor	%xmm2,%xmm1,%xmm1
+	vmovdqa	%xmm5,96(%esp)
+	addl	%esi,%edi
+	xorl	%ecx,%ebp
+	vmovdqa	%xmm4,%xmm5
+	vpaddd	%xmm0,%xmm4,%xmm4
+	shrdl	$7,%ebx,%ebx
+	addl	%eax,%edi
+	vpxor	%xmm3,%xmm1,%xmm1
+	addl	20(%esp),%edx
+	xorl	%ebx,%ebp
+	movl	%edi,%esi
+	shldl	$5,%edi,%edi
+	vpsrld	$30,%xmm1,%xmm3
+	vmovdqa	%xmm4,(%esp)
+	addl	%ebp,%edx
+	xorl	%ebx,%esi
+	shrdl	$7,%eax,%eax
+	addl	%edi,%edx
+	vpslld	$2,%xmm1,%xmm1
+	addl	24(%esp),%ecx
+	xorl	%eax,%esi
+	movl	%edx,%ebp
+	shldl	$5,%edx,%edx
+	addl	%esi,%ecx
+	xorl	%eax,%ebp
+	shrdl	$7,%edi,%edi
+	addl	%edx,%ecx
+	vpor	%xmm3,%xmm1,%xmm1
+	addl	28(%esp),%ebx
+	xorl	%edi,%ebp
+	vmovdqa	64(%esp),%xmm3
+	movl	%ecx,%esi
+	shldl	$5,%ecx,%ecx
+	addl	%ebp,%ebx
+	xorl	%edi,%esi
+	shrdl	$7,%edx,%edx
+	addl	%ecx,%ebx
+	vpalignr	$8,%xmm0,%xmm1,%xmm4
+	vpxor	%xmm6,%xmm2,%xmm2
+	addl	32(%esp),%eax
+	xorl	%edx,%esi
+	movl	%ebx,%ebp
+	shldl	$5,%ebx,%ebx
+	vpxor	%xmm3,%xmm2,%xmm2
+	vmovdqa	%xmm6,64(%esp)
+	addl	%esi,%eax
+	xorl	%edx,%ebp
+	vmovdqa	128(%esp),%xmm6
+	vpaddd	%xmm1,%xmm5,%xmm5
+	shrdl	$7,%ecx,%ecx
+	addl	%ebx,%eax
+	vpxor	%xmm4,%xmm2,%xmm2
+	addl	36(%esp),%edi
+	xorl	%ecx,%ebp
+	movl	%eax,%esi
+	shldl	$5,%eax,%eax
+	vpsrld	$30,%xmm2,%xmm4
+	vmovdqa	%xmm5,16(%esp)
+	addl	%ebp,%edi
+	xorl	%ecx,%esi
+	shrdl	$7,%ebx,%ebx
+	addl	%eax,%edi
+	vpslld	$2,%xmm2,%xmm2
+	addl	40(%esp),%edx
+	xorl	%ebx,%esi
+	movl	%edi,%ebp
+	shldl	$5,%edi,%edi
+	addl	%esi,%edx
+	xorl	%ebx,%ebp
+	shrdl	$7,%eax,%eax
+	addl	%edi,%edx
+	vpor	%xmm4,%xmm2,%xmm2
+	addl	44(%esp),%ecx
+	xorl	%eax,%ebp
+	vmovdqa	80(%esp),%xmm4
+	movl	%edx,%esi
+	shldl	$5,%edx,%edx
+	addl	%ebp,%ecx
+	xorl	%eax,%esi
+	shrdl	$7,%edi,%edi
+	addl	%edx,%ecx
+	vpalignr	$8,%xmm1,%xmm2,%xmm5
+	vpxor	%xmm7,%xmm3,%xmm3
+	addl	48(%esp),%ebx
+	xorl	%edi,%esi
+	movl	%ecx,%ebp
+	shldl	$5,%ecx,%ecx
+	vpxor	%xmm4,%xmm3,%xmm3
+	vmovdqa	%xmm7,80(%esp)
+	addl	%esi,%ebx
+	xorl	%edi,%ebp
+	vmovdqa	%xmm6,%xmm7
+	vpaddd	%xmm2,%xmm6,%xmm6
+	shrdl	$7,%edx,%edx
+	addl	%ecx,%ebx
+	vpxor	%xmm5,%xmm3,%xmm3
+	addl	52(%esp),%eax
+	xorl	%edx,%ebp
+	movl	%ebx,%esi
+	shldl	$5,%ebx,%ebx
+	vpsrld	$30,%xmm3,%xmm5
+	vmovdqa	%xmm6,32(%esp)
+	addl	%ebp,%eax
+	xorl	%edx,%esi
+	shrdl	$7,%ecx,%ecx
+	addl	%ebx,%eax
+	vpslld	$2,%xmm3,%xmm3
+	addl	56(%esp),%edi
+	xorl	%ecx,%esi
+	movl	%eax,%ebp
+	shldl	$5,%eax,%eax
+	addl	%esi,%edi
+	xorl	%ecx,%ebp
+	shrdl	$7,%ebx,%ebx
+	addl	%eax,%edi
+	vpor	%xmm5,%xmm3,%xmm3
+	addl	60(%esp),%edx
+	xorl	%ebx,%ebp
+	vmovdqa	96(%esp),%xmm5
+	movl	%edi,%esi
+	shldl	$5,%edi,%edi
+	addl	%ebp,%edx
+	xorl	%ebx,%esi
+	shrdl	$7,%eax,%eax
+	addl	%edi,%edx
+	vpalignr	$8,%xmm2,%xmm3,%xmm6
+	vpxor	%xmm0,%xmm4,%xmm4
+	addl	(%esp),%ecx
+	xorl	%eax,%esi
+	movl	%edx,%ebp
+	shldl	$5,%edx,%edx
+	vpxor	%xmm5,%xmm4,%xmm4
+	vmovdqa	%xmm0,96(%esp)
+	addl	%esi,%ecx
+	xorl	%eax,%ebp
+	vmovdqa	%xmm7,%xmm0
+	vpaddd	%xmm3,%xmm7,%xmm7
+	shrdl	$7,%edi,%edi
+	addl	%edx,%ecx
+	vpxor	%xmm6,%xmm4,%xmm4
+	addl	4(%esp),%ebx
+	xorl	%edi,%ebp
+	movl	%ecx,%esi
+	shldl	$5,%ecx,%ecx
+	vpsrld	$30,%xmm4,%xmm6
+	vmovdqa	%xmm7,48(%esp)
+	addl	%ebp,%ebx
+	xorl	%edi,%esi
+	shrdl	$7,%edx,%edx
+	addl	%ecx,%ebx
+	vpslld	$2,%xmm4,%xmm4
+	addl	8(%esp),%eax
+	xorl	%edx,%esi
+	movl	%ebx,%ebp
+	shldl	$5,%ebx,%ebx
+	addl	%esi,%eax
+	xorl	%edx,%ebp
+	shrdl	$7,%ecx,%ecx
+	addl	%ebx,%eax
+	vpor	%xmm6,%xmm4,%xmm4
+	addl	12(%esp),%edi
+	xorl	%ecx,%ebp
+	vmovdqa	64(%esp),%xmm6
+	movl	%eax,%esi
+	shldl	$5,%eax,%eax
+	addl	%ebp,%edi
+	xorl	%ecx,%esi
+	shrdl	$7,%ebx,%ebx
+	addl	%eax,%edi
+	vpalignr	$8,%xmm3,%xmm4,%xmm7
+	vpxor	%xmm1,%xmm5,%xmm5
+	addl	16(%esp),%edx
+	xorl	%ebx,%esi
+	movl	%edi,%ebp
+	shldl	$5,%edi,%edi
+	vpxor	%xmm6,%xmm5,%xmm5
+	vmovdqa	%xmm1,64(%esp)
+	addl	%esi,%edx
+	xorl	%ebx,%ebp
+	vmovdqa	%xmm0,%xmm1
+	vpaddd	%xmm4,%xmm0,%xmm0
+	shrdl	$7,%eax,%eax
+	addl	%edi,%edx
+	vpxor	%xmm7,%xmm5,%xmm5
+	addl	20(%esp),%ecx
+	xorl	%eax,%ebp
+	movl	%edx,%esi
+	shldl	$5,%edx,%edx
+	vpsrld	$30,%xmm5,%xmm7
+	vmovdqa	%xmm0,(%esp)
+	addl	%ebp,%ecx
+	xorl	%eax,%esi
+	shrdl	$7,%edi,%edi
+	addl	%edx,%ecx
+	vpslld	$2,%xmm5,%xmm5
+	addl	24(%esp),%ebx
+	xorl	%edi,%esi
+	movl	%ecx,%ebp
+	shldl	$5,%ecx,%ecx
+	addl	%esi,%ebx
+	xorl	%edi,%ebp
+	shrdl	$7,%edx,%edx
+	addl	%ecx,%ebx
+	vpor	%xmm7,%xmm5,%xmm5
+	addl	28(%esp),%eax
+	vmovdqa	80(%esp),%xmm7
+	shrdl	$7,%ecx,%ecx
+	movl	%ebx,%esi
+	xorl	%edx,%ebp
+	shldl	$5,%ebx,%ebx
+	addl	%ebp,%eax
+	xorl	%ecx,%esi
+	xorl	%edx,%ecx
+	addl	%ebx,%eax
+	vpalignr	$8,%xmm4,%xmm5,%xmm0
+	vpxor	%xmm2,%xmm6,%xmm6
+	addl	32(%esp),%edi
+	andl	%ecx,%esi
+	xorl	%edx,%ecx
+	shrdl	$7,%ebx,%ebx
+	vpxor	%xmm7,%xmm6,%xmm6
+	vmovdqa	%xmm2,80(%esp)
+	movl	%eax,%ebp
+	xorl	%ecx,%esi
+	vmovdqa	%xmm1,%xmm2
+	vpaddd	%xmm5,%xmm1,%xmm1
+	shldl	$5,%eax,%eax
+	addl	%esi,%edi
+	vpxor	%xmm0,%xmm6,%xmm6
+	xorl	%ebx,%ebp
+	xorl	%ecx,%ebx
+	addl	%eax,%edi
+	addl	36(%esp),%edx
+	vpsrld	$30,%xmm6,%xmm0
+	vmovdqa	%xmm1,16(%esp)
+	andl	%ebx,%ebp
+	xorl	%ecx,%ebx
+	shrdl	$7,%eax,%eax
+	movl	%edi,%esi
+	vpslld	$2,%xmm6,%xmm6
+	xorl	%ebx,%ebp
+	shldl	$5,%edi,%edi
+	addl	%ebp,%edx
+	xorl	%eax,%esi
+	xorl	%ebx,%eax
+	addl	%edi,%edx
+	addl	40(%esp),%ecx
+	andl	%eax,%esi
+	vpor	%xmm0,%xmm6,%xmm6
+	xorl	%ebx,%eax
+	shrdl	$7,%edi,%edi
+	vmovdqa	96(%esp),%xmm0
+	movl	%edx,%ebp
+	xorl	%eax,%esi
+	shldl	$5,%edx,%edx
+	addl	%esi,%ecx
+	xorl	%edi,%ebp
+	xorl	%eax,%edi
+	addl	%edx,%ecx
+	addl	44(%esp),%ebx
+	andl	%edi,%ebp
+	xorl	%eax,%edi
+	shrdl	$7,%edx,%edx
+	movl	%ecx,%esi
+	xorl	%edi,%ebp
+	shldl	$5,%ecx,%ecx
+	addl	%ebp,%ebx
+	xorl	%edx,%esi
+	xorl	%edi,%edx
+	addl	%ecx,%ebx
+	vpalignr	$8,%xmm5,%xmm6,%xmm1
+	vpxor	%xmm3,%xmm7,%xmm7
+	addl	48(%esp),%eax
+	andl	%edx,%esi
+	xorl	%edi,%edx
+	shrdl	$7,%ecx,%ecx
+	vpxor	%xmm0,%xmm7,%xmm7
+	vmovdqa	%xmm3,96(%esp)
+	movl	%ebx,%ebp
+	xorl	%edx,%esi
+	vmovdqa	144(%esp),%xmm3
+	vpaddd	%xmm6,%xmm2,%xmm2
+	shldl	$5,%ebx,%ebx
+	addl	%esi,%eax
+	vpxor	%xmm1,%xmm7,%xmm7
+	xorl	%ecx,%ebp
+	xorl	%edx,%ecx
+	addl	%ebx,%eax
+	addl	52(%esp),%edi
+	vpsrld	$30,%xmm7,%xmm1
+	vmovdqa	%xmm2,32(%esp)
+	andl	%ecx,%ebp
+	xorl	%edx,%ecx
+	shrdl	$7,%ebx,%ebx
+	movl	%eax,%esi
+	vpslld	$2,%xmm7,%xmm7
+	xorl	%ecx,%ebp
+	shldl	$5,%eax,%eax
+	addl	%ebp,%edi
+	xorl	%ebx,%esi
+	xorl	%ecx,%ebx
+	addl	%eax,%edi
+	addl	56(%esp),%edx
+	andl	%ebx,%esi
+	vpor	%xmm1,%xmm7,%xmm7
+	xorl	%ecx,%ebx
+	shrdl	$7,%eax,%eax
+	vmovdqa	64(%esp),%xmm1
+	movl	%edi,%ebp
+	xorl	%ebx,%esi
+	shldl	$5,%edi,%edi
+	addl	%esi,%edx
+	xorl	%eax,%ebp
+	xorl	%ebx,%eax
+	addl	%edi,%edx
+	addl	60(%esp),%ecx
+	andl	%eax,%ebp
+	xorl	%ebx,%eax
+	shrdl	$7,%edi,%edi
+	movl	%edx,%esi
+	xorl	%eax,%ebp
+	shldl	$5,%edx,%edx
+	addl	%ebp,%ecx
+	xorl	%edi,%esi
+	xorl	%eax,%edi
+	addl	%edx,%ecx
+	vpalignr	$8,%xmm6,%xmm7,%xmm2
+	vpxor	%xmm4,%xmm0,%xmm0
+	addl	(%esp),%ebx
+	andl	%edi,%esi
+	xorl	%eax,%edi
+	shrdl	$7,%edx,%edx
+	vpxor	%xmm1,%xmm0,%xmm0
+	vmovdqa	%xmm4,64(%esp)
+	movl	%ecx,%ebp
+	xorl	%edi,%esi
+	vmovdqa	%xmm3,%xmm4
+	vpaddd	%xmm7,%xmm3,%xmm3
+	shldl	$5,%ecx,%ecx
+	addl	%esi,%ebx
+	vpxor	%xmm2,%xmm0,%xmm0
+	xorl	%edx,%ebp
+	xorl	%edi,%edx
+	addl	%ecx,%ebx
+	addl	4(%esp),%eax
+	vpsrld	$30,%xmm0,%xmm2
+	vmovdqa	%xmm3,48(%esp)
+	andl	%edx,%ebp
+	xorl	%edi,%edx
+	shrdl	$7,%ecx,%ecx
+	movl	%ebx,%esi
+	vpslld	$2,%xmm0,%xmm0
+	xorl	%edx,%ebp
+	shldl	$5,%ebx,%ebx
+	addl	%ebp,%eax
+	xorl	%ecx,%esi
+	xorl	%edx,%ecx
+	addl	%ebx,%eax
+	addl	8(%esp),%edi
+	andl	%ecx,%esi
+	vpor	%xmm2,%xmm0,%xmm0
+	xorl	%edx,%ecx
+	shrdl	$7,%ebx,%ebx
+	vmovdqa	80(%esp),%xmm2
+	movl	%eax,%ebp
+	xorl	%ecx,%esi
+	shldl	$5,%eax,%eax
+	addl	%esi,%edi
+	xorl	%ebx,%ebp
+	xorl	%ecx,%ebx
+	addl	%eax,%edi
+	addl	12(%esp),%edx
+	andl	%ebx,%ebp
+	xorl	%ecx,%ebx
+	shrdl	$7,%eax,%eax
+	movl	%edi,%esi
+	xorl	%ebx,%ebp
+	shldl	$5,%edi,%edi
+	addl	%ebp,%edx
+	xorl	%eax,%esi
+	xorl	%ebx,%eax
+	addl	%edi,%edx
+	vpalignr	$8,%xmm7,%xmm0,%xmm3
+	vpxor	%xmm5,%xmm1,%xmm1
+	addl	16(%esp),%ecx
+	andl	%eax,%esi
+	xorl	%ebx,%eax
+	shrdl	$7,%edi,%edi
+	vpxor	%xmm2,%xmm1,%xmm1
+	vmovdqa	%xmm5,80(%esp)
+	movl	%edx,%ebp
+	xorl	%eax,%esi
+	vmovdqa	%xmm4,%xmm5
+	vpaddd	%xmm0,%xmm4,%xmm4
+	shldl	$5,%edx,%edx
+	addl	%esi,%ecx
+	vpxor	%xmm3,%xmm1,%xmm1
+	xorl	%edi,%ebp
+	xorl	%eax,%edi
+	addl	%edx,%ecx
+	addl	20(%esp),%ebx
+	vpsrld	$30,%xmm1,%xmm3
+	vmovdqa	%xmm4,(%esp)
+	andl	%edi,%ebp
+	xorl	%eax,%edi
+	shrdl	$7,%edx,%edx
+	movl	%ecx,%esi
+	vpslld	$2,%xmm1,%xmm1
+	xorl	%edi,%ebp
+	shldl	$5,%ecx,%ecx
+	addl	%ebp,%ebx
+	xorl	%edx,%esi
+	xorl	%edi,%edx
+	addl	%ecx,%ebx
+	addl	24(%esp),%eax
+	andl	%edx,%esi
+	vpor	%xmm3,%xmm1,%xmm1
+	xorl	%edi,%edx
+	shrdl	$7,%ecx,%ecx
+	vmovdqa	96(%esp),%xmm3
+	movl	%ebx,%ebp
+	xorl	%edx,%esi
+	shldl	$5,%ebx,%ebx
+	addl	%esi,%eax
+	xorl	%ecx,%ebp
+	xorl	%edx,%ecx
+	addl	%ebx,%eax
+	addl	28(%esp),%edi
+	andl	%ecx,%ebp
+	xorl	%edx,%ecx
+	shrdl	$7,%ebx,%ebx
+	movl	%eax,%esi
+	xorl	%ecx,%ebp
+	shldl	$5,%eax,%eax
+	addl	%ebp,%edi
+	xorl	%ebx,%esi
+	xorl	%ecx,%ebx
+	addl	%eax,%edi
+	vpalignr	$8,%xmm0,%xmm1,%xmm4
+	vpxor	%xmm6,%xmm2,%xmm2
+	addl	32(%esp),%edx
+	andl	%ebx,%esi
+	xorl	%ecx,%ebx
+	shrdl	$7,%eax,%eax
+	vpxor	%xmm3,%xmm2,%xmm2
+	vmovdqa	%xmm6,96(%esp)
+	movl	%edi,%ebp
+	xorl	%ebx,%esi
+	vmovdqa	%xmm5,%xmm6
+	vpaddd	%xmm1,%xmm5,%xmm5
+	shldl	$5,%edi,%edi
+	addl	%esi,%edx
+	vpxor	%xmm4,%xmm2,%xmm2
+	xorl	%eax,%ebp
+	xorl	%ebx,%eax
+	addl	%edi,%edx
+	addl	36(%esp),%ecx
+	vpsrld	$30,%xmm2,%xmm4
+	vmovdqa	%xmm5,16(%esp)
+	andl	%eax,%ebp
+	xorl	%ebx,%eax
+	shrdl	$7,%edi,%edi
+	movl	%edx,%esi
+	vpslld	$2,%xmm2,%xmm2
+	xorl	%eax,%ebp
+	shldl	$5,%edx,%edx
+	addl	%ebp,%ecx
+	xorl	%edi,%esi
+	xorl	%eax,%edi
+	addl	%edx,%ecx
+	addl	40(%esp),%ebx
+	andl	%edi,%esi
+	vpor	%xmm4,%xmm2,%xmm2
+	xorl	%eax,%edi
+	shrdl	$7,%edx,%edx
+	vmovdqa	64(%esp),%xmm4
+	movl	%ecx,%ebp
+	xorl	%edi,%esi
+	shldl	$5,%ecx,%ecx
+	addl	%esi,%ebx
+	xorl	%edx,%ebp
+	xorl	%edi,%edx
+	addl	%ecx,%ebx
+	addl	44(%esp),%eax
+	andl	%edx,%ebp
+	xorl	%edi,%edx
+	shrdl	$7,%ecx,%ecx
+	movl	%ebx,%esi
+	xorl	%edx,%ebp
+	shldl	$5,%ebx,%ebx
+	addl	%ebp,%eax
+	xorl	%edx,%esi
+	addl	%ebx,%eax
+	vpalignr	$8,%xmm1,%xmm2,%xmm5
+	vpxor	%xmm7,%xmm3,%xmm3
+	addl	48(%esp),%edi
+	xorl	%ecx,%esi
+	movl	%eax,%ebp
+	shldl	$5,%eax,%eax
+	vpxor	%xmm4,%xmm3,%xmm3
+	vmovdqa	%xmm7,64(%esp)
+	addl	%esi,%edi
+	xorl	%ecx,%ebp
+	vmovdqa	%xmm6,%xmm7
+	vpaddd	%xmm2,%xmm6,%xmm6
+	shrdl	$7,%ebx,%ebx
+	addl	%eax,%edi
+	vpxor	%xmm5,%xmm3,%xmm3
+	addl	52(%esp),%edx
+	xorl	%ebx,%ebp
+	movl	%edi,%esi
+	shldl	$5,%edi,%edi
+	vpsrld	$30,%xmm3,%xmm5
+	vmovdqa	%xmm6,32(%esp)
+	addl	%ebp,%edx
+	xorl	%ebx,%esi
+	shrdl	$7,%eax,%eax
+	addl	%edi,%edx
+	vpslld	$2,%xmm3,%xmm3
+	addl	56(%esp),%ecx
+	xorl	%eax,%esi
+	movl	%edx,%ebp
+	shldl	$5,%edx,%edx
+	addl	%esi,%ecx
+	xorl	%eax,%ebp
+	shrdl	$7,%edi,%edi
+	addl	%edx,%ecx
+	vpor	%xmm5,%xmm3,%xmm3
+	addl	60(%esp),%ebx
+	xorl	%edi,%ebp
+	movl	%ecx,%esi
+	shldl	$5,%ecx,%ecx
+	addl	%ebp,%ebx
+	xorl	%edi,%esi
+	shrdl	$7,%edx,%edx
+	addl	%ecx,%ebx
+	addl	(%esp),%eax
+	vpaddd	%xmm3,%xmm7,%xmm7
+	xorl	%edx,%esi
+	movl	%ebx,%ebp
+	shldl	$5,%ebx,%ebx
+	addl	%esi,%eax
+	vmovdqa	%xmm7,48(%esp)
+	xorl	%edx,%ebp
+	shrdl	$7,%ecx,%ecx
+	addl	%ebx,%eax
+	addl	4(%esp),%edi
+	xorl	%ecx,%ebp
+	movl	%eax,%esi
+	shldl	$5,%eax,%eax
+	addl	%ebp,%edi
+	xorl	%ecx,%esi
+	shrdl	$7,%ebx,%ebx
+	addl	%eax,%edi
+	addl	8(%esp),%edx
+	xorl	%ebx,%esi
+	movl	%edi,%ebp
+	shldl	$5,%edi,%edi
+	addl	%esi,%edx
+	xorl	%ebx,%ebp
+	shrdl	$7,%eax,%eax
+	addl	%edi,%edx
+	addl	12(%esp),%ecx
+	xorl	%eax,%ebp
+	movl	%edx,%esi
+	shldl	$5,%edx,%edx
+	addl	%ebp,%ecx
+	xorl	%eax,%esi
+	shrdl	$7,%edi,%edi
+	addl	%edx,%ecx
+	movl	196(%esp),%ebp
+	cmpl	200(%esp),%ebp
+	je	.L008done
+	vmovdqa	160(%esp),%xmm7
+	vmovdqa	176(%esp),%xmm6
+	vmovdqu	(%ebp),%xmm0
+	vmovdqu	16(%ebp),%xmm1
+	vmovdqu	32(%ebp),%xmm2
+	vmovdqu	48(%ebp),%xmm3
+	addl	$64,%ebp
+	vpshufb	%xmm6,%xmm0,%xmm0
+	movl	%ebp,196(%esp)
+	vmovdqa	%xmm7,96(%esp)
+	addl	16(%esp),%ebx
+	xorl	%edi,%esi
+	vpshufb	%xmm6,%xmm1,%xmm1
+	movl	%ecx,%ebp
+	shldl	$5,%ecx,%ecx
+	vpaddd	%xmm7,%xmm0,%xmm4
+	addl	%esi,%ebx
+	xorl	%edi,%ebp
+	shrdl	$7,%edx,%edx
+	addl	%ecx,%ebx
+	vmovdqa	%xmm4,(%esp)
+	addl	20(%esp),%eax
+	xorl	%edx,%ebp
+	movl	%ebx,%esi
+	shldl	$5,%ebx,%ebx
+	addl	%ebp,%eax
+	xorl	%edx,%esi
+	shrdl	$7,%ecx,%ecx
+	addl	%ebx,%eax
+	addl	24(%esp),%edi
+	xorl	%ecx,%esi
+	movl	%eax,%ebp
+	shldl	$5,%eax,%eax
+	addl	%esi,%edi
+	xorl	%ecx,%ebp
+	shrdl	$7,%ebx,%ebx
+	addl	%eax,%edi
+	addl	28(%esp),%edx
+	xorl	%ebx,%ebp
+	movl	%edi,%esi
+	shldl	$5,%edi,%edi
+	addl	%ebp,%edx
+	xorl	%ebx,%esi
+	shrdl	$7,%eax,%eax
+	addl	%edi,%edx
+	addl	32(%esp),%ecx
+	xorl	%eax,%esi
+	vpshufb	%xmm6,%xmm2,%xmm2
+	movl	%edx,%ebp
+	shldl	$5,%edx,%edx
+	vpaddd	%xmm7,%xmm1,%xmm5
+	addl	%esi,%ecx
+	xorl	%eax,%ebp
+	shrdl	$7,%edi,%edi
+	addl	%edx,%ecx
+	vmovdqa	%xmm5,16(%esp)
+	addl	36(%esp),%ebx
+	xorl	%edi,%ebp
+	movl	%ecx,%esi
+	shldl	$5,%ecx,%ecx
+	addl	%ebp,%ebx
+	xorl	%edi,%esi
+	shrdl	$7,%edx,%edx
+	addl	%ecx,%ebx
+	addl	40(%esp),%eax
+	xorl	%edx,%esi
+	movl	%ebx,%ebp
+	shldl	$5,%ebx,%ebx
+	addl	%esi,%eax
+	xorl	%edx,%ebp
+	shrdl	$7,%ecx,%ecx
+	addl	%ebx,%eax
+	addl	44(%esp),%edi
+	xorl	%ecx,%ebp
+	movl	%eax,%esi
+	shldl	$5,%eax,%eax
+	addl	%ebp,%edi
+	xorl	%ecx,%esi
+	shrdl	$7,%ebx,%ebx
+	addl	%eax,%edi
+	addl	48(%esp),%edx
+	xorl	%ebx,%esi
+	vpshufb	%xmm6,%xmm3,%xmm3
+	movl	%edi,%ebp
+	shldl	$5,%edi,%edi
+	vpaddd	%xmm7,%xmm2,%xmm6
+	addl	%esi,%edx
+	xorl	%ebx,%ebp
+	shrdl	$7,%eax,%eax
+	addl	%edi,%edx
+	vmovdqa	%xmm6,32(%esp)
+	addl	52(%esp),%ecx
+	xorl	%eax,%ebp
+	movl	%edx,%esi
+	shldl	$5,%edx,%edx
+	addl	%ebp,%ecx
+	xorl	%eax,%esi
+	shrdl	$7,%edi,%edi
+	addl	%edx,%ecx
+	addl	56(%esp),%ebx
+	xorl	%edi,%esi
+	movl	%ecx,%ebp
+	shldl	$5,%ecx,%ecx
+	addl	%esi,%ebx
+	xorl	%edi,%ebp
+	shrdl	$7,%edx,%edx
+	addl	%ecx,%ebx
+	addl	60(%esp),%eax
+	xorl	%edx,%ebp
+	movl	%ebx,%esi
+	shldl	$5,%ebx,%ebx
+	addl	%ebp,%eax
+	shrdl	$7,%ecx,%ecx
+	addl	%ebx,%eax
+	movl	192(%esp),%ebp
+	addl	(%ebp),%eax
+	addl	4(%ebp),%esi
+	addl	8(%ebp),%ecx
+	movl	%eax,(%ebp)
+	addl	12(%ebp),%edx
+	movl	%esi,4(%ebp)
+	addl	16(%ebp),%edi
+	movl	%ecx,%ebx
+	movl	%ecx,8(%ebp)
+	xorl	%edx,%ebx
+	movl	%edx,12(%ebp)
+	movl	%edi,16(%ebp)
+	movl	%esi,%ebp
+	andl	%ebx,%esi
+	movl	%ebp,%ebx
+	jmp	.L007loop
+.align	16
+.L008done:
+	addl	16(%esp),%ebx
+	xorl	%edi,%esi
+	movl	%ecx,%ebp
+	shldl	$5,%ecx,%ecx
+	addl	%esi,%ebx
+	xorl	%edi,%ebp
+	shrdl	$7,%edx,%edx
+	addl	%ecx,%ebx
+	addl	20(%esp),%eax
+	xorl	%edx,%ebp
+	movl	%ebx,%esi
+	shldl	$5,%ebx,%ebx
+	addl	%ebp,%eax
+	xorl	%edx,%esi
+	shrdl	$7,%ecx,%ecx
+	addl	%ebx,%eax
+	addl	24(%esp),%edi
+	xorl	%ecx,%esi
+	movl	%eax,%ebp
+	shldl	$5,%eax,%eax
+	addl	%esi,%edi
+	xorl	%ecx,%ebp
+	shrdl	$7,%ebx,%ebx
+	addl	%eax,%edi
+	addl	28(%esp),%edx
+	xorl	%ebx,%ebp
+	movl	%edi,%esi
+	shldl	$5,%edi,%edi
+	addl	%ebp,%edx
+	xorl	%ebx,%esi
+	shrdl	$7,%eax,%eax
+	addl	%edi,%edx
+	addl	32(%esp),%ecx
+	xorl	%eax,%esi
+	movl	%edx,%ebp
+	shldl	$5,%edx,%edx
+	addl	%esi,%ecx
+	xorl	%eax,%ebp
+	shrdl	$7,%edi,%edi
+	addl	%edx,%ecx
+	addl	36(%esp),%ebx
+	xorl	%edi,%ebp
+	movl	%ecx,%esi
+	shldl	$5,%ecx,%ecx
+	addl	%ebp,%ebx
+	xorl	%edi,%esi
+	shrdl	$7,%edx,%edx
+	addl	%ecx,%ebx
+	addl	40(%esp),%eax
+	xorl	%edx,%esi
+	movl	%ebx,%ebp
+	shldl	$5,%ebx,%ebx
+	addl	%esi,%eax
+	xorl	%edx,%ebp
+	shrdl	$7,%ecx,%ecx
+	addl	%ebx,%eax
+	addl	44(%esp),%edi
+	xorl	%ecx,%ebp
+	movl	%eax,%esi
+	shldl	$5,%eax,%eax
+	addl	%ebp,%edi
+	xorl	%ecx,%esi
+	shrdl	$7,%ebx,%ebx
+	addl	%eax,%edi
+	addl	48(%esp),%edx
+	xorl	%ebx,%esi
+	movl	%edi,%ebp
+	shldl	$5,%edi,%edi
+	addl	%esi,%edx
+	xorl	%ebx,%ebp
+	shrdl	$7,%eax,%eax
+	addl	%edi,%edx
+	addl	52(%esp),%ecx
+	xorl	%eax,%ebp
+	movl	%edx,%esi
+	shldl	$5,%edx,%edx
+	addl	%ebp,%ecx
+	xorl	%eax,%esi
+	shrdl	$7,%edi,%edi
+	addl	%edx,%ecx
+	addl	56(%esp),%ebx
+	xorl	%edi,%esi
+	movl	%ecx,%ebp
+	shldl	$5,%ecx,%ecx
+	addl	%esi,%ebx
+	xorl	%edi,%ebp
+	shrdl	$7,%edx,%edx
+	addl	%ecx,%ebx
+	addl	60(%esp),%eax
+	xorl	%edx,%ebp
+	movl	%ebx,%esi
+	shldl	$5,%ebx,%ebx
+	addl	%ebp,%eax
+	shrdl	$7,%ecx,%ecx
+	addl	%ebx,%eax
+	vzeroall
+	movl	192(%esp),%ebp
+	addl	(%ebp),%eax
+	movl	204(%esp),%esp
+	addl	4(%ebp),%esi
+	addl	8(%ebp),%ecx
+	movl	%eax,(%ebp)
+	addl	12(%ebp),%edx
+	movl	%esi,4(%ebp)
+	addl	16(%ebp),%edi
+	movl	%ecx,8(%ebp)
+	movl	%edx,12(%ebp)
+	movl	%edi,16(%ebp)
+	popl	%edi
+	popl	%esi
+	popl	%ebx
+	popl	%ebp
+	ret
+.size	_sha1_block_data_order_avx,.-_sha1_block_data_order_avx
 .align	64
 .LK_XX_XX:
 .long	1518500249,1518500249,1518500249,1518500249
diff --git a/packager/third_party/boringssl/linux-x86/crypto/sha/sha256-586.S b/packager/third_party/boringssl/linux-x86/crypto/sha/sha256-586.S
index 08d948432b..38acbd8374 100644
--- a/packager/third_party/boringssl/linux-x86/crypto/sha/sha256-586.S
+++ b/packager/third_party/boringssl/linux-x86/crypto/sha/sha256-586.S
@@ -37,11 +37,10 @@ sha256_block_data_order:
 	jz	.L003no_xmm
 	andl	$1073741824,%ecx
 	andl	$268435968,%ebx
-	testl	$536870912,%edx
-	jnz	.L004shaext
 	orl	%ebx,%ecx
 	andl	$1342177280,%ecx
 	cmpl	$1342177280,%ecx
+	je	.L004AVX
 	testl	$512,%ebx
 	jnz	.L005SSSE3
 .L003no_xmm:
@@ -3167,204 +3166,6 @@ sha256_block_data_order:
 	popl	%ebp
 	ret
 .align	32
-.L004shaext:
-	subl	$32,%esp
-	movdqu	(%esi),%xmm1
-	leal	128(%ebp),%ebp
-	movdqu	16(%esi),%xmm2
-	movdqa	128(%ebp),%xmm7
-	pshufd	$27,%xmm1,%xmm0
-	pshufd	$177,%xmm1,%xmm1
-	pshufd	$27,%xmm2,%xmm2
-.byte	102,15,58,15,202,8
-	punpcklqdq	%xmm0,%xmm2
-	jmp	.L010loop_shaext
-.align	16
-.L010loop_shaext:
-	movdqu	(%edi),%xmm3
-	movdqu	16(%edi),%xmm4
-	movdqu	32(%edi),%xmm5
-.byte	102,15,56,0,223
-	movdqu	48(%edi),%xmm6
-	movdqa	%xmm2,16(%esp)
-	movdqa	-128(%ebp),%xmm0
-	paddd	%xmm3,%xmm0
-.byte	102,15,56,0,231
-.byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
-	nop
-	movdqa	%xmm1,(%esp)
-.byte	15,56,203,202
-	movdqa	-112(%ebp),%xmm0
-	paddd	%xmm4,%xmm0
-.byte	102,15,56,0,239
-.byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
-	leal	64(%edi),%edi
-.byte	15,56,204,220
-.byte	15,56,203,202
-	movdqa	-96(%ebp),%xmm0
-	paddd	%xmm5,%xmm0
-.byte	102,15,56,0,247
-.byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
-	movdqa	%xmm6,%xmm7
-.byte	102,15,58,15,253,4
-	nop
-	paddd	%xmm7,%xmm3
-.byte	15,56,204,229
-.byte	15,56,203,202
-	movdqa	-80(%ebp),%xmm0
-	paddd	%xmm6,%xmm0
-.byte	15,56,205,222
-.byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
-	movdqa	%xmm3,%xmm7
-.byte	102,15,58,15,254,4
-	nop
-	paddd	%xmm7,%xmm4
-.byte	15,56,204,238
-.byte	15,56,203,202
-	movdqa	-64(%ebp),%xmm0
-	paddd	%xmm3,%xmm0
-.byte	15,56,205,227
-.byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
-	movdqa	%xmm4,%xmm7
-.byte	102,15,58,15,251,4
-	nop
-	paddd	%xmm7,%xmm5
-.byte	15,56,204,243
-.byte	15,56,203,202
-	movdqa	-48(%ebp),%xmm0
-	paddd	%xmm4,%xmm0
-.byte	15,56,205,236
-.byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
-	movdqa	%xmm5,%xmm7
-.byte	102,15,58,15,252,4
-	nop
-	paddd	%xmm7,%xmm6
-.byte	15,56,204,220
-.byte	15,56,203,202
-	movdqa	-32(%ebp),%xmm0
-	paddd	%xmm5,%xmm0
-.byte	15,56,205,245
-.byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
-	movdqa	%xmm6,%xmm7
-.byte	102,15,58,15,253,4
-	nop
-	paddd	%xmm7,%xmm3
-.byte	15,56,204,229
-.byte	15,56,203,202
-	movdqa	-16(%ebp),%xmm0
-	paddd	%xmm6,%xmm0
-.byte	15,56,205,222
-.byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
-	movdqa	%xmm3,%xmm7
-.byte	102,15,58,15,254,4
-	nop
-	paddd	%xmm7,%xmm4
-.byte	15,56,204,238
-.byte	15,56,203,202
-	movdqa	(%ebp),%xmm0
-	paddd	%xmm3,%xmm0
-.byte	15,56,205,227
-.byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
-	movdqa	%xmm4,%xmm7
-.byte	102,15,58,15,251,4
-	nop
-	paddd	%xmm7,%xmm5
-.byte	15,56,204,243
-.byte	15,56,203,202
-	movdqa	16(%ebp),%xmm0
-	paddd	%xmm4,%xmm0
-.byte	15,56,205,236
-.byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
-	movdqa	%xmm5,%xmm7
-.byte	102,15,58,15,252,4
-	nop
-	paddd	%xmm7,%xmm6
-.byte	15,56,204,220
-.byte	15,56,203,202
-	movdqa	32(%ebp),%xmm0
-	paddd	%xmm5,%xmm0
-.byte	15,56,205,245
-.byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
-	movdqa	%xmm6,%xmm7
-.byte	102,15,58,15,253,4
-	nop
-	paddd	%xmm7,%xmm3
-.byte	15,56,204,229
-.byte	15,56,203,202
-	movdqa	48(%ebp),%xmm0
-	paddd	%xmm6,%xmm0
-.byte	15,56,205,222
-.byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
-	movdqa	%xmm3,%xmm7
-.byte	102,15,58,15,254,4
-	nop
-	paddd	%xmm7,%xmm4
-.byte	15,56,204,238
-.byte	15,56,203,202
-	movdqa	64(%ebp),%xmm0
-	paddd	%xmm3,%xmm0
-.byte	15,56,205,227
-.byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
-	movdqa	%xmm4,%xmm7
-.byte	102,15,58,15,251,4
-	nop
-	paddd	%xmm7,%xmm5
-.byte	15,56,204,243
-.byte	15,56,203,202
-	movdqa	80(%ebp),%xmm0
-	paddd	%xmm4,%xmm0
-.byte	15,56,205,236
-.byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
-	movdqa	%xmm5,%xmm7
-.byte	102,15,58,15,252,4
-.byte	15,56,203,202
-	paddd	%xmm7,%xmm6
-	movdqa	96(%ebp),%xmm0
-	paddd	%xmm5,%xmm0
-.byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
-.byte	15,56,205,245
-	movdqa	128(%ebp),%xmm7
-.byte	15,56,203,202
-	movdqa	112(%ebp),%xmm0
-	paddd	%xmm6,%xmm0
-	nop
-.byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
-	cmpl	%edi,%eax
-	nop
-.byte	15,56,203,202
-	paddd	16(%esp),%xmm2
-	paddd	(%esp),%xmm1
-	jnz	.L010loop_shaext
-	pshufd	$177,%xmm2,%xmm2
-	pshufd	$27,%xmm1,%xmm7
-	pshufd	$177,%xmm1,%xmm1
-	punpckhqdq	%xmm2,%xmm1
-.byte	102,15,58,15,215,8
-	movl	44(%esp),%esp
-	movdqu	%xmm1,(%esi)
-	movdqu	%xmm2,16(%esi)
-	popl	%edi
-	popl	%esi
-	popl	%ebx
-	popl	%ebp
-	ret
-.align	32
 .L005SSSE3:
 	leal	-96(%esp),%esp
 	movl	(%esi),%eax
@@ -3384,9 +3185,9 @@ sha256_block_data_order:
 	movl	%ecx,24(%esp)
 	movl	%esi,28(%esp)
 	movdqa	256(%ebp),%xmm7
-	jmp	.L011grand_ssse3
+	jmp	.L010grand_ssse3
 .align	16
-.L011grand_ssse3:
+.L010grand_ssse3:
 	movdqu	(%edi),%xmm0
 	movdqu	16(%edi),%xmm1
 	movdqu	32(%edi),%xmm2
@@ -3409,9 +3210,9 @@ sha256_block_data_order:
 	paddd	%xmm3,%xmm7
 	movdqa	%xmm6,64(%esp)
 	movdqa	%xmm7,80(%esp)
-	jmp	.L012ssse3_00_47
+	jmp	.L011ssse3_00_47
 .align	16
-.L012ssse3_00_47:
+.L011ssse3_00_47:
 	addl	$64,%ebp
 	movl	%edx,%ecx
 	movdqa	%xmm1,%xmm4
@@ -4054,7 +3855,7 @@ sha256_block_data_order:
 	addl	%ecx,%eax
 	movdqa	%xmm6,80(%esp)
 	cmpl	$66051,64(%ebp)
-	jne	.L012ssse3_00_47
+	jne	.L011ssse3_00_47
 	movl	%edx,%ecx
 	rorl	$14,%edx
 	movl	20(%esp),%esi
@@ -4568,12 +4369,1193 @@ sha256_block_data_order:
 	movdqa	64(%ebp),%xmm7
 	subl	$192,%ebp
 	cmpl	104(%esp),%edi
-	jb	.L011grand_ssse3
+	jb	.L010grand_ssse3
 	movl	108(%esp),%esp
 	popl	%edi
 	popl	%esi
 	popl	%ebx
 	popl	%ebp
 	ret
+.align	32
+.L004AVX:
+	leal	-96(%esp),%esp
+	vzeroall
+	movl	(%esi),%eax
+	movl	4(%esi),%ebx
+	movl	8(%esi),%ecx
+	movl	12(%esi),%edi
+	movl	%ebx,4(%esp)
+	xorl	%ecx,%ebx
+	movl	%ecx,8(%esp)
+	movl	%edi,12(%esp)
+	movl	16(%esi),%edx
+	movl	20(%esi),%edi
+	movl	24(%esi),%ecx
+	movl	28(%esi),%esi
+	movl	%edi,20(%esp)
+	movl	100(%esp),%edi
+	movl	%ecx,24(%esp)
+	movl	%esi,28(%esp)
+	vmovdqa	256(%ebp),%xmm7
+	jmp	.L012grand_avx
+.align	32
+.L012grand_avx:
+	vmovdqu	(%edi),%xmm0
+	vmovdqu	16(%edi),%xmm1
+	vmovdqu	32(%edi),%xmm2
+	vmovdqu	48(%edi),%xmm3
+	addl	$64,%edi
+	vpshufb	%xmm7,%xmm0,%xmm0
+	movl	%edi,100(%esp)
+	vpshufb	%xmm7,%xmm1,%xmm1
+	vpshufb	%xmm7,%xmm2,%xmm2
+	vpaddd	(%ebp),%xmm0,%xmm4
+	vpshufb	%xmm7,%xmm3,%xmm3
+	vpaddd	16(%ebp),%xmm1,%xmm5
+	vpaddd	32(%ebp),%xmm2,%xmm6
+	vpaddd	48(%ebp),%xmm3,%xmm7
+	vmovdqa	%xmm4,32(%esp)
+	vmovdqa	%xmm5,48(%esp)
+	vmovdqa	%xmm6,64(%esp)
+	vmovdqa	%xmm7,80(%esp)
+	jmp	.L013avx_00_47
+.align	16
+.L013avx_00_47:
+	addl	$64,%ebp
+	vpalignr	$4,%xmm0,%xmm1,%xmm4
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	20(%esp),%esi
+	vpalignr	$4,%xmm2,%xmm3,%xmm7
+	xorl	%ecx,%edx
+	movl	24(%esp),%edi
+	xorl	%edi,%esi
+	vpsrld	$7,%xmm4,%xmm6
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,16(%esp)
+	vpaddd	%xmm7,%xmm0,%xmm0
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	vpsrld	$3,%xmm4,%xmm7
+	movl	%eax,%ecx
+	addl	%edi,%edx
+	movl	4(%esp),%edi
+	vpslld	$14,%xmm4,%xmm5
+	movl	%eax,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%eax,(%esp)
+	vpxor	%xmm6,%xmm7,%xmm4
+	xorl	%eax,%ecx
+	xorl	%edi,%eax
+	addl	28(%esp),%edx
+	vpshufd	$250,%xmm3,%xmm7
+	shrdl	$11,%ecx,%ecx
+	andl	%eax,%ebx
+	xorl	%esi,%ecx
+	vpsrld	$11,%xmm6,%xmm6
+	addl	32(%esp),%edx
+	xorl	%edi,%ebx
+	shrdl	$2,%ecx,%ecx
+	vpxor	%xmm5,%xmm4,%xmm4
+	addl	%edx,%ebx
+	addl	12(%esp),%edx
+	addl	%ecx,%ebx
+	vpslld	$11,%xmm5,%xmm5
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	16(%esp),%esi
+	vpxor	%xmm6,%xmm4,%xmm4
+	xorl	%ecx,%edx
+	movl	20(%esp),%edi
+	xorl	%edi,%esi
+	vpsrld	$10,%xmm7,%xmm6
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,12(%esp)
+	vpxor	%xmm5,%xmm4,%xmm4
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	vpsrlq	$17,%xmm7,%xmm5
+	movl	%ebx,%ecx
+	addl	%edi,%edx
+	movl	(%esp),%edi
+	vpaddd	%xmm4,%xmm0,%xmm0
+	movl	%ebx,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%ebx,28(%esp)
+	vpxor	%xmm5,%xmm6,%xmm6
+	xorl	%ebx,%ecx
+	xorl	%edi,%ebx
+	addl	24(%esp),%edx
+	vpsrlq	$19,%xmm7,%xmm7
+	shrdl	$11,%ecx,%ecx
+	andl	%ebx,%eax
+	xorl	%esi,%ecx
+	vpxor	%xmm7,%xmm6,%xmm6
+	addl	36(%esp),%edx
+	xorl	%edi,%eax
+	shrdl	$2,%ecx,%ecx
+	vpshufd	$132,%xmm6,%xmm7
+	addl	%edx,%eax
+	addl	8(%esp),%edx
+	addl	%ecx,%eax
+	vpsrldq	$8,%xmm7,%xmm7
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	12(%esp),%esi
+	vpaddd	%xmm7,%xmm0,%xmm0
+	xorl	%ecx,%edx
+	movl	16(%esp),%edi
+	xorl	%edi,%esi
+	vpshufd	$80,%xmm0,%xmm7
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,8(%esp)
+	vpsrld	$10,%xmm7,%xmm6
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	vpsrlq	$17,%xmm7,%xmm5
+	movl	%eax,%ecx
+	addl	%edi,%edx
+	movl	28(%esp),%edi
+	vpxor	%xmm5,%xmm6,%xmm6
+	movl	%eax,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%eax,24(%esp)
+	vpsrlq	$19,%xmm7,%xmm7
+	xorl	%eax,%ecx
+	xorl	%edi,%eax
+	addl	20(%esp),%edx
+	vpxor	%xmm7,%xmm6,%xmm6
+	shrdl	$11,%ecx,%ecx
+	andl	%eax,%ebx
+	xorl	%esi,%ecx
+	vpshufd	$232,%xmm6,%xmm7
+	addl	40(%esp),%edx
+	xorl	%edi,%ebx
+	shrdl	$2,%ecx,%ecx
+	vpslldq	$8,%xmm7,%xmm7
+	addl	%edx,%ebx
+	addl	4(%esp),%edx
+	addl	%ecx,%ebx
+	vpaddd	%xmm7,%xmm0,%xmm0
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	8(%esp),%esi
+	vpaddd	(%ebp),%xmm0,%xmm6
+	xorl	%ecx,%edx
+	movl	12(%esp),%edi
+	xorl	%edi,%esi
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,4(%esp)
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	movl	%ebx,%ecx
+	addl	%edi,%edx
+	movl	24(%esp),%edi
+	movl	%ebx,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%ebx,20(%esp)
+	xorl	%ebx,%ecx
+	xorl	%edi,%ebx
+	addl	16(%esp),%edx
+	shrdl	$11,%ecx,%ecx
+	andl	%ebx,%eax
+	xorl	%esi,%ecx
+	addl	44(%esp),%edx
+	xorl	%edi,%eax
+	shrdl	$2,%ecx,%ecx
+	addl	%edx,%eax
+	addl	(%esp),%edx
+	addl	%ecx,%eax
+	vmovdqa	%xmm6,32(%esp)
+	vpalignr	$4,%xmm1,%xmm2,%xmm4
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	4(%esp),%esi
+	vpalignr	$4,%xmm3,%xmm0,%xmm7
+	xorl	%ecx,%edx
+	movl	8(%esp),%edi
+	xorl	%edi,%esi
+	vpsrld	$7,%xmm4,%xmm6
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,(%esp)
+	vpaddd	%xmm7,%xmm1,%xmm1
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	vpsrld	$3,%xmm4,%xmm7
+	movl	%eax,%ecx
+	addl	%edi,%edx
+	movl	20(%esp),%edi
+	vpslld	$14,%xmm4,%xmm5
+	movl	%eax,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%eax,16(%esp)
+	vpxor	%xmm6,%xmm7,%xmm4
+	xorl	%eax,%ecx
+	xorl	%edi,%eax
+	addl	12(%esp),%edx
+	vpshufd	$250,%xmm0,%xmm7
+	shrdl	$11,%ecx,%ecx
+	andl	%eax,%ebx
+	xorl	%esi,%ecx
+	vpsrld	$11,%xmm6,%xmm6
+	addl	48(%esp),%edx
+	xorl	%edi,%ebx
+	shrdl	$2,%ecx,%ecx
+	vpxor	%xmm5,%xmm4,%xmm4
+	addl	%edx,%ebx
+	addl	28(%esp),%edx
+	addl	%ecx,%ebx
+	vpslld	$11,%xmm5,%xmm5
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	(%esp),%esi
+	vpxor	%xmm6,%xmm4,%xmm4
+	xorl	%ecx,%edx
+	movl	4(%esp),%edi
+	xorl	%edi,%esi
+	vpsrld	$10,%xmm7,%xmm6
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,28(%esp)
+	vpxor	%xmm5,%xmm4,%xmm4
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	vpsrlq	$17,%xmm7,%xmm5
+	movl	%ebx,%ecx
+	addl	%edi,%edx
+	movl	16(%esp),%edi
+	vpaddd	%xmm4,%xmm1,%xmm1
+	movl	%ebx,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%ebx,12(%esp)
+	vpxor	%xmm5,%xmm6,%xmm6
+	xorl	%ebx,%ecx
+	xorl	%edi,%ebx
+	addl	8(%esp),%edx
+	vpsrlq	$19,%xmm7,%xmm7
+	shrdl	$11,%ecx,%ecx
+	andl	%ebx,%eax
+	xorl	%esi,%ecx
+	vpxor	%xmm7,%xmm6,%xmm6
+	addl	52(%esp),%edx
+	xorl	%edi,%eax
+	shrdl	$2,%ecx,%ecx
+	vpshufd	$132,%xmm6,%xmm7
+	addl	%edx,%eax
+	addl	24(%esp),%edx
+	addl	%ecx,%eax
+	vpsrldq	$8,%xmm7,%xmm7
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	28(%esp),%esi
+	vpaddd	%xmm7,%xmm1,%xmm1
+	xorl	%ecx,%edx
+	movl	(%esp),%edi
+	xorl	%edi,%esi
+	vpshufd	$80,%xmm1,%xmm7
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,24(%esp)
+	vpsrld	$10,%xmm7,%xmm6
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	vpsrlq	$17,%xmm7,%xmm5
+	movl	%eax,%ecx
+	addl	%edi,%edx
+	movl	12(%esp),%edi
+	vpxor	%xmm5,%xmm6,%xmm6
+	movl	%eax,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%eax,8(%esp)
+	vpsrlq	$19,%xmm7,%xmm7
+	xorl	%eax,%ecx
+	xorl	%edi,%eax
+	addl	4(%esp),%edx
+	vpxor	%xmm7,%xmm6,%xmm6
+	shrdl	$11,%ecx,%ecx
+	andl	%eax,%ebx
+	xorl	%esi,%ecx
+	vpshufd	$232,%xmm6,%xmm7
+	addl	56(%esp),%edx
+	xorl	%edi,%ebx
+	shrdl	$2,%ecx,%ecx
+	vpslldq	$8,%xmm7,%xmm7
+	addl	%edx,%ebx
+	addl	20(%esp),%edx
+	addl	%ecx,%ebx
+	vpaddd	%xmm7,%xmm1,%xmm1
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	24(%esp),%esi
+	vpaddd	16(%ebp),%xmm1,%xmm6
+	xorl	%ecx,%edx
+	movl	28(%esp),%edi
+	xorl	%edi,%esi
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,20(%esp)
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	movl	%ebx,%ecx
+	addl	%edi,%edx
+	movl	8(%esp),%edi
+	movl	%ebx,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%ebx,4(%esp)
+	xorl	%ebx,%ecx
+	xorl	%edi,%ebx
+	addl	(%esp),%edx
+	shrdl	$11,%ecx,%ecx
+	andl	%ebx,%eax
+	xorl	%esi,%ecx
+	addl	60(%esp),%edx
+	xorl	%edi,%eax
+	shrdl	$2,%ecx,%ecx
+	addl	%edx,%eax
+	addl	16(%esp),%edx
+	addl	%ecx,%eax
+	vmovdqa	%xmm6,48(%esp)
+	vpalignr	$4,%xmm2,%xmm3,%xmm4
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	20(%esp),%esi
+	vpalignr	$4,%xmm0,%xmm1,%xmm7
+	xorl	%ecx,%edx
+	movl	24(%esp),%edi
+	xorl	%edi,%esi
+	vpsrld	$7,%xmm4,%xmm6
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,16(%esp)
+	vpaddd	%xmm7,%xmm2,%xmm2
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	vpsrld	$3,%xmm4,%xmm7
+	movl	%eax,%ecx
+	addl	%edi,%edx
+	movl	4(%esp),%edi
+	vpslld	$14,%xmm4,%xmm5
+	movl	%eax,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%eax,(%esp)
+	vpxor	%xmm6,%xmm7,%xmm4
+	xorl	%eax,%ecx
+	xorl	%edi,%eax
+	addl	28(%esp),%edx
+	vpshufd	$250,%xmm1,%xmm7
+	shrdl	$11,%ecx,%ecx
+	andl	%eax,%ebx
+	xorl	%esi,%ecx
+	vpsrld	$11,%xmm6,%xmm6
+	addl	64(%esp),%edx
+	xorl	%edi,%ebx
+	shrdl	$2,%ecx,%ecx
+	vpxor	%xmm5,%xmm4,%xmm4
+	addl	%edx,%ebx
+	addl	12(%esp),%edx
+	addl	%ecx,%ebx
+	vpslld	$11,%xmm5,%xmm5
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	16(%esp),%esi
+	vpxor	%xmm6,%xmm4,%xmm4
+	xorl	%ecx,%edx
+	movl	20(%esp),%edi
+	xorl	%edi,%esi
+	vpsrld	$10,%xmm7,%xmm6
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,12(%esp)
+	vpxor	%xmm5,%xmm4,%xmm4
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	vpsrlq	$17,%xmm7,%xmm5
+	movl	%ebx,%ecx
+	addl	%edi,%edx
+	movl	(%esp),%edi
+	vpaddd	%xmm4,%xmm2,%xmm2
+	movl	%ebx,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%ebx,28(%esp)
+	vpxor	%xmm5,%xmm6,%xmm6
+	xorl	%ebx,%ecx
+	xorl	%edi,%ebx
+	addl	24(%esp),%edx
+	vpsrlq	$19,%xmm7,%xmm7
+	shrdl	$11,%ecx,%ecx
+	andl	%ebx,%eax
+	xorl	%esi,%ecx
+	vpxor	%xmm7,%xmm6,%xmm6
+	addl	68(%esp),%edx
+	xorl	%edi,%eax
+	shrdl	$2,%ecx,%ecx
+	vpshufd	$132,%xmm6,%xmm7
+	addl	%edx,%eax
+	addl	8(%esp),%edx
+	addl	%ecx,%eax
+	vpsrldq	$8,%xmm7,%xmm7
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	12(%esp),%esi
+	vpaddd	%xmm7,%xmm2,%xmm2
+	xorl	%ecx,%edx
+	movl	16(%esp),%edi
+	xorl	%edi,%esi
+	vpshufd	$80,%xmm2,%xmm7
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,8(%esp)
+	vpsrld	$10,%xmm7,%xmm6
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	vpsrlq	$17,%xmm7,%xmm5
+	movl	%eax,%ecx
+	addl	%edi,%edx
+	movl	28(%esp),%edi
+	vpxor	%xmm5,%xmm6,%xmm6
+	movl	%eax,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%eax,24(%esp)
+	vpsrlq	$19,%xmm7,%xmm7
+	xorl	%eax,%ecx
+	xorl	%edi,%eax
+	addl	20(%esp),%edx
+	vpxor	%xmm7,%xmm6,%xmm6
+	shrdl	$11,%ecx,%ecx
+	andl	%eax,%ebx
+	xorl	%esi,%ecx
+	vpshufd	$232,%xmm6,%xmm7
+	addl	72(%esp),%edx
+	xorl	%edi,%ebx
+	shrdl	$2,%ecx,%ecx
+	vpslldq	$8,%xmm7,%xmm7
+	addl	%edx,%ebx
+	addl	4(%esp),%edx
+	addl	%ecx,%ebx
+	vpaddd	%xmm7,%xmm2,%xmm2
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	8(%esp),%esi
+	vpaddd	32(%ebp),%xmm2,%xmm6
+	xorl	%ecx,%edx
+	movl	12(%esp),%edi
+	xorl	%edi,%esi
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,4(%esp)
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	movl	%ebx,%ecx
+	addl	%edi,%edx
+	movl	24(%esp),%edi
+	movl	%ebx,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%ebx,20(%esp)
+	xorl	%ebx,%ecx
+	xorl	%edi,%ebx
+	addl	16(%esp),%edx
+	shrdl	$11,%ecx,%ecx
+	andl	%ebx,%eax
+	xorl	%esi,%ecx
+	addl	76(%esp),%edx
+	xorl	%edi,%eax
+	shrdl	$2,%ecx,%ecx
+	addl	%edx,%eax
+	addl	(%esp),%edx
+	addl	%ecx,%eax
+	vmovdqa	%xmm6,64(%esp)
+	vpalignr	$4,%xmm3,%xmm0,%xmm4
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	4(%esp),%esi
+	vpalignr	$4,%xmm1,%xmm2,%xmm7
+	xorl	%ecx,%edx
+	movl	8(%esp),%edi
+	xorl	%edi,%esi
+	vpsrld	$7,%xmm4,%xmm6
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,(%esp)
+	vpaddd	%xmm7,%xmm3,%xmm3
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	vpsrld	$3,%xmm4,%xmm7
+	movl	%eax,%ecx
+	addl	%edi,%edx
+	movl	20(%esp),%edi
+	vpslld	$14,%xmm4,%xmm5
+	movl	%eax,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%eax,16(%esp)
+	vpxor	%xmm6,%xmm7,%xmm4
+	xorl	%eax,%ecx
+	xorl	%edi,%eax
+	addl	12(%esp),%edx
+	vpshufd	$250,%xmm2,%xmm7
+	shrdl	$11,%ecx,%ecx
+	andl	%eax,%ebx
+	xorl	%esi,%ecx
+	vpsrld	$11,%xmm6,%xmm6
+	addl	80(%esp),%edx
+	xorl	%edi,%ebx
+	shrdl	$2,%ecx,%ecx
+	vpxor	%xmm5,%xmm4,%xmm4
+	addl	%edx,%ebx
+	addl	28(%esp),%edx
+	addl	%ecx,%ebx
+	vpslld	$11,%xmm5,%xmm5
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	(%esp),%esi
+	vpxor	%xmm6,%xmm4,%xmm4
+	xorl	%ecx,%edx
+	movl	4(%esp),%edi
+	xorl	%edi,%esi
+	vpsrld	$10,%xmm7,%xmm6
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,28(%esp)
+	vpxor	%xmm5,%xmm4,%xmm4
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	vpsrlq	$17,%xmm7,%xmm5
+	movl	%ebx,%ecx
+	addl	%edi,%edx
+	movl	16(%esp),%edi
+	vpaddd	%xmm4,%xmm3,%xmm3
+	movl	%ebx,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%ebx,12(%esp)
+	vpxor	%xmm5,%xmm6,%xmm6
+	xorl	%ebx,%ecx
+	xorl	%edi,%ebx
+	addl	8(%esp),%edx
+	vpsrlq	$19,%xmm7,%xmm7
+	shrdl	$11,%ecx,%ecx
+	andl	%ebx,%eax
+	xorl	%esi,%ecx
+	vpxor	%xmm7,%xmm6,%xmm6
+	addl	84(%esp),%edx
+	xorl	%edi,%eax
+	shrdl	$2,%ecx,%ecx
+	vpshufd	$132,%xmm6,%xmm7
+	addl	%edx,%eax
+	addl	24(%esp),%edx
+	addl	%ecx,%eax
+	vpsrldq	$8,%xmm7,%xmm7
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	28(%esp),%esi
+	vpaddd	%xmm7,%xmm3,%xmm3
+	xorl	%ecx,%edx
+	movl	(%esp),%edi
+	xorl	%edi,%esi
+	vpshufd	$80,%xmm3,%xmm7
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,24(%esp)
+	vpsrld	$10,%xmm7,%xmm6
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	vpsrlq	$17,%xmm7,%xmm5
+	movl	%eax,%ecx
+	addl	%edi,%edx
+	movl	12(%esp),%edi
+	vpxor	%xmm5,%xmm6,%xmm6
+	movl	%eax,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%eax,8(%esp)
+	vpsrlq	$19,%xmm7,%xmm7
+	xorl	%eax,%ecx
+	xorl	%edi,%eax
+	addl	4(%esp),%edx
+	vpxor	%xmm7,%xmm6,%xmm6
+	shrdl	$11,%ecx,%ecx
+	andl	%eax,%ebx
+	xorl	%esi,%ecx
+	vpshufd	$232,%xmm6,%xmm7
+	addl	88(%esp),%edx
+	xorl	%edi,%ebx
+	shrdl	$2,%ecx,%ecx
+	vpslldq	$8,%xmm7,%xmm7
+	addl	%edx,%ebx
+	addl	20(%esp),%edx
+	addl	%ecx,%ebx
+	vpaddd	%xmm7,%xmm3,%xmm3
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	24(%esp),%esi
+	vpaddd	48(%ebp),%xmm3,%xmm6
+	xorl	%ecx,%edx
+	movl	28(%esp),%edi
+	xorl	%edi,%esi
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,20(%esp)
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	movl	%ebx,%ecx
+	addl	%edi,%edx
+	movl	8(%esp),%edi
+	movl	%ebx,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%ebx,4(%esp)
+	xorl	%ebx,%ecx
+	xorl	%edi,%ebx
+	addl	(%esp),%edx
+	shrdl	$11,%ecx,%ecx
+	andl	%ebx,%eax
+	xorl	%esi,%ecx
+	addl	92(%esp),%edx
+	xorl	%edi,%eax
+	shrdl	$2,%ecx,%ecx
+	addl	%edx,%eax
+	addl	16(%esp),%edx
+	addl	%ecx,%eax
+	vmovdqa	%xmm6,80(%esp)
+	cmpl	$66051,64(%ebp)
+	jne	.L013avx_00_47
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	20(%esp),%esi
+	xorl	%ecx,%edx
+	movl	24(%esp),%edi
+	xorl	%edi,%esi
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,16(%esp)
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	movl	%eax,%ecx
+	addl	%edi,%edx
+	movl	4(%esp),%edi
+	movl	%eax,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%eax,(%esp)
+	xorl	%eax,%ecx
+	xorl	%edi,%eax
+	addl	28(%esp),%edx
+	shrdl	$11,%ecx,%ecx
+	andl	%eax,%ebx
+	xorl	%esi,%ecx
+	addl	32(%esp),%edx
+	xorl	%edi,%ebx
+	shrdl	$2,%ecx,%ecx
+	addl	%edx,%ebx
+	addl	12(%esp),%edx
+	addl	%ecx,%ebx
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	16(%esp),%esi
+	xorl	%ecx,%edx
+	movl	20(%esp),%edi
+	xorl	%edi,%esi
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,12(%esp)
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	movl	%ebx,%ecx
+	addl	%edi,%edx
+	movl	(%esp),%edi
+	movl	%ebx,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%ebx,28(%esp)
+	xorl	%ebx,%ecx
+	xorl	%edi,%ebx
+	addl	24(%esp),%edx
+	shrdl	$11,%ecx,%ecx
+	andl	%ebx,%eax
+	xorl	%esi,%ecx
+	addl	36(%esp),%edx
+	xorl	%edi,%eax
+	shrdl	$2,%ecx,%ecx
+	addl	%edx,%eax
+	addl	8(%esp),%edx
+	addl	%ecx,%eax
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	12(%esp),%esi
+	xorl	%ecx,%edx
+	movl	16(%esp),%edi
+	xorl	%edi,%esi
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,8(%esp)
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	movl	%eax,%ecx
+	addl	%edi,%edx
+	movl	28(%esp),%edi
+	movl	%eax,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%eax,24(%esp)
+	xorl	%eax,%ecx
+	xorl	%edi,%eax
+	addl	20(%esp),%edx
+	shrdl	$11,%ecx,%ecx
+	andl	%eax,%ebx
+	xorl	%esi,%ecx
+	addl	40(%esp),%edx
+	xorl	%edi,%ebx
+	shrdl	$2,%ecx,%ecx
+	addl	%edx,%ebx
+	addl	4(%esp),%edx
+	addl	%ecx,%ebx
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	8(%esp),%esi
+	xorl	%ecx,%edx
+	movl	12(%esp),%edi
+	xorl	%edi,%esi
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,4(%esp)
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	movl	%ebx,%ecx
+	addl	%edi,%edx
+	movl	24(%esp),%edi
+	movl	%ebx,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%ebx,20(%esp)
+	xorl	%ebx,%ecx
+	xorl	%edi,%ebx
+	addl	16(%esp),%edx
+	shrdl	$11,%ecx,%ecx
+	andl	%ebx,%eax
+	xorl	%esi,%ecx
+	addl	44(%esp),%edx
+	xorl	%edi,%eax
+	shrdl	$2,%ecx,%ecx
+	addl	%edx,%eax
+	addl	(%esp),%edx
+	addl	%ecx,%eax
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	4(%esp),%esi
+	xorl	%ecx,%edx
+	movl	8(%esp),%edi
+	xorl	%edi,%esi
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,(%esp)
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	movl	%eax,%ecx
+	addl	%edi,%edx
+	movl	20(%esp),%edi
+	movl	%eax,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%eax,16(%esp)
+	xorl	%eax,%ecx
+	xorl	%edi,%eax
+	addl	12(%esp),%edx
+	shrdl	$11,%ecx,%ecx
+	andl	%eax,%ebx
+	xorl	%esi,%ecx
+	addl	48(%esp),%edx
+	xorl	%edi,%ebx
+	shrdl	$2,%ecx,%ecx
+	addl	%edx,%ebx
+	addl	28(%esp),%edx
+	addl	%ecx,%ebx
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	(%esp),%esi
+	xorl	%ecx,%edx
+	movl	4(%esp),%edi
+	xorl	%edi,%esi
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,28(%esp)
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	movl	%ebx,%ecx
+	addl	%edi,%edx
+	movl	16(%esp),%edi
+	movl	%ebx,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%ebx,12(%esp)
+	xorl	%ebx,%ecx
+	xorl	%edi,%ebx
+	addl	8(%esp),%edx
+	shrdl	$11,%ecx,%ecx
+	andl	%ebx,%eax
+	xorl	%esi,%ecx
+	addl	52(%esp),%edx
+	xorl	%edi,%eax
+	shrdl	$2,%ecx,%ecx
+	addl	%edx,%eax
+	addl	24(%esp),%edx
+	addl	%ecx,%eax
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	28(%esp),%esi
+	xorl	%ecx,%edx
+	movl	(%esp),%edi
+	xorl	%edi,%esi
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,24(%esp)
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	movl	%eax,%ecx
+	addl	%edi,%edx
+	movl	12(%esp),%edi
+	movl	%eax,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%eax,8(%esp)
+	xorl	%eax,%ecx
+	xorl	%edi,%eax
+	addl	4(%esp),%edx
+	shrdl	$11,%ecx,%ecx
+	andl	%eax,%ebx
+	xorl	%esi,%ecx
+	addl	56(%esp),%edx
+	xorl	%edi,%ebx
+	shrdl	$2,%ecx,%ecx
+	addl	%edx,%ebx
+	addl	20(%esp),%edx
+	addl	%ecx,%ebx
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	24(%esp),%esi
+	xorl	%ecx,%edx
+	movl	28(%esp),%edi
+	xorl	%edi,%esi
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,20(%esp)
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	movl	%ebx,%ecx
+	addl	%edi,%edx
+	movl	8(%esp),%edi
+	movl	%ebx,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%ebx,4(%esp)
+	xorl	%ebx,%ecx
+	xorl	%edi,%ebx
+	addl	(%esp),%edx
+	shrdl	$11,%ecx,%ecx
+	andl	%ebx,%eax
+	xorl	%esi,%ecx
+	addl	60(%esp),%edx
+	xorl	%edi,%eax
+	shrdl	$2,%ecx,%ecx
+	addl	%edx,%eax
+	addl	16(%esp),%edx
+	addl	%ecx,%eax
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	20(%esp),%esi
+	xorl	%ecx,%edx
+	movl	24(%esp),%edi
+	xorl	%edi,%esi
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,16(%esp)
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	movl	%eax,%ecx
+	addl	%edi,%edx
+	movl	4(%esp),%edi
+	movl	%eax,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%eax,(%esp)
+	xorl	%eax,%ecx
+	xorl	%edi,%eax
+	addl	28(%esp),%edx
+	shrdl	$11,%ecx,%ecx
+	andl	%eax,%ebx
+	xorl	%esi,%ecx
+	addl	64(%esp),%edx
+	xorl	%edi,%ebx
+	shrdl	$2,%ecx,%ecx
+	addl	%edx,%ebx
+	addl	12(%esp),%edx
+	addl	%ecx,%ebx
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	16(%esp),%esi
+	xorl	%ecx,%edx
+	movl	20(%esp),%edi
+	xorl	%edi,%esi
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,12(%esp)
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	movl	%ebx,%ecx
+	addl	%edi,%edx
+	movl	(%esp),%edi
+	movl	%ebx,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%ebx,28(%esp)
+	xorl	%ebx,%ecx
+	xorl	%edi,%ebx
+	addl	24(%esp),%edx
+	shrdl	$11,%ecx,%ecx
+	andl	%ebx,%eax
+	xorl	%esi,%ecx
+	addl	68(%esp),%edx
+	xorl	%edi,%eax
+	shrdl	$2,%ecx,%ecx
+	addl	%edx,%eax
+	addl	8(%esp),%edx
+	addl	%ecx,%eax
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	12(%esp),%esi
+	xorl	%ecx,%edx
+	movl	16(%esp),%edi
+	xorl	%edi,%esi
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,8(%esp)
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	movl	%eax,%ecx
+	addl	%edi,%edx
+	movl	28(%esp),%edi
+	movl	%eax,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%eax,24(%esp)
+	xorl	%eax,%ecx
+	xorl	%edi,%eax
+	addl	20(%esp),%edx
+	shrdl	$11,%ecx,%ecx
+	andl	%eax,%ebx
+	xorl	%esi,%ecx
+	addl	72(%esp),%edx
+	xorl	%edi,%ebx
+	shrdl	$2,%ecx,%ecx
+	addl	%edx,%ebx
+	addl	4(%esp),%edx
+	addl	%ecx,%ebx
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	8(%esp),%esi
+	xorl	%ecx,%edx
+	movl	12(%esp),%edi
+	xorl	%edi,%esi
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,4(%esp)
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	movl	%ebx,%ecx
+	addl	%edi,%edx
+	movl	24(%esp),%edi
+	movl	%ebx,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%ebx,20(%esp)
+	xorl	%ebx,%ecx
+	xorl	%edi,%ebx
+	addl	16(%esp),%edx
+	shrdl	$11,%ecx,%ecx
+	andl	%ebx,%eax
+	xorl	%esi,%ecx
+	addl	76(%esp),%edx
+	xorl	%edi,%eax
+	shrdl	$2,%ecx,%ecx
+	addl	%edx,%eax
+	addl	(%esp),%edx
+	addl	%ecx,%eax
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	4(%esp),%esi
+	xorl	%ecx,%edx
+	movl	8(%esp),%edi
+	xorl	%edi,%esi
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,(%esp)
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	movl	%eax,%ecx
+	addl	%edi,%edx
+	movl	20(%esp),%edi
+	movl	%eax,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%eax,16(%esp)
+	xorl	%eax,%ecx
+	xorl	%edi,%eax
+	addl	12(%esp),%edx
+	shrdl	$11,%ecx,%ecx
+	andl	%eax,%ebx
+	xorl	%esi,%ecx
+	addl	80(%esp),%edx
+	xorl	%edi,%ebx
+	shrdl	$2,%ecx,%ecx
+	addl	%edx,%ebx
+	addl	28(%esp),%edx
+	addl	%ecx,%ebx
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	(%esp),%esi
+	xorl	%ecx,%edx
+	movl	4(%esp),%edi
+	xorl	%edi,%esi
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,28(%esp)
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	movl	%ebx,%ecx
+	addl	%edi,%edx
+	movl	16(%esp),%edi
+	movl	%ebx,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%ebx,12(%esp)
+	xorl	%ebx,%ecx
+	xorl	%edi,%ebx
+	addl	8(%esp),%edx
+	shrdl	$11,%ecx,%ecx
+	andl	%ebx,%eax
+	xorl	%esi,%ecx
+	addl	84(%esp),%edx
+	xorl	%edi,%eax
+	shrdl	$2,%ecx,%ecx
+	addl	%edx,%eax
+	addl	24(%esp),%edx
+	addl	%ecx,%eax
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	28(%esp),%esi
+	xorl	%ecx,%edx
+	movl	(%esp),%edi
+	xorl	%edi,%esi
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,24(%esp)
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	movl	%eax,%ecx
+	addl	%edi,%edx
+	movl	12(%esp),%edi
+	movl	%eax,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%eax,8(%esp)
+	xorl	%eax,%ecx
+	xorl	%edi,%eax
+	addl	4(%esp),%edx
+	shrdl	$11,%ecx,%ecx
+	andl	%eax,%ebx
+	xorl	%esi,%ecx
+	addl	88(%esp),%edx
+	xorl	%edi,%ebx
+	shrdl	$2,%ecx,%ecx
+	addl	%edx,%ebx
+	addl	20(%esp),%edx
+	addl	%ecx,%ebx
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	24(%esp),%esi
+	xorl	%ecx,%edx
+	movl	28(%esp),%edi
+	xorl	%edi,%esi
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,20(%esp)
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	movl	%ebx,%ecx
+	addl	%edi,%edx
+	movl	8(%esp),%edi
+	movl	%ebx,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%ebx,4(%esp)
+	xorl	%ebx,%ecx
+	xorl	%edi,%ebx
+	addl	(%esp),%edx
+	shrdl	$11,%ecx,%ecx
+	andl	%ebx,%eax
+	xorl	%esi,%ecx
+	addl	92(%esp),%edx
+	xorl	%edi,%eax
+	shrdl	$2,%ecx,%ecx
+	addl	%edx,%eax
+	addl	16(%esp),%edx
+	addl	%ecx,%eax
+	movl	96(%esp),%esi
+	xorl	%edi,%ebx
+	movl	12(%esp),%ecx
+	addl	(%esi),%eax
+	addl	4(%esi),%ebx
+	addl	8(%esi),%edi
+	addl	12(%esi),%ecx
+	movl	%eax,(%esi)
+	movl	%ebx,4(%esi)
+	movl	%edi,8(%esi)
+	movl	%ecx,12(%esi)
+	movl	%ebx,4(%esp)
+	xorl	%edi,%ebx
+	movl	%edi,8(%esp)
+	movl	%ecx,12(%esp)
+	movl	20(%esp),%edi
+	movl	24(%esp),%ecx
+	addl	16(%esi),%edx
+	addl	20(%esi),%edi
+	addl	24(%esi),%ecx
+	movl	%edx,16(%esi)
+	movl	%edi,20(%esi)
+	movl	%edi,20(%esp)
+	movl	28(%esp),%edi
+	movl	%ecx,24(%esi)
+	addl	28(%esi),%edi
+	movl	%ecx,24(%esp)
+	movl	%edi,28(%esi)
+	movl	%edi,28(%esp)
+	movl	100(%esp),%edi
+	vmovdqa	64(%ebp),%xmm7
+	subl	$192,%ebp
+	cmpl	104(%esp),%edi
+	jb	.L012grand_avx
+	movl	108(%esp),%esp
+	vzeroall
+	popl	%edi
+	popl	%esi
+	popl	%ebx
+	popl	%ebp
+	ret
 .size	sha256_block_data_order,.-.L_sha256_block_data_order_begin
 #endif
diff --git a/packager/third_party/boringssl/linux-x86_64/crypto/aes/aes-x86_64.S b/packager/third_party/boringssl/linux-x86_64/crypto/aes/aes-x86_64.S
index 5f4b057ffa..361e84c77f 100644
--- a/packager/third_party/boringssl/linux-x86_64/crypto/aes/aes-x86_64.S
+++ b/packager/third_party/boringssl/linux-x86_64/crypto/aes/aes-x86_64.S
@@ -82,8 +82,8 @@ _x86_64_AES_encrypt:
 	movl	0(%r14,%rdi,8),%edi
 	movl	0(%r14,%rbp,8),%ebp
 
-	andl	$65280,%edi
-	andl	$65280,%ebp
+	andl	$0x0000ff00,%edi
+	andl	$0x0000ff00,%ebp
 
 	xorl	%edi,%r10d
 	xorl	%ebp,%r11d
@@ -95,8 +95,8 @@ _x86_64_AES_encrypt:
 	movl	0(%r14,%rsi,8),%esi
 	movl	0(%r14,%rdi,8),%edi
 
-	andl	$65280,%esi
-	andl	$65280,%edi
+	andl	$0x0000ff00,%esi
+	andl	$0x0000ff00,%edi
 	shrl	$16,%ebx
 	xorl	%esi,%r12d
 	xorl	%edi,%r8d
@@ -109,9 +109,9 @@ _x86_64_AES_encrypt:
 	movl	0(%r14,%rdi,8),%edi
 	movl	0(%r14,%rbp,8),%ebp
 
-	andl	$16711680,%esi
-	andl	$16711680,%edi
-	andl	$16711680,%ebp
+	andl	$0x00ff0000,%esi
+	andl	$0x00ff0000,%edi
+	andl	$0x00ff0000,%ebp
 
 	xorl	%esi,%r10d
 	xorl	%edi,%r11d
@@ -124,9 +124,9 @@ _x86_64_AES_encrypt:
 	movl	2(%r14,%rdi,8),%edi
 	movl	2(%r14,%rbp,8),%ebp
 
-	andl	$16711680,%esi
-	andl	$4278190080,%edi
-	andl	$4278190080,%ebp
+	andl	$0x00ff0000,%esi
+	andl	$0xff000000,%edi
+	andl	$0xff000000,%ebp
 
 	xorl	%esi,%r8d
 	xorl	%edi,%r10d
@@ -139,8 +139,8 @@ _x86_64_AES_encrypt:
 	movl	2(%r14,%rdi,8),%edi
 	movl	16+0(%r15),%eax
 
-	andl	$4278190080,%esi
-	andl	$4278190080,%edi
+	andl	$0xff000000,%esi
+	andl	$0xff000000,%edi
 
 	xorl	%esi,%r12d
 	xorl	%edi,%r8d
@@ -242,8 +242,8 @@ _x86_64_AES_encrypt_compact:
 	xorl	%r8d,%edx
 	cmpq	16(%rsp),%r15
 	je	.Lenc_compact_done
-	movl	$2155905152,%r10d
-	movl	$2155905152,%r11d
+	movl	$0x80808080,%r10d
+	movl	$0x80808080,%r11d
 	andl	%eax,%r10d
 	andl	%ebx,%r11d
 	movl	%r10d,%esi
@@ -254,10 +254,10 @@ _x86_64_AES_encrypt_compact:
 	leal	(%rbx,%rbx,1),%r9d
 	subl	%r10d,%esi
 	subl	%r11d,%edi
-	andl	$4278124286,%r8d
-	andl	$4278124286,%r9d
-	andl	$454761243,%esi
-	andl	$454761243,%edi
+	andl	$0xfefefefe,%r8d
+	andl	$0xfefefefe,%r9d
+	andl	$0x1b1b1b1b,%esi
+	andl	$0x1b1b1b1b,%edi
 	movl	%eax,%r10d
 	movl	%ebx,%r11d
 	xorl	%esi,%r8d
@@ -265,9 +265,9 @@ _x86_64_AES_encrypt_compact:
 
 	xorl	%r8d,%eax
 	xorl	%r9d,%ebx
-	movl	$2155905152,%r12d
+	movl	$0x80808080,%r12d
 	roll	$24,%eax
-	movl	$2155905152,%ebp
+	movl	$0x80808080,%ebp
 	roll	$24,%ebx
 	andl	%ecx,%r12d
 	andl	%edx,%ebp
@@ -290,10 +290,10 @@ _x86_64_AES_encrypt_compact:
 	xorl	%r10d,%eax
 	xorl	%r11d,%ebx
 
-	andl	$4278124286,%r8d
-	andl	$4278124286,%r9d
-	andl	$454761243,%esi
-	andl	$454761243,%edi
+	andl	$0xfefefefe,%r8d
+	andl	$0xfefefefe,%r9d
+	andl	$0x1b1b1b1b,%esi
+	andl	$0x1b1b1b1b,%edi
 	movl	%ecx,%r12d
 	movl	%edx,%ebp
 	xorl	%esi,%r8d
@@ -345,7 +345,7 @@ asm_AES_encrypt:
 	andq	$-64,%rsp
 	subq	%rsp,%rcx
 	negq	%rcx
-	andq	$960,%rcx
+	andq	$0x3c0,%rcx
 	subq	%rcx,%rsp
 	subq	$32,%rsp
 
@@ -370,7 +370,7 @@ asm_AES_encrypt:
 	leaq	.LAES_Te+2048(%rip),%r14
 	leaq	768(%rsp),%rbp
 	subq	%r14,%rbp
-	andq	$768,%rbp
+	andq	$0x300,%rbp
 	leaq	(%r14,%rbp,1),%r14
 
 	call	_x86_64_AES_encrypt_compact
@@ -791,7 +791,7 @@ asm_AES_decrypt:
 	andq	$-64,%rsp
 	subq	%rsp,%rcx
 	negq	%rcx
-	andq	$960,%rcx
+	andq	$0x3c0,%rcx
 	subq	%rcx,%rsp
 	subq	$32,%rsp
 
@@ -816,7 +816,7 @@ asm_AES_decrypt:
 	leaq	.LAES_Td+2048(%rip),%r14
 	leaq	768(%rsp),%rbp
 	subq	%r14,%rbp
-	andq	$768,%rbp
+	andq	$0x300,%rbp
 	leaq	(%r14,%rbp,1),%r14
 	shrq	$3,%rbp
 	addq	%rbp,%r14
@@ -1334,9 +1334,9 @@ asm_AES_cbc_encrypt:
 	movq	%r14,%r10
 	leaq	2304(%r14),%r11
 	movq	%r15,%r12
-	andq	$4095,%r10
-	andq	$4095,%r11
-	andq	$4095,%r12
+	andq	$0xFFF,%r10
+	andq	$0xFFF,%r11
+	andq	$0xFFF,%r12
 
 	cmpq	%r11,%r12
 	jb	.Lcbc_te_break_out
@@ -1345,7 +1345,7 @@ asm_AES_cbc_encrypt:
 	jmp	.Lcbc_te_ok
 .Lcbc_te_break_out:
 	subq	%r10,%r12
-	andq	$4095,%r12
+	andq	$0xFFF,%r12
 	addq	$320,%r12
 	subq	%r12,%r15
 .align	4
@@ -1371,7 +1371,7 @@ asm_AES_cbc_encrypt:
 
 	movq	%r15,%r10
 	subq	%r14,%r10
-	andq	$4095,%r10
+	andq	$0xfff,%r10
 	cmpq	$2304,%r10
 	jb	.Lcbc_do_ecopy
 	cmpq	$4096-248,%r10
@@ -1558,7 +1558,7 @@ asm_AES_cbc_encrypt:
 	leaq	-88-63(%rcx),%r10
 	subq	%rbp,%r10
 	negq	%r10
-	andq	$960,%r10
+	andq	$0x3c0,%r10
 	subq	%r10,%rbp
 
 	xchgq	%rsp,%rbp
@@ -1587,7 +1587,7 @@ asm_AES_cbc_encrypt:
 	leaq	2048(%r14),%r14
 	leaq	768-8(%rsp),%rax
 	subq	%r14,%rax
-	andq	$768,%rax
+	andq	$0x300,%rax
 	leaq	(%r14,%rax,1),%r14
 
 	cmpq	$0,%rbx
diff --git a/packager/third_party/boringssl/linux-x86_64/crypto/aes/aesni-x86_64.S b/packager/third_party/boringssl/linux-x86_64/crypto/aes/aesni-x86_64.S
index 1d51d5b50e..5709a2d024 100644
--- a/packager/third_party/boringssl/linux-x86_64/crypto/aes/aesni-x86_64.S
+++ b/packager/third_party/boringssl/linux-x86_64/crypto/aes/aesni-x86_64.S
@@ -508,7 +508,7 @@ aesni_ecb_encrypt:
 	testl	%r8d,%r8d
 	jz	.Lecb_decrypt
 
-	cmpq	$128,%rdx
+	cmpq	$0x80,%rdx
 	jb	.Lecb_enc_tail
 
 	movdqu	(%rdi),%xmm2
@@ -520,7 +520,7 @@ aesni_ecb_encrypt:
 	movdqu	96(%rdi),%xmm8
 	movdqu	112(%rdi),%xmm9
 	leaq	128(%rdi),%rdi
-	subq	$128,%rdx
+	subq	$0x80,%rdx
 	jmp	.Lecb_enc_loop8_enter
 .align	16
 .Lecb_enc_loop8:
@@ -548,7 +548,7 @@ aesni_ecb_encrypt:
 
 	call	_aesni_encrypt8
 
-	subq	$128,%rdx
+	subq	$0x80,%rdx
 	jnc	.Lecb_enc_loop8
 
 	movups	%xmm2,(%rsi)
@@ -562,22 +562,22 @@ aesni_ecb_encrypt:
 	movups	%xmm8,96(%rsi)
 	movups	%xmm9,112(%rsi)
 	leaq	128(%rsi),%rsi
-	addq	$128,%rdx
+	addq	$0x80,%rdx
 	jz	.Lecb_ret
 
 .Lecb_enc_tail:
 	movups	(%rdi),%xmm2
-	cmpq	$32,%rdx
+	cmpq	$0x20,%rdx
 	jb	.Lecb_enc_one
 	movups	16(%rdi),%xmm3
 	je	.Lecb_enc_two
 	movups	32(%rdi),%xmm4
-	cmpq	$64,%rdx
+	cmpq	$0x40,%rdx
 	jb	.Lecb_enc_three
 	movups	48(%rdi),%xmm5
 	je	.Lecb_enc_four
 	movups	64(%rdi),%xmm6
-	cmpq	$96,%rdx
+	cmpq	$0x60,%rdx
 	jb	.Lecb_enc_five
 	movups	80(%rdi),%xmm7
 	je	.Lecb_enc_six
@@ -651,7 +651,7 @@ aesni_ecb_encrypt:
 
 .align	16
 .Lecb_decrypt:
-	cmpq	$128,%rdx
+	cmpq	$0x80,%rdx
 	jb	.Lecb_dec_tail
 
 	movdqu	(%rdi),%xmm2
@@ -663,7 +663,7 @@ aesni_ecb_encrypt:
 	movdqu	96(%rdi),%xmm8
 	movdqu	112(%rdi),%xmm9
 	leaq	128(%rdi),%rdi
-	subq	$128,%rdx
+	subq	$0x80,%rdx
 	jmp	.Lecb_dec_loop8_enter
 .align	16
 .Lecb_dec_loop8:
@@ -692,7 +692,7 @@ aesni_ecb_encrypt:
 	call	_aesni_decrypt8
 
 	movups	(%r11),%xmm0
-	subq	$128,%rdx
+	subq	$0x80,%rdx
 	jnc	.Lecb_dec_loop8
 
 	movups	%xmm2,(%rsi)
@@ -714,22 +714,22 @@ aesni_ecb_encrypt:
 	movups	%xmm9,112(%rsi)
 	pxor	%xmm9,%xmm9
 	leaq	128(%rsi),%rsi
-	addq	$128,%rdx
+	addq	$0x80,%rdx
 	jz	.Lecb_ret
 
 .Lecb_dec_tail:
 	movups	(%rdi),%xmm2
-	cmpq	$32,%rdx
+	cmpq	$0x20,%rdx
 	jb	.Lecb_dec_one
 	movups	16(%rdi),%xmm3
 	je	.Lecb_dec_two
 	movups	32(%rdi),%xmm4
-	cmpq	$64,%rdx
+	cmpq	$0x40,%rdx
 	jb	.Lecb_dec_three
 	movups	48(%rdi),%xmm5
 	je	.Lecb_dec_four
 	movups	64(%rdi),%xmm6
-	cmpq	$96,%rdx
+	cmpq	$0x60,%rdx
 	jb	.Lecb_dec_five
 	movups	80(%rdi),%xmm7
 	je	.Lecb_dec_six
@@ -1607,7 +1607,7 @@ aesni_xts_encrypt:
 
 	movdqa	.Lxts_magic(%rip),%xmm8
 	movdqa	%xmm2,%xmm15
-	pshufd	$95,%xmm2,%xmm9
+	pshufd	$0x5f,%xmm2,%xmm9
 	pxor	%xmm0,%xmm1
 	movdqa	%xmm9,%xmm14
 	paddd	%xmm9,%xmm9
@@ -1706,7 +1706,7 @@ aesni_xts_encrypt:
 .byte	102,15,56,220,248
 	movups	64(%r11),%xmm0
 	movdqa	%xmm8,80(%rsp)
-	pshufd	$95,%xmm15,%xmm9
+	pshufd	$0x5f,%xmm15,%xmm9
 	jmp	.Lxts_enc_loop6
 .align	32
 .Lxts_enc_loop6:
@@ -1845,13 +1845,13 @@ aesni_xts_encrypt:
 	jz	.Lxts_enc_done
 
 	pxor	%xmm0,%xmm11
-	cmpq	$32,%rdx
+	cmpq	$0x20,%rdx
 	jb	.Lxts_enc_one
 	pxor	%xmm0,%xmm12
 	je	.Lxts_enc_two
 
 	pxor	%xmm0,%xmm13
-	cmpq	$64,%rdx
+	cmpq	$0x40,%rdx
 	jb	.Lxts_enc_three
 	pxor	%xmm0,%xmm14
 	je	.Lxts_enc_four
@@ -2079,7 +2079,7 @@ aesni_xts_decrypt:
 
 	movdqa	.Lxts_magic(%rip),%xmm8
 	movdqa	%xmm2,%xmm15
-	pshufd	$95,%xmm2,%xmm9
+	pshufd	$0x5f,%xmm2,%xmm9
 	pxor	%xmm0,%xmm1
 	movdqa	%xmm9,%xmm14
 	paddd	%xmm9,%xmm9
@@ -2178,7 +2178,7 @@ aesni_xts_decrypt:
 .byte	102,15,56,222,248
 	movups	64(%r11),%xmm0
 	movdqa	%xmm8,80(%rsp)
-	pshufd	$95,%xmm15,%xmm9
+	pshufd	$0x5f,%xmm15,%xmm9
 	jmp	.Lxts_dec_loop6
 .align	32
 .Lxts_dec_loop6:
@@ -2318,13 +2318,13 @@ aesni_xts_decrypt:
 	jz	.Lxts_dec_done
 
 	pxor	%xmm0,%xmm12
-	cmpq	$32,%rdx
+	cmpq	$0x20,%rdx
 	jb	.Lxts_dec_one
 	pxor	%xmm0,%xmm13
 	je	.Lxts_dec_two
 
 	pxor	%xmm0,%xmm14
-	cmpq	$64,%rdx
+	cmpq	$0x40,%rdx
 	jb	.Lxts_dec_three
 	je	.Lxts_dec_four
 
@@ -2355,7 +2355,7 @@ aesni_xts_decrypt:
 	pcmpgtd	%xmm15,%xmm14
 	movdqu	%xmm6,64(%rsi)
 	leaq	80(%rsi),%rsi
-	pshufd	$19,%xmm14,%xmm11
+	pshufd	$0x13,%xmm14,%xmm11
 	andq	$15,%r9
 	jz	.Lxts_dec_ret
 
@@ -2645,7 +2645,7 @@ aesni_cbc_encrypt:
 	leaq	-8(%rax),%rbp
 	movups	(%r8),%xmm10
 	movl	%r10d,%eax
-	cmpq	$80,%rdx
+	cmpq	$0x50,%rdx
 	jbe	.Lcbc_dec_tail
 
 	movups	(%rcx),%xmm0
@@ -2661,14 +2661,14 @@ aesni_cbc_encrypt:
 	movdqu	80(%rdi),%xmm7
 	movdqa	%xmm6,%xmm15
 	movl	OPENSSL_ia32cap_P+4(%rip),%r9d
-	cmpq	$112,%rdx
+	cmpq	$0x70,%rdx
 	jbe	.Lcbc_dec_six_or_seven
 
 	andl	$71303168,%r9d
-	subq	$80,%rdx
+	subq	$0x50,%rdx
 	cmpl	$4194304,%r9d
 	je	.Lcbc_dec_loop6_enter
-	subq	$32,%rdx
+	subq	$0x20,%rdx
 	leaq	112(%rcx),%rcx
 	jmp	.Lcbc_dec_loop8_enter
 .align	16
@@ -2683,7 +2683,7 @@ aesni_cbc_encrypt:
 	movups	16-112(%rcx),%xmm1
 	pxor	%xmm0,%xmm4
 	xorq	%r11,%r11
-	cmpq	$112,%rdx
+	cmpq	$0x70,%rdx
 	pxor	%xmm0,%xmm5
 	pxor	%xmm0,%xmm6
 	pxor	%xmm0,%xmm7
@@ -2868,21 +2868,21 @@ aesni_cbc_encrypt:
 	movups	%xmm8,96(%rsi)
 	leaq	112(%rsi),%rsi
 
-	subq	$128,%rdx
+	subq	$0x80,%rdx
 	ja	.Lcbc_dec_loop8
 
 	movaps	%xmm9,%xmm2
 	leaq	-112(%rcx),%rcx
-	addq	$112,%rdx
+	addq	$0x70,%rdx
 	jle	.Lcbc_dec_clear_tail_collected
 	movups	%xmm9,(%rsi)
 	leaq	16(%rsi),%rsi
-	cmpq	$80,%rdx
+	cmpq	$0x50,%rdx
 	jbe	.Lcbc_dec_tail
 
 	movaps	%xmm11,%xmm2
 .Lcbc_dec_six_or_seven:
-	cmpq	$96,%rdx
+	cmpq	$0x60,%rdx
 	ja	.Lcbc_dec_seven
 
 	movaps	%xmm7,%xmm8
@@ -2975,33 +2975,33 @@ aesni_cbc_encrypt:
 	movl	%r10d,%eax
 	movdqu	%xmm6,64(%rsi)
 	leaq	80(%rsi),%rsi
-	subq	$96,%rdx
+	subq	$0x60,%rdx
 	ja	.Lcbc_dec_loop6
 
 	movdqa	%xmm7,%xmm2
-	addq	$80,%rdx
+	addq	$0x50,%rdx
 	jle	.Lcbc_dec_clear_tail_collected
 	movups	%xmm7,(%rsi)
 	leaq	16(%rsi),%rsi
 
 .Lcbc_dec_tail:
 	movups	(%rdi),%xmm2
-	subq	$16,%rdx
+	subq	$0x10,%rdx
 	jbe	.Lcbc_dec_one
 
 	movups	16(%rdi),%xmm3
 	movaps	%xmm2,%xmm11
-	subq	$16,%rdx
+	subq	$0x10,%rdx
 	jbe	.Lcbc_dec_two
 
 	movups	32(%rdi),%xmm4
 	movaps	%xmm3,%xmm12
-	subq	$16,%rdx
+	subq	$0x10,%rdx
 	jbe	.Lcbc_dec_three
 
 	movups	48(%rdi),%xmm5
 	movaps	%xmm4,%xmm13
-	subq	$16,%rdx
+	subq	$0x10,%rdx
 	jbe	.Lcbc_dec_four
 
 	movups	64(%rdi),%xmm6
@@ -3026,7 +3026,7 @@ aesni_cbc_encrypt:
 	movdqa	%xmm6,%xmm2
 	pxor	%xmm6,%xmm6
 	pxor	%xmm7,%xmm7
-	subq	$16,%rdx
+	subq	$0x10,%rdx
 	jmp	.Lcbc_dec_tail_collected
 
 .align	16
@@ -3345,7 +3345,7 @@ __aesni_set_encrypt_key:
 	pslldq	$4,%xmm0
 	pxor	%xmm3,%xmm0
 
-	pshufd	$255,%xmm0,%xmm3
+	pshufd	$0xff,%xmm0,%xmm3
 	pxor	%xmm1,%xmm3
 	pslldq	$4,%xmm1
 	pxor	%xmm1,%xmm3
@@ -3432,7 +3432,7 @@ __aesni_set_encrypt_key:
 	decl	%r10d
 	jz	.Ldone_key256
 
-	pshufd	$255,%xmm0,%xmm2
+	pshufd	$0xff,%xmm0,%xmm2
 	pxor	%xmm3,%xmm3
 .byte	102,15,56,221,211
 
diff --git a/packager/third_party/boringssl/linux-x86_64/crypto/aes/bsaes-x86_64.S b/packager/third_party/boringssl/linux-x86_64/crypto/aes/bsaes-x86_64.S
index 8cfa4df5ba..c5491ce4d0 100644
--- a/packager/third_party/boringssl/linux-x86_64/crypto/aes/bsaes-x86_64.S
+++ b/packager/third_party/boringssl/linux-x86_64/crypto/aes/bsaes-x86_64.S
@@ -327,45 +327,45 @@ _bsaes_encrypt8_bitslice:
 	pxor	%xmm2,%xmm5
 	decl	%r10d
 	jl	.Lenc_done
-	pshufd	$147,%xmm15,%xmm7
-	pshufd	$147,%xmm0,%xmm8
+	pshufd	$0x93,%xmm15,%xmm7
+	pshufd	$0x93,%xmm0,%xmm8
 	pxor	%xmm7,%xmm15
-	pshufd	$147,%xmm3,%xmm9
+	pshufd	$0x93,%xmm3,%xmm9
 	pxor	%xmm8,%xmm0
-	pshufd	$147,%xmm5,%xmm10
+	pshufd	$0x93,%xmm5,%xmm10
 	pxor	%xmm9,%xmm3
-	pshufd	$147,%xmm2,%xmm11
+	pshufd	$0x93,%xmm2,%xmm11
 	pxor	%xmm10,%xmm5
-	pshufd	$147,%xmm6,%xmm12
+	pshufd	$0x93,%xmm6,%xmm12
 	pxor	%xmm11,%xmm2
-	pshufd	$147,%xmm1,%xmm13
+	pshufd	$0x93,%xmm1,%xmm13
 	pxor	%xmm12,%xmm6
-	pshufd	$147,%xmm4,%xmm14
+	pshufd	$0x93,%xmm4,%xmm14
 	pxor	%xmm13,%xmm1
 	pxor	%xmm14,%xmm4
 
 	pxor	%xmm15,%xmm8
 	pxor	%xmm4,%xmm7
 	pxor	%xmm4,%xmm8
-	pshufd	$78,%xmm15,%xmm15
+	pshufd	$0x4E,%xmm15,%xmm15
 	pxor	%xmm0,%xmm9
-	pshufd	$78,%xmm0,%xmm0
+	pshufd	$0x4E,%xmm0,%xmm0
 	pxor	%xmm2,%xmm12
 	pxor	%xmm7,%xmm15
 	pxor	%xmm6,%xmm13
 	pxor	%xmm8,%xmm0
 	pxor	%xmm5,%xmm11
-	pshufd	$78,%xmm2,%xmm7
+	pshufd	$0x4E,%xmm2,%xmm7
 	pxor	%xmm1,%xmm14
-	pshufd	$78,%xmm6,%xmm8
+	pshufd	$0x4E,%xmm6,%xmm8
 	pxor	%xmm3,%xmm10
-	pshufd	$78,%xmm5,%xmm2
+	pshufd	$0x4E,%xmm5,%xmm2
 	pxor	%xmm4,%xmm10
-	pshufd	$78,%xmm4,%xmm6
+	pshufd	$0x4E,%xmm4,%xmm6
 	pxor	%xmm4,%xmm11
-	pshufd	$78,%xmm1,%xmm5
+	pshufd	$0x4E,%xmm1,%xmm5
 	pxor	%xmm11,%xmm7
-	pshufd	$78,%xmm3,%xmm1
+	pshufd	$0x4E,%xmm3,%xmm1
 	pxor	%xmm12,%xmm8
 	pxor	%xmm10,%xmm2
 	pxor	%xmm14,%xmm6
@@ -799,24 +799,24 @@ _bsaes_decrypt8:
 	decl	%r10d
 	jl	.Ldec_done
 
-	pshufd	$78,%xmm15,%xmm7
-	pshufd	$78,%xmm2,%xmm13
+	pshufd	$0x4E,%xmm15,%xmm7
+	pshufd	$0x4E,%xmm2,%xmm13
 	pxor	%xmm15,%xmm7
-	pshufd	$78,%xmm4,%xmm14
+	pshufd	$0x4E,%xmm4,%xmm14
 	pxor	%xmm2,%xmm13
-	pshufd	$78,%xmm0,%xmm8
+	pshufd	$0x4E,%xmm0,%xmm8
 	pxor	%xmm4,%xmm14
-	pshufd	$78,%xmm5,%xmm9
+	pshufd	$0x4E,%xmm5,%xmm9
 	pxor	%xmm0,%xmm8
-	pshufd	$78,%xmm3,%xmm10
+	pshufd	$0x4E,%xmm3,%xmm10
 	pxor	%xmm5,%xmm9
 	pxor	%xmm13,%xmm15
 	pxor	%xmm13,%xmm0
-	pshufd	$78,%xmm1,%xmm11
+	pshufd	$0x4E,%xmm1,%xmm11
 	pxor	%xmm3,%xmm10
 	pxor	%xmm7,%xmm5
 	pxor	%xmm8,%xmm3
-	pshufd	$78,%xmm6,%xmm12
+	pshufd	$0x4E,%xmm6,%xmm12
 	pxor	%xmm1,%xmm11
 	pxor	%xmm14,%xmm0
 	pxor	%xmm9,%xmm1
@@ -830,45 +830,45 @@ _bsaes_decrypt8:
 	pxor	%xmm14,%xmm1
 	pxor	%xmm14,%xmm6
 	pxor	%xmm12,%xmm4
-	pshufd	$147,%xmm15,%xmm7
-	pshufd	$147,%xmm0,%xmm8
+	pshufd	$0x93,%xmm15,%xmm7
+	pshufd	$0x93,%xmm0,%xmm8
 	pxor	%xmm7,%xmm15
-	pshufd	$147,%xmm5,%xmm9
+	pshufd	$0x93,%xmm5,%xmm9
 	pxor	%xmm8,%xmm0
-	pshufd	$147,%xmm3,%xmm10
+	pshufd	$0x93,%xmm3,%xmm10
 	pxor	%xmm9,%xmm5
-	pshufd	$147,%xmm1,%xmm11
+	pshufd	$0x93,%xmm1,%xmm11
 	pxor	%xmm10,%xmm3
-	pshufd	$147,%xmm6,%xmm12
+	pshufd	$0x93,%xmm6,%xmm12
 	pxor	%xmm11,%xmm1
-	pshufd	$147,%xmm2,%xmm13
+	pshufd	$0x93,%xmm2,%xmm13
 	pxor	%xmm12,%xmm6
-	pshufd	$147,%xmm4,%xmm14
+	pshufd	$0x93,%xmm4,%xmm14
 	pxor	%xmm13,%xmm2
 	pxor	%xmm14,%xmm4
 
 	pxor	%xmm15,%xmm8
 	pxor	%xmm4,%xmm7
 	pxor	%xmm4,%xmm8
-	pshufd	$78,%xmm15,%xmm15
+	pshufd	$0x4E,%xmm15,%xmm15
 	pxor	%xmm0,%xmm9
-	pshufd	$78,%xmm0,%xmm0
+	pshufd	$0x4E,%xmm0,%xmm0
 	pxor	%xmm1,%xmm12
 	pxor	%xmm7,%xmm15
 	pxor	%xmm6,%xmm13
 	pxor	%xmm8,%xmm0
 	pxor	%xmm3,%xmm11
-	pshufd	$78,%xmm1,%xmm7
+	pshufd	$0x4E,%xmm1,%xmm7
 	pxor	%xmm2,%xmm14
-	pshufd	$78,%xmm6,%xmm8
+	pshufd	$0x4E,%xmm6,%xmm8
 	pxor	%xmm5,%xmm10
-	pshufd	$78,%xmm3,%xmm1
+	pshufd	$0x4E,%xmm3,%xmm1
 	pxor	%xmm4,%xmm10
-	pshufd	$78,%xmm4,%xmm6
+	pshufd	$0x4E,%xmm4,%xmm6
 	pxor	%xmm4,%xmm11
-	pshufd	$78,%xmm2,%xmm3
+	pshufd	$0x4E,%xmm2,%xmm3
 	pxor	%xmm11,%xmm7
-	pshufd	$78,%xmm5,%xmm2
+	pshufd	$0x4E,%xmm5,%xmm2
 	pxor	%xmm12,%xmm8
 	pxor	%xmm1,%xmm10
 	pxor	%xmm14,%xmm6
@@ -1559,20 +1559,20 @@ bsaes_xts_encrypt:
 	movdqa	%xmm7,(%rax)
 
 	andq	$-16,%r14
-	subq	$128,%rsp
+	subq	$0x80,%rsp
 	movdqa	32(%rbp),%xmm6
 
 	pxor	%xmm14,%xmm14
 	movdqa	.Lxts_magic(%rip),%xmm12
 	pcmpgtd	%xmm6,%xmm14
 
-	subq	$128,%r14
+	subq	$0x80,%r14
 	jc	.Lxts_enc_short
 	jmp	.Lxts_enc_loop
 
 .align	16
 .Lxts_enc_loop:
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm15
 	movdqa	%xmm6,0(%rsp)
@@ -1580,7 +1580,7 @@ bsaes_xts_encrypt:
 	pand	%xmm12,%xmm13
 	pcmpgtd	%xmm6,%xmm14
 	pxor	%xmm13,%xmm6
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm0
 	movdqa	%xmm6,16(%rsp)
@@ -1589,7 +1589,7 @@ bsaes_xts_encrypt:
 	pcmpgtd	%xmm6,%xmm14
 	pxor	%xmm13,%xmm6
 	movdqu	0(%r12),%xmm7
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm1
 	movdqa	%xmm6,32(%rsp)
@@ -1599,7 +1599,7 @@ bsaes_xts_encrypt:
 	pxor	%xmm13,%xmm6
 	movdqu	16(%r12),%xmm8
 	pxor	%xmm7,%xmm15
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm2
 	movdqa	%xmm6,48(%rsp)
@@ -1609,7 +1609,7 @@ bsaes_xts_encrypt:
 	pxor	%xmm13,%xmm6
 	movdqu	32(%r12),%xmm9
 	pxor	%xmm8,%xmm0
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm3
 	movdqa	%xmm6,64(%rsp)
@@ -1619,7 +1619,7 @@ bsaes_xts_encrypt:
 	pxor	%xmm13,%xmm6
 	movdqu	48(%r12),%xmm10
 	pxor	%xmm9,%xmm1
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm4
 	movdqa	%xmm6,80(%rsp)
@@ -1629,7 +1629,7 @@ bsaes_xts_encrypt:
 	pxor	%xmm13,%xmm6
 	movdqu	64(%r12),%xmm11
 	pxor	%xmm10,%xmm2
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm5
 	movdqa	%xmm6,96(%rsp)
@@ -1673,20 +1673,20 @@ bsaes_xts_encrypt:
 	pxor	%xmm14,%xmm14
 	movdqa	.Lxts_magic(%rip),%xmm12
 	pcmpgtd	%xmm6,%xmm14
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	paddq	%xmm6,%xmm6
 	pand	%xmm12,%xmm13
 	pcmpgtd	%xmm6,%xmm14
 	pxor	%xmm13,%xmm6
 
-	subq	$128,%r14
+	subq	$0x80,%r14
 	jnc	.Lxts_enc_loop
 
 .Lxts_enc_short:
-	addq	$128,%r14
+	addq	$0x80,%r14
 	jz	.Lxts_enc_done
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm15
 	movdqa	%xmm6,0(%rsp)
@@ -1694,7 +1694,7 @@ bsaes_xts_encrypt:
 	pand	%xmm12,%xmm13
 	pcmpgtd	%xmm6,%xmm14
 	pxor	%xmm13,%xmm6
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm0
 	movdqa	%xmm6,16(%rsp)
@@ -1705,7 +1705,7 @@ bsaes_xts_encrypt:
 	movdqu	0(%r12),%xmm7
 	cmpq	$16,%r14
 	je	.Lxts_enc_1
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm1
 	movdqa	%xmm6,32(%rsp)
@@ -1717,7 +1717,7 @@ bsaes_xts_encrypt:
 	cmpq	$32,%r14
 	je	.Lxts_enc_2
 	pxor	%xmm7,%xmm15
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm2
 	movdqa	%xmm6,48(%rsp)
@@ -1729,7 +1729,7 @@ bsaes_xts_encrypt:
 	cmpq	$48,%r14
 	je	.Lxts_enc_3
 	pxor	%xmm8,%xmm0
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm3
 	movdqa	%xmm6,64(%rsp)
@@ -1741,7 +1741,7 @@ bsaes_xts_encrypt:
 	cmpq	$64,%r14
 	je	.Lxts_enc_4
 	pxor	%xmm9,%xmm1
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm4
 	movdqa	%xmm6,80(%rsp)
@@ -1753,7 +1753,7 @@ bsaes_xts_encrypt:
 	cmpq	$80,%r14
 	je	.Lxts_enc_5
 	pxor	%xmm10,%xmm2
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm5
 	movdqa	%xmm6,96(%rsp)
@@ -2019,20 +2019,20 @@ bsaes_xts_decrypt:
 	shlq	$4,%rax
 	subq	%rax,%r14
 
-	subq	$128,%rsp
+	subq	$0x80,%rsp
 	movdqa	32(%rbp),%xmm6
 
 	pxor	%xmm14,%xmm14
 	movdqa	.Lxts_magic(%rip),%xmm12
 	pcmpgtd	%xmm6,%xmm14
 
-	subq	$128,%r14
+	subq	$0x80,%r14
 	jc	.Lxts_dec_short
 	jmp	.Lxts_dec_loop
 
 .align	16
 .Lxts_dec_loop:
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm15
 	movdqa	%xmm6,0(%rsp)
@@ -2040,7 +2040,7 @@ bsaes_xts_decrypt:
 	pand	%xmm12,%xmm13
 	pcmpgtd	%xmm6,%xmm14
 	pxor	%xmm13,%xmm6
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm0
 	movdqa	%xmm6,16(%rsp)
@@ -2049,7 +2049,7 @@ bsaes_xts_decrypt:
 	pcmpgtd	%xmm6,%xmm14
 	pxor	%xmm13,%xmm6
 	movdqu	0(%r12),%xmm7
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm1
 	movdqa	%xmm6,32(%rsp)
@@ -2059,7 +2059,7 @@ bsaes_xts_decrypt:
 	pxor	%xmm13,%xmm6
 	movdqu	16(%r12),%xmm8
 	pxor	%xmm7,%xmm15
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm2
 	movdqa	%xmm6,48(%rsp)
@@ -2069,7 +2069,7 @@ bsaes_xts_decrypt:
 	pxor	%xmm13,%xmm6
 	movdqu	32(%r12),%xmm9
 	pxor	%xmm8,%xmm0
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm3
 	movdqa	%xmm6,64(%rsp)
@@ -2079,7 +2079,7 @@ bsaes_xts_decrypt:
 	pxor	%xmm13,%xmm6
 	movdqu	48(%r12),%xmm10
 	pxor	%xmm9,%xmm1
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm4
 	movdqa	%xmm6,80(%rsp)
@@ -2089,7 +2089,7 @@ bsaes_xts_decrypt:
 	pxor	%xmm13,%xmm6
 	movdqu	64(%r12),%xmm11
 	pxor	%xmm10,%xmm2
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm5
 	movdqa	%xmm6,96(%rsp)
@@ -2133,20 +2133,20 @@ bsaes_xts_decrypt:
 	pxor	%xmm14,%xmm14
 	movdqa	.Lxts_magic(%rip),%xmm12
 	pcmpgtd	%xmm6,%xmm14
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	paddq	%xmm6,%xmm6
 	pand	%xmm12,%xmm13
 	pcmpgtd	%xmm6,%xmm14
 	pxor	%xmm13,%xmm6
 
-	subq	$128,%r14
+	subq	$0x80,%r14
 	jnc	.Lxts_dec_loop
 
 .Lxts_dec_short:
-	addq	$128,%r14
+	addq	$0x80,%r14
 	jz	.Lxts_dec_done
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm15
 	movdqa	%xmm6,0(%rsp)
@@ -2154,7 +2154,7 @@ bsaes_xts_decrypt:
 	pand	%xmm12,%xmm13
 	pcmpgtd	%xmm6,%xmm14
 	pxor	%xmm13,%xmm6
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm0
 	movdqa	%xmm6,16(%rsp)
@@ -2165,7 +2165,7 @@ bsaes_xts_decrypt:
 	movdqu	0(%r12),%xmm7
 	cmpq	$16,%r14
 	je	.Lxts_dec_1
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm1
 	movdqa	%xmm6,32(%rsp)
@@ -2177,7 +2177,7 @@ bsaes_xts_decrypt:
 	cmpq	$32,%r14
 	je	.Lxts_dec_2
 	pxor	%xmm7,%xmm15
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm2
 	movdqa	%xmm6,48(%rsp)
@@ -2189,7 +2189,7 @@ bsaes_xts_decrypt:
 	cmpq	$48,%r14
 	je	.Lxts_dec_3
 	pxor	%xmm8,%xmm0
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm3
 	movdqa	%xmm6,64(%rsp)
@@ -2201,7 +2201,7 @@ bsaes_xts_decrypt:
 	cmpq	$64,%r14
 	je	.Lxts_dec_4
 	pxor	%xmm9,%xmm1
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm4
 	movdqa	%xmm6,80(%rsp)
@@ -2213,7 +2213,7 @@ bsaes_xts_decrypt:
 	cmpq	$80,%r14
 	je	.Lxts_dec_5
 	pxor	%xmm10,%xmm2
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm5
 	movdqa	%xmm6,96(%rsp)
@@ -2390,7 +2390,7 @@ bsaes_xts_decrypt:
 	pxor	%xmm14,%xmm14
 	movdqa	.Lxts_magic(%rip),%xmm12
 	pcmpgtd	%xmm6,%xmm14
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	movdqa	%xmm6,%xmm5
 	paddq	%xmm6,%xmm6
 	pand	%xmm12,%xmm13
diff --git a/packager/third_party/boringssl/linux-x86_64/crypto/aes/vpaes-x86_64.S b/packager/third_party/boringssl/linux-x86_64/crypto/aes/vpaes-x86_64.S
index 1d124246af..4dfafa97ea 100644
--- a/packager/third_party/boringssl/linux-x86_64/crypto/aes/vpaes-x86_64.S
+++ b/packager/third_party/boringssl/linux-x86_64/crypto/aes/vpaes-x86_64.S
@@ -61,7 +61,7 @@ _vpaes_encrypt_core:
 	addq	$16,%r11
 	pxor	%xmm0,%xmm3
 .byte	102,15,56,0,193
-	andq	$48,%r11
+	andq	$0x30,%r11
 	subq	$1,%rax
 	pxor	%xmm3,%xmm0
 
@@ -121,10 +121,10 @@ _vpaes_decrypt_core:
 	pand	%xmm9,%xmm0
 .byte	102,15,56,0,208
 	movdqa	.Lk_dipt+16(%rip),%xmm0
-	xorq	$48,%r11
+	xorq	$0x30,%r11
 	leaq	.Lk_dsbd(%rip),%r10
 .byte	102,15,56,0,193
-	andq	$48,%r11
+	andq	$0x30,%r11
 	pxor	%xmm5,%xmm2
 	movdqa	.Lk_mc_forward+48(%rip),%xmm5
 	pxor	%xmm2,%xmm0
@@ -243,7 +243,7 @@ _vpaes_schedule_core:
 	movdqa	(%r8,%r10,1),%xmm1
 .byte	102,15,56,0,217
 	movdqu	%xmm3,(%rdx)
-	xorq	$48,%r8
+	xorq	$0x30,%r8
 
 .Lschedule_go:
 	cmpl	$192,%esi
@@ -333,7 +333,7 @@ _vpaes_schedule_core:
 	call	_vpaes_schedule_mangle
 
 
-	pshufd	$255,%xmm0,%xmm0
+	pshufd	$0xFF,%xmm0,%xmm0
 	movdqa	%xmm7,%xmm5
 	movdqa	%xmm6,%xmm7
 	call	_vpaes_schedule_low_round
@@ -400,8 +400,8 @@ _vpaes_schedule_core:
 .type	_vpaes_schedule_192_smear,@function
 .align	16
 _vpaes_schedule_192_smear:
-	pshufd	$128,%xmm6,%xmm1
-	pshufd	$254,%xmm7,%xmm0
+	pshufd	$0x80,%xmm6,%xmm1
+	pshufd	$0xFE,%xmm7,%xmm0
 	pxor	%xmm1,%xmm6
 	pxor	%xmm1,%xmm1
 	pxor	%xmm0,%xmm6
@@ -438,7 +438,7 @@ _vpaes_schedule_round:
 	pxor	%xmm1,%xmm7
 
 
-	pshufd	$255,%xmm0,%xmm0
+	pshufd	$0xFF,%xmm0,%xmm0
 .byte	102,15,58,15,192,1
 
 
@@ -597,7 +597,7 @@ _vpaes_schedule_mangle:
 	movdqa	(%r8,%r10,1),%xmm1
 .byte	102,15,56,0,217
 	addq	$-16,%r8
-	andq	$48,%r8
+	andq	$0x30,%r8
 	movdqu	%xmm3,(%rdx)
 	.byte	0xf3,0xc3
 .size	_vpaes_schedule_mangle,.-_vpaes_schedule_mangle
@@ -616,7 +616,7 @@ vpaes_set_encrypt_key:
 	movl	%eax,240(%rdx)
 
 	movl	$0,%ecx
-	movl	$48,%r8d
+	movl	$0x30,%r8d
 	call	_vpaes_schedule_core
 	xorl	%eax,%eax
 	.byte	0xf3,0xc3
diff --git a/packager/third_party/boringssl/linux-x86_64/crypto/bn/rsaz-x86_64.S b/packager/third_party/boringssl/linux-x86_64/crypto/bn/rsaz-x86_64.S
index dd3d3106d1..21531d1c65 100644
--- a/packager/third_party/boringssl/linux-x86_64/crypto/bn/rsaz-x86_64.S
+++ b/packager/third_party/boringssl/linux-x86_64/crypto/bn/rsaz-x86_64.S
@@ -466,48 +466,94 @@ rsaz_512_mul_gather4:
 	pushq	%r14
 	pushq	%r15
 
-	movl	%r9d,%r9d
-	subq	$128+24,%rsp
+	subq	$152,%rsp
 .Lmul_gather4_body:
-	movl	64(%rdx,%r9,4),%eax
-.byte	102,72,15,110,199
-	movl	(%rdx,%r9,4),%ebx
-.byte	102,72,15,110,201
-	movq	%r8,128(%rsp)
+	movd	%r9d,%xmm8
+	movdqa	.Linc+16(%rip),%xmm1
+	movdqa	.Linc(%rip),%xmm0
+
+	pshufd	$0,%xmm8,%xmm8
+	movdqa	%xmm1,%xmm7
+	movdqa	%xmm1,%xmm2
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm8,%xmm0
+	movdqa	%xmm7,%xmm3
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm8,%xmm1
+	movdqa	%xmm7,%xmm4
+	paddd	%xmm2,%xmm3
+	pcmpeqd	%xmm8,%xmm2
+	movdqa	%xmm7,%xmm5
+	paddd	%xmm3,%xmm4
+	pcmpeqd	%xmm8,%xmm3
+	movdqa	%xmm7,%xmm6
+	paddd	%xmm4,%xmm5
+	pcmpeqd	%xmm8,%xmm4
+	paddd	%xmm5,%xmm6
+	pcmpeqd	%xmm8,%xmm5
+	paddd	%xmm6,%xmm7
+	pcmpeqd	%xmm8,%xmm6
+	pcmpeqd	%xmm8,%xmm7
+
+	movdqa	0(%rdx),%xmm8
+	movdqa	16(%rdx),%xmm9
+	movdqa	32(%rdx),%xmm10
+	movdqa	48(%rdx),%xmm11
+	pand	%xmm0,%xmm8
+	movdqa	64(%rdx),%xmm12
+	pand	%xmm1,%xmm9
+	movdqa	80(%rdx),%xmm13
+	pand	%xmm2,%xmm10
+	movdqa	96(%rdx),%xmm14
+	pand	%xmm3,%xmm11
+	movdqa	112(%rdx),%xmm15
+	leaq	128(%rdx),%rbp
+	pand	%xmm4,%xmm12
+	pand	%xmm5,%xmm13
+	pand	%xmm6,%xmm14
+	pand	%xmm7,%xmm15
+	por	%xmm10,%xmm8
+	por	%xmm11,%xmm9
+	por	%xmm12,%xmm8
+	por	%xmm13,%xmm9
+	por	%xmm14,%xmm8
+	por	%xmm15,%xmm9
+
+	por	%xmm9,%xmm8
+	pshufd	$0x4e,%xmm8,%xmm9
+	por	%xmm9,%xmm8
+.byte	102,76,15,126,195
+
+	movq	%r8,128(%rsp)
+	movq	%rdi,128+8(%rsp)
+	movq	%rcx,128+16(%rsp)
 
-	shlq	$32,%rax
-	orq	%rax,%rbx
 	movq	(%rsi),%rax
 	movq	8(%rsi),%rcx
-	leaq	128(%rdx,%r9,4),%rbp
 	mulq	%rbx
 	movq	%rax,(%rsp)
 	movq	%rcx,%rax
 	movq	%rdx,%r8
 
 	mulq	%rbx
-	movd	(%rbp),%xmm4
 	addq	%rax,%r8
 	movq	16(%rsi),%rax
 	movq	%rdx,%r9
 	adcq	$0,%r9
 
 	mulq	%rbx
-	movd	64(%rbp),%xmm5
 	addq	%rax,%r9
 	movq	24(%rsi),%rax
 	movq	%rdx,%r10
 	adcq	$0,%r10
 
 	mulq	%rbx
-	pslldq	$4,%xmm5
 	addq	%rax,%r10
 	movq	32(%rsi),%rax
 	movq	%rdx,%r11
 	adcq	$0,%r11
 
 	mulq	%rbx
-	por	%xmm5,%xmm4
 	addq	%rax,%r11
 	movq	40(%rsi),%rax
 	movq	%rdx,%r12
@@ -520,14 +566,12 @@ rsaz_512_mul_gather4:
 	adcq	$0,%r13
 
 	mulq	%rbx
-	leaq	128(%rbp),%rbp
 	addq	%rax,%r13
 	movq	56(%rsi),%rax
 	movq	%rdx,%r14
 	adcq	$0,%r14
 
 	mulq	%rbx
-.byte	102,72,15,126,227
 	addq	%rax,%r14
 	movq	(%rsi),%rax
 	movq	%rdx,%r15
@@ -539,6 +583,35 @@ rsaz_512_mul_gather4:
 
 .align	32
 .Loop_mul_gather:
+	movdqa	0(%rbp),%xmm8
+	movdqa	16(%rbp),%xmm9
+	movdqa	32(%rbp),%xmm10
+	movdqa	48(%rbp),%xmm11
+	pand	%xmm0,%xmm8
+	movdqa	64(%rbp),%xmm12
+	pand	%xmm1,%xmm9
+	movdqa	80(%rbp),%xmm13
+	pand	%xmm2,%xmm10
+	movdqa	96(%rbp),%xmm14
+	pand	%xmm3,%xmm11
+	movdqa	112(%rbp),%xmm15
+	leaq	128(%rbp),%rbp
+	pand	%xmm4,%xmm12
+	pand	%xmm5,%xmm13
+	pand	%xmm6,%xmm14
+	pand	%xmm7,%xmm15
+	por	%xmm10,%xmm8
+	por	%xmm11,%xmm9
+	por	%xmm12,%xmm8
+	por	%xmm13,%xmm9
+	por	%xmm14,%xmm8
+	por	%xmm15,%xmm9
+
+	por	%xmm9,%xmm8
+	pshufd	$0x4e,%xmm8,%xmm9
+	por	%xmm9,%xmm8
+.byte	102,76,15,126,195
+
 	mulq	%rbx
 	addq	%rax,%r8
 	movq	8(%rsi),%rax
@@ -547,7 +620,6 @@ rsaz_512_mul_gather4:
 	adcq	$0,%r8
 
 	mulq	%rbx
-	movd	(%rbp),%xmm4
 	addq	%rax,%r9
 	movq	16(%rsi),%rax
 	adcq	$0,%rdx
@@ -556,7 +628,6 @@ rsaz_512_mul_gather4:
 	adcq	$0,%r9
 
 	mulq	%rbx
-	movd	64(%rbp),%xmm5
 	addq	%rax,%r10
 	movq	24(%rsi),%rax
 	adcq	$0,%rdx
@@ -565,7 +636,6 @@ rsaz_512_mul_gather4:
 	adcq	$0,%r10
 
 	mulq	%rbx
-	pslldq	$4,%xmm5
 	addq	%rax,%r11
 	movq	32(%rsi),%rax
 	adcq	$0,%rdx
@@ -574,7 +644,6 @@ rsaz_512_mul_gather4:
 	adcq	$0,%r11
 
 	mulq	%rbx
-	por	%xmm5,%xmm4
 	addq	%rax,%r12
 	movq	40(%rsi),%rax
 	adcq	$0,%rdx
@@ -599,7 +668,6 @@ rsaz_512_mul_gather4:
 	adcq	$0,%r14
 
 	mulq	%rbx
-.byte	102,72,15,126,227
 	addq	%rax,%r15
 	movq	(%rsi),%rax
 	adcq	$0,%rdx
@@ -607,7 +675,6 @@ rsaz_512_mul_gather4:
 	movq	%rdx,%r15
 	adcq	$0,%r15
 
-	leaq	128(%rbp),%rbp
 	leaq	8(%rdi),%rdi
 
 	decl	%ecx
@@ -622,8 +689,8 @@ rsaz_512_mul_gather4:
 	movq	%r14,48(%rdi)
 	movq	%r15,56(%rdi)
 
-.byte	102,72,15,126,199
-.byte	102,72,15,126,205
+	movq	128+8(%rsp),%rdi
+	movq	128+16(%rsp),%rbp
 
 	movq	(%rsp),%r8
 	movq	8(%rsp),%r9
@@ -673,7 +740,7 @@ rsaz_512_mul_scatter4:
 	movl	%r9d,%r9d
 	subq	$128+24,%rsp
 .Lmul_scatter4_body:
-	leaq	(%r8,%r9,4),%r8
+	leaq	(%r8,%r9,8),%r8
 .byte	102,72,15,110,199
 .byte	102,72,15,110,202
 .byte	102,73,15,110,208
@@ -709,30 +776,14 @@ rsaz_512_mul_scatter4:
 
 	call	__rsaz_512_subtract
 
-	movl	%r8d,0(%rsi)
-	shrq	$32,%r8
-	movl	%r9d,128(%rsi)
-	shrq	$32,%r9
-	movl	%r10d,256(%rsi)
-	shrq	$32,%r10
-	movl	%r11d,384(%rsi)
-	shrq	$32,%r11
-	movl	%r12d,512(%rsi)
-	shrq	$32,%r12
-	movl	%r13d,640(%rsi)
-	shrq	$32,%r13
-	movl	%r14d,768(%rsi)
-	shrq	$32,%r14
-	movl	%r15d,896(%rsi)
-	shrq	$32,%r15
-	movl	%r8d,64(%rsi)
-	movl	%r9d,192(%rsi)
-	movl	%r10d,320(%rsi)
-	movl	%r11d,448(%rsi)
-	movl	%r12d,576(%rsi)
-	movl	%r13d,704(%rsi)
-	movl	%r14d,832(%rsi)
-	movl	%r15d,960(%rsi)
+	movq	%r8,0(%rsi)
+	movq	%r9,128(%rsi)
+	movq	%r10,256(%rsi)
+	movq	%r11,384(%rsi)
+	movq	%r12,512(%rsi)
+	movq	%r13,640(%rsi)
+	movq	%r14,768(%rsi)
+	movq	%r15,896(%rsi)
 
 	leaq	128+24+48(%rsp),%rax
 	movq	-48(%rax),%r15
@@ -1087,16 +1138,14 @@ __rsaz_512_mul:
 .type	rsaz_512_scatter4,@function
 .align	16
 rsaz_512_scatter4:
-	leaq	(%rdi,%rdx,4),%rdi
+	leaq	(%rdi,%rdx,8),%rdi
 	movl	$8,%r9d
 	jmp	.Loop_scatter
 .align	16
 .Loop_scatter:
 	movq	(%rsi),%rax
 	leaq	8(%rsi),%rsi
-	movl	%eax,(%rdi)
-	shrq	$32,%rax
-	movl	%eax,64(%rdi)
+	movq	%rax,(%rdi)
 	leaq	128(%rdi),%rdi
 	decl	%r9d
 	jnz	.Loop_scatter
@@ -1108,20 +1157,73 @@ rsaz_512_scatter4:
 .type	rsaz_512_gather4,@function
 .align	16
 rsaz_512_gather4:
-	leaq	(%rsi,%rdx,4),%rsi
+	movd	%edx,%xmm8
+	movdqa	.Linc+16(%rip),%xmm1
+	movdqa	.Linc(%rip),%xmm0
+
+	pshufd	$0,%xmm8,%xmm8
+	movdqa	%xmm1,%xmm7
+	movdqa	%xmm1,%xmm2
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm8,%xmm0
+	movdqa	%xmm7,%xmm3
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm8,%xmm1
+	movdqa	%xmm7,%xmm4
+	paddd	%xmm2,%xmm3
+	pcmpeqd	%xmm8,%xmm2
+	movdqa	%xmm7,%xmm5
+	paddd	%xmm3,%xmm4
+	pcmpeqd	%xmm8,%xmm3
+	movdqa	%xmm7,%xmm6
+	paddd	%xmm4,%xmm5
+	pcmpeqd	%xmm8,%xmm4
+	paddd	%xmm5,%xmm6
+	pcmpeqd	%xmm8,%xmm5
+	paddd	%xmm6,%xmm7
+	pcmpeqd	%xmm8,%xmm6
+	pcmpeqd	%xmm8,%xmm7
 	movl	$8,%r9d
 	jmp	.Loop_gather
 .align	16
 .Loop_gather:
-	movl	(%rsi),%eax
-	movl	64(%rsi),%r8d
+	movdqa	0(%rsi),%xmm8
+	movdqa	16(%rsi),%xmm9
+	movdqa	32(%rsi),%xmm10
+	movdqa	48(%rsi),%xmm11
+	pand	%xmm0,%xmm8
+	movdqa	64(%rsi),%xmm12
+	pand	%xmm1,%xmm9
+	movdqa	80(%rsi),%xmm13
+	pand	%xmm2,%xmm10
+	movdqa	96(%rsi),%xmm14
+	pand	%xmm3,%xmm11
+	movdqa	112(%rsi),%xmm15
 	leaq	128(%rsi),%rsi
-	shlq	$32,%r8
-	orq	%r8,%rax
-	movq	%rax,(%rdi)
+	pand	%xmm4,%xmm12
+	pand	%xmm5,%xmm13
+	pand	%xmm6,%xmm14
+	pand	%xmm7,%xmm15
+	por	%xmm10,%xmm8
+	por	%xmm11,%xmm9
+	por	%xmm12,%xmm8
+	por	%xmm13,%xmm9
+	por	%xmm14,%xmm8
+	por	%xmm15,%xmm9
+
+	por	%xmm9,%xmm8
+	pshufd	$0x4e,%xmm8,%xmm9
+	por	%xmm9,%xmm8
+	movq	%xmm8,(%rdi)
 	leaq	8(%rdi),%rdi
 	decl	%r9d
 	jnz	.Loop_gather
 	.byte	0xf3,0xc3
+.LSEH_end_rsaz_512_gather4:
 .size	rsaz_512_gather4,.-rsaz_512_gather4
+
+.align	64
+.Linc:
+.long	0,0, 1,1
+.long	2,2, 2,2
 #endif
diff --git a/packager/third_party/boringssl/linux-x86_64/crypto/bn/x86_64-mont.S b/packager/third_party/boringssl/linux-x86_64/crypto/bn/x86_64-mont.S
index 4d401c6743..83926ad789 100644
--- a/packager/third_party/boringssl/linux-x86_64/crypto/bn/x86_64-mont.S
+++ b/packager/third_party/boringssl/linux-x86_64/crypto/bn/x86_64-mont.S
@@ -636,20 +636,20 @@ bn_sqr8x_mont:
 
 
 
-	leaq	-64(%rsp,%r9,4),%r11
+	leaq	-64(%rsp,%r9,2),%r11
 	movq	(%r8),%r8
 	subq	%rsi,%r11
 	andq	$4095,%r11
 	cmpq	%r11,%r10
 	jb	.Lsqr8x_sp_alt
 	subq	%r11,%rsp
-	leaq	-64(%rsp,%r9,4),%rsp
+	leaq	-64(%rsp,%r9,2),%rsp
 	jmp	.Lsqr8x_sp_done
 
 .align	32
 .Lsqr8x_sp_alt:
-	leaq	4096-64(,%r9,4),%r10
-	leaq	-64(%rsp,%r9,4),%rsp
+	leaq	4096-64(,%r9,2),%r10
+	leaq	-64(%rsp,%r9,2),%rsp
 	subq	%r10,%r11
 	movq	$0,%r10
 	cmovcq	%r10,%r11
@@ -659,58 +659,80 @@ bn_sqr8x_mont:
 	movq	%r9,%r10
 	negq	%r9
 
-	leaq	64(%rsp,%r9,2),%r11
 	movq	%r8,32(%rsp)
 	movq	%rax,40(%rsp)
 .Lsqr8x_body:
 
-	movq	%r9,%rbp
-.byte	102,73,15,110,211
-	shrq	$3+2,%rbp
-	movl	OPENSSL_ia32cap_P+8(%rip),%eax
-	jmp	.Lsqr8x_copy_n
-
-.align	32
-.Lsqr8x_copy_n:
-	movq	0(%rcx),%xmm0
-	movq	8(%rcx),%xmm1
-	movq	16(%rcx),%xmm3
-	movq	24(%rcx),%xmm4
-	leaq	32(%rcx),%rcx
-	movdqa	%xmm0,0(%r11)
-	movdqa	%xmm1,16(%r11)
-	movdqa	%xmm3,32(%r11)
-	movdqa	%xmm4,48(%r11)
-	leaq	64(%r11),%r11
-	decq	%rbp
-	jnz	.Lsqr8x_copy_n
-
+.byte	102,72,15,110,209
 	pxor	%xmm0,%xmm0
 .byte	102,72,15,110,207
 .byte	102,73,15,110,218
 	call	bn_sqr8x_internal
 
-	pxor	%xmm0,%xmm0
-	leaq	48(%rsp),%rax
-	leaq	64(%rsp,%r9,2),%rdx
-	shrq	$3+2,%r9
-	movq	40(%rsp),%rsi
-	jmp	.Lsqr8x_zero
+
+
+
+	leaq	(%rdi,%r9,1),%rbx
+	movq	%r9,%rcx
+	movq	%r9,%rdx
+.byte	102,72,15,126,207
+	sarq	$3+2,%rcx
+	jmp	.Lsqr8x_sub
 
 .align	32
-.Lsqr8x_zero:
-	movdqa	%xmm0,0(%rax)
-	movdqa	%xmm0,16(%rax)
-	movdqa	%xmm0,32(%rax)
-	movdqa	%xmm0,48(%rax)
-	leaq	64(%rax),%rax
-	movdqa	%xmm0,0(%rdx)
-	movdqa	%xmm0,16(%rdx)
-	movdqa	%xmm0,32(%rdx)
-	movdqa	%xmm0,48(%rdx)
-	leaq	64(%rdx),%rdx
-	decq	%r9
-	jnz	.Lsqr8x_zero
+.Lsqr8x_sub:
+	movq	0(%rbx),%r12
+	movq	8(%rbx),%r13
+	movq	16(%rbx),%r14
+	movq	24(%rbx),%r15
+	leaq	32(%rbx),%rbx
+	sbbq	0(%rbp),%r12
+	sbbq	8(%rbp),%r13
+	sbbq	16(%rbp),%r14
+	sbbq	24(%rbp),%r15
+	leaq	32(%rbp),%rbp
+	movq	%r12,0(%rdi)
+	movq	%r13,8(%rdi)
+	movq	%r14,16(%rdi)
+	movq	%r15,24(%rdi)
+	leaq	32(%rdi),%rdi
+	incq	%rcx
+	jnz	.Lsqr8x_sub
+
+	sbbq	$0,%rax
+	leaq	(%rbx,%r9,1),%rbx
+	leaq	(%rdi,%r9,1),%rdi
+
+.byte	102,72,15,110,200
+	pxor	%xmm0,%xmm0
+	pshufd	$0,%xmm1,%xmm1
+	movq	40(%rsp),%rsi
+	jmp	.Lsqr8x_cond_copy
+
+.align	32
+.Lsqr8x_cond_copy:
+	movdqa	0(%rbx),%xmm2
+	movdqa	16(%rbx),%xmm3
+	leaq	32(%rbx),%rbx
+	movdqu	0(%rdi),%xmm4
+	movdqu	16(%rdi),%xmm5
+	leaq	32(%rdi),%rdi
+	movdqa	%xmm0,-32(%rbx)
+	movdqa	%xmm0,-16(%rbx)
+	movdqa	%xmm0,-32(%rbx,%rdx,1)
+	movdqa	%xmm0,-16(%rbx,%rdx,1)
+	pcmpeqd	%xmm1,%xmm0
+	pand	%xmm1,%xmm2
+	pand	%xmm1,%xmm3
+	pand	%xmm0,%xmm4
+	pand	%xmm0,%xmm5
+	pxor	%xmm0,%xmm0
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+	movdqu	%xmm4,-32(%rdi)
+	movdqu	%xmm5,-16(%rdi)
+	addq	$32,%r9
+	jnz	.Lsqr8x_cond_copy
 
 	movq	$1,%rax
 	movq	-48(%rsi),%r15
diff --git a/packager/third_party/boringssl/linux-x86_64/crypto/bn/x86_64-mont5.S b/packager/third_party/boringssl/linux-x86_64/crypto/bn/x86_64-mont5.S
index 02edc69b36..554df1ffac 100644
--- a/packager/third_party/boringssl/linux-x86_64/crypto/bn/x86_64-mont5.S
+++ b/packager/third_party/boringssl/linux-x86_64/crypto/bn/x86_64-mont5.S
@@ -17,46 +17,151 @@ bn_mul_mont_gather5:
 .Lmul_enter:
 	movl	%r9d,%r9d
 	movq	%rsp,%rax
-	movl	8(%rsp),%r10d
+	movd	8(%rsp),%xmm5
+	leaq	.Linc(%rip),%r10
 	pushq	%rbx
 	pushq	%rbp
 	pushq	%r12
 	pushq	%r13
 	pushq	%r14
 	pushq	%r15
+
 	leaq	2(%r9),%r11
 	negq	%r11
-	leaq	(%rsp,%r11,8),%rsp
+	leaq	-264(%rsp,%r11,8),%rsp
 	andq	$-1024,%rsp
 
 	movq	%rax,8(%rsp,%r9,8)
 .Lmul_body:
-	movq	%rdx,%r12
-	movq	%r10,%r11
-	shrq	$3,%r10
-	andq	$7,%r11
-	notq	%r10
-	leaq	.Lmagic_masks(%rip),%rax
-	andq	$3,%r10
-	leaq	96(%r12,%r11,8),%r12
-	movq	0(%rax,%r10,8),%xmm4
-	movq	8(%rax,%r10,8),%xmm5
-	movq	16(%rax,%r10,8),%xmm6
-	movq	24(%rax,%r10,8),%xmm7
+	leaq	128(%rdx),%r12
+	movdqa	0(%r10),%xmm0
+	movdqa	16(%r10),%xmm1
+	leaq	24-112(%rsp,%r9,8),%r10
+	andq	$-16,%r10
 
-	movq	-96(%r12),%xmm0
-	movq	-32(%r12),%xmm1
-	pand	%xmm4,%xmm0
-	movq	32(%r12),%xmm2
-	pand	%xmm5,%xmm1
-	movq	96(%r12),%xmm3
-	pand	%xmm6,%xmm2
-	por	%xmm1,%xmm0
-	pand	%xmm7,%xmm3
+	pshufd	$0,%xmm5,%xmm5
+	movdqa	%xmm1,%xmm4
+	movdqa	%xmm1,%xmm2
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0
+.byte	0x67
+	movdqa	%xmm4,%xmm3
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1
+	movdqa	%xmm0,112(%r10)
+	movdqa	%xmm4,%xmm0
+
+	paddd	%xmm2,%xmm3
+	pcmpeqd	%xmm5,%xmm2
+	movdqa	%xmm1,128(%r10)
+	movdqa	%xmm4,%xmm1
+
+	paddd	%xmm3,%xmm0
+	pcmpeqd	%xmm5,%xmm3
+	movdqa	%xmm2,144(%r10)
+	movdqa	%xmm4,%xmm2
+
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0
+	movdqa	%xmm3,160(%r10)
+	movdqa	%xmm4,%xmm3
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1
+	movdqa	%xmm0,176(%r10)
+	movdqa	%xmm4,%xmm0
+
+	paddd	%xmm2,%xmm3
+	pcmpeqd	%xmm5,%xmm2
+	movdqa	%xmm1,192(%r10)
+	movdqa	%xmm4,%xmm1
+
+	paddd	%xmm3,%xmm0
+	pcmpeqd	%xmm5,%xmm3
+	movdqa	%xmm2,208(%r10)
+	movdqa	%xmm4,%xmm2
+
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0
+	movdqa	%xmm3,224(%r10)
+	movdqa	%xmm4,%xmm3
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1
+	movdqa	%xmm0,240(%r10)
+	movdqa	%xmm4,%xmm0
+
+	paddd	%xmm2,%xmm3
+	pcmpeqd	%xmm5,%xmm2
+	movdqa	%xmm1,256(%r10)
+	movdqa	%xmm4,%xmm1
+
+	paddd	%xmm3,%xmm0
+	pcmpeqd	%xmm5,%xmm3
+	movdqa	%xmm2,272(%r10)
+	movdqa	%xmm4,%xmm2
+
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0
+	movdqa	%xmm3,288(%r10)
+	movdqa	%xmm4,%xmm3
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1
+	movdqa	%xmm0,304(%r10)
+
+	paddd	%xmm2,%xmm3
+.byte	0x67
+	pcmpeqd	%xmm5,%xmm2
+	movdqa	%xmm1,320(%r10)
+
+	pcmpeqd	%xmm5,%xmm3
+	movdqa	%xmm2,336(%r10)
+	pand	64(%r12),%xmm0
+
+	pand	80(%r12),%xmm1
+	pand	96(%r12),%xmm2
+	movdqa	%xmm3,352(%r10)
+	pand	112(%r12),%xmm3
 	por	%xmm2,%xmm0
+	por	%xmm3,%xmm1
+	movdqa	-128(%r12),%xmm4
+	movdqa	-112(%r12),%xmm5
+	movdqa	-96(%r12),%xmm2
+	pand	112(%r10),%xmm4
+	movdqa	-80(%r12),%xmm3
+	pand	128(%r10),%xmm5
+	por	%xmm4,%xmm0
+	pand	144(%r10),%xmm2
+	por	%xmm5,%xmm1
+	pand	160(%r10),%xmm3
+	por	%xmm2,%xmm0
+	por	%xmm3,%xmm1
+	movdqa	-64(%r12),%xmm4
+	movdqa	-48(%r12),%xmm5
+	movdqa	-32(%r12),%xmm2
+	pand	176(%r10),%xmm4
+	movdqa	-16(%r12),%xmm3
+	pand	192(%r10),%xmm5
+	por	%xmm4,%xmm0
+	pand	208(%r10),%xmm2
+	por	%xmm5,%xmm1
+	pand	224(%r10),%xmm3
+	por	%xmm2,%xmm0
+	por	%xmm3,%xmm1
+	movdqa	0(%r12),%xmm4
+	movdqa	16(%r12),%xmm5
+	movdqa	32(%r12),%xmm2
+	pand	240(%r10),%xmm4
+	movdqa	48(%r12),%xmm3
+	pand	256(%r10),%xmm5
+	por	%xmm4,%xmm0
+	pand	272(%r10),%xmm2
+	por	%xmm5,%xmm1
+	pand	288(%r10),%xmm3
+	por	%xmm2,%xmm0
+	por	%xmm3,%xmm1
+	por	%xmm1,%xmm0
+	pshufd	$0x4e,%xmm0,%xmm1
+	por	%xmm1,%xmm0
 	leaq	256(%r12),%r12
-	por	%xmm3,%xmm0
-
 .byte	102,72,15,126,195
 
 	movq	(%r8),%r8
@@ -65,29 +170,14 @@ bn_mul_mont_gather5:
 	xorq	%r14,%r14
 	xorq	%r15,%r15
 
-	movq	-96(%r12),%xmm0
-	movq	-32(%r12),%xmm1
-	pand	%xmm4,%xmm0
-	movq	32(%r12),%xmm2
-	pand	%xmm5,%xmm1
-
 	movq	%r8,%rbp
 	mulq	%rbx
 	movq	%rax,%r10
 	movq	(%rcx),%rax
 
-	movq	96(%r12),%xmm3
-	pand	%xmm6,%xmm2
-	por	%xmm1,%xmm0
-	pand	%xmm7,%xmm3
-
 	imulq	%r10,%rbp
 	movq	%rdx,%r11
 
-	por	%xmm2,%xmm0
-	leaq	256(%r12),%r12
-	por	%xmm3,%xmm0
-
 	mulq	%rbp
 	addq	%rax,%r10
 	movq	8(%rsi),%rax
@@ -120,14 +210,12 @@ bn_mul_mont_gather5:
 	cmpq	%r9,%r15
 	jne	.L1st
 
-.byte	102,72,15,126,195
 
 	addq	%rax,%r13
-	movq	(%rsi),%rax
 	adcq	$0,%rdx
 	addq	%r11,%r13
 	adcq	$0,%rdx
-	movq	%r13,-16(%rsp,%r15,8)
+	movq	%r13,-16(%rsp,%r9,8)
 	movq	%rdx,%r13
 	movq	%r10,%r11
 
@@ -141,33 +229,78 @@ bn_mul_mont_gather5:
 	jmp	.Louter
 .align	16
 .Louter:
+	leaq	24+128(%rsp,%r9,8),%rdx
+	andq	$-16,%rdx
+	pxor	%xmm4,%xmm4
+	pxor	%xmm5,%xmm5
+	movdqa	-128(%r12),%xmm0
+	movdqa	-112(%r12),%xmm1
+	movdqa	-96(%r12),%xmm2
+	movdqa	-80(%r12),%xmm3
+	pand	-128(%rdx),%xmm0
+	pand	-112(%rdx),%xmm1
+	por	%xmm0,%xmm4
+	pand	-96(%rdx),%xmm2
+	por	%xmm1,%xmm5
+	pand	-80(%rdx),%xmm3
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+	movdqa	-64(%r12),%xmm0
+	movdqa	-48(%r12),%xmm1
+	movdqa	-32(%r12),%xmm2
+	movdqa	-16(%r12),%xmm3
+	pand	-64(%rdx),%xmm0
+	pand	-48(%rdx),%xmm1
+	por	%xmm0,%xmm4
+	pand	-32(%rdx),%xmm2
+	por	%xmm1,%xmm5
+	pand	-16(%rdx),%xmm3
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+	movdqa	0(%r12),%xmm0
+	movdqa	16(%r12),%xmm1
+	movdqa	32(%r12),%xmm2
+	movdqa	48(%r12),%xmm3
+	pand	0(%rdx),%xmm0
+	pand	16(%rdx),%xmm1
+	por	%xmm0,%xmm4
+	pand	32(%rdx),%xmm2
+	por	%xmm1,%xmm5
+	pand	48(%rdx),%xmm3
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+	movdqa	64(%r12),%xmm0
+	movdqa	80(%r12),%xmm1
+	movdqa	96(%r12),%xmm2
+	movdqa	112(%r12),%xmm3
+	pand	64(%rdx),%xmm0
+	pand	80(%rdx),%xmm1
+	por	%xmm0,%xmm4
+	pand	96(%rdx),%xmm2
+	por	%xmm1,%xmm5
+	pand	112(%rdx),%xmm3
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+	por	%xmm5,%xmm4
+	pshufd	$0x4e,%xmm4,%xmm0
+	por	%xmm4,%xmm0
+	leaq	256(%r12),%r12
+
+	movq	(%rsi),%rax
+.byte	102,72,15,126,195
+
 	xorq	%r15,%r15
 	movq	%r8,%rbp
 	movq	(%rsp),%r10
 
-	movq	-96(%r12),%xmm0
-	movq	-32(%r12),%xmm1
-	pand	%xmm4,%xmm0
-	movq	32(%r12),%xmm2
-	pand	%xmm5,%xmm1
-
 	mulq	%rbx
 	addq	%rax,%r10
 	movq	(%rcx),%rax
 	adcq	$0,%rdx
 
-	movq	96(%r12),%xmm3
-	pand	%xmm6,%xmm2
-	por	%xmm1,%xmm0
-	pand	%xmm7,%xmm3
-
 	imulq	%r10,%rbp
 	movq	%rdx,%r11
 
-	por	%xmm2,%xmm0
-	leaq	256(%r12),%r12
-	por	%xmm3,%xmm0
-
 	mulq	%rbp
 	addq	%rax,%r10
 	movq	8(%rsi),%rax
@@ -203,15 +336,12 @@ bn_mul_mont_gather5:
 	cmpq	%r9,%r15
 	jne	.Linner
 
-.byte	102,72,15,126,195
-
 	addq	%rax,%r13
-	movq	(%rsi),%rax
 	adcq	$0,%rdx
 	addq	%r10,%r13
-	movq	(%rsp,%r15,8),%r10
+	movq	(%rsp,%r9,8),%r10
 	adcq	$0,%rdx
-	movq	%r13,-16(%rsp,%r15,8)
+	movq	%r13,-16(%rsp,%r9,8)
 	movq	%rdx,%r13
 
 	xorq	%rdx,%rdx
@@ -257,6 +387,7 @@ bn_mul_mont_gather5:
 
 	movq	8(%rsp,%r9,8),%rsi
 	movq	$1,%rax
+
 	movq	-48(%rsi),%r15
 	movq	-40(%rsi),%r14
 	movq	-32(%rsi),%r13
@@ -279,10 +410,10 @@ bn_mul4x_mont_gather5:
 	pushq	%r13
 	pushq	%r14
 	pushq	%r15
+
 .byte	0x67
-	movl	%r9d,%r10d
 	shll	$3,%r9d
-	shll	$3+2,%r10d
+	leaq	(%r9,%r9,2),%r10
 	negq	%r9
 
 
@@ -292,19 +423,21 @@ bn_mul4x_mont_gather5:
 
 
 
-	leaq	-64(%rsp,%r9,2),%r11
-	subq	%rsi,%r11
+
+
+	leaq	-320(%rsp,%r9,2),%r11
+	subq	%rdi,%r11
 	andq	$4095,%r11
 	cmpq	%r11,%r10
 	jb	.Lmul4xsp_alt
 	subq	%r11,%rsp
-	leaq	-64(%rsp,%r9,2),%rsp
+	leaq	-320(%rsp,%r9,2),%rsp
 	jmp	.Lmul4xsp_done
 
 .align	32
 .Lmul4xsp_alt:
-	leaq	4096-64(,%r9,2),%r10
-	leaq	-64(%rsp,%r9,2),%rsp
+	leaq	4096-320(,%r9,2),%r10
+	leaq	-320(%rsp,%r9,2),%rsp
 	subq	%r10,%r11
 	movq	$0,%r10
 	cmovcq	%r10,%r11
@@ -320,6 +453,7 @@ bn_mul4x_mont_gather5:
 
 	movq	40(%rsp),%rsi
 	movq	$1,%rax
+
 	movq	-48(%rsi),%r15
 	movq	-40(%rsi),%r14
 	movq	-32(%rsi),%r13
@@ -335,47 +469,141 @@ bn_mul4x_mont_gather5:
 .align	32
 mul4x_internal:
 	shlq	$5,%r9
-	movl	8(%rax),%r10d
-	leaq	256(%rdx,%r9,1),%r13
+	movd	8(%rax),%xmm5
+	leaq	.Linc(%rip),%rax
+	leaq	128(%rdx,%r9,1),%r13
 	shrq	$5,%r9
-	movq	%r10,%r11
-	shrq	$3,%r10
-	andq	$7,%r11
-	notq	%r10
-	leaq	.Lmagic_masks(%rip),%rax
-	andq	$3,%r10
-	leaq	96(%rdx,%r11,8),%r12
-	movq	0(%rax,%r10,8),%xmm4
-	movq	8(%rax,%r10,8),%xmm5
-	addq	$7,%r11
-	movq	16(%rax,%r10,8),%xmm6
-	movq	24(%rax,%r10,8),%xmm7
-	andq	$7,%r11
+	movdqa	0(%rax),%xmm0
+	movdqa	16(%rax),%xmm1
+	leaq	88-112(%rsp,%r9,1),%r10
+	leaq	128(%rdx),%r12
 
-	movq	-96(%r12),%xmm0
-	leaq	256(%r12),%r14
-	movq	-32(%r12),%xmm1
-	pand	%xmm4,%xmm0
-	movq	32(%r12),%xmm2
-	pand	%xmm5,%xmm1
-	movq	96(%r12),%xmm3
-	pand	%xmm6,%xmm2
+	pshufd	$0,%xmm5,%xmm5
+	movdqa	%xmm1,%xmm4
+.byte	0x67,0x67
+	movdqa	%xmm1,%xmm2
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0
 .byte	0x67
-	por	%xmm1,%xmm0
-	movq	-96(%r14),%xmm1
-.byte	0x67
-	pand	%xmm7,%xmm3
+	movdqa	%xmm4,%xmm3
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1
+	movdqa	%xmm0,112(%r10)
+	movdqa	%xmm4,%xmm0
+
+	paddd	%xmm2,%xmm3
+	pcmpeqd	%xmm5,%xmm2
+	movdqa	%xmm1,128(%r10)
+	movdqa	%xmm4,%xmm1
+
+	paddd	%xmm3,%xmm0
+	pcmpeqd	%xmm5,%xmm3
+	movdqa	%xmm2,144(%r10)
+	movdqa	%xmm4,%xmm2
+
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0
+	movdqa	%xmm3,160(%r10)
+	movdqa	%xmm4,%xmm3
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1
+	movdqa	%xmm0,176(%r10)
+	movdqa	%xmm4,%xmm0
+
+	paddd	%xmm2,%xmm3
+	pcmpeqd	%xmm5,%xmm2
+	movdqa	%xmm1,192(%r10)
+	movdqa	%xmm4,%xmm1
+
+	paddd	%xmm3,%xmm0
+	pcmpeqd	%xmm5,%xmm3
+	movdqa	%xmm2,208(%r10)
+	movdqa	%xmm4,%xmm2
+
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0
+	movdqa	%xmm3,224(%r10)
+	movdqa	%xmm4,%xmm3
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1
+	movdqa	%xmm0,240(%r10)
+	movdqa	%xmm4,%xmm0
+
+	paddd	%xmm2,%xmm3
+	pcmpeqd	%xmm5,%xmm2
+	movdqa	%xmm1,256(%r10)
+	movdqa	%xmm4,%xmm1
+
+	paddd	%xmm3,%xmm0
+	pcmpeqd	%xmm5,%xmm3
+	movdqa	%xmm2,272(%r10)
+	movdqa	%xmm4,%xmm2
+
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0
+	movdqa	%xmm3,288(%r10)
+	movdqa	%xmm4,%xmm3
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1
+	movdqa	%xmm0,304(%r10)
+
+	paddd	%xmm2,%xmm3
 .byte	0x67
+	pcmpeqd	%xmm5,%xmm2
+	movdqa	%xmm1,320(%r10)
+
+	pcmpeqd	%xmm5,%xmm3
+	movdqa	%xmm2,336(%r10)
+	pand	64(%r12),%xmm0
+
+	pand	80(%r12),%xmm1
+	pand	96(%r12),%xmm2
+	movdqa	%xmm3,352(%r10)
+	pand	112(%r12),%xmm3
 	por	%xmm2,%xmm0
-	movq	-32(%r14),%xmm2
-.byte	0x67
-	pand	%xmm4,%xmm1
-.byte	0x67
-	por	%xmm3,%xmm0
-	movq	32(%r14),%xmm3
-
+	por	%xmm3,%xmm1
+	movdqa	-128(%r12),%xmm4
+	movdqa	-112(%r12),%xmm5
+	movdqa	-96(%r12),%xmm2
+	pand	112(%r10),%xmm4
+	movdqa	-80(%r12),%xmm3
+	pand	128(%r10),%xmm5
+	por	%xmm4,%xmm0
+	pand	144(%r10),%xmm2
+	por	%xmm5,%xmm1
+	pand	160(%r10),%xmm3
+	por	%xmm2,%xmm0
+	por	%xmm3,%xmm1
+	movdqa	-64(%r12),%xmm4
+	movdqa	-48(%r12),%xmm5
+	movdqa	-32(%r12),%xmm2
+	pand	176(%r10),%xmm4
+	movdqa	-16(%r12),%xmm3
+	pand	192(%r10),%xmm5
+	por	%xmm4,%xmm0
+	pand	208(%r10),%xmm2
+	por	%xmm5,%xmm1
+	pand	224(%r10),%xmm3
+	por	%xmm2,%xmm0
+	por	%xmm3,%xmm1
+	movdqa	0(%r12),%xmm4
+	movdqa	16(%r12),%xmm5
+	movdqa	32(%r12),%xmm2
+	pand	240(%r10),%xmm4
+	movdqa	48(%r12),%xmm3
+	pand	256(%r10),%xmm5
+	por	%xmm4,%xmm0
+	pand	272(%r10),%xmm2
+	por	%xmm5,%xmm1
+	pand	288(%r10),%xmm3
+	por	%xmm2,%xmm0
+	por	%xmm3,%xmm1
+	por	%xmm1,%xmm0
+	pshufd	$0x4e,%xmm0,%xmm1
+	por	%xmm1,%xmm0
+	leaq	256(%r12),%r12
 .byte	102,72,15,126,195
-	movq	96(%r14),%xmm0
+
 	movq	%r13,16+8(%rsp)
 	movq	%rdi,56+8(%rsp)
 
@@ -389,26 +617,10 @@ mul4x_internal:
 	movq	%rax,%r10
 	movq	(%rcx),%rax
 
-	pand	%xmm5,%xmm2
-	pand	%xmm6,%xmm3
-	por	%xmm2,%xmm1
-
 	imulq	%r10,%rbp
-
-
-
-
-
-
-
-	leaq	64+8(%rsp,%r11,8),%r14
+	leaq	64+8(%rsp),%r14
 	movq	%rdx,%r11
 
-	pand	%xmm7,%xmm0
-	por	%xmm3,%xmm1
-	leaq	512(%r12),%r12
-	por	%xmm1,%xmm0
-
 	mulq	%rbp
 	addq	%rax,%r10
 	movq	8(%rsi,%r9,1),%rax
@@ -417,7 +629,7 @@ mul4x_internal:
 
 	mulq	%rbx
 	addq	%rax,%r11
-	movq	16(%rcx),%rax
+	movq	8(%rcx),%rax
 	adcq	$0,%rdx
 	movq	%rdx,%r10
 
@@ -427,7 +639,7 @@ mul4x_internal:
 	adcq	$0,%rdx
 	addq	%r11,%rdi
 	leaq	32(%r9),%r15
-	leaq	64(%rcx),%rcx
+	leaq	32(%rcx),%rcx
 	adcq	$0,%rdx
 	movq	%rdi,(%r14)
 	movq	%rdx,%r13
@@ -437,7 +649,7 @@ mul4x_internal:
 .L1st4x:
 	mulq	%rbx
 	addq	%rax,%r10
-	movq	-32(%rcx),%rax
+	movq	-16(%rcx),%rax
 	leaq	32(%r14),%r14
 	adcq	$0,%rdx
 	movq	%rdx,%r11
@@ -453,7 +665,7 @@ mul4x_internal:
 
 	mulq	%rbx
 	addq	%rax,%r11
-	movq	-16(%rcx),%rax
+	movq	-8(%rcx),%rax
 	adcq	$0,%rdx
 	movq	%rdx,%r10
 
@@ -483,7 +695,7 @@ mul4x_internal:
 
 	mulq	%rbx
 	addq	%rax,%r11
-	movq	16(%rcx),%rax
+	movq	8(%rcx),%rax
 	adcq	$0,%rdx
 	movq	%rdx,%r10
 
@@ -492,7 +704,7 @@ mul4x_internal:
 	movq	16(%rsi,%r15,1),%rax
 	adcq	$0,%rdx
 	addq	%r11,%rdi
-	leaq	64(%rcx),%rcx
+	leaq	32(%rcx),%rcx
 	adcq	$0,%rdx
 	movq	%rdi,(%r14)
 	movq	%rdx,%r13
@@ -502,7 +714,7 @@ mul4x_internal:
 
 	mulq	%rbx
 	addq	%rax,%r10
-	movq	-32(%rcx),%rax
+	movq	-16(%rcx),%rax
 	leaq	32(%r14),%r14
 	adcq	$0,%rdx
 	movq	%rdx,%r11
@@ -518,7 +730,7 @@ mul4x_internal:
 
 	mulq	%rbx
 	addq	%rax,%r11
-	movq	-16(%rcx),%rax
+	movq	-8(%rcx),%rax
 	adcq	$0,%rdx
 	movq	%rdx,%r10
 
@@ -531,8 +743,7 @@ mul4x_internal:
 	movq	%rdi,-16(%r14)
 	movq	%rdx,%r13
 
-.byte	102,72,15,126,195
-	leaq	(%rcx,%r9,2),%rcx
+	leaq	(%rcx,%r9,1),%rcx
 
 	xorq	%rdi,%rdi
 	addq	%r10,%r13
@@ -543,6 +754,63 @@ mul4x_internal:
 
 .align	32
 .Louter4x:
+	leaq	16+128(%r14),%rdx
+	pxor	%xmm4,%xmm4
+	pxor	%xmm5,%xmm5
+	movdqa	-128(%r12),%xmm0
+	movdqa	-112(%r12),%xmm1
+	movdqa	-96(%r12),%xmm2
+	movdqa	-80(%r12),%xmm3
+	pand	-128(%rdx),%xmm0
+	pand	-112(%rdx),%xmm1
+	por	%xmm0,%xmm4
+	pand	-96(%rdx),%xmm2
+	por	%xmm1,%xmm5
+	pand	-80(%rdx),%xmm3
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+	movdqa	-64(%r12),%xmm0
+	movdqa	-48(%r12),%xmm1
+	movdqa	-32(%r12),%xmm2
+	movdqa	-16(%r12),%xmm3
+	pand	-64(%rdx),%xmm0
+	pand	-48(%rdx),%xmm1
+	por	%xmm0,%xmm4
+	pand	-32(%rdx),%xmm2
+	por	%xmm1,%xmm5
+	pand	-16(%rdx),%xmm3
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+	movdqa	0(%r12),%xmm0
+	movdqa	16(%r12),%xmm1
+	movdqa	32(%r12),%xmm2
+	movdqa	48(%r12),%xmm3
+	pand	0(%rdx),%xmm0
+	pand	16(%rdx),%xmm1
+	por	%xmm0,%xmm4
+	pand	32(%rdx),%xmm2
+	por	%xmm1,%xmm5
+	pand	48(%rdx),%xmm3
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+	movdqa	64(%r12),%xmm0
+	movdqa	80(%r12),%xmm1
+	movdqa	96(%r12),%xmm2
+	movdqa	112(%r12),%xmm3
+	pand	64(%rdx),%xmm0
+	pand	80(%rdx),%xmm1
+	por	%xmm0,%xmm4
+	pand	96(%rdx),%xmm2
+	por	%xmm1,%xmm5
+	pand	112(%rdx),%xmm3
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+	por	%xmm5,%xmm4
+	pshufd	$0x4e,%xmm4,%xmm0
+	por	%xmm4,%xmm0
+	leaq	256(%r12),%r12
+.byte	102,72,15,126,195
+
 	movq	(%r14,%r9,1),%r10
 	movq	%r8,%rbp
 	mulq	%rbx
@@ -550,25 +818,11 @@ mul4x_internal:
 	movq	(%rcx),%rax
 	adcq	$0,%rdx
 
-	movq	-96(%r12),%xmm0
-	movq	-32(%r12),%xmm1
-	pand	%xmm4,%xmm0
-	movq	32(%r12),%xmm2
-	pand	%xmm5,%xmm1
-	movq	96(%r12),%xmm3
-
 	imulq	%r10,%rbp
-.byte	0x67
 	movq	%rdx,%r11
 	movq	%rdi,(%r14)
 
-	pand	%xmm6,%xmm2
-	por	%xmm1,%xmm0
-	pand	%xmm7,%xmm3
-	por	%xmm2,%xmm0
 	leaq	(%r14,%r9,1),%r14
-	leaq	256(%r12),%r12
-	por	%xmm3,%xmm0
 
 	mulq	%rbp
 	addq	%rax,%r10
@@ -578,7 +832,7 @@ mul4x_internal:
 
 	mulq	%rbx
 	addq	%rax,%r11
-	movq	16(%rcx),%rax
+	movq	8(%rcx),%rax
 	adcq	$0,%rdx
 	addq	8(%r14),%r11
 	adcq	$0,%rdx
@@ -590,7 +844,7 @@ mul4x_internal:
 	adcq	$0,%rdx
 	addq	%r11,%rdi
 	leaq	32(%r9),%r15
-	leaq	64(%rcx),%rcx
+	leaq	32(%rcx),%rcx
 	adcq	$0,%rdx
 	movq	%rdx,%r13
 	jmp	.Linner4x
@@ -599,7 +853,7 @@ mul4x_internal:
 .Linner4x:
 	mulq	%rbx
 	addq	%rax,%r10
-	movq	-32(%rcx),%rax
+	movq	-16(%rcx),%rax
 	adcq	$0,%rdx
 	addq	16(%r14),%r10
 	leaq	32(%r14),%r14
@@ -617,7 +871,7 @@ mul4x_internal:
 
 	mulq	%rbx
 	addq	%rax,%r11
-	movq	-16(%rcx),%rax
+	movq	-8(%rcx),%rax
 	adcq	$0,%rdx
 	addq	-8(%r14),%r11
 	adcq	$0,%rdx
@@ -651,7 +905,7 @@ mul4x_internal:
 
 	mulq	%rbx
 	addq	%rax,%r11
-	movq	16(%rcx),%rax
+	movq	8(%rcx),%rax
 	adcq	$0,%rdx
 	addq	8(%r14),%r11
 	adcq	$0,%rdx
@@ -662,7 +916,7 @@ mul4x_internal:
 	movq	16(%rsi,%r15,1),%rax
 	adcq	$0,%rdx
 	addq	%r11,%rdi
-	leaq	64(%rcx),%rcx
+	leaq	32(%rcx),%rcx
 	adcq	$0,%rdx
 	movq	%r13,-8(%r14)
 	movq	%rdx,%r13
@@ -672,7 +926,7 @@ mul4x_internal:
 
 	mulq	%rbx
 	addq	%rax,%r10
-	movq	-32(%rcx),%rax
+	movq	-16(%rcx),%rax
 	adcq	$0,%rdx
 	addq	16(%r14),%r10
 	leaq	32(%r14),%r14
@@ -691,7 +945,7 @@ mul4x_internal:
 	mulq	%rbx
 	addq	%rax,%r11
 	movq	%rbp,%rax
-	movq	-16(%rcx),%rbp
+	movq	-8(%rcx),%rbp
 	adcq	$0,%rdx
 	addq	-8(%r14),%r11
 	adcq	$0,%rdx
@@ -706,9 +960,8 @@ mul4x_internal:
 	movq	%r13,-24(%r14)
 	movq	%rdx,%r13
 
-.byte	102,72,15,126,195
 	movq	%rdi,-16(%r14)
-	leaq	(%rcx,%r9,2),%rcx
+	leaq	(%rcx,%r9,1),%rcx
 
 	xorq	%rdi,%rdi
 	addq	%r10,%r13
@@ -719,16 +972,23 @@ mul4x_internal:
 
 	cmpq	16+8(%rsp),%r12
 	jb	.Louter4x
+	xorq	%rax,%rax
 	subq	%r13,%rbp
 	adcq	%r15,%r15
 	orq	%r15,%rdi
-	xorq	$1,%rdi
+	subq	%rdi,%rax
 	leaq	(%r14,%r9,1),%rbx
-	leaq	(%rcx,%rdi,8),%rbp
+	movq	(%rcx),%r12
+	leaq	(%rcx),%rbp
 	movq	%r9,%rcx
 	sarq	$3+2,%rcx
 	movq	56+8(%rsp),%rdi
-	jmp	.Lsqr4x_sub
+	decq	%r12
+	xorq	%r10,%r10
+	movq	8(%rbp),%r13
+	movq	16(%rbp),%r14
+	movq	24(%rbp),%r15
+	jmp	.Lsqr4x_sub_entry
 .size	mul4x_internal,.-mul4x_internal
 .globl	bn_power5
 .hidden bn_power5
@@ -742,9 +1002,9 @@ bn_power5:
 	pushq	%r13
 	pushq	%r14
 	pushq	%r15
-	movl	%r9d,%r10d
+
 	shll	$3,%r9d
-	shll	$3+2,%r10d
+	leal	(%r9,%r9,2),%r10d
 	negq	%r9
 	movq	(%r8),%r8
 
@@ -754,19 +1014,20 @@ bn_power5:
 
 
 
-	leaq	-64(%rsp,%r9,2),%r11
-	subq	%rsi,%r11
+
+	leaq	-320(%rsp,%r9,2),%r11
+	subq	%rdi,%r11
 	andq	$4095,%r11
 	cmpq	%r11,%r10
 	jb	.Lpwr_sp_alt
 	subq	%r11,%rsp
-	leaq	-64(%rsp,%r9,2),%rsp
+	leaq	-320(%rsp,%r9,2),%rsp
 	jmp	.Lpwr_sp_done
 
 .align	32
 .Lpwr_sp_alt:
-	leaq	4096-64(,%r9,2),%r10
-	leaq	-64(%rsp,%r9,2),%rsp
+	leaq	4096-320(,%r9,2),%r10
+	leaq	-320(%rsp,%r9,2),%rsp
 	subq	%r10,%r11
 	movq	$0,%r10
 	cmovcq	%r10,%r11
@@ -794,10 +1055,15 @@ bn_power5:
 .byte	102,72,15,110,226
 
 	call	__bn_sqr8x_internal
+	call	__bn_post4x_internal
 	call	__bn_sqr8x_internal
+	call	__bn_post4x_internal
 	call	__bn_sqr8x_internal
+	call	__bn_post4x_internal
 	call	__bn_sqr8x_internal
+	call	__bn_post4x_internal
 	call	__bn_sqr8x_internal
+	call	__bn_post4x_internal
 
 .byte	102,72,15,126,209
 .byte	102,72,15,126,226
@@ -1342,9 +1608,9 @@ __bn_sqr8x_internal:
 	movq	%rbx,-16(%rdi)
 	movq	%r8,-8(%rdi)
 .byte	102,72,15,126,213
-sqr8x_reduction:
+__bn_sqr8x_reduction:
 	xorq	%rax,%rax
-	leaq	(%rbp,%r9,2),%rcx
+	leaq	(%r9,%rbp,1),%rcx
 	leaq	48+8(%rsp,%r9,2),%rdx
 	movq	%rcx,0+8(%rsp)
 	leaq	48+8(%rsp,%r9,1),%rdi
@@ -1377,14 +1643,14 @@ sqr8x_reduction:
 .align	32
 .L8x_reduce:
 	mulq	%rbx
-	movq	16(%rbp),%rax
+	movq	8(%rbp),%rax
 	negq	%r8
 	movq	%rdx,%r8
 	adcq	$0,%r8
 
 	mulq	%rbx
 	addq	%rax,%r9
-	movq	32(%rbp),%rax
+	movq	16(%rbp),%rax
 	adcq	$0,%rdx
 	addq	%r9,%r8
 	movq	%rbx,48-8+8(%rsp,%rcx,8)
@@ -1393,7 +1659,7 @@ sqr8x_reduction:
 
 	mulq	%rbx
 	addq	%rax,%r10
-	movq	48(%rbp),%rax
+	movq	24(%rbp),%rax
 	adcq	$0,%rdx
 	addq	%r10,%r9
 	movq	32+8(%rsp),%rsi
@@ -1402,7 +1668,7 @@ sqr8x_reduction:
 
 	mulq	%rbx
 	addq	%rax,%r11
-	movq	64(%rbp),%rax
+	movq	32(%rbp),%rax
 	adcq	$0,%rdx
 	imulq	%r8,%rsi
 	addq	%r11,%r10
@@ -1411,7 +1677,7 @@ sqr8x_reduction:
 
 	mulq	%rbx
 	addq	%rax,%r12
-	movq	80(%rbp),%rax
+	movq	40(%rbp),%rax
 	adcq	$0,%rdx
 	addq	%r12,%r11
 	movq	%rdx,%r12
@@ -1419,7 +1685,7 @@ sqr8x_reduction:
 
 	mulq	%rbx
 	addq	%rax,%r13
-	movq	96(%rbp),%rax
+	movq	48(%rbp),%rax
 	adcq	$0,%rdx
 	addq	%r13,%r12
 	movq	%rdx,%r13
@@ -1427,7 +1693,7 @@ sqr8x_reduction:
 
 	mulq	%rbx
 	addq	%rax,%r14
-	movq	112(%rbp),%rax
+	movq	56(%rbp),%rax
 	adcq	$0,%rdx
 	addq	%r14,%r13
 	movq	%rdx,%r14
@@ -1445,7 +1711,7 @@ sqr8x_reduction:
 	decl	%ecx
 	jnz	.L8x_reduce
 
-	leaq	128(%rbp),%rbp
+	leaq	64(%rbp),%rbp
 	xorq	%rax,%rax
 	movq	8+8(%rsp),%rdx
 	cmpq	0+8(%rsp),%rbp
@@ -1471,14 +1737,14 @@ sqr8x_reduction:
 .L8x_tail:
 	mulq	%rbx
 	addq	%rax,%r8
-	movq	16(%rbp),%rax
+	movq	8(%rbp),%rax
 	movq	%r8,(%rdi)
 	movq	%rdx,%r8
 	adcq	$0,%r8
 
 	mulq	%rbx
 	addq	%rax,%r9
-	movq	32(%rbp),%rax
+	movq	16(%rbp),%rax
 	adcq	$0,%rdx
 	addq	%r9,%r8
 	leaq	8(%rdi),%rdi
@@ -1487,7 +1753,7 @@ sqr8x_reduction:
 
 	mulq	%rbx
 	addq	%rax,%r10
-	movq	48(%rbp),%rax
+	movq	24(%rbp),%rax
 	adcq	$0,%rdx
 	addq	%r10,%r9
 	movq	%rdx,%r10
@@ -1495,7 +1761,7 @@ sqr8x_reduction:
 
 	mulq	%rbx
 	addq	%rax,%r11
-	movq	64(%rbp),%rax
+	movq	32(%rbp),%rax
 	adcq	$0,%rdx
 	addq	%r11,%r10
 	movq	%rdx,%r11
@@ -1503,7 +1769,7 @@ sqr8x_reduction:
 
 	mulq	%rbx
 	addq	%rax,%r12
-	movq	80(%rbp),%rax
+	movq	40(%rbp),%rax
 	adcq	$0,%rdx
 	addq	%r12,%r11
 	movq	%rdx,%r12
@@ -1511,7 +1777,7 @@ sqr8x_reduction:
 
 	mulq	%rbx
 	addq	%rax,%r13
-	movq	96(%rbp),%rax
+	movq	48(%rbp),%rax
 	adcq	$0,%rdx
 	addq	%r13,%r12
 	movq	%rdx,%r13
@@ -1519,7 +1785,7 @@ sqr8x_reduction:
 
 	mulq	%rbx
 	addq	%rax,%r14
-	movq	112(%rbp),%rax
+	movq	56(%rbp),%rax
 	adcq	$0,%rdx
 	addq	%r14,%r13
 	movq	%rdx,%r14
@@ -1537,7 +1803,7 @@ sqr8x_reduction:
 	decl	%ecx
 	jnz	.L8x_tail
 
-	leaq	128(%rbp),%rbp
+	leaq	64(%rbp),%rbp
 	movq	8+8(%rsp),%rdx
 	cmpq	0+8(%rsp),%rbp
 	jae	.L8x_tail_done
@@ -1561,6 +1827,15 @@ sqr8x_reduction:
 .align	32
 .L8x_tail_done:
 	addq	(%rdx),%r8
+	adcq	$0,%r9
+	adcq	$0,%r10
+	adcq	$0,%r11
+	adcq	$0,%r12
+	adcq	$0,%r13
+	adcq	$0,%r14
+	adcq	$0,%r15
+
+
 	xorq	%rax,%rax
 
 	negq	%rsi
@@ -1574,7 +1849,7 @@ sqr8x_reduction:
 	adcq	48(%rdi),%r14
 	adcq	56(%rdi),%r15
 	adcq	$0,%rax
-	movq	-16(%rbp),%rcx
+	movq	-8(%rbp),%rcx
 	xorq	%rsi,%rsi
 
 .byte	102,72,15,126,213
@@ -1592,44 +1867,62 @@ sqr8x_reduction:
 
 	cmpq	%rdx,%rdi
 	jb	.L8x_reduction_loop
-
-	subq	%r15,%rcx
-	leaq	(%rdi,%r9,1),%rbx
-	adcq	%rsi,%rsi
-	movq	%r9,%rcx
-	orq	%rsi,%rax
-.byte	102,72,15,126,207
-	xorq	$1,%rax
-.byte	102,72,15,126,206
-	leaq	(%rbp,%rax,8),%rbp
-	sarq	$3+2,%rcx
-	jmp	.Lsqr4x_sub
-
+	.byte	0xf3,0xc3
+.size	bn_sqr8x_internal,.-bn_sqr8x_internal
+.type	__bn_post4x_internal,@function
 .align	32
+__bn_post4x_internal:
+	movq	0(%rbp),%r12
+	leaq	(%rdi,%r9,1),%rbx
+	movq	%r9,%rcx
+.byte	102,72,15,126,207
+	negq	%rax
+.byte	102,72,15,126,206
+	sarq	$3+2,%rcx
+	decq	%r12
+	xorq	%r10,%r10
+	movq	8(%rbp),%r13
+	movq	16(%rbp),%r14
+	movq	24(%rbp),%r15
+	jmp	.Lsqr4x_sub_entry
+
+.align	16
 .Lsqr4x_sub:
-.byte	0x66
-	movq	0(%rbx),%r12
-	movq	8(%rbx),%r13
-	sbbq	0(%rbp),%r12
-	movq	16(%rbx),%r14
-	sbbq	16(%rbp),%r13
-	movq	24(%rbx),%r15
-	leaq	32(%rbx),%rbx
-	sbbq	32(%rbp),%r14
+	movq	0(%rbp),%r12
+	movq	8(%rbp),%r13
+	movq	16(%rbp),%r14
+	movq	24(%rbp),%r15
+.Lsqr4x_sub_entry:
+	leaq	32(%rbp),%rbp
+	notq	%r12
+	notq	%r13
+	notq	%r14
+	notq	%r15
+	andq	%rax,%r12
+	andq	%rax,%r13
+	andq	%rax,%r14
+	andq	%rax,%r15
+
+	negq	%r10
+	adcq	0(%rbx),%r12
+	adcq	8(%rbx),%r13
+	adcq	16(%rbx),%r14
+	adcq	24(%rbx),%r15
 	movq	%r12,0(%rdi)
-	sbbq	48(%rbp),%r15
-	leaq	64(%rbp),%rbp
+	leaq	32(%rbx),%rbx
 	movq	%r13,8(%rdi)
+	sbbq	%r10,%r10
 	movq	%r14,16(%rdi)
 	movq	%r15,24(%rdi)
 	leaq	32(%rdi),%rdi
 
 	incq	%rcx
 	jnz	.Lsqr4x_sub
+
 	movq	%r9,%r10
 	negq	%r9
 	.byte	0xf3,0xc3
-.size	bn_sqr8x_internal,.-bn_sqr8x_internal
+.size	__bn_post4x_internal,.-__bn_post4x_internal
 .globl	bn_from_montgomery
 .hidden bn_from_montgomery
 .type	bn_from_montgomery,@function
@@ -1652,10 +1945,9 @@ bn_from_mont8x:
 	pushq	%r13
 	pushq	%r14
 	pushq	%r15
-.byte	0x67
-	movl	%r9d,%r10d
+
 	shll	$3,%r9d
-	shll	$3+2,%r10d
+	leaq	(%r9,%r9,2),%r10
 	negq	%r9
 	movq	(%r8),%r8
 
@@ -1665,19 +1957,20 @@ bn_from_mont8x:
 
 
 
-	leaq	-64(%rsp,%r9,2),%r11
-	subq	%rsi,%r11
+
+	leaq	-320(%rsp,%r9,2),%r11
+	subq	%rdi,%r11
 	andq	$4095,%r11
 	cmpq	%r11,%r10
 	jb	.Lfrom_sp_alt
 	subq	%r11,%rsp
-	leaq	-64(%rsp,%r9,2),%rsp
+	leaq	-320(%rsp,%r9,2),%rsp
 	jmp	.Lfrom_sp_done
 
 .align	32
 .Lfrom_sp_alt:
-	leaq	4096-64(,%r9,2),%r10
-	leaq	-64(%rsp,%r9,2),%rsp
+	leaq	4096-320(,%r9,2),%r10
+	leaq	-320(%rsp,%r9,2),%rsp
 	subq	%r10,%r11
 	movq	$0,%r10
 	cmovcq	%r10,%r11
@@ -1728,7 +2021,8 @@ bn_from_mont8x:
 .byte	0x67
 	movq	%rcx,%rbp
 .byte	102,73,15,110,218
-	call	sqr8x_reduction
+	call	__bn_sqr8x_reduction
+	call	__bn_post4x_internal
 
 	pxor	%xmm0,%xmm0
 	leaq	48(%rsp),%rax
@@ -1778,46 +2072,170 @@ bn_scatter5:
 .globl	bn_gather5
 .hidden bn_gather5
 .type	bn_gather5,@function
-.align	16
+.align	32
 bn_gather5:
-	movl	%ecx,%r11d
-	shrl	$3,%ecx
-	andq	$7,%r11
-	notl	%ecx
-	leaq	.Lmagic_masks(%rip),%rax
-	andl	$3,%ecx
-	leaq	128(%rdx,%r11,8),%rdx
-	movq	0(%rax,%rcx,8),%xmm4
-	movq	8(%rax,%rcx,8),%xmm5
-	movq	16(%rax,%rcx,8),%xmm6
-	movq	24(%rax,%rcx,8),%xmm7
-	jmp	.Lgather
-.align	16
-.Lgather:
-	movq	-128(%rdx),%xmm0
-	movq	-64(%rdx),%xmm1
-	pand	%xmm4,%xmm0
-	movq	0(%rdx),%xmm2
-	pand	%xmm5,%xmm1
-	movq	64(%rdx),%xmm3
-	pand	%xmm6,%xmm2
-	por	%xmm1,%xmm0
-	pand	%xmm7,%xmm3
-.byte	0x67,0x67
-	por	%xmm2,%xmm0
-	leaq	256(%rdx),%rdx
-	por	%xmm3,%xmm0
+.LSEH_begin_bn_gather5:
 
+.byte	0x4c,0x8d,0x14,0x24
+.byte	0x48,0x81,0xec,0x08,0x01,0x00,0x00
+	leaq	.Linc(%rip),%rax
+	andq	$-16,%rsp
+
+	movd	%ecx,%xmm5
+	movdqa	0(%rax),%xmm0
+	movdqa	16(%rax),%xmm1
+	leaq	128(%rdx),%r11
+	leaq	128(%rsp),%rax
+
+	pshufd	$0,%xmm5,%xmm5
+	movdqa	%xmm1,%xmm4
+	movdqa	%xmm1,%xmm2
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0
+	movdqa	%xmm4,%xmm3
+
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1
+	movdqa	%xmm0,-128(%rax)
+	movdqa	%xmm4,%xmm0
+
+	paddd	%xmm2,%xmm3
+	pcmpeqd	%xmm5,%xmm2
+	movdqa	%xmm1,-112(%rax)
+	movdqa	%xmm4,%xmm1
+
+	paddd	%xmm3,%xmm0
+	pcmpeqd	%xmm5,%xmm3
+	movdqa	%xmm2,-96(%rax)
+	movdqa	%xmm4,%xmm2
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0
+	movdqa	%xmm3,-80(%rax)
+	movdqa	%xmm4,%xmm3
+
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1
+	movdqa	%xmm0,-64(%rax)
+	movdqa	%xmm4,%xmm0
+
+	paddd	%xmm2,%xmm3
+	pcmpeqd	%xmm5,%xmm2
+	movdqa	%xmm1,-48(%rax)
+	movdqa	%xmm4,%xmm1
+
+	paddd	%xmm3,%xmm0
+	pcmpeqd	%xmm5,%xmm3
+	movdqa	%xmm2,-32(%rax)
+	movdqa	%xmm4,%xmm2
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0
+	movdqa	%xmm3,-16(%rax)
+	movdqa	%xmm4,%xmm3
+
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1
+	movdqa	%xmm0,0(%rax)
+	movdqa	%xmm4,%xmm0
+
+	paddd	%xmm2,%xmm3
+	pcmpeqd	%xmm5,%xmm2
+	movdqa	%xmm1,16(%rax)
+	movdqa	%xmm4,%xmm1
+
+	paddd	%xmm3,%xmm0
+	pcmpeqd	%xmm5,%xmm3
+	movdqa	%xmm2,32(%rax)
+	movdqa	%xmm4,%xmm2
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0
+	movdqa	%xmm3,48(%rax)
+	movdqa	%xmm4,%xmm3
+
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1
+	movdqa	%xmm0,64(%rax)
+	movdqa	%xmm4,%xmm0
+
+	paddd	%xmm2,%xmm3
+	pcmpeqd	%xmm5,%xmm2
+	movdqa	%xmm1,80(%rax)
+	movdqa	%xmm4,%xmm1
+
+	paddd	%xmm3,%xmm0
+	pcmpeqd	%xmm5,%xmm3
+	movdqa	%xmm2,96(%rax)
+	movdqa	%xmm4,%xmm2
+	movdqa	%xmm3,112(%rax)
+	jmp	.Lgather
+
+.align	32
+.Lgather:
+	pxor	%xmm4,%xmm4
+	pxor	%xmm5,%xmm5
+	movdqa	-128(%r11),%xmm0
+	movdqa	-112(%r11),%xmm1
+	movdqa	-96(%r11),%xmm2
+	pand	-128(%rax),%xmm0
+	movdqa	-80(%r11),%xmm3
+	pand	-112(%rax),%xmm1
+	por	%xmm0,%xmm4
+	pand	-96(%rax),%xmm2
+	por	%xmm1,%xmm5
+	pand	-80(%rax),%xmm3
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+	movdqa	-64(%r11),%xmm0
+	movdqa	-48(%r11),%xmm1
+	movdqa	-32(%r11),%xmm2
+	pand	-64(%rax),%xmm0
+	movdqa	-16(%r11),%xmm3
+	pand	-48(%rax),%xmm1
+	por	%xmm0,%xmm4
+	pand	-32(%rax),%xmm2
+	por	%xmm1,%xmm5
+	pand	-16(%rax),%xmm3
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+	movdqa	0(%r11),%xmm0
+	movdqa	16(%r11),%xmm1
+	movdqa	32(%r11),%xmm2
+	pand	0(%rax),%xmm0
+	movdqa	48(%r11),%xmm3
+	pand	16(%rax),%xmm1
+	por	%xmm0,%xmm4
+	pand	32(%rax),%xmm2
+	por	%xmm1,%xmm5
+	pand	48(%rax),%xmm3
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+	movdqa	64(%r11),%xmm0
+	movdqa	80(%r11),%xmm1
+	movdqa	96(%r11),%xmm2
+	pand	64(%rax),%xmm0
+	movdqa	112(%r11),%xmm3
+	pand	80(%rax),%xmm1
+	por	%xmm0,%xmm4
+	pand	96(%rax),%xmm2
+	por	%xmm1,%xmm5
+	pand	112(%rax),%xmm3
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+	por	%xmm5,%xmm4
+	leaq	256(%r11),%r11
+	pshufd	$0x4e,%xmm4,%xmm0
+	por	%xmm4,%xmm0
 	movq	%xmm0,(%rdi)
 	leaq	8(%rdi),%rdi
 	subl	$1,%esi
 	jnz	.Lgather
+
+	leaq	(%r10),%rsp
 	.byte	0xf3,0xc3
 .LSEH_end_bn_gather5:
 .size	bn_gather5,.-bn_gather5
 .align	64
-.Lmagic_masks:
-.long	0,0, 0,0, 0,0, -1,-1
-.long	0,0, 0,0, 0,0,  0,0
+.Linc:
+.long	0,0, 1,1
+.long	2,2, 2,2
 .byte	77,111,110,116,103,111,109,101,114,121,32,77,117,108,116,105,112,108,105,99,97,116,105,111,110,32,119,105,116,104,32,115,99,97,116,116,101,114,47,103,97,116,104,101,114,32,102,111,114,32,120,56,54,95,54,52,44,32,67,82,89,80,84,79,71,65,77,83,32,98,121,32,60,97,112,112,114,111,64,111,112,101,110,115,115,108,46,111,114,103,62,0
 #endif
diff --git a/packager/third_party/boringssl/linux-x86_64/crypto/chacha/chacha-x86_64.S b/packager/third_party/boringssl/linux-x86_64/crypto/chacha/chacha-x86_64.S
new file mode 100644
index 0000000000..e994940a3f
--- /dev/null
+++ b/packager/third_party/boringssl/linux-x86_64/crypto/chacha/chacha-x86_64.S
@@ -0,0 +1,1585 @@
+#if defined(__x86_64__)
+.text	
+
+.extern	OPENSSL_ia32cap_P
+.hidden OPENSSL_ia32cap_P
+
+.align	64
+.Lzero:
+.long	0,0,0,0
+.Lone:
+.long	1,0,0,0
+.Linc:
+.long	0,1,2,3
+.Lfour:
+.long	4,4,4,4
+.Lincy:
+.long	0,2,4,6,1,3,5,7
+.Leight:
+.long	8,8,8,8,8,8,8,8
+.Lrot16:
+.byte	0x2,0x3,0x0,0x1, 0x6,0x7,0x4,0x5, 0xa,0xb,0x8,0x9, 0xe,0xf,0xc,0xd
+.Lrot24:
+.byte	0x3,0x0,0x1,0x2, 0x7,0x4,0x5,0x6, 0xb,0x8,0x9,0xa, 0xf,0xc,0xd,0xe
+.Lsigma:
+.byte	101,120,112,97,110,100,32,51,50,45,98,121,116,101,32,107,0
+.byte	67,104,97,67,104,97,50,48,32,102,111,114,32,120,56,54,95,54,52,44,32,67,82,89,80,84,79,71,65,77,83,32,98,121,32,60,97,112,112,114,111,64,111,112,101,110,115,115,108,46,111,114,103,62,0
+.globl	ChaCha20_ctr32
+.hidden ChaCha20_ctr32
+.type	ChaCha20_ctr32,@function
+.align	64
+ChaCha20_ctr32:
+	cmpq	$0,%rdx
+	je	.Lno_data
+	movq	OPENSSL_ia32cap_P+4(%rip),%r10
+	testl	$512,%r10d
+	jnz	.LChaCha20_ssse3
+
+	pushq	%rbx
+	pushq	%rbp
+	pushq	%r12
+	pushq	%r13
+	pushq	%r14
+	pushq	%r15
+	subq	$64+24,%rsp
+
+
+	movdqu	(%rcx),%xmm1
+	movdqu	16(%rcx),%xmm2
+	movdqu	(%r8),%xmm3
+	movdqa	.Lone(%rip),%xmm4
+
+
+	movdqa	%xmm1,16(%rsp)
+	movdqa	%xmm2,32(%rsp)
+	movdqa	%xmm3,48(%rsp)
+	movq	%rdx,%rbp
+	jmp	.Loop_outer
+
+.align	32
+.Loop_outer:
+	movl	$0x61707865,%eax
+	movl	$0x3320646e,%ebx
+	movl	$0x79622d32,%ecx
+	movl	$0x6b206574,%edx
+	movl	16(%rsp),%r8d
+	movl	20(%rsp),%r9d
+	movl	24(%rsp),%r10d
+	movl	28(%rsp),%r11d
+	movd	%xmm3,%r12d
+	movl	52(%rsp),%r13d
+	movl	56(%rsp),%r14d
+	movl	60(%rsp),%r15d
+
+	movq	%rbp,64+0(%rsp)
+	movl	$10,%ebp
+	movq	%rsi,64+8(%rsp)
+.byte	102,72,15,126,214
+	movq	%rdi,64+16(%rsp)
+	movq	%rsi,%rdi
+	shrq	$32,%rdi
+	jmp	.Loop
+
+.align	32
+.Loop:
+	addl	%r8d,%eax
+	xorl	%eax,%r12d
+	roll	$16,%r12d
+	addl	%r9d,%ebx
+	xorl	%ebx,%r13d
+	roll	$16,%r13d
+	addl	%r12d,%esi
+	xorl	%esi,%r8d
+	roll	$12,%r8d
+	addl	%r13d,%edi
+	xorl	%edi,%r9d
+	roll	$12,%r9d
+	addl	%r8d,%eax
+	xorl	%eax,%r12d
+	roll	$8,%r12d
+	addl	%r9d,%ebx
+	xorl	%ebx,%r13d
+	roll	$8,%r13d
+	addl	%r12d,%esi
+	xorl	%esi,%r8d
+	roll	$7,%r8d
+	addl	%r13d,%edi
+	xorl	%edi,%r9d
+	roll	$7,%r9d
+	movl	%esi,32(%rsp)
+	movl	%edi,36(%rsp)
+	movl	40(%rsp),%esi
+	movl	44(%rsp),%edi
+	addl	%r10d,%ecx
+	xorl	%ecx,%r14d
+	roll	$16,%r14d
+	addl	%r11d,%edx
+	xorl	%edx,%r15d
+	roll	$16,%r15d
+	addl	%r14d,%esi
+	xorl	%esi,%r10d
+	roll	$12,%r10d
+	addl	%r15d,%edi
+	xorl	%edi,%r11d
+	roll	$12,%r11d
+	addl	%r10d,%ecx
+	xorl	%ecx,%r14d
+	roll	$8,%r14d
+	addl	%r11d,%edx
+	xorl	%edx,%r15d
+	roll	$8,%r15d
+	addl	%r14d,%esi
+	xorl	%esi,%r10d
+	roll	$7,%r10d
+	addl	%r15d,%edi
+	xorl	%edi,%r11d
+	roll	$7,%r11d
+	addl	%r9d,%eax
+	xorl	%eax,%r15d
+	roll	$16,%r15d
+	addl	%r10d,%ebx
+	xorl	%ebx,%r12d
+	roll	$16,%r12d
+	addl	%r15d,%esi
+	xorl	%esi,%r9d
+	roll	$12,%r9d
+	addl	%r12d,%edi
+	xorl	%edi,%r10d
+	roll	$12,%r10d
+	addl	%r9d,%eax
+	xorl	%eax,%r15d
+	roll	$8,%r15d
+	addl	%r10d,%ebx
+	xorl	%ebx,%r12d
+	roll	$8,%r12d
+	addl	%r15d,%esi
+	xorl	%esi,%r9d
+	roll	$7,%r9d
+	addl	%r12d,%edi
+	xorl	%edi,%r10d
+	roll	$7,%r10d
+	movl	%esi,40(%rsp)
+	movl	%edi,44(%rsp)
+	movl	32(%rsp),%esi
+	movl	36(%rsp),%edi
+	addl	%r11d,%ecx
+	xorl	%ecx,%r13d
+	roll	$16,%r13d
+	addl	%r8d,%edx
+	xorl	%edx,%r14d
+	roll	$16,%r14d
+	addl	%r13d,%esi
+	xorl	%esi,%r11d
+	roll	$12,%r11d
+	addl	%r14d,%edi
+	xorl	%edi,%r8d
+	roll	$12,%r8d
+	addl	%r11d,%ecx
+	xorl	%ecx,%r13d
+	roll	$8,%r13d
+	addl	%r8d,%edx
+	xorl	%edx,%r14d
+	roll	$8,%r14d
+	addl	%r13d,%esi
+	xorl	%esi,%r11d
+	roll	$7,%r11d
+	addl	%r14d,%edi
+	xorl	%edi,%r8d
+	roll	$7,%r8d
+	decl	%ebp
+	jnz	.Loop
+	movl	%edi,36(%rsp)
+	movl	%esi,32(%rsp)
+	movq	64(%rsp),%rbp
+	movdqa	%xmm2,%xmm1
+	movq	64+8(%rsp),%rsi
+	paddd	%xmm4,%xmm3
+	movq	64+16(%rsp),%rdi
+
+	addl	$0x61707865,%eax
+	addl	$0x3320646e,%ebx
+	addl	$0x79622d32,%ecx
+	addl	$0x6b206574,%edx
+	addl	16(%rsp),%r8d
+	addl	20(%rsp),%r9d
+	addl	24(%rsp),%r10d
+	addl	28(%rsp),%r11d
+	addl	48(%rsp),%r12d
+	addl	52(%rsp),%r13d
+	addl	56(%rsp),%r14d
+	addl	60(%rsp),%r15d
+	paddd	32(%rsp),%xmm1
+
+	cmpq	$64,%rbp
+	jb	.Ltail
+
+	xorl	0(%rsi),%eax
+	xorl	4(%rsi),%ebx
+	xorl	8(%rsi),%ecx
+	xorl	12(%rsi),%edx
+	xorl	16(%rsi),%r8d
+	xorl	20(%rsi),%r9d
+	xorl	24(%rsi),%r10d
+	xorl	28(%rsi),%r11d
+	movdqu	32(%rsi),%xmm0
+	xorl	48(%rsi),%r12d
+	xorl	52(%rsi),%r13d
+	xorl	56(%rsi),%r14d
+	xorl	60(%rsi),%r15d
+	leaq	64(%rsi),%rsi
+	pxor	%xmm1,%xmm0
+
+	movdqa	%xmm2,32(%rsp)
+	movd	%xmm3,48(%rsp)
+
+	movl	%eax,0(%rdi)
+	movl	%ebx,4(%rdi)
+	movl	%ecx,8(%rdi)
+	movl	%edx,12(%rdi)
+	movl	%r8d,16(%rdi)
+	movl	%r9d,20(%rdi)
+	movl	%r10d,24(%rdi)
+	movl	%r11d,28(%rdi)
+	movdqu	%xmm0,32(%rdi)
+	movl	%r12d,48(%rdi)
+	movl	%r13d,52(%rdi)
+	movl	%r14d,56(%rdi)
+	movl	%r15d,60(%rdi)
+	leaq	64(%rdi),%rdi
+
+	subq	$64,%rbp
+	jnz	.Loop_outer
+
+	jmp	.Ldone
+
+.align	16
+.Ltail:
+	movl	%eax,0(%rsp)
+	movl	%ebx,4(%rsp)
+	xorq	%rbx,%rbx
+	movl	%ecx,8(%rsp)
+	movl	%edx,12(%rsp)
+	movl	%r8d,16(%rsp)
+	movl	%r9d,20(%rsp)
+	movl	%r10d,24(%rsp)
+	movl	%r11d,28(%rsp)
+	movdqa	%xmm1,32(%rsp)
+	movl	%r12d,48(%rsp)
+	movl	%r13d,52(%rsp)
+	movl	%r14d,56(%rsp)
+	movl	%r15d,60(%rsp)
+
+.Loop_tail:
+	movzbl	(%rsi,%rbx,1),%eax
+	movzbl	(%rsp,%rbx,1),%edx
+	leaq	1(%rbx),%rbx
+	xorl	%edx,%eax
+	movb	%al,-1(%rdi,%rbx,1)
+	decq	%rbp
+	jnz	.Loop_tail
+
+.Ldone:
+	addq	$64+24,%rsp
+	popq	%r15
+	popq	%r14
+	popq	%r13
+	popq	%r12
+	popq	%rbp
+	popq	%rbx
+.Lno_data:
+	.byte	0xf3,0xc3
+.size	ChaCha20_ctr32,.-ChaCha20_ctr32
+.type	ChaCha20_ssse3,@function
+.align	32
+ChaCha20_ssse3:
+.LChaCha20_ssse3:
+	cmpq	$128,%rdx
+	ja	.LChaCha20_4x
+
+.Ldo_sse3_after_all:
+	pushq	%rbx
+	pushq	%rbp
+	pushq	%r12
+	pushq	%r13
+	pushq	%r14
+	pushq	%r15
+
+	subq	$64+24,%rsp
+	movdqa	.Lsigma(%rip),%xmm0
+	movdqu	(%rcx),%xmm1
+	movdqu	16(%rcx),%xmm2
+	movdqu	(%r8),%xmm3
+	movdqa	.Lrot16(%rip),%xmm6
+	movdqa	.Lrot24(%rip),%xmm7
+
+	movdqa	%xmm0,0(%rsp)
+	movdqa	%xmm1,16(%rsp)
+	movdqa	%xmm2,32(%rsp)
+	movdqa	%xmm3,48(%rsp)
+	movl	$10,%ebp
+	jmp	.Loop_ssse3
+
+.align	32
+.Loop_outer_ssse3:
+	movdqa	.Lone(%rip),%xmm3
+	movdqa	0(%rsp),%xmm0
+	movdqa	16(%rsp),%xmm1
+	movdqa	32(%rsp),%xmm2
+	paddd	48(%rsp),%xmm3
+	movl	$10,%ebp
+	movdqa	%xmm3,48(%rsp)
+	jmp	.Loop_ssse3
+
+.align	32
+.Loop_ssse3:
+	paddd	%xmm1,%xmm0
+	pxor	%xmm0,%xmm3
+.byte	102,15,56,0,222
+	paddd	%xmm3,%xmm2
+	pxor	%xmm2,%xmm1
+	movdqa	%xmm1,%xmm4
+	psrld	$20,%xmm1
+	pslld	$12,%xmm4
+	por	%xmm4,%xmm1
+	paddd	%xmm1,%xmm0
+	pxor	%xmm0,%xmm3
+.byte	102,15,56,0,223
+	paddd	%xmm3,%xmm2
+	pxor	%xmm2,%xmm1
+	movdqa	%xmm1,%xmm4
+	psrld	$25,%xmm1
+	pslld	$7,%xmm4
+	por	%xmm4,%xmm1
+	pshufd	$78,%xmm2,%xmm2
+	pshufd	$57,%xmm1,%xmm1
+	pshufd	$147,%xmm3,%xmm3
+	nop
+	paddd	%xmm1,%xmm0
+	pxor	%xmm0,%xmm3
+.byte	102,15,56,0,222
+	paddd	%xmm3,%xmm2
+	pxor	%xmm2,%xmm1
+	movdqa	%xmm1,%xmm4
+	psrld	$20,%xmm1
+	pslld	$12,%xmm4
+	por	%xmm4,%xmm1
+	paddd	%xmm1,%xmm0
+	pxor	%xmm0,%xmm3
+.byte	102,15,56,0,223
+	paddd	%xmm3,%xmm2
+	pxor	%xmm2,%xmm1
+	movdqa	%xmm1,%xmm4
+	psrld	$25,%xmm1
+	pslld	$7,%xmm4
+	por	%xmm4,%xmm1
+	pshufd	$78,%xmm2,%xmm2
+	pshufd	$147,%xmm1,%xmm1
+	pshufd	$57,%xmm3,%xmm3
+	decl	%ebp
+	jnz	.Loop_ssse3
+	paddd	0(%rsp),%xmm0
+	paddd	16(%rsp),%xmm1
+	paddd	32(%rsp),%xmm2
+	paddd	48(%rsp),%xmm3
+
+	cmpq	$64,%rdx
+	jb	.Ltail_ssse3
+
+	movdqu	0(%rsi),%xmm4
+	movdqu	16(%rsi),%xmm5
+	pxor	%xmm4,%xmm0
+	movdqu	32(%rsi),%xmm4
+	pxor	%xmm5,%xmm1
+	movdqu	48(%rsi),%xmm5
+	leaq	64(%rsi),%rsi
+	pxor	%xmm4,%xmm2
+	pxor	%xmm5,%xmm3
+
+	movdqu	%xmm0,0(%rdi)
+	movdqu	%xmm1,16(%rdi)
+	movdqu	%xmm2,32(%rdi)
+	movdqu	%xmm3,48(%rdi)
+	leaq	64(%rdi),%rdi
+
+	subq	$64,%rdx
+	jnz	.Loop_outer_ssse3
+
+	jmp	.Ldone_ssse3
+
+.align	16
+.Ltail_ssse3:
+	movdqa	%xmm0,0(%rsp)
+	movdqa	%xmm1,16(%rsp)
+	movdqa	%xmm2,32(%rsp)
+	movdqa	%xmm3,48(%rsp)
+	xorq	%rbx,%rbx
+
+.Loop_tail_ssse3:
+	movzbl	(%rsi,%rbx,1),%eax
+	movzbl	(%rsp,%rbx,1),%ecx
+	leaq	1(%rbx),%rbx
+	xorl	%ecx,%eax
+	movb	%al,-1(%rdi,%rbx,1)
+	decq	%rdx
+	jnz	.Loop_tail_ssse3
+
+.Ldone_ssse3:
+	addq	$64+24,%rsp
+	popq	%r15
+	popq	%r14
+	popq	%r13
+	popq	%r12
+	popq	%rbp
+	popq	%rbx
+	.byte	0xf3,0xc3
+.size	ChaCha20_ssse3,.-ChaCha20_ssse3
+.type	ChaCha20_4x,@function
+.align	32
+ChaCha20_4x:
+.LChaCha20_4x:
+	movq	%r10,%r11
+	shrq	$32,%r10
+	testq	$32,%r10
+	jnz	.LChaCha20_8x
+	cmpq	$192,%rdx
+	ja	.Lproceed4x
+
+	andq	$71303168,%r11
+	cmpq	$4194304,%r11
+	je	.Ldo_sse3_after_all
+
+.Lproceed4x:
+	leaq	-120(%rsp),%r11
+	subq	$0x148+0,%rsp
+	movdqa	.Lsigma(%rip),%xmm11
+	movdqu	(%rcx),%xmm15
+	movdqu	16(%rcx),%xmm7
+	movdqu	(%r8),%xmm3
+	leaq	256(%rsp),%rcx
+	leaq	.Lrot16(%rip),%r10
+	leaq	.Lrot24(%rip),%r11
+
+	pshufd	$0x00,%xmm11,%xmm8
+	pshufd	$0x55,%xmm11,%xmm9
+	movdqa	%xmm8,64(%rsp)
+	pshufd	$0xaa,%xmm11,%xmm10
+	movdqa	%xmm9,80(%rsp)
+	pshufd	$0xff,%xmm11,%xmm11
+	movdqa	%xmm10,96(%rsp)
+	movdqa	%xmm11,112(%rsp)
+
+	pshufd	$0x00,%xmm15,%xmm12
+	pshufd	$0x55,%xmm15,%xmm13
+	movdqa	%xmm12,128-256(%rcx)
+	pshufd	$0xaa,%xmm15,%xmm14
+	movdqa	%xmm13,144-256(%rcx)
+	pshufd	$0xff,%xmm15,%xmm15
+	movdqa	%xmm14,160-256(%rcx)
+	movdqa	%xmm15,176-256(%rcx)
+
+	pshufd	$0x00,%xmm7,%xmm4
+	pshufd	$0x55,%xmm7,%xmm5
+	movdqa	%xmm4,192-256(%rcx)
+	pshufd	$0xaa,%xmm7,%xmm6
+	movdqa	%xmm5,208-256(%rcx)
+	pshufd	$0xff,%xmm7,%xmm7
+	movdqa	%xmm6,224-256(%rcx)
+	movdqa	%xmm7,240-256(%rcx)
+
+	pshufd	$0x00,%xmm3,%xmm0
+	pshufd	$0x55,%xmm3,%xmm1
+	paddd	.Linc(%rip),%xmm0
+	pshufd	$0xaa,%xmm3,%xmm2
+	movdqa	%xmm1,272-256(%rcx)
+	pshufd	$0xff,%xmm3,%xmm3
+	movdqa	%xmm2,288-256(%rcx)
+	movdqa	%xmm3,304-256(%rcx)
+
+	jmp	.Loop_enter4x
+
+.align	32
+.Loop_outer4x:
+	movdqa	64(%rsp),%xmm8
+	movdqa	80(%rsp),%xmm9
+	movdqa	96(%rsp),%xmm10
+	movdqa	112(%rsp),%xmm11
+	movdqa	128-256(%rcx),%xmm12
+	movdqa	144-256(%rcx),%xmm13
+	movdqa	160-256(%rcx),%xmm14
+	movdqa	176-256(%rcx),%xmm15
+	movdqa	192-256(%rcx),%xmm4
+	movdqa	208-256(%rcx),%xmm5
+	movdqa	224-256(%rcx),%xmm6
+	movdqa	240-256(%rcx),%xmm7
+	movdqa	256-256(%rcx),%xmm0
+	movdqa	272-256(%rcx),%xmm1
+	movdqa	288-256(%rcx),%xmm2
+	movdqa	304-256(%rcx),%xmm3
+	paddd	.Lfour(%rip),%xmm0
+
+.Loop_enter4x:
+	movdqa	%xmm6,32(%rsp)
+	movdqa	%xmm7,48(%rsp)
+	movdqa	(%r10),%xmm7
+	movl	$10,%eax
+	movdqa	%xmm0,256-256(%rcx)
+	jmp	.Loop4x
+
+.align	32
+.Loop4x:
+	paddd	%xmm12,%xmm8
+	paddd	%xmm13,%xmm9
+	pxor	%xmm8,%xmm0
+	pxor	%xmm9,%xmm1
+.byte	102,15,56,0,199
+.byte	102,15,56,0,207
+	paddd	%xmm0,%xmm4
+	paddd	%xmm1,%xmm5
+	pxor	%xmm4,%xmm12
+	pxor	%xmm5,%xmm13
+	movdqa	%xmm12,%xmm6
+	pslld	$12,%xmm12
+	psrld	$20,%xmm6
+	movdqa	%xmm13,%xmm7
+	pslld	$12,%xmm13
+	por	%xmm6,%xmm12
+	psrld	$20,%xmm7
+	movdqa	(%r11),%xmm6
+	por	%xmm7,%xmm13
+	paddd	%xmm12,%xmm8
+	paddd	%xmm13,%xmm9
+	pxor	%xmm8,%xmm0
+	pxor	%xmm9,%xmm1
+.byte	102,15,56,0,198
+.byte	102,15,56,0,206
+	paddd	%xmm0,%xmm4
+	paddd	%xmm1,%xmm5
+	pxor	%xmm4,%xmm12
+	pxor	%xmm5,%xmm13
+	movdqa	%xmm12,%xmm7
+	pslld	$7,%xmm12
+	psrld	$25,%xmm7
+	movdqa	%xmm13,%xmm6
+	pslld	$7,%xmm13
+	por	%xmm7,%xmm12
+	psrld	$25,%xmm6
+	movdqa	(%r10),%xmm7
+	por	%xmm6,%xmm13
+	movdqa	%xmm4,0(%rsp)
+	movdqa	%xmm5,16(%rsp)
+	movdqa	32(%rsp),%xmm4
+	movdqa	48(%rsp),%xmm5
+	paddd	%xmm14,%xmm10
+	paddd	%xmm15,%xmm11
+	pxor	%xmm10,%xmm2
+	pxor	%xmm11,%xmm3
+.byte	102,15,56,0,215
+.byte	102,15,56,0,223
+	paddd	%xmm2,%xmm4
+	paddd	%xmm3,%xmm5
+	pxor	%xmm4,%xmm14
+	pxor	%xmm5,%xmm15
+	movdqa	%xmm14,%xmm6
+	pslld	$12,%xmm14
+	psrld	$20,%xmm6
+	movdqa	%xmm15,%xmm7
+	pslld	$12,%xmm15
+	por	%xmm6,%xmm14
+	psrld	$20,%xmm7
+	movdqa	(%r11),%xmm6
+	por	%xmm7,%xmm15
+	paddd	%xmm14,%xmm10
+	paddd	%xmm15,%xmm11
+	pxor	%xmm10,%xmm2
+	pxor	%xmm11,%xmm3
+.byte	102,15,56,0,214
+.byte	102,15,56,0,222
+	paddd	%xmm2,%xmm4
+	paddd	%xmm3,%xmm5
+	pxor	%xmm4,%xmm14
+	pxor	%xmm5,%xmm15
+	movdqa	%xmm14,%xmm7
+	pslld	$7,%xmm14
+	psrld	$25,%xmm7
+	movdqa	%xmm15,%xmm6
+	pslld	$7,%xmm15
+	por	%xmm7,%xmm14
+	psrld	$25,%xmm6
+	movdqa	(%r10),%xmm7
+	por	%xmm6,%xmm15
+	paddd	%xmm13,%xmm8
+	paddd	%xmm14,%xmm9
+	pxor	%xmm8,%xmm3
+	pxor	%xmm9,%xmm0
+.byte	102,15,56,0,223
+.byte	102,15,56,0,199
+	paddd	%xmm3,%xmm4
+	paddd	%xmm0,%xmm5
+	pxor	%xmm4,%xmm13
+	pxor	%xmm5,%xmm14
+	movdqa	%xmm13,%xmm6
+	pslld	$12,%xmm13
+	psrld	$20,%xmm6
+	movdqa	%xmm14,%xmm7
+	pslld	$12,%xmm14
+	por	%xmm6,%xmm13
+	psrld	$20,%xmm7
+	movdqa	(%r11),%xmm6
+	por	%xmm7,%xmm14
+	paddd	%xmm13,%xmm8
+	paddd	%xmm14,%xmm9
+	pxor	%xmm8,%xmm3
+	pxor	%xmm9,%xmm0
+.byte	102,15,56,0,222
+.byte	102,15,56,0,198
+	paddd	%xmm3,%xmm4
+	paddd	%xmm0,%xmm5
+	pxor	%xmm4,%xmm13
+	pxor	%xmm5,%xmm14
+	movdqa	%xmm13,%xmm7
+	pslld	$7,%xmm13
+	psrld	$25,%xmm7
+	movdqa	%xmm14,%xmm6
+	pslld	$7,%xmm14
+	por	%xmm7,%xmm13
+	psrld	$25,%xmm6
+	movdqa	(%r10),%xmm7
+	por	%xmm6,%xmm14
+	movdqa	%xmm4,32(%rsp)
+	movdqa	%xmm5,48(%rsp)
+	movdqa	0(%rsp),%xmm4
+	movdqa	16(%rsp),%xmm5
+	paddd	%xmm15,%xmm10
+	paddd	%xmm12,%xmm11
+	pxor	%xmm10,%xmm1
+	pxor	%xmm11,%xmm2
+.byte	102,15,56,0,207
+.byte	102,15,56,0,215
+	paddd	%xmm1,%xmm4
+	paddd	%xmm2,%xmm5
+	pxor	%xmm4,%xmm15
+	pxor	%xmm5,%xmm12
+	movdqa	%xmm15,%xmm6
+	pslld	$12,%xmm15
+	psrld	$20,%xmm6
+	movdqa	%xmm12,%xmm7
+	pslld	$12,%xmm12
+	por	%xmm6,%xmm15
+	psrld	$20,%xmm7
+	movdqa	(%r11),%xmm6
+	por	%xmm7,%xmm12
+	paddd	%xmm15,%xmm10
+	paddd	%xmm12,%xmm11
+	pxor	%xmm10,%xmm1
+	pxor	%xmm11,%xmm2
+.byte	102,15,56,0,206
+.byte	102,15,56,0,214
+	paddd	%xmm1,%xmm4
+	paddd	%xmm2,%xmm5
+	pxor	%xmm4,%xmm15
+	pxor	%xmm5,%xmm12
+	movdqa	%xmm15,%xmm7
+	pslld	$7,%xmm15
+	psrld	$25,%xmm7
+	movdqa	%xmm12,%xmm6
+	pslld	$7,%xmm12
+	por	%xmm7,%xmm15
+	psrld	$25,%xmm6
+	movdqa	(%r10),%xmm7
+	por	%xmm6,%xmm12
+	decl	%eax
+	jnz	.Loop4x
+
+	paddd	64(%rsp),%xmm8
+	paddd	80(%rsp),%xmm9
+	paddd	96(%rsp),%xmm10
+	paddd	112(%rsp),%xmm11
+
+	movdqa	%xmm8,%xmm6
+	punpckldq	%xmm9,%xmm8
+	movdqa	%xmm10,%xmm7
+	punpckldq	%xmm11,%xmm10
+	punpckhdq	%xmm9,%xmm6
+	punpckhdq	%xmm11,%xmm7
+	movdqa	%xmm8,%xmm9
+	punpcklqdq	%xmm10,%xmm8
+	movdqa	%xmm6,%xmm11
+	punpcklqdq	%xmm7,%xmm6
+	punpckhqdq	%xmm10,%xmm9
+	punpckhqdq	%xmm7,%xmm11
+	paddd	128-256(%rcx),%xmm12
+	paddd	144-256(%rcx),%xmm13
+	paddd	160-256(%rcx),%xmm14
+	paddd	176-256(%rcx),%xmm15
+
+	movdqa	%xmm8,0(%rsp)
+	movdqa	%xmm9,16(%rsp)
+	movdqa	32(%rsp),%xmm8
+	movdqa	48(%rsp),%xmm9
+
+	movdqa	%xmm12,%xmm10
+	punpckldq	%xmm13,%xmm12
+	movdqa	%xmm14,%xmm7
+	punpckldq	%xmm15,%xmm14
+	punpckhdq	%xmm13,%xmm10
+	punpckhdq	%xmm15,%xmm7
+	movdqa	%xmm12,%xmm13
+	punpcklqdq	%xmm14,%xmm12
+	movdqa	%xmm10,%xmm15
+	punpcklqdq	%xmm7,%xmm10
+	punpckhqdq	%xmm14,%xmm13
+	punpckhqdq	%xmm7,%xmm15
+	paddd	192-256(%rcx),%xmm4
+	paddd	208-256(%rcx),%xmm5
+	paddd	224-256(%rcx),%xmm8
+	paddd	240-256(%rcx),%xmm9
+
+	movdqa	%xmm6,32(%rsp)
+	movdqa	%xmm11,48(%rsp)
+
+	movdqa	%xmm4,%xmm14
+	punpckldq	%xmm5,%xmm4
+	movdqa	%xmm8,%xmm7
+	punpckldq	%xmm9,%xmm8
+	punpckhdq	%xmm5,%xmm14
+	punpckhdq	%xmm9,%xmm7
+	movdqa	%xmm4,%xmm5
+	punpcklqdq	%xmm8,%xmm4
+	movdqa	%xmm14,%xmm9
+	punpcklqdq	%xmm7,%xmm14
+	punpckhqdq	%xmm8,%xmm5
+	punpckhqdq	%xmm7,%xmm9
+	paddd	256-256(%rcx),%xmm0
+	paddd	272-256(%rcx),%xmm1
+	paddd	288-256(%rcx),%xmm2
+	paddd	304-256(%rcx),%xmm3
+
+	movdqa	%xmm0,%xmm8
+	punpckldq	%xmm1,%xmm0
+	movdqa	%xmm2,%xmm7
+	punpckldq	%xmm3,%xmm2
+	punpckhdq	%xmm1,%xmm8
+	punpckhdq	%xmm3,%xmm7
+	movdqa	%xmm0,%xmm1
+	punpcklqdq	%xmm2,%xmm0
+	movdqa	%xmm8,%xmm3
+	punpcklqdq	%xmm7,%xmm8
+	punpckhqdq	%xmm2,%xmm1
+	punpckhqdq	%xmm7,%xmm3
+	cmpq	$256,%rdx
+	jb	.Ltail4x
+
+	movdqu	0(%rsi),%xmm6
+	movdqu	16(%rsi),%xmm11
+	movdqu	32(%rsi),%xmm2
+	movdqu	48(%rsi),%xmm7
+	pxor	0(%rsp),%xmm6
+	pxor	%xmm12,%xmm11
+	pxor	%xmm4,%xmm2
+	pxor	%xmm0,%xmm7
+
+	movdqu	%xmm6,0(%rdi)
+	movdqu	64(%rsi),%xmm6
+	movdqu	%xmm11,16(%rdi)
+	movdqu	80(%rsi),%xmm11
+	movdqu	%xmm2,32(%rdi)
+	movdqu	96(%rsi),%xmm2
+	movdqu	%xmm7,48(%rdi)
+	movdqu	112(%rsi),%xmm7
+	leaq	128(%rsi),%rsi
+	pxor	16(%rsp),%xmm6
+	pxor	%xmm13,%xmm11
+	pxor	%xmm5,%xmm2
+	pxor	%xmm1,%xmm7
+
+	movdqu	%xmm6,64(%rdi)
+	movdqu	0(%rsi),%xmm6
+	movdqu	%xmm11,80(%rdi)
+	movdqu	16(%rsi),%xmm11
+	movdqu	%xmm2,96(%rdi)
+	movdqu	32(%rsi),%xmm2
+	movdqu	%xmm7,112(%rdi)
+	leaq	128(%rdi),%rdi
+	movdqu	48(%rsi),%xmm7
+	pxor	32(%rsp),%xmm6
+	pxor	%xmm10,%xmm11
+	pxor	%xmm14,%xmm2
+	pxor	%xmm8,%xmm7
+
+	movdqu	%xmm6,0(%rdi)
+	movdqu	64(%rsi),%xmm6
+	movdqu	%xmm11,16(%rdi)
+	movdqu	80(%rsi),%xmm11
+	movdqu	%xmm2,32(%rdi)
+	movdqu	96(%rsi),%xmm2
+	movdqu	%xmm7,48(%rdi)
+	movdqu	112(%rsi),%xmm7
+	leaq	128(%rsi),%rsi
+	pxor	48(%rsp),%xmm6
+	pxor	%xmm15,%xmm11
+	pxor	%xmm9,%xmm2
+	pxor	%xmm3,%xmm7
+	movdqu	%xmm6,64(%rdi)
+	movdqu	%xmm11,80(%rdi)
+	movdqu	%xmm2,96(%rdi)
+	movdqu	%xmm7,112(%rdi)
+	leaq	128(%rdi),%rdi
+
+	subq	$256,%rdx
+	jnz	.Loop_outer4x
+
+	jmp	.Ldone4x
+
+.Ltail4x:
+	cmpq	$192,%rdx
+	jae	.L192_or_more4x
+	cmpq	$128,%rdx
+	jae	.L128_or_more4x
+	cmpq	$64,%rdx
+	jae	.L64_or_more4x
+
+
+	xorq	%r10,%r10
+
+	movdqa	%xmm12,16(%rsp)
+	movdqa	%xmm4,32(%rsp)
+	movdqa	%xmm0,48(%rsp)
+	jmp	.Loop_tail4x
+
+.align	32
+.L64_or_more4x:
+	movdqu	0(%rsi),%xmm6
+	movdqu	16(%rsi),%xmm11
+	movdqu	32(%rsi),%xmm2
+	movdqu	48(%rsi),%xmm7
+	pxor	0(%rsp),%xmm6
+	pxor	%xmm12,%xmm11
+	pxor	%xmm4,%xmm2
+	pxor	%xmm0,%xmm7
+	movdqu	%xmm6,0(%rdi)
+	movdqu	%xmm11,16(%rdi)
+	movdqu	%xmm2,32(%rdi)
+	movdqu	%xmm7,48(%rdi)
+	je	.Ldone4x
+
+	movdqa	16(%rsp),%xmm6
+	leaq	64(%rsi),%rsi
+	xorq	%r10,%r10
+	movdqa	%xmm6,0(%rsp)
+	movdqa	%xmm13,16(%rsp)
+	leaq	64(%rdi),%rdi
+	movdqa	%xmm5,32(%rsp)
+	subq	$64,%rdx
+	movdqa	%xmm1,48(%rsp)
+	jmp	.Loop_tail4x
+
+.align	32
+.L128_or_more4x:
+	movdqu	0(%rsi),%xmm6
+	movdqu	16(%rsi),%xmm11
+	movdqu	32(%rsi),%xmm2
+	movdqu	48(%rsi),%xmm7
+	pxor	0(%rsp),%xmm6
+	pxor	%xmm12,%xmm11
+	pxor	%xmm4,%xmm2
+	pxor	%xmm0,%xmm7
+
+	movdqu	%xmm6,0(%rdi)
+	movdqu	64(%rsi),%xmm6
+	movdqu	%xmm11,16(%rdi)
+	movdqu	80(%rsi),%xmm11
+	movdqu	%xmm2,32(%rdi)
+	movdqu	96(%rsi),%xmm2
+	movdqu	%xmm7,48(%rdi)
+	movdqu	112(%rsi),%xmm7
+	pxor	16(%rsp),%xmm6
+	pxor	%xmm13,%xmm11
+	pxor	%xmm5,%xmm2
+	pxor	%xmm1,%xmm7
+	movdqu	%xmm6,64(%rdi)
+	movdqu	%xmm11,80(%rdi)
+	movdqu	%xmm2,96(%rdi)
+	movdqu	%xmm7,112(%rdi)
+	je	.Ldone4x
+
+	movdqa	32(%rsp),%xmm6
+	leaq	128(%rsi),%rsi
+	xorq	%r10,%r10
+	movdqa	%xmm6,0(%rsp)
+	movdqa	%xmm10,16(%rsp)
+	leaq	128(%rdi),%rdi
+	movdqa	%xmm14,32(%rsp)
+	subq	$128,%rdx
+	movdqa	%xmm8,48(%rsp)
+	jmp	.Loop_tail4x
+
+.align	32
+.L192_or_more4x:
+	movdqu	0(%rsi),%xmm6
+	movdqu	16(%rsi),%xmm11
+	movdqu	32(%rsi),%xmm2
+	movdqu	48(%rsi),%xmm7
+	pxor	0(%rsp),%xmm6
+	pxor	%xmm12,%xmm11
+	pxor	%xmm4,%xmm2
+	pxor	%xmm0,%xmm7
+
+	movdqu	%xmm6,0(%rdi)
+	movdqu	64(%rsi),%xmm6
+	movdqu	%xmm11,16(%rdi)
+	movdqu	80(%rsi),%xmm11
+	movdqu	%xmm2,32(%rdi)
+	movdqu	96(%rsi),%xmm2
+	movdqu	%xmm7,48(%rdi)
+	movdqu	112(%rsi),%xmm7
+	leaq	128(%rsi),%rsi
+	pxor	16(%rsp),%xmm6
+	pxor	%xmm13,%xmm11
+	pxor	%xmm5,%xmm2
+	pxor	%xmm1,%xmm7
+
+	movdqu	%xmm6,64(%rdi)
+	movdqu	0(%rsi),%xmm6
+	movdqu	%xmm11,80(%rdi)
+	movdqu	16(%rsi),%xmm11
+	movdqu	%xmm2,96(%rdi)
+	movdqu	32(%rsi),%xmm2
+	movdqu	%xmm7,112(%rdi)
+	leaq	128(%rdi),%rdi
+	movdqu	48(%rsi),%xmm7
+	pxor	32(%rsp),%xmm6
+	pxor	%xmm10,%xmm11
+	pxor	%xmm14,%xmm2
+	pxor	%xmm8,%xmm7
+	movdqu	%xmm6,0(%rdi)
+	movdqu	%xmm11,16(%rdi)
+	movdqu	%xmm2,32(%rdi)
+	movdqu	%xmm7,48(%rdi)
+	je	.Ldone4x
+
+	movdqa	48(%rsp),%xmm6
+	leaq	64(%rsi),%rsi
+	xorq	%r10,%r10
+	movdqa	%xmm6,0(%rsp)
+	movdqa	%xmm15,16(%rsp)
+	leaq	64(%rdi),%rdi
+	movdqa	%xmm9,32(%rsp)
+	subq	$192,%rdx
+	movdqa	%xmm3,48(%rsp)
+
+.Loop_tail4x:
+	movzbl	(%rsi,%r10,1),%eax
+	movzbl	(%rsp,%r10,1),%ecx
+	leaq	1(%r10),%r10
+	xorl	%ecx,%eax
+	movb	%al,-1(%rdi,%r10,1)
+	decq	%rdx
+	jnz	.Loop_tail4x
+
+.Ldone4x:
+	addq	$0x148+0,%rsp
+	.byte	0xf3,0xc3
+.size	ChaCha20_4x,.-ChaCha20_4x
+.type	ChaCha20_8x,@function
+.align	32
+ChaCha20_8x:
+.LChaCha20_8x:
+	movq	%rsp,%r10
+	subq	$0x280+8,%rsp
+	andq	$-32,%rsp
+	vzeroupper
+	movq	%r10,640(%rsp)
+
+
+
+
+
+
+
+
+
+
+	vbroadcasti128	.Lsigma(%rip),%ymm11
+	vbroadcasti128	(%rcx),%ymm3
+	vbroadcasti128	16(%rcx),%ymm15
+	vbroadcasti128	(%r8),%ymm7
+	leaq	256(%rsp),%rcx
+	leaq	512(%rsp),%rax
+	leaq	.Lrot16(%rip),%r10
+	leaq	.Lrot24(%rip),%r11
+
+	vpshufd	$0x00,%ymm11,%ymm8
+	vpshufd	$0x55,%ymm11,%ymm9
+	vmovdqa	%ymm8,128-256(%rcx)
+	vpshufd	$0xaa,%ymm11,%ymm10
+	vmovdqa	%ymm9,160-256(%rcx)
+	vpshufd	$0xff,%ymm11,%ymm11
+	vmovdqa	%ymm10,192-256(%rcx)
+	vmovdqa	%ymm11,224-256(%rcx)
+
+	vpshufd	$0x00,%ymm3,%ymm0
+	vpshufd	$0x55,%ymm3,%ymm1
+	vmovdqa	%ymm0,256-256(%rcx)
+	vpshufd	$0xaa,%ymm3,%ymm2
+	vmovdqa	%ymm1,288-256(%rcx)
+	vpshufd	$0xff,%ymm3,%ymm3
+	vmovdqa	%ymm2,320-256(%rcx)
+	vmovdqa	%ymm3,352-256(%rcx)
+
+	vpshufd	$0x00,%ymm15,%ymm12
+	vpshufd	$0x55,%ymm15,%ymm13
+	vmovdqa	%ymm12,384-512(%rax)
+	vpshufd	$0xaa,%ymm15,%ymm14
+	vmovdqa	%ymm13,416-512(%rax)
+	vpshufd	$0xff,%ymm15,%ymm15
+	vmovdqa	%ymm14,448-512(%rax)
+	vmovdqa	%ymm15,480-512(%rax)
+
+	vpshufd	$0x00,%ymm7,%ymm4
+	vpshufd	$0x55,%ymm7,%ymm5
+	vpaddd	.Lincy(%rip),%ymm4,%ymm4
+	vpshufd	$0xaa,%ymm7,%ymm6
+	vmovdqa	%ymm5,544-512(%rax)
+	vpshufd	$0xff,%ymm7,%ymm7
+	vmovdqa	%ymm6,576-512(%rax)
+	vmovdqa	%ymm7,608-512(%rax)
+
+	jmp	.Loop_enter8x
+
+.align	32
+.Loop_outer8x:
+	vmovdqa	128-256(%rcx),%ymm8
+	vmovdqa	160-256(%rcx),%ymm9
+	vmovdqa	192-256(%rcx),%ymm10
+	vmovdqa	224-256(%rcx),%ymm11
+	vmovdqa	256-256(%rcx),%ymm0
+	vmovdqa	288-256(%rcx),%ymm1
+	vmovdqa	320-256(%rcx),%ymm2
+	vmovdqa	352-256(%rcx),%ymm3
+	vmovdqa	384-512(%rax),%ymm12
+	vmovdqa	416-512(%rax),%ymm13
+	vmovdqa	448-512(%rax),%ymm14
+	vmovdqa	480-512(%rax),%ymm15
+	vmovdqa	512-512(%rax),%ymm4
+	vmovdqa	544-512(%rax),%ymm5
+	vmovdqa	576-512(%rax),%ymm6
+	vmovdqa	608-512(%rax),%ymm7
+	vpaddd	.Leight(%rip),%ymm4,%ymm4
+
+.Loop_enter8x:
+	vmovdqa	%ymm14,64(%rsp)
+	vmovdqa	%ymm15,96(%rsp)
+	vbroadcasti128	(%r10),%ymm15
+	vmovdqa	%ymm4,512-512(%rax)
+	movl	$10,%eax
+	jmp	.Loop8x
+
+.align	32
+.Loop8x:
+	vpaddd	%ymm0,%ymm8,%ymm8
+	vpxor	%ymm4,%ymm8,%ymm4
+	vpshufb	%ymm15,%ymm4,%ymm4
+	vpaddd	%ymm1,%ymm9,%ymm9
+	vpxor	%ymm5,%ymm9,%ymm5
+	vpshufb	%ymm15,%ymm5,%ymm5
+	vpaddd	%ymm4,%ymm12,%ymm12
+	vpxor	%ymm0,%ymm12,%ymm0
+	vpslld	$12,%ymm0,%ymm14
+	vpsrld	$20,%ymm0,%ymm0
+	vpor	%ymm0,%ymm14,%ymm0
+	vbroadcasti128	(%r11),%ymm14
+	vpaddd	%ymm5,%ymm13,%ymm13
+	vpxor	%ymm1,%ymm13,%ymm1
+	vpslld	$12,%ymm1,%ymm15
+	vpsrld	$20,%ymm1,%ymm1
+	vpor	%ymm1,%ymm15,%ymm1
+	vpaddd	%ymm0,%ymm8,%ymm8
+	vpxor	%ymm4,%ymm8,%ymm4
+	vpshufb	%ymm14,%ymm4,%ymm4
+	vpaddd	%ymm1,%ymm9,%ymm9
+	vpxor	%ymm5,%ymm9,%ymm5
+	vpshufb	%ymm14,%ymm5,%ymm5
+	vpaddd	%ymm4,%ymm12,%ymm12
+	vpxor	%ymm0,%ymm12,%ymm0
+	vpslld	$7,%ymm0,%ymm15
+	vpsrld	$25,%ymm0,%ymm0
+	vpor	%ymm0,%ymm15,%ymm0
+	vbroadcasti128	(%r10),%ymm15
+	vpaddd	%ymm5,%ymm13,%ymm13
+	vpxor	%ymm1,%ymm13,%ymm1
+	vpslld	$7,%ymm1,%ymm14
+	vpsrld	$25,%ymm1,%ymm1
+	vpor	%ymm1,%ymm14,%ymm1
+	vmovdqa	%ymm12,0(%rsp)
+	vmovdqa	%ymm13,32(%rsp)
+	vmovdqa	64(%rsp),%ymm12
+	vmovdqa	96(%rsp),%ymm13
+	vpaddd	%ymm2,%ymm10,%ymm10
+	vpxor	%ymm6,%ymm10,%ymm6
+	vpshufb	%ymm15,%ymm6,%ymm6
+	vpaddd	%ymm3,%ymm11,%ymm11
+	vpxor	%ymm7,%ymm11,%ymm7
+	vpshufb	%ymm15,%ymm7,%ymm7
+	vpaddd	%ymm6,%ymm12,%ymm12
+	vpxor	%ymm2,%ymm12,%ymm2
+	vpslld	$12,%ymm2,%ymm14
+	vpsrld	$20,%ymm2,%ymm2
+	vpor	%ymm2,%ymm14,%ymm2
+	vbroadcasti128	(%r11),%ymm14
+	vpaddd	%ymm7,%ymm13,%ymm13
+	vpxor	%ymm3,%ymm13,%ymm3
+	vpslld	$12,%ymm3,%ymm15
+	vpsrld	$20,%ymm3,%ymm3
+	vpor	%ymm3,%ymm15,%ymm3
+	vpaddd	%ymm2,%ymm10,%ymm10
+	vpxor	%ymm6,%ymm10,%ymm6
+	vpshufb	%ymm14,%ymm6,%ymm6
+	vpaddd	%ymm3,%ymm11,%ymm11
+	vpxor	%ymm7,%ymm11,%ymm7
+	vpshufb	%ymm14,%ymm7,%ymm7
+	vpaddd	%ymm6,%ymm12,%ymm12
+	vpxor	%ymm2,%ymm12,%ymm2
+	vpslld	$7,%ymm2,%ymm15
+	vpsrld	$25,%ymm2,%ymm2
+	vpor	%ymm2,%ymm15,%ymm2
+	vbroadcasti128	(%r10),%ymm15
+	vpaddd	%ymm7,%ymm13,%ymm13
+	vpxor	%ymm3,%ymm13,%ymm3
+	vpslld	$7,%ymm3,%ymm14
+	vpsrld	$25,%ymm3,%ymm3
+	vpor	%ymm3,%ymm14,%ymm3
+	vpaddd	%ymm1,%ymm8,%ymm8
+	vpxor	%ymm7,%ymm8,%ymm7
+	vpshufb	%ymm15,%ymm7,%ymm7
+	vpaddd	%ymm2,%ymm9,%ymm9
+	vpxor	%ymm4,%ymm9,%ymm4
+	vpshufb	%ymm15,%ymm4,%ymm4
+	vpaddd	%ymm7,%ymm12,%ymm12
+	vpxor	%ymm1,%ymm12,%ymm1
+	vpslld	$12,%ymm1,%ymm14
+	vpsrld	$20,%ymm1,%ymm1
+	vpor	%ymm1,%ymm14,%ymm1
+	vbroadcasti128	(%r11),%ymm14
+	vpaddd	%ymm4,%ymm13,%ymm13
+	vpxor	%ymm2,%ymm13,%ymm2
+	vpslld	$12,%ymm2,%ymm15
+	vpsrld	$20,%ymm2,%ymm2
+	vpor	%ymm2,%ymm15,%ymm2
+	vpaddd	%ymm1,%ymm8,%ymm8
+	vpxor	%ymm7,%ymm8,%ymm7
+	vpshufb	%ymm14,%ymm7,%ymm7
+	vpaddd	%ymm2,%ymm9,%ymm9
+	vpxor	%ymm4,%ymm9,%ymm4
+	vpshufb	%ymm14,%ymm4,%ymm4
+	vpaddd	%ymm7,%ymm12,%ymm12
+	vpxor	%ymm1,%ymm12,%ymm1
+	vpslld	$7,%ymm1,%ymm15
+	vpsrld	$25,%ymm1,%ymm1
+	vpor	%ymm1,%ymm15,%ymm1
+	vbroadcasti128	(%r10),%ymm15
+	vpaddd	%ymm4,%ymm13,%ymm13
+	vpxor	%ymm2,%ymm13,%ymm2
+	vpslld	$7,%ymm2,%ymm14
+	vpsrld	$25,%ymm2,%ymm2
+	vpor	%ymm2,%ymm14,%ymm2
+	vmovdqa	%ymm12,64(%rsp)
+	vmovdqa	%ymm13,96(%rsp)
+	vmovdqa	0(%rsp),%ymm12
+	vmovdqa	32(%rsp),%ymm13
+	vpaddd	%ymm3,%ymm10,%ymm10
+	vpxor	%ymm5,%ymm10,%ymm5
+	vpshufb	%ymm15,%ymm5,%ymm5
+	vpaddd	%ymm0,%ymm11,%ymm11
+	vpxor	%ymm6,%ymm11,%ymm6
+	vpshufb	%ymm15,%ymm6,%ymm6
+	vpaddd	%ymm5,%ymm12,%ymm12
+	vpxor	%ymm3,%ymm12,%ymm3
+	vpslld	$12,%ymm3,%ymm14
+	vpsrld	$20,%ymm3,%ymm3
+	vpor	%ymm3,%ymm14,%ymm3
+	vbroadcasti128	(%r11),%ymm14
+	vpaddd	%ymm6,%ymm13,%ymm13
+	vpxor	%ymm0,%ymm13,%ymm0
+	vpslld	$12,%ymm0,%ymm15
+	vpsrld	$20,%ymm0,%ymm0
+	vpor	%ymm0,%ymm15,%ymm0
+	vpaddd	%ymm3,%ymm10,%ymm10
+	vpxor	%ymm5,%ymm10,%ymm5
+	vpshufb	%ymm14,%ymm5,%ymm5
+	vpaddd	%ymm0,%ymm11,%ymm11
+	vpxor	%ymm6,%ymm11,%ymm6
+	vpshufb	%ymm14,%ymm6,%ymm6
+	vpaddd	%ymm5,%ymm12,%ymm12
+	vpxor	%ymm3,%ymm12,%ymm3
+	vpslld	$7,%ymm3,%ymm15
+	vpsrld	$25,%ymm3,%ymm3
+	vpor	%ymm3,%ymm15,%ymm3
+	vbroadcasti128	(%r10),%ymm15
+	vpaddd	%ymm6,%ymm13,%ymm13
+	vpxor	%ymm0,%ymm13,%ymm0
+	vpslld	$7,%ymm0,%ymm14
+	vpsrld	$25,%ymm0,%ymm0
+	vpor	%ymm0,%ymm14,%ymm0
+	decl	%eax
+	jnz	.Loop8x
+
+	leaq	512(%rsp),%rax
+	vpaddd	128-256(%rcx),%ymm8,%ymm8
+	vpaddd	160-256(%rcx),%ymm9,%ymm9
+	vpaddd	192-256(%rcx),%ymm10,%ymm10
+	vpaddd	224-256(%rcx),%ymm11,%ymm11
+
+	vpunpckldq	%ymm9,%ymm8,%ymm14
+	vpunpckldq	%ymm11,%ymm10,%ymm15
+	vpunpckhdq	%ymm9,%ymm8,%ymm8
+	vpunpckhdq	%ymm11,%ymm10,%ymm10
+	vpunpcklqdq	%ymm15,%ymm14,%ymm9
+	vpunpckhqdq	%ymm15,%ymm14,%ymm14
+	vpunpcklqdq	%ymm10,%ymm8,%ymm11
+	vpunpckhqdq	%ymm10,%ymm8,%ymm8
+	vpaddd	256-256(%rcx),%ymm0,%ymm0
+	vpaddd	288-256(%rcx),%ymm1,%ymm1
+	vpaddd	320-256(%rcx),%ymm2,%ymm2
+	vpaddd	352-256(%rcx),%ymm3,%ymm3
+
+	vpunpckldq	%ymm1,%ymm0,%ymm10
+	vpunpckldq	%ymm3,%ymm2,%ymm15
+	vpunpckhdq	%ymm1,%ymm0,%ymm0
+	vpunpckhdq	%ymm3,%ymm2,%ymm2
+	vpunpcklqdq	%ymm15,%ymm10,%ymm1
+	vpunpckhqdq	%ymm15,%ymm10,%ymm10
+	vpunpcklqdq	%ymm2,%ymm0,%ymm3
+	vpunpckhqdq	%ymm2,%ymm0,%ymm0
+	vperm2i128	$0x20,%ymm1,%ymm9,%ymm15
+	vperm2i128	$0x31,%ymm1,%ymm9,%ymm1
+	vperm2i128	$0x20,%ymm10,%ymm14,%ymm9
+	vperm2i128	$0x31,%ymm10,%ymm14,%ymm10
+	vperm2i128	$0x20,%ymm3,%ymm11,%ymm14
+	vperm2i128	$0x31,%ymm3,%ymm11,%ymm3
+	vperm2i128	$0x20,%ymm0,%ymm8,%ymm11
+	vperm2i128	$0x31,%ymm0,%ymm8,%ymm0
+	vmovdqa	%ymm15,0(%rsp)
+	vmovdqa	%ymm9,32(%rsp)
+	vmovdqa	64(%rsp),%ymm15
+	vmovdqa	96(%rsp),%ymm9
+
+	vpaddd	384-512(%rax),%ymm12,%ymm12
+	vpaddd	416-512(%rax),%ymm13,%ymm13
+	vpaddd	448-512(%rax),%ymm15,%ymm15
+	vpaddd	480-512(%rax),%ymm9,%ymm9
+
+	vpunpckldq	%ymm13,%ymm12,%ymm2
+	vpunpckldq	%ymm9,%ymm15,%ymm8
+	vpunpckhdq	%ymm13,%ymm12,%ymm12
+	vpunpckhdq	%ymm9,%ymm15,%ymm15
+	vpunpcklqdq	%ymm8,%ymm2,%ymm13
+	vpunpckhqdq	%ymm8,%ymm2,%ymm2
+	vpunpcklqdq	%ymm15,%ymm12,%ymm9
+	vpunpckhqdq	%ymm15,%ymm12,%ymm12
+	vpaddd	512-512(%rax),%ymm4,%ymm4
+	vpaddd	544-512(%rax),%ymm5,%ymm5
+	vpaddd	576-512(%rax),%ymm6,%ymm6
+	vpaddd	608-512(%rax),%ymm7,%ymm7
+
+	vpunpckldq	%ymm5,%ymm4,%ymm15
+	vpunpckldq	%ymm7,%ymm6,%ymm8
+	vpunpckhdq	%ymm5,%ymm4,%ymm4
+	vpunpckhdq	%ymm7,%ymm6,%ymm6
+	vpunpcklqdq	%ymm8,%ymm15,%ymm5
+	vpunpckhqdq	%ymm8,%ymm15,%ymm15
+	vpunpcklqdq	%ymm6,%ymm4,%ymm7
+	vpunpckhqdq	%ymm6,%ymm4,%ymm4
+	vperm2i128	$0x20,%ymm5,%ymm13,%ymm8
+	vperm2i128	$0x31,%ymm5,%ymm13,%ymm5
+	vperm2i128	$0x20,%ymm15,%ymm2,%ymm13
+	vperm2i128	$0x31,%ymm15,%ymm2,%ymm15
+	vperm2i128	$0x20,%ymm7,%ymm9,%ymm2
+	vperm2i128	$0x31,%ymm7,%ymm9,%ymm7
+	vperm2i128	$0x20,%ymm4,%ymm12,%ymm9
+	vperm2i128	$0x31,%ymm4,%ymm12,%ymm4
+	vmovdqa	0(%rsp),%ymm6
+	vmovdqa	32(%rsp),%ymm12
+
+	cmpq	$512,%rdx
+	jb	.Ltail8x
+
+	vpxor	0(%rsi),%ymm6,%ymm6
+	vpxor	32(%rsi),%ymm8,%ymm8
+	vpxor	64(%rsi),%ymm1,%ymm1
+	vpxor	96(%rsi),%ymm5,%ymm5
+	leaq	128(%rsi),%rsi
+	vmovdqu	%ymm6,0(%rdi)
+	vmovdqu	%ymm8,32(%rdi)
+	vmovdqu	%ymm1,64(%rdi)
+	vmovdqu	%ymm5,96(%rdi)
+	leaq	128(%rdi),%rdi
+
+	vpxor	0(%rsi),%ymm12,%ymm12
+	vpxor	32(%rsi),%ymm13,%ymm13
+	vpxor	64(%rsi),%ymm10,%ymm10
+	vpxor	96(%rsi),%ymm15,%ymm15
+	leaq	128(%rsi),%rsi
+	vmovdqu	%ymm12,0(%rdi)
+	vmovdqu	%ymm13,32(%rdi)
+	vmovdqu	%ymm10,64(%rdi)
+	vmovdqu	%ymm15,96(%rdi)
+	leaq	128(%rdi),%rdi
+
+	vpxor	0(%rsi),%ymm14,%ymm14
+	vpxor	32(%rsi),%ymm2,%ymm2
+	vpxor	64(%rsi),%ymm3,%ymm3
+	vpxor	96(%rsi),%ymm7,%ymm7
+	leaq	128(%rsi),%rsi
+	vmovdqu	%ymm14,0(%rdi)
+	vmovdqu	%ymm2,32(%rdi)
+	vmovdqu	%ymm3,64(%rdi)
+	vmovdqu	%ymm7,96(%rdi)
+	leaq	128(%rdi),%rdi
+
+	vpxor	0(%rsi),%ymm11,%ymm11
+	vpxor	32(%rsi),%ymm9,%ymm9
+	vpxor	64(%rsi),%ymm0,%ymm0
+	vpxor	96(%rsi),%ymm4,%ymm4
+	leaq	128(%rsi),%rsi
+	vmovdqu	%ymm11,0(%rdi)
+	vmovdqu	%ymm9,32(%rdi)
+	vmovdqu	%ymm0,64(%rdi)
+	vmovdqu	%ymm4,96(%rdi)
+	leaq	128(%rdi),%rdi
+
+	subq	$512,%rdx
+	jnz	.Loop_outer8x
+
+	jmp	.Ldone8x
+
+.Ltail8x:
+	cmpq	$448,%rdx
+	jae	.L448_or_more8x
+	cmpq	$384,%rdx
+	jae	.L384_or_more8x
+	cmpq	$320,%rdx
+	jae	.L320_or_more8x
+	cmpq	$256,%rdx
+	jae	.L256_or_more8x
+	cmpq	$192,%rdx
+	jae	.L192_or_more8x
+	cmpq	$128,%rdx
+	jae	.L128_or_more8x
+	cmpq	$64,%rdx
+	jae	.L64_or_more8x
+
+	xorq	%r10,%r10
+	vmovdqa	%ymm6,0(%rsp)
+	vmovdqa	%ymm8,32(%rsp)
+	jmp	.Loop_tail8x
+
+.align	32
+.L64_or_more8x:
+	vpxor	0(%rsi),%ymm6,%ymm6
+	vpxor	32(%rsi),%ymm8,%ymm8
+	vmovdqu	%ymm6,0(%rdi)
+	vmovdqu	%ymm8,32(%rdi)
+	je	.Ldone8x
+
+	leaq	64(%rsi),%rsi
+	xorq	%r10,%r10
+	vmovdqa	%ymm1,0(%rsp)
+	leaq	64(%rdi),%rdi
+	subq	$64,%rdx
+	vmovdqa	%ymm5,32(%rsp)
+	jmp	.Loop_tail8x
+
+.align	32
+.L128_or_more8x:
+	vpxor	0(%rsi),%ymm6,%ymm6
+	vpxor	32(%rsi),%ymm8,%ymm8
+	vpxor	64(%rsi),%ymm1,%ymm1
+	vpxor	96(%rsi),%ymm5,%ymm5
+	vmovdqu	%ymm6,0(%rdi)
+	vmovdqu	%ymm8,32(%rdi)
+	vmovdqu	%ymm1,64(%rdi)
+	vmovdqu	%ymm5,96(%rdi)
+	je	.Ldone8x
+
+	leaq	128(%rsi),%rsi
+	xorq	%r10,%r10
+	vmovdqa	%ymm12,0(%rsp)
+	leaq	128(%rdi),%rdi
+	subq	$128,%rdx
+	vmovdqa	%ymm13,32(%rsp)
+	jmp	.Loop_tail8x
+
+.align	32
+.L192_or_more8x:
+	vpxor	0(%rsi),%ymm6,%ymm6
+	vpxor	32(%rsi),%ymm8,%ymm8
+	vpxor	64(%rsi),%ymm1,%ymm1
+	vpxor	96(%rsi),%ymm5,%ymm5
+	vpxor	128(%rsi),%ymm12,%ymm12
+	vpxor	160(%rsi),%ymm13,%ymm13
+	vmovdqu	%ymm6,0(%rdi)
+	vmovdqu	%ymm8,32(%rdi)
+	vmovdqu	%ymm1,64(%rdi)
+	vmovdqu	%ymm5,96(%rdi)
+	vmovdqu	%ymm12,128(%rdi)
+	vmovdqu	%ymm13,160(%rdi)
+	je	.Ldone8x
+
+	leaq	192(%rsi),%rsi
+	xorq	%r10,%r10
+	vmovdqa	%ymm10,0(%rsp)
+	leaq	192(%rdi),%rdi
+	subq	$192,%rdx
+	vmovdqa	%ymm15,32(%rsp)
+	jmp	.Loop_tail8x
+
+.align	32
+.L256_or_more8x:
+	vpxor	0(%rsi),%ymm6,%ymm6
+	vpxor	32(%rsi),%ymm8,%ymm8
+	vpxor	64(%rsi),%ymm1,%ymm1
+	vpxor	96(%rsi),%ymm5,%ymm5
+	vpxor	128(%rsi),%ymm12,%ymm12
+	vpxor	160(%rsi),%ymm13,%ymm13
+	vpxor	192(%rsi),%ymm10,%ymm10
+	vpxor	224(%rsi),%ymm15,%ymm15
+	vmovdqu	%ymm6,0(%rdi)
+	vmovdqu	%ymm8,32(%rdi)
+	vmovdqu	%ymm1,64(%rdi)
+	vmovdqu	%ymm5,96(%rdi)
+	vmovdqu	%ymm12,128(%rdi)
+	vmovdqu	%ymm13,160(%rdi)
+	vmovdqu	%ymm10,192(%rdi)
+	vmovdqu	%ymm15,224(%rdi)
+	je	.Ldone8x
+
+	leaq	256(%rsi),%rsi
+	xorq	%r10,%r10
+	vmovdqa	%ymm14,0(%rsp)
+	leaq	256(%rdi),%rdi
+	subq	$256,%rdx
+	vmovdqa	%ymm2,32(%rsp)
+	jmp	.Loop_tail8x
+
+.align	32
+.L320_or_more8x:
+	vpxor	0(%rsi),%ymm6,%ymm6
+	vpxor	32(%rsi),%ymm8,%ymm8
+	vpxor	64(%rsi),%ymm1,%ymm1
+	vpxor	96(%rsi),%ymm5,%ymm5
+	vpxor	128(%rsi),%ymm12,%ymm12
+	vpxor	160(%rsi),%ymm13,%ymm13
+	vpxor	192(%rsi),%ymm10,%ymm10
+	vpxor	224(%rsi),%ymm15,%ymm15
+	vpxor	256(%rsi),%ymm14,%ymm14
+	vpxor	288(%rsi),%ymm2,%ymm2
+	vmovdqu	%ymm6,0(%rdi)
+	vmovdqu	%ymm8,32(%rdi)
+	vmovdqu	%ymm1,64(%rdi)
+	vmovdqu	%ymm5,96(%rdi)
+	vmovdqu	%ymm12,128(%rdi)
+	vmovdqu	%ymm13,160(%rdi)
+	vmovdqu	%ymm10,192(%rdi)
+	vmovdqu	%ymm15,224(%rdi)
+	vmovdqu	%ymm14,256(%rdi)
+	vmovdqu	%ymm2,288(%rdi)
+	je	.Ldone8x
+
+	leaq	320(%rsi),%rsi
+	xorq	%r10,%r10
+	vmovdqa	%ymm3,0(%rsp)
+	leaq	320(%rdi),%rdi
+	subq	$320,%rdx
+	vmovdqa	%ymm7,32(%rsp)
+	jmp	.Loop_tail8x
+
+.align	32
+.L384_or_more8x:
+	vpxor	0(%rsi),%ymm6,%ymm6
+	vpxor	32(%rsi),%ymm8,%ymm8
+	vpxor	64(%rsi),%ymm1,%ymm1
+	vpxor	96(%rsi),%ymm5,%ymm5
+	vpxor	128(%rsi),%ymm12,%ymm12
+	vpxor	160(%rsi),%ymm13,%ymm13
+	vpxor	192(%rsi),%ymm10,%ymm10
+	vpxor	224(%rsi),%ymm15,%ymm15
+	vpxor	256(%rsi),%ymm14,%ymm14
+	vpxor	288(%rsi),%ymm2,%ymm2
+	vpxor	320(%rsi),%ymm3,%ymm3
+	vpxor	352(%rsi),%ymm7,%ymm7
+	vmovdqu	%ymm6,0(%rdi)
+	vmovdqu	%ymm8,32(%rdi)
+	vmovdqu	%ymm1,64(%rdi)
+	vmovdqu	%ymm5,96(%rdi)
+	vmovdqu	%ymm12,128(%rdi)
+	vmovdqu	%ymm13,160(%rdi)
+	vmovdqu	%ymm10,192(%rdi)
+	vmovdqu	%ymm15,224(%rdi)
+	vmovdqu	%ymm14,256(%rdi)
+	vmovdqu	%ymm2,288(%rdi)
+	vmovdqu	%ymm3,320(%rdi)
+	vmovdqu	%ymm7,352(%rdi)
+	je	.Ldone8x
+
+	leaq	384(%rsi),%rsi
+	xorq	%r10,%r10
+	vmovdqa	%ymm11,0(%rsp)
+	leaq	384(%rdi),%rdi
+	subq	$384,%rdx
+	vmovdqa	%ymm9,32(%rsp)
+	jmp	.Loop_tail8x
+
+.align	32
+.L448_or_more8x:
+	vpxor	0(%rsi),%ymm6,%ymm6
+	vpxor	32(%rsi),%ymm8,%ymm8
+	vpxor	64(%rsi),%ymm1,%ymm1
+	vpxor	96(%rsi),%ymm5,%ymm5
+	vpxor	128(%rsi),%ymm12,%ymm12
+	vpxor	160(%rsi),%ymm13,%ymm13
+	vpxor	192(%rsi),%ymm10,%ymm10
+	vpxor	224(%rsi),%ymm15,%ymm15
+	vpxor	256(%rsi),%ymm14,%ymm14
+	vpxor	288(%rsi),%ymm2,%ymm2
+	vpxor	320(%rsi),%ymm3,%ymm3
+	vpxor	352(%rsi),%ymm7,%ymm7
+	vpxor	384(%rsi),%ymm11,%ymm11
+	vpxor	416(%rsi),%ymm9,%ymm9
+	vmovdqu	%ymm6,0(%rdi)
+	vmovdqu	%ymm8,32(%rdi)
+	vmovdqu	%ymm1,64(%rdi)
+	vmovdqu	%ymm5,96(%rdi)
+	vmovdqu	%ymm12,128(%rdi)
+	vmovdqu	%ymm13,160(%rdi)
+	vmovdqu	%ymm10,192(%rdi)
+	vmovdqu	%ymm15,224(%rdi)
+	vmovdqu	%ymm14,256(%rdi)
+	vmovdqu	%ymm2,288(%rdi)
+	vmovdqu	%ymm3,320(%rdi)
+	vmovdqu	%ymm7,352(%rdi)
+	vmovdqu	%ymm11,384(%rdi)
+	vmovdqu	%ymm9,416(%rdi)
+	je	.Ldone8x
+
+	leaq	448(%rsi),%rsi
+	xorq	%r10,%r10
+	vmovdqa	%ymm0,0(%rsp)
+	leaq	448(%rdi),%rdi
+	subq	$448,%rdx
+	vmovdqa	%ymm4,32(%rsp)
+
+.Loop_tail8x:
+	movzbl	(%rsi,%r10,1),%eax
+	movzbl	(%rsp,%r10,1),%ecx
+	leaq	1(%r10),%r10
+	xorl	%ecx,%eax
+	movb	%al,-1(%rdi,%r10,1)
+	decq	%rdx
+	jnz	.Loop_tail8x
+
+.Ldone8x:
+	vzeroall
+	movq	640(%rsp),%rsp
+	.byte	0xf3,0xc3
+.size	ChaCha20_8x,.-ChaCha20_8x
+#endif
diff --git a/packager/third_party/boringssl/linux-x86_64/crypto/ec/p256-x86_64-asm.S b/packager/third_party/boringssl/linux-x86_64/crypto/ec/p256-x86_64-asm.S
new file mode 100644
index 0000000000..4abce6f91e
--- /dev/null
+++ b/packager/third_party/boringssl/linux-x86_64/crypto/ec/p256-x86_64-asm.S
@@ -0,0 +1,1789 @@
+#if defined(__x86_64__)
+.text	
+.extern	OPENSSL_ia32cap_P
+.hidden OPENSSL_ia32cap_P
+
+
+.align	64
+.Lpoly:
+.quad	0xffffffffffffffff, 0x00000000ffffffff, 0x0000000000000000, 0xffffffff00000001
+
+.LOne:
+.long	1,1,1,1,1,1,1,1
+.LTwo:
+.long	2,2,2,2,2,2,2,2
+.LThree:
+.long	3,3,3,3,3,3,3,3
+.LONE_mont:
+.quad	0x0000000000000001, 0xffffffff00000000, 0xffffffffffffffff, 0x00000000fffffffe
+
+.type	ecp_nistz256_mul_by_2,@function
+.align	64
+ecp_nistz256_mul_by_2:
+	pushq	%r12
+	pushq	%r13
+
+	movq	0(%rsi),%r8
+	movq	8(%rsi),%r9
+	addq	%r8,%r8
+	movq	16(%rsi),%r10
+	adcq	%r9,%r9
+	movq	24(%rsi),%r11
+	leaq	.Lpoly(%rip),%rsi
+	movq	%r8,%rax
+	adcq	%r10,%r10
+	adcq	%r11,%r11
+	movq	%r9,%rdx
+	sbbq	%r13,%r13
+
+	subq	0(%rsi),%r8
+	movq	%r10,%rcx
+	sbbq	8(%rsi),%r9
+	sbbq	16(%rsi),%r10
+	movq	%r11,%r12
+	sbbq	24(%rsi),%r11
+	testq	%r13,%r13
+
+	cmovzq	%rax,%r8
+	cmovzq	%rdx,%r9
+	movq	%r8,0(%rdi)
+	cmovzq	%rcx,%r10
+	movq	%r9,8(%rdi)
+	cmovzq	%r12,%r11
+	movq	%r10,16(%rdi)
+	movq	%r11,24(%rdi)
+
+	popq	%r13
+	popq	%r12
+	.byte	0xf3,0xc3
+.size	ecp_nistz256_mul_by_2,.-ecp_nistz256_mul_by_2
+
+
+
+.globl	ecp_nistz256_neg
+.hidden ecp_nistz256_neg
+.type	ecp_nistz256_neg,@function
+.align	32
+ecp_nistz256_neg:
+	pushq	%r12
+	pushq	%r13
+
+	xorq	%r8,%r8
+	xorq	%r9,%r9
+	xorq	%r10,%r10
+	xorq	%r11,%r11
+	xorq	%r13,%r13
+
+	subq	0(%rsi),%r8
+	sbbq	8(%rsi),%r9
+	sbbq	16(%rsi),%r10
+	movq	%r8,%rax
+	sbbq	24(%rsi),%r11
+	leaq	.Lpoly(%rip),%rsi
+	movq	%r9,%rdx
+	sbbq	$0,%r13
+
+	addq	0(%rsi),%r8
+	movq	%r10,%rcx
+	adcq	8(%rsi),%r9
+	adcq	16(%rsi),%r10
+	movq	%r11,%r12
+	adcq	24(%rsi),%r11
+	testq	%r13,%r13
+
+	cmovzq	%rax,%r8
+	cmovzq	%rdx,%r9
+	movq	%r8,0(%rdi)
+	cmovzq	%rcx,%r10
+	movq	%r9,8(%rdi)
+	cmovzq	%r12,%r11
+	movq	%r10,16(%rdi)
+	movq	%r11,24(%rdi)
+
+	popq	%r13
+	popq	%r12
+	.byte	0xf3,0xc3
+.size	ecp_nistz256_neg,.-ecp_nistz256_neg
+
+
+
+
+
+
+.globl	ecp_nistz256_mul_mont
+.hidden ecp_nistz256_mul_mont
+.type	ecp_nistz256_mul_mont,@function
+.align	32
+ecp_nistz256_mul_mont:
+.Lmul_mont:
+	pushq	%rbp
+	pushq	%rbx
+	pushq	%r12
+	pushq	%r13
+	pushq	%r14
+	pushq	%r15
+	movq	%rdx,%rbx
+	movq	0(%rdx),%rax
+	movq	0(%rsi),%r9
+	movq	8(%rsi),%r10
+	movq	16(%rsi),%r11
+	movq	24(%rsi),%r12
+
+	call	__ecp_nistz256_mul_montq
+.Lmul_mont_done:
+	popq	%r15
+	popq	%r14
+	popq	%r13
+	popq	%r12
+	popq	%rbx
+	popq	%rbp
+	.byte	0xf3,0xc3
+.size	ecp_nistz256_mul_mont,.-ecp_nistz256_mul_mont
+
+.type	__ecp_nistz256_mul_montq,@function
+.align	32
+__ecp_nistz256_mul_montq:
+
+
+	movq	%rax,%rbp
+	mulq	%r9
+	movq	.Lpoly+8(%rip),%r14
+	movq	%rax,%r8
+	movq	%rbp,%rax
+	movq	%rdx,%r9
+
+	mulq	%r10
+	movq	.Lpoly+24(%rip),%r15
+	addq	%rax,%r9
+	movq	%rbp,%rax
+	adcq	$0,%rdx
+	movq	%rdx,%r10
+
+	mulq	%r11
+	addq	%rax,%r10
+	movq	%rbp,%rax
+	adcq	$0,%rdx
+	movq	%rdx,%r11
+
+	mulq	%r12
+	addq	%rax,%r11
+	movq	%r8,%rax
+	adcq	$0,%rdx
+	xorq	%r13,%r13
+	movq	%rdx,%r12
+
+
+
+
+
+
+
+
+
+
+	movq	%r8,%rbp
+	shlq	$32,%r8
+	mulq	%r15
+	shrq	$32,%rbp
+	addq	%r8,%r9
+	adcq	%rbp,%r10
+	adcq	%rax,%r11
+	movq	8(%rbx),%rax
+	adcq	%rdx,%r12
+	adcq	$0,%r13
+	xorq	%r8,%r8
+
+
+
+	movq	%rax,%rbp
+	mulq	0(%rsi)
+	addq	%rax,%r9
+	movq	%rbp,%rax
+	adcq	$0,%rdx
+	movq	%rdx,%rcx
+
+	mulq	8(%rsi)
+	addq	%rcx,%r10
+	adcq	$0,%rdx
+	addq	%rax,%r10
+	movq	%rbp,%rax
+	adcq	$0,%rdx
+	movq	%rdx,%rcx
+
+	mulq	16(%rsi)
+	addq	%rcx,%r11
+	adcq	$0,%rdx
+	addq	%rax,%r11
+	movq	%rbp,%rax
+	adcq	$0,%rdx
+	movq	%rdx,%rcx
+
+	mulq	24(%rsi)
+	addq	%rcx,%r12
+	adcq	$0,%rdx
+	addq	%rax,%r12
+	movq	%r9,%rax
+	adcq	%rdx,%r13
+	adcq	$0,%r8
+
+
+
+	movq	%r9,%rbp
+	shlq	$32,%r9
+	mulq	%r15
+	shrq	$32,%rbp
+	addq	%r9,%r10
+	adcq	%rbp,%r11
+	adcq	%rax,%r12
+	movq	16(%rbx),%rax
+	adcq	%rdx,%r13
+	adcq	$0,%r8
+	xorq	%r9,%r9
+
+
+
+	movq	%rax,%rbp
+	mulq	0(%rsi)
+	addq	%rax,%r10
+	movq	%rbp,%rax
+	adcq	$0,%rdx
+	movq	%rdx,%rcx
+
+	mulq	8(%rsi)
+	addq	%rcx,%r11
+	adcq	$0,%rdx
+	addq	%rax,%r11
+	movq	%rbp,%rax
+	adcq	$0,%rdx
+	movq	%rdx,%rcx
+
+	mulq	16(%rsi)
+	addq	%rcx,%r12
+	adcq	$0,%rdx
+	addq	%rax,%r12
+	movq	%rbp,%rax
+	adcq	$0,%rdx
+	movq	%rdx,%rcx
+
+	mulq	24(%rsi)
+	addq	%rcx,%r13
+	adcq	$0,%rdx
+	addq	%rax,%r13
+	movq	%r10,%rax
+	adcq	%rdx,%r8
+	adcq	$0,%r9
+
+
+
+	movq	%r10,%rbp
+	shlq	$32,%r10
+	mulq	%r15
+	shrq	$32,%rbp
+	addq	%r10,%r11
+	adcq	%rbp,%r12
+	adcq	%rax,%r13
+	movq	24(%rbx),%rax
+	adcq	%rdx,%r8
+	adcq	$0,%r9
+	xorq	%r10,%r10
+
+
+
+	movq	%rax,%rbp
+	mulq	0(%rsi)
+	addq	%rax,%r11
+	movq	%rbp,%rax
+	adcq	$0,%rdx
+	movq	%rdx,%rcx
+
+	mulq	8(%rsi)
+	addq	%rcx,%r12
+	adcq	$0,%rdx
+	addq	%rax,%r12
+	movq	%rbp,%rax
+	adcq	$0,%rdx
+	movq	%rdx,%rcx
+
+	mulq	16(%rsi)
+	addq	%rcx,%r13
+	adcq	$0,%rdx
+	addq	%rax,%r13
+	movq	%rbp,%rax
+	adcq	$0,%rdx
+	movq	%rdx,%rcx
+
+	mulq	24(%rsi)
+	addq	%rcx,%r8
+	adcq	$0,%rdx
+	addq	%rax,%r8
+	movq	%r11,%rax
+	adcq	%rdx,%r9
+	adcq	$0,%r10
+
+
+
+	movq	%r11,%rbp
+	shlq	$32,%r11
+	mulq	%r15
+	shrq	$32,%rbp
+	addq	%r11,%r12
+	adcq	%rbp,%r13
+	movq	%r12,%rcx
+	adcq	%rax,%r8
+	adcq	%rdx,%r9
+	movq	%r13,%rbp
+	adcq	$0,%r10
+
+
+
+	subq	$-1,%r12
+	movq	%r8,%rbx
+	sbbq	%r14,%r13
+	sbbq	$0,%r8
+	movq	%r9,%rdx
+	sbbq	%r15,%r9
+	sbbq	$0,%r10
+
+	cmovcq	%rcx,%r12
+	cmovcq	%rbp,%r13
+	movq	%r12,0(%rdi)
+	cmovcq	%rbx,%r8
+	movq	%r13,8(%rdi)
+	cmovcq	%rdx,%r9
+	movq	%r8,16(%rdi)
+	movq	%r9,24(%rdi)
+
+	.byte	0xf3,0xc3
+.size	__ecp_nistz256_mul_montq,.-__ecp_nistz256_mul_montq
+
+
+
+
+
+
+
+
+.globl	ecp_nistz256_sqr_mont
+.hidden ecp_nistz256_sqr_mont
+.type	ecp_nistz256_sqr_mont,@function
+.align	32
+ecp_nistz256_sqr_mont:
+	pushq	%rbp
+	pushq	%rbx
+	pushq	%r12
+	pushq	%r13
+	pushq	%r14
+	pushq	%r15
+	movq	0(%rsi),%rax
+	movq	8(%rsi),%r14
+	movq	16(%rsi),%r15
+	movq	24(%rsi),%r8
+
+	call	__ecp_nistz256_sqr_montq
+.Lsqr_mont_done:
+	popq	%r15
+	popq	%r14
+	popq	%r13
+	popq	%r12
+	popq	%rbx
+	popq	%rbp
+	.byte	0xf3,0xc3
+.size	ecp_nistz256_sqr_mont,.-ecp_nistz256_sqr_mont
+
+.type	__ecp_nistz256_sqr_montq,@function
+.align	32
+__ecp_nistz256_sqr_montq:
+	movq	%rax,%r13
+	mulq	%r14
+	movq	%rax,%r9
+	movq	%r15,%rax
+	movq	%rdx,%r10
+
+	mulq	%r13
+	addq	%rax,%r10
+	movq	%r8,%rax
+	adcq	$0,%rdx
+	movq	%rdx,%r11
+
+	mulq	%r13
+	addq	%rax,%r11
+	movq	%r15,%rax
+	adcq	$0,%rdx
+	movq	%rdx,%r12
+
+
+	mulq	%r14
+	addq	%rax,%r11
+	movq	%r8,%rax
+	adcq	$0,%rdx
+	movq	%rdx,%rbp
+
+	mulq	%r14
+	addq	%rax,%r12
+	movq	%r8,%rax
+	adcq	$0,%rdx
+	addq	%rbp,%r12
+	movq	%rdx,%r13
+	adcq	$0,%r13
+
+
+	mulq	%r15
+	xorq	%r15,%r15
+	addq	%rax,%r13
+	movq	0(%rsi),%rax
+	movq	%rdx,%r14
+	adcq	$0,%r14
+
+	addq	%r9,%r9
+	adcq	%r10,%r10
+	adcq	%r11,%r11
+	adcq	%r12,%r12
+	adcq	%r13,%r13
+	adcq	%r14,%r14
+	adcq	$0,%r15
+
+	mulq	%rax
+	movq	%rax,%r8
+	movq	8(%rsi),%rax
+	movq	%rdx,%rcx
+
+	mulq	%rax
+	addq	%rcx,%r9
+	adcq	%rax,%r10
+	movq	16(%rsi),%rax
+	adcq	$0,%rdx
+	movq	%rdx,%rcx
+
+	mulq	%rax
+	addq	%rcx,%r11
+	adcq	%rax,%r12
+	movq	24(%rsi),%rax
+	adcq	$0,%rdx
+	movq	%rdx,%rcx
+
+	mulq	%rax
+	addq	%rcx,%r13
+	adcq	%rax,%r14
+	movq	%r8,%rax
+	adcq	%rdx,%r15
+
+	movq	.Lpoly+8(%rip),%rsi
+	movq	.Lpoly+24(%rip),%rbp
+
+
+
+
+	movq	%r8,%rcx
+	shlq	$32,%r8
+	mulq	%rbp
+	shrq	$32,%rcx
+	addq	%r8,%r9
+	adcq	%rcx,%r10
+	adcq	%rax,%r11
+	movq	%r9,%rax
+	adcq	$0,%rdx
+
+
+
+	movq	%r9,%rcx
+	shlq	$32,%r9
+	movq	%rdx,%r8
+	mulq	%rbp
+	shrq	$32,%rcx
+	addq	%r9,%r10
+	adcq	%rcx,%r11
+	adcq	%rax,%r8
+	movq	%r10,%rax
+	adcq	$0,%rdx
+
+
+
+	movq	%r10,%rcx
+	shlq	$32,%r10
+	movq	%rdx,%r9
+	mulq	%rbp
+	shrq	$32,%rcx
+	addq	%r10,%r11
+	adcq	%rcx,%r8
+	adcq	%rax,%r9
+	movq	%r11,%rax
+	adcq	$0,%rdx
+
+
+
+	movq	%r11,%rcx
+	shlq	$32,%r11
+	movq	%rdx,%r10
+	mulq	%rbp
+	shrq	$32,%rcx
+	addq	%r11,%r8
+	adcq	%rcx,%r9
+	adcq	%rax,%r10
+	adcq	$0,%rdx
+	xorq	%r11,%r11
+
+
+
+	addq	%r8,%r12
+	adcq	%r9,%r13
+	movq	%r12,%r8
+	adcq	%r10,%r14
+	adcq	%rdx,%r15
+	movq	%r13,%r9
+	adcq	$0,%r11
+
+	subq	$-1,%r12
+	movq	%r14,%r10
+	sbbq	%rsi,%r13
+	sbbq	$0,%r14
+	movq	%r15,%rcx
+	sbbq	%rbp,%r15
+	sbbq	$0,%r11
+
+	cmovcq	%r8,%r12
+	cmovcq	%r9,%r13
+	movq	%r12,0(%rdi)
+	cmovcq	%r10,%r14
+	movq	%r13,8(%rdi)
+	cmovcq	%rcx,%r15
+	movq	%r14,16(%rdi)
+	movq	%r15,24(%rdi)
+
+	.byte	0xf3,0xc3
+.size	__ecp_nistz256_sqr_montq,.-__ecp_nistz256_sqr_montq
+
+
+
+
+
+
+.globl	ecp_nistz256_from_mont
+.hidden ecp_nistz256_from_mont
+.type	ecp_nistz256_from_mont,@function
+.align	32
+ecp_nistz256_from_mont:
+	pushq	%r12
+	pushq	%r13
+
+	movq	0(%rsi),%rax
+	movq	.Lpoly+24(%rip),%r13
+	movq	8(%rsi),%r9
+	movq	16(%rsi),%r10
+	movq	24(%rsi),%r11
+	movq	%rax,%r8
+	movq	.Lpoly+8(%rip),%r12
+
+
+
+	movq	%rax,%rcx
+	shlq	$32,%r8
+	mulq	%r13
+	shrq	$32,%rcx
+	addq	%r8,%r9
+	adcq	%rcx,%r10
+	adcq	%rax,%r11
+	movq	%r9,%rax
+	adcq	$0,%rdx
+
+
+
+	movq	%r9,%rcx
+	shlq	$32,%r9
+	movq	%rdx,%r8
+	mulq	%r13
+	shrq	$32,%rcx
+	addq	%r9,%r10
+	adcq	%rcx,%r11
+	adcq	%rax,%r8
+	movq	%r10,%rax
+	adcq	$0,%rdx
+
+
+
+	movq	%r10,%rcx
+	shlq	$32,%r10
+	movq	%rdx,%r9
+	mulq	%r13
+	shrq	$32,%rcx
+	addq	%r10,%r11
+	adcq	%rcx,%r8
+	adcq	%rax,%r9
+	movq	%r11,%rax
+	adcq	$0,%rdx
+
+
+
+	movq	%r11,%rcx
+	shlq	$32,%r11
+	movq	%rdx,%r10
+	mulq	%r13
+	shrq	$32,%rcx
+	addq	%r11,%r8
+	adcq	%rcx,%r9
+	movq	%r8,%rcx
+	adcq	%rax,%r10
+	movq	%r9,%rsi
+	adcq	$0,%rdx
+
+	subq	$-1,%r8
+	movq	%r10,%rax
+	sbbq	%r12,%r9
+	sbbq	$0,%r10
+	movq	%rdx,%r11
+	sbbq	%r13,%rdx
+	sbbq	%r13,%r13
+
+	cmovnzq	%rcx,%r8
+	cmovnzq	%rsi,%r9
+	movq	%r8,0(%rdi)
+	cmovnzq	%rax,%r10
+	movq	%r9,8(%rdi)
+	cmovzq	%rdx,%r11
+	movq	%r10,16(%rdi)
+	movq	%r11,24(%rdi)
+
+	popq	%r13
+	popq	%r12
+	.byte	0xf3,0xc3
+.size	ecp_nistz256_from_mont,.-ecp_nistz256_from_mont
+
+
+.globl	ecp_nistz256_select_w5
+.hidden ecp_nistz256_select_w5
+.type	ecp_nistz256_select_w5,@function
+.align	32
+ecp_nistz256_select_w5:
+	movdqa	.LOne(%rip),%xmm0
+	movd	%edx,%xmm1
+
+	pxor	%xmm2,%xmm2
+	pxor	%xmm3,%xmm3
+	pxor	%xmm4,%xmm4
+	pxor	%xmm5,%xmm5
+	pxor	%xmm6,%xmm6
+	pxor	%xmm7,%xmm7
+
+	movdqa	%xmm0,%xmm8
+	pshufd	$0,%xmm1,%xmm1
+
+	movq	$16,%rax
+.Lselect_loop_sse_w5:
+
+	movdqa	%xmm8,%xmm15
+	paddd	%xmm0,%xmm8
+	pcmpeqd	%xmm1,%xmm15
+
+	movdqa	0(%rsi),%xmm9
+	movdqa	16(%rsi),%xmm10
+	movdqa	32(%rsi),%xmm11
+	movdqa	48(%rsi),%xmm12
+	movdqa	64(%rsi),%xmm13
+	movdqa	80(%rsi),%xmm14
+	leaq	96(%rsi),%rsi
+
+	pand	%xmm15,%xmm9
+	pand	%xmm15,%xmm10
+	por	%xmm9,%xmm2
+	pand	%xmm15,%xmm11
+	por	%xmm10,%xmm3
+	pand	%xmm15,%xmm12
+	por	%xmm11,%xmm4
+	pand	%xmm15,%xmm13
+	por	%xmm12,%xmm5
+	pand	%xmm15,%xmm14
+	por	%xmm13,%xmm6
+	por	%xmm14,%xmm7
+
+	decq	%rax
+	jnz	.Lselect_loop_sse_w5
+
+	movdqu	%xmm2,0(%rdi)
+	movdqu	%xmm3,16(%rdi)
+	movdqu	%xmm4,32(%rdi)
+	movdqu	%xmm5,48(%rdi)
+	movdqu	%xmm6,64(%rdi)
+	movdqu	%xmm7,80(%rdi)
+	.byte	0xf3,0xc3
+.size	ecp_nistz256_select_w5,.-ecp_nistz256_select_w5
+
+
+
+.globl	ecp_nistz256_select_w7
+.hidden ecp_nistz256_select_w7
+.type	ecp_nistz256_select_w7,@function
+.align	32
+ecp_nistz256_select_w7:
+	movdqa	.LOne(%rip),%xmm8
+	movd	%edx,%xmm1
+
+	pxor	%xmm2,%xmm2
+	pxor	%xmm3,%xmm3
+	pxor	%xmm4,%xmm4
+	pxor	%xmm5,%xmm5
+
+	movdqa	%xmm8,%xmm0
+	pshufd	$0,%xmm1,%xmm1
+	movq	$64,%rax
+
+.Lselect_loop_sse_w7:
+	movdqa	%xmm8,%xmm15
+	paddd	%xmm0,%xmm8
+	movdqa	0(%rsi),%xmm9
+	movdqa	16(%rsi),%xmm10
+	pcmpeqd	%xmm1,%xmm15
+	movdqa	32(%rsi),%xmm11
+	movdqa	48(%rsi),%xmm12
+	leaq	64(%rsi),%rsi
+
+	pand	%xmm15,%xmm9
+	pand	%xmm15,%xmm10
+	por	%xmm9,%xmm2
+	pand	%xmm15,%xmm11
+	por	%xmm10,%xmm3
+	pand	%xmm15,%xmm12
+	por	%xmm11,%xmm4
+	prefetcht0	255(%rsi)
+	por	%xmm12,%xmm5
+
+	decq	%rax
+	jnz	.Lselect_loop_sse_w7
+
+	movdqu	%xmm2,0(%rdi)
+	movdqu	%xmm3,16(%rdi)
+	movdqu	%xmm4,32(%rdi)
+	movdqu	%xmm5,48(%rdi)
+	.byte	0xf3,0xc3
+.size	ecp_nistz256_select_w7,.-ecp_nistz256_select_w7
+.globl	ecp_nistz256_avx2_select_w7
+.hidden ecp_nistz256_avx2_select_w7
+.type	ecp_nistz256_avx2_select_w7,@function
+.align	32
+ecp_nistz256_avx2_select_w7:
+.byte	0x0f,0x0b
+	.byte	0xf3,0xc3
+.size	ecp_nistz256_avx2_select_w7,.-ecp_nistz256_avx2_select_w7
+.type	__ecp_nistz256_add_toq,@function
+.align	32
+__ecp_nistz256_add_toq:
+	addq	0(%rbx),%r12
+	adcq	8(%rbx),%r13
+	movq	%r12,%rax
+	adcq	16(%rbx),%r8
+	adcq	24(%rbx),%r9
+	movq	%r13,%rbp
+	sbbq	%r11,%r11
+
+	subq	$-1,%r12
+	movq	%r8,%rcx
+	sbbq	%r14,%r13
+	sbbq	$0,%r8
+	movq	%r9,%r10
+	sbbq	%r15,%r9
+	testq	%r11,%r11
+
+	cmovzq	%rax,%r12
+	cmovzq	%rbp,%r13
+	movq	%r12,0(%rdi)
+	cmovzq	%rcx,%r8
+	movq	%r13,8(%rdi)
+	cmovzq	%r10,%r9
+	movq	%r8,16(%rdi)
+	movq	%r9,24(%rdi)
+
+	.byte	0xf3,0xc3
+.size	__ecp_nistz256_add_toq,.-__ecp_nistz256_add_toq
+
+.type	__ecp_nistz256_sub_fromq,@function
+.align	32
+__ecp_nistz256_sub_fromq:
+	subq	0(%rbx),%r12
+	sbbq	8(%rbx),%r13
+	movq	%r12,%rax
+	sbbq	16(%rbx),%r8
+	sbbq	24(%rbx),%r9
+	movq	%r13,%rbp
+	sbbq	%r11,%r11
+
+	addq	$-1,%r12
+	movq	%r8,%rcx
+	adcq	%r14,%r13
+	adcq	$0,%r8
+	movq	%r9,%r10
+	adcq	%r15,%r9
+	testq	%r11,%r11
+
+	cmovzq	%rax,%r12
+	cmovzq	%rbp,%r13
+	movq	%r12,0(%rdi)
+	cmovzq	%rcx,%r8
+	movq	%r13,8(%rdi)
+	cmovzq	%r10,%r9
+	movq	%r8,16(%rdi)
+	movq	%r9,24(%rdi)
+
+	.byte	0xf3,0xc3
+.size	__ecp_nistz256_sub_fromq,.-__ecp_nistz256_sub_fromq
+
+.type	__ecp_nistz256_subq,@function
+.align	32
+__ecp_nistz256_subq:
+	subq	%r12,%rax
+	sbbq	%r13,%rbp
+	movq	%rax,%r12
+	sbbq	%r8,%rcx
+	sbbq	%r9,%r10
+	movq	%rbp,%r13
+	sbbq	%r11,%r11
+
+	addq	$-1,%rax
+	movq	%rcx,%r8
+	adcq	%r14,%rbp
+	adcq	$0,%rcx
+	movq	%r10,%r9
+	adcq	%r15,%r10
+	testq	%r11,%r11
+
+	cmovnzq	%rax,%r12
+	cmovnzq	%rbp,%r13
+	cmovnzq	%rcx,%r8
+	cmovnzq	%r10,%r9
+
+	.byte	0xf3,0xc3
+.size	__ecp_nistz256_subq,.-__ecp_nistz256_subq
+
+.type	__ecp_nistz256_mul_by_2q,@function
+.align	32
+__ecp_nistz256_mul_by_2q:
+	addq	%r12,%r12
+	adcq	%r13,%r13
+	movq	%r12,%rax
+	adcq	%r8,%r8
+	adcq	%r9,%r9
+	movq	%r13,%rbp
+	sbbq	%r11,%r11
+
+	subq	$-1,%r12
+	movq	%r8,%rcx
+	sbbq	%r14,%r13
+	sbbq	$0,%r8
+	movq	%r9,%r10
+	sbbq	%r15,%r9
+	testq	%r11,%r11
+
+	cmovzq	%rax,%r12
+	cmovzq	%rbp,%r13
+	movq	%r12,0(%rdi)
+	cmovzq	%rcx,%r8
+	movq	%r13,8(%rdi)
+	cmovzq	%r10,%r9
+	movq	%r8,16(%rdi)
+	movq	%r9,24(%rdi)
+
+	.byte	0xf3,0xc3
+.size	__ecp_nistz256_mul_by_2q,.-__ecp_nistz256_mul_by_2q
+.globl	ecp_nistz256_point_double
+.hidden ecp_nistz256_point_double
+.type	ecp_nistz256_point_double,@function
+.align	32
+ecp_nistz256_point_double:
+	pushq	%rbp
+	pushq	%rbx
+	pushq	%r12
+	pushq	%r13
+	pushq	%r14
+	pushq	%r15
+	subq	$160+8,%rsp
+
+.Lpoint_double_shortcutq:
+	movdqu	0(%rsi),%xmm0
+	movq	%rsi,%rbx
+	movdqu	16(%rsi),%xmm1
+	movq	32+0(%rsi),%r12
+	movq	32+8(%rsi),%r13
+	movq	32+16(%rsi),%r8
+	movq	32+24(%rsi),%r9
+	movq	.Lpoly+8(%rip),%r14
+	movq	.Lpoly+24(%rip),%r15
+	movdqa	%xmm0,96(%rsp)
+	movdqa	%xmm1,96+16(%rsp)
+	leaq	32(%rdi),%r10
+	leaq	64(%rdi),%r11
+.byte	102,72,15,110,199
+.byte	102,73,15,110,202
+.byte	102,73,15,110,211
+
+	leaq	0(%rsp),%rdi
+	call	__ecp_nistz256_mul_by_2q
+
+	movq	64+0(%rsi),%rax
+	movq	64+8(%rsi),%r14
+	movq	64+16(%rsi),%r15
+	movq	64+24(%rsi),%r8
+	leaq	64-0(%rsi),%rsi
+	leaq	64(%rsp),%rdi
+	call	__ecp_nistz256_sqr_montq
+
+	movq	0+0(%rsp),%rax
+	movq	8+0(%rsp),%r14
+	leaq	0+0(%rsp),%rsi
+	movq	16+0(%rsp),%r15
+	movq	24+0(%rsp),%r8
+	leaq	0(%rsp),%rdi
+	call	__ecp_nistz256_sqr_montq
+
+	movq	32(%rbx),%rax
+	movq	64+0(%rbx),%r9
+	movq	64+8(%rbx),%r10
+	movq	64+16(%rbx),%r11
+	movq	64+24(%rbx),%r12
+	leaq	64-0(%rbx),%rsi
+	leaq	32(%rbx),%rbx
+.byte	102,72,15,126,215
+	call	__ecp_nistz256_mul_montq
+	call	__ecp_nistz256_mul_by_2q
+
+	movq	96+0(%rsp),%r12
+	movq	96+8(%rsp),%r13
+	leaq	64(%rsp),%rbx
+	movq	96+16(%rsp),%r8
+	movq	96+24(%rsp),%r9
+	leaq	32(%rsp),%rdi
+	call	__ecp_nistz256_add_toq
+
+	movq	96+0(%rsp),%r12
+	movq	96+8(%rsp),%r13
+	leaq	64(%rsp),%rbx
+	movq	96+16(%rsp),%r8
+	movq	96+24(%rsp),%r9
+	leaq	64(%rsp),%rdi
+	call	__ecp_nistz256_sub_fromq
+
+	movq	0+0(%rsp),%rax
+	movq	8+0(%rsp),%r14
+	leaq	0+0(%rsp),%rsi
+	movq	16+0(%rsp),%r15
+	movq	24+0(%rsp),%r8
+.byte	102,72,15,126,207
+	call	__ecp_nistz256_sqr_montq
+	xorq	%r9,%r9
+	movq	%r12,%rax
+	addq	$-1,%r12
+	movq	%r13,%r10
+	adcq	%rsi,%r13
+	movq	%r14,%rcx
+	adcq	$0,%r14
+	movq	%r15,%r8
+	adcq	%rbp,%r15
+	adcq	$0,%r9
+	xorq	%rsi,%rsi
+	testq	$1,%rax
+
+	cmovzq	%rax,%r12
+	cmovzq	%r10,%r13
+	cmovzq	%rcx,%r14
+	cmovzq	%r8,%r15
+	cmovzq	%rsi,%r9
+
+	movq	%r13,%rax
+	shrq	$1,%r12
+	shlq	$63,%rax
+	movq	%r14,%r10
+	shrq	$1,%r13
+	orq	%rax,%r12
+	shlq	$63,%r10
+	movq	%r15,%rcx
+	shrq	$1,%r14
+	orq	%r10,%r13
+	shlq	$63,%rcx
+	movq	%r12,0(%rdi)
+	shrq	$1,%r15
+	movq	%r13,8(%rdi)
+	shlq	$63,%r9
+	orq	%rcx,%r14
+	orq	%r9,%r15
+	movq	%r14,16(%rdi)
+	movq	%r15,24(%rdi)
+	movq	64(%rsp),%rax
+	leaq	64(%rsp),%rbx
+	movq	0+32(%rsp),%r9
+	movq	8+32(%rsp),%r10
+	leaq	0+32(%rsp),%rsi
+	movq	16+32(%rsp),%r11
+	movq	24+32(%rsp),%r12
+	leaq	32(%rsp),%rdi
+	call	__ecp_nistz256_mul_montq
+
+	leaq	128(%rsp),%rdi
+	call	__ecp_nistz256_mul_by_2q
+
+	leaq	32(%rsp),%rbx
+	leaq	32(%rsp),%rdi
+	call	__ecp_nistz256_add_toq
+
+	movq	96(%rsp),%rax
+	leaq	96(%rsp),%rbx
+	movq	0+0(%rsp),%r9
+	movq	8+0(%rsp),%r10
+	leaq	0+0(%rsp),%rsi
+	movq	16+0(%rsp),%r11
+	movq	24+0(%rsp),%r12
+	leaq	0(%rsp),%rdi
+	call	__ecp_nistz256_mul_montq
+
+	leaq	128(%rsp),%rdi
+	call	__ecp_nistz256_mul_by_2q
+
+	movq	0+32(%rsp),%rax
+	movq	8+32(%rsp),%r14
+	leaq	0+32(%rsp),%rsi
+	movq	16+32(%rsp),%r15
+	movq	24+32(%rsp),%r8
+.byte	102,72,15,126,199
+	call	__ecp_nistz256_sqr_montq
+
+	leaq	128(%rsp),%rbx
+	movq	%r14,%r8
+	movq	%r15,%r9
+	movq	%rsi,%r14
+	movq	%rbp,%r15
+	call	__ecp_nistz256_sub_fromq
+
+	movq	0+0(%rsp),%rax
+	movq	0+8(%rsp),%rbp
+	movq	0+16(%rsp),%rcx
+	movq	0+24(%rsp),%r10
+	leaq	0(%rsp),%rdi
+	call	__ecp_nistz256_subq
+
+	movq	32(%rsp),%rax
+	leaq	32(%rsp),%rbx
+	movq	%r12,%r14
+	xorl	%ecx,%ecx
+	movq	%r12,0+0(%rsp)
+	movq	%r13,%r10
+	movq	%r13,0+8(%rsp)
+	cmovzq	%r8,%r11
+	movq	%r8,0+16(%rsp)
+	leaq	0-0(%rsp),%rsi
+	cmovzq	%r9,%r12
+	movq	%r9,0+24(%rsp)
+	movq	%r14,%r9
+	leaq	0(%rsp),%rdi
+	call	__ecp_nistz256_mul_montq
+
+.byte	102,72,15,126,203
+.byte	102,72,15,126,207
+	call	__ecp_nistz256_sub_fromq
+
+	addq	$160+8,%rsp
+	popq	%r15
+	popq	%r14
+	popq	%r13
+	popq	%r12
+	popq	%rbx
+	popq	%rbp
+	.byte	0xf3,0xc3
+.size	ecp_nistz256_point_double,.-ecp_nistz256_point_double
+.globl	ecp_nistz256_point_add
+.hidden ecp_nistz256_point_add
+.type	ecp_nistz256_point_add,@function
+.align	32
+ecp_nistz256_point_add:
+	pushq	%rbp
+	pushq	%rbx
+	pushq	%r12
+	pushq	%r13
+	pushq	%r14
+	pushq	%r15
+	subq	$576+8,%rsp
+
+	movdqu	0(%rsi),%xmm0
+	movdqu	16(%rsi),%xmm1
+	movdqu	32(%rsi),%xmm2
+	movdqu	48(%rsi),%xmm3
+	movdqu	64(%rsi),%xmm4
+	movdqu	80(%rsi),%xmm5
+	movq	%rsi,%rbx
+	movq	%rdx,%rsi
+	movdqa	%xmm0,384(%rsp)
+	movdqa	%xmm1,384+16(%rsp)
+	por	%xmm0,%xmm1
+	movdqa	%xmm2,416(%rsp)
+	movdqa	%xmm3,416+16(%rsp)
+	por	%xmm2,%xmm3
+	movdqa	%xmm4,448(%rsp)
+	movdqa	%xmm5,448+16(%rsp)
+	por	%xmm1,%xmm3
+
+	movdqu	0(%rsi),%xmm0
+	pshufd	$0xb1,%xmm3,%xmm5
+	movdqu	16(%rsi),%xmm1
+	movdqu	32(%rsi),%xmm2
+	por	%xmm3,%xmm5
+	movdqu	48(%rsi),%xmm3
+	movq	64+0(%rsi),%rax
+	movq	64+8(%rsi),%r14
+	movq	64+16(%rsi),%r15
+	movq	64+24(%rsi),%r8
+	movdqa	%xmm0,480(%rsp)
+	pshufd	$0x1e,%xmm5,%xmm4
+	movdqa	%xmm1,480+16(%rsp)
+	por	%xmm0,%xmm1
+.byte	102,72,15,110,199
+	movdqa	%xmm2,512(%rsp)
+	movdqa	%xmm3,512+16(%rsp)
+	por	%xmm2,%xmm3
+	por	%xmm4,%xmm5
+	pxor	%xmm4,%xmm4
+	por	%xmm1,%xmm3
+
+	leaq	64-0(%rsi),%rsi
+	movq	%rax,544+0(%rsp)
+	movq	%r14,544+8(%rsp)
+	movq	%r15,544+16(%rsp)
+	movq	%r8,544+24(%rsp)
+	leaq	96(%rsp),%rdi
+	call	__ecp_nistz256_sqr_montq
+
+	pcmpeqd	%xmm4,%xmm5
+	pshufd	$0xb1,%xmm3,%xmm4
+	por	%xmm3,%xmm4
+	pshufd	$0,%xmm5,%xmm5
+	pshufd	$0x1e,%xmm4,%xmm3
+	por	%xmm3,%xmm4
+	pxor	%xmm3,%xmm3
+	pcmpeqd	%xmm3,%xmm4
+	pshufd	$0,%xmm4,%xmm4
+	movq	64+0(%rbx),%rax
+	movq	64+8(%rbx),%r14
+	movq	64+16(%rbx),%r15
+	movq	64+24(%rbx),%r8
+.byte	102,72,15,110,203
+
+	leaq	64-0(%rbx),%rsi
+	leaq	32(%rsp),%rdi
+	call	__ecp_nistz256_sqr_montq
+
+	movq	544(%rsp),%rax
+	leaq	544(%rsp),%rbx
+	movq	0+96(%rsp),%r9
+	movq	8+96(%rsp),%r10
+	leaq	0+96(%rsp),%rsi
+	movq	16+96(%rsp),%r11
+	movq	24+96(%rsp),%r12
+	leaq	224(%rsp),%rdi
+	call	__ecp_nistz256_mul_montq
+
+	movq	448(%rsp),%rax
+	leaq	448(%rsp),%rbx
+	movq	0+32(%rsp),%r9
+	movq	8+32(%rsp),%r10
+	leaq	0+32(%rsp),%rsi
+	movq	16+32(%rsp),%r11
+	movq	24+32(%rsp),%r12
+	leaq	256(%rsp),%rdi
+	call	__ecp_nistz256_mul_montq
+
+	movq	416(%rsp),%rax
+	leaq	416(%rsp),%rbx
+	movq	0+224(%rsp),%r9
+	movq	8+224(%rsp),%r10
+	leaq	0+224(%rsp),%rsi
+	movq	16+224(%rsp),%r11
+	movq	24+224(%rsp),%r12
+	leaq	224(%rsp),%rdi
+	call	__ecp_nistz256_mul_montq
+
+	movq	512(%rsp),%rax
+	leaq	512(%rsp),%rbx
+	movq	0+256(%rsp),%r9
+	movq	8+256(%rsp),%r10
+	leaq	0+256(%rsp),%rsi
+	movq	16+256(%rsp),%r11
+	movq	24+256(%rsp),%r12
+	leaq	256(%rsp),%rdi
+	call	__ecp_nistz256_mul_montq
+
+	leaq	224(%rsp),%rbx
+	leaq	64(%rsp),%rdi
+	call	__ecp_nistz256_sub_fromq
+
+	orq	%r13,%r12
+	movdqa	%xmm4,%xmm2
+	orq	%r8,%r12
+	orq	%r9,%r12
+	por	%xmm5,%xmm2
+.byte	102,73,15,110,220
+
+	movq	384(%rsp),%rax
+	leaq	384(%rsp),%rbx
+	movq	0+96(%rsp),%r9
+	movq	8+96(%rsp),%r10
+	leaq	0+96(%rsp),%rsi
+	movq	16+96(%rsp),%r11
+	movq	24+96(%rsp),%r12
+	leaq	160(%rsp),%rdi
+	call	__ecp_nistz256_mul_montq
+
+	movq	480(%rsp),%rax
+	leaq	480(%rsp),%rbx
+	movq	0+32(%rsp),%r9
+	movq	8+32(%rsp),%r10
+	leaq	0+32(%rsp),%rsi
+	movq	16+32(%rsp),%r11
+	movq	24+32(%rsp),%r12
+	leaq	192(%rsp),%rdi
+	call	__ecp_nistz256_mul_montq
+
+	leaq	160(%rsp),%rbx
+	leaq	0(%rsp),%rdi
+	call	__ecp_nistz256_sub_fromq
+
+	orq	%r13,%r12
+	orq	%r8,%r12
+	orq	%r9,%r12
+
+.byte	0x3e
+	jnz	.Ladd_proceedq
+.byte	102,73,15,126,208
+.byte	102,73,15,126,217
+	testq	%r8,%r8
+	jnz	.Ladd_proceedq
+	testq	%r9,%r9
+	jz	.Ladd_doubleq
+
+.byte	102,72,15,126,199
+	pxor	%xmm0,%xmm0
+	movdqu	%xmm0,0(%rdi)
+	movdqu	%xmm0,16(%rdi)
+	movdqu	%xmm0,32(%rdi)
+	movdqu	%xmm0,48(%rdi)
+	movdqu	%xmm0,64(%rdi)
+	movdqu	%xmm0,80(%rdi)
+	jmp	.Ladd_doneq
+
+.align	32
+.Ladd_doubleq:
+.byte	102,72,15,126,206
+.byte	102,72,15,126,199
+	addq	$416,%rsp
+	jmp	.Lpoint_double_shortcutq
+
+.align	32
+.Ladd_proceedq:
+	movq	0+64(%rsp),%rax
+	movq	8+64(%rsp),%r14
+	leaq	0+64(%rsp),%rsi
+	movq	16+64(%rsp),%r15
+	movq	24+64(%rsp),%r8
+	leaq	96(%rsp),%rdi
+	call	__ecp_nistz256_sqr_montq
+
+	movq	448(%rsp),%rax
+	leaq	448(%rsp),%rbx
+	movq	0+0(%rsp),%r9
+	movq	8+0(%rsp),%r10
+	leaq	0+0(%rsp),%rsi
+	movq	16+0(%rsp),%r11
+	movq	24+0(%rsp),%r12
+	leaq	352(%rsp),%rdi
+	call	__ecp_nistz256_mul_montq
+
+	movq	0+0(%rsp),%rax
+	movq	8+0(%rsp),%r14
+	leaq	0+0(%rsp),%rsi
+	movq	16+0(%rsp),%r15
+	movq	24+0(%rsp),%r8
+	leaq	32(%rsp),%rdi
+	call	__ecp_nistz256_sqr_montq
+
+	movq	544(%rsp),%rax
+	leaq	544(%rsp),%rbx
+	movq	0+352(%rsp),%r9
+	movq	8+352(%rsp),%r10
+	leaq	0+352(%rsp),%rsi
+	movq	16+352(%rsp),%r11
+	movq	24+352(%rsp),%r12
+	leaq	352(%rsp),%rdi
+	call	__ecp_nistz256_mul_montq
+
+	movq	0(%rsp),%rax
+	leaq	0(%rsp),%rbx
+	movq	0+32(%rsp),%r9
+	movq	8+32(%rsp),%r10
+	leaq	0+32(%rsp),%rsi
+	movq	16+32(%rsp),%r11
+	movq	24+32(%rsp),%r12
+	leaq	128(%rsp),%rdi
+	call	__ecp_nistz256_mul_montq
+
+	movq	160(%rsp),%rax
+	leaq	160(%rsp),%rbx
+	movq	0+32(%rsp),%r9
+	movq	8+32(%rsp),%r10
+	leaq	0+32(%rsp),%rsi
+	movq	16+32(%rsp),%r11
+	movq	24+32(%rsp),%r12
+	leaq	192(%rsp),%rdi
+	call	__ecp_nistz256_mul_montq
+
+
+
+
+	addq	%r12,%r12
+	leaq	96(%rsp),%rsi
+	adcq	%r13,%r13
+	movq	%r12,%rax
+	adcq	%r8,%r8
+	adcq	%r9,%r9
+	movq	%r13,%rbp
+	sbbq	%r11,%r11
+
+	subq	$-1,%r12
+	movq	%r8,%rcx
+	sbbq	%r14,%r13
+	sbbq	$0,%r8
+	movq	%r9,%r10
+	sbbq	%r15,%r9
+	testq	%r11,%r11
+
+	cmovzq	%rax,%r12
+	movq	0(%rsi),%rax
+	cmovzq	%rbp,%r13
+	movq	8(%rsi),%rbp
+	cmovzq	%rcx,%r8
+	movq	16(%rsi),%rcx
+	cmovzq	%r10,%r9
+	movq	24(%rsi),%r10
+
+	call	__ecp_nistz256_subq
+
+	leaq	128(%rsp),%rbx
+	leaq	288(%rsp),%rdi
+	call	__ecp_nistz256_sub_fromq
+
+	movq	192+0(%rsp),%rax
+	movq	192+8(%rsp),%rbp
+	movq	192+16(%rsp),%rcx
+	movq	192+24(%rsp),%r10
+	leaq	320(%rsp),%rdi
+
+	call	__ecp_nistz256_subq
+
+	movq	%r12,0(%rdi)
+	movq	%r13,8(%rdi)
+	movq	%r8,16(%rdi)
+	movq	%r9,24(%rdi)
+	movq	128(%rsp),%rax
+	leaq	128(%rsp),%rbx
+	movq	0+224(%rsp),%r9
+	movq	8+224(%rsp),%r10
+	leaq	0+224(%rsp),%rsi
+	movq	16+224(%rsp),%r11
+	movq	24+224(%rsp),%r12
+	leaq	256(%rsp),%rdi
+	call	__ecp_nistz256_mul_montq
+
+	movq	320(%rsp),%rax
+	leaq	320(%rsp),%rbx
+	movq	0+64(%rsp),%r9
+	movq	8+64(%rsp),%r10
+	leaq	0+64(%rsp),%rsi
+	movq	16+64(%rsp),%r11
+	movq	24+64(%rsp),%r12
+	leaq	320(%rsp),%rdi
+	call	__ecp_nistz256_mul_montq
+
+	leaq	256(%rsp),%rbx
+	leaq	320(%rsp),%rdi
+	call	__ecp_nistz256_sub_fromq
+
+.byte	102,72,15,126,199
+
+	movdqa	%xmm5,%xmm0
+	movdqa	%xmm5,%xmm1
+	pandn	352(%rsp),%xmm0
+	movdqa	%xmm5,%xmm2
+	pandn	352+16(%rsp),%xmm1
+	movdqa	%xmm5,%xmm3
+	pand	544(%rsp),%xmm2
+	pand	544+16(%rsp),%xmm3
+	por	%xmm0,%xmm2
+	por	%xmm1,%xmm3
+
+	movdqa	%xmm4,%xmm0
+	movdqa	%xmm4,%xmm1
+	pandn	%xmm2,%xmm0
+	movdqa	%xmm4,%xmm2
+	pandn	%xmm3,%xmm1
+	movdqa	%xmm4,%xmm3
+	pand	448(%rsp),%xmm2
+	pand	448+16(%rsp),%xmm3
+	por	%xmm0,%xmm2
+	por	%xmm1,%xmm3
+	movdqu	%xmm2,64(%rdi)
+	movdqu	%xmm3,80(%rdi)
+
+	movdqa	%xmm5,%xmm0
+	movdqa	%xmm5,%xmm1
+	pandn	288(%rsp),%xmm0
+	movdqa	%xmm5,%xmm2
+	pandn	288+16(%rsp),%xmm1
+	movdqa	%xmm5,%xmm3
+	pand	480(%rsp),%xmm2
+	pand	480+16(%rsp),%xmm3
+	por	%xmm0,%xmm2
+	por	%xmm1,%xmm3
+
+	movdqa	%xmm4,%xmm0
+	movdqa	%xmm4,%xmm1
+	pandn	%xmm2,%xmm0
+	movdqa	%xmm4,%xmm2
+	pandn	%xmm3,%xmm1
+	movdqa	%xmm4,%xmm3
+	pand	384(%rsp),%xmm2
+	pand	384+16(%rsp),%xmm3
+	por	%xmm0,%xmm2
+	por	%xmm1,%xmm3
+	movdqu	%xmm2,0(%rdi)
+	movdqu	%xmm3,16(%rdi)
+
+	movdqa	%xmm5,%xmm0
+	movdqa	%xmm5,%xmm1
+	pandn	320(%rsp),%xmm0
+	movdqa	%xmm5,%xmm2
+	pandn	320+16(%rsp),%xmm1
+	movdqa	%xmm5,%xmm3
+	pand	512(%rsp),%xmm2
+	pand	512+16(%rsp),%xmm3
+	por	%xmm0,%xmm2
+	por	%xmm1,%xmm3
+
+	movdqa	%xmm4,%xmm0
+	movdqa	%xmm4,%xmm1
+	pandn	%xmm2,%xmm0
+	movdqa	%xmm4,%xmm2
+	pandn	%xmm3,%xmm1
+	movdqa	%xmm4,%xmm3
+	pand	416(%rsp),%xmm2
+	pand	416+16(%rsp),%xmm3
+	por	%xmm0,%xmm2
+	por	%xmm1,%xmm3
+	movdqu	%xmm2,32(%rdi)
+	movdqu	%xmm3,48(%rdi)
+
+.Ladd_doneq:
+	addq	$576+8,%rsp
+	popq	%r15
+	popq	%r14
+	popq	%r13
+	popq	%r12
+	popq	%rbx
+	popq	%rbp
+	.byte	0xf3,0xc3
+.size	ecp_nistz256_point_add,.-ecp_nistz256_point_add
+.globl	ecp_nistz256_point_add_affine
+.hidden ecp_nistz256_point_add_affine
+.type	ecp_nistz256_point_add_affine,@function
+.align	32
+ecp_nistz256_point_add_affine:
+	pushq	%rbp
+	pushq	%rbx
+	pushq	%r12
+	pushq	%r13
+	pushq	%r14
+	pushq	%r15
+	subq	$480+8,%rsp
+
+	movdqu	0(%rsi),%xmm0
+	movq	%rdx,%rbx
+	movdqu	16(%rsi),%xmm1
+	movdqu	32(%rsi),%xmm2
+	movdqu	48(%rsi),%xmm3
+	movdqu	64(%rsi),%xmm4
+	movdqu	80(%rsi),%xmm5
+	movq	64+0(%rsi),%rax
+	movq	64+8(%rsi),%r14
+	movq	64+16(%rsi),%r15
+	movq	64+24(%rsi),%r8
+	movdqa	%xmm0,320(%rsp)
+	movdqa	%xmm1,320+16(%rsp)
+	por	%xmm0,%xmm1
+	movdqa	%xmm2,352(%rsp)
+	movdqa	%xmm3,352+16(%rsp)
+	por	%xmm2,%xmm3
+	movdqa	%xmm4,384(%rsp)
+	movdqa	%xmm5,384+16(%rsp)
+	por	%xmm1,%xmm3
+
+	movdqu	0(%rbx),%xmm0
+	pshufd	$0xb1,%xmm3,%xmm5
+	movdqu	16(%rbx),%xmm1
+	movdqu	32(%rbx),%xmm2
+	por	%xmm3,%xmm5
+	movdqu	48(%rbx),%xmm3
+	movdqa	%xmm0,416(%rsp)
+	pshufd	$0x1e,%xmm5,%xmm4
+	movdqa	%xmm1,416+16(%rsp)
+	por	%xmm0,%xmm1
+.byte	102,72,15,110,199
+	movdqa	%xmm2,448(%rsp)
+	movdqa	%xmm3,448+16(%rsp)
+	por	%xmm2,%xmm3
+	por	%xmm4,%xmm5
+	pxor	%xmm4,%xmm4
+	por	%xmm1,%xmm3
+
+	leaq	64-0(%rsi),%rsi
+	leaq	32(%rsp),%rdi
+	call	__ecp_nistz256_sqr_montq
+
+	pcmpeqd	%xmm4,%xmm5
+	pshufd	$0xb1,%xmm3,%xmm4
+	movq	0(%rbx),%rax
+
+	movq	%r12,%r9
+	por	%xmm3,%xmm4
+	pshufd	$0,%xmm5,%xmm5
+	pshufd	$0x1e,%xmm4,%xmm3
+	movq	%r13,%r10
+	por	%xmm3,%xmm4
+	pxor	%xmm3,%xmm3
+	movq	%r14,%r11
+	pcmpeqd	%xmm3,%xmm4
+	pshufd	$0,%xmm4,%xmm4
+
+	leaq	32-0(%rsp),%rsi
+	movq	%r15,%r12
+	leaq	0(%rsp),%rdi
+	call	__ecp_nistz256_mul_montq
+
+	leaq	320(%rsp),%rbx
+	leaq	64(%rsp),%rdi
+	call	__ecp_nistz256_sub_fromq
+
+	movq	384(%rsp),%rax
+	leaq	384(%rsp),%rbx
+	movq	0+32(%rsp),%r9
+	movq	8+32(%rsp),%r10
+	leaq	0+32(%rsp),%rsi
+	movq	16+32(%rsp),%r11
+	movq	24+32(%rsp),%r12
+	leaq	32(%rsp),%rdi
+	call	__ecp_nistz256_mul_montq
+
+	movq	384(%rsp),%rax
+	leaq	384(%rsp),%rbx
+	movq	0+64(%rsp),%r9
+	movq	8+64(%rsp),%r10
+	leaq	0+64(%rsp),%rsi
+	movq	16+64(%rsp),%r11
+	movq	24+64(%rsp),%r12
+	leaq	288(%rsp),%rdi
+	call	__ecp_nistz256_mul_montq
+
+	movq	448(%rsp),%rax
+	leaq	448(%rsp),%rbx
+	movq	0+32(%rsp),%r9
+	movq	8+32(%rsp),%r10
+	leaq	0+32(%rsp),%rsi
+	movq	16+32(%rsp),%r11
+	movq	24+32(%rsp),%r12
+	leaq	32(%rsp),%rdi
+	call	__ecp_nistz256_mul_montq
+
+	leaq	352(%rsp),%rbx
+	leaq	96(%rsp),%rdi
+	call	__ecp_nistz256_sub_fromq
+
+	movq	0+64(%rsp),%rax
+	movq	8+64(%rsp),%r14
+	leaq	0+64(%rsp),%rsi
+	movq	16+64(%rsp),%r15
+	movq	24+64(%rsp),%r8
+	leaq	128(%rsp),%rdi
+	call	__ecp_nistz256_sqr_montq
+
+	movq	0+96(%rsp),%rax
+	movq	8+96(%rsp),%r14
+	leaq	0+96(%rsp),%rsi
+	movq	16+96(%rsp),%r15
+	movq	24+96(%rsp),%r8
+	leaq	192(%rsp),%rdi
+	call	__ecp_nistz256_sqr_montq
+
+	movq	128(%rsp),%rax
+	leaq	128(%rsp),%rbx
+	movq	0+64(%rsp),%r9
+	movq	8+64(%rsp),%r10
+	leaq	0+64(%rsp),%rsi
+	movq	16+64(%rsp),%r11
+	movq	24+64(%rsp),%r12
+	leaq	160(%rsp),%rdi
+	call	__ecp_nistz256_mul_montq
+
+	movq	320(%rsp),%rax
+	leaq	320(%rsp),%rbx
+	movq	0+128(%rsp),%r9
+	movq	8+128(%rsp),%r10
+	leaq	0+128(%rsp),%rsi
+	movq	16+128(%rsp),%r11
+	movq	24+128(%rsp),%r12
+	leaq	0(%rsp),%rdi
+	call	__ecp_nistz256_mul_montq
+
+
+
+
+	addq	%r12,%r12
+	leaq	192(%rsp),%rsi
+	adcq	%r13,%r13
+	movq	%r12,%rax
+	adcq	%r8,%r8
+	adcq	%r9,%r9
+	movq	%r13,%rbp
+	sbbq	%r11,%r11
+
+	subq	$-1,%r12
+	movq	%r8,%rcx
+	sbbq	%r14,%r13
+	sbbq	$0,%r8
+	movq	%r9,%r10
+	sbbq	%r15,%r9
+	testq	%r11,%r11
+
+	cmovzq	%rax,%r12
+	movq	0(%rsi),%rax
+	cmovzq	%rbp,%r13
+	movq	8(%rsi),%rbp
+	cmovzq	%rcx,%r8
+	movq	16(%rsi),%rcx
+	cmovzq	%r10,%r9
+	movq	24(%rsi),%r10
+
+	call	__ecp_nistz256_subq
+
+	leaq	160(%rsp),%rbx
+	leaq	224(%rsp),%rdi
+	call	__ecp_nistz256_sub_fromq
+
+	movq	0+0(%rsp),%rax
+	movq	0+8(%rsp),%rbp
+	movq	0+16(%rsp),%rcx
+	movq	0+24(%rsp),%r10
+	leaq	64(%rsp),%rdi
+
+	call	__ecp_nistz256_subq
+
+	movq	%r12,0(%rdi)
+	movq	%r13,8(%rdi)
+	movq	%r8,16(%rdi)
+	movq	%r9,24(%rdi)
+	movq	352(%rsp),%rax
+	leaq	352(%rsp),%rbx
+	movq	0+160(%rsp),%r9
+	movq	8+160(%rsp),%r10
+	leaq	0+160(%rsp),%rsi
+	movq	16+160(%rsp),%r11
+	movq	24+160(%rsp),%r12
+	leaq	32(%rsp),%rdi
+	call	__ecp_nistz256_mul_montq
+
+	movq	96(%rsp),%rax
+	leaq	96(%rsp),%rbx
+	movq	0+64(%rsp),%r9
+	movq	8+64(%rsp),%r10
+	leaq	0+64(%rsp),%rsi
+	movq	16+64(%rsp),%r11
+	movq	24+64(%rsp),%r12
+	leaq	64(%rsp),%rdi
+	call	__ecp_nistz256_mul_montq
+
+	leaq	32(%rsp),%rbx
+	leaq	256(%rsp),%rdi
+	call	__ecp_nistz256_sub_fromq
+
+.byte	102,72,15,126,199
+
+	movdqa	%xmm5,%xmm0
+	movdqa	%xmm5,%xmm1
+	pandn	288(%rsp),%xmm0
+	movdqa	%xmm5,%xmm2
+	pandn	288+16(%rsp),%xmm1
+	movdqa	%xmm5,%xmm3
+	pand	.LONE_mont(%rip),%xmm2
+	pand	.LONE_mont+16(%rip),%xmm3
+	por	%xmm0,%xmm2
+	por	%xmm1,%xmm3
+
+	movdqa	%xmm4,%xmm0
+	movdqa	%xmm4,%xmm1
+	pandn	%xmm2,%xmm0
+	movdqa	%xmm4,%xmm2
+	pandn	%xmm3,%xmm1
+	movdqa	%xmm4,%xmm3
+	pand	384(%rsp),%xmm2
+	pand	384+16(%rsp),%xmm3
+	por	%xmm0,%xmm2
+	por	%xmm1,%xmm3
+	movdqu	%xmm2,64(%rdi)
+	movdqu	%xmm3,80(%rdi)
+
+	movdqa	%xmm5,%xmm0
+	movdqa	%xmm5,%xmm1
+	pandn	224(%rsp),%xmm0
+	movdqa	%xmm5,%xmm2
+	pandn	224+16(%rsp),%xmm1
+	movdqa	%xmm5,%xmm3
+	pand	416(%rsp),%xmm2
+	pand	416+16(%rsp),%xmm3
+	por	%xmm0,%xmm2
+	por	%xmm1,%xmm3
+
+	movdqa	%xmm4,%xmm0
+	movdqa	%xmm4,%xmm1
+	pandn	%xmm2,%xmm0
+	movdqa	%xmm4,%xmm2
+	pandn	%xmm3,%xmm1
+	movdqa	%xmm4,%xmm3
+	pand	320(%rsp),%xmm2
+	pand	320+16(%rsp),%xmm3
+	por	%xmm0,%xmm2
+	por	%xmm1,%xmm3
+	movdqu	%xmm2,0(%rdi)
+	movdqu	%xmm3,16(%rdi)
+
+	movdqa	%xmm5,%xmm0
+	movdqa	%xmm5,%xmm1
+	pandn	256(%rsp),%xmm0
+	movdqa	%xmm5,%xmm2
+	pandn	256+16(%rsp),%xmm1
+	movdqa	%xmm5,%xmm3
+	pand	448(%rsp),%xmm2
+	pand	448+16(%rsp),%xmm3
+	por	%xmm0,%xmm2
+	por	%xmm1,%xmm3
+
+	movdqa	%xmm4,%xmm0
+	movdqa	%xmm4,%xmm1
+	pandn	%xmm2,%xmm0
+	movdqa	%xmm4,%xmm2
+	pandn	%xmm3,%xmm1
+	movdqa	%xmm4,%xmm3
+	pand	352(%rsp),%xmm2
+	pand	352+16(%rsp),%xmm3
+	por	%xmm0,%xmm2
+	por	%xmm1,%xmm3
+	movdqu	%xmm2,32(%rdi)
+	movdqu	%xmm3,48(%rdi)
+
+	addq	$480+8,%rsp
+	popq	%r15
+	popq	%r14
+	popq	%r13
+	popq	%r12
+	popq	%rbx
+	popq	%rbp
+	.byte	0xf3,0xc3
+.size	ecp_nistz256_point_add_affine,.-ecp_nistz256_point_add_affine
+#endif
diff --git a/packager/third_party/boringssl/linux-x86_64/crypto/md5/md5-x86_64.S b/packager/third_party/boringssl/linux-x86_64/crypto/md5/md5-x86_64.S
index 7644689644..05369e2a77 100644
--- a/packager/third_party/boringssl/linux-x86_64/crypto/md5/md5-x86_64.S
+++ b/packager/third_party/boringssl/linux-x86_64/crypto/md5/md5-x86_64.S
@@ -495,14 +495,14 @@ md5_block_asm_data_order:
 	movl	%ecx,%r11d
 	addl	%ecx,%ebx
 	movl	0(%rsi),%r10d
-	movl	$4294967295,%r11d
+	movl	$0xffffffff,%r11d
 	xorl	%edx,%r11d
 	leal	-198630844(%rax,%r10,1),%eax
 	orl	%ebx,%r11d
 	xorl	%ecx,%r11d
 	addl	%r11d,%eax
 	movl	28(%rsi),%r10d
-	movl	$4294967295,%r11d
+	movl	$0xffffffff,%r11d
 	roll	$6,%eax
 	xorl	%ecx,%r11d
 	addl	%ebx,%eax
@@ -511,7 +511,7 @@ md5_block_asm_data_order:
 	xorl	%ebx,%r11d
 	addl	%r11d,%edx
 	movl	56(%rsi),%r10d
-	movl	$4294967295,%r11d
+	movl	$0xffffffff,%r11d
 	roll	$10,%edx
 	xorl	%ebx,%r11d
 	addl	%eax,%edx
@@ -520,7 +520,7 @@ md5_block_asm_data_order:
 	xorl	%eax,%r11d
 	addl	%r11d,%ecx
 	movl	20(%rsi),%r10d
-	movl	$4294967295,%r11d
+	movl	$0xffffffff,%r11d
 	roll	$15,%ecx
 	xorl	%eax,%r11d
 	addl	%edx,%ecx
@@ -529,7 +529,7 @@ md5_block_asm_data_order:
 	xorl	%edx,%r11d
 	addl	%r11d,%ebx
 	movl	48(%rsi),%r10d
-	movl	$4294967295,%r11d
+	movl	$0xffffffff,%r11d
 	roll	$21,%ebx
 	xorl	%edx,%r11d
 	addl	%ecx,%ebx
@@ -538,7 +538,7 @@ md5_block_asm_data_order:
 	xorl	%ecx,%r11d
 	addl	%r11d,%eax
 	movl	12(%rsi),%r10d
-	movl	$4294967295,%r11d
+	movl	$0xffffffff,%r11d
 	roll	$6,%eax
 	xorl	%ecx,%r11d
 	addl	%ebx,%eax
@@ -547,7 +547,7 @@ md5_block_asm_data_order:
 	xorl	%ebx,%r11d
 	addl	%r11d,%edx
 	movl	40(%rsi),%r10d
-	movl	$4294967295,%r11d
+	movl	$0xffffffff,%r11d
 	roll	$10,%edx
 	xorl	%ebx,%r11d
 	addl	%eax,%edx
@@ -556,7 +556,7 @@ md5_block_asm_data_order:
 	xorl	%eax,%r11d
 	addl	%r11d,%ecx
 	movl	4(%rsi),%r10d
-	movl	$4294967295,%r11d
+	movl	$0xffffffff,%r11d
 	roll	$15,%ecx
 	xorl	%eax,%r11d
 	addl	%edx,%ecx
@@ -565,7 +565,7 @@ md5_block_asm_data_order:
 	xorl	%edx,%r11d
 	addl	%r11d,%ebx
 	movl	32(%rsi),%r10d
-	movl	$4294967295,%r11d
+	movl	$0xffffffff,%r11d
 	roll	$21,%ebx
 	xorl	%edx,%r11d
 	addl	%ecx,%ebx
@@ -574,7 +574,7 @@ md5_block_asm_data_order:
 	xorl	%ecx,%r11d
 	addl	%r11d,%eax
 	movl	60(%rsi),%r10d
-	movl	$4294967295,%r11d
+	movl	$0xffffffff,%r11d
 	roll	$6,%eax
 	xorl	%ecx,%r11d
 	addl	%ebx,%eax
@@ -583,7 +583,7 @@ md5_block_asm_data_order:
 	xorl	%ebx,%r11d
 	addl	%r11d,%edx
 	movl	24(%rsi),%r10d
-	movl	$4294967295,%r11d
+	movl	$0xffffffff,%r11d
 	roll	$10,%edx
 	xorl	%ebx,%r11d
 	addl	%eax,%edx
@@ -592,7 +592,7 @@ md5_block_asm_data_order:
 	xorl	%eax,%r11d
 	addl	%r11d,%ecx
 	movl	52(%rsi),%r10d
-	movl	$4294967295,%r11d
+	movl	$0xffffffff,%r11d
 	roll	$15,%ecx
 	xorl	%eax,%r11d
 	addl	%edx,%ecx
@@ -601,7 +601,7 @@ md5_block_asm_data_order:
 	xorl	%edx,%r11d
 	addl	%r11d,%ebx
 	movl	16(%rsi),%r10d
-	movl	$4294967295,%r11d
+	movl	$0xffffffff,%r11d
 	roll	$21,%ebx
 	xorl	%edx,%r11d
 	addl	%ecx,%ebx
@@ -610,7 +610,7 @@ md5_block_asm_data_order:
 	xorl	%ecx,%r11d
 	addl	%r11d,%eax
 	movl	44(%rsi),%r10d
-	movl	$4294967295,%r11d
+	movl	$0xffffffff,%r11d
 	roll	$6,%eax
 	xorl	%ecx,%r11d
 	addl	%ebx,%eax
@@ -619,7 +619,7 @@ md5_block_asm_data_order:
 	xorl	%ebx,%r11d
 	addl	%r11d,%edx
 	movl	8(%rsi),%r10d
-	movl	$4294967295,%r11d
+	movl	$0xffffffff,%r11d
 	roll	$10,%edx
 	xorl	%ebx,%r11d
 	addl	%eax,%edx
@@ -628,7 +628,7 @@ md5_block_asm_data_order:
 	xorl	%eax,%r11d
 	addl	%r11d,%ecx
 	movl	36(%rsi),%r10d
-	movl	$4294967295,%r11d
+	movl	$0xffffffff,%r11d
 	roll	$15,%ecx
 	xorl	%eax,%r11d
 	addl	%edx,%ecx
@@ -637,7 +637,7 @@ md5_block_asm_data_order:
 	xorl	%edx,%r11d
 	addl	%r11d,%ebx
 	movl	0(%rsi),%r10d
-	movl	$4294967295,%r11d
+	movl	$0xffffffff,%r11d
 	roll	$21,%ebx
 	xorl	%edx,%r11d
 	addl	%ecx,%ebx
diff --git a/packager/third_party/boringssl/linux-x86_64/crypto/modes/ghash-x86_64.S b/packager/third_party/boringssl/linux-x86_64/crypto/modes/ghash-x86_64.S
index 1db7d69d4b..b47bdc9bd9 100644
--- a/packager/third_party/boringssl/linux-x86_64/crypto/modes/ghash-x86_64.S
+++ b/packager/third_party/boringssl/linux-x86_64/crypto/modes/ghash-x86_64.S
@@ -23,14 +23,14 @@ gcm_gmult_4bit:
 	movq	$14,%rcx
 	movq	8(%rsi,%rax,1),%r8
 	movq	(%rsi,%rax,1),%r9
-	andb	$240,%bl
+	andb	$0xf0,%bl
 	movq	%r8,%rdx
 	jmp	.Loop1
 
 .align	16
 .Loop1:
 	shrq	$4,%r8
-	andq	$15,%rdx
+	andq	$0xf,%rdx
 	movq	%r9,%r10
 	movb	(%rdi,%rcx,1),%al
 	shrq	$4,%r9
@@ -46,13 +46,13 @@ gcm_gmult_4bit:
 	js	.Lbreak1
 
 	shrq	$4,%r8
-	andq	$15,%rdx
+	andq	$0xf,%rdx
 	movq	%r9,%r10
 	shrq	$4,%r9
 	xorq	8(%rsi,%rax,1),%r8
 	shlq	$60,%r10
 	xorq	(%rsi,%rax,1),%r9
-	andb	$240,%bl
+	andb	$0xf0,%bl
 	xorq	(%r11,%rdx,8),%r9
 	movq	%r8,%rdx
 	xorq	%r10,%r8
@@ -61,19 +61,19 @@ gcm_gmult_4bit:
 .align	16
 .Lbreak1:
 	shrq	$4,%r8
-	andq	$15,%rdx
+	andq	$0xf,%rdx
 	movq	%r9,%r10
 	shrq	$4,%r9
 	xorq	8(%rsi,%rax,1),%r8
 	shlq	$60,%r10
 	xorq	(%rsi,%rax,1),%r9
-	andb	$240,%bl
+	andb	$0xf0,%bl
 	xorq	(%r11,%rdx,8),%r9
 	movq	%r8,%rdx
 	xorq	%r10,%r8
 
 	shrq	$4,%r8
-	andq	$15,%rdx
+	andq	$0xf,%rdx
 	movq	%r9,%r10
 	shrq	$4,%r9
 	xorq	8(%rsi,%rbx,1),%r8
@@ -881,20 +881,20 @@ gcm_ghash_clmul:
 	movdqu	32(%rsi),%xmm7
 .byte	102,65,15,56,0,194
 
-	subq	$16,%rcx
+	subq	$0x10,%rcx
 	jz	.Lodd_tail
 
 	movdqu	16(%rsi),%xmm6
 	movl	OPENSSL_ia32cap_P+4(%rip),%eax
-	cmpq	$48,%rcx
+	cmpq	$0x30,%rcx
 	jb	.Lskip4x
 
 	andl	$71303168,%eax
 	cmpl	$4194304,%eax
 	je	.Lskip4x
 
-	subq	$48,%rcx
-	movq	$11547335547999543296,%rax
+	subq	$0x30,%rcx
+	movq	$0xA040608020C0E000,%rax
 	movdqu	48(%rsi),%xmm14
 	movdqu	64(%rsi),%xmm15
 
@@ -941,7 +941,7 @@ gcm_ghash_clmul:
 	xorps	%xmm13,%xmm5
 
 	leaq	64(%rdx),%rdx
-	subq	$64,%rcx
+	subq	$0x40,%rcx
 	jc	.Ltail4x
 
 	jmp	.Lmod4_loop
@@ -1024,7 +1024,7 @@ gcm_ghash_clmul:
 	xorps	%xmm13,%xmm5
 
 	leaq	64(%rdx),%rdx
-	subq	$64,%rcx
+	subq	$0x40,%rcx
 	jnc	.Lmod4_loop
 
 .Ltail4x:
@@ -1068,10 +1068,10 @@ gcm_ghash_clmul:
 	pxor	%xmm4,%xmm0
 	psrlq	$1,%xmm0
 	pxor	%xmm1,%xmm0
-	addq	$64,%rcx
+	addq	$0x40,%rcx
 	jz	.Ldone
 	movdqu	32(%rsi),%xmm7
-	subq	$16,%rcx
+	subq	$0x10,%rcx
 	jz	.Lodd_tail
 .Lskip4x:
 
@@ -1094,7 +1094,7 @@ gcm_ghash_clmul:
 
 	leaq	32(%rdx),%rdx
 	nop
-	subq	$32,%rcx
+	subq	$0x20,%rcx
 	jbe	.Leven_tail
 	nop
 	jmp	.Lmod_loop
@@ -1157,7 +1157,7 @@ gcm_ghash_clmul:
 .byte	102,15,58,68,231,0
 	pxor	%xmm1,%xmm0
 
-	subq	$32,%rcx
+	subq	$0x20,%rcx
 	ja	.Lmod_loop
 
 .Leven_tail:
diff --git a/packager/third_party/boringssl/linux-x86_64/crypto/sha/sha1-x86_64.S b/packager/third_party/boringssl/linux-x86_64/crypto/sha/sha1-x86_64.S
index 7668c2b1f5..d830b534de 100644
--- a/packager/third_party/boringssl/linux-x86_64/crypto/sha/sha1-x86_64.S
+++ b/packager/third_party/boringssl/linux-x86_64/crypto/sha/sha1-x86_64.S
@@ -13,6 +13,11 @@ sha1_block_data_order:
 	movl	OPENSSL_ia32cap_P+8(%rip),%r10d
 	testl	$512,%r8d
 	jz	.Lialu
+	andl	$268435456,%r8d
+	andl	$1073741824,%r9d
+	orl	%r9d,%r8d
+	cmpl	$1342177280,%r8d
+	je	_avx_shortcut
 	jmp	_ssse3_shortcut
 
 .align	16
@@ -2408,6 +2413,1122 @@ _ssse3_shortcut:
 .Lepilogue_ssse3:
 	.byte	0xf3,0xc3
 .size	sha1_block_data_order_ssse3,.-sha1_block_data_order_ssse3
+.type	sha1_block_data_order_avx,@function
+.align	16
+sha1_block_data_order_avx:
+_avx_shortcut:
+	movq	%rsp,%rax
+	pushq	%rbx
+	pushq	%rbp
+	pushq	%r12
+	pushq	%r13
+	pushq	%r14
+	leaq	-64(%rsp),%rsp
+	vzeroupper
+	movq	%rax,%r14
+	andq	$-64,%rsp
+	movq	%rdi,%r8
+	movq	%rsi,%r9
+	movq	%rdx,%r10
+
+	shlq	$6,%r10
+	addq	%r9,%r10
+	leaq	K_XX_XX+64(%rip),%r11
+
+	movl	0(%r8),%eax
+	movl	4(%r8),%ebx
+	movl	8(%r8),%ecx
+	movl	12(%r8),%edx
+	movl	%ebx,%esi
+	movl	16(%r8),%ebp
+	movl	%ecx,%edi
+	xorl	%edx,%edi
+	andl	%edi,%esi
+
+	vmovdqa	64(%r11),%xmm6
+	vmovdqa	-64(%r11),%xmm11
+	vmovdqu	0(%r9),%xmm0
+	vmovdqu	16(%r9),%xmm1
+	vmovdqu	32(%r9),%xmm2
+	vmovdqu	48(%r9),%xmm3
+	vpshufb	%xmm6,%xmm0,%xmm0
+	addq	$64,%r9
+	vpshufb	%xmm6,%xmm1,%xmm1
+	vpshufb	%xmm6,%xmm2,%xmm2
+	vpshufb	%xmm6,%xmm3,%xmm3
+	vpaddd	%xmm11,%xmm0,%xmm4
+	vpaddd	%xmm11,%xmm1,%xmm5
+	vpaddd	%xmm11,%xmm2,%xmm6
+	vmovdqa	%xmm4,0(%rsp)
+	vmovdqa	%xmm5,16(%rsp)
+	vmovdqa	%xmm6,32(%rsp)
+	jmp	.Loop_avx
+.align	16
+.Loop_avx:
+	shrdl	$2,%ebx,%ebx
+	xorl	%edx,%esi
+	vpalignr	$8,%xmm0,%xmm1,%xmm4
+	movl	%eax,%edi
+	addl	0(%rsp),%ebp
+	vpaddd	%xmm3,%xmm11,%xmm9
+	xorl	%ecx,%ebx
+	shldl	$5,%eax,%eax
+	vpsrldq	$4,%xmm3,%xmm8
+	addl	%esi,%ebp
+	andl	%ebx,%edi
+	vpxor	%xmm0,%xmm4,%xmm4
+	xorl	%ecx,%ebx
+	addl	%eax,%ebp
+	vpxor	%xmm2,%xmm8,%xmm8
+	shrdl	$7,%eax,%eax
+	xorl	%ecx,%edi
+	movl	%ebp,%esi
+	addl	4(%rsp),%edx
+	vpxor	%xmm8,%xmm4,%xmm4
+	xorl	%ebx,%eax
+	shldl	$5,%ebp,%ebp
+	vmovdqa	%xmm9,48(%rsp)
+	addl	%edi,%edx
+	andl	%eax,%esi
+	vpsrld	$31,%xmm4,%xmm8
+	xorl	%ebx,%eax
+	addl	%ebp,%edx
+	shrdl	$7,%ebp,%ebp
+	xorl	%ebx,%esi
+	vpslldq	$12,%xmm4,%xmm10
+	vpaddd	%xmm4,%xmm4,%xmm4
+	movl	%edx,%edi
+	addl	8(%rsp),%ecx
+	xorl	%eax,%ebp
+	shldl	$5,%edx,%edx
+	vpsrld	$30,%xmm10,%xmm9
+	vpor	%xmm8,%xmm4,%xmm4
+	addl	%esi,%ecx
+	andl	%ebp,%edi
+	xorl	%eax,%ebp
+	addl	%edx,%ecx
+	vpslld	$2,%xmm10,%xmm10
+	vpxor	%xmm9,%xmm4,%xmm4
+	shrdl	$7,%edx,%edx
+	xorl	%eax,%edi
+	movl	%ecx,%esi
+	addl	12(%rsp),%ebx
+	vpxor	%xmm10,%xmm4,%xmm4
+	xorl	%ebp,%edx
+	shldl	$5,%ecx,%ecx
+	addl	%edi,%ebx
+	andl	%edx,%esi
+	xorl	%ebp,%edx
+	addl	%ecx,%ebx
+	shrdl	$7,%ecx,%ecx
+	xorl	%ebp,%esi
+	vpalignr	$8,%xmm1,%xmm2,%xmm5
+	movl	%ebx,%edi
+	addl	16(%rsp),%eax
+	vpaddd	%xmm4,%xmm11,%xmm9
+	xorl	%edx,%ecx
+	shldl	$5,%ebx,%ebx
+	vpsrldq	$4,%xmm4,%xmm8
+	addl	%esi,%eax
+	andl	%ecx,%edi
+	vpxor	%xmm1,%xmm5,%xmm5
+	xorl	%edx,%ecx
+	addl	%ebx,%eax
+	vpxor	%xmm3,%xmm8,%xmm8
+	shrdl	$7,%ebx,%ebx
+	xorl	%edx,%edi
+	movl	%eax,%esi
+	addl	20(%rsp),%ebp
+	vpxor	%xmm8,%xmm5,%xmm5
+	xorl	%ecx,%ebx
+	shldl	$5,%eax,%eax
+	vmovdqa	%xmm9,0(%rsp)
+	addl	%edi,%ebp
+	andl	%ebx,%esi
+	vpsrld	$31,%xmm5,%xmm8
+	xorl	%ecx,%ebx
+	addl	%eax,%ebp
+	shrdl	$7,%eax,%eax
+	xorl	%ecx,%esi
+	vpslldq	$12,%xmm5,%xmm10
+	vpaddd	%xmm5,%xmm5,%xmm5
+	movl	%ebp,%edi
+	addl	24(%rsp),%edx
+	xorl	%ebx,%eax
+	shldl	$5,%ebp,%ebp
+	vpsrld	$30,%xmm10,%xmm9
+	vpor	%xmm8,%xmm5,%xmm5
+	addl	%esi,%edx
+	andl	%eax,%edi
+	xorl	%ebx,%eax
+	addl	%ebp,%edx
+	vpslld	$2,%xmm10,%xmm10
+	vpxor	%xmm9,%xmm5,%xmm5
+	shrdl	$7,%ebp,%ebp
+	xorl	%ebx,%edi
+	movl	%edx,%esi
+	addl	28(%rsp),%ecx
+	vpxor	%xmm10,%xmm5,%xmm5
+	xorl	%eax,%ebp
+	shldl	$5,%edx,%edx
+	vmovdqa	-32(%r11),%xmm11
+	addl	%edi,%ecx
+	andl	%ebp,%esi
+	xorl	%eax,%ebp
+	addl	%edx,%ecx
+	shrdl	$7,%edx,%edx
+	xorl	%eax,%esi
+	vpalignr	$8,%xmm2,%xmm3,%xmm6
+	movl	%ecx,%edi
+	addl	32(%rsp),%ebx
+	vpaddd	%xmm5,%xmm11,%xmm9
+	xorl	%ebp,%edx
+	shldl	$5,%ecx,%ecx
+	vpsrldq	$4,%xmm5,%xmm8
+	addl	%esi,%ebx
+	andl	%edx,%edi
+	vpxor	%xmm2,%xmm6,%xmm6
+	xorl	%ebp,%edx
+	addl	%ecx,%ebx
+	vpxor	%xmm4,%xmm8,%xmm8
+	shrdl	$7,%ecx,%ecx
+	xorl	%ebp,%edi
+	movl	%ebx,%esi
+	addl	36(%rsp),%eax
+	vpxor	%xmm8,%xmm6,%xmm6
+	xorl	%edx,%ecx
+	shldl	$5,%ebx,%ebx
+	vmovdqa	%xmm9,16(%rsp)
+	addl	%edi,%eax
+	andl	%ecx,%esi
+	vpsrld	$31,%xmm6,%xmm8
+	xorl	%edx,%ecx
+	addl	%ebx,%eax
+	shrdl	$7,%ebx,%ebx
+	xorl	%edx,%esi
+	vpslldq	$12,%xmm6,%xmm10
+	vpaddd	%xmm6,%xmm6,%xmm6
+	movl	%eax,%edi
+	addl	40(%rsp),%ebp
+	xorl	%ecx,%ebx
+	shldl	$5,%eax,%eax
+	vpsrld	$30,%xmm10,%xmm9
+	vpor	%xmm8,%xmm6,%xmm6
+	addl	%esi,%ebp
+	andl	%ebx,%edi
+	xorl	%ecx,%ebx
+	addl	%eax,%ebp
+	vpslld	$2,%xmm10,%xmm10
+	vpxor	%xmm9,%xmm6,%xmm6
+	shrdl	$7,%eax,%eax
+	xorl	%ecx,%edi
+	movl	%ebp,%esi
+	addl	44(%rsp),%edx
+	vpxor	%xmm10,%xmm6,%xmm6
+	xorl	%ebx,%eax
+	shldl	$5,%ebp,%ebp
+	addl	%edi,%edx
+	andl	%eax,%esi
+	xorl	%ebx,%eax
+	addl	%ebp,%edx
+	shrdl	$7,%ebp,%ebp
+	xorl	%ebx,%esi
+	vpalignr	$8,%xmm3,%xmm4,%xmm7
+	movl	%edx,%edi
+	addl	48(%rsp),%ecx
+	vpaddd	%xmm6,%xmm11,%xmm9
+	xorl	%eax,%ebp
+	shldl	$5,%edx,%edx
+	vpsrldq	$4,%xmm6,%xmm8
+	addl	%esi,%ecx
+	andl	%ebp,%edi
+	vpxor	%xmm3,%xmm7,%xmm7
+	xorl	%eax,%ebp
+	addl	%edx,%ecx
+	vpxor	%xmm5,%xmm8,%xmm8
+	shrdl	$7,%edx,%edx
+	xorl	%eax,%edi
+	movl	%ecx,%esi
+	addl	52(%rsp),%ebx
+	vpxor	%xmm8,%xmm7,%xmm7
+	xorl	%ebp,%edx
+	shldl	$5,%ecx,%ecx
+	vmovdqa	%xmm9,32(%rsp)
+	addl	%edi,%ebx
+	andl	%edx,%esi
+	vpsrld	$31,%xmm7,%xmm8
+	xorl	%ebp,%edx
+	addl	%ecx,%ebx
+	shrdl	$7,%ecx,%ecx
+	xorl	%ebp,%esi
+	vpslldq	$12,%xmm7,%xmm10
+	vpaddd	%xmm7,%xmm7,%xmm7
+	movl	%ebx,%edi
+	addl	56(%rsp),%eax
+	xorl	%edx,%ecx
+	shldl	$5,%ebx,%ebx
+	vpsrld	$30,%xmm10,%xmm9
+	vpor	%xmm8,%xmm7,%xmm7
+	addl	%esi,%eax
+	andl	%ecx,%edi
+	xorl	%edx,%ecx
+	addl	%ebx,%eax
+	vpslld	$2,%xmm10,%xmm10
+	vpxor	%xmm9,%xmm7,%xmm7
+	shrdl	$7,%ebx,%ebx
+	xorl	%edx,%edi
+	movl	%eax,%esi
+	addl	60(%rsp),%ebp
+	vpxor	%xmm10,%xmm7,%xmm7
+	xorl	%ecx,%ebx
+	shldl	$5,%eax,%eax
+	addl	%edi,%ebp
+	andl	%ebx,%esi
+	xorl	%ecx,%ebx
+	addl	%eax,%ebp
+	vpalignr	$8,%xmm6,%xmm7,%xmm8
+	vpxor	%xmm4,%xmm0,%xmm0
+	shrdl	$7,%eax,%eax
+	xorl	%ecx,%esi
+	movl	%ebp,%edi
+	addl	0(%rsp),%edx
+	vpxor	%xmm1,%xmm0,%xmm0
+	xorl	%ebx,%eax
+	shldl	$5,%ebp,%ebp
+	vpaddd	%xmm7,%xmm11,%xmm9
+	addl	%esi,%edx
+	andl	%eax,%edi
+	vpxor	%xmm8,%xmm0,%xmm0
+	xorl	%ebx,%eax
+	addl	%ebp,%edx
+	shrdl	$7,%ebp,%ebp
+	xorl	%ebx,%edi
+	vpsrld	$30,%xmm0,%xmm8
+	vmovdqa	%xmm9,48(%rsp)
+	movl	%edx,%esi
+	addl	4(%rsp),%ecx
+	xorl	%eax,%ebp
+	shldl	$5,%edx,%edx
+	vpslld	$2,%xmm0,%xmm0
+	addl	%edi,%ecx
+	andl	%ebp,%esi
+	xorl	%eax,%ebp
+	addl	%edx,%ecx
+	shrdl	$7,%edx,%edx
+	xorl	%eax,%esi
+	movl	%ecx,%edi
+	addl	8(%rsp),%ebx
+	vpor	%xmm8,%xmm0,%xmm0
+	xorl	%ebp,%edx
+	shldl	$5,%ecx,%ecx
+	addl	%esi,%ebx
+	andl	%edx,%edi
+	xorl	%ebp,%edx
+	addl	%ecx,%ebx
+	addl	12(%rsp),%eax
+	xorl	%ebp,%edi
+	movl	%ebx,%esi
+	shldl	$5,%ebx,%ebx
+	addl	%edi,%eax
+	xorl	%edx,%esi
+	shrdl	$7,%ecx,%ecx
+	addl	%ebx,%eax
+	vpalignr	$8,%xmm7,%xmm0,%xmm8
+	vpxor	%xmm5,%xmm1,%xmm1
+	addl	16(%rsp),%ebp
+	xorl	%ecx,%esi
+	movl	%eax,%edi
+	shldl	$5,%eax,%eax
+	vpxor	%xmm2,%xmm1,%xmm1
+	addl	%esi,%ebp
+	xorl	%ecx,%edi
+	vpaddd	%xmm0,%xmm11,%xmm9
+	shrdl	$7,%ebx,%ebx
+	addl	%eax,%ebp
+	vpxor	%xmm8,%xmm1,%xmm1
+	addl	20(%rsp),%edx
+	xorl	%ebx,%edi
+	movl	%ebp,%esi
+	shldl	$5,%ebp,%ebp
+	vpsrld	$30,%xmm1,%xmm8
+	vmovdqa	%xmm9,0(%rsp)
+	addl	%edi,%edx
+	xorl	%ebx,%esi
+	shrdl	$7,%eax,%eax
+	addl	%ebp,%edx
+	vpslld	$2,%xmm1,%xmm1
+	addl	24(%rsp),%ecx
+	xorl	%eax,%esi
+	movl	%edx,%edi
+	shldl	$5,%edx,%edx
+	addl	%esi,%ecx
+	xorl	%eax,%edi
+	shrdl	$7,%ebp,%ebp
+	addl	%edx,%ecx
+	vpor	%xmm8,%xmm1,%xmm1
+	addl	28(%rsp),%ebx
+	xorl	%ebp,%edi
+	movl	%ecx,%esi
+	shldl	$5,%ecx,%ecx
+	addl	%edi,%ebx
+	xorl	%ebp,%esi
+	shrdl	$7,%edx,%edx
+	addl	%ecx,%ebx
+	vpalignr	$8,%xmm0,%xmm1,%xmm8
+	vpxor	%xmm6,%xmm2,%xmm2
+	addl	32(%rsp),%eax
+	xorl	%edx,%esi
+	movl	%ebx,%edi
+	shldl	$5,%ebx,%ebx
+	vpxor	%xmm3,%xmm2,%xmm2
+	addl	%esi,%eax
+	xorl	%edx,%edi
+	vpaddd	%xmm1,%xmm11,%xmm9
+	vmovdqa	0(%r11),%xmm11
+	shrdl	$7,%ecx,%ecx
+	addl	%ebx,%eax
+	vpxor	%xmm8,%xmm2,%xmm2
+	addl	36(%rsp),%ebp
+	xorl	%ecx,%edi
+	movl	%eax,%esi
+	shldl	$5,%eax,%eax
+	vpsrld	$30,%xmm2,%xmm8
+	vmovdqa	%xmm9,16(%rsp)
+	addl	%edi,%ebp
+	xorl	%ecx,%esi
+	shrdl	$7,%ebx,%ebx
+	addl	%eax,%ebp
+	vpslld	$2,%xmm2,%xmm2
+	addl	40(%rsp),%edx
+	xorl	%ebx,%esi
+	movl	%ebp,%edi
+	shldl	$5,%ebp,%ebp
+	addl	%esi,%edx
+	xorl	%ebx,%edi
+	shrdl	$7,%eax,%eax
+	addl	%ebp,%edx
+	vpor	%xmm8,%xmm2,%xmm2
+	addl	44(%rsp),%ecx
+	xorl	%eax,%edi
+	movl	%edx,%esi
+	shldl	$5,%edx,%edx
+	addl	%edi,%ecx
+	xorl	%eax,%esi
+	shrdl	$7,%ebp,%ebp
+	addl	%edx,%ecx
+	vpalignr	$8,%xmm1,%xmm2,%xmm8
+	vpxor	%xmm7,%xmm3,%xmm3
+	addl	48(%rsp),%ebx
+	xorl	%ebp,%esi
+	movl	%ecx,%edi
+	shldl	$5,%ecx,%ecx
+	vpxor	%xmm4,%xmm3,%xmm3
+	addl	%esi,%ebx
+	xorl	%ebp,%edi
+	vpaddd	%xmm2,%xmm11,%xmm9
+	shrdl	$7,%edx,%edx
+	addl	%ecx,%ebx
+	vpxor	%xmm8,%xmm3,%xmm3
+	addl	52(%rsp),%eax
+	xorl	%edx,%edi
+	movl	%ebx,%esi
+	shldl	$5,%ebx,%ebx
+	vpsrld	$30,%xmm3,%xmm8
+	vmovdqa	%xmm9,32(%rsp)
+	addl	%edi,%eax
+	xorl	%edx,%esi
+	shrdl	$7,%ecx,%ecx
+	addl	%ebx,%eax
+	vpslld	$2,%xmm3,%xmm3
+	addl	56(%rsp),%ebp
+	xorl	%ecx,%esi
+	movl	%eax,%edi
+	shldl	$5,%eax,%eax
+	addl	%esi,%ebp
+	xorl	%ecx,%edi
+	shrdl	$7,%ebx,%ebx
+	addl	%eax,%ebp
+	vpor	%xmm8,%xmm3,%xmm3
+	addl	60(%rsp),%edx
+	xorl	%ebx,%edi
+	movl	%ebp,%esi
+	shldl	$5,%ebp,%ebp
+	addl	%edi,%edx
+	xorl	%ebx,%esi
+	shrdl	$7,%eax,%eax
+	addl	%ebp,%edx
+	vpalignr	$8,%xmm2,%xmm3,%xmm8
+	vpxor	%xmm0,%xmm4,%xmm4
+	addl	0(%rsp),%ecx
+	xorl	%eax,%esi
+	movl	%edx,%edi
+	shldl	$5,%edx,%edx
+	vpxor	%xmm5,%xmm4,%xmm4
+	addl	%esi,%ecx
+	xorl	%eax,%edi
+	vpaddd	%xmm3,%xmm11,%xmm9
+	shrdl	$7,%ebp,%ebp
+	addl	%edx,%ecx
+	vpxor	%xmm8,%xmm4,%xmm4
+	addl	4(%rsp),%ebx
+	xorl	%ebp,%edi
+	movl	%ecx,%esi
+	shldl	$5,%ecx,%ecx
+	vpsrld	$30,%xmm4,%xmm8
+	vmovdqa	%xmm9,48(%rsp)
+	addl	%edi,%ebx
+	xorl	%ebp,%esi
+	shrdl	$7,%edx,%edx
+	addl	%ecx,%ebx
+	vpslld	$2,%xmm4,%xmm4
+	addl	8(%rsp),%eax
+	xorl	%edx,%esi
+	movl	%ebx,%edi
+	shldl	$5,%ebx,%ebx
+	addl	%esi,%eax
+	xorl	%edx,%edi
+	shrdl	$7,%ecx,%ecx
+	addl	%ebx,%eax
+	vpor	%xmm8,%xmm4,%xmm4
+	addl	12(%rsp),%ebp
+	xorl	%ecx,%edi
+	movl	%eax,%esi
+	shldl	$5,%eax,%eax
+	addl	%edi,%ebp
+	xorl	%ecx,%esi
+	shrdl	$7,%ebx,%ebx
+	addl	%eax,%ebp
+	vpalignr	$8,%xmm3,%xmm4,%xmm8
+	vpxor	%xmm1,%xmm5,%xmm5
+	addl	16(%rsp),%edx
+	xorl	%ebx,%esi
+	movl	%ebp,%edi
+	shldl	$5,%ebp,%ebp
+	vpxor	%xmm6,%xmm5,%xmm5
+	addl	%esi,%edx
+	xorl	%ebx,%edi
+	vpaddd	%xmm4,%xmm11,%xmm9
+	shrdl	$7,%eax,%eax
+	addl	%ebp,%edx
+	vpxor	%xmm8,%xmm5,%xmm5
+	addl	20(%rsp),%ecx
+	xorl	%eax,%edi
+	movl	%edx,%esi
+	shldl	$5,%edx,%edx
+	vpsrld	$30,%xmm5,%xmm8
+	vmovdqa	%xmm9,0(%rsp)
+	addl	%edi,%ecx
+	xorl	%eax,%esi
+	shrdl	$7,%ebp,%ebp
+	addl	%edx,%ecx
+	vpslld	$2,%xmm5,%xmm5
+	addl	24(%rsp),%ebx
+	xorl	%ebp,%esi
+	movl	%ecx,%edi
+	shldl	$5,%ecx,%ecx
+	addl	%esi,%ebx
+	xorl	%ebp,%edi
+	shrdl	$7,%edx,%edx
+	addl	%ecx,%ebx
+	vpor	%xmm8,%xmm5,%xmm5
+	addl	28(%rsp),%eax
+	shrdl	$7,%ecx,%ecx
+	movl	%ebx,%esi
+	xorl	%edx,%edi
+	shldl	$5,%ebx,%ebx
+	addl	%edi,%eax
+	xorl	%ecx,%esi
+	xorl	%edx,%ecx
+	addl	%ebx,%eax
+	vpalignr	$8,%xmm4,%xmm5,%xmm8
+	vpxor	%xmm2,%xmm6,%xmm6
+	addl	32(%rsp),%ebp
+	andl	%ecx,%esi
+	xorl	%edx,%ecx
+	shrdl	$7,%ebx,%ebx
+	vpxor	%xmm7,%xmm6,%xmm6
+	movl	%eax,%edi
+	xorl	%ecx,%esi
+	vpaddd	%xmm5,%xmm11,%xmm9
+	shldl	$5,%eax,%eax
+	addl	%esi,%ebp
+	vpxor	%xmm8,%xmm6,%xmm6
+	xorl	%ebx,%edi
+	xorl	%ecx,%ebx
+	addl	%eax,%ebp
+	addl	36(%rsp),%edx
+	vpsrld	$30,%xmm6,%xmm8
+	vmovdqa	%xmm9,16(%rsp)
+	andl	%ebx,%edi
+	xorl	%ecx,%ebx
+	shrdl	$7,%eax,%eax
+	movl	%ebp,%esi
+	vpslld	$2,%xmm6,%xmm6
+	xorl	%ebx,%edi
+	shldl	$5,%ebp,%ebp
+	addl	%edi,%edx
+	xorl	%eax,%esi
+	xorl	%ebx,%eax
+	addl	%ebp,%edx
+	addl	40(%rsp),%ecx
+	andl	%eax,%esi
+	vpor	%xmm8,%xmm6,%xmm6
+	xorl	%ebx,%eax
+	shrdl	$7,%ebp,%ebp
+	movl	%edx,%edi
+	xorl	%eax,%esi
+	shldl	$5,%edx,%edx
+	addl	%esi,%ecx
+	xorl	%ebp,%edi
+	xorl	%eax,%ebp
+	addl	%edx,%ecx
+	addl	44(%rsp),%ebx
+	andl	%ebp,%edi
+	xorl	%eax,%ebp
+	shrdl	$7,%edx,%edx
+	movl	%ecx,%esi
+	xorl	%ebp,%edi
+	shldl	$5,%ecx,%ecx
+	addl	%edi,%ebx
+	xorl	%edx,%esi
+	xorl	%ebp,%edx
+	addl	%ecx,%ebx
+	vpalignr	$8,%xmm5,%xmm6,%xmm8
+	vpxor	%xmm3,%xmm7,%xmm7
+	addl	48(%rsp),%eax
+	andl	%edx,%esi
+	xorl	%ebp,%edx
+	shrdl	$7,%ecx,%ecx
+	vpxor	%xmm0,%xmm7,%xmm7
+	movl	%ebx,%edi
+	xorl	%edx,%esi
+	vpaddd	%xmm6,%xmm11,%xmm9
+	vmovdqa	32(%r11),%xmm11
+	shldl	$5,%ebx,%ebx
+	addl	%esi,%eax
+	vpxor	%xmm8,%xmm7,%xmm7
+	xorl	%ecx,%edi
+	xorl	%edx,%ecx
+	addl	%ebx,%eax
+	addl	52(%rsp),%ebp
+	vpsrld	$30,%xmm7,%xmm8
+	vmovdqa	%xmm9,32(%rsp)
+	andl	%ecx,%edi
+	xorl	%edx,%ecx
+	shrdl	$7,%ebx,%ebx
+	movl	%eax,%esi
+	vpslld	$2,%xmm7,%xmm7
+	xorl	%ecx,%edi
+	shldl	$5,%eax,%eax
+	addl	%edi,%ebp
+	xorl	%ebx,%esi
+	xorl	%ecx,%ebx
+	addl	%eax,%ebp
+	addl	56(%rsp),%edx
+	andl	%ebx,%esi
+	vpor	%xmm8,%xmm7,%xmm7
+	xorl	%ecx,%ebx
+	shrdl	$7,%eax,%eax
+	movl	%ebp,%edi
+	xorl	%ebx,%esi
+	shldl	$5,%ebp,%ebp
+	addl	%esi,%edx
+	xorl	%eax,%edi
+	xorl	%ebx,%eax
+	addl	%ebp,%edx
+	addl	60(%rsp),%ecx
+	andl	%eax,%edi
+	xorl	%ebx,%eax
+	shrdl	$7,%ebp,%ebp
+	movl	%edx,%esi
+	xorl	%eax,%edi
+	shldl	$5,%edx,%edx
+	addl	%edi,%ecx
+	xorl	%ebp,%esi
+	xorl	%eax,%ebp
+	addl	%edx,%ecx
+	vpalignr	$8,%xmm6,%xmm7,%xmm8
+	vpxor	%xmm4,%xmm0,%xmm0
+	addl	0(%rsp),%ebx
+	andl	%ebp,%esi
+	xorl	%eax,%ebp
+	shrdl	$7,%edx,%edx
+	vpxor	%xmm1,%xmm0,%xmm0
+	movl	%ecx,%edi
+	xorl	%ebp,%esi
+	vpaddd	%xmm7,%xmm11,%xmm9
+	shldl	$5,%ecx,%ecx
+	addl	%esi,%ebx
+	vpxor	%xmm8,%xmm0,%xmm0
+	xorl	%edx,%edi
+	xorl	%ebp,%edx
+	addl	%ecx,%ebx
+	addl	4(%rsp),%eax
+	vpsrld	$30,%xmm0,%xmm8
+	vmovdqa	%xmm9,48(%rsp)
+	andl	%edx,%edi
+	xorl	%ebp,%edx
+	shrdl	$7,%ecx,%ecx
+	movl	%ebx,%esi
+	vpslld	$2,%xmm0,%xmm0
+	xorl	%edx,%edi
+	shldl	$5,%ebx,%ebx
+	addl	%edi,%eax
+	xorl	%ecx,%esi
+	xorl	%edx,%ecx
+	addl	%ebx,%eax
+	addl	8(%rsp),%ebp
+	andl	%ecx,%esi
+	vpor	%xmm8,%xmm0,%xmm0
+	xorl	%edx,%ecx
+	shrdl	$7,%ebx,%ebx
+	movl	%eax,%edi
+	xorl	%ecx,%esi
+	shldl	$5,%eax,%eax
+	addl	%esi,%ebp
+	xorl	%ebx,%edi
+	xorl	%ecx,%ebx
+	addl	%eax,%ebp
+	addl	12(%rsp),%edx
+	andl	%ebx,%edi
+	xorl	%ecx,%ebx
+	shrdl	$7,%eax,%eax
+	movl	%ebp,%esi
+	xorl	%ebx,%edi
+	shldl	$5,%ebp,%ebp
+	addl	%edi,%edx
+	xorl	%eax,%esi
+	xorl	%ebx,%eax
+	addl	%ebp,%edx
+	vpalignr	$8,%xmm7,%xmm0,%xmm8
+	vpxor	%xmm5,%xmm1,%xmm1
+	addl	16(%rsp),%ecx
+	andl	%eax,%esi
+	xorl	%ebx,%eax
+	shrdl	$7,%ebp,%ebp
+	vpxor	%xmm2,%xmm1,%xmm1
+	movl	%edx,%edi
+	xorl	%eax,%esi
+	vpaddd	%xmm0,%xmm11,%xmm9
+	shldl	$5,%edx,%edx
+	addl	%esi,%ecx
+	vpxor	%xmm8,%xmm1,%xmm1
+	xorl	%ebp,%edi
+	xorl	%eax,%ebp
+	addl	%edx,%ecx
+	addl	20(%rsp),%ebx
+	vpsrld	$30,%xmm1,%xmm8
+	vmovdqa	%xmm9,0(%rsp)
+	andl	%ebp,%edi
+	xorl	%eax,%ebp
+	shrdl	$7,%edx,%edx
+	movl	%ecx,%esi
+	vpslld	$2,%xmm1,%xmm1
+	xorl	%ebp,%edi
+	shldl	$5,%ecx,%ecx
+	addl	%edi,%ebx
+	xorl	%edx,%esi
+	xorl	%ebp,%edx
+	addl	%ecx,%ebx
+	addl	24(%rsp),%eax
+	andl	%edx,%esi
+	vpor	%xmm8,%xmm1,%xmm1
+	xorl	%ebp,%edx
+	shrdl	$7,%ecx,%ecx
+	movl	%ebx,%edi
+	xorl	%edx,%esi
+	shldl	$5,%ebx,%ebx
+	addl	%esi,%eax
+	xorl	%ecx,%edi
+	xorl	%edx,%ecx
+	addl	%ebx,%eax
+	addl	28(%rsp),%ebp
+	andl	%ecx,%edi
+	xorl	%edx,%ecx
+	shrdl	$7,%ebx,%ebx
+	movl	%eax,%esi
+	xorl	%ecx,%edi
+	shldl	$5,%eax,%eax
+	addl	%edi,%ebp
+	xorl	%ebx,%esi
+	xorl	%ecx,%ebx
+	addl	%eax,%ebp
+	vpalignr	$8,%xmm0,%xmm1,%xmm8
+	vpxor	%xmm6,%xmm2,%xmm2
+	addl	32(%rsp),%edx
+	andl	%ebx,%esi
+	xorl	%ecx,%ebx
+	shrdl	$7,%eax,%eax
+	vpxor	%xmm3,%xmm2,%xmm2
+	movl	%ebp,%edi
+	xorl	%ebx,%esi
+	vpaddd	%xmm1,%xmm11,%xmm9
+	shldl	$5,%ebp,%ebp
+	addl	%esi,%edx
+	vpxor	%xmm8,%xmm2,%xmm2
+	xorl	%eax,%edi
+	xorl	%ebx,%eax
+	addl	%ebp,%edx
+	addl	36(%rsp),%ecx
+	vpsrld	$30,%xmm2,%xmm8
+	vmovdqa	%xmm9,16(%rsp)
+	andl	%eax,%edi
+	xorl	%ebx,%eax
+	shrdl	$7,%ebp,%ebp
+	movl	%edx,%esi
+	vpslld	$2,%xmm2,%xmm2
+	xorl	%eax,%edi
+	shldl	$5,%edx,%edx
+	addl	%edi,%ecx
+	xorl	%ebp,%esi
+	xorl	%eax,%ebp
+	addl	%edx,%ecx
+	addl	40(%rsp),%ebx
+	andl	%ebp,%esi
+	vpor	%xmm8,%xmm2,%xmm2
+	xorl	%eax,%ebp
+	shrdl	$7,%edx,%edx
+	movl	%ecx,%edi
+	xorl	%ebp,%esi
+	shldl	$5,%ecx,%ecx
+	addl	%esi,%ebx
+	xorl	%edx,%edi
+	xorl	%ebp,%edx
+	addl	%ecx,%ebx
+	addl	44(%rsp),%eax
+	andl	%edx,%edi
+	xorl	%ebp,%edx
+	shrdl	$7,%ecx,%ecx
+	movl	%ebx,%esi
+	xorl	%edx,%edi
+	shldl	$5,%ebx,%ebx
+	addl	%edi,%eax
+	xorl	%edx,%esi
+	addl	%ebx,%eax
+	vpalignr	$8,%xmm1,%xmm2,%xmm8
+	vpxor	%xmm7,%xmm3,%xmm3
+	addl	48(%rsp),%ebp
+	xorl	%ecx,%esi
+	movl	%eax,%edi
+	shldl	$5,%eax,%eax
+	vpxor	%xmm4,%xmm3,%xmm3
+	addl	%esi,%ebp
+	xorl	%ecx,%edi
+	vpaddd	%xmm2,%xmm11,%xmm9
+	shrdl	$7,%ebx,%ebx
+	addl	%eax,%ebp
+	vpxor	%xmm8,%xmm3,%xmm3
+	addl	52(%rsp),%edx
+	xorl	%ebx,%edi
+	movl	%ebp,%esi
+	shldl	$5,%ebp,%ebp
+	vpsrld	$30,%xmm3,%xmm8
+	vmovdqa	%xmm9,32(%rsp)
+	addl	%edi,%edx
+	xorl	%ebx,%esi
+	shrdl	$7,%eax,%eax
+	addl	%ebp,%edx
+	vpslld	$2,%xmm3,%xmm3
+	addl	56(%rsp),%ecx
+	xorl	%eax,%esi
+	movl	%edx,%edi
+	shldl	$5,%edx,%edx
+	addl	%esi,%ecx
+	xorl	%eax,%edi
+	shrdl	$7,%ebp,%ebp
+	addl	%edx,%ecx
+	vpor	%xmm8,%xmm3,%xmm3
+	addl	60(%rsp),%ebx
+	xorl	%ebp,%edi
+	movl	%ecx,%esi
+	shldl	$5,%ecx,%ecx
+	addl	%edi,%ebx
+	xorl	%ebp,%esi
+	shrdl	$7,%edx,%edx
+	addl	%ecx,%ebx
+	addl	0(%rsp),%eax
+	vpaddd	%xmm3,%xmm11,%xmm9
+	xorl	%edx,%esi
+	movl	%ebx,%edi
+	shldl	$5,%ebx,%ebx
+	addl	%esi,%eax
+	vmovdqa	%xmm9,48(%rsp)
+	xorl	%edx,%edi
+	shrdl	$7,%ecx,%ecx
+	addl	%ebx,%eax
+	addl	4(%rsp),%ebp
+	xorl	%ecx,%edi
+	movl	%eax,%esi
+	shldl	$5,%eax,%eax
+	addl	%edi,%ebp
+	xorl	%ecx,%esi
+	shrdl	$7,%ebx,%ebx
+	addl	%eax,%ebp
+	addl	8(%rsp),%edx
+	xorl	%ebx,%esi
+	movl	%ebp,%edi
+	shldl	$5,%ebp,%ebp
+	addl	%esi,%edx
+	xorl	%ebx,%edi
+	shrdl	$7,%eax,%eax
+	addl	%ebp,%edx
+	addl	12(%rsp),%ecx
+	xorl	%eax,%edi
+	movl	%edx,%esi
+	shldl	$5,%edx,%edx
+	addl	%edi,%ecx
+	xorl	%eax,%esi
+	shrdl	$7,%ebp,%ebp
+	addl	%edx,%ecx
+	cmpq	%r10,%r9
+	je	.Ldone_avx
+	vmovdqa	64(%r11),%xmm6
+	vmovdqa	-64(%r11),%xmm11
+	vmovdqu	0(%r9),%xmm0
+	vmovdqu	16(%r9),%xmm1
+	vmovdqu	32(%r9),%xmm2
+	vmovdqu	48(%r9),%xmm3
+	vpshufb	%xmm6,%xmm0,%xmm0
+	addq	$64,%r9
+	addl	16(%rsp),%ebx
+	xorl	%ebp,%esi
+	vpshufb	%xmm6,%xmm1,%xmm1
+	movl	%ecx,%edi
+	shldl	$5,%ecx,%ecx
+	vpaddd	%xmm11,%xmm0,%xmm4
+	addl	%esi,%ebx
+	xorl	%ebp,%edi
+	shrdl	$7,%edx,%edx
+	addl	%ecx,%ebx
+	vmovdqa	%xmm4,0(%rsp)
+	addl	20(%rsp),%eax
+	xorl	%edx,%edi
+	movl	%ebx,%esi
+	shldl	$5,%ebx,%ebx
+	addl	%edi,%eax
+	xorl	%edx,%esi
+	shrdl	$7,%ecx,%ecx
+	addl	%ebx,%eax
+	addl	24(%rsp),%ebp
+	xorl	%ecx,%esi
+	movl	%eax,%edi
+	shldl	$5,%eax,%eax
+	addl	%esi,%ebp
+	xorl	%ecx,%edi
+	shrdl	$7,%ebx,%ebx
+	addl	%eax,%ebp
+	addl	28(%rsp),%edx
+	xorl	%ebx,%edi
+	movl	%ebp,%esi
+	shldl	$5,%ebp,%ebp
+	addl	%edi,%edx
+	xorl	%ebx,%esi
+	shrdl	$7,%eax,%eax
+	addl	%ebp,%edx
+	addl	32(%rsp),%ecx
+	xorl	%eax,%esi
+	vpshufb	%xmm6,%xmm2,%xmm2
+	movl	%edx,%edi
+	shldl	$5,%edx,%edx
+	vpaddd	%xmm11,%xmm1,%xmm5
+	addl	%esi,%ecx
+	xorl	%eax,%edi
+	shrdl	$7,%ebp,%ebp
+	addl	%edx,%ecx
+	vmovdqa	%xmm5,16(%rsp)
+	addl	36(%rsp),%ebx
+	xorl	%ebp,%edi
+	movl	%ecx,%esi
+	shldl	$5,%ecx,%ecx
+	addl	%edi,%ebx
+	xorl	%ebp,%esi
+	shrdl	$7,%edx,%edx
+	addl	%ecx,%ebx
+	addl	40(%rsp),%eax
+	xorl	%edx,%esi
+	movl	%ebx,%edi
+	shldl	$5,%ebx,%ebx
+	addl	%esi,%eax
+	xorl	%edx,%edi
+	shrdl	$7,%ecx,%ecx
+	addl	%ebx,%eax
+	addl	44(%rsp),%ebp
+	xorl	%ecx,%edi
+	movl	%eax,%esi
+	shldl	$5,%eax,%eax
+	addl	%edi,%ebp
+	xorl	%ecx,%esi
+	shrdl	$7,%ebx,%ebx
+	addl	%eax,%ebp
+	addl	48(%rsp),%edx
+	xorl	%ebx,%esi
+	vpshufb	%xmm6,%xmm3,%xmm3
+	movl	%ebp,%edi
+	shldl	$5,%ebp,%ebp
+	vpaddd	%xmm11,%xmm2,%xmm6
+	addl	%esi,%edx
+	xorl	%ebx,%edi
+	shrdl	$7,%eax,%eax
+	addl	%ebp,%edx
+	vmovdqa	%xmm6,32(%rsp)
+	addl	52(%rsp),%ecx
+	xorl	%eax,%edi
+	movl	%edx,%esi
+	shldl	$5,%edx,%edx
+	addl	%edi,%ecx
+	xorl	%eax,%esi
+	shrdl	$7,%ebp,%ebp
+	addl	%edx,%ecx
+	addl	56(%rsp),%ebx
+	xorl	%ebp,%esi
+	movl	%ecx,%edi
+	shldl	$5,%ecx,%ecx
+	addl	%esi,%ebx
+	xorl	%ebp,%edi
+	shrdl	$7,%edx,%edx
+	addl	%ecx,%ebx
+	addl	60(%rsp),%eax
+	xorl	%edx,%edi
+	movl	%ebx,%esi
+	shldl	$5,%ebx,%ebx
+	addl	%edi,%eax
+	shrdl	$7,%ecx,%ecx
+	addl	%ebx,%eax
+	addl	0(%r8),%eax
+	addl	4(%r8),%esi
+	addl	8(%r8),%ecx
+	addl	12(%r8),%edx
+	movl	%eax,0(%r8)
+	addl	16(%r8),%ebp
+	movl	%esi,4(%r8)
+	movl	%esi,%ebx
+	movl	%ecx,8(%r8)
+	movl	%ecx,%edi
+	movl	%edx,12(%r8)
+	xorl	%edx,%edi
+	movl	%ebp,16(%r8)
+	andl	%edi,%esi
+	jmp	.Loop_avx
+
+.align	16
+.Ldone_avx:
+	addl	16(%rsp),%ebx
+	xorl	%ebp,%esi
+	movl	%ecx,%edi
+	shldl	$5,%ecx,%ecx
+	addl	%esi,%ebx
+	xorl	%ebp,%edi
+	shrdl	$7,%edx,%edx
+	addl	%ecx,%ebx
+	addl	20(%rsp),%eax
+	xorl	%edx,%edi
+	movl	%ebx,%esi
+	shldl	$5,%ebx,%ebx
+	addl	%edi,%eax
+	xorl	%edx,%esi
+	shrdl	$7,%ecx,%ecx
+	addl	%ebx,%eax
+	addl	24(%rsp),%ebp
+	xorl	%ecx,%esi
+	movl	%eax,%edi
+	shldl	$5,%eax,%eax
+	addl	%esi,%ebp
+	xorl	%ecx,%edi
+	shrdl	$7,%ebx,%ebx
+	addl	%eax,%ebp
+	addl	28(%rsp),%edx
+	xorl	%ebx,%edi
+	movl	%ebp,%esi
+	shldl	$5,%ebp,%ebp
+	addl	%edi,%edx
+	xorl	%ebx,%esi
+	shrdl	$7,%eax,%eax
+	addl	%ebp,%edx
+	addl	32(%rsp),%ecx
+	xorl	%eax,%esi
+	movl	%edx,%edi
+	shldl	$5,%edx,%edx
+	addl	%esi,%ecx
+	xorl	%eax,%edi
+	shrdl	$7,%ebp,%ebp
+	addl	%edx,%ecx
+	addl	36(%rsp),%ebx
+	xorl	%ebp,%edi
+	movl	%ecx,%esi
+	shldl	$5,%ecx,%ecx
+	addl	%edi,%ebx
+	xorl	%ebp,%esi
+	shrdl	$7,%edx,%edx
+	addl	%ecx,%ebx
+	addl	40(%rsp),%eax
+	xorl	%edx,%esi
+	movl	%ebx,%edi
+	shldl	$5,%ebx,%ebx
+	addl	%esi,%eax
+	xorl	%edx,%edi
+	shrdl	$7,%ecx,%ecx
+	addl	%ebx,%eax
+	addl	44(%rsp),%ebp
+	xorl	%ecx,%edi
+	movl	%eax,%esi
+	shldl	$5,%eax,%eax
+	addl	%edi,%ebp
+	xorl	%ecx,%esi
+	shrdl	$7,%ebx,%ebx
+	addl	%eax,%ebp
+	addl	48(%rsp),%edx
+	xorl	%ebx,%esi
+	movl	%ebp,%edi
+	shldl	$5,%ebp,%ebp
+	addl	%esi,%edx
+	xorl	%ebx,%edi
+	shrdl	$7,%eax,%eax
+	addl	%ebp,%edx
+	addl	52(%rsp),%ecx
+	xorl	%eax,%edi
+	movl	%edx,%esi
+	shldl	$5,%edx,%edx
+	addl	%edi,%ecx
+	xorl	%eax,%esi
+	shrdl	$7,%ebp,%ebp
+	addl	%edx,%ecx
+	addl	56(%rsp),%ebx
+	xorl	%ebp,%esi
+	movl	%ecx,%edi
+	shldl	$5,%ecx,%ecx
+	addl	%esi,%ebx
+	xorl	%ebp,%edi
+	shrdl	$7,%edx,%edx
+	addl	%ecx,%ebx
+	addl	60(%rsp),%eax
+	xorl	%edx,%edi
+	movl	%ebx,%esi
+	shldl	$5,%ebx,%ebx
+	addl	%edi,%eax
+	shrdl	$7,%ecx,%ecx
+	addl	%ebx,%eax
+	vzeroupper
+
+	addl	0(%r8),%eax
+	addl	4(%r8),%esi
+	addl	8(%r8),%ecx
+	movl	%eax,0(%r8)
+	addl	12(%r8),%edx
+	movl	%esi,4(%r8)
+	addl	16(%r8),%ebp
+	movl	%ecx,8(%r8)
+	movl	%edx,12(%r8)
+	movl	%ebp,16(%r8)
+	leaq	(%r14),%rsi
+	movq	-40(%rsi),%r14
+	movq	-32(%rsi),%r13
+	movq	-24(%rsi),%r12
+	movq	-16(%rsi),%rbp
+	movq	-8(%rsi),%rbx
+	leaq	(%rsi),%rsp
+.Lepilogue_avx:
+	.byte	0xf3,0xc3
+.size	sha1_block_data_order_avx,.-sha1_block_data_order_avx
 .align	64
 K_XX_XX:
 .long	0x5a827999,0x5a827999,0x5a827999,0x5a827999
diff --git a/packager/third_party/boringssl/linux-x86_64/crypto/sha/sha256-x86_64.S b/packager/third_party/boringssl/linux-x86_64/crypto/sha/sha256-x86_64.S
index f526de51ad..445b497e88 100644
--- a/packager/third_party/boringssl/linux-x86_64/crypto/sha/sha256-x86_64.S
+++ b/packager/third_party/boringssl/linux-x86_64/crypto/sha/sha256-x86_64.S
@@ -12,6 +12,11 @@ sha256_block_data_order:
 	movl	0(%r11),%r9d
 	movl	4(%r11),%r10d
 	movl	8(%r11),%r11d
+	andl	$1073741824,%r9d
+	andl	$268435968,%r10d
+	orl	%r9d,%r10d
+	cmpl	$1342177792,%r10d
+	je	.Lavx_shortcut
 	testl	$512,%r10d
 	jnz	.Lssse3_shortcut
 	pushq	%rbx
@@ -2841,4 +2846,1061 @@ sha256_block_data_order_ssse3:
 .Lepilogue_ssse3:
 	.byte	0xf3,0xc3
 .size	sha256_block_data_order_ssse3,.-sha256_block_data_order_ssse3
+.type	sha256_block_data_order_avx,@function
+.align	64
+sha256_block_data_order_avx:
+.Lavx_shortcut:
+	pushq	%rbx
+	pushq	%rbp
+	pushq	%r12
+	pushq	%r13
+	pushq	%r14
+	pushq	%r15
+	movq	%rsp,%r11
+	shlq	$4,%rdx
+	subq	$96,%rsp
+	leaq	(%rsi,%rdx,4),%rdx
+	andq	$-64,%rsp
+	movq	%rdi,64+0(%rsp)
+	movq	%rsi,64+8(%rsp)
+	movq	%rdx,64+16(%rsp)
+	movq	%r11,64+24(%rsp)
+.Lprologue_avx:
+
+	vzeroupper
+	movl	0(%rdi),%eax
+	movl	4(%rdi),%ebx
+	movl	8(%rdi),%ecx
+	movl	12(%rdi),%edx
+	movl	16(%rdi),%r8d
+	movl	20(%rdi),%r9d
+	movl	24(%rdi),%r10d
+	movl	28(%rdi),%r11d
+	vmovdqa	K256+512+32(%rip),%xmm8
+	vmovdqa	K256+512+64(%rip),%xmm9
+	jmp	.Lloop_avx
+.align	16
+.Lloop_avx:
+	vmovdqa	K256+512(%rip),%xmm7
+	vmovdqu	0(%rsi),%xmm0
+	vmovdqu	16(%rsi),%xmm1
+	vmovdqu	32(%rsi),%xmm2
+	vmovdqu	48(%rsi),%xmm3
+	vpshufb	%xmm7,%xmm0,%xmm0
+	leaq	K256(%rip),%rbp
+	vpshufb	%xmm7,%xmm1,%xmm1
+	vpshufb	%xmm7,%xmm2,%xmm2
+	vpaddd	0(%rbp),%xmm0,%xmm4
+	vpshufb	%xmm7,%xmm3,%xmm3
+	vpaddd	32(%rbp),%xmm1,%xmm5
+	vpaddd	64(%rbp),%xmm2,%xmm6
+	vpaddd	96(%rbp),%xmm3,%xmm7
+	vmovdqa	%xmm4,0(%rsp)
+	movl	%eax,%r14d
+	vmovdqa	%xmm5,16(%rsp)
+	movl	%ebx,%edi
+	vmovdqa	%xmm6,32(%rsp)
+	xorl	%ecx,%edi
+	vmovdqa	%xmm7,48(%rsp)
+	movl	%r8d,%r13d
+	jmp	.Lavx_00_47
+
+.align	16
+.Lavx_00_47:
+	subq	$-128,%rbp
+	vpalignr	$4,%xmm0,%xmm1,%xmm4
+	shrdl	$14,%r13d,%r13d
+	movl	%r14d,%eax
+	movl	%r9d,%r12d
+	vpalignr	$4,%xmm2,%xmm3,%xmm7
+	shrdl	$9,%r14d,%r14d
+	xorl	%r8d,%r13d
+	xorl	%r10d,%r12d
+	vpsrld	$7,%xmm4,%xmm6
+	shrdl	$5,%r13d,%r13d
+	xorl	%eax,%r14d
+	andl	%r8d,%r12d
+	vpaddd	%xmm7,%xmm0,%xmm0
+	xorl	%r8d,%r13d
+	addl	0(%rsp),%r11d
+	movl	%eax,%r15d
+	vpsrld	$3,%xmm4,%xmm7
+	xorl	%r10d,%r12d
+	shrdl	$11,%r14d,%r14d
+	xorl	%ebx,%r15d
+	vpslld	$14,%xmm4,%xmm5
+	addl	%r12d,%r11d
+	shrdl	$6,%r13d,%r13d
+	andl	%r15d,%edi
+	vpxor	%xmm6,%xmm7,%xmm4
+	xorl	%eax,%r14d
+	addl	%r13d,%r11d
+	xorl	%ebx,%edi
+	vpshufd	$250,%xmm3,%xmm7
+	shrdl	$2,%r14d,%r14d
+	addl	%r11d,%edx
+	addl	%edi,%r11d
+	vpsrld	$11,%xmm6,%xmm6
+	movl	%edx,%r13d
+	addl	%r11d,%r14d
+	shrdl	$14,%r13d,%r13d
+	vpxor	%xmm5,%xmm4,%xmm4
+	movl	%r14d,%r11d
+	movl	%r8d,%r12d
+	shrdl	$9,%r14d,%r14d
+	vpslld	$11,%xmm5,%xmm5
+	xorl	%edx,%r13d
+	xorl	%r9d,%r12d
+	shrdl	$5,%r13d,%r13d
+	vpxor	%xmm6,%xmm4,%xmm4
+	xorl	%r11d,%r14d
+	andl	%edx,%r12d
+	xorl	%edx,%r13d
+	vpsrld	$10,%xmm7,%xmm6
+	addl	4(%rsp),%r10d
+	movl	%r11d,%edi
+	xorl	%r9d,%r12d
+	vpxor	%xmm5,%xmm4,%xmm4
+	shrdl	$11,%r14d,%r14d
+	xorl	%eax,%edi
+	addl	%r12d,%r10d
+	vpsrlq	$17,%xmm7,%xmm7
+	shrdl	$6,%r13d,%r13d
+	andl	%edi,%r15d
+	xorl	%r11d,%r14d
+	vpaddd	%xmm4,%xmm0,%xmm0
+	addl	%r13d,%r10d
+	xorl	%eax,%r15d
+	shrdl	$2,%r14d,%r14d
+	vpxor	%xmm7,%xmm6,%xmm6
+	addl	%r10d,%ecx
+	addl	%r15d,%r10d
+	movl	%ecx,%r13d
+	vpsrlq	$2,%xmm7,%xmm7
+	addl	%r10d,%r14d
+	shrdl	$14,%r13d,%r13d
+	movl	%r14d,%r10d
+	vpxor	%xmm7,%xmm6,%xmm6
+	movl	%edx,%r12d
+	shrdl	$9,%r14d,%r14d
+	xorl	%ecx,%r13d
+	vpshufb	%xmm8,%xmm6,%xmm6
+	xorl	%r8d,%r12d
+	shrdl	$5,%r13d,%r13d
+	xorl	%r10d,%r14d
+	vpaddd	%xmm6,%xmm0,%xmm0
+	andl	%ecx,%r12d
+	xorl	%ecx,%r13d
+	addl	8(%rsp),%r9d
+	vpshufd	$80,%xmm0,%xmm7
+	movl	%r10d,%r15d
+	xorl	%r8d,%r12d
+	shrdl	$11,%r14d,%r14d
+	vpsrld	$10,%xmm7,%xmm6
+	xorl	%r11d,%r15d
+	addl	%r12d,%r9d
+	shrdl	$6,%r13d,%r13d
+	vpsrlq	$17,%xmm7,%xmm7
+	andl	%r15d,%edi
+	xorl	%r10d,%r14d
+	addl	%r13d,%r9d
+	vpxor	%xmm7,%xmm6,%xmm6
+	xorl	%r11d,%edi
+	shrdl	$2,%r14d,%r14d
+	addl	%r9d,%ebx
+	vpsrlq	$2,%xmm7,%xmm7
+	addl	%edi,%r9d
+	movl	%ebx,%r13d
+	addl	%r9d,%r14d
+	vpxor	%xmm7,%xmm6,%xmm6
+	shrdl	$14,%r13d,%r13d
+	movl	%r14d,%r9d
+	movl	%ecx,%r12d
+	vpshufb	%xmm9,%xmm6,%xmm6
+	shrdl	$9,%r14d,%r14d
+	xorl	%ebx,%r13d
+	xorl	%edx,%r12d
+	vpaddd	%xmm6,%xmm0,%xmm0
+	shrdl	$5,%r13d,%r13d
+	xorl	%r9d,%r14d
+	andl	%ebx,%r12d
+	vpaddd	0(%rbp),%xmm0,%xmm6
+	xorl	%ebx,%r13d
+	addl	12(%rsp),%r8d
+	movl	%r9d,%edi
+	xorl	%edx,%r12d
+	shrdl	$11,%r14d,%r14d
+	xorl	%r10d,%edi
+	addl	%r12d,%r8d
+	shrdl	$6,%r13d,%r13d
+	andl	%edi,%r15d
+	xorl	%r9d,%r14d
+	addl	%r13d,%r8d
+	xorl	%r10d,%r15d
+	shrdl	$2,%r14d,%r14d
+	addl	%r8d,%eax
+	addl	%r15d,%r8d
+	movl	%eax,%r13d
+	addl	%r8d,%r14d
+	vmovdqa	%xmm6,0(%rsp)
+	vpalignr	$4,%xmm1,%xmm2,%xmm4
+	shrdl	$14,%r13d,%r13d
+	movl	%r14d,%r8d
+	movl	%ebx,%r12d
+	vpalignr	$4,%xmm3,%xmm0,%xmm7
+	shrdl	$9,%r14d,%r14d
+	xorl	%eax,%r13d
+	xorl	%ecx,%r12d
+	vpsrld	$7,%xmm4,%xmm6
+	shrdl	$5,%r13d,%r13d
+	xorl	%r8d,%r14d
+	andl	%eax,%r12d
+	vpaddd	%xmm7,%xmm1,%xmm1
+	xorl	%eax,%r13d
+	addl	16(%rsp),%edx
+	movl	%r8d,%r15d
+	vpsrld	$3,%xmm4,%xmm7
+	xorl	%ecx,%r12d
+	shrdl	$11,%r14d,%r14d
+	xorl	%r9d,%r15d
+	vpslld	$14,%xmm4,%xmm5
+	addl	%r12d,%edx
+	shrdl	$6,%r13d,%r13d
+	andl	%r15d,%edi
+	vpxor	%xmm6,%xmm7,%xmm4
+	xorl	%r8d,%r14d
+	addl	%r13d,%edx
+	xorl	%r9d,%edi
+	vpshufd	$250,%xmm0,%xmm7
+	shrdl	$2,%r14d,%r14d
+	addl	%edx,%r11d
+	addl	%edi,%edx
+	vpsrld	$11,%xmm6,%xmm6
+	movl	%r11d,%r13d
+	addl	%edx,%r14d
+	shrdl	$14,%r13d,%r13d
+	vpxor	%xmm5,%xmm4,%xmm4
+	movl	%r14d,%edx
+	movl	%eax,%r12d
+	shrdl	$9,%r14d,%r14d
+	vpslld	$11,%xmm5,%xmm5
+	xorl	%r11d,%r13d
+	xorl	%ebx,%r12d
+	shrdl	$5,%r13d,%r13d
+	vpxor	%xmm6,%xmm4,%xmm4
+	xorl	%edx,%r14d
+	andl	%r11d,%r12d
+	xorl	%r11d,%r13d
+	vpsrld	$10,%xmm7,%xmm6
+	addl	20(%rsp),%ecx
+	movl	%edx,%edi
+	xorl	%ebx,%r12d
+	vpxor	%xmm5,%xmm4,%xmm4
+	shrdl	$11,%r14d,%r14d
+	xorl	%r8d,%edi
+	addl	%r12d,%ecx
+	vpsrlq	$17,%xmm7,%xmm7
+	shrdl	$6,%r13d,%r13d
+	andl	%edi,%r15d
+	xorl	%edx,%r14d
+	vpaddd	%xmm4,%xmm1,%xmm1
+	addl	%r13d,%ecx
+	xorl	%r8d,%r15d
+	shrdl	$2,%r14d,%r14d
+	vpxor	%xmm7,%xmm6,%xmm6
+	addl	%ecx,%r10d
+	addl	%r15d,%ecx
+	movl	%r10d,%r13d
+	vpsrlq	$2,%xmm7,%xmm7
+	addl	%ecx,%r14d
+	shrdl	$14,%r13d,%r13d
+	movl	%r14d,%ecx
+	vpxor	%xmm7,%xmm6,%xmm6
+	movl	%r11d,%r12d
+	shrdl	$9,%r14d,%r14d
+	xorl	%r10d,%r13d
+	vpshufb	%xmm8,%xmm6,%xmm6
+	xorl	%eax,%r12d
+	shrdl	$5,%r13d,%r13d
+	xorl	%ecx,%r14d
+	vpaddd	%xmm6,%xmm1,%xmm1
+	andl	%r10d,%r12d
+	xorl	%r10d,%r13d
+	addl	24(%rsp),%ebx
+	vpshufd	$80,%xmm1,%xmm7
+	movl	%ecx,%r15d
+	xorl	%eax,%r12d
+	shrdl	$11,%r14d,%r14d
+	vpsrld	$10,%xmm7,%xmm6
+	xorl	%edx,%r15d
+	addl	%r12d,%ebx
+	shrdl	$6,%r13d,%r13d
+	vpsrlq	$17,%xmm7,%xmm7
+	andl	%r15d,%edi
+	xorl	%ecx,%r14d
+	addl	%r13d,%ebx
+	vpxor	%xmm7,%xmm6,%xmm6
+	xorl	%edx,%edi
+	shrdl	$2,%r14d,%r14d
+	addl	%ebx,%r9d
+	vpsrlq	$2,%xmm7,%xmm7
+	addl	%edi,%ebx
+	movl	%r9d,%r13d
+	addl	%ebx,%r14d
+	vpxor	%xmm7,%xmm6,%xmm6
+	shrdl	$14,%r13d,%r13d
+	movl	%r14d,%ebx
+	movl	%r10d,%r12d
+	vpshufb	%xmm9,%xmm6,%xmm6
+	shrdl	$9,%r14d,%r14d
+	xorl	%r9d,%r13d
+	xorl	%r11d,%r12d
+	vpaddd	%xmm6,%xmm1,%xmm1
+	shrdl	$5,%r13d,%r13d
+	xorl	%ebx,%r14d
+	andl	%r9d,%r12d
+	vpaddd	32(%rbp),%xmm1,%xmm6
+	xorl	%r9d,%r13d
+	addl	28(%rsp),%eax
+	movl	%ebx,%edi
+	xorl	%r11d,%r12d
+	shrdl	$11,%r14d,%r14d
+	xorl	%ecx,%edi
+	addl	%r12d,%eax
+	shrdl	$6,%r13d,%r13d
+	andl	%edi,%r15d
+	xorl	%ebx,%r14d
+	addl	%r13d,%eax
+	xorl	%ecx,%r15d
+	shrdl	$2,%r14d,%r14d
+	addl	%eax,%r8d
+	addl	%r15d,%eax
+	movl	%r8d,%r13d
+	addl	%eax,%r14d
+	vmovdqa	%xmm6,16(%rsp)
+	vpalignr	$4,%xmm2,%xmm3,%xmm4
+	shrdl	$14,%r13d,%r13d
+	movl	%r14d,%eax
+	movl	%r9d,%r12d
+	vpalignr	$4,%xmm0,%xmm1,%xmm7
+	shrdl	$9,%r14d,%r14d
+	xorl	%r8d,%r13d
+	xorl	%r10d,%r12d
+	vpsrld	$7,%xmm4,%xmm6
+	shrdl	$5,%r13d,%r13d
+	xorl	%eax,%r14d
+	andl	%r8d,%r12d
+	vpaddd	%xmm7,%xmm2,%xmm2
+	xorl	%r8d,%r13d
+	addl	32(%rsp),%r11d
+	movl	%eax,%r15d
+	vpsrld	$3,%xmm4,%xmm7
+	xorl	%r10d,%r12d
+	shrdl	$11,%r14d,%r14d
+	xorl	%ebx,%r15d
+	vpslld	$14,%xmm4,%xmm5
+	addl	%r12d,%r11d
+	shrdl	$6,%r13d,%r13d
+	andl	%r15d,%edi
+	vpxor	%xmm6,%xmm7,%xmm4
+	xorl	%eax,%r14d
+	addl	%r13d,%r11d
+	xorl	%ebx,%edi
+	vpshufd	$250,%xmm1,%xmm7
+	shrdl	$2,%r14d,%r14d
+	addl	%r11d,%edx
+	addl	%edi,%r11d
+	vpsrld	$11,%xmm6,%xmm6
+	movl	%edx,%r13d
+	addl	%r11d,%r14d
+	shrdl	$14,%r13d,%r13d
+	vpxor	%xmm5,%xmm4,%xmm4
+	movl	%r14d,%r11d
+	movl	%r8d,%r12d
+	shrdl	$9,%r14d,%r14d
+	vpslld	$11,%xmm5,%xmm5
+	xorl	%edx,%r13d
+	xorl	%r9d,%r12d
+	shrdl	$5,%r13d,%r13d
+	vpxor	%xmm6,%xmm4,%xmm4
+	xorl	%r11d,%r14d
+	andl	%edx,%r12d
+	xorl	%edx,%r13d
+	vpsrld	$10,%xmm7,%xmm6
+	addl	36(%rsp),%r10d
+	movl	%r11d,%edi
+	xorl	%r9d,%r12d
+	vpxor	%xmm5,%xmm4,%xmm4
+	shrdl	$11,%r14d,%r14d
+	xorl	%eax,%edi
+	addl	%r12d,%r10d
+	vpsrlq	$17,%xmm7,%xmm7
+	shrdl	$6,%r13d,%r13d
+	andl	%edi,%r15d
+	xorl	%r11d,%r14d
+	vpaddd	%xmm4,%xmm2,%xmm2
+	addl	%r13d,%r10d
+	xorl	%eax,%r15d
+	shrdl	$2,%r14d,%r14d
+	vpxor	%xmm7,%xmm6,%xmm6
+	addl	%r10d,%ecx
+	addl	%r15d,%r10d
+	movl	%ecx,%r13d
+	vpsrlq	$2,%xmm7,%xmm7
+	addl	%r10d,%r14d
+	shrdl	$14,%r13d,%r13d
+	movl	%r14d,%r10d
+	vpxor	%xmm7,%xmm6,%xmm6
+	movl	%edx,%r12d
+	shrdl	$9,%r14d,%r14d
+	xorl	%ecx,%r13d
+	vpshufb	%xmm8,%xmm6,%xmm6
+	xorl	%r8d,%r12d
+	shrdl	$5,%r13d,%r13d
+	xorl	%r10d,%r14d
+	vpaddd	%xmm6,%xmm2,%xmm2
+	andl	%ecx,%r12d
+	xorl	%ecx,%r13d
+	addl	40(%rsp),%r9d
+	vpshufd	$80,%xmm2,%xmm7
+	movl	%r10d,%r15d
+	xorl	%r8d,%r12d
+	shrdl	$11,%r14d,%r14d
+	vpsrld	$10,%xmm7,%xmm6
+	xorl	%r11d,%r15d
+	addl	%r12d,%r9d
+	shrdl	$6,%r13d,%r13d
+	vpsrlq	$17,%xmm7,%xmm7
+	andl	%r15d,%edi
+	xorl	%r10d,%r14d
+	addl	%r13d,%r9d
+	vpxor	%xmm7,%xmm6,%xmm6
+	xorl	%r11d,%edi
+	shrdl	$2,%r14d,%r14d
+	addl	%r9d,%ebx
+	vpsrlq	$2,%xmm7,%xmm7
+	addl	%edi,%r9d
+	movl	%ebx,%r13d
+	addl	%r9d,%r14d
+	vpxor	%xmm7,%xmm6,%xmm6
+	shrdl	$14,%r13d,%r13d
+	movl	%r14d,%r9d
+	movl	%ecx,%r12d
+	vpshufb	%xmm9,%xmm6,%xmm6
+	shrdl	$9,%r14d,%r14d
+	xorl	%ebx,%r13d
+	xorl	%edx,%r12d
+	vpaddd	%xmm6,%xmm2,%xmm2
+	shrdl	$5,%r13d,%r13d
+	xorl	%r9d,%r14d
+	andl	%ebx,%r12d
+	vpaddd	64(%rbp),%xmm2,%xmm6
+	xorl	%ebx,%r13d
+	addl	44(%rsp),%r8d
+	movl	%r9d,%edi
+	xorl	%edx,%r12d
+	shrdl	$11,%r14d,%r14d
+	xorl	%r10d,%edi
+	addl	%r12d,%r8d
+	shrdl	$6,%r13d,%r13d
+	andl	%edi,%r15d
+	xorl	%r9d,%r14d
+	addl	%r13d,%r8d
+	xorl	%r10d,%r15d
+	shrdl	$2,%r14d,%r14d
+	addl	%r8d,%eax
+	addl	%r15d,%r8d
+	movl	%eax,%r13d
+	addl	%r8d,%r14d
+	vmovdqa	%xmm6,32(%rsp)
+	vpalignr	$4,%xmm3,%xmm0,%xmm4
+	shrdl	$14,%r13d,%r13d
+	movl	%r14d,%r8d
+	movl	%ebx,%r12d
+	vpalignr	$4,%xmm1,%xmm2,%xmm7
+	shrdl	$9,%r14d,%r14d
+	xorl	%eax,%r13d
+	xorl	%ecx,%r12d
+	vpsrld	$7,%xmm4,%xmm6
+	shrdl	$5,%r13d,%r13d
+	xorl	%r8d,%r14d
+	andl	%eax,%r12d
+	vpaddd	%xmm7,%xmm3,%xmm3
+	xorl	%eax,%r13d
+	addl	48(%rsp),%edx
+	movl	%r8d,%r15d
+	vpsrld	$3,%xmm4,%xmm7
+	xorl	%ecx,%r12d
+	shrdl	$11,%r14d,%r14d
+	xorl	%r9d,%r15d
+	vpslld	$14,%xmm4,%xmm5
+	addl	%r12d,%edx
+	shrdl	$6,%r13d,%r13d
+	andl	%r15d,%edi
+	vpxor	%xmm6,%xmm7,%xmm4
+	xorl	%r8d,%r14d
+	addl	%r13d,%edx
+	xorl	%r9d,%edi
+	vpshufd	$250,%xmm2,%xmm7
+	shrdl	$2,%r14d,%r14d
+	addl	%edx,%r11d
+	addl	%edi,%edx
+	vpsrld	$11,%xmm6,%xmm6
+	movl	%r11d,%r13d
+	addl	%edx,%r14d
+	shrdl	$14,%r13d,%r13d
+	vpxor	%xmm5,%xmm4,%xmm4
+	movl	%r14d,%edx
+	movl	%eax,%r12d
+	shrdl	$9,%r14d,%r14d
+	vpslld	$11,%xmm5,%xmm5
+	xorl	%r11d,%r13d
+	xorl	%ebx,%r12d
+	shrdl	$5,%r13d,%r13d
+	vpxor	%xmm6,%xmm4,%xmm4
+	xorl	%edx,%r14d
+	andl	%r11d,%r12d
+	xorl	%r11d,%r13d
+	vpsrld	$10,%xmm7,%xmm6
+	addl	52(%rsp),%ecx
+	movl	%edx,%edi
+	xorl	%ebx,%r12d
+	vpxor	%xmm5,%xmm4,%xmm4
+	shrdl	$11,%r14d,%r14d
+	xorl	%r8d,%edi
+	addl	%r12d,%ecx
+	vpsrlq	$17,%xmm7,%xmm7
+	shrdl	$6,%r13d,%r13d
+	andl	%edi,%r15d
+	xorl	%edx,%r14d
+	vpaddd	%xmm4,%xmm3,%xmm3
+	addl	%r13d,%ecx
+	xorl	%r8d,%r15d
+	shrdl	$2,%r14d,%r14d
+	vpxor	%xmm7,%xmm6,%xmm6
+	addl	%ecx,%r10d
+	addl	%r15d,%ecx
+	movl	%r10d,%r13d
+	vpsrlq	$2,%xmm7,%xmm7
+	addl	%ecx,%r14d
+	shrdl	$14,%r13d,%r13d
+	movl	%r14d,%ecx
+	vpxor	%xmm7,%xmm6,%xmm6
+	movl	%r11d,%r12d
+	shrdl	$9,%r14d,%r14d
+	xorl	%r10d,%r13d
+	vpshufb	%xmm8,%xmm6,%xmm6
+	xorl	%eax,%r12d
+	shrdl	$5,%r13d,%r13d
+	xorl	%ecx,%r14d
+	vpaddd	%xmm6,%xmm3,%xmm3
+	andl	%r10d,%r12d
+	xorl	%r10d,%r13d
+	addl	56(%rsp),%ebx
+	vpshufd	$80,%xmm3,%xmm7
+	movl	%ecx,%r15d
+	xorl	%eax,%r12d
+	shrdl	$11,%r14d,%r14d
+	vpsrld	$10,%xmm7,%xmm6
+	xorl	%edx,%r15d
+	addl	%r12d,%ebx
+	shrdl	$6,%r13d,%r13d
+	vpsrlq	$17,%xmm7,%xmm7
+	andl	%r15d,%edi
+	xorl	%ecx,%r14d
+	addl	%r13d,%ebx
+	vpxor	%xmm7,%xmm6,%xmm6
+	xorl	%edx,%edi
+	shrdl	$2,%r14d,%r14d
+	addl	%ebx,%r9d
+	vpsrlq	$2,%xmm7,%xmm7
+	addl	%edi,%ebx
+	movl	%r9d,%r13d
+	addl	%ebx,%r14d
+	vpxor	%xmm7,%xmm6,%xmm6
+	shrdl	$14,%r13d,%r13d
+	movl	%r14d,%ebx
+	movl	%r10d,%r12d
+	vpshufb	%xmm9,%xmm6,%xmm6
+	shrdl	$9,%r14d,%r14d
+	xorl	%r9d,%r13d
+	xorl	%r11d,%r12d
+	vpaddd	%xmm6,%xmm3,%xmm3
+	shrdl	$5,%r13d,%r13d
+	xorl	%ebx,%r14d
+	andl	%r9d,%r12d
+	vpaddd	96(%rbp),%xmm3,%xmm6
+	xorl	%r9d,%r13d
+	addl	60(%rsp),%eax
+	movl	%ebx,%edi
+	xorl	%r11d,%r12d
+	shrdl	$11,%r14d,%r14d
+	xorl	%ecx,%edi
+	addl	%r12d,%eax
+	shrdl	$6,%r13d,%r13d
+	andl	%edi,%r15d
+	xorl	%ebx,%r14d
+	addl	%r13d,%eax
+	xorl	%ecx,%r15d
+	shrdl	$2,%r14d,%r14d
+	addl	%eax,%r8d
+	addl	%r15d,%eax
+	movl	%r8d,%r13d
+	addl	%eax,%r14d
+	vmovdqa	%xmm6,48(%rsp)
+	cmpb	$0,131(%rbp)
+	jne	.Lavx_00_47
+	shrdl	$14,%r13d,%r13d
+	movl	%r14d,%eax
+	movl	%r9d,%r12d
+	shrdl	$9,%r14d,%r14d
+	xorl	%r8d,%r13d
+	xorl	%r10d,%r12d
+	shrdl	$5,%r13d,%r13d
+	xorl	%eax,%r14d
+	andl	%r8d,%r12d
+	xorl	%r8d,%r13d
+	addl	0(%rsp),%r11d
+	movl	%eax,%r15d
+	xorl	%r10d,%r12d
+	shrdl	$11,%r14d,%r14d
+	xorl	%ebx,%r15d
+	addl	%r12d,%r11d
+	shrdl	$6,%r13d,%r13d
+	andl	%r15d,%edi
+	xorl	%eax,%r14d
+	addl	%r13d,%r11d
+	xorl	%ebx,%edi
+	shrdl	$2,%r14d,%r14d
+	addl	%r11d,%edx
+	addl	%edi,%r11d
+	movl	%edx,%r13d
+	addl	%r11d,%r14d
+	shrdl	$14,%r13d,%r13d
+	movl	%r14d,%r11d
+	movl	%r8d,%r12d
+	shrdl	$9,%r14d,%r14d
+	xorl	%edx,%r13d
+	xorl	%r9d,%r12d
+	shrdl	$5,%r13d,%r13d
+	xorl	%r11d,%r14d
+	andl	%edx,%r12d
+	xorl	%edx,%r13d
+	addl	4(%rsp),%r10d
+	movl	%r11d,%edi
+	xorl	%r9d,%r12d
+	shrdl	$11,%r14d,%r14d
+	xorl	%eax,%edi
+	addl	%r12d,%r10d
+	shrdl	$6,%r13d,%r13d
+	andl	%edi,%r15d
+	xorl	%r11d,%r14d
+	addl	%r13d,%r10d
+	xorl	%eax,%r15d
+	shrdl	$2,%r14d,%r14d
+	addl	%r10d,%ecx
+	addl	%r15d,%r10d
+	movl	%ecx,%r13d
+	addl	%r10d,%r14d
+	shrdl	$14,%r13d,%r13d
+	movl	%r14d,%r10d
+	movl	%edx,%r12d
+	shrdl	$9,%r14d,%r14d
+	xorl	%ecx,%r13d
+	xorl	%r8d,%r12d
+	shrdl	$5,%r13d,%r13d
+	xorl	%r10d,%r14d
+	andl	%ecx,%r12d
+	xorl	%ecx,%r13d
+	addl	8(%rsp),%r9d
+	movl	%r10d,%r15d
+	xorl	%r8d,%r12d
+	shrdl	$11,%r14d,%r14d
+	xorl	%r11d,%r15d
+	addl	%r12d,%r9d
+	shrdl	$6,%r13d,%r13d
+	andl	%r15d,%edi
+	xorl	%r10d,%r14d
+	addl	%r13d,%r9d
+	xorl	%r11d,%edi
+	shrdl	$2,%r14d,%r14d
+	addl	%r9d,%ebx
+	addl	%edi,%r9d
+	movl	%ebx,%r13d
+	addl	%r9d,%r14d
+	shrdl	$14,%r13d,%r13d
+	movl	%r14d,%r9d
+	movl	%ecx,%r12d
+	shrdl	$9,%r14d,%r14d
+	xorl	%ebx,%r13d
+	xorl	%edx,%r12d
+	shrdl	$5,%r13d,%r13d
+	xorl	%r9d,%r14d
+	andl	%ebx,%r12d
+	xorl	%ebx,%r13d
+	addl	12(%rsp),%r8d
+	movl	%r9d,%edi
+	xorl	%edx,%r12d
+	shrdl	$11,%r14d,%r14d
+	xorl	%r10d,%edi
+	addl	%r12d,%r8d
+	shrdl	$6,%r13d,%r13d
+	andl	%edi,%r15d
+	xorl	%r9d,%r14d
+	addl	%r13d,%r8d
+	xorl	%r10d,%r15d
+	shrdl	$2,%r14d,%r14d
+	addl	%r8d,%eax
+	addl	%r15d,%r8d
+	movl	%eax,%r13d
+	addl	%r8d,%r14d
+	shrdl	$14,%r13d,%r13d
+	movl	%r14d,%r8d
+	movl	%ebx,%r12d
+	shrdl	$9,%r14d,%r14d
+	xorl	%eax,%r13d
+	xorl	%ecx,%r12d
+	shrdl	$5,%r13d,%r13d
+	xorl	%r8d,%r14d
+	andl	%eax,%r12d
+	xorl	%eax,%r13d
+	addl	16(%rsp),%edx
+	movl	%r8d,%r15d
+	xorl	%ecx,%r12d
+	shrdl	$11,%r14d,%r14d
+	xorl	%r9d,%r15d
+	addl	%r12d,%edx
+	shrdl	$6,%r13d,%r13d
+	andl	%r15d,%edi
+	xorl	%r8d,%r14d
+	addl	%r13d,%edx
+	xorl	%r9d,%edi
+	shrdl	$2,%r14d,%r14d
+	addl	%edx,%r11d
+	addl	%edi,%edx
+	movl	%r11d,%r13d
+	addl	%edx,%r14d
+	shrdl	$14,%r13d,%r13d
+	movl	%r14d,%edx
+	movl	%eax,%r12d
+	shrdl	$9,%r14d,%r14d
+	xorl	%r11d,%r13d
+	xorl	%ebx,%r12d
+	shrdl	$5,%r13d,%r13d
+	xorl	%edx,%r14d
+	andl	%r11d,%r12d
+	xorl	%r11d,%r13d
+	addl	20(%rsp),%ecx
+	movl	%edx,%edi
+	xorl	%ebx,%r12d
+	shrdl	$11,%r14d,%r14d
+	xorl	%r8d,%edi
+	addl	%r12d,%ecx
+	shrdl	$6,%r13d,%r13d
+	andl	%edi,%r15d
+	xorl	%edx,%r14d
+	addl	%r13d,%ecx
+	xorl	%r8d,%r15d
+	shrdl	$2,%r14d,%r14d
+	addl	%ecx,%r10d
+	addl	%r15d,%ecx
+	movl	%r10d,%r13d
+	addl	%ecx,%r14d
+	shrdl	$14,%r13d,%r13d
+	movl	%r14d,%ecx
+	movl	%r11d,%r12d
+	shrdl	$9,%r14d,%r14d
+	xorl	%r10d,%r13d
+	xorl	%eax,%r12d
+	shrdl	$5,%r13d,%r13d
+	xorl	%ecx,%r14d
+	andl	%r10d,%r12d
+	xorl	%r10d,%r13d
+	addl	24(%rsp),%ebx
+	movl	%ecx,%r15d
+	xorl	%eax,%r12d
+	shrdl	$11,%r14d,%r14d
+	xorl	%edx,%r15d
+	addl	%r12d,%ebx
+	shrdl	$6,%r13d,%r13d
+	andl	%r15d,%edi
+	xorl	%ecx,%r14d
+	addl	%r13d,%ebx
+	xorl	%edx,%edi
+	shrdl	$2,%r14d,%r14d
+	addl	%ebx,%r9d
+	addl	%edi,%ebx
+	movl	%r9d,%r13d
+	addl	%ebx,%r14d
+	shrdl	$14,%r13d,%r13d
+	movl	%r14d,%ebx
+	movl	%r10d,%r12d
+	shrdl	$9,%r14d,%r14d
+	xorl	%r9d,%r13d
+	xorl	%r11d,%r12d
+	shrdl	$5,%r13d,%r13d
+	xorl	%ebx,%r14d
+	andl	%r9d,%r12d
+	xorl	%r9d,%r13d
+	addl	28(%rsp),%eax
+	movl	%ebx,%edi
+	xorl	%r11d,%r12d
+	shrdl	$11,%r14d,%r14d
+	xorl	%ecx,%edi
+	addl	%r12d,%eax
+	shrdl	$6,%r13d,%r13d
+	andl	%edi,%r15d
+	xorl	%ebx,%r14d
+	addl	%r13d,%eax
+	xorl	%ecx,%r15d
+	shrdl	$2,%r14d,%r14d
+	addl	%eax,%r8d
+	addl	%r15d,%eax
+	movl	%r8d,%r13d
+	addl	%eax,%r14d
+	shrdl	$14,%r13d,%r13d
+	movl	%r14d,%eax
+	movl	%r9d,%r12d
+	shrdl	$9,%r14d,%r14d
+	xorl	%r8d,%r13d
+	xorl	%r10d,%r12d
+	shrdl	$5,%r13d,%r13d
+	xorl	%eax,%r14d
+	andl	%r8d,%r12d
+	xorl	%r8d,%r13d
+	addl	32(%rsp),%r11d
+	movl	%eax,%r15d
+	xorl	%r10d,%r12d
+	shrdl	$11,%r14d,%r14d
+	xorl	%ebx,%r15d
+	addl	%r12d,%r11d
+	shrdl	$6,%r13d,%r13d
+	andl	%r15d,%edi
+	xorl	%eax,%r14d
+	addl	%r13d,%r11d
+	xorl	%ebx,%edi
+	shrdl	$2,%r14d,%r14d
+	addl	%r11d,%edx
+	addl	%edi,%r11d
+	movl	%edx,%r13d
+	addl	%r11d,%r14d
+	shrdl	$14,%r13d,%r13d
+	movl	%r14d,%r11d
+	movl	%r8d,%r12d
+	shrdl	$9,%r14d,%r14d
+	xorl	%edx,%r13d
+	xorl	%r9d,%r12d
+	shrdl	$5,%r13d,%r13d
+	xorl	%r11d,%r14d
+	andl	%edx,%r12d
+	xorl	%edx,%r13d
+	addl	36(%rsp),%r10d
+	movl	%r11d,%edi
+	xorl	%r9d,%r12d
+	shrdl	$11,%r14d,%r14d
+	xorl	%eax,%edi
+	addl	%r12d,%r10d
+	shrdl	$6,%r13d,%r13d
+	andl	%edi,%r15d
+	xorl	%r11d,%r14d
+	addl	%r13d,%r10d
+	xorl	%eax,%r15d
+	shrdl	$2,%r14d,%r14d
+	addl	%r10d,%ecx
+	addl	%r15d,%r10d
+	movl	%ecx,%r13d
+	addl	%r10d,%r14d
+	shrdl	$14,%r13d,%r13d
+	movl	%r14d,%r10d
+	movl	%edx,%r12d
+	shrdl	$9,%r14d,%r14d
+	xorl	%ecx,%r13d
+	xorl	%r8d,%r12d
+	shrdl	$5,%r13d,%r13d
+	xorl	%r10d,%r14d
+	andl	%ecx,%r12d
+	xorl	%ecx,%r13d
+	addl	40(%rsp),%r9d
+	movl	%r10d,%r15d
+	xorl	%r8d,%r12d
+	shrdl	$11,%r14d,%r14d
+	xorl	%r11d,%r15d
+	addl	%r12d,%r9d
+	shrdl	$6,%r13d,%r13d
+	andl	%r15d,%edi
+	xorl	%r10d,%r14d
+	addl	%r13d,%r9d
+	xorl	%r11d,%edi
+	shrdl	$2,%r14d,%r14d
+	addl	%r9d,%ebx
+	addl	%edi,%r9d
+	movl	%ebx,%r13d
+	addl	%r9d,%r14d
+	shrdl	$14,%r13d,%r13d
+	movl	%r14d,%r9d
+	movl	%ecx,%r12d
+	shrdl	$9,%r14d,%r14d
+	xorl	%ebx,%r13d
+	xorl	%edx,%r12d
+	shrdl	$5,%r13d,%r13d
+	xorl	%r9d,%r14d
+	andl	%ebx,%r12d
+	xorl	%ebx,%r13d
+	addl	44(%rsp),%r8d
+	movl	%r9d,%edi
+	xorl	%edx,%r12d
+	shrdl	$11,%r14d,%r14d
+	xorl	%r10d,%edi
+	addl	%r12d,%r8d
+	shrdl	$6,%r13d,%r13d
+	andl	%edi,%r15d
+	xorl	%r9d,%r14d
+	addl	%r13d,%r8d
+	xorl	%r10d,%r15d
+	shrdl	$2,%r14d,%r14d
+	addl	%r8d,%eax
+	addl	%r15d,%r8d
+	movl	%eax,%r13d
+	addl	%r8d,%r14d
+	shrdl	$14,%r13d,%r13d
+	movl	%r14d,%r8d
+	movl	%ebx,%r12d
+	shrdl	$9,%r14d,%r14d
+	xorl	%eax,%r13d
+	xorl	%ecx,%r12d
+	shrdl	$5,%r13d,%r13d
+	xorl	%r8d,%r14d
+	andl	%eax,%r12d
+	xorl	%eax,%r13d
+	addl	48(%rsp),%edx
+	movl	%r8d,%r15d
+	xorl	%ecx,%r12d
+	shrdl	$11,%r14d,%r14d
+	xorl	%r9d,%r15d
+	addl	%r12d,%edx
+	shrdl	$6,%r13d,%r13d
+	andl	%r15d,%edi
+	xorl	%r8d,%r14d
+	addl	%r13d,%edx
+	xorl	%r9d,%edi
+	shrdl	$2,%r14d,%r14d
+	addl	%edx,%r11d
+	addl	%edi,%edx
+	movl	%r11d,%r13d
+	addl	%edx,%r14d
+	shrdl	$14,%r13d,%r13d
+	movl	%r14d,%edx
+	movl	%eax,%r12d
+	shrdl	$9,%r14d,%r14d
+	xorl	%r11d,%r13d
+	xorl	%ebx,%r12d
+	shrdl	$5,%r13d,%r13d
+	xorl	%edx,%r14d
+	andl	%r11d,%r12d
+	xorl	%r11d,%r13d
+	addl	52(%rsp),%ecx
+	movl	%edx,%edi
+	xorl	%ebx,%r12d
+	shrdl	$11,%r14d,%r14d
+	xorl	%r8d,%edi
+	addl	%r12d,%ecx
+	shrdl	$6,%r13d,%r13d
+	andl	%edi,%r15d
+	xorl	%edx,%r14d
+	addl	%r13d,%ecx
+	xorl	%r8d,%r15d
+	shrdl	$2,%r14d,%r14d
+	addl	%ecx,%r10d
+	addl	%r15d,%ecx
+	movl	%r10d,%r13d
+	addl	%ecx,%r14d
+	shrdl	$14,%r13d,%r13d
+	movl	%r14d,%ecx
+	movl	%r11d,%r12d
+	shrdl	$9,%r14d,%r14d
+	xorl	%r10d,%r13d
+	xorl	%eax,%r12d
+	shrdl	$5,%r13d,%r13d
+	xorl	%ecx,%r14d
+	andl	%r10d,%r12d
+	xorl	%r10d,%r13d
+	addl	56(%rsp),%ebx
+	movl	%ecx,%r15d
+	xorl	%eax,%r12d
+	shrdl	$11,%r14d,%r14d
+	xorl	%edx,%r15d
+	addl	%r12d,%ebx
+	shrdl	$6,%r13d,%r13d
+	andl	%r15d,%edi
+	xorl	%ecx,%r14d
+	addl	%r13d,%ebx
+	xorl	%edx,%edi
+	shrdl	$2,%r14d,%r14d
+	addl	%ebx,%r9d
+	addl	%edi,%ebx
+	movl	%r9d,%r13d
+	addl	%ebx,%r14d
+	shrdl	$14,%r13d,%r13d
+	movl	%r14d,%ebx
+	movl	%r10d,%r12d
+	shrdl	$9,%r14d,%r14d
+	xorl	%r9d,%r13d
+	xorl	%r11d,%r12d
+	shrdl	$5,%r13d,%r13d
+	xorl	%ebx,%r14d
+	andl	%r9d,%r12d
+	xorl	%r9d,%r13d
+	addl	60(%rsp),%eax
+	movl	%ebx,%edi
+	xorl	%r11d,%r12d
+	shrdl	$11,%r14d,%r14d
+	xorl	%ecx,%edi
+	addl	%r12d,%eax
+	shrdl	$6,%r13d,%r13d
+	andl	%edi,%r15d
+	xorl	%ebx,%r14d
+	addl	%r13d,%eax
+	xorl	%ecx,%r15d
+	shrdl	$2,%r14d,%r14d
+	addl	%eax,%r8d
+	addl	%r15d,%eax
+	movl	%r8d,%r13d
+	addl	%eax,%r14d
+	movq	64+0(%rsp),%rdi
+	movl	%r14d,%eax
+
+	addl	0(%rdi),%eax
+	leaq	64(%rsi),%rsi
+	addl	4(%rdi),%ebx
+	addl	8(%rdi),%ecx
+	addl	12(%rdi),%edx
+	addl	16(%rdi),%r8d
+	addl	20(%rdi),%r9d
+	addl	24(%rdi),%r10d
+	addl	28(%rdi),%r11d
+
+	cmpq	64+16(%rsp),%rsi
+
+	movl	%eax,0(%rdi)
+	movl	%ebx,4(%rdi)
+	movl	%ecx,8(%rdi)
+	movl	%edx,12(%rdi)
+	movl	%r8d,16(%rdi)
+	movl	%r9d,20(%rdi)
+	movl	%r10d,24(%rdi)
+	movl	%r11d,28(%rdi)
+	jb	.Lloop_avx
+
+	movq	64+24(%rsp),%rsi
+	vzeroupper
+	movq	(%rsi),%r15
+	movq	8(%rsi),%r14
+	movq	16(%rsi),%r13
+	movq	24(%rsi),%r12
+	movq	32(%rsi),%rbp
+	movq	40(%rsi),%rbx
+	leaq	48(%rsi),%rsp
+.Lepilogue_avx:
+	.byte	0xf3,0xc3
+.size	sha256_block_data_order_avx,.-sha256_block_data_order_avx
 #endif
diff --git a/packager/third_party/boringssl/linux-x86_64/crypto/sha/sha512-x86_64.S b/packager/third_party/boringssl/linux-x86_64/crypto/sha/sha512-x86_64.S
index ca3a3a1644..d65743fd52 100644
--- a/packager/third_party/boringssl/linux-x86_64/crypto/sha/sha512-x86_64.S
+++ b/packager/third_party/boringssl/linux-x86_64/crypto/sha/sha512-x86_64.S
@@ -8,6 +8,17 @@
 .type	sha512_block_data_order,@function
 .align	16
 sha512_block_data_order:
+	leaq	OPENSSL_ia32cap_P(%rip),%r11
+	movl	0(%r11),%r9d
+	movl	4(%r11),%r10d
+	movl	8(%r11),%r11d
+	testl	$2048,%r10d
+	jnz	.Lxop_shortcut
+	andl	$1073741824,%r9d
+	andl	$268435968,%r10d
+	orl	%r9d,%r10d
+	cmpl	$1342177792,%r10d
+	je	.Lavx_shortcut
 	pushq	%rbx
 	pushq	%rbp
 	pushq	%r12
@@ -1784,4 +1795,2234 @@ K512:
 .quad	0x0001020304050607,0x08090a0b0c0d0e0f
 .quad	0x0001020304050607,0x08090a0b0c0d0e0f
 .byte	83,72,65,53,49,50,32,98,108,111,99,107,32,116,114,97,110,115,102,111,114,109,32,102,111,114,32,120,56,54,95,54,52,44,32,67,82,89,80,84,79,71,65,77,83,32,98,121,32,60,97,112,112,114,111,64,111,112,101,110,115,115,108,46,111,114,103,62,0
+.type	sha512_block_data_order_xop,@function
+.align	64
+sha512_block_data_order_xop:
+.Lxop_shortcut:
+	pushq	%rbx
+	pushq	%rbp
+	pushq	%r12
+	pushq	%r13
+	pushq	%r14
+	pushq	%r15
+	movq	%rsp,%r11
+	shlq	$4,%rdx
+	subq	$160,%rsp
+	leaq	(%rsi,%rdx,8),%rdx
+	andq	$-64,%rsp
+	movq	%rdi,128+0(%rsp)
+	movq	%rsi,128+8(%rsp)
+	movq	%rdx,128+16(%rsp)
+	movq	%r11,128+24(%rsp)
+.Lprologue_xop:
+
+	vzeroupper
+	movq	0(%rdi),%rax
+	movq	8(%rdi),%rbx
+	movq	16(%rdi),%rcx
+	movq	24(%rdi),%rdx
+	movq	32(%rdi),%r8
+	movq	40(%rdi),%r9
+	movq	48(%rdi),%r10
+	movq	56(%rdi),%r11
+	jmp	.Lloop_xop
+.align	16
+.Lloop_xop:
+	vmovdqa	K512+1280(%rip),%xmm11
+	vmovdqu	0(%rsi),%xmm0
+	leaq	K512+128(%rip),%rbp
+	vmovdqu	16(%rsi),%xmm1
+	vmovdqu	32(%rsi),%xmm2
+	vpshufb	%xmm11,%xmm0,%xmm0
+	vmovdqu	48(%rsi),%xmm3
+	vpshufb	%xmm11,%xmm1,%xmm1
+	vmovdqu	64(%rsi),%xmm4
+	vpshufb	%xmm11,%xmm2,%xmm2
+	vmovdqu	80(%rsi),%xmm5
+	vpshufb	%xmm11,%xmm3,%xmm3
+	vmovdqu	96(%rsi),%xmm6
+	vpshufb	%xmm11,%xmm4,%xmm4
+	vmovdqu	112(%rsi),%xmm7
+	vpshufb	%xmm11,%xmm5,%xmm5
+	vpaddq	-128(%rbp),%xmm0,%xmm8
+	vpshufb	%xmm11,%xmm6,%xmm6
+	vpaddq	-96(%rbp),%xmm1,%xmm9
+	vpshufb	%xmm11,%xmm7,%xmm7
+	vpaddq	-64(%rbp),%xmm2,%xmm10
+	vpaddq	-32(%rbp),%xmm3,%xmm11
+	vmovdqa	%xmm8,0(%rsp)
+	vpaddq	0(%rbp),%xmm4,%xmm8
+	vmovdqa	%xmm9,16(%rsp)
+	vpaddq	32(%rbp),%xmm5,%xmm9
+	vmovdqa	%xmm10,32(%rsp)
+	vpaddq	64(%rbp),%xmm6,%xmm10
+	vmovdqa	%xmm11,48(%rsp)
+	vpaddq	96(%rbp),%xmm7,%xmm11
+	vmovdqa	%xmm8,64(%rsp)
+	movq	%rax,%r14
+	vmovdqa	%xmm9,80(%rsp)
+	movq	%rbx,%rdi
+	vmovdqa	%xmm10,96(%rsp)
+	xorq	%rcx,%rdi
+	vmovdqa	%xmm11,112(%rsp)
+	movq	%r8,%r13
+	jmp	.Lxop_00_47
+
+.align	16
+.Lxop_00_47:
+	addq	$256,%rbp
+	vpalignr	$8,%xmm0,%xmm1,%xmm8
+	rorq	$23,%r13
+	movq	%r14,%rax
+	vpalignr	$8,%xmm4,%xmm5,%xmm11
+	movq	%r9,%r12
+	rorq	$5,%r14
+.byte	143,72,120,195,200,56
+	xorq	%r8,%r13
+	xorq	%r10,%r12
+	vpsrlq	$7,%xmm8,%xmm8
+	rorq	$4,%r13
+	xorq	%rax,%r14
+	vpaddq	%xmm11,%xmm0,%xmm0
+	andq	%r8,%r12
+	xorq	%r8,%r13
+	addq	0(%rsp),%r11
+	movq	%rax,%r15
+.byte	143,72,120,195,209,7
+	xorq	%r10,%r12
+	rorq	$6,%r14
+	vpxor	%xmm9,%xmm8,%xmm8
+	xorq	%rbx,%r15
+	addq	%r12,%r11
+	rorq	$14,%r13
+	andq	%r15,%rdi
+.byte	143,104,120,195,223,3
+	xorq	%rax,%r14
+	addq	%r13,%r11
+	vpxor	%xmm10,%xmm8,%xmm8
+	xorq	%rbx,%rdi
+	rorq	$28,%r14
+	vpsrlq	$6,%xmm7,%xmm10
+	addq	%r11,%rdx
+	addq	%rdi,%r11
+	vpaddq	%xmm8,%xmm0,%xmm0
+	movq	%rdx,%r13
+	addq	%r11,%r14
+.byte	143,72,120,195,203,42
+	rorq	$23,%r13
+	movq	%r14,%r11
+	vpxor	%xmm10,%xmm11,%xmm11
+	movq	%r8,%r12
+	rorq	$5,%r14
+	xorq	%rdx,%r13
+	xorq	%r9,%r12
+	vpxor	%xmm9,%xmm11,%xmm11
+	rorq	$4,%r13
+	xorq	%r11,%r14
+	andq	%rdx,%r12
+	xorq	%rdx,%r13
+	vpaddq	%xmm11,%xmm0,%xmm0
+	addq	8(%rsp),%r10
+	movq	%r11,%rdi
+	xorq	%r9,%r12
+	rorq	$6,%r14
+	vpaddq	-128(%rbp),%xmm0,%xmm10
+	xorq	%rax,%rdi
+	addq	%r12,%r10
+	rorq	$14,%r13
+	andq	%rdi,%r15
+	xorq	%r11,%r14
+	addq	%r13,%r10
+	xorq	%rax,%r15
+	rorq	$28,%r14
+	addq	%r10,%rcx
+	addq	%r15,%r10
+	movq	%rcx,%r13
+	addq	%r10,%r14
+	vmovdqa	%xmm10,0(%rsp)
+	vpalignr	$8,%xmm1,%xmm2,%xmm8
+	rorq	$23,%r13
+	movq	%r14,%r10
+	vpalignr	$8,%xmm5,%xmm6,%xmm11
+	movq	%rdx,%r12
+	rorq	$5,%r14
+.byte	143,72,120,195,200,56
+	xorq	%rcx,%r13
+	xorq	%r8,%r12
+	vpsrlq	$7,%xmm8,%xmm8
+	rorq	$4,%r13
+	xorq	%r10,%r14
+	vpaddq	%xmm11,%xmm1,%xmm1
+	andq	%rcx,%r12
+	xorq	%rcx,%r13
+	addq	16(%rsp),%r9
+	movq	%r10,%r15
+.byte	143,72,120,195,209,7
+	xorq	%r8,%r12
+	rorq	$6,%r14
+	vpxor	%xmm9,%xmm8,%xmm8
+	xorq	%r11,%r15
+	addq	%r12,%r9
+	rorq	$14,%r13
+	andq	%r15,%rdi
+.byte	143,104,120,195,216,3
+	xorq	%r10,%r14
+	addq	%r13,%r9
+	vpxor	%xmm10,%xmm8,%xmm8
+	xorq	%r11,%rdi
+	rorq	$28,%r14
+	vpsrlq	$6,%xmm0,%xmm10
+	addq	%r9,%rbx
+	addq	%rdi,%r9
+	vpaddq	%xmm8,%xmm1,%xmm1
+	movq	%rbx,%r13
+	addq	%r9,%r14
+.byte	143,72,120,195,203,42
+	rorq	$23,%r13
+	movq	%r14,%r9
+	vpxor	%xmm10,%xmm11,%xmm11
+	movq	%rcx,%r12
+	rorq	$5,%r14
+	xorq	%rbx,%r13
+	xorq	%rdx,%r12
+	vpxor	%xmm9,%xmm11,%xmm11
+	rorq	$4,%r13
+	xorq	%r9,%r14
+	andq	%rbx,%r12
+	xorq	%rbx,%r13
+	vpaddq	%xmm11,%xmm1,%xmm1
+	addq	24(%rsp),%r8
+	movq	%r9,%rdi
+	xorq	%rdx,%r12
+	rorq	$6,%r14
+	vpaddq	-96(%rbp),%xmm1,%xmm10
+	xorq	%r10,%rdi
+	addq	%r12,%r8
+	rorq	$14,%r13
+	andq	%rdi,%r15
+	xorq	%r9,%r14
+	addq	%r13,%r8
+	xorq	%r10,%r15
+	rorq	$28,%r14
+	addq	%r8,%rax
+	addq	%r15,%r8
+	movq	%rax,%r13
+	addq	%r8,%r14
+	vmovdqa	%xmm10,16(%rsp)
+	vpalignr	$8,%xmm2,%xmm3,%xmm8
+	rorq	$23,%r13
+	movq	%r14,%r8
+	vpalignr	$8,%xmm6,%xmm7,%xmm11
+	movq	%rbx,%r12
+	rorq	$5,%r14
+.byte	143,72,120,195,200,56
+	xorq	%rax,%r13
+	xorq	%rcx,%r12
+	vpsrlq	$7,%xmm8,%xmm8
+	rorq	$4,%r13
+	xorq	%r8,%r14
+	vpaddq	%xmm11,%xmm2,%xmm2
+	andq	%rax,%r12
+	xorq	%rax,%r13
+	addq	32(%rsp),%rdx
+	movq	%r8,%r15
+.byte	143,72,120,195,209,7
+	xorq	%rcx,%r12
+	rorq	$6,%r14
+	vpxor	%xmm9,%xmm8,%xmm8
+	xorq	%r9,%r15
+	addq	%r12,%rdx
+	rorq	$14,%r13
+	andq	%r15,%rdi
+.byte	143,104,120,195,217,3
+	xorq	%r8,%r14
+	addq	%r13,%rdx
+	vpxor	%xmm10,%xmm8,%xmm8
+	xorq	%r9,%rdi
+	rorq	$28,%r14
+	vpsrlq	$6,%xmm1,%xmm10
+	addq	%rdx,%r11
+	addq	%rdi,%rdx
+	vpaddq	%xmm8,%xmm2,%xmm2
+	movq	%r11,%r13
+	addq	%rdx,%r14
+.byte	143,72,120,195,203,42
+	rorq	$23,%r13
+	movq	%r14,%rdx
+	vpxor	%xmm10,%xmm11,%xmm11
+	movq	%rax,%r12
+	rorq	$5,%r14
+	xorq	%r11,%r13
+	xorq	%rbx,%r12
+	vpxor	%xmm9,%xmm11,%xmm11
+	rorq	$4,%r13
+	xorq	%rdx,%r14
+	andq	%r11,%r12
+	xorq	%r11,%r13
+	vpaddq	%xmm11,%xmm2,%xmm2
+	addq	40(%rsp),%rcx
+	movq	%rdx,%rdi
+	xorq	%rbx,%r12
+	rorq	$6,%r14
+	vpaddq	-64(%rbp),%xmm2,%xmm10
+	xorq	%r8,%rdi
+	addq	%r12,%rcx
+	rorq	$14,%r13
+	andq	%rdi,%r15
+	xorq	%rdx,%r14
+	addq	%r13,%rcx
+	xorq	%r8,%r15
+	rorq	$28,%r14
+	addq	%rcx,%r10
+	addq	%r15,%rcx
+	movq	%r10,%r13
+	addq	%rcx,%r14
+	vmovdqa	%xmm10,32(%rsp)
+	vpalignr	$8,%xmm3,%xmm4,%xmm8
+	rorq	$23,%r13
+	movq	%r14,%rcx
+	vpalignr	$8,%xmm7,%xmm0,%xmm11
+	movq	%r11,%r12
+	rorq	$5,%r14
+.byte	143,72,120,195,200,56
+	xorq	%r10,%r13
+	xorq	%rax,%r12
+	vpsrlq	$7,%xmm8,%xmm8
+	rorq	$4,%r13
+	xorq	%rcx,%r14
+	vpaddq	%xmm11,%xmm3,%xmm3
+	andq	%r10,%r12
+	xorq	%r10,%r13
+	addq	48(%rsp),%rbx
+	movq	%rcx,%r15
+.byte	143,72,120,195,209,7
+	xorq	%rax,%r12
+	rorq	$6,%r14
+	vpxor	%xmm9,%xmm8,%xmm8
+	xorq	%rdx,%r15
+	addq	%r12,%rbx
+	rorq	$14,%r13
+	andq	%r15,%rdi
+.byte	143,104,120,195,218,3
+	xorq	%rcx,%r14
+	addq	%r13,%rbx
+	vpxor	%xmm10,%xmm8,%xmm8
+	xorq	%rdx,%rdi
+	rorq	$28,%r14
+	vpsrlq	$6,%xmm2,%xmm10
+	addq	%rbx,%r9
+	addq	%rdi,%rbx
+	vpaddq	%xmm8,%xmm3,%xmm3
+	movq	%r9,%r13
+	addq	%rbx,%r14
+.byte	143,72,120,195,203,42
+	rorq	$23,%r13
+	movq	%r14,%rbx
+	vpxor	%xmm10,%xmm11,%xmm11
+	movq	%r10,%r12
+	rorq	$5,%r14
+	xorq	%r9,%r13
+	xorq	%r11,%r12
+	vpxor	%xmm9,%xmm11,%xmm11
+	rorq	$4,%r13
+	xorq	%rbx,%r14
+	andq	%r9,%r12
+	xorq	%r9,%r13
+	vpaddq	%xmm11,%xmm3,%xmm3
+	addq	56(%rsp),%rax
+	movq	%rbx,%rdi
+	xorq	%r11,%r12
+	rorq	$6,%r14
+	vpaddq	-32(%rbp),%xmm3,%xmm10
+	xorq	%rcx,%rdi
+	addq	%r12,%rax
+	rorq	$14,%r13
+	andq	%rdi,%r15
+	xorq	%rbx,%r14
+	addq	%r13,%rax
+	xorq	%rcx,%r15
+	rorq	$28,%r14
+	addq	%rax,%r8
+	addq	%r15,%rax
+	movq	%r8,%r13
+	addq	%rax,%r14
+	vmovdqa	%xmm10,48(%rsp)
+	vpalignr	$8,%xmm4,%xmm5,%xmm8
+	rorq	$23,%r13
+	movq	%r14,%rax
+	vpalignr	$8,%xmm0,%xmm1,%xmm11
+	movq	%r9,%r12
+	rorq	$5,%r14
+.byte	143,72,120,195,200,56
+	xorq	%r8,%r13
+	xorq	%r10,%r12
+	vpsrlq	$7,%xmm8,%xmm8
+	rorq	$4,%r13
+	xorq	%rax,%r14
+	vpaddq	%xmm11,%xmm4,%xmm4
+	andq	%r8,%r12
+	xorq	%r8,%r13
+	addq	64(%rsp),%r11
+	movq	%rax,%r15
+.byte	143,72,120,195,209,7
+	xorq	%r10,%r12
+	rorq	$6,%r14
+	vpxor	%xmm9,%xmm8,%xmm8
+	xorq	%rbx,%r15
+	addq	%r12,%r11
+	rorq	$14,%r13
+	andq	%r15,%rdi
+.byte	143,104,120,195,219,3
+	xorq	%rax,%r14
+	addq	%r13,%r11
+	vpxor	%xmm10,%xmm8,%xmm8
+	xorq	%rbx,%rdi
+	rorq	$28,%r14
+	vpsrlq	$6,%xmm3,%xmm10
+	addq	%r11,%rdx
+	addq	%rdi,%r11
+	vpaddq	%xmm8,%xmm4,%xmm4
+	movq	%rdx,%r13
+	addq	%r11,%r14
+.byte	143,72,120,195,203,42
+	rorq	$23,%r13
+	movq	%r14,%r11
+	vpxor	%xmm10,%xmm11,%xmm11
+	movq	%r8,%r12
+	rorq	$5,%r14
+	xorq	%rdx,%r13
+	xorq	%r9,%r12
+	vpxor	%xmm9,%xmm11,%xmm11
+	rorq	$4,%r13
+	xorq	%r11,%r14
+	andq	%rdx,%r12
+	xorq	%rdx,%r13
+	vpaddq	%xmm11,%xmm4,%xmm4
+	addq	72(%rsp),%r10
+	movq	%r11,%rdi
+	xorq	%r9,%r12
+	rorq	$6,%r14
+	vpaddq	0(%rbp),%xmm4,%xmm10
+	xorq	%rax,%rdi
+	addq	%r12,%r10
+	rorq	$14,%r13
+	andq	%rdi,%r15
+	xorq	%r11,%r14
+	addq	%r13,%r10
+	xorq	%rax,%r15
+	rorq	$28,%r14
+	addq	%r10,%rcx
+	addq	%r15,%r10
+	movq	%rcx,%r13
+	addq	%r10,%r14
+	vmovdqa	%xmm10,64(%rsp)
+	vpalignr	$8,%xmm5,%xmm6,%xmm8
+	rorq	$23,%r13
+	movq	%r14,%r10
+	vpalignr	$8,%xmm1,%xmm2,%xmm11
+	movq	%rdx,%r12
+	rorq	$5,%r14
+.byte	143,72,120,195,200,56
+	xorq	%rcx,%r13
+	xorq	%r8,%r12
+	vpsrlq	$7,%xmm8,%xmm8
+	rorq	$4,%r13
+	xorq	%r10,%r14
+	vpaddq	%xmm11,%xmm5,%xmm5
+	andq	%rcx,%r12
+	xorq	%rcx,%r13
+	addq	80(%rsp),%r9
+	movq	%r10,%r15
+.byte	143,72,120,195,209,7
+	xorq	%r8,%r12
+	rorq	$6,%r14
+	vpxor	%xmm9,%xmm8,%xmm8
+	xorq	%r11,%r15
+	addq	%r12,%r9
+	rorq	$14,%r13
+	andq	%r15,%rdi
+.byte	143,104,120,195,220,3
+	xorq	%r10,%r14
+	addq	%r13,%r9
+	vpxor	%xmm10,%xmm8,%xmm8
+	xorq	%r11,%rdi
+	rorq	$28,%r14
+	vpsrlq	$6,%xmm4,%xmm10
+	addq	%r9,%rbx
+	addq	%rdi,%r9
+	vpaddq	%xmm8,%xmm5,%xmm5
+	movq	%rbx,%r13
+	addq	%r9,%r14
+.byte	143,72,120,195,203,42
+	rorq	$23,%r13
+	movq	%r14,%r9
+	vpxor	%xmm10,%xmm11,%xmm11
+	movq	%rcx,%r12
+	rorq	$5,%r14
+	xorq	%rbx,%r13
+	xorq	%rdx,%r12
+	vpxor	%xmm9,%xmm11,%xmm11
+	rorq	$4,%r13
+	xorq	%r9,%r14
+	andq	%rbx,%r12
+	xorq	%rbx,%r13
+	vpaddq	%xmm11,%xmm5,%xmm5
+	addq	88(%rsp),%r8
+	movq	%r9,%rdi
+	xorq	%rdx,%r12
+	rorq	$6,%r14
+	vpaddq	32(%rbp),%xmm5,%xmm10
+	xorq	%r10,%rdi
+	addq	%r12,%r8
+	rorq	$14,%r13
+	andq	%rdi,%r15
+	xorq	%r9,%r14
+	addq	%r13,%r8
+	xorq	%r10,%r15
+	rorq	$28,%r14
+	addq	%r8,%rax
+	addq	%r15,%r8
+	movq	%rax,%r13
+	addq	%r8,%r14
+	vmovdqa	%xmm10,80(%rsp)
+	vpalignr	$8,%xmm6,%xmm7,%xmm8
+	rorq	$23,%r13
+	movq	%r14,%r8
+	vpalignr	$8,%xmm2,%xmm3,%xmm11
+	movq	%rbx,%r12
+	rorq	$5,%r14
+.byte	143,72,120,195,200,56
+	xorq	%rax,%r13
+	xorq	%rcx,%r12
+	vpsrlq	$7,%xmm8,%xmm8
+	rorq	$4,%r13
+	xorq	%r8,%r14
+	vpaddq	%xmm11,%xmm6,%xmm6
+	andq	%rax,%r12
+	xorq	%rax,%r13
+	addq	96(%rsp),%rdx
+	movq	%r8,%r15
+.byte	143,72,120,195,209,7
+	xorq	%rcx,%r12
+	rorq	$6,%r14
+	vpxor	%xmm9,%xmm8,%xmm8
+	xorq	%r9,%r15
+	addq	%r12,%rdx
+	rorq	$14,%r13
+	andq	%r15,%rdi
+.byte	143,104,120,195,221,3
+	xorq	%r8,%r14
+	addq	%r13,%rdx
+	vpxor	%xmm10,%xmm8,%xmm8
+	xorq	%r9,%rdi
+	rorq	$28,%r14
+	vpsrlq	$6,%xmm5,%xmm10
+	addq	%rdx,%r11
+	addq	%rdi,%rdx
+	vpaddq	%xmm8,%xmm6,%xmm6
+	movq	%r11,%r13
+	addq	%rdx,%r14
+.byte	143,72,120,195,203,42
+	rorq	$23,%r13
+	movq	%r14,%rdx
+	vpxor	%xmm10,%xmm11,%xmm11
+	movq	%rax,%r12
+	rorq	$5,%r14
+	xorq	%r11,%r13
+	xorq	%rbx,%r12
+	vpxor	%xmm9,%xmm11,%xmm11
+	rorq	$4,%r13
+	xorq	%rdx,%r14
+	andq	%r11,%r12
+	xorq	%r11,%r13
+	vpaddq	%xmm11,%xmm6,%xmm6
+	addq	104(%rsp),%rcx
+	movq	%rdx,%rdi
+	xorq	%rbx,%r12
+	rorq	$6,%r14
+	vpaddq	64(%rbp),%xmm6,%xmm10
+	xorq	%r8,%rdi
+	addq	%r12,%rcx
+	rorq	$14,%r13
+	andq	%rdi,%r15
+	xorq	%rdx,%r14
+	addq	%r13,%rcx
+	xorq	%r8,%r15
+	rorq	$28,%r14
+	addq	%rcx,%r10
+	addq	%r15,%rcx
+	movq	%r10,%r13
+	addq	%rcx,%r14
+	vmovdqa	%xmm10,96(%rsp)
+	vpalignr	$8,%xmm7,%xmm0,%xmm8
+	rorq	$23,%r13
+	movq	%r14,%rcx
+	vpalignr	$8,%xmm3,%xmm4,%xmm11
+	movq	%r11,%r12
+	rorq	$5,%r14
+.byte	143,72,120,195,200,56
+	xorq	%r10,%r13
+	xorq	%rax,%r12
+	vpsrlq	$7,%xmm8,%xmm8
+	rorq	$4,%r13
+	xorq	%rcx,%r14
+	vpaddq	%xmm11,%xmm7,%xmm7
+	andq	%r10,%r12
+	xorq	%r10,%r13
+	addq	112(%rsp),%rbx
+	movq	%rcx,%r15
+.byte	143,72,120,195,209,7
+	xorq	%rax,%r12
+	rorq	$6,%r14
+	vpxor	%xmm9,%xmm8,%xmm8
+	xorq	%rdx,%r15
+	addq	%r12,%rbx
+	rorq	$14,%r13
+	andq	%r15,%rdi
+.byte	143,104,120,195,222,3
+	xorq	%rcx,%r14
+	addq	%r13,%rbx
+	vpxor	%xmm10,%xmm8,%xmm8
+	xorq	%rdx,%rdi
+	rorq	$28,%r14
+	vpsrlq	$6,%xmm6,%xmm10
+	addq	%rbx,%r9
+	addq	%rdi,%rbx
+	vpaddq	%xmm8,%xmm7,%xmm7
+	movq	%r9,%r13
+	addq	%rbx,%r14
+.byte	143,72,120,195,203,42
+	rorq	$23,%r13
+	movq	%r14,%rbx
+	vpxor	%xmm10,%xmm11,%xmm11
+	movq	%r10,%r12
+	rorq	$5,%r14
+	xorq	%r9,%r13
+	xorq	%r11,%r12
+	vpxor	%xmm9,%xmm11,%xmm11
+	rorq	$4,%r13
+	xorq	%rbx,%r14
+	andq	%r9,%r12
+	xorq	%r9,%r13
+	vpaddq	%xmm11,%xmm7,%xmm7
+	addq	120(%rsp),%rax
+	movq	%rbx,%rdi
+	xorq	%r11,%r12
+	rorq	$6,%r14
+	vpaddq	96(%rbp),%xmm7,%xmm10
+	xorq	%rcx,%rdi
+	addq	%r12,%rax
+	rorq	$14,%r13
+	andq	%rdi,%r15
+	xorq	%rbx,%r14
+	addq	%r13,%rax
+	xorq	%rcx,%r15
+	rorq	$28,%r14
+	addq	%rax,%r8
+	addq	%r15,%rax
+	movq	%r8,%r13
+	addq	%rax,%r14
+	vmovdqa	%xmm10,112(%rsp)
+	cmpb	$0,135(%rbp)
+	jne	.Lxop_00_47
+	rorq	$23,%r13
+	movq	%r14,%rax
+	movq	%r9,%r12
+	rorq	$5,%r14
+	xorq	%r8,%r13
+	xorq	%r10,%r12
+	rorq	$4,%r13
+	xorq	%rax,%r14
+	andq	%r8,%r12
+	xorq	%r8,%r13
+	addq	0(%rsp),%r11
+	movq	%rax,%r15
+	xorq	%r10,%r12
+	rorq	$6,%r14
+	xorq	%rbx,%r15
+	addq	%r12,%r11
+	rorq	$14,%r13
+	andq	%r15,%rdi
+	xorq	%rax,%r14
+	addq	%r13,%r11
+	xorq	%rbx,%rdi
+	rorq	$28,%r14
+	addq	%r11,%rdx
+	addq	%rdi,%r11
+	movq	%rdx,%r13
+	addq	%r11,%r14
+	rorq	$23,%r13
+	movq	%r14,%r11
+	movq	%r8,%r12
+	rorq	$5,%r14
+	xorq	%rdx,%r13
+	xorq	%r9,%r12
+	rorq	$4,%r13
+	xorq	%r11,%r14
+	andq	%rdx,%r12
+	xorq	%rdx,%r13
+	addq	8(%rsp),%r10
+	movq	%r11,%rdi
+	xorq	%r9,%r12
+	rorq	$6,%r14
+	xorq	%rax,%rdi
+	addq	%r12,%r10
+	rorq	$14,%r13
+	andq	%rdi,%r15
+	xorq	%r11,%r14
+	addq	%r13,%r10
+	xorq	%rax,%r15
+	rorq	$28,%r14
+	addq	%r10,%rcx
+	addq	%r15,%r10
+	movq	%rcx,%r13
+	addq	%r10,%r14
+	rorq	$23,%r13
+	movq	%r14,%r10
+	movq	%rdx,%r12
+	rorq	$5,%r14
+	xorq	%rcx,%r13
+	xorq	%r8,%r12
+	rorq	$4,%r13
+	xorq	%r10,%r14
+	andq	%rcx,%r12
+	xorq	%rcx,%r13
+	addq	16(%rsp),%r9
+	movq	%r10,%r15
+	xorq	%r8,%r12
+	rorq	$6,%r14
+	xorq	%r11,%r15
+	addq	%r12,%r9
+	rorq	$14,%r13
+	andq	%r15,%rdi
+	xorq	%r10,%r14
+	addq	%r13,%r9
+	xorq	%r11,%rdi
+	rorq	$28,%r14
+	addq	%r9,%rbx
+	addq	%rdi,%r9
+	movq	%rbx,%r13
+	addq	%r9,%r14
+	rorq	$23,%r13
+	movq	%r14,%r9
+	movq	%rcx,%r12
+	rorq	$5,%r14
+	xorq	%rbx,%r13
+	xorq	%rdx,%r12
+	rorq	$4,%r13
+	xorq	%r9,%r14
+	andq	%rbx,%r12
+	xorq	%rbx,%r13
+	addq	24(%rsp),%r8
+	movq	%r9,%rdi
+	xorq	%rdx,%r12
+	rorq	$6,%r14
+	xorq	%r10,%rdi
+	addq	%r12,%r8
+	rorq	$14,%r13
+	andq	%rdi,%r15
+	xorq	%r9,%r14
+	addq	%r13,%r8
+	xorq	%r10,%r15
+	rorq	$28,%r14
+	addq	%r8,%rax
+	addq	%r15,%r8
+	movq	%rax,%r13
+	addq	%r8,%r14
+	rorq	$23,%r13
+	movq	%r14,%r8
+	movq	%rbx,%r12
+	rorq	$5,%r14
+	xorq	%rax,%r13
+	xorq	%rcx,%r12
+	rorq	$4,%r13
+	xorq	%r8,%r14
+	andq	%rax,%r12
+	xorq	%rax,%r13
+	addq	32(%rsp),%rdx
+	movq	%r8,%r15
+	xorq	%rcx,%r12
+	rorq	$6,%r14
+	xorq	%r9,%r15
+	addq	%r12,%rdx
+	rorq	$14,%r13
+	andq	%r15,%rdi
+	xorq	%r8,%r14
+	addq	%r13,%rdx
+	xorq	%r9,%rdi
+	rorq	$28,%r14
+	addq	%rdx,%r11
+	addq	%rdi,%rdx
+	movq	%r11,%r13
+	addq	%rdx,%r14
+	rorq	$23,%r13
+	movq	%r14,%rdx
+	movq	%rax,%r12
+	rorq	$5,%r14
+	xorq	%r11,%r13
+	xorq	%rbx,%r12
+	rorq	$4,%r13
+	xorq	%rdx,%r14
+	andq	%r11,%r12
+	xorq	%r11,%r13
+	addq	40(%rsp),%rcx
+	movq	%rdx,%rdi
+	xorq	%rbx,%r12
+	rorq	$6,%r14
+	xorq	%r8,%rdi
+	addq	%r12,%rcx
+	rorq	$14,%r13
+	andq	%rdi,%r15
+	xorq	%rdx,%r14
+	addq	%r13,%rcx
+	xorq	%r8,%r15
+	rorq	$28,%r14
+	addq	%rcx,%r10
+	addq	%r15,%rcx
+	movq	%r10,%r13
+	addq	%rcx,%r14
+	rorq	$23,%r13
+	movq	%r14,%rcx
+	movq	%r11,%r12
+	rorq	$5,%r14
+	xorq	%r10,%r13
+	xorq	%rax,%r12
+	rorq	$4,%r13
+	xorq	%rcx,%r14
+	andq	%r10,%r12
+	xorq	%r10,%r13
+	addq	48(%rsp),%rbx
+	movq	%rcx,%r15
+	xorq	%rax,%r12
+	rorq	$6,%r14
+	xorq	%rdx,%r15
+	addq	%r12,%rbx
+	rorq	$14,%r13
+	andq	%r15,%rdi
+	xorq	%rcx,%r14
+	addq	%r13,%rbx
+	xorq	%rdx,%rdi
+	rorq	$28,%r14
+	addq	%rbx,%r9
+	addq	%rdi,%rbx
+	movq	%r9,%r13
+	addq	%rbx,%r14
+	rorq	$23,%r13
+	movq	%r14,%rbx
+	movq	%r10,%r12
+	rorq	$5,%r14
+	xorq	%r9,%r13
+	xorq	%r11,%r12
+	rorq	$4,%r13
+	xorq	%rbx,%r14
+	andq	%r9,%r12
+	xorq	%r9,%r13
+	addq	56(%rsp),%rax
+	movq	%rbx,%rdi
+	xorq	%r11,%r12
+	rorq	$6,%r14
+	xorq	%rcx,%rdi
+	addq	%r12,%rax
+	rorq	$14,%r13
+	andq	%rdi,%r15
+	xorq	%rbx,%r14
+	addq	%r13,%rax
+	xorq	%rcx,%r15
+	rorq	$28,%r14
+	addq	%rax,%r8
+	addq	%r15,%rax
+	movq	%r8,%r13
+	addq	%rax,%r14
+	rorq	$23,%r13
+	movq	%r14,%rax
+	movq	%r9,%r12
+	rorq	$5,%r14
+	xorq	%r8,%r13
+	xorq	%r10,%r12
+	rorq	$4,%r13
+	xorq	%rax,%r14
+	andq	%r8,%r12
+	xorq	%r8,%r13
+	addq	64(%rsp),%r11
+	movq	%rax,%r15
+	xorq	%r10,%r12
+	rorq	$6,%r14
+	xorq	%rbx,%r15
+	addq	%r12,%r11
+	rorq	$14,%r13
+	andq	%r15,%rdi
+	xorq	%rax,%r14
+	addq	%r13,%r11
+	xorq	%rbx,%rdi
+	rorq	$28,%r14
+	addq	%r11,%rdx
+	addq	%rdi,%r11
+	movq	%rdx,%r13
+	addq	%r11,%r14
+	rorq	$23,%r13
+	movq	%r14,%r11
+	movq	%r8,%r12
+	rorq	$5,%r14
+	xorq	%rdx,%r13
+	xorq	%r9,%r12
+	rorq	$4,%r13
+	xorq	%r11,%r14
+	andq	%rdx,%r12
+	xorq	%rdx,%r13
+	addq	72(%rsp),%r10
+	movq	%r11,%rdi
+	xorq	%r9,%r12
+	rorq	$6,%r14
+	xorq	%rax,%rdi
+	addq	%r12,%r10
+	rorq	$14,%r13
+	andq	%rdi,%r15
+	xorq	%r11,%r14
+	addq	%r13,%r10
+	xorq	%rax,%r15
+	rorq	$28,%r14
+	addq	%r10,%rcx
+	addq	%r15,%r10
+	movq	%rcx,%r13
+	addq	%r10,%r14
+	rorq	$23,%r13
+	movq	%r14,%r10
+	movq	%rdx,%r12
+	rorq	$5,%r14
+	xorq	%rcx,%r13
+	xorq	%r8,%r12
+	rorq	$4,%r13
+	xorq	%r10,%r14
+	andq	%rcx,%r12
+	xorq	%rcx,%r13
+	addq	80(%rsp),%r9
+	movq	%r10,%r15
+	xorq	%r8,%r12
+	rorq	$6,%r14
+	xorq	%r11,%r15
+	addq	%r12,%r9
+	rorq	$14,%r13
+	andq	%r15,%rdi
+	xorq	%r10,%r14
+	addq	%r13,%r9
+	xorq	%r11,%rdi
+	rorq	$28,%r14
+	addq	%r9,%rbx
+	addq	%rdi,%r9
+	movq	%rbx,%r13
+	addq	%r9,%r14
+	rorq	$23,%r13
+	movq	%r14,%r9
+	movq	%rcx,%r12
+	rorq	$5,%r14
+	xorq	%rbx,%r13
+	xorq	%rdx,%r12
+	rorq	$4,%r13
+	xorq	%r9,%r14
+	andq	%rbx,%r12
+	xorq	%rbx,%r13
+	addq	88(%rsp),%r8
+	movq	%r9,%rdi
+	xorq	%rdx,%r12
+	rorq	$6,%r14
+	xorq	%r10,%rdi
+	addq	%r12,%r8
+	rorq	$14,%r13
+	andq	%rdi,%r15
+	xorq	%r9,%r14
+	addq	%r13,%r8
+	xorq	%r10,%r15
+	rorq	$28,%r14
+	addq	%r8,%rax
+	addq	%r15,%r8
+	movq	%rax,%r13
+	addq	%r8,%r14
+	rorq	$23,%r13
+	movq	%r14,%r8
+	movq	%rbx,%r12
+	rorq	$5,%r14
+	xorq	%rax,%r13
+	xorq	%rcx,%r12
+	rorq	$4,%r13
+	xorq	%r8,%r14
+	andq	%rax,%r12
+	xorq	%rax,%r13
+	addq	96(%rsp),%rdx
+	movq	%r8,%r15
+	xorq	%rcx,%r12
+	rorq	$6,%r14
+	xorq	%r9,%r15
+	addq	%r12,%rdx
+	rorq	$14,%r13
+	andq	%r15,%rdi
+	xorq	%r8,%r14
+	addq	%r13,%rdx
+	xorq	%r9,%rdi
+	rorq	$28,%r14
+	addq	%rdx,%r11
+	addq	%rdi,%rdx
+	movq	%r11,%r13
+	addq	%rdx,%r14
+	rorq	$23,%r13
+	movq	%r14,%rdx
+	movq	%rax,%r12
+	rorq	$5,%r14
+	xorq	%r11,%r13
+	xorq	%rbx,%r12
+	rorq	$4,%r13
+	xorq	%rdx,%r14
+	andq	%r11,%r12
+	xorq	%r11,%r13
+	addq	104(%rsp),%rcx
+	movq	%rdx,%rdi
+	xorq	%rbx,%r12
+	rorq	$6,%r14
+	xorq	%r8,%rdi
+	addq	%r12,%rcx
+	rorq	$14,%r13
+	andq	%rdi,%r15
+	xorq	%rdx,%r14
+	addq	%r13,%rcx
+	xorq	%r8,%r15
+	rorq	$28,%r14
+	addq	%rcx,%r10
+	addq	%r15,%rcx
+	movq	%r10,%r13
+	addq	%rcx,%r14
+	rorq	$23,%r13
+	movq	%r14,%rcx
+	movq	%r11,%r12
+	rorq	$5,%r14
+	xorq	%r10,%r13
+	xorq	%rax,%r12
+	rorq	$4,%r13
+	xorq	%rcx,%r14
+	andq	%r10,%r12
+	xorq	%r10,%r13
+	addq	112(%rsp),%rbx
+	movq	%rcx,%r15
+	xorq	%rax,%r12
+	rorq	$6,%r14
+	xorq	%rdx,%r15
+	addq	%r12,%rbx
+	rorq	$14,%r13
+	andq	%r15,%rdi
+	xorq	%rcx,%r14
+	addq	%r13,%rbx
+	xorq	%rdx,%rdi
+	rorq	$28,%r14
+	addq	%rbx,%r9
+	addq	%rdi,%rbx
+	movq	%r9,%r13
+	addq	%rbx,%r14
+	rorq	$23,%r13
+	movq	%r14,%rbx
+	movq	%r10,%r12
+	rorq	$5,%r14
+	xorq	%r9,%r13
+	xorq	%r11,%r12
+	rorq	$4,%r13
+	xorq	%rbx,%r14
+	andq	%r9,%r12
+	xorq	%r9,%r13
+	addq	120(%rsp),%rax
+	movq	%rbx,%rdi
+	xorq	%r11,%r12
+	rorq	$6,%r14
+	xorq	%rcx,%rdi
+	addq	%r12,%rax
+	rorq	$14,%r13
+	andq	%rdi,%r15
+	xorq	%rbx,%r14
+	addq	%r13,%rax
+	xorq	%rcx,%r15
+	rorq	$28,%r14
+	addq	%rax,%r8
+	addq	%r15,%rax
+	movq	%r8,%r13
+	addq	%rax,%r14
+	movq	128+0(%rsp),%rdi
+	movq	%r14,%rax
+
+	addq	0(%rdi),%rax
+	leaq	128(%rsi),%rsi
+	addq	8(%rdi),%rbx
+	addq	16(%rdi),%rcx
+	addq	24(%rdi),%rdx
+	addq	32(%rdi),%r8
+	addq	40(%rdi),%r9
+	addq	48(%rdi),%r10
+	addq	56(%rdi),%r11
+
+	cmpq	128+16(%rsp),%rsi
+
+	movq	%rax,0(%rdi)
+	movq	%rbx,8(%rdi)
+	movq	%rcx,16(%rdi)
+	movq	%rdx,24(%rdi)
+	movq	%r8,32(%rdi)
+	movq	%r9,40(%rdi)
+	movq	%r10,48(%rdi)
+	movq	%r11,56(%rdi)
+	jb	.Lloop_xop
+
+	movq	128+24(%rsp),%rsi
+	vzeroupper
+	movq	(%rsi),%r15
+	movq	8(%rsi),%r14
+	movq	16(%rsi),%r13
+	movq	24(%rsi),%r12
+	movq	32(%rsi),%rbp
+	movq	40(%rsi),%rbx
+	leaq	48(%rsi),%rsp
+.Lepilogue_xop:
+	.byte	0xf3,0xc3
+.size	sha512_block_data_order_xop,.-sha512_block_data_order_xop
+.type	sha512_block_data_order_avx,@function
+.align	64
+sha512_block_data_order_avx:
+.Lavx_shortcut:
+	pushq	%rbx
+	pushq	%rbp
+	pushq	%r12
+	pushq	%r13
+	pushq	%r14
+	pushq	%r15
+	movq	%rsp,%r11
+	shlq	$4,%rdx
+	subq	$160,%rsp
+	leaq	(%rsi,%rdx,8),%rdx
+	andq	$-64,%rsp
+	movq	%rdi,128+0(%rsp)
+	movq	%rsi,128+8(%rsp)
+	movq	%rdx,128+16(%rsp)
+	movq	%r11,128+24(%rsp)
+.Lprologue_avx:
+
+	vzeroupper
+	movq	0(%rdi),%rax
+	movq	8(%rdi),%rbx
+	movq	16(%rdi),%rcx
+	movq	24(%rdi),%rdx
+	movq	32(%rdi),%r8
+	movq	40(%rdi),%r9
+	movq	48(%rdi),%r10
+	movq	56(%rdi),%r11
+	jmp	.Lloop_avx
+.align	16
+.Lloop_avx:
+	vmovdqa	K512+1280(%rip),%xmm11
+	vmovdqu	0(%rsi),%xmm0
+	leaq	K512+128(%rip),%rbp
+	vmovdqu	16(%rsi),%xmm1
+	vmovdqu	32(%rsi),%xmm2
+	vpshufb	%xmm11,%xmm0,%xmm0
+	vmovdqu	48(%rsi),%xmm3
+	vpshufb	%xmm11,%xmm1,%xmm1
+	vmovdqu	64(%rsi),%xmm4
+	vpshufb	%xmm11,%xmm2,%xmm2
+	vmovdqu	80(%rsi),%xmm5
+	vpshufb	%xmm11,%xmm3,%xmm3
+	vmovdqu	96(%rsi),%xmm6
+	vpshufb	%xmm11,%xmm4,%xmm4
+	vmovdqu	112(%rsi),%xmm7
+	vpshufb	%xmm11,%xmm5,%xmm5
+	vpaddq	-128(%rbp),%xmm0,%xmm8
+	vpshufb	%xmm11,%xmm6,%xmm6
+	vpaddq	-96(%rbp),%xmm1,%xmm9
+	vpshufb	%xmm11,%xmm7,%xmm7
+	vpaddq	-64(%rbp),%xmm2,%xmm10
+	vpaddq	-32(%rbp),%xmm3,%xmm11
+	vmovdqa	%xmm8,0(%rsp)
+	vpaddq	0(%rbp),%xmm4,%xmm8
+	vmovdqa	%xmm9,16(%rsp)
+	vpaddq	32(%rbp),%xmm5,%xmm9
+	vmovdqa	%xmm10,32(%rsp)
+	vpaddq	64(%rbp),%xmm6,%xmm10
+	vmovdqa	%xmm11,48(%rsp)
+	vpaddq	96(%rbp),%xmm7,%xmm11
+	vmovdqa	%xmm8,64(%rsp)
+	movq	%rax,%r14
+	vmovdqa	%xmm9,80(%rsp)
+	movq	%rbx,%rdi
+	vmovdqa	%xmm10,96(%rsp)
+	xorq	%rcx,%rdi
+	vmovdqa	%xmm11,112(%rsp)
+	movq	%r8,%r13
+	jmp	.Lavx_00_47
+
+.align	16
+.Lavx_00_47:
+	addq	$256,%rbp
+	vpalignr	$8,%xmm0,%xmm1,%xmm8
+	shrdq	$23,%r13,%r13
+	movq	%r14,%rax
+	vpalignr	$8,%xmm4,%xmm5,%xmm11
+	movq	%r9,%r12
+	shrdq	$5,%r14,%r14
+	vpsrlq	$1,%xmm8,%xmm10
+	xorq	%r8,%r13
+	xorq	%r10,%r12
+	vpaddq	%xmm11,%xmm0,%xmm0
+	shrdq	$4,%r13,%r13
+	xorq	%rax,%r14
+	vpsrlq	$7,%xmm8,%xmm11
+	andq	%r8,%r12
+	xorq	%r8,%r13
+	vpsllq	$56,%xmm8,%xmm9
+	addq	0(%rsp),%r11
+	movq	%rax,%r15
+	vpxor	%xmm10,%xmm11,%xmm8
+	xorq	%r10,%r12
+	shrdq	$6,%r14,%r14
+	vpsrlq	$7,%xmm10,%xmm10
+	xorq	%rbx,%r15
+	addq	%r12,%r11
+	vpxor	%xmm9,%xmm8,%xmm8
+	shrdq	$14,%r13,%r13
+	andq	%r15,%rdi
+	vpsllq	$7,%xmm9,%xmm9
+	xorq	%rax,%r14
+	addq	%r13,%r11
+	vpxor	%xmm10,%xmm8,%xmm8
+	xorq	%rbx,%rdi
+	shrdq	$28,%r14,%r14
+	vpsrlq	$6,%xmm7,%xmm11
+	addq	%r11,%rdx
+	addq	%rdi,%r11
+	vpxor	%xmm9,%xmm8,%xmm8
+	movq	%rdx,%r13
+	addq	%r11,%r14
+	vpsllq	$3,%xmm7,%xmm10
+	shrdq	$23,%r13,%r13
+	movq	%r14,%r11
+	vpaddq	%xmm8,%xmm0,%xmm0
+	movq	%r8,%r12
+	shrdq	$5,%r14,%r14
+	vpsrlq	$19,%xmm7,%xmm9
+	xorq	%rdx,%r13
+	xorq	%r9,%r12
+	vpxor	%xmm10,%xmm11,%xmm11
+	shrdq	$4,%r13,%r13
+	xorq	%r11,%r14
+	vpsllq	$42,%xmm10,%xmm10
+	andq	%rdx,%r12
+	xorq	%rdx,%r13
+	vpxor	%xmm9,%xmm11,%xmm11
+	addq	8(%rsp),%r10
+	movq	%r11,%rdi
+	vpsrlq	$42,%xmm9,%xmm9
+	xorq	%r9,%r12
+	shrdq	$6,%r14,%r14
+	vpxor	%xmm10,%xmm11,%xmm11
+	xorq	%rax,%rdi
+	addq	%r12,%r10
+	vpxor	%xmm9,%xmm11,%xmm11
+	shrdq	$14,%r13,%r13
+	andq	%rdi,%r15
+	vpaddq	%xmm11,%xmm0,%xmm0
+	xorq	%r11,%r14
+	addq	%r13,%r10
+	vpaddq	-128(%rbp),%xmm0,%xmm10
+	xorq	%rax,%r15
+	shrdq	$28,%r14,%r14
+	addq	%r10,%rcx
+	addq	%r15,%r10
+	movq	%rcx,%r13
+	addq	%r10,%r14
+	vmovdqa	%xmm10,0(%rsp)
+	vpalignr	$8,%xmm1,%xmm2,%xmm8
+	shrdq	$23,%r13,%r13
+	movq	%r14,%r10
+	vpalignr	$8,%xmm5,%xmm6,%xmm11
+	movq	%rdx,%r12
+	shrdq	$5,%r14,%r14
+	vpsrlq	$1,%xmm8,%xmm10
+	xorq	%rcx,%r13
+	xorq	%r8,%r12
+	vpaddq	%xmm11,%xmm1,%xmm1
+	shrdq	$4,%r13,%r13
+	xorq	%r10,%r14
+	vpsrlq	$7,%xmm8,%xmm11
+	andq	%rcx,%r12
+	xorq	%rcx,%r13
+	vpsllq	$56,%xmm8,%xmm9
+	addq	16(%rsp),%r9
+	movq	%r10,%r15
+	vpxor	%xmm10,%xmm11,%xmm8
+	xorq	%r8,%r12
+	shrdq	$6,%r14,%r14
+	vpsrlq	$7,%xmm10,%xmm10
+	xorq	%r11,%r15
+	addq	%r12,%r9
+	vpxor	%xmm9,%xmm8,%xmm8
+	shrdq	$14,%r13,%r13
+	andq	%r15,%rdi
+	vpsllq	$7,%xmm9,%xmm9
+	xorq	%r10,%r14
+	addq	%r13,%r9
+	vpxor	%xmm10,%xmm8,%xmm8
+	xorq	%r11,%rdi
+	shrdq	$28,%r14,%r14
+	vpsrlq	$6,%xmm0,%xmm11
+	addq	%r9,%rbx
+	addq	%rdi,%r9
+	vpxor	%xmm9,%xmm8,%xmm8
+	movq	%rbx,%r13
+	addq	%r9,%r14
+	vpsllq	$3,%xmm0,%xmm10
+	shrdq	$23,%r13,%r13
+	movq	%r14,%r9
+	vpaddq	%xmm8,%xmm1,%xmm1
+	movq	%rcx,%r12
+	shrdq	$5,%r14,%r14
+	vpsrlq	$19,%xmm0,%xmm9
+	xorq	%rbx,%r13
+	xorq	%rdx,%r12
+	vpxor	%xmm10,%xmm11,%xmm11
+	shrdq	$4,%r13,%r13
+	xorq	%r9,%r14
+	vpsllq	$42,%xmm10,%xmm10
+	andq	%rbx,%r12
+	xorq	%rbx,%r13
+	vpxor	%xmm9,%xmm11,%xmm11
+	addq	24(%rsp),%r8
+	movq	%r9,%rdi
+	vpsrlq	$42,%xmm9,%xmm9
+	xorq	%rdx,%r12
+	shrdq	$6,%r14,%r14
+	vpxor	%xmm10,%xmm11,%xmm11
+	xorq	%r10,%rdi
+	addq	%r12,%r8
+	vpxor	%xmm9,%xmm11,%xmm11
+	shrdq	$14,%r13,%r13
+	andq	%rdi,%r15
+	vpaddq	%xmm11,%xmm1,%xmm1
+	xorq	%r9,%r14
+	addq	%r13,%r8
+	vpaddq	-96(%rbp),%xmm1,%xmm10
+	xorq	%r10,%r15
+	shrdq	$28,%r14,%r14
+	addq	%r8,%rax
+	addq	%r15,%r8
+	movq	%rax,%r13
+	addq	%r8,%r14
+	vmovdqa	%xmm10,16(%rsp)
+	vpalignr	$8,%xmm2,%xmm3,%xmm8
+	shrdq	$23,%r13,%r13
+	movq	%r14,%r8
+	vpalignr	$8,%xmm6,%xmm7,%xmm11
+	movq	%rbx,%r12
+	shrdq	$5,%r14,%r14
+	vpsrlq	$1,%xmm8,%xmm10
+	xorq	%rax,%r13
+	xorq	%rcx,%r12
+	vpaddq	%xmm11,%xmm2,%xmm2
+	shrdq	$4,%r13,%r13
+	xorq	%r8,%r14
+	vpsrlq	$7,%xmm8,%xmm11
+	andq	%rax,%r12
+	xorq	%rax,%r13
+	vpsllq	$56,%xmm8,%xmm9
+	addq	32(%rsp),%rdx
+	movq	%r8,%r15
+	vpxor	%xmm10,%xmm11,%xmm8
+	xorq	%rcx,%r12
+	shrdq	$6,%r14,%r14
+	vpsrlq	$7,%xmm10,%xmm10
+	xorq	%r9,%r15
+	addq	%r12,%rdx
+	vpxor	%xmm9,%xmm8,%xmm8
+	shrdq	$14,%r13,%r13
+	andq	%r15,%rdi
+	vpsllq	$7,%xmm9,%xmm9
+	xorq	%r8,%r14
+	addq	%r13,%rdx
+	vpxor	%xmm10,%xmm8,%xmm8
+	xorq	%r9,%rdi
+	shrdq	$28,%r14,%r14
+	vpsrlq	$6,%xmm1,%xmm11
+	addq	%rdx,%r11
+	addq	%rdi,%rdx
+	vpxor	%xmm9,%xmm8,%xmm8
+	movq	%r11,%r13
+	addq	%rdx,%r14
+	vpsllq	$3,%xmm1,%xmm10
+	shrdq	$23,%r13,%r13
+	movq	%r14,%rdx
+	vpaddq	%xmm8,%xmm2,%xmm2
+	movq	%rax,%r12
+	shrdq	$5,%r14,%r14
+	vpsrlq	$19,%xmm1,%xmm9
+	xorq	%r11,%r13
+	xorq	%rbx,%r12
+	vpxor	%xmm10,%xmm11,%xmm11
+	shrdq	$4,%r13,%r13
+	xorq	%rdx,%r14
+	vpsllq	$42,%xmm10,%xmm10
+	andq	%r11,%r12
+	xorq	%r11,%r13
+	vpxor	%xmm9,%xmm11,%xmm11
+	addq	40(%rsp),%rcx
+	movq	%rdx,%rdi
+	vpsrlq	$42,%xmm9,%xmm9
+	xorq	%rbx,%r12
+	shrdq	$6,%r14,%r14
+	vpxor	%xmm10,%xmm11,%xmm11
+	xorq	%r8,%rdi
+	addq	%r12,%rcx
+	vpxor	%xmm9,%xmm11,%xmm11
+	shrdq	$14,%r13,%r13
+	andq	%rdi,%r15
+	vpaddq	%xmm11,%xmm2,%xmm2
+	xorq	%rdx,%r14
+	addq	%r13,%rcx
+	vpaddq	-64(%rbp),%xmm2,%xmm10
+	xorq	%r8,%r15
+	shrdq	$28,%r14,%r14
+	addq	%rcx,%r10
+	addq	%r15,%rcx
+	movq	%r10,%r13
+	addq	%rcx,%r14
+	vmovdqa	%xmm10,32(%rsp)
+	vpalignr	$8,%xmm3,%xmm4,%xmm8
+	shrdq	$23,%r13,%r13
+	movq	%r14,%rcx
+	vpalignr	$8,%xmm7,%xmm0,%xmm11
+	movq	%r11,%r12
+	shrdq	$5,%r14,%r14
+	vpsrlq	$1,%xmm8,%xmm10
+	xorq	%r10,%r13
+	xorq	%rax,%r12
+	vpaddq	%xmm11,%xmm3,%xmm3
+	shrdq	$4,%r13,%r13
+	xorq	%rcx,%r14
+	vpsrlq	$7,%xmm8,%xmm11
+	andq	%r10,%r12
+	xorq	%r10,%r13
+	vpsllq	$56,%xmm8,%xmm9
+	addq	48(%rsp),%rbx
+	movq	%rcx,%r15
+	vpxor	%xmm10,%xmm11,%xmm8
+	xorq	%rax,%r12
+	shrdq	$6,%r14,%r14
+	vpsrlq	$7,%xmm10,%xmm10
+	xorq	%rdx,%r15
+	addq	%r12,%rbx
+	vpxor	%xmm9,%xmm8,%xmm8
+	shrdq	$14,%r13,%r13
+	andq	%r15,%rdi
+	vpsllq	$7,%xmm9,%xmm9
+	xorq	%rcx,%r14
+	addq	%r13,%rbx
+	vpxor	%xmm10,%xmm8,%xmm8
+	xorq	%rdx,%rdi
+	shrdq	$28,%r14,%r14
+	vpsrlq	$6,%xmm2,%xmm11
+	addq	%rbx,%r9
+	addq	%rdi,%rbx
+	vpxor	%xmm9,%xmm8,%xmm8
+	movq	%r9,%r13
+	addq	%rbx,%r14
+	vpsllq	$3,%xmm2,%xmm10
+	shrdq	$23,%r13,%r13
+	movq	%r14,%rbx
+	vpaddq	%xmm8,%xmm3,%xmm3
+	movq	%r10,%r12
+	shrdq	$5,%r14,%r14
+	vpsrlq	$19,%xmm2,%xmm9
+	xorq	%r9,%r13
+	xorq	%r11,%r12
+	vpxor	%xmm10,%xmm11,%xmm11
+	shrdq	$4,%r13,%r13
+	xorq	%rbx,%r14
+	vpsllq	$42,%xmm10,%xmm10
+	andq	%r9,%r12
+	xorq	%r9,%r13
+	vpxor	%xmm9,%xmm11,%xmm11
+	addq	56(%rsp),%rax
+	movq	%rbx,%rdi
+	vpsrlq	$42,%xmm9,%xmm9
+	xorq	%r11,%r12
+	shrdq	$6,%r14,%r14
+	vpxor	%xmm10,%xmm11,%xmm11
+	xorq	%rcx,%rdi
+	addq	%r12,%rax
+	vpxor	%xmm9,%xmm11,%xmm11
+	shrdq	$14,%r13,%r13
+	andq	%rdi,%r15
+	vpaddq	%xmm11,%xmm3,%xmm3
+	xorq	%rbx,%r14
+	addq	%r13,%rax
+	vpaddq	-32(%rbp),%xmm3,%xmm10
+	xorq	%rcx,%r15
+	shrdq	$28,%r14,%r14
+	addq	%rax,%r8
+	addq	%r15,%rax
+	movq	%r8,%r13
+	addq	%rax,%r14
+	vmovdqa	%xmm10,48(%rsp)
+	vpalignr	$8,%xmm4,%xmm5,%xmm8
+	shrdq	$23,%r13,%r13
+	movq	%r14,%rax
+	vpalignr	$8,%xmm0,%xmm1,%xmm11
+	movq	%r9,%r12
+	shrdq	$5,%r14,%r14
+	vpsrlq	$1,%xmm8,%xmm10
+	xorq	%r8,%r13
+	xorq	%r10,%r12
+	vpaddq	%xmm11,%xmm4,%xmm4
+	shrdq	$4,%r13,%r13
+	xorq	%rax,%r14
+	vpsrlq	$7,%xmm8,%xmm11
+	andq	%r8,%r12
+	xorq	%r8,%r13
+	vpsllq	$56,%xmm8,%xmm9
+	addq	64(%rsp),%r11
+	movq	%rax,%r15
+	vpxor	%xmm10,%xmm11,%xmm8
+	xorq	%r10,%r12
+	shrdq	$6,%r14,%r14
+	vpsrlq	$7,%xmm10,%xmm10
+	xorq	%rbx,%r15
+	addq	%r12,%r11
+	vpxor	%xmm9,%xmm8,%xmm8
+	shrdq	$14,%r13,%r13
+	andq	%r15,%rdi
+	vpsllq	$7,%xmm9,%xmm9
+	xorq	%rax,%r14
+	addq	%r13,%r11
+	vpxor	%xmm10,%xmm8,%xmm8
+	xorq	%rbx,%rdi
+	shrdq	$28,%r14,%r14
+	vpsrlq	$6,%xmm3,%xmm11
+	addq	%r11,%rdx
+	addq	%rdi,%r11
+	vpxor	%xmm9,%xmm8,%xmm8
+	movq	%rdx,%r13
+	addq	%r11,%r14
+	vpsllq	$3,%xmm3,%xmm10
+	shrdq	$23,%r13,%r13
+	movq	%r14,%r11
+	vpaddq	%xmm8,%xmm4,%xmm4
+	movq	%r8,%r12
+	shrdq	$5,%r14,%r14
+	vpsrlq	$19,%xmm3,%xmm9
+	xorq	%rdx,%r13
+	xorq	%r9,%r12
+	vpxor	%xmm10,%xmm11,%xmm11
+	shrdq	$4,%r13,%r13
+	xorq	%r11,%r14
+	vpsllq	$42,%xmm10,%xmm10
+	andq	%rdx,%r12
+	xorq	%rdx,%r13
+	vpxor	%xmm9,%xmm11,%xmm11
+	addq	72(%rsp),%r10
+	movq	%r11,%rdi
+	vpsrlq	$42,%xmm9,%xmm9
+	xorq	%r9,%r12
+	shrdq	$6,%r14,%r14
+	vpxor	%xmm10,%xmm11,%xmm11
+	xorq	%rax,%rdi
+	addq	%r12,%r10
+	vpxor	%xmm9,%xmm11,%xmm11
+	shrdq	$14,%r13,%r13
+	andq	%rdi,%r15
+	vpaddq	%xmm11,%xmm4,%xmm4
+	xorq	%r11,%r14
+	addq	%r13,%r10
+	vpaddq	0(%rbp),%xmm4,%xmm10
+	xorq	%rax,%r15
+	shrdq	$28,%r14,%r14
+	addq	%r10,%rcx
+	addq	%r15,%r10
+	movq	%rcx,%r13
+	addq	%r10,%r14
+	vmovdqa	%xmm10,64(%rsp)
+	vpalignr	$8,%xmm5,%xmm6,%xmm8
+	shrdq	$23,%r13,%r13
+	movq	%r14,%r10
+	vpalignr	$8,%xmm1,%xmm2,%xmm11
+	movq	%rdx,%r12
+	shrdq	$5,%r14,%r14
+	vpsrlq	$1,%xmm8,%xmm10
+	xorq	%rcx,%r13
+	xorq	%r8,%r12
+	vpaddq	%xmm11,%xmm5,%xmm5
+	shrdq	$4,%r13,%r13
+	xorq	%r10,%r14
+	vpsrlq	$7,%xmm8,%xmm11
+	andq	%rcx,%r12
+	xorq	%rcx,%r13
+	vpsllq	$56,%xmm8,%xmm9
+	addq	80(%rsp),%r9
+	movq	%r10,%r15
+	vpxor	%xmm10,%xmm11,%xmm8
+	xorq	%r8,%r12
+	shrdq	$6,%r14,%r14
+	vpsrlq	$7,%xmm10,%xmm10
+	xorq	%r11,%r15
+	addq	%r12,%r9
+	vpxor	%xmm9,%xmm8,%xmm8
+	shrdq	$14,%r13,%r13
+	andq	%r15,%rdi
+	vpsllq	$7,%xmm9,%xmm9
+	xorq	%r10,%r14
+	addq	%r13,%r9
+	vpxor	%xmm10,%xmm8,%xmm8
+	xorq	%r11,%rdi
+	shrdq	$28,%r14,%r14
+	vpsrlq	$6,%xmm4,%xmm11
+	addq	%r9,%rbx
+	addq	%rdi,%r9
+	vpxor	%xmm9,%xmm8,%xmm8
+	movq	%rbx,%r13
+	addq	%r9,%r14
+	vpsllq	$3,%xmm4,%xmm10
+	shrdq	$23,%r13,%r13
+	movq	%r14,%r9
+	vpaddq	%xmm8,%xmm5,%xmm5
+	movq	%rcx,%r12
+	shrdq	$5,%r14,%r14
+	vpsrlq	$19,%xmm4,%xmm9
+	xorq	%rbx,%r13
+	xorq	%rdx,%r12
+	vpxor	%xmm10,%xmm11,%xmm11
+	shrdq	$4,%r13,%r13
+	xorq	%r9,%r14
+	vpsllq	$42,%xmm10,%xmm10
+	andq	%rbx,%r12
+	xorq	%rbx,%r13
+	vpxor	%xmm9,%xmm11,%xmm11
+	addq	88(%rsp),%r8
+	movq	%r9,%rdi
+	vpsrlq	$42,%xmm9,%xmm9
+	xorq	%rdx,%r12
+	shrdq	$6,%r14,%r14
+	vpxor	%xmm10,%xmm11,%xmm11
+	xorq	%r10,%rdi
+	addq	%r12,%r8
+	vpxor	%xmm9,%xmm11,%xmm11
+	shrdq	$14,%r13,%r13
+	andq	%rdi,%r15
+	vpaddq	%xmm11,%xmm5,%xmm5
+	xorq	%r9,%r14
+	addq	%r13,%r8
+	vpaddq	32(%rbp),%xmm5,%xmm10
+	xorq	%r10,%r15
+	shrdq	$28,%r14,%r14
+	addq	%r8,%rax
+	addq	%r15,%r8
+	movq	%rax,%r13
+	addq	%r8,%r14
+	vmovdqa	%xmm10,80(%rsp)
+	vpalignr	$8,%xmm6,%xmm7,%xmm8
+	shrdq	$23,%r13,%r13
+	movq	%r14,%r8
+	vpalignr	$8,%xmm2,%xmm3,%xmm11
+	movq	%rbx,%r12
+	shrdq	$5,%r14,%r14
+	vpsrlq	$1,%xmm8,%xmm10
+	xorq	%rax,%r13
+	xorq	%rcx,%r12
+	vpaddq	%xmm11,%xmm6,%xmm6
+	shrdq	$4,%r13,%r13
+	xorq	%r8,%r14
+	vpsrlq	$7,%xmm8,%xmm11
+	andq	%rax,%r12
+	xorq	%rax,%r13
+	vpsllq	$56,%xmm8,%xmm9
+	addq	96(%rsp),%rdx
+	movq	%r8,%r15
+	vpxor	%xmm10,%xmm11,%xmm8
+	xorq	%rcx,%r12
+	shrdq	$6,%r14,%r14
+	vpsrlq	$7,%xmm10,%xmm10
+	xorq	%r9,%r15
+	addq	%r12,%rdx
+	vpxor	%xmm9,%xmm8,%xmm8
+	shrdq	$14,%r13,%r13
+	andq	%r15,%rdi
+	vpsllq	$7,%xmm9,%xmm9
+	xorq	%r8,%r14
+	addq	%r13,%rdx
+	vpxor	%xmm10,%xmm8,%xmm8
+	xorq	%r9,%rdi
+	shrdq	$28,%r14,%r14
+	vpsrlq	$6,%xmm5,%xmm11
+	addq	%rdx,%r11
+	addq	%rdi,%rdx
+	vpxor	%xmm9,%xmm8,%xmm8
+	movq	%r11,%r13
+	addq	%rdx,%r14
+	vpsllq	$3,%xmm5,%xmm10
+	shrdq	$23,%r13,%r13
+	movq	%r14,%rdx
+	vpaddq	%xmm8,%xmm6,%xmm6
+	movq	%rax,%r12
+	shrdq	$5,%r14,%r14
+	vpsrlq	$19,%xmm5,%xmm9
+	xorq	%r11,%r13
+	xorq	%rbx,%r12
+	vpxor	%xmm10,%xmm11,%xmm11
+	shrdq	$4,%r13,%r13
+	xorq	%rdx,%r14
+	vpsllq	$42,%xmm10,%xmm10
+	andq	%r11,%r12
+	xorq	%r11,%r13
+	vpxor	%xmm9,%xmm11,%xmm11
+	addq	104(%rsp),%rcx
+	movq	%rdx,%rdi
+	vpsrlq	$42,%xmm9,%xmm9
+	xorq	%rbx,%r12
+	shrdq	$6,%r14,%r14
+	vpxor	%xmm10,%xmm11,%xmm11
+	xorq	%r8,%rdi
+	addq	%r12,%rcx
+	vpxor	%xmm9,%xmm11,%xmm11
+	shrdq	$14,%r13,%r13
+	andq	%rdi,%r15
+	vpaddq	%xmm11,%xmm6,%xmm6
+	xorq	%rdx,%r14
+	addq	%r13,%rcx
+	vpaddq	64(%rbp),%xmm6,%xmm10
+	xorq	%r8,%r15
+	shrdq	$28,%r14,%r14
+	addq	%rcx,%r10
+	addq	%r15,%rcx
+	movq	%r10,%r13
+	addq	%rcx,%r14
+	vmovdqa	%xmm10,96(%rsp)
+	vpalignr	$8,%xmm7,%xmm0,%xmm8
+	shrdq	$23,%r13,%r13
+	movq	%r14,%rcx
+	vpalignr	$8,%xmm3,%xmm4,%xmm11
+	movq	%r11,%r12
+	shrdq	$5,%r14,%r14
+	vpsrlq	$1,%xmm8,%xmm10
+	xorq	%r10,%r13
+	xorq	%rax,%r12
+	vpaddq	%xmm11,%xmm7,%xmm7
+	shrdq	$4,%r13,%r13
+	xorq	%rcx,%r14
+	vpsrlq	$7,%xmm8,%xmm11
+	andq	%r10,%r12
+	xorq	%r10,%r13
+	vpsllq	$56,%xmm8,%xmm9
+	addq	112(%rsp),%rbx
+	movq	%rcx,%r15
+	vpxor	%xmm10,%xmm11,%xmm8
+	xorq	%rax,%r12
+	shrdq	$6,%r14,%r14
+	vpsrlq	$7,%xmm10,%xmm10
+	xorq	%rdx,%r15
+	addq	%r12,%rbx
+	vpxor	%xmm9,%xmm8,%xmm8
+	shrdq	$14,%r13,%r13
+	andq	%r15,%rdi
+	vpsllq	$7,%xmm9,%xmm9
+	xorq	%rcx,%r14
+	addq	%r13,%rbx
+	vpxor	%xmm10,%xmm8,%xmm8
+	xorq	%rdx,%rdi
+	shrdq	$28,%r14,%r14
+	vpsrlq	$6,%xmm6,%xmm11
+	addq	%rbx,%r9
+	addq	%rdi,%rbx
+	vpxor	%xmm9,%xmm8,%xmm8
+	movq	%r9,%r13
+	addq	%rbx,%r14
+	vpsllq	$3,%xmm6,%xmm10
+	shrdq	$23,%r13,%r13
+	movq	%r14,%rbx
+	vpaddq	%xmm8,%xmm7,%xmm7
+	movq	%r10,%r12
+	shrdq	$5,%r14,%r14
+	vpsrlq	$19,%xmm6,%xmm9
+	xorq	%r9,%r13
+	xorq	%r11,%r12
+	vpxor	%xmm10,%xmm11,%xmm11
+	shrdq	$4,%r13,%r13
+	xorq	%rbx,%r14
+	vpsllq	$42,%xmm10,%xmm10
+	andq	%r9,%r12
+	xorq	%r9,%r13
+	vpxor	%xmm9,%xmm11,%xmm11
+	addq	120(%rsp),%rax
+	movq	%rbx,%rdi
+	vpsrlq	$42,%xmm9,%xmm9
+	xorq	%r11,%r12
+	shrdq	$6,%r14,%r14
+	vpxor	%xmm10,%xmm11,%xmm11
+	xorq	%rcx,%rdi
+	addq	%r12,%rax
+	vpxor	%xmm9,%xmm11,%xmm11
+	shrdq	$14,%r13,%r13
+	andq	%rdi,%r15
+	vpaddq	%xmm11,%xmm7,%xmm7
+	xorq	%rbx,%r14
+	addq	%r13,%rax
+	vpaddq	96(%rbp),%xmm7,%xmm10
+	xorq	%rcx,%r15
+	shrdq	$28,%r14,%r14
+	addq	%rax,%r8
+	addq	%r15,%rax
+	movq	%r8,%r13
+	addq	%rax,%r14
+	vmovdqa	%xmm10,112(%rsp)
+	cmpb	$0,135(%rbp)
+	jne	.Lavx_00_47
+	shrdq	$23,%r13,%r13
+	movq	%r14,%rax
+	movq	%r9,%r12
+	shrdq	$5,%r14,%r14
+	xorq	%r8,%r13
+	xorq	%r10,%r12
+	shrdq	$4,%r13,%r13
+	xorq	%rax,%r14
+	andq	%r8,%r12
+	xorq	%r8,%r13
+	addq	0(%rsp),%r11
+	movq	%rax,%r15
+	xorq	%r10,%r12
+	shrdq	$6,%r14,%r14
+	xorq	%rbx,%r15
+	addq	%r12,%r11
+	shrdq	$14,%r13,%r13
+	andq	%r15,%rdi
+	xorq	%rax,%r14
+	addq	%r13,%r11
+	xorq	%rbx,%rdi
+	shrdq	$28,%r14,%r14
+	addq	%r11,%rdx
+	addq	%rdi,%r11
+	movq	%rdx,%r13
+	addq	%r11,%r14
+	shrdq	$23,%r13,%r13
+	movq	%r14,%r11
+	movq	%r8,%r12
+	shrdq	$5,%r14,%r14
+	xorq	%rdx,%r13
+	xorq	%r9,%r12
+	shrdq	$4,%r13,%r13
+	xorq	%r11,%r14
+	andq	%rdx,%r12
+	xorq	%rdx,%r13
+	addq	8(%rsp),%r10
+	movq	%r11,%rdi
+	xorq	%r9,%r12
+	shrdq	$6,%r14,%r14
+	xorq	%rax,%rdi
+	addq	%r12,%r10
+	shrdq	$14,%r13,%r13
+	andq	%rdi,%r15
+	xorq	%r11,%r14
+	addq	%r13,%r10
+	xorq	%rax,%r15
+	shrdq	$28,%r14,%r14
+	addq	%r10,%rcx
+	addq	%r15,%r10
+	movq	%rcx,%r13
+	addq	%r10,%r14
+	shrdq	$23,%r13,%r13
+	movq	%r14,%r10
+	movq	%rdx,%r12
+	shrdq	$5,%r14,%r14
+	xorq	%rcx,%r13
+	xorq	%r8,%r12
+	shrdq	$4,%r13,%r13
+	xorq	%r10,%r14
+	andq	%rcx,%r12
+	xorq	%rcx,%r13
+	addq	16(%rsp),%r9
+	movq	%r10,%r15
+	xorq	%r8,%r12
+	shrdq	$6,%r14,%r14
+	xorq	%r11,%r15
+	addq	%r12,%r9
+	shrdq	$14,%r13,%r13
+	andq	%r15,%rdi
+	xorq	%r10,%r14
+	addq	%r13,%r9
+	xorq	%r11,%rdi
+	shrdq	$28,%r14,%r14
+	addq	%r9,%rbx
+	addq	%rdi,%r9
+	movq	%rbx,%r13
+	addq	%r9,%r14
+	shrdq	$23,%r13,%r13
+	movq	%r14,%r9
+	movq	%rcx,%r12
+	shrdq	$5,%r14,%r14
+	xorq	%rbx,%r13
+	xorq	%rdx,%r12
+	shrdq	$4,%r13,%r13
+	xorq	%r9,%r14
+	andq	%rbx,%r12
+	xorq	%rbx,%r13
+	addq	24(%rsp),%r8
+	movq	%r9,%rdi
+	xorq	%rdx,%r12
+	shrdq	$6,%r14,%r14
+	xorq	%r10,%rdi
+	addq	%r12,%r8
+	shrdq	$14,%r13,%r13
+	andq	%rdi,%r15
+	xorq	%r9,%r14
+	addq	%r13,%r8
+	xorq	%r10,%r15
+	shrdq	$28,%r14,%r14
+	addq	%r8,%rax
+	addq	%r15,%r8
+	movq	%rax,%r13
+	addq	%r8,%r14
+	shrdq	$23,%r13,%r13
+	movq	%r14,%r8
+	movq	%rbx,%r12
+	shrdq	$5,%r14,%r14
+	xorq	%rax,%r13
+	xorq	%rcx,%r12
+	shrdq	$4,%r13,%r13
+	xorq	%r8,%r14
+	andq	%rax,%r12
+	xorq	%rax,%r13
+	addq	32(%rsp),%rdx
+	movq	%r8,%r15
+	xorq	%rcx,%r12
+	shrdq	$6,%r14,%r14
+	xorq	%r9,%r15
+	addq	%r12,%rdx
+	shrdq	$14,%r13,%r13
+	andq	%r15,%rdi
+	xorq	%r8,%r14
+	addq	%r13,%rdx
+	xorq	%r9,%rdi
+	shrdq	$28,%r14,%r14
+	addq	%rdx,%r11
+	addq	%rdi,%rdx
+	movq	%r11,%r13
+	addq	%rdx,%r14
+	shrdq	$23,%r13,%r13
+	movq	%r14,%rdx
+	movq	%rax,%r12
+	shrdq	$5,%r14,%r14
+	xorq	%r11,%r13
+	xorq	%rbx,%r12
+	shrdq	$4,%r13,%r13
+	xorq	%rdx,%r14
+	andq	%r11,%r12
+	xorq	%r11,%r13
+	addq	40(%rsp),%rcx
+	movq	%rdx,%rdi
+	xorq	%rbx,%r12
+	shrdq	$6,%r14,%r14
+	xorq	%r8,%rdi
+	addq	%r12,%rcx
+	shrdq	$14,%r13,%r13
+	andq	%rdi,%r15
+	xorq	%rdx,%r14
+	addq	%r13,%rcx
+	xorq	%r8,%r15
+	shrdq	$28,%r14,%r14
+	addq	%rcx,%r10
+	addq	%r15,%rcx
+	movq	%r10,%r13
+	addq	%rcx,%r14
+	shrdq	$23,%r13,%r13
+	movq	%r14,%rcx
+	movq	%r11,%r12
+	shrdq	$5,%r14,%r14
+	xorq	%r10,%r13
+	xorq	%rax,%r12
+	shrdq	$4,%r13,%r13
+	xorq	%rcx,%r14
+	andq	%r10,%r12
+	xorq	%r10,%r13
+	addq	48(%rsp),%rbx
+	movq	%rcx,%r15
+	xorq	%rax,%r12
+	shrdq	$6,%r14,%r14
+	xorq	%rdx,%r15
+	addq	%r12,%rbx
+	shrdq	$14,%r13,%r13
+	andq	%r15,%rdi
+	xorq	%rcx,%r14
+	addq	%r13,%rbx
+	xorq	%rdx,%rdi
+	shrdq	$28,%r14,%r14
+	addq	%rbx,%r9
+	addq	%rdi,%rbx
+	movq	%r9,%r13
+	addq	%rbx,%r14
+	shrdq	$23,%r13,%r13
+	movq	%r14,%rbx
+	movq	%r10,%r12
+	shrdq	$5,%r14,%r14
+	xorq	%r9,%r13
+	xorq	%r11,%r12
+	shrdq	$4,%r13,%r13
+	xorq	%rbx,%r14
+	andq	%r9,%r12
+	xorq	%r9,%r13
+	addq	56(%rsp),%rax
+	movq	%rbx,%rdi
+	xorq	%r11,%r12
+	shrdq	$6,%r14,%r14
+	xorq	%rcx,%rdi
+	addq	%r12,%rax
+	shrdq	$14,%r13,%r13
+	andq	%rdi,%r15
+	xorq	%rbx,%r14
+	addq	%r13,%rax
+	xorq	%rcx,%r15
+	shrdq	$28,%r14,%r14
+	addq	%rax,%r8
+	addq	%r15,%rax
+	movq	%r8,%r13
+	addq	%rax,%r14
+	shrdq	$23,%r13,%r13
+	movq	%r14,%rax
+	movq	%r9,%r12
+	shrdq	$5,%r14,%r14
+	xorq	%r8,%r13
+	xorq	%r10,%r12
+	shrdq	$4,%r13,%r13
+	xorq	%rax,%r14
+	andq	%r8,%r12
+	xorq	%r8,%r13
+	addq	64(%rsp),%r11
+	movq	%rax,%r15
+	xorq	%r10,%r12
+	shrdq	$6,%r14,%r14
+	xorq	%rbx,%r15
+	addq	%r12,%r11
+	shrdq	$14,%r13,%r13
+	andq	%r15,%rdi
+	xorq	%rax,%r14
+	addq	%r13,%r11
+	xorq	%rbx,%rdi
+	shrdq	$28,%r14,%r14
+	addq	%r11,%rdx
+	addq	%rdi,%r11
+	movq	%rdx,%r13
+	addq	%r11,%r14
+	shrdq	$23,%r13,%r13
+	movq	%r14,%r11
+	movq	%r8,%r12
+	shrdq	$5,%r14,%r14
+	xorq	%rdx,%r13
+	xorq	%r9,%r12
+	shrdq	$4,%r13,%r13
+	xorq	%r11,%r14
+	andq	%rdx,%r12
+	xorq	%rdx,%r13
+	addq	72(%rsp),%r10
+	movq	%r11,%rdi
+	xorq	%r9,%r12
+	shrdq	$6,%r14,%r14
+	xorq	%rax,%rdi
+	addq	%r12,%r10
+	shrdq	$14,%r13,%r13
+	andq	%rdi,%r15
+	xorq	%r11,%r14
+	addq	%r13,%r10
+	xorq	%rax,%r15
+	shrdq	$28,%r14,%r14
+	addq	%r10,%rcx
+	addq	%r15,%r10
+	movq	%rcx,%r13
+	addq	%r10,%r14
+	shrdq	$23,%r13,%r13
+	movq	%r14,%r10
+	movq	%rdx,%r12
+	shrdq	$5,%r14,%r14
+	xorq	%rcx,%r13
+	xorq	%r8,%r12
+	shrdq	$4,%r13,%r13
+	xorq	%r10,%r14
+	andq	%rcx,%r12
+	xorq	%rcx,%r13
+	addq	80(%rsp),%r9
+	movq	%r10,%r15
+	xorq	%r8,%r12
+	shrdq	$6,%r14,%r14
+	xorq	%r11,%r15
+	addq	%r12,%r9
+	shrdq	$14,%r13,%r13
+	andq	%r15,%rdi
+	xorq	%r10,%r14
+	addq	%r13,%r9
+	xorq	%r11,%rdi
+	shrdq	$28,%r14,%r14
+	addq	%r9,%rbx
+	addq	%rdi,%r9
+	movq	%rbx,%r13
+	addq	%r9,%r14
+	shrdq	$23,%r13,%r13
+	movq	%r14,%r9
+	movq	%rcx,%r12
+	shrdq	$5,%r14,%r14
+	xorq	%rbx,%r13
+	xorq	%rdx,%r12
+	shrdq	$4,%r13,%r13
+	xorq	%r9,%r14
+	andq	%rbx,%r12
+	xorq	%rbx,%r13
+	addq	88(%rsp),%r8
+	movq	%r9,%rdi
+	xorq	%rdx,%r12
+	shrdq	$6,%r14,%r14
+	xorq	%r10,%rdi
+	addq	%r12,%r8
+	shrdq	$14,%r13,%r13
+	andq	%rdi,%r15
+	xorq	%r9,%r14
+	addq	%r13,%r8
+	xorq	%r10,%r15
+	shrdq	$28,%r14,%r14
+	addq	%r8,%rax
+	addq	%r15,%r8
+	movq	%rax,%r13
+	addq	%r8,%r14
+	shrdq	$23,%r13,%r13
+	movq	%r14,%r8
+	movq	%rbx,%r12
+	shrdq	$5,%r14,%r14
+	xorq	%rax,%r13
+	xorq	%rcx,%r12
+	shrdq	$4,%r13,%r13
+	xorq	%r8,%r14
+	andq	%rax,%r12
+	xorq	%rax,%r13
+	addq	96(%rsp),%rdx
+	movq	%r8,%r15
+	xorq	%rcx,%r12
+	shrdq	$6,%r14,%r14
+	xorq	%r9,%r15
+	addq	%r12,%rdx
+	shrdq	$14,%r13,%r13
+	andq	%r15,%rdi
+	xorq	%r8,%r14
+	addq	%r13,%rdx
+	xorq	%r9,%rdi
+	shrdq	$28,%r14,%r14
+	addq	%rdx,%r11
+	addq	%rdi,%rdx
+	movq	%r11,%r13
+	addq	%rdx,%r14
+	shrdq	$23,%r13,%r13
+	movq	%r14,%rdx
+	movq	%rax,%r12
+	shrdq	$5,%r14,%r14
+	xorq	%r11,%r13
+	xorq	%rbx,%r12
+	shrdq	$4,%r13,%r13
+	xorq	%rdx,%r14
+	andq	%r11,%r12
+	xorq	%r11,%r13
+	addq	104(%rsp),%rcx
+	movq	%rdx,%rdi
+	xorq	%rbx,%r12
+	shrdq	$6,%r14,%r14
+	xorq	%r8,%rdi
+	addq	%r12,%rcx
+	shrdq	$14,%r13,%r13
+	andq	%rdi,%r15
+	xorq	%rdx,%r14
+	addq	%r13,%rcx
+	xorq	%r8,%r15
+	shrdq	$28,%r14,%r14
+	addq	%rcx,%r10
+	addq	%r15,%rcx
+	movq	%r10,%r13
+	addq	%rcx,%r14
+	shrdq	$23,%r13,%r13
+	movq	%r14,%rcx
+	movq	%r11,%r12
+	shrdq	$5,%r14,%r14
+	xorq	%r10,%r13
+	xorq	%rax,%r12
+	shrdq	$4,%r13,%r13
+	xorq	%rcx,%r14
+	andq	%r10,%r12
+	xorq	%r10,%r13
+	addq	112(%rsp),%rbx
+	movq	%rcx,%r15
+	xorq	%rax,%r12
+	shrdq	$6,%r14,%r14
+	xorq	%rdx,%r15
+	addq	%r12,%rbx
+	shrdq	$14,%r13,%r13
+	andq	%r15,%rdi
+	xorq	%rcx,%r14
+	addq	%r13,%rbx
+	xorq	%rdx,%rdi
+	shrdq	$28,%r14,%r14
+	addq	%rbx,%r9
+	addq	%rdi,%rbx
+	movq	%r9,%r13
+	addq	%rbx,%r14
+	shrdq	$23,%r13,%r13
+	movq	%r14,%rbx
+	movq	%r10,%r12
+	shrdq	$5,%r14,%r14
+	xorq	%r9,%r13
+	xorq	%r11,%r12
+	shrdq	$4,%r13,%r13
+	xorq	%rbx,%r14
+	andq	%r9,%r12
+	xorq	%r9,%r13
+	addq	120(%rsp),%rax
+	movq	%rbx,%rdi
+	xorq	%r11,%r12
+	shrdq	$6,%r14,%r14
+	xorq	%rcx,%rdi
+	addq	%r12,%rax
+	shrdq	$14,%r13,%r13
+	andq	%rdi,%r15
+	xorq	%rbx,%r14
+	addq	%r13,%rax
+	xorq	%rcx,%r15
+	shrdq	$28,%r14,%r14
+	addq	%rax,%r8
+	addq	%r15,%rax
+	movq	%r8,%r13
+	addq	%rax,%r14
+	movq	128+0(%rsp),%rdi
+	movq	%r14,%rax
+
+	addq	0(%rdi),%rax
+	leaq	128(%rsi),%rsi
+	addq	8(%rdi),%rbx
+	addq	16(%rdi),%rcx
+	addq	24(%rdi),%rdx
+	addq	32(%rdi),%r8
+	addq	40(%rdi),%r9
+	addq	48(%rdi),%r10
+	addq	56(%rdi),%r11
+
+	cmpq	128+16(%rsp),%rsi
+
+	movq	%rax,0(%rdi)
+	movq	%rbx,8(%rdi)
+	movq	%rcx,16(%rdi)
+	movq	%rdx,24(%rdi)
+	movq	%r8,32(%rdi)
+	movq	%r9,40(%rdi)
+	movq	%r10,48(%rdi)
+	movq	%r11,56(%rdi)
+	jb	.Lloop_avx
+
+	movq	128+24(%rsp),%rsi
+	vzeroupper
+	movq	(%rsi),%r15
+	movq	8(%rsi),%r14
+	movq	16(%rsi),%r13
+	movq	24(%rsi),%r12
+	movq	32(%rsi),%rbp
+	movq	40(%rsi),%rbx
+	leaq	48(%rsi),%rsp
+.Lepilogue_avx:
+	.byte	0xf3,0xc3
+.size	sha512_block_data_order_avx,.-sha512_block_data_order_avx
 #endif
diff --git a/packager/third_party/boringssl/mac-x86/crypto/chacha/chacha-x86.S b/packager/third_party/boringssl/mac-x86/crypto/chacha/chacha-x86.S
new file mode 100644
index 0000000000..5de98a3d61
--- /dev/null
+++ b/packager/third_party/boringssl/mac-x86/crypto/chacha/chacha-x86.S
@@ -0,0 +1,969 @@
+#if defined(__i386__)
+.file	"chacha-x86.S"
+.text
+.globl	_ChaCha20_ctr32
+.private_extern	_ChaCha20_ctr32
+.align	4
+_ChaCha20_ctr32:
+L_ChaCha20_ctr32_begin:
+	pushl	%ebp
+	pushl	%ebx
+	pushl	%esi
+	pushl	%edi
+	xorl	%eax,%eax
+	cmpl	28(%esp),%eax
+	je	L000no_data
+	call	Lpic_point
+Lpic_point:
+	popl	%eax
+	movl	L_OPENSSL_ia32cap_P$non_lazy_ptr-Lpic_point(%eax),%ebp
+	testl	$16777216,(%ebp)
+	jz	L001x86
+	testl	$512,4(%ebp)
+	jz	L001x86
+	jmp	Lssse3_shortcut
+L001x86:
+	movl	32(%esp),%esi
+	movl	36(%esp),%edi
+	subl	$132,%esp
+	movl	(%esi),%eax
+	movl	4(%esi),%ebx
+	movl	8(%esi),%ecx
+	movl	12(%esi),%edx
+	movl	%eax,80(%esp)
+	movl	%ebx,84(%esp)
+	movl	%ecx,88(%esp)
+	movl	%edx,92(%esp)
+	movl	16(%esi),%eax
+	movl	20(%esi),%ebx
+	movl	24(%esi),%ecx
+	movl	28(%esi),%edx
+	movl	%eax,96(%esp)
+	movl	%ebx,100(%esp)
+	movl	%ecx,104(%esp)
+	movl	%edx,108(%esp)
+	movl	(%edi),%eax
+	movl	4(%edi),%ebx
+	movl	8(%edi),%ecx
+	movl	12(%edi),%edx
+	subl	$1,%eax
+	movl	%eax,112(%esp)
+	movl	%ebx,116(%esp)
+	movl	%ecx,120(%esp)
+	movl	%edx,124(%esp)
+	jmp	L002entry
+.align	4,0x90
+L003outer_loop:
+	movl	%ebx,156(%esp)
+	movl	%eax,152(%esp)
+	movl	%ecx,160(%esp)
+L002entry:
+	movl	$1634760805,%eax
+	movl	$857760878,4(%esp)
+	movl	$2036477234,8(%esp)
+	movl	$1797285236,12(%esp)
+	movl	84(%esp),%ebx
+	movl	88(%esp),%ebp
+	movl	104(%esp),%ecx
+	movl	108(%esp),%esi
+	movl	116(%esp),%edx
+	movl	120(%esp),%edi
+	movl	%ebx,20(%esp)
+	movl	%ebp,24(%esp)
+	movl	%ecx,40(%esp)
+	movl	%esi,44(%esp)
+	movl	%edx,52(%esp)
+	movl	%edi,56(%esp)
+	movl	92(%esp),%ebx
+	movl	124(%esp),%edi
+	movl	112(%esp),%edx
+	movl	80(%esp),%ebp
+	movl	96(%esp),%ecx
+	movl	100(%esp),%esi
+	addl	$1,%edx
+	movl	%ebx,28(%esp)
+	movl	%edi,60(%esp)
+	movl	%edx,112(%esp)
+	movl	$10,%ebx
+	jmp	L004loop
+.align	4,0x90
+L004loop:
+	addl	%ebp,%eax
+	movl	%ebx,128(%esp)
+	movl	%ebp,%ebx
+	xorl	%eax,%edx
+	roll	$16,%edx
+	addl	%edx,%ecx
+	xorl	%ecx,%ebx
+	movl	52(%esp),%edi
+	roll	$12,%ebx
+	movl	20(%esp),%ebp
+	addl	%ebx,%eax
+	xorl	%eax,%edx
+	movl	%eax,(%esp)
+	roll	$8,%edx
+	movl	4(%esp),%eax
+	addl	%edx,%ecx
+	movl	%edx,48(%esp)
+	xorl	%ecx,%ebx
+	addl	%ebp,%eax
+	roll	$7,%ebx
+	xorl	%eax,%edi
+	movl	%ecx,32(%esp)
+	roll	$16,%edi
+	movl	%ebx,16(%esp)
+	addl	%edi,%esi
+	movl	40(%esp),%ecx
+	xorl	%esi,%ebp
+	movl	56(%esp),%edx
+	roll	$12,%ebp
+	movl	24(%esp),%ebx
+	addl	%ebp,%eax
+	xorl	%eax,%edi
+	movl	%eax,4(%esp)
+	roll	$8,%edi
+	movl	8(%esp),%eax
+	addl	%edi,%esi
+	movl	%edi,52(%esp)
+	xorl	%esi,%ebp
+	addl	%ebx,%eax
+	roll	$7,%ebp
+	xorl	%eax,%edx
+	movl	%esi,36(%esp)
+	roll	$16,%edx
+	movl	%ebp,20(%esp)
+	addl	%edx,%ecx
+	movl	44(%esp),%esi
+	xorl	%ecx,%ebx
+	movl	60(%esp),%edi
+	roll	$12,%ebx
+	movl	28(%esp),%ebp
+	addl	%ebx,%eax
+	xorl	%eax,%edx
+	movl	%eax,8(%esp)
+	roll	$8,%edx
+	movl	12(%esp),%eax
+	addl	%edx,%ecx
+	movl	%edx,56(%esp)
+	xorl	%ecx,%ebx
+	addl	%ebp,%eax
+	roll	$7,%ebx
+	xorl	%eax,%edi
+	roll	$16,%edi
+	movl	%ebx,24(%esp)
+	addl	%edi,%esi
+	xorl	%esi,%ebp
+	roll	$12,%ebp
+	movl	20(%esp),%ebx
+	addl	%ebp,%eax
+	xorl	%eax,%edi
+	movl	%eax,12(%esp)
+	roll	$8,%edi
+	movl	(%esp),%eax
+	addl	%edi,%esi
+	movl	%edi,%edx
+	xorl	%esi,%ebp
+	addl	%ebx,%eax
+	roll	$7,%ebp
+	xorl	%eax,%edx
+	roll	$16,%edx
+	movl	%ebp,28(%esp)
+	addl	%edx,%ecx
+	xorl	%ecx,%ebx
+	movl	48(%esp),%edi
+	roll	$12,%ebx
+	movl	24(%esp),%ebp
+	addl	%ebx,%eax
+	xorl	%eax,%edx
+	movl	%eax,(%esp)
+	roll	$8,%edx
+	movl	4(%esp),%eax
+	addl	%edx,%ecx
+	movl	%edx,60(%esp)
+	xorl	%ecx,%ebx
+	addl	%ebp,%eax
+	roll	$7,%ebx
+	xorl	%eax,%edi
+	movl	%ecx,40(%esp)
+	roll	$16,%edi
+	movl	%ebx,20(%esp)
+	addl	%edi,%esi
+	movl	32(%esp),%ecx
+	xorl	%esi,%ebp
+	movl	52(%esp),%edx
+	roll	$12,%ebp
+	movl	28(%esp),%ebx
+	addl	%ebp,%eax
+	xorl	%eax,%edi
+	movl	%eax,4(%esp)
+	roll	$8,%edi
+	movl	8(%esp),%eax
+	addl	%edi,%esi
+	movl	%edi,48(%esp)
+	xorl	%esi,%ebp
+	addl	%ebx,%eax
+	roll	$7,%ebp
+	xorl	%eax,%edx
+	movl	%esi,44(%esp)
+	roll	$16,%edx
+	movl	%ebp,24(%esp)
+	addl	%edx,%ecx
+	movl	36(%esp),%esi
+	xorl	%ecx,%ebx
+	movl	56(%esp),%edi
+	roll	$12,%ebx
+	movl	16(%esp),%ebp
+	addl	%ebx,%eax
+	xorl	%eax,%edx
+	movl	%eax,8(%esp)
+	roll	$8,%edx
+	movl	12(%esp),%eax
+	addl	%edx,%ecx
+	movl	%edx,52(%esp)
+	xorl	%ecx,%ebx
+	addl	%ebp,%eax
+	roll	$7,%ebx
+	xorl	%eax,%edi
+	roll	$16,%edi
+	movl	%ebx,28(%esp)
+	addl	%edi,%esi
+	xorl	%esi,%ebp
+	movl	48(%esp),%edx
+	roll	$12,%ebp
+	movl	128(%esp),%ebx
+	addl	%ebp,%eax
+	xorl	%eax,%edi
+	movl	%eax,12(%esp)
+	roll	$8,%edi
+	movl	(%esp),%eax
+	addl	%edi,%esi
+	movl	%edi,56(%esp)
+	xorl	%esi,%ebp
+	roll	$7,%ebp
+	decl	%ebx
+	jnz	L004loop
+	movl	160(%esp),%ebx
+	addl	$1634760805,%eax
+	addl	80(%esp),%ebp
+	addl	96(%esp),%ecx
+	addl	100(%esp),%esi
+	cmpl	$64,%ebx
+	jb	L005tail
+	movl	156(%esp),%ebx
+	addl	112(%esp),%edx
+	addl	120(%esp),%edi
+	xorl	(%ebx),%eax
+	xorl	16(%ebx),%ebp
+	movl	%eax,(%esp)
+	movl	152(%esp),%eax
+	xorl	32(%ebx),%ecx
+	xorl	36(%ebx),%esi
+	xorl	48(%ebx),%edx
+	xorl	56(%ebx),%edi
+	movl	%ebp,16(%eax)
+	movl	%ecx,32(%eax)
+	movl	%esi,36(%eax)
+	movl	%edx,48(%eax)
+	movl	%edi,56(%eax)
+	movl	4(%esp),%ebp
+	movl	8(%esp),%ecx
+	movl	12(%esp),%esi
+	movl	20(%esp),%edx
+	movl	24(%esp),%edi
+	addl	$857760878,%ebp
+	addl	$2036477234,%ecx
+	addl	$1797285236,%esi
+	addl	84(%esp),%edx
+	addl	88(%esp),%edi
+	xorl	4(%ebx),%ebp
+	xorl	8(%ebx),%ecx
+	xorl	12(%ebx),%esi
+	xorl	20(%ebx),%edx
+	xorl	24(%ebx),%edi
+	movl	%ebp,4(%eax)
+	movl	%ecx,8(%eax)
+	movl	%esi,12(%eax)
+	movl	%edx,20(%eax)
+	movl	%edi,24(%eax)
+	movl	28(%esp),%ebp
+	movl	40(%esp),%ecx
+	movl	44(%esp),%esi
+	movl	52(%esp),%edx
+	movl	60(%esp),%edi
+	addl	92(%esp),%ebp
+	addl	104(%esp),%ecx
+	addl	108(%esp),%esi
+	addl	116(%esp),%edx
+	addl	124(%esp),%edi
+	xorl	28(%ebx),%ebp
+	xorl	40(%ebx),%ecx
+	xorl	44(%ebx),%esi
+	xorl	52(%ebx),%edx
+	xorl	60(%ebx),%edi
+	leal	64(%ebx),%ebx
+	movl	%ebp,28(%eax)
+	movl	(%esp),%ebp
+	movl	%ecx,40(%eax)
+	movl	160(%esp),%ecx
+	movl	%esi,44(%eax)
+	movl	%edx,52(%eax)
+	movl	%edi,60(%eax)
+	movl	%ebp,(%eax)
+	leal	64(%eax),%eax
+	subl	$64,%ecx
+	jnz	L003outer_loop
+	jmp	L006done
+L005tail:
+	addl	112(%esp),%edx
+	addl	120(%esp),%edi
+	movl	%eax,(%esp)
+	movl	%ebp,16(%esp)
+	movl	%ecx,32(%esp)
+	movl	%esi,36(%esp)
+	movl	%edx,48(%esp)
+	movl	%edi,56(%esp)
+	movl	4(%esp),%ebp
+	movl	8(%esp),%ecx
+	movl	12(%esp),%esi
+	movl	20(%esp),%edx
+	movl	24(%esp),%edi
+	addl	$857760878,%ebp
+	addl	$2036477234,%ecx
+	addl	$1797285236,%esi
+	addl	84(%esp),%edx
+	addl	88(%esp),%edi
+	movl	%ebp,4(%esp)
+	movl	%ecx,8(%esp)
+	movl	%esi,12(%esp)
+	movl	%edx,20(%esp)
+	movl	%edi,24(%esp)
+	movl	28(%esp),%ebp
+	movl	40(%esp),%ecx
+	movl	44(%esp),%esi
+	movl	52(%esp),%edx
+	movl	60(%esp),%edi
+	addl	92(%esp),%ebp
+	addl	104(%esp),%ecx
+	addl	108(%esp),%esi
+	addl	116(%esp),%edx
+	addl	124(%esp),%edi
+	movl	%ebp,28(%esp)
+	movl	156(%esp),%ebp
+	movl	%ecx,40(%esp)
+	movl	152(%esp),%ecx
+	movl	%esi,44(%esp)
+	xorl	%esi,%esi
+	movl	%edx,52(%esp)
+	movl	%edi,60(%esp)
+	xorl	%eax,%eax
+	xorl	%edx,%edx
+L007tail_loop:
+	movb	(%esi,%ebp,1),%al
+	movb	(%esp,%esi,1),%dl
+	leal	1(%esi),%esi
+	xorb	%dl,%al
+	movb	%al,-1(%ecx,%esi,1)
+	decl	%ebx
+	jnz	L007tail_loop
+L006done:
+	addl	$132,%esp
+L000no_data:
+	popl	%edi
+	popl	%esi
+	popl	%ebx
+	popl	%ebp
+	ret
+.globl	_ChaCha20_ssse3
+.private_extern	_ChaCha20_ssse3
+.align	4
+_ChaCha20_ssse3:
+L_ChaCha20_ssse3_begin:
+	pushl	%ebp
+	pushl	%ebx
+	pushl	%esi
+	pushl	%edi
+Lssse3_shortcut:
+	movl	20(%esp),%edi
+	movl	24(%esp),%esi
+	movl	28(%esp),%ecx
+	movl	32(%esp),%edx
+	movl	36(%esp),%ebx
+	movl	%esp,%ebp
+	subl	$524,%esp
+	andl	$-64,%esp
+	movl	%ebp,512(%esp)
+	leal	Lssse3_data-Lpic_point(%eax),%eax
+	movdqu	(%ebx),%xmm3
+	cmpl	$256,%ecx
+	jb	L0081x
+	movl	%edx,516(%esp)
+	movl	%ebx,520(%esp)
+	subl	$256,%ecx
+	leal	384(%esp),%ebp
+	movdqu	(%edx),%xmm7
+	pshufd	$0,%xmm3,%xmm0
+	pshufd	$85,%xmm3,%xmm1
+	pshufd	$170,%xmm3,%xmm2
+	pshufd	$255,%xmm3,%xmm3
+	paddd	48(%eax),%xmm0
+	pshufd	$0,%xmm7,%xmm4
+	pshufd	$85,%xmm7,%xmm5
+	psubd	64(%eax),%xmm0
+	pshufd	$170,%xmm7,%xmm6
+	pshufd	$255,%xmm7,%xmm7
+	movdqa	%xmm0,64(%ebp)
+	movdqa	%xmm1,80(%ebp)
+	movdqa	%xmm2,96(%ebp)
+	movdqa	%xmm3,112(%ebp)
+	movdqu	16(%edx),%xmm3
+	movdqa	%xmm4,-64(%ebp)
+	movdqa	%xmm5,-48(%ebp)
+	movdqa	%xmm6,-32(%ebp)
+	movdqa	%xmm7,-16(%ebp)
+	movdqa	32(%eax),%xmm7
+	leal	128(%esp),%ebx
+	pshufd	$0,%xmm3,%xmm0
+	pshufd	$85,%xmm3,%xmm1
+	pshufd	$170,%xmm3,%xmm2
+	pshufd	$255,%xmm3,%xmm3
+	pshufd	$0,%xmm7,%xmm4
+	pshufd	$85,%xmm7,%xmm5
+	pshufd	$170,%xmm7,%xmm6
+	pshufd	$255,%xmm7,%xmm7
+	movdqa	%xmm0,(%ebp)
+	movdqa	%xmm1,16(%ebp)
+	movdqa	%xmm2,32(%ebp)
+	movdqa	%xmm3,48(%ebp)
+	movdqa	%xmm4,-128(%ebp)
+	movdqa	%xmm5,-112(%ebp)
+	movdqa	%xmm6,-96(%ebp)
+	movdqa	%xmm7,-80(%ebp)
+	leal	128(%esi),%esi
+	leal	128(%edi),%edi
+	jmp	L009outer_loop
+.align	4,0x90
+L009outer_loop:
+	movdqa	-112(%ebp),%xmm1
+	movdqa	-96(%ebp),%xmm2
+	movdqa	-80(%ebp),%xmm3
+	movdqa	-48(%ebp),%xmm5
+	movdqa	-32(%ebp),%xmm6
+	movdqa	-16(%ebp),%xmm7
+	movdqa	%xmm1,-112(%ebx)
+	movdqa	%xmm2,-96(%ebx)
+	movdqa	%xmm3,-80(%ebx)
+	movdqa	%xmm5,-48(%ebx)
+	movdqa	%xmm6,-32(%ebx)
+	movdqa	%xmm7,-16(%ebx)
+	movdqa	32(%ebp),%xmm2
+	movdqa	48(%ebp),%xmm3
+	movdqa	64(%ebp),%xmm4
+	movdqa	80(%ebp),%xmm5
+	movdqa	96(%ebp),%xmm6
+	movdqa	112(%ebp),%xmm7
+	paddd	64(%eax),%xmm4
+	movdqa	%xmm2,32(%ebx)
+	movdqa	%xmm3,48(%ebx)
+	movdqa	%xmm4,64(%ebx)
+	movdqa	%xmm5,80(%ebx)
+	movdqa	%xmm6,96(%ebx)
+	movdqa	%xmm7,112(%ebx)
+	movdqa	%xmm4,64(%ebp)
+	movdqa	-128(%ebp),%xmm0
+	movdqa	%xmm4,%xmm6
+	movdqa	-64(%ebp),%xmm3
+	movdqa	(%ebp),%xmm4
+	movdqa	16(%ebp),%xmm5
+	movl	$10,%edx
+	nop
+.align	4,0x90
+L010loop:
+	paddd	%xmm3,%xmm0
+	movdqa	%xmm3,%xmm2
+	pxor	%xmm0,%xmm6
+	pshufb	(%eax),%xmm6
+	paddd	%xmm6,%xmm4
+	pxor	%xmm4,%xmm2
+	movdqa	-48(%ebx),%xmm3
+	movdqa	%xmm2,%xmm1
+	pslld	$12,%xmm2
+	psrld	$20,%xmm1
+	por	%xmm1,%xmm2
+	movdqa	-112(%ebx),%xmm1
+	paddd	%xmm2,%xmm0
+	movdqa	80(%ebx),%xmm7
+	pxor	%xmm0,%xmm6
+	movdqa	%xmm0,-128(%ebx)
+	pshufb	16(%eax),%xmm6
+	paddd	%xmm6,%xmm4
+	movdqa	%xmm6,64(%ebx)
+	pxor	%xmm4,%xmm2
+	paddd	%xmm3,%xmm1
+	movdqa	%xmm2,%xmm0
+	pslld	$7,%xmm2
+	psrld	$25,%xmm0
+	pxor	%xmm1,%xmm7
+	por	%xmm0,%xmm2
+	movdqa	%xmm4,(%ebx)
+	pshufb	(%eax),%xmm7
+	movdqa	%xmm2,-64(%ebx)
+	paddd	%xmm7,%xmm5
+	movdqa	32(%ebx),%xmm4
+	pxor	%xmm5,%xmm3
+	movdqa	-32(%ebx),%xmm2
+	movdqa	%xmm3,%xmm0
+	pslld	$12,%xmm3
+	psrld	$20,%xmm0
+	por	%xmm0,%xmm3
+	movdqa	-96(%ebx),%xmm0
+	paddd	%xmm3,%xmm1
+	movdqa	96(%ebx),%xmm6
+	pxor	%xmm1,%xmm7
+	movdqa	%xmm1,-112(%ebx)
+	pshufb	16(%eax),%xmm7
+	paddd	%xmm7,%xmm5
+	movdqa	%xmm7,80(%ebx)
+	pxor	%xmm5,%xmm3
+	paddd	%xmm2,%xmm0
+	movdqa	%xmm3,%xmm1
+	pslld	$7,%xmm3
+	psrld	$25,%xmm1
+	pxor	%xmm0,%xmm6
+	por	%xmm1,%xmm3
+	movdqa	%xmm5,16(%ebx)
+	pshufb	(%eax),%xmm6
+	movdqa	%xmm3,-48(%ebx)
+	paddd	%xmm6,%xmm4
+	movdqa	48(%ebx),%xmm5
+	pxor	%xmm4,%xmm2
+	movdqa	-16(%ebx),%xmm3
+	movdqa	%xmm2,%xmm1
+	pslld	$12,%xmm2
+	psrld	$20,%xmm1
+	por	%xmm1,%xmm2
+	movdqa	-80(%ebx),%xmm1
+	paddd	%xmm2,%xmm0
+	movdqa	112(%ebx),%xmm7
+	pxor	%xmm0,%xmm6
+	movdqa	%xmm0,-96(%ebx)
+	pshufb	16(%eax),%xmm6
+	paddd	%xmm6,%xmm4
+	movdqa	%xmm6,96(%ebx)
+	pxor	%xmm4,%xmm2
+	paddd	%xmm3,%xmm1
+	movdqa	%xmm2,%xmm0
+	pslld	$7,%xmm2
+	psrld	$25,%xmm0
+	pxor	%xmm1,%xmm7
+	por	%xmm0,%xmm2
+	pshufb	(%eax),%xmm7
+	movdqa	%xmm2,-32(%ebx)
+	paddd	%xmm7,%xmm5
+	pxor	%xmm5,%xmm3
+	movdqa	-48(%ebx),%xmm2
+	movdqa	%xmm3,%xmm0
+	pslld	$12,%xmm3
+	psrld	$20,%xmm0
+	por	%xmm0,%xmm3
+	movdqa	-128(%ebx),%xmm0
+	paddd	%xmm3,%xmm1
+	pxor	%xmm1,%xmm7
+	movdqa	%xmm1,-80(%ebx)
+	pshufb	16(%eax),%xmm7
+	paddd	%xmm7,%xmm5
+	movdqa	%xmm7,%xmm6
+	pxor	%xmm5,%xmm3
+	paddd	%xmm2,%xmm0
+	movdqa	%xmm3,%xmm1
+	pslld	$7,%xmm3
+	psrld	$25,%xmm1
+	pxor	%xmm0,%xmm6
+	por	%xmm1,%xmm3
+	pshufb	(%eax),%xmm6
+	movdqa	%xmm3,-16(%ebx)
+	paddd	%xmm6,%xmm4
+	pxor	%xmm4,%xmm2
+	movdqa	-32(%ebx),%xmm3
+	movdqa	%xmm2,%xmm1
+	pslld	$12,%xmm2
+	psrld	$20,%xmm1
+	por	%xmm1,%xmm2
+	movdqa	-112(%ebx),%xmm1
+	paddd	%xmm2,%xmm0
+	movdqa	64(%ebx),%xmm7
+	pxor	%xmm0,%xmm6
+	movdqa	%xmm0,-128(%ebx)
+	pshufb	16(%eax),%xmm6
+	paddd	%xmm6,%xmm4
+	movdqa	%xmm6,112(%ebx)
+	pxor	%xmm4,%xmm2
+	paddd	%xmm3,%xmm1
+	movdqa	%xmm2,%xmm0
+	pslld	$7,%xmm2
+	psrld	$25,%xmm0
+	pxor	%xmm1,%xmm7
+	por	%xmm0,%xmm2
+	movdqa	%xmm4,32(%ebx)
+	pshufb	(%eax),%xmm7
+	movdqa	%xmm2,-48(%ebx)
+	paddd	%xmm7,%xmm5
+	movdqa	(%ebx),%xmm4
+	pxor	%xmm5,%xmm3
+	movdqa	-16(%ebx),%xmm2
+	movdqa	%xmm3,%xmm0
+	pslld	$12,%xmm3
+	psrld	$20,%xmm0
+	por	%xmm0,%xmm3
+	movdqa	-96(%ebx),%xmm0
+	paddd	%xmm3,%xmm1
+	movdqa	80(%ebx),%xmm6
+	pxor	%xmm1,%xmm7
+	movdqa	%xmm1,-112(%ebx)
+	pshufb	16(%eax),%xmm7
+	paddd	%xmm7,%xmm5
+	movdqa	%xmm7,64(%ebx)
+	pxor	%xmm5,%xmm3
+	paddd	%xmm2,%xmm0
+	movdqa	%xmm3,%xmm1
+	pslld	$7,%xmm3
+	psrld	$25,%xmm1
+	pxor	%xmm0,%xmm6
+	por	%xmm1,%xmm3
+	movdqa	%xmm5,48(%ebx)
+	pshufb	(%eax),%xmm6
+	movdqa	%xmm3,-32(%ebx)
+	paddd	%xmm6,%xmm4
+	movdqa	16(%ebx),%xmm5
+	pxor	%xmm4,%xmm2
+	movdqa	-64(%ebx),%xmm3
+	movdqa	%xmm2,%xmm1
+	pslld	$12,%xmm2
+	psrld	$20,%xmm1
+	por	%xmm1,%xmm2
+	movdqa	-80(%ebx),%xmm1
+	paddd	%xmm2,%xmm0
+	movdqa	96(%ebx),%xmm7
+	pxor	%xmm0,%xmm6
+	movdqa	%xmm0,-96(%ebx)
+	pshufb	16(%eax),%xmm6
+	paddd	%xmm6,%xmm4
+	movdqa	%xmm6,80(%ebx)
+	pxor	%xmm4,%xmm2
+	paddd	%xmm3,%xmm1
+	movdqa	%xmm2,%xmm0
+	pslld	$7,%xmm2
+	psrld	$25,%xmm0
+	pxor	%xmm1,%xmm7
+	por	%xmm0,%xmm2
+	pshufb	(%eax),%xmm7
+	movdqa	%xmm2,-16(%ebx)
+	paddd	%xmm7,%xmm5
+	pxor	%xmm5,%xmm3
+	movdqa	%xmm3,%xmm0
+	pslld	$12,%xmm3
+	psrld	$20,%xmm0
+	por	%xmm0,%xmm3
+	movdqa	-128(%ebx),%xmm0
+	paddd	%xmm3,%xmm1
+	movdqa	64(%ebx),%xmm6
+	pxor	%xmm1,%xmm7
+	movdqa	%xmm1,-80(%ebx)
+	pshufb	16(%eax),%xmm7
+	paddd	%xmm7,%xmm5
+	movdqa	%xmm7,96(%ebx)
+	pxor	%xmm5,%xmm3
+	movdqa	%xmm3,%xmm1
+	pslld	$7,%xmm3
+	psrld	$25,%xmm1
+	por	%xmm1,%xmm3
+	decl	%edx
+	jnz	L010loop
+	movdqa	%xmm3,-64(%ebx)
+	movdqa	%xmm4,(%ebx)
+	movdqa	%xmm5,16(%ebx)
+	movdqa	%xmm6,64(%ebx)
+	movdqa	%xmm7,96(%ebx)
+	movdqa	-112(%ebx),%xmm1
+	movdqa	-96(%ebx),%xmm2
+	movdqa	-80(%ebx),%xmm3
+	paddd	-128(%ebp),%xmm0
+	paddd	-112(%ebp),%xmm1
+	paddd	-96(%ebp),%xmm2
+	paddd	-80(%ebp),%xmm3
+	movdqa	%xmm0,%xmm6
+	punpckldq	%xmm1,%xmm0
+	movdqa	%xmm2,%xmm7
+	punpckldq	%xmm3,%xmm2
+	punpckhdq	%xmm1,%xmm6
+	punpckhdq	%xmm3,%xmm7
+	movdqa	%xmm0,%xmm1
+	punpcklqdq	%xmm2,%xmm0
+	movdqa	%xmm6,%xmm3
+	punpcklqdq	%xmm7,%xmm6
+	punpckhqdq	%xmm2,%xmm1
+	punpckhqdq	%xmm7,%xmm3
+	movdqu	-128(%esi),%xmm4
+	movdqu	-64(%esi),%xmm5
+	movdqu	(%esi),%xmm2
+	movdqu	64(%esi),%xmm7
+	leal	16(%esi),%esi
+	pxor	%xmm0,%xmm4
+	movdqa	-64(%ebx),%xmm0
+	pxor	%xmm1,%xmm5
+	movdqa	-48(%ebx),%xmm1
+	pxor	%xmm2,%xmm6
+	movdqa	-32(%ebx),%xmm2
+	pxor	%xmm3,%xmm7
+	movdqa	-16(%ebx),%xmm3
+	movdqu	%xmm4,-128(%edi)
+	movdqu	%xmm5,-64(%edi)
+	movdqu	%xmm6,(%edi)
+	movdqu	%xmm7,64(%edi)
+	leal	16(%edi),%edi
+	paddd	-64(%ebp),%xmm0
+	paddd	-48(%ebp),%xmm1
+	paddd	-32(%ebp),%xmm2
+	paddd	-16(%ebp),%xmm3
+	movdqa	%xmm0,%xmm6
+	punpckldq	%xmm1,%xmm0
+	movdqa	%xmm2,%xmm7
+	punpckldq	%xmm3,%xmm2
+	punpckhdq	%xmm1,%xmm6
+	punpckhdq	%xmm3,%xmm7
+	movdqa	%xmm0,%xmm1
+	punpcklqdq	%xmm2,%xmm0
+	movdqa	%xmm6,%xmm3
+	punpcklqdq	%xmm7,%xmm6
+	punpckhqdq	%xmm2,%xmm1
+	punpckhqdq	%xmm7,%xmm3
+	movdqu	-128(%esi),%xmm4
+	movdqu	-64(%esi),%xmm5
+	movdqu	(%esi),%xmm2
+	movdqu	64(%esi),%xmm7
+	leal	16(%esi),%esi
+	pxor	%xmm0,%xmm4
+	movdqa	(%ebx),%xmm0
+	pxor	%xmm1,%xmm5
+	movdqa	16(%ebx),%xmm1
+	pxor	%xmm2,%xmm6
+	movdqa	32(%ebx),%xmm2
+	pxor	%xmm3,%xmm7
+	movdqa	48(%ebx),%xmm3
+	movdqu	%xmm4,-128(%edi)
+	movdqu	%xmm5,-64(%edi)
+	movdqu	%xmm6,(%edi)
+	movdqu	%xmm7,64(%edi)
+	leal	16(%edi),%edi
+	paddd	(%ebp),%xmm0
+	paddd	16(%ebp),%xmm1
+	paddd	32(%ebp),%xmm2
+	paddd	48(%ebp),%xmm3
+	movdqa	%xmm0,%xmm6
+	punpckldq	%xmm1,%xmm0
+	movdqa	%xmm2,%xmm7
+	punpckldq	%xmm3,%xmm2
+	punpckhdq	%xmm1,%xmm6
+	punpckhdq	%xmm3,%xmm7
+	movdqa	%xmm0,%xmm1
+	punpcklqdq	%xmm2,%xmm0
+	movdqa	%xmm6,%xmm3
+	punpcklqdq	%xmm7,%xmm6
+	punpckhqdq	%xmm2,%xmm1
+	punpckhqdq	%xmm7,%xmm3
+	movdqu	-128(%esi),%xmm4
+	movdqu	-64(%esi),%xmm5
+	movdqu	(%esi),%xmm2
+	movdqu	64(%esi),%xmm7
+	leal	16(%esi),%esi
+	pxor	%xmm0,%xmm4
+	movdqa	64(%ebx),%xmm0
+	pxor	%xmm1,%xmm5
+	movdqa	80(%ebx),%xmm1
+	pxor	%xmm2,%xmm6
+	movdqa	96(%ebx),%xmm2
+	pxor	%xmm3,%xmm7
+	movdqa	112(%ebx),%xmm3
+	movdqu	%xmm4,-128(%edi)
+	movdqu	%xmm5,-64(%edi)
+	movdqu	%xmm6,(%edi)
+	movdqu	%xmm7,64(%edi)
+	leal	16(%edi),%edi
+	paddd	64(%ebp),%xmm0
+	paddd	80(%ebp),%xmm1
+	paddd	96(%ebp),%xmm2
+	paddd	112(%ebp),%xmm3
+	movdqa	%xmm0,%xmm6
+	punpckldq	%xmm1,%xmm0
+	movdqa	%xmm2,%xmm7
+	punpckldq	%xmm3,%xmm2
+	punpckhdq	%xmm1,%xmm6
+	punpckhdq	%xmm3,%xmm7
+	movdqa	%xmm0,%xmm1
+	punpcklqdq	%xmm2,%xmm0
+	movdqa	%xmm6,%xmm3
+	punpcklqdq	%xmm7,%xmm6
+	punpckhqdq	%xmm2,%xmm1
+	punpckhqdq	%xmm7,%xmm3
+	movdqu	-128(%esi),%xmm4
+	movdqu	-64(%esi),%xmm5
+	movdqu	(%esi),%xmm2
+	movdqu	64(%esi),%xmm7
+	leal	208(%esi),%esi
+	pxor	%xmm0,%xmm4
+	pxor	%xmm1,%xmm5
+	pxor	%xmm2,%xmm6
+	pxor	%xmm3,%xmm7
+	movdqu	%xmm4,-128(%edi)
+	movdqu	%xmm5,-64(%edi)
+	movdqu	%xmm6,(%edi)
+	movdqu	%xmm7,64(%edi)
+	leal	208(%edi),%edi
+	subl	$256,%ecx
+	jnc	L009outer_loop
+	addl	$256,%ecx
+	jz	L011done
+	movl	520(%esp),%ebx
+	leal	-128(%esi),%esi
+	movl	516(%esp),%edx
+	leal	-128(%edi),%edi
+	movd	64(%ebp),%xmm2
+	movdqu	(%ebx),%xmm3
+	paddd	96(%eax),%xmm2
+	pand	112(%eax),%xmm3
+	por	%xmm2,%xmm3
+L0081x:
+	movdqa	32(%eax),%xmm0
+	movdqu	(%edx),%xmm1
+	movdqu	16(%edx),%xmm2
+	movdqa	(%eax),%xmm6
+	movdqa	16(%eax),%xmm7
+	movl	%ebp,48(%esp)
+	movdqa	%xmm0,(%esp)
+	movdqa	%xmm1,16(%esp)
+	movdqa	%xmm2,32(%esp)
+	movdqa	%xmm3,48(%esp)
+	movl	$10,%edx
+	jmp	L012loop1x
+.align	4,0x90
+L013outer1x:
+	movdqa	80(%eax),%xmm3
+	movdqa	(%esp),%xmm0
+	movdqa	16(%esp),%xmm1
+	movdqa	32(%esp),%xmm2
+	paddd	48(%esp),%xmm3
+	movl	$10,%edx
+	movdqa	%xmm3,48(%esp)
+	jmp	L012loop1x
+.align	4,0x90
+L012loop1x:
+	paddd	%xmm1,%xmm0
+	pxor	%xmm0,%xmm3
+.byte	102,15,56,0,222
+	paddd	%xmm3,%xmm2
+	pxor	%xmm2,%xmm1
+	movdqa	%xmm1,%xmm4
+	psrld	$20,%xmm1
+	pslld	$12,%xmm4
+	por	%xmm4,%xmm1
+	paddd	%xmm1,%xmm0
+	pxor	%xmm0,%xmm3
+.byte	102,15,56,0,223
+	paddd	%xmm3,%xmm2
+	pxor	%xmm2,%xmm1
+	movdqa	%xmm1,%xmm4
+	psrld	$25,%xmm1
+	pslld	$7,%xmm4
+	por	%xmm4,%xmm1
+	pshufd	$78,%xmm2,%xmm2
+	pshufd	$57,%xmm1,%xmm1
+	pshufd	$147,%xmm3,%xmm3
+	nop
+	paddd	%xmm1,%xmm0
+	pxor	%xmm0,%xmm3
+.byte	102,15,56,0,222
+	paddd	%xmm3,%xmm2
+	pxor	%xmm2,%xmm1
+	movdqa	%xmm1,%xmm4
+	psrld	$20,%xmm1
+	pslld	$12,%xmm4
+	por	%xmm4,%xmm1
+	paddd	%xmm1,%xmm0
+	pxor	%xmm0,%xmm3
+.byte	102,15,56,0,223
+	paddd	%xmm3,%xmm2
+	pxor	%xmm2,%xmm1
+	movdqa	%xmm1,%xmm4
+	psrld	$25,%xmm1
+	pslld	$7,%xmm4
+	por	%xmm4,%xmm1
+	pshufd	$78,%xmm2,%xmm2
+	pshufd	$147,%xmm1,%xmm1
+	pshufd	$57,%xmm3,%xmm3
+	decl	%edx
+	jnz	L012loop1x
+	paddd	(%esp),%xmm0
+	paddd	16(%esp),%xmm1
+	paddd	32(%esp),%xmm2
+	paddd	48(%esp),%xmm3
+	cmpl	$64,%ecx
+	jb	L014tail
+	movdqu	(%esi),%xmm4
+	movdqu	16(%esi),%xmm5
+	pxor	%xmm4,%xmm0
+	movdqu	32(%esi),%xmm4
+	pxor	%xmm5,%xmm1
+	movdqu	48(%esi),%xmm5
+	pxor	%xmm4,%xmm2
+	pxor	%xmm5,%xmm3
+	leal	64(%esi),%esi
+	movdqu	%xmm0,(%edi)
+	movdqu	%xmm1,16(%edi)
+	movdqu	%xmm2,32(%edi)
+	movdqu	%xmm3,48(%edi)
+	leal	64(%edi),%edi
+	subl	$64,%ecx
+	jnz	L013outer1x
+	jmp	L011done
+L014tail:
+	movdqa	%xmm0,(%esp)
+	movdqa	%xmm1,16(%esp)
+	movdqa	%xmm2,32(%esp)
+	movdqa	%xmm3,48(%esp)
+	xorl	%eax,%eax
+	xorl	%edx,%edx
+	xorl	%ebp,%ebp
+L015tail_loop:
+	movb	(%esp,%ebp,1),%al
+	movb	(%esi,%ebp,1),%dl
+	leal	1(%ebp),%ebp
+	xorb	%dl,%al
+	movb	%al,-1(%edi,%ebp,1)
+	decl	%ecx
+	jnz	L015tail_loop
+L011done:
+	movl	512(%esp),%esp
+	popl	%edi
+	popl	%esi
+	popl	%ebx
+	popl	%ebp
+	ret
+.align	6,0x90
+Lssse3_data:
+.byte	2,3,0,1,6,7,4,5,10,11,8,9,14,15,12,13
+.byte	3,0,1,2,7,4,5,6,11,8,9,10,15,12,13,14
+.long	1634760805,857760878,2036477234,1797285236
+.long	0,1,2,3
+.long	4,4,4,4
+.long	1,0,0,0
+.long	4,0,0,0
+.long	0,-1,-1,-1
+.align	6,0x90
+.byte	67,104,97,67,104,97,50,48,32,102,111,114,32,120,56,54
+.byte	44,32,67,82,89,80,84,79,71,65,77,83,32,98,121,32
+.byte	60,97,112,112,114,111,64,111,112,101,110,115,115,108,46,111
+.byte	114,103,62,0
+.section __IMPORT,__pointers,non_lazy_symbol_pointers
+L_OPENSSL_ia32cap_P$non_lazy_ptr:
+.indirect_symbol	_OPENSSL_ia32cap_P
+.long	0
+#endif
diff --git a/packager/third_party/boringssl/mac-x86/crypto/rc4/rc4-586.S b/packager/third_party/boringssl/mac-x86/crypto/rc4/rc4-586.S
index faecdfa9f2..dcddc58388 100644
--- a/packager/third_party/boringssl/mac-x86/crypto/rc4/rc4-586.S
+++ b/packager/third_party/boringssl/mac-x86/crypto/rc4/rc4-586.S
@@ -343,39 +343,6 @@ L015exit:
 	popl	%ebx
 	popl	%ebp
 	ret
-.globl	_RC4_options
-.private_extern	_RC4_options
-.align	4
-_RC4_options:
-L_RC4_options_begin:
-	call	L018pic_point
-L018pic_point:
-	popl	%eax
-	leal	L019opts-L018pic_point(%eax),%eax
-	call	L020PIC_me_up
-L020PIC_me_up:
-	popl	%edx
-	movl	L_OPENSSL_ia32cap_P$non_lazy_ptr-L020PIC_me_up(%edx),%edx
-	movl	(%edx),%edx
-	btl	$20,%edx
-	jc	L0211xchar
-	btl	$26,%edx
-	jnc	L022ret
-	addl	$25,%eax
-	ret
-L0211xchar:
-	addl	$12,%eax
-L022ret:
-	ret
-.align	6,0x90
-L019opts:
-.byte	114,99,52,40,52,120,44,105,110,116,41,0
-.byte	114,99,52,40,49,120,44,99,104,97,114,41,0
-.byte	114,99,52,40,56,120,44,109,109,120,41,0
-.byte	82,67,52,32,102,111,114,32,120,56,54,44,32,67,82,89
-.byte	80,84,79,71,65,77,83,32,98,121,32,60,97,112,112,114
-.byte	111,64,111,112,101,110,115,115,108,46,111,114,103,62,0
-.align	6,0x90
 .section __IMPORT,__pointers,non_lazy_symbol_pointers
 L_OPENSSL_ia32cap_P$non_lazy_ptr:
 .indirect_symbol	_OPENSSL_ia32cap_P
diff --git a/packager/third_party/boringssl/mac-x86/crypto/sha/sha1-586.S b/packager/third_party/boringssl/mac-x86/crypto/sha/sha1-586.S
index 97aafbf198..72a7205dea 100644
--- a/packager/third_party/boringssl/mac-x86/crypto/sha/sha1-586.S
+++ b/packager/third_party/boringssl/mac-x86/crypto/sha/sha1-586.S
@@ -22,8 +22,11 @@ L000pic_point:
 	movl	8(%esi),%ecx
 	testl	$16777216,%eax
 	jz	L001x86
-	testl	$536870912,%ecx
-	jnz	Lshaext_shortcut
+	andl	$268435456,%edx
+	andl	$1073741824,%eax
+	orl	%edx,%eax
+	cmpl	$1342177280,%eax
+	je	Lavx_shortcut
 	jmp	Lssse3_shortcut
 .align	4,0x90
 L001x86:
@@ -1391,9 +1394,9 @@ L002loop:
 	popl	%ebx
 	popl	%ebp
 	ret
-.private_extern	__sha1_block_data_order_shaext
+.private_extern	__sha1_block_data_order_ssse3
 .align	4
-__sha1_block_data_order_shaext:
+__sha1_block_data_order_ssse3:
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -1402,175 +1405,6 @@ __sha1_block_data_order_shaext:
 L003pic_point:
 	popl	%ebp
 	leal	LK_XX_XX-L003pic_point(%ebp),%ebp
-Lshaext_shortcut:
-	movl	20(%esp),%edi
-	movl	%esp,%ebx
-	movl	24(%esp),%esi
-	movl	28(%esp),%ecx
-	subl	$32,%esp
-	movdqu	(%edi),%xmm0
-	movd	16(%edi),%xmm1
-	andl	$-32,%esp
-	movdqa	80(%ebp),%xmm3
-	movdqu	(%esi),%xmm4
-	pshufd	$27,%xmm0,%xmm0
-	movdqu	16(%esi),%xmm5
-	pshufd	$27,%xmm1,%xmm1
-	movdqu	32(%esi),%xmm6
-.byte	102,15,56,0,227
-	movdqu	48(%esi),%xmm7
-.byte	102,15,56,0,235
-.byte	102,15,56,0,243
-.byte	102,15,56,0,251
-	jmp	L004loop_shaext
-.align	4,0x90
-L004loop_shaext:
-	decl	%ecx
-	leal	64(%esi),%eax
-	movdqa	%xmm1,(%esp)
-	paddd	%xmm4,%xmm1
-	cmovnel	%eax,%esi
-	movdqa	%xmm0,16(%esp)
-.byte	15,56,201,229
-	movdqa	%xmm0,%xmm2
-.byte	15,58,204,193,0
-.byte	15,56,200,213
-	pxor	%xmm6,%xmm4
-.byte	15,56,201,238
-.byte	15,56,202,231
-	movdqa	%xmm0,%xmm1
-.byte	15,58,204,194,0
-.byte	15,56,200,206
-	pxor	%xmm7,%xmm5
-.byte	15,56,202,236
-.byte	15,56,201,247
-	movdqa	%xmm0,%xmm2
-.byte	15,58,204,193,0
-.byte	15,56,200,215
-	pxor	%xmm4,%xmm6
-.byte	15,56,201,252
-.byte	15,56,202,245
-	movdqa	%xmm0,%xmm1
-.byte	15,58,204,194,0
-.byte	15,56,200,204
-	pxor	%xmm5,%xmm7
-.byte	15,56,202,254
-.byte	15,56,201,229
-	movdqa	%xmm0,%xmm2
-.byte	15,58,204,193,0
-.byte	15,56,200,213
-	pxor	%xmm6,%xmm4
-.byte	15,56,201,238
-.byte	15,56,202,231
-	movdqa	%xmm0,%xmm1
-.byte	15,58,204,194,1
-.byte	15,56,200,206
-	pxor	%xmm7,%xmm5
-.byte	15,56,202,236
-.byte	15,56,201,247
-	movdqa	%xmm0,%xmm2
-.byte	15,58,204,193,1
-.byte	15,56,200,215
-	pxor	%xmm4,%xmm6
-.byte	15,56,201,252
-.byte	15,56,202,245
-	movdqa	%xmm0,%xmm1
-.byte	15,58,204,194,1
-.byte	15,56,200,204
-	pxor	%xmm5,%xmm7
-.byte	15,56,202,254
-.byte	15,56,201,229
-	movdqa	%xmm0,%xmm2
-.byte	15,58,204,193,1
-.byte	15,56,200,213
-	pxor	%xmm6,%xmm4
-.byte	15,56,201,238
-.byte	15,56,202,231
-	movdqa	%xmm0,%xmm1
-.byte	15,58,204,194,1
-.byte	15,56,200,206
-	pxor	%xmm7,%xmm5
-.byte	15,56,202,236
-.byte	15,56,201,247
-	movdqa	%xmm0,%xmm2
-.byte	15,58,204,193,2
-.byte	15,56,200,215
-	pxor	%xmm4,%xmm6
-.byte	15,56,201,252
-.byte	15,56,202,245
-	movdqa	%xmm0,%xmm1
-.byte	15,58,204,194,2
-.byte	15,56,200,204
-	pxor	%xmm5,%xmm7
-.byte	15,56,202,254
-.byte	15,56,201,229
-	movdqa	%xmm0,%xmm2
-.byte	15,58,204,193,2
-.byte	15,56,200,213
-	pxor	%xmm6,%xmm4
-.byte	15,56,201,238
-.byte	15,56,202,231
-	movdqa	%xmm0,%xmm1
-.byte	15,58,204,194,2
-.byte	15,56,200,206
-	pxor	%xmm7,%xmm5
-.byte	15,56,202,236
-.byte	15,56,201,247
-	movdqa	%xmm0,%xmm2
-.byte	15,58,204,193,2
-.byte	15,56,200,215
-	pxor	%xmm4,%xmm6
-.byte	15,56,201,252
-.byte	15,56,202,245
-	movdqa	%xmm0,%xmm1
-.byte	15,58,204,194,3
-.byte	15,56,200,204
-	pxor	%xmm5,%xmm7
-.byte	15,56,202,254
-	movdqu	(%esi),%xmm4
-	movdqa	%xmm0,%xmm2
-.byte	15,58,204,193,3
-.byte	15,56,200,213
-	movdqu	16(%esi),%xmm5
-.byte	102,15,56,0,227
-	movdqa	%xmm0,%xmm1
-.byte	15,58,204,194,3
-.byte	15,56,200,206
-	movdqu	32(%esi),%xmm6
-.byte	102,15,56,0,235
-	movdqa	%xmm0,%xmm2
-.byte	15,58,204,193,3
-.byte	15,56,200,215
-	movdqu	48(%esi),%xmm7
-.byte	102,15,56,0,243
-	movdqa	%xmm0,%xmm1
-.byte	15,58,204,194,3
-	movdqa	(%esp),%xmm2
-.byte	102,15,56,0,251
-.byte	15,56,200,202
-	paddd	16(%esp),%xmm0
-	jnz	L004loop_shaext
-	pshufd	$27,%xmm0,%xmm0
-	pshufd	$27,%xmm1,%xmm1
-	movdqu	%xmm0,(%edi)
-	movd	%xmm1,16(%edi)
-	movl	%ebx,%esp
-	popl	%edi
-	popl	%esi
-	popl	%ebx
-	popl	%ebp
-	ret
-.private_extern	__sha1_block_data_order_ssse3
-.align	4
-__sha1_block_data_order_ssse3:
-	pushl	%ebp
-	pushl	%ebx
-	pushl	%esi
-	pushl	%edi
-	call	L005pic_point
-L005pic_point:
-	popl	%ebp
-	leal	LK_XX_XX-L005pic_point(%ebp),%ebp
 Lssse3_shortcut:
 	movdqa	(%ebp),%xmm7
 	movdqa	16(%ebp),%xmm0
@@ -1623,9 +1457,9 @@ Lssse3_shortcut:
 	xorl	%edx,%ebp
 	pshufd	$238,%xmm0,%xmm4
 	andl	%ebp,%esi
-	jmp	L006loop
+	jmp	L004loop
 .align	4,0x90
-L006loop:
+L004loop:
 	rorl	$2,%ebx
 	xorl	%edx,%esi
 	movl	%eax,%ebp
@@ -2528,7 +2362,7 @@ L006loop:
 	addl	%edx,%ecx
 	movl	196(%esp),%ebp
 	cmpl	200(%esp),%ebp
-	je	L007done
+	je	L005done
 	movdqa	160(%esp),%xmm7
 	movdqa	176(%esp),%xmm6
 	movdqu	(%ebp),%xmm0
@@ -2663,9 +2497,9 @@ L006loop:
 	pshufd	$238,%xmm0,%xmm4
 	andl	%ebx,%esi
 	movl	%ebp,%ebx
-	jmp	L006loop
+	jmp	L004loop
 .align	4,0x90
-L007done:
+L005done:
 	addl	16(%esp),%ebx
 	xorl	%edi,%esi
 	movl	%ecx,%ebp
@@ -2778,6 +2612,1175 @@ L007done:
 	popl	%ebx
 	popl	%ebp
 	ret
+.private_extern	__sha1_block_data_order_avx
+.align	4
+__sha1_block_data_order_avx:
+	pushl	%ebp
+	pushl	%ebx
+	pushl	%esi
+	pushl	%edi
+	call	L006pic_point
+L006pic_point:
+	popl	%ebp
+	leal	LK_XX_XX-L006pic_point(%ebp),%ebp
+Lavx_shortcut:
+	vzeroall
+	vmovdqa	(%ebp),%xmm7
+	vmovdqa	16(%ebp),%xmm0
+	vmovdqa	32(%ebp),%xmm1
+	vmovdqa	48(%ebp),%xmm2
+	vmovdqa	64(%ebp),%xmm6
+	movl	20(%esp),%edi
+	movl	24(%esp),%ebp
+	movl	28(%esp),%edx
+	movl	%esp,%esi
+	subl	$208,%esp
+	andl	$-64,%esp
+	vmovdqa	%xmm0,112(%esp)
+	vmovdqa	%xmm1,128(%esp)
+	vmovdqa	%xmm2,144(%esp)
+	shll	$6,%edx
+	vmovdqa	%xmm7,160(%esp)
+	addl	%ebp,%edx
+	vmovdqa	%xmm6,176(%esp)
+	addl	$64,%ebp
+	movl	%edi,192(%esp)
+	movl	%ebp,196(%esp)
+	movl	%edx,200(%esp)
+	movl	%esi,204(%esp)
+	movl	(%edi),%eax
+	movl	4(%edi),%ebx
+	movl	8(%edi),%ecx
+	movl	12(%edi),%edx
+	movl	16(%edi),%edi
+	movl	%ebx,%esi
+	vmovdqu	-64(%ebp),%xmm0
+	vmovdqu	-48(%ebp),%xmm1
+	vmovdqu	-32(%ebp),%xmm2
+	vmovdqu	-16(%ebp),%xmm3
+	vpshufb	%xmm6,%xmm0,%xmm0
+	vpshufb	%xmm6,%xmm1,%xmm1
+	vpshufb	%xmm6,%xmm2,%xmm2
+	vmovdqa	%xmm7,96(%esp)
+	vpshufb	%xmm6,%xmm3,%xmm3
+	vpaddd	%xmm7,%xmm0,%xmm4
+	vpaddd	%xmm7,%xmm1,%xmm5
+	vpaddd	%xmm7,%xmm2,%xmm6
+	vmovdqa	%xmm4,(%esp)
+	movl	%ecx,%ebp
+	vmovdqa	%xmm5,16(%esp)
+	xorl	%edx,%ebp
+	vmovdqa	%xmm6,32(%esp)
+	andl	%ebp,%esi
+	jmp	L007loop
+.align	4,0x90
+L007loop:
+	shrdl	$2,%ebx,%ebx
+	xorl	%edx,%esi
+	vpalignr	$8,%xmm0,%xmm1,%xmm4
+	movl	%eax,%ebp
+	addl	(%esp),%edi
+	vpaddd	%xmm3,%xmm7,%xmm7
+	vmovdqa	%xmm0,64(%esp)
+	xorl	%ecx,%ebx
+	shldl	$5,%eax,%eax
+	vpsrldq	$4,%xmm3,%xmm6
+	addl	%esi,%edi
+	andl	%ebx,%ebp
+	vpxor	%xmm0,%xmm4,%xmm4
+	xorl	%ecx,%ebx
+	addl	%eax,%edi
+	vpxor	%xmm2,%xmm6,%xmm6
+	shrdl	$7,%eax,%eax
+	xorl	%ecx,%ebp
+	vmovdqa	%xmm7,48(%esp)
+	movl	%edi,%esi
+	addl	4(%esp),%edx
+	vpxor	%xmm6,%xmm4,%xmm4
+	xorl	%ebx,%eax
+	shldl	$5,%edi,%edi
+	addl	%ebp,%edx
+	andl	%eax,%esi
+	vpsrld	$31,%xmm4,%xmm6
+	xorl	%ebx,%eax
+	addl	%edi,%edx
+	shrdl	$7,%edi,%edi
+	xorl	%ebx,%esi
+	vpslldq	$12,%xmm4,%xmm0
+	vpaddd	%xmm4,%xmm4,%xmm4
+	movl	%edx,%ebp
+	addl	8(%esp),%ecx
+	xorl	%eax,%edi
+	shldl	$5,%edx,%edx
+	vpsrld	$30,%xmm0,%xmm7
+	vpor	%xmm6,%xmm4,%xmm4
+	addl	%esi,%ecx
+	andl	%edi,%ebp
+	xorl	%eax,%edi
+	addl	%edx,%ecx
+	vpslld	$2,%xmm0,%xmm0
+	shrdl	$7,%edx,%edx
+	xorl	%eax,%ebp
+	vpxor	%xmm7,%xmm4,%xmm4
+	movl	%ecx,%esi
+	addl	12(%esp),%ebx
+	xorl	%edi,%edx
+	shldl	$5,%ecx,%ecx
+	vpxor	%xmm0,%xmm4,%xmm4
+	addl	%ebp,%ebx
+	andl	%edx,%esi
+	vmovdqa	96(%esp),%xmm0
+	xorl	%edi,%edx
+	addl	%ecx,%ebx
+	shrdl	$7,%ecx,%ecx
+	xorl	%edi,%esi
+	vpalignr	$8,%xmm1,%xmm2,%xmm5
+	movl	%ebx,%ebp
+	addl	16(%esp),%eax
+	vpaddd	%xmm4,%xmm0,%xmm0
+	vmovdqa	%xmm1,80(%esp)
+	xorl	%edx,%ecx
+	shldl	$5,%ebx,%ebx
+	vpsrldq	$4,%xmm4,%xmm7
+	addl	%esi,%eax
+	andl	%ecx,%ebp
+	vpxor	%xmm1,%xmm5,%xmm5
+	xorl	%edx,%ecx
+	addl	%ebx,%eax
+	vpxor	%xmm3,%xmm7,%xmm7
+	shrdl	$7,%ebx,%ebx
+	xorl	%edx,%ebp
+	vmovdqa	%xmm0,(%esp)
+	movl	%eax,%esi
+	addl	20(%esp),%edi
+	vpxor	%xmm7,%xmm5,%xmm5
+	xorl	%ecx,%ebx
+	shldl	$5,%eax,%eax
+	addl	%ebp,%edi
+	andl	%ebx,%esi
+	vpsrld	$31,%xmm5,%xmm7
+	xorl	%ecx,%ebx
+	addl	%eax,%edi
+	shrdl	$7,%eax,%eax
+	xorl	%ecx,%esi
+	vpslldq	$12,%xmm5,%xmm1
+	vpaddd	%xmm5,%xmm5,%xmm5
+	movl	%edi,%ebp
+	addl	24(%esp),%edx
+	xorl	%ebx,%eax
+	shldl	$5,%edi,%edi
+	vpsrld	$30,%xmm1,%xmm0
+	vpor	%xmm7,%xmm5,%xmm5
+	addl	%esi,%edx
+	andl	%eax,%ebp
+	xorl	%ebx,%eax
+	addl	%edi,%edx
+	vpslld	$2,%xmm1,%xmm1
+	shrdl	$7,%edi,%edi
+	xorl	%ebx,%ebp
+	vpxor	%xmm0,%xmm5,%xmm5
+	movl	%edx,%esi
+	addl	28(%esp),%ecx
+	xorl	%eax,%edi
+	shldl	$5,%edx,%edx
+	vpxor	%xmm1,%xmm5,%xmm5
+	addl	%ebp,%ecx
+	andl	%edi,%esi
+	vmovdqa	112(%esp),%xmm1
+	xorl	%eax,%edi
+	addl	%edx,%ecx
+	shrdl	$7,%edx,%edx
+	xorl	%eax,%esi
+	vpalignr	$8,%xmm2,%xmm3,%xmm6
+	movl	%ecx,%ebp
+	addl	32(%esp),%ebx
+	vpaddd	%xmm5,%xmm1,%xmm1
+	vmovdqa	%xmm2,96(%esp)
+	xorl	%edi,%edx
+	shldl	$5,%ecx,%ecx
+	vpsrldq	$4,%xmm5,%xmm0
+	addl	%esi,%ebx
+	andl	%edx,%ebp
+	vpxor	%xmm2,%xmm6,%xmm6
+	xorl	%edi,%edx
+	addl	%ecx,%ebx
+	vpxor	%xmm4,%xmm0,%xmm0
+	shrdl	$7,%ecx,%ecx
+	xorl	%edi,%ebp
+	vmovdqa	%xmm1,16(%esp)
+	movl	%ebx,%esi
+	addl	36(%esp),%eax
+	vpxor	%xmm0,%xmm6,%xmm6
+	xorl	%edx,%ecx
+	shldl	$5,%ebx,%ebx
+	addl	%ebp,%eax
+	andl	%ecx,%esi
+	vpsrld	$31,%xmm6,%xmm0
+	xorl	%edx,%ecx
+	addl	%ebx,%eax
+	shrdl	$7,%ebx,%ebx
+	xorl	%edx,%esi
+	vpslldq	$12,%xmm6,%xmm2
+	vpaddd	%xmm6,%xmm6,%xmm6
+	movl	%eax,%ebp
+	addl	40(%esp),%edi
+	xorl	%ecx,%ebx
+	shldl	$5,%eax,%eax
+	vpsrld	$30,%xmm2,%xmm1
+	vpor	%xmm0,%xmm6,%xmm6
+	addl	%esi,%edi
+	andl	%ebx,%ebp
+	xorl	%ecx,%ebx
+	addl	%eax,%edi
+	vpslld	$2,%xmm2,%xmm2
+	vmovdqa	64(%esp),%xmm0
+	shrdl	$7,%eax,%eax
+	xorl	%ecx,%ebp
+	vpxor	%xmm1,%xmm6,%xmm6
+	movl	%edi,%esi
+	addl	44(%esp),%edx
+	xorl	%ebx,%eax
+	shldl	$5,%edi,%edi
+	vpxor	%xmm2,%xmm6,%xmm6
+	addl	%ebp,%edx
+	andl	%eax,%esi
+	vmovdqa	112(%esp),%xmm2
+	xorl	%ebx,%eax
+	addl	%edi,%edx
+	shrdl	$7,%edi,%edi
+	xorl	%ebx,%esi
+	vpalignr	$8,%xmm3,%xmm4,%xmm7
+	movl	%edx,%ebp
+	addl	48(%esp),%ecx
+	vpaddd	%xmm6,%xmm2,%xmm2
+	vmovdqa	%xmm3,64(%esp)
+	xorl	%eax,%edi
+	shldl	$5,%edx,%edx
+	vpsrldq	$4,%xmm6,%xmm1
+	addl	%esi,%ecx
+	andl	%edi,%ebp
+	vpxor	%xmm3,%xmm7,%xmm7
+	xorl	%eax,%edi
+	addl	%edx,%ecx
+	vpxor	%xmm5,%xmm1,%xmm1
+	shrdl	$7,%edx,%edx
+	xorl	%eax,%ebp
+	vmovdqa	%xmm2,32(%esp)
+	movl	%ecx,%esi
+	addl	52(%esp),%ebx
+	vpxor	%xmm1,%xmm7,%xmm7
+	xorl	%edi,%edx
+	shldl	$5,%ecx,%ecx
+	addl	%ebp,%ebx
+	andl	%edx,%esi
+	vpsrld	$31,%xmm7,%xmm1
+	xorl	%edi,%edx
+	addl	%ecx,%ebx
+	shrdl	$7,%ecx,%ecx
+	xorl	%edi,%esi
+	vpslldq	$12,%xmm7,%xmm3
+	vpaddd	%xmm7,%xmm7,%xmm7
+	movl	%ebx,%ebp
+	addl	56(%esp),%eax
+	xorl	%edx,%ecx
+	shldl	$5,%ebx,%ebx
+	vpsrld	$30,%xmm3,%xmm2
+	vpor	%xmm1,%xmm7,%xmm7
+	addl	%esi,%eax
+	andl	%ecx,%ebp
+	xorl	%edx,%ecx
+	addl	%ebx,%eax
+	vpslld	$2,%xmm3,%xmm3
+	vmovdqa	80(%esp),%xmm1
+	shrdl	$7,%ebx,%ebx
+	xorl	%edx,%ebp
+	vpxor	%xmm2,%xmm7,%xmm7
+	movl	%eax,%esi
+	addl	60(%esp),%edi
+	xorl	%ecx,%ebx
+	shldl	$5,%eax,%eax
+	vpxor	%xmm3,%xmm7,%xmm7
+	addl	%ebp,%edi
+	andl	%ebx,%esi
+	vmovdqa	112(%esp),%xmm3
+	xorl	%ecx,%ebx
+	addl	%eax,%edi
+	vpalignr	$8,%xmm6,%xmm7,%xmm2
+	vpxor	%xmm4,%xmm0,%xmm0
+	shrdl	$7,%eax,%eax
+	xorl	%ecx,%esi
+	movl	%edi,%ebp
+	addl	(%esp),%edx
+	vpxor	%xmm1,%xmm0,%xmm0
+	vmovdqa	%xmm4,80(%esp)
+	xorl	%ebx,%eax
+	shldl	$5,%edi,%edi
+	vmovdqa	%xmm3,%xmm4
+	vpaddd	%xmm7,%xmm3,%xmm3
+	addl	%esi,%edx
+	andl	%eax,%ebp
+	vpxor	%xmm2,%xmm0,%xmm0
+	xorl	%ebx,%eax
+	addl	%edi,%edx
+	shrdl	$7,%edi,%edi
+	xorl	%ebx,%ebp
+	vpsrld	$30,%xmm0,%xmm2
+	vmovdqa	%xmm3,48(%esp)
+	movl	%edx,%esi
+	addl	4(%esp),%ecx
+	xorl	%eax,%edi
+	shldl	$5,%edx,%edx
+	vpslld	$2,%xmm0,%xmm0
+	addl	%ebp,%ecx
+	andl	%edi,%esi
+	xorl	%eax,%edi
+	addl	%edx,%ecx
+	shrdl	$7,%edx,%edx
+	xorl	%eax,%esi
+	movl	%ecx,%ebp
+	addl	8(%esp),%ebx
+	vpor	%xmm2,%xmm0,%xmm0
+	xorl	%edi,%edx
+	shldl	$5,%ecx,%ecx
+	vmovdqa	96(%esp),%xmm2
+	addl	%esi,%ebx
+	andl	%edx,%ebp
+	xorl	%edi,%edx
+	addl	%ecx,%ebx
+	addl	12(%esp),%eax
+	xorl	%edi,%ebp
+	movl	%ebx,%esi
+	shldl	$5,%ebx,%ebx
+	addl	%ebp,%eax
+	xorl	%edx,%esi
+	shrdl	$7,%ecx,%ecx
+	addl	%ebx,%eax
+	vpalignr	$8,%xmm7,%xmm0,%xmm3
+	vpxor	%xmm5,%xmm1,%xmm1
+	addl	16(%esp),%edi
+	xorl	%ecx,%esi
+	movl	%eax,%ebp
+	shldl	$5,%eax,%eax
+	vpxor	%xmm2,%xmm1,%xmm1
+	vmovdqa	%xmm5,96(%esp)
+	addl	%esi,%edi
+	xorl	%ecx,%ebp
+	vmovdqa	%xmm4,%xmm5
+	vpaddd	%xmm0,%xmm4,%xmm4
+	shrdl	$7,%ebx,%ebx
+	addl	%eax,%edi
+	vpxor	%xmm3,%xmm1,%xmm1
+	addl	20(%esp),%edx
+	xorl	%ebx,%ebp
+	movl	%edi,%esi
+	shldl	$5,%edi,%edi
+	vpsrld	$30,%xmm1,%xmm3
+	vmovdqa	%xmm4,(%esp)
+	addl	%ebp,%edx
+	xorl	%ebx,%esi
+	shrdl	$7,%eax,%eax
+	addl	%edi,%edx
+	vpslld	$2,%xmm1,%xmm1
+	addl	24(%esp),%ecx
+	xorl	%eax,%esi
+	movl	%edx,%ebp
+	shldl	$5,%edx,%edx
+	addl	%esi,%ecx
+	xorl	%eax,%ebp
+	shrdl	$7,%edi,%edi
+	addl	%edx,%ecx
+	vpor	%xmm3,%xmm1,%xmm1
+	addl	28(%esp),%ebx
+	xorl	%edi,%ebp
+	vmovdqa	64(%esp),%xmm3
+	movl	%ecx,%esi
+	shldl	$5,%ecx,%ecx
+	addl	%ebp,%ebx
+	xorl	%edi,%esi
+	shrdl	$7,%edx,%edx
+	addl	%ecx,%ebx
+	vpalignr	$8,%xmm0,%xmm1,%xmm4
+	vpxor	%xmm6,%xmm2,%xmm2
+	addl	32(%esp),%eax
+	xorl	%edx,%esi
+	movl	%ebx,%ebp
+	shldl	$5,%ebx,%ebx
+	vpxor	%xmm3,%xmm2,%xmm2
+	vmovdqa	%xmm6,64(%esp)
+	addl	%esi,%eax
+	xorl	%edx,%ebp
+	vmovdqa	128(%esp),%xmm6
+	vpaddd	%xmm1,%xmm5,%xmm5
+	shrdl	$7,%ecx,%ecx
+	addl	%ebx,%eax
+	vpxor	%xmm4,%xmm2,%xmm2
+	addl	36(%esp),%edi
+	xorl	%ecx,%ebp
+	movl	%eax,%esi
+	shldl	$5,%eax,%eax
+	vpsrld	$30,%xmm2,%xmm4
+	vmovdqa	%xmm5,16(%esp)
+	addl	%ebp,%edi
+	xorl	%ecx,%esi
+	shrdl	$7,%ebx,%ebx
+	addl	%eax,%edi
+	vpslld	$2,%xmm2,%xmm2
+	addl	40(%esp),%edx
+	xorl	%ebx,%esi
+	movl	%edi,%ebp
+	shldl	$5,%edi,%edi
+	addl	%esi,%edx
+	xorl	%ebx,%ebp
+	shrdl	$7,%eax,%eax
+	addl	%edi,%edx
+	vpor	%xmm4,%xmm2,%xmm2
+	addl	44(%esp),%ecx
+	xorl	%eax,%ebp
+	vmovdqa	80(%esp),%xmm4
+	movl	%edx,%esi
+	shldl	$5,%edx,%edx
+	addl	%ebp,%ecx
+	xorl	%eax,%esi
+	shrdl	$7,%edi,%edi
+	addl	%edx,%ecx
+	vpalignr	$8,%xmm1,%xmm2,%xmm5
+	vpxor	%xmm7,%xmm3,%xmm3
+	addl	48(%esp),%ebx
+	xorl	%edi,%esi
+	movl	%ecx,%ebp
+	shldl	$5,%ecx,%ecx
+	vpxor	%xmm4,%xmm3,%xmm3
+	vmovdqa	%xmm7,80(%esp)
+	addl	%esi,%ebx
+	xorl	%edi,%ebp
+	vmovdqa	%xmm6,%xmm7
+	vpaddd	%xmm2,%xmm6,%xmm6
+	shrdl	$7,%edx,%edx
+	addl	%ecx,%ebx
+	vpxor	%xmm5,%xmm3,%xmm3
+	addl	52(%esp),%eax
+	xorl	%edx,%ebp
+	movl	%ebx,%esi
+	shldl	$5,%ebx,%ebx
+	vpsrld	$30,%xmm3,%xmm5
+	vmovdqa	%xmm6,32(%esp)
+	addl	%ebp,%eax
+	xorl	%edx,%esi
+	shrdl	$7,%ecx,%ecx
+	addl	%ebx,%eax
+	vpslld	$2,%xmm3,%xmm3
+	addl	56(%esp),%edi
+	xorl	%ecx,%esi
+	movl	%eax,%ebp
+	shldl	$5,%eax,%eax
+	addl	%esi,%edi
+	xorl	%ecx,%ebp
+	shrdl	$7,%ebx,%ebx
+	addl	%eax,%edi
+	vpor	%xmm5,%xmm3,%xmm3
+	addl	60(%esp),%edx
+	xorl	%ebx,%ebp
+	vmovdqa	96(%esp),%xmm5
+	movl	%edi,%esi
+	shldl	$5,%edi,%edi
+	addl	%ebp,%edx
+	xorl	%ebx,%esi
+	shrdl	$7,%eax,%eax
+	addl	%edi,%edx
+	vpalignr	$8,%xmm2,%xmm3,%xmm6
+	vpxor	%xmm0,%xmm4,%xmm4
+	addl	(%esp),%ecx
+	xorl	%eax,%esi
+	movl	%edx,%ebp
+	shldl	$5,%edx,%edx
+	vpxor	%xmm5,%xmm4,%xmm4
+	vmovdqa	%xmm0,96(%esp)
+	addl	%esi,%ecx
+	xorl	%eax,%ebp
+	vmovdqa	%xmm7,%xmm0
+	vpaddd	%xmm3,%xmm7,%xmm7
+	shrdl	$7,%edi,%edi
+	addl	%edx,%ecx
+	vpxor	%xmm6,%xmm4,%xmm4
+	addl	4(%esp),%ebx
+	xorl	%edi,%ebp
+	movl	%ecx,%esi
+	shldl	$5,%ecx,%ecx
+	vpsrld	$30,%xmm4,%xmm6
+	vmovdqa	%xmm7,48(%esp)
+	addl	%ebp,%ebx
+	xorl	%edi,%esi
+	shrdl	$7,%edx,%edx
+	addl	%ecx,%ebx
+	vpslld	$2,%xmm4,%xmm4
+	addl	8(%esp),%eax
+	xorl	%edx,%esi
+	movl	%ebx,%ebp
+	shldl	$5,%ebx,%ebx
+	addl	%esi,%eax
+	xorl	%edx,%ebp
+	shrdl	$7,%ecx,%ecx
+	addl	%ebx,%eax
+	vpor	%xmm6,%xmm4,%xmm4
+	addl	12(%esp),%edi
+	xorl	%ecx,%ebp
+	vmovdqa	64(%esp),%xmm6
+	movl	%eax,%esi
+	shldl	$5,%eax,%eax
+	addl	%ebp,%edi
+	xorl	%ecx,%esi
+	shrdl	$7,%ebx,%ebx
+	addl	%eax,%edi
+	vpalignr	$8,%xmm3,%xmm4,%xmm7
+	vpxor	%xmm1,%xmm5,%xmm5
+	addl	16(%esp),%edx
+	xorl	%ebx,%esi
+	movl	%edi,%ebp
+	shldl	$5,%edi,%edi
+	vpxor	%xmm6,%xmm5,%xmm5
+	vmovdqa	%xmm1,64(%esp)
+	addl	%esi,%edx
+	xorl	%ebx,%ebp
+	vmovdqa	%xmm0,%xmm1
+	vpaddd	%xmm4,%xmm0,%xmm0
+	shrdl	$7,%eax,%eax
+	addl	%edi,%edx
+	vpxor	%xmm7,%xmm5,%xmm5
+	addl	20(%esp),%ecx
+	xorl	%eax,%ebp
+	movl	%edx,%esi
+	shldl	$5,%edx,%edx
+	vpsrld	$30,%xmm5,%xmm7
+	vmovdqa	%xmm0,(%esp)
+	addl	%ebp,%ecx
+	xorl	%eax,%esi
+	shrdl	$7,%edi,%edi
+	addl	%edx,%ecx
+	vpslld	$2,%xmm5,%xmm5
+	addl	24(%esp),%ebx
+	xorl	%edi,%esi
+	movl	%ecx,%ebp
+	shldl	$5,%ecx,%ecx
+	addl	%esi,%ebx
+	xorl	%edi,%ebp
+	shrdl	$7,%edx,%edx
+	addl	%ecx,%ebx
+	vpor	%xmm7,%xmm5,%xmm5
+	addl	28(%esp),%eax
+	vmovdqa	80(%esp),%xmm7
+	shrdl	$7,%ecx,%ecx
+	movl	%ebx,%esi
+	xorl	%edx,%ebp
+	shldl	$5,%ebx,%ebx
+	addl	%ebp,%eax
+	xorl	%ecx,%esi
+	xorl	%edx,%ecx
+	addl	%ebx,%eax
+	vpalignr	$8,%xmm4,%xmm5,%xmm0
+	vpxor	%xmm2,%xmm6,%xmm6
+	addl	32(%esp),%edi
+	andl	%ecx,%esi
+	xorl	%edx,%ecx
+	shrdl	$7,%ebx,%ebx
+	vpxor	%xmm7,%xmm6,%xmm6
+	vmovdqa	%xmm2,80(%esp)
+	movl	%eax,%ebp
+	xorl	%ecx,%esi
+	vmovdqa	%xmm1,%xmm2
+	vpaddd	%xmm5,%xmm1,%xmm1
+	shldl	$5,%eax,%eax
+	addl	%esi,%edi
+	vpxor	%xmm0,%xmm6,%xmm6
+	xorl	%ebx,%ebp
+	xorl	%ecx,%ebx
+	addl	%eax,%edi
+	addl	36(%esp),%edx
+	vpsrld	$30,%xmm6,%xmm0
+	vmovdqa	%xmm1,16(%esp)
+	andl	%ebx,%ebp
+	xorl	%ecx,%ebx
+	shrdl	$7,%eax,%eax
+	movl	%edi,%esi
+	vpslld	$2,%xmm6,%xmm6
+	xorl	%ebx,%ebp
+	shldl	$5,%edi,%edi
+	addl	%ebp,%edx
+	xorl	%eax,%esi
+	xorl	%ebx,%eax
+	addl	%edi,%edx
+	addl	40(%esp),%ecx
+	andl	%eax,%esi
+	vpor	%xmm0,%xmm6,%xmm6
+	xorl	%ebx,%eax
+	shrdl	$7,%edi,%edi
+	vmovdqa	96(%esp),%xmm0
+	movl	%edx,%ebp
+	xorl	%eax,%esi
+	shldl	$5,%edx,%edx
+	addl	%esi,%ecx
+	xorl	%edi,%ebp
+	xorl	%eax,%edi
+	addl	%edx,%ecx
+	addl	44(%esp),%ebx
+	andl	%edi,%ebp
+	xorl	%eax,%edi
+	shrdl	$7,%edx,%edx
+	movl	%ecx,%esi
+	xorl	%edi,%ebp
+	shldl	$5,%ecx,%ecx
+	addl	%ebp,%ebx
+	xorl	%edx,%esi
+	xorl	%edi,%edx
+	addl	%ecx,%ebx
+	vpalignr	$8,%xmm5,%xmm6,%xmm1
+	vpxor	%xmm3,%xmm7,%xmm7
+	addl	48(%esp),%eax
+	andl	%edx,%esi
+	xorl	%edi,%edx
+	shrdl	$7,%ecx,%ecx
+	vpxor	%xmm0,%xmm7,%xmm7
+	vmovdqa	%xmm3,96(%esp)
+	movl	%ebx,%ebp
+	xorl	%edx,%esi
+	vmovdqa	144(%esp),%xmm3
+	vpaddd	%xmm6,%xmm2,%xmm2
+	shldl	$5,%ebx,%ebx
+	addl	%esi,%eax
+	vpxor	%xmm1,%xmm7,%xmm7
+	xorl	%ecx,%ebp
+	xorl	%edx,%ecx
+	addl	%ebx,%eax
+	addl	52(%esp),%edi
+	vpsrld	$30,%xmm7,%xmm1
+	vmovdqa	%xmm2,32(%esp)
+	andl	%ecx,%ebp
+	xorl	%edx,%ecx
+	shrdl	$7,%ebx,%ebx
+	movl	%eax,%esi
+	vpslld	$2,%xmm7,%xmm7
+	xorl	%ecx,%ebp
+	shldl	$5,%eax,%eax
+	addl	%ebp,%edi
+	xorl	%ebx,%esi
+	xorl	%ecx,%ebx
+	addl	%eax,%edi
+	addl	56(%esp),%edx
+	andl	%ebx,%esi
+	vpor	%xmm1,%xmm7,%xmm7
+	xorl	%ecx,%ebx
+	shrdl	$7,%eax,%eax
+	vmovdqa	64(%esp),%xmm1
+	movl	%edi,%ebp
+	xorl	%ebx,%esi
+	shldl	$5,%edi,%edi
+	addl	%esi,%edx
+	xorl	%eax,%ebp
+	xorl	%ebx,%eax
+	addl	%edi,%edx
+	addl	60(%esp),%ecx
+	andl	%eax,%ebp
+	xorl	%ebx,%eax
+	shrdl	$7,%edi,%edi
+	movl	%edx,%esi
+	xorl	%eax,%ebp
+	shldl	$5,%edx,%edx
+	addl	%ebp,%ecx
+	xorl	%edi,%esi
+	xorl	%eax,%edi
+	addl	%edx,%ecx
+	vpalignr	$8,%xmm6,%xmm7,%xmm2
+	vpxor	%xmm4,%xmm0,%xmm0
+	addl	(%esp),%ebx
+	andl	%edi,%esi
+	xorl	%eax,%edi
+	shrdl	$7,%edx,%edx
+	vpxor	%xmm1,%xmm0,%xmm0
+	vmovdqa	%xmm4,64(%esp)
+	movl	%ecx,%ebp
+	xorl	%edi,%esi
+	vmovdqa	%xmm3,%xmm4
+	vpaddd	%xmm7,%xmm3,%xmm3
+	shldl	$5,%ecx,%ecx
+	addl	%esi,%ebx
+	vpxor	%xmm2,%xmm0,%xmm0
+	xorl	%edx,%ebp
+	xorl	%edi,%edx
+	addl	%ecx,%ebx
+	addl	4(%esp),%eax
+	vpsrld	$30,%xmm0,%xmm2
+	vmovdqa	%xmm3,48(%esp)
+	andl	%edx,%ebp
+	xorl	%edi,%edx
+	shrdl	$7,%ecx,%ecx
+	movl	%ebx,%esi
+	vpslld	$2,%xmm0,%xmm0
+	xorl	%edx,%ebp
+	shldl	$5,%ebx,%ebx
+	addl	%ebp,%eax
+	xorl	%ecx,%esi
+	xorl	%edx,%ecx
+	addl	%ebx,%eax
+	addl	8(%esp),%edi
+	andl	%ecx,%esi
+	vpor	%xmm2,%xmm0,%xmm0
+	xorl	%edx,%ecx
+	shrdl	$7,%ebx,%ebx
+	vmovdqa	80(%esp),%xmm2
+	movl	%eax,%ebp
+	xorl	%ecx,%esi
+	shldl	$5,%eax,%eax
+	addl	%esi,%edi
+	xorl	%ebx,%ebp
+	xorl	%ecx,%ebx
+	addl	%eax,%edi
+	addl	12(%esp),%edx
+	andl	%ebx,%ebp
+	xorl	%ecx,%ebx
+	shrdl	$7,%eax,%eax
+	movl	%edi,%esi
+	xorl	%ebx,%ebp
+	shldl	$5,%edi,%edi
+	addl	%ebp,%edx
+	xorl	%eax,%esi
+	xorl	%ebx,%eax
+	addl	%edi,%edx
+	vpalignr	$8,%xmm7,%xmm0,%xmm3
+	vpxor	%xmm5,%xmm1,%xmm1
+	addl	16(%esp),%ecx
+	andl	%eax,%esi
+	xorl	%ebx,%eax
+	shrdl	$7,%edi,%edi
+	vpxor	%xmm2,%xmm1,%xmm1
+	vmovdqa	%xmm5,80(%esp)
+	movl	%edx,%ebp
+	xorl	%eax,%esi
+	vmovdqa	%xmm4,%xmm5
+	vpaddd	%xmm0,%xmm4,%xmm4
+	shldl	$5,%edx,%edx
+	addl	%esi,%ecx
+	vpxor	%xmm3,%xmm1,%xmm1
+	xorl	%edi,%ebp
+	xorl	%eax,%edi
+	addl	%edx,%ecx
+	addl	20(%esp),%ebx
+	vpsrld	$30,%xmm1,%xmm3
+	vmovdqa	%xmm4,(%esp)
+	andl	%edi,%ebp
+	xorl	%eax,%edi
+	shrdl	$7,%edx,%edx
+	movl	%ecx,%esi
+	vpslld	$2,%xmm1,%xmm1
+	xorl	%edi,%ebp
+	shldl	$5,%ecx,%ecx
+	addl	%ebp,%ebx
+	xorl	%edx,%esi
+	xorl	%edi,%edx
+	addl	%ecx,%ebx
+	addl	24(%esp),%eax
+	andl	%edx,%esi
+	vpor	%xmm3,%xmm1,%xmm1
+	xorl	%edi,%edx
+	shrdl	$7,%ecx,%ecx
+	vmovdqa	96(%esp),%xmm3
+	movl	%ebx,%ebp
+	xorl	%edx,%esi
+	shldl	$5,%ebx,%ebx
+	addl	%esi,%eax
+	xorl	%ecx,%ebp
+	xorl	%edx,%ecx
+	addl	%ebx,%eax
+	addl	28(%esp),%edi
+	andl	%ecx,%ebp
+	xorl	%edx,%ecx
+	shrdl	$7,%ebx,%ebx
+	movl	%eax,%esi
+	xorl	%ecx,%ebp
+	shldl	$5,%eax,%eax
+	addl	%ebp,%edi
+	xorl	%ebx,%esi
+	xorl	%ecx,%ebx
+	addl	%eax,%edi
+	vpalignr	$8,%xmm0,%xmm1,%xmm4
+	vpxor	%xmm6,%xmm2,%xmm2
+	addl	32(%esp),%edx
+	andl	%ebx,%esi
+	xorl	%ecx,%ebx
+	shrdl	$7,%eax,%eax
+	vpxor	%xmm3,%xmm2,%xmm2
+	vmovdqa	%xmm6,96(%esp)
+	movl	%edi,%ebp
+	xorl	%ebx,%esi
+	vmovdqa	%xmm5,%xmm6
+	vpaddd	%xmm1,%xmm5,%xmm5
+	shldl	$5,%edi,%edi
+	addl	%esi,%edx
+	vpxor	%xmm4,%xmm2,%xmm2
+	xorl	%eax,%ebp
+	xorl	%ebx,%eax
+	addl	%edi,%edx
+	addl	36(%esp),%ecx
+	vpsrld	$30,%xmm2,%xmm4
+	vmovdqa	%xmm5,16(%esp)
+	andl	%eax,%ebp
+	xorl	%ebx,%eax
+	shrdl	$7,%edi,%edi
+	movl	%edx,%esi
+	vpslld	$2,%xmm2,%xmm2
+	xorl	%eax,%ebp
+	shldl	$5,%edx,%edx
+	addl	%ebp,%ecx
+	xorl	%edi,%esi
+	xorl	%eax,%edi
+	addl	%edx,%ecx
+	addl	40(%esp),%ebx
+	andl	%edi,%esi
+	vpor	%xmm4,%xmm2,%xmm2
+	xorl	%eax,%edi
+	shrdl	$7,%edx,%edx
+	vmovdqa	64(%esp),%xmm4
+	movl	%ecx,%ebp
+	xorl	%edi,%esi
+	shldl	$5,%ecx,%ecx
+	addl	%esi,%ebx
+	xorl	%edx,%ebp
+	xorl	%edi,%edx
+	addl	%ecx,%ebx
+	addl	44(%esp),%eax
+	andl	%edx,%ebp
+	xorl	%edi,%edx
+	shrdl	$7,%ecx,%ecx
+	movl	%ebx,%esi
+	xorl	%edx,%ebp
+	shldl	$5,%ebx,%ebx
+	addl	%ebp,%eax
+	xorl	%edx,%esi
+	addl	%ebx,%eax
+	vpalignr	$8,%xmm1,%xmm2,%xmm5
+	vpxor	%xmm7,%xmm3,%xmm3
+	addl	48(%esp),%edi
+	xorl	%ecx,%esi
+	movl	%eax,%ebp
+	shldl	$5,%eax,%eax
+	vpxor	%xmm4,%xmm3,%xmm3
+	vmovdqa	%xmm7,64(%esp)
+	addl	%esi,%edi
+	xorl	%ecx,%ebp
+	vmovdqa	%xmm6,%xmm7
+	vpaddd	%xmm2,%xmm6,%xmm6
+	shrdl	$7,%ebx,%ebx
+	addl	%eax,%edi
+	vpxor	%xmm5,%xmm3,%xmm3
+	addl	52(%esp),%edx
+	xorl	%ebx,%ebp
+	movl	%edi,%esi
+	shldl	$5,%edi,%edi
+	vpsrld	$30,%xmm3,%xmm5
+	vmovdqa	%xmm6,32(%esp)
+	addl	%ebp,%edx
+	xorl	%ebx,%esi
+	shrdl	$7,%eax,%eax
+	addl	%edi,%edx
+	vpslld	$2,%xmm3,%xmm3
+	addl	56(%esp),%ecx
+	xorl	%eax,%esi
+	movl	%edx,%ebp
+	shldl	$5,%edx,%edx
+	addl	%esi,%ecx
+	xorl	%eax,%ebp
+	shrdl	$7,%edi,%edi
+	addl	%edx,%ecx
+	vpor	%xmm5,%xmm3,%xmm3
+	addl	60(%esp),%ebx
+	xorl	%edi,%ebp
+	movl	%ecx,%esi
+	shldl	$5,%ecx,%ecx
+	addl	%ebp,%ebx
+	xorl	%edi,%esi
+	shrdl	$7,%edx,%edx
+	addl	%ecx,%ebx
+	addl	(%esp),%eax
+	vpaddd	%xmm3,%xmm7,%xmm7
+	xorl	%edx,%esi
+	movl	%ebx,%ebp
+	shldl	$5,%ebx,%ebx
+	addl	%esi,%eax
+	vmovdqa	%xmm7,48(%esp)
+	xorl	%edx,%ebp
+	shrdl	$7,%ecx,%ecx
+	addl	%ebx,%eax
+	addl	4(%esp),%edi
+	xorl	%ecx,%ebp
+	movl	%eax,%esi
+	shldl	$5,%eax,%eax
+	addl	%ebp,%edi
+	xorl	%ecx,%esi
+	shrdl	$7,%ebx,%ebx
+	addl	%eax,%edi
+	addl	8(%esp),%edx
+	xorl	%ebx,%esi
+	movl	%edi,%ebp
+	shldl	$5,%edi,%edi
+	addl	%esi,%edx
+	xorl	%ebx,%ebp
+	shrdl	$7,%eax,%eax
+	addl	%edi,%edx
+	addl	12(%esp),%ecx
+	xorl	%eax,%ebp
+	movl	%edx,%esi
+	shldl	$5,%edx,%edx
+	addl	%ebp,%ecx
+	xorl	%eax,%esi
+	shrdl	$7,%edi,%edi
+	addl	%edx,%ecx
+	movl	196(%esp),%ebp
+	cmpl	200(%esp),%ebp
+	je	L008done
+	vmovdqa	160(%esp),%xmm7
+	vmovdqa	176(%esp),%xmm6
+	vmovdqu	(%ebp),%xmm0
+	vmovdqu	16(%ebp),%xmm1
+	vmovdqu	32(%ebp),%xmm2
+	vmovdqu	48(%ebp),%xmm3
+	addl	$64,%ebp
+	vpshufb	%xmm6,%xmm0,%xmm0
+	movl	%ebp,196(%esp)
+	vmovdqa	%xmm7,96(%esp)
+	addl	16(%esp),%ebx
+	xorl	%edi,%esi
+	vpshufb	%xmm6,%xmm1,%xmm1
+	movl	%ecx,%ebp
+	shldl	$5,%ecx,%ecx
+	vpaddd	%xmm7,%xmm0,%xmm4
+	addl	%esi,%ebx
+	xorl	%edi,%ebp
+	shrdl	$7,%edx,%edx
+	addl	%ecx,%ebx
+	vmovdqa	%xmm4,(%esp)
+	addl	20(%esp),%eax
+	xorl	%edx,%ebp
+	movl	%ebx,%esi
+	shldl	$5,%ebx,%ebx
+	addl	%ebp,%eax
+	xorl	%edx,%esi
+	shrdl	$7,%ecx,%ecx
+	addl	%ebx,%eax
+	addl	24(%esp),%edi
+	xorl	%ecx,%esi
+	movl	%eax,%ebp
+	shldl	$5,%eax,%eax
+	addl	%esi,%edi
+	xorl	%ecx,%ebp
+	shrdl	$7,%ebx,%ebx
+	addl	%eax,%edi
+	addl	28(%esp),%edx
+	xorl	%ebx,%ebp
+	movl	%edi,%esi
+	shldl	$5,%edi,%edi
+	addl	%ebp,%edx
+	xorl	%ebx,%esi
+	shrdl	$7,%eax,%eax
+	addl	%edi,%edx
+	addl	32(%esp),%ecx
+	xorl	%eax,%esi
+	vpshufb	%xmm6,%xmm2,%xmm2
+	movl	%edx,%ebp
+	shldl	$5,%edx,%edx
+	vpaddd	%xmm7,%xmm1,%xmm5
+	addl	%esi,%ecx
+	xorl	%eax,%ebp
+	shrdl	$7,%edi,%edi
+	addl	%edx,%ecx
+	vmovdqa	%xmm5,16(%esp)
+	addl	36(%esp),%ebx
+	xorl	%edi,%ebp
+	movl	%ecx,%esi
+	shldl	$5,%ecx,%ecx
+	addl	%ebp,%ebx
+	xorl	%edi,%esi
+	shrdl	$7,%edx,%edx
+	addl	%ecx,%ebx
+	addl	40(%esp),%eax
+	xorl	%edx,%esi
+	movl	%ebx,%ebp
+	shldl	$5,%ebx,%ebx
+	addl	%esi,%eax
+	xorl	%edx,%ebp
+	shrdl	$7,%ecx,%ecx
+	addl	%ebx,%eax
+	addl	44(%esp),%edi
+	xorl	%ecx,%ebp
+	movl	%eax,%esi
+	shldl	$5,%eax,%eax
+	addl	%ebp,%edi
+	xorl	%ecx,%esi
+	shrdl	$7,%ebx,%ebx
+	addl	%eax,%edi
+	addl	48(%esp),%edx
+	xorl	%ebx,%esi
+	vpshufb	%xmm6,%xmm3,%xmm3
+	movl	%edi,%ebp
+	shldl	$5,%edi,%edi
+	vpaddd	%xmm7,%xmm2,%xmm6
+	addl	%esi,%edx
+	xorl	%ebx,%ebp
+	shrdl	$7,%eax,%eax
+	addl	%edi,%edx
+	vmovdqa	%xmm6,32(%esp)
+	addl	52(%esp),%ecx
+	xorl	%eax,%ebp
+	movl	%edx,%esi
+	shldl	$5,%edx,%edx
+	addl	%ebp,%ecx
+	xorl	%eax,%esi
+	shrdl	$7,%edi,%edi
+	addl	%edx,%ecx
+	addl	56(%esp),%ebx
+	xorl	%edi,%esi
+	movl	%ecx,%ebp
+	shldl	$5,%ecx,%ecx
+	addl	%esi,%ebx
+	xorl	%edi,%ebp
+	shrdl	$7,%edx,%edx
+	addl	%ecx,%ebx
+	addl	60(%esp),%eax
+	xorl	%edx,%ebp
+	movl	%ebx,%esi
+	shldl	$5,%ebx,%ebx
+	addl	%ebp,%eax
+	shrdl	$7,%ecx,%ecx
+	addl	%ebx,%eax
+	movl	192(%esp),%ebp
+	addl	(%ebp),%eax
+	addl	4(%ebp),%esi
+	addl	8(%ebp),%ecx
+	movl	%eax,(%ebp)
+	addl	12(%ebp),%edx
+	movl	%esi,4(%ebp)
+	addl	16(%ebp),%edi
+	movl	%ecx,%ebx
+	movl	%ecx,8(%ebp)
+	xorl	%edx,%ebx
+	movl	%edx,12(%ebp)
+	movl	%edi,16(%ebp)
+	movl	%esi,%ebp
+	andl	%ebx,%esi
+	movl	%ebp,%ebx
+	jmp	L007loop
+.align	4,0x90
+L008done:
+	addl	16(%esp),%ebx
+	xorl	%edi,%esi
+	movl	%ecx,%ebp
+	shldl	$5,%ecx,%ecx
+	addl	%esi,%ebx
+	xorl	%edi,%ebp
+	shrdl	$7,%edx,%edx
+	addl	%ecx,%ebx
+	addl	20(%esp),%eax
+	xorl	%edx,%ebp
+	movl	%ebx,%esi
+	shldl	$5,%ebx,%ebx
+	addl	%ebp,%eax
+	xorl	%edx,%esi
+	shrdl	$7,%ecx,%ecx
+	addl	%ebx,%eax
+	addl	24(%esp),%edi
+	xorl	%ecx,%esi
+	movl	%eax,%ebp
+	shldl	$5,%eax,%eax
+	addl	%esi,%edi
+	xorl	%ecx,%ebp
+	shrdl	$7,%ebx,%ebx
+	addl	%eax,%edi
+	addl	28(%esp),%edx
+	xorl	%ebx,%ebp
+	movl	%edi,%esi
+	shldl	$5,%edi,%edi
+	addl	%ebp,%edx
+	xorl	%ebx,%esi
+	shrdl	$7,%eax,%eax
+	addl	%edi,%edx
+	addl	32(%esp),%ecx
+	xorl	%eax,%esi
+	movl	%edx,%ebp
+	shldl	$5,%edx,%edx
+	addl	%esi,%ecx
+	xorl	%eax,%ebp
+	shrdl	$7,%edi,%edi
+	addl	%edx,%ecx
+	addl	36(%esp),%ebx
+	xorl	%edi,%ebp
+	movl	%ecx,%esi
+	shldl	$5,%ecx,%ecx
+	addl	%ebp,%ebx
+	xorl	%edi,%esi
+	shrdl	$7,%edx,%edx
+	addl	%ecx,%ebx
+	addl	40(%esp),%eax
+	xorl	%edx,%esi
+	movl	%ebx,%ebp
+	shldl	$5,%ebx,%ebx
+	addl	%esi,%eax
+	xorl	%edx,%ebp
+	shrdl	$7,%ecx,%ecx
+	addl	%ebx,%eax
+	addl	44(%esp),%edi
+	xorl	%ecx,%ebp
+	movl	%eax,%esi
+	shldl	$5,%eax,%eax
+	addl	%ebp,%edi
+	xorl	%ecx,%esi
+	shrdl	$7,%ebx,%ebx
+	addl	%eax,%edi
+	addl	48(%esp),%edx
+	xorl	%ebx,%esi
+	movl	%edi,%ebp
+	shldl	$5,%edi,%edi
+	addl	%esi,%edx
+	xorl	%ebx,%ebp
+	shrdl	$7,%eax,%eax
+	addl	%edi,%edx
+	addl	52(%esp),%ecx
+	xorl	%eax,%ebp
+	movl	%edx,%esi
+	shldl	$5,%edx,%edx
+	addl	%ebp,%ecx
+	xorl	%eax,%esi
+	shrdl	$7,%edi,%edi
+	addl	%edx,%ecx
+	addl	56(%esp),%ebx
+	xorl	%edi,%esi
+	movl	%ecx,%ebp
+	shldl	$5,%ecx,%ecx
+	addl	%esi,%ebx
+	xorl	%edi,%ebp
+	shrdl	$7,%edx,%edx
+	addl	%ecx,%ebx
+	addl	60(%esp),%eax
+	xorl	%edx,%ebp
+	movl	%ebx,%esi
+	shldl	$5,%ebx,%ebx
+	addl	%ebp,%eax
+	shrdl	$7,%ecx,%ecx
+	addl	%ebx,%eax
+	vzeroall
+	movl	192(%esp),%ebp
+	addl	(%ebp),%eax
+	movl	204(%esp),%esp
+	addl	4(%ebp),%esi
+	addl	8(%ebp),%ecx
+	movl	%eax,(%ebp)
+	addl	12(%ebp),%edx
+	movl	%esi,4(%ebp)
+	addl	16(%ebp),%edi
+	movl	%ecx,8(%ebp)
+	movl	%edx,12(%ebp)
+	movl	%edi,16(%ebp)
+	popl	%edi
+	popl	%esi
+	popl	%ebx
+	popl	%ebp
+	ret
 .align	6,0x90
 LK_XX_XX:
 .long	1518500249,1518500249,1518500249,1518500249
diff --git a/packager/third_party/boringssl/mac-x86/crypto/sha/sha256-586.S b/packager/third_party/boringssl/mac-x86/crypto/sha/sha256-586.S
index f0ba612fab..841854f7a9 100644
--- a/packager/third_party/boringssl/mac-x86/crypto/sha/sha256-586.S
+++ b/packager/third_party/boringssl/mac-x86/crypto/sha/sha256-586.S
@@ -36,11 +36,10 @@ L000pic_point:
 	jz	L003no_xmm
 	andl	$1073741824,%ecx
 	andl	$268435968,%ebx
-	testl	$536870912,%edx
-	jnz	L004shaext
 	orl	%ebx,%ecx
 	andl	$1342177280,%ecx
 	cmpl	$1342177280,%ecx
+	je	L004AVX
 	testl	$512,%ebx
 	jnz	L005SSSE3
 L003no_xmm:
@@ -3166,204 +3165,6 @@ L009grand_loop:
 	popl	%ebp
 	ret
 .align	5,0x90
-L004shaext:
-	subl	$32,%esp
-	movdqu	(%esi),%xmm1
-	leal	128(%ebp),%ebp
-	movdqu	16(%esi),%xmm2
-	movdqa	128(%ebp),%xmm7
-	pshufd	$27,%xmm1,%xmm0
-	pshufd	$177,%xmm1,%xmm1
-	pshufd	$27,%xmm2,%xmm2
-.byte	102,15,58,15,202,8
-	punpcklqdq	%xmm0,%xmm2
-	jmp	L010loop_shaext
-.align	4,0x90
-L010loop_shaext:
-	movdqu	(%edi),%xmm3
-	movdqu	16(%edi),%xmm4
-	movdqu	32(%edi),%xmm5
-.byte	102,15,56,0,223
-	movdqu	48(%edi),%xmm6
-	movdqa	%xmm2,16(%esp)
-	movdqa	-128(%ebp),%xmm0
-	paddd	%xmm3,%xmm0
-.byte	102,15,56,0,231
-.byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
-	nop
-	movdqa	%xmm1,(%esp)
-.byte	15,56,203,202
-	movdqa	-112(%ebp),%xmm0
-	paddd	%xmm4,%xmm0
-.byte	102,15,56,0,239
-.byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
-	leal	64(%edi),%edi
-.byte	15,56,204,220
-.byte	15,56,203,202
-	movdqa	-96(%ebp),%xmm0
-	paddd	%xmm5,%xmm0
-.byte	102,15,56,0,247
-.byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
-	movdqa	%xmm6,%xmm7
-.byte	102,15,58,15,253,4
-	nop
-	paddd	%xmm7,%xmm3
-.byte	15,56,204,229
-.byte	15,56,203,202
-	movdqa	-80(%ebp),%xmm0
-	paddd	%xmm6,%xmm0
-.byte	15,56,205,222
-.byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
-	movdqa	%xmm3,%xmm7
-.byte	102,15,58,15,254,4
-	nop
-	paddd	%xmm7,%xmm4
-.byte	15,56,204,238
-.byte	15,56,203,202
-	movdqa	-64(%ebp),%xmm0
-	paddd	%xmm3,%xmm0
-.byte	15,56,205,227
-.byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
-	movdqa	%xmm4,%xmm7
-.byte	102,15,58,15,251,4
-	nop
-	paddd	%xmm7,%xmm5
-.byte	15,56,204,243
-.byte	15,56,203,202
-	movdqa	-48(%ebp),%xmm0
-	paddd	%xmm4,%xmm0
-.byte	15,56,205,236
-.byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
-	movdqa	%xmm5,%xmm7
-.byte	102,15,58,15,252,4
-	nop
-	paddd	%xmm7,%xmm6
-.byte	15,56,204,220
-.byte	15,56,203,202
-	movdqa	-32(%ebp),%xmm0
-	paddd	%xmm5,%xmm0
-.byte	15,56,205,245
-.byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
-	movdqa	%xmm6,%xmm7
-.byte	102,15,58,15,253,4
-	nop
-	paddd	%xmm7,%xmm3
-.byte	15,56,204,229
-.byte	15,56,203,202
-	movdqa	-16(%ebp),%xmm0
-	paddd	%xmm6,%xmm0
-.byte	15,56,205,222
-.byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
-	movdqa	%xmm3,%xmm7
-.byte	102,15,58,15,254,4
-	nop
-	paddd	%xmm7,%xmm4
-.byte	15,56,204,238
-.byte	15,56,203,202
-	movdqa	(%ebp),%xmm0
-	paddd	%xmm3,%xmm0
-.byte	15,56,205,227
-.byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
-	movdqa	%xmm4,%xmm7
-.byte	102,15,58,15,251,4
-	nop
-	paddd	%xmm7,%xmm5
-.byte	15,56,204,243
-.byte	15,56,203,202
-	movdqa	16(%ebp),%xmm0
-	paddd	%xmm4,%xmm0
-.byte	15,56,205,236
-.byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
-	movdqa	%xmm5,%xmm7
-.byte	102,15,58,15,252,4
-	nop
-	paddd	%xmm7,%xmm6
-.byte	15,56,204,220
-.byte	15,56,203,202
-	movdqa	32(%ebp),%xmm0
-	paddd	%xmm5,%xmm0
-.byte	15,56,205,245
-.byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
-	movdqa	%xmm6,%xmm7
-.byte	102,15,58,15,253,4
-	nop
-	paddd	%xmm7,%xmm3
-.byte	15,56,204,229
-.byte	15,56,203,202
-	movdqa	48(%ebp),%xmm0
-	paddd	%xmm6,%xmm0
-.byte	15,56,205,222
-.byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
-	movdqa	%xmm3,%xmm7
-.byte	102,15,58,15,254,4
-	nop
-	paddd	%xmm7,%xmm4
-.byte	15,56,204,238
-.byte	15,56,203,202
-	movdqa	64(%ebp),%xmm0
-	paddd	%xmm3,%xmm0
-.byte	15,56,205,227
-.byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
-	movdqa	%xmm4,%xmm7
-.byte	102,15,58,15,251,4
-	nop
-	paddd	%xmm7,%xmm5
-.byte	15,56,204,243
-.byte	15,56,203,202
-	movdqa	80(%ebp),%xmm0
-	paddd	%xmm4,%xmm0
-.byte	15,56,205,236
-.byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
-	movdqa	%xmm5,%xmm7
-.byte	102,15,58,15,252,4
-.byte	15,56,203,202
-	paddd	%xmm7,%xmm6
-	movdqa	96(%ebp),%xmm0
-	paddd	%xmm5,%xmm0
-.byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
-.byte	15,56,205,245
-	movdqa	128(%ebp),%xmm7
-.byte	15,56,203,202
-	movdqa	112(%ebp),%xmm0
-	paddd	%xmm6,%xmm0
-	nop
-.byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
-	cmpl	%edi,%eax
-	nop
-.byte	15,56,203,202
-	paddd	16(%esp),%xmm2
-	paddd	(%esp),%xmm1
-	jnz	L010loop_shaext
-	pshufd	$177,%xmm2,%xmm2
-	pshufd	$27,%xmm1,%xmm7
-	pshufd	$177,%xmm1,%xmm1
-	punpckhqdq	%xmm2,%xmm1
-.byte	102,15,58,15,215,8
-	movl	44(%esp),%esp
-	movdqu	%xmm1,(%esi)
-	movdqu	%xmm2,16(%esi)
-	popl	%edi
-	popl	%esi
-	popl	%ebx
-	popl	%ebp
-	ret
-.align	5,0x90
 L005SSSE3:
 	leal	-96(%esp),%esp
 	movl	(%esi),%eax
@@ -3383,9 +3184,9 @@ L005SSSE3:
 	movl	%ecx,24(%esp)
 	movl	%esi,28(%esp)
 	movdqa	256(%ebp),%xmm7
-	jmp	L011grand_ssse3
+	jmp	L010grand_ssse3
 .align	4,0x90
-L011grand_ssse3:
+L010grand_ssse3:
 	movdqu	(%edi),%xmm0
 	movdqu	16(%edi),%xmm1
 	movdqu	32(%edi),%xmm2
@@ -3408,9 +3209,9 @@ L011grand_ssse3:
 	paddd	%xmm3,%xmm7
 	movdqa	%xmm6,64(%esp)
 	movdqa	%xmm7,80(%esp)
-	jmp	L012ssse3_00_47
+	jmp	L011ssse3_00_47
 .align	4,0x90
-L012ssse3_00_47:
+L011ssse3_00_47:
 	addl	$64,%ebp
 	movl	%edx,%ecx
 	movdqa	%xmm1,%xmm4
@@ -4053,7 +3854,7 @@ L012ssse3_00_47:
 	addl	%ecx,%eax
 	movdqa	%xmm6,80(%esp)
 	cmpl	$66051,64(%ebp)
-	jne	L012ssse3_00_47
+	jne	L011ssse3_00_47
 	movl	%edx,%ecx
 	rorl	$14,%edx
 	movl	20(%esp),%esi
@@ -4567,13 +4368,1194 @@ L012ssse3_00_47:
 	movdqa	64(%ebp),%xmm7
 	subl	$192,%ebp
 	cmpl	104(%esp),%edi
-	jb	L011grand_ssse3
+	jb	L010grand_ssse3
 	movl	108(%esp),%esp
 	popl	%edi
 	popl	%esi
 	popl	%ebx
 	popl	%ebp
 	ret
+.align	5,0x90
+L004AVX:
+	leal	-96(%esp),%esp
+	vzeroall
+	movl	(%esi),%eax
+	movl	4(%esi),%ebx
+	movl	8(%esi),%ecx
+	movl	12(%esi),%edi
+	movl	%ebx,4(%esp)
+	xorl	%ecx,%ebx
+	movl	%ecx,8(%esp)
+	movl	%edi,12(%esp)
+	movl	16(%esi),%edx
+	movl	20(%esi),%edi
+	movl	24(%esi),%ecx
+	movl	28(%esi),%esi
+	movl	%edi,20(%esp)
+	movl	100(%esp),%edi
+	movl	%ecx,24(%esp)
+	movl	%esi,28(%esp)
+	vmovdqa	256(%ebp),%xmm7
+	jmp	L012grand_avx
+.align	5,0x90
+L012grand_avx:
+	vmovdqu	(%edi),%xmm0
+	vmovdqu	16(%edi),%xmm1
+	vmovdqu	32(%edi),%xmm2
+	vmovdqu	48(%edi),%xmm3
+	addl	$64,%edi
+	vpshufb	%xmm7,%xmm0,%xmm0
+	movl	%edi,100(%esp)
+	vpshufb	%xmm7,%xmm1,%xmm1
+	vpshufb	%xmm7,%xmm2,%xmm2
+	vpaddd	(%ebp),%xmm0,%xmm4
+	vpshufb	%xmm7,%xmm3,%xmm3
+	vpaddd	16(%ebp),%xmm1,%xmm5
+	vpaddd	32(%ebp),%xmm2,%xmm6
+	vpaddd	48(%ebp),%xmm3,%xmm7
+	vmovdqa	%xmm4,32(%esp)
+	vmovdqa	%xmm5,48(%esp)
+	vmovdqa	%xmm6,64(%esp)
+	vmovdqa	%xmm7,80(%esp)
+	jmp	L013avx_00_47
+.align	4,0x90
+L013avx_00_47:
+	addl	$64,%ebp
+	vpalignr	$4,%xmm0,%xmm1,%xmm4
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	20(%esp),%esi
+	vpalignr	$4,%xmm2,%xmm3,%xmm7
+	xorl	%ecx,%edx
+	movl	24(%esp),%edi
+	xorl	%edi,%esi
+	vpsrld	$7,%xmm4,%xmm6
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,16(%esp)
+	vpaddd	%xmm7,%xmm0,%xmm0
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	vpsrld	$3,%xmm4,%xmm7
+	movl	%eax,%ecx
+	addl	%edi,%edx
+	movl	4(%esp),%edi
+	vpslld	$14,%xmm4,%xmm5
+	movl	%eax,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%eax,(%esp)
+	vpxor	%xmm6,%xmm7,%xmm4
+	xorl	%eax,%ecx
+	xorl	%edi,%eax
+	addl	28(%esp),%edx
+	vpshufd	$250,%xmm3,%xmm7
+	shrdl	$11,%ecx,%ecx
+	andl	%eax,%ebx
+	xorl	%esi,%ecx
+	vpsrld	$11,%xmm6,%xmm6
+	addl	32(%esp),%edx
+	xorl	%edi,%ebx
+	shrdl	$2,%ecx,%ecx
+	vpxor	%xmm5,%xmm4,%xmm4
+	addl	%edx,%ebx
+	addl	12(%esp),%edx
+	addl	%ecx,%ebx
+	vpslld	$11,%xmm5,%xmm5
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	16(%esp),%esi
+	vpxor	%xmm6,%xmm4,%xmm4
+	xorl	%ecx,%edx
+	movl	20(%esp),%edi
+	xorl	%edi,%esi
+	vpsrld	$10,%xmm7,%xmm6
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,12(%esp)
+	vpxor	%xmm5,%xmm4,%xmm4
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	vpsrlq	$17,%xmm7,%xmm5
+	movl	%ebx,%ecx
+	addl	%edi,%edx
+	movl	(%esp),%edi
+	vpaddd	%xmm4,%xmm0,%xmm0
+	movl	%ebx,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%ebx,28(%esp)
+	vpxor	%xmm5,%xmm6,%xmm6
+	xorl	%ebx,%ecx
+	xorl	%edi,%ebx
+	addl	24(%esp),%edx
+	vpsrlq	$19,%xmm7,%xmm7
+	shrdl	$11,%ecx,%ecx
+	andl	%ebx,%eax
+	xorl	%esi,%ecx
+	vpxor	%xmm7,%xmm6,%xmm6
+	addl	36(%esp),%edx
+	xorl	%edi,%eax
+	shrdl	$2,%ecx,%ecx
+	vpshufd	$132,%xmm6,%xmm7
+	addl	%edx,%eax
+	addl	8(%esp),%edx
+	addl	%ecx,%eax
+	vpsrldq	$8,%xmm7,%xmm7
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	12(%esp),%esi
+	vpaddd	%xmm7,%xmm0,%xmm0
+	xorl	%ecx,%edx
+	movl	16(%esp),%edi
+	xorl	%edi,%esi
+	vpshufd	$80,%xmm0,%xmm7
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,8(%esp)
+	vpsrld	$10,%xmm7,%xmm6
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	vpsrlq	$17,%xmm7,%xmm5
+	movl	%eax,%ecx
+	addl	%edi,%edx
+	movl	28(%esp),%edi
+	vpxor	%xmm5,%xmm6,%xmm6
+	movl	%eax,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%eax,24(%esp)
+	vpsrlq	$19,%xmm7,%xmm7
+	xorl	%eax,%ecx
+	xorl	%edi,%eax
+	addl	20(%esp),%edx
+	vpxor	%xmm7,%xmm6,%xmm6
+	shrdl	$11,%ecx,%ecx
+	andl	%eax,%ebx
+	xorl	%esi,%ecx
+	vpshufd	$232,%xmm6,%xmm7
+	addl	40(%esp),%edx
+	xorl	%edi,%ebx
+	shrdl	$2,%ecx,%ecx
+	vpslldq	$8,%xmm7,%xmm7
+	addl	%edx,%ebx
+	addl	4(%esp),%edx
+	addl	%ecx,%ebx
+	vpaddd	%xmm7,%xmm0,%xmm0
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	8(%esp),%esi
+	vpaddd	(%ebp),%xmm0,%xmm6
+	xorl	%ecx,%edx
+	movl	12(%esp),%edi
+	xorl	%edi,%esi
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,4(%esp)
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	movl	%ebx,%ecx
+	addl	%edi,%edx
+	movl	24(%esp),%edi
+	movl	%ebx,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%ebx,20(%esp)
+	xorl	%ebx,%ecx
+	xorl	%edi,%ebx
+	addl	16(%esp),%edx
+	shrdl	$11,%ecx,%ecx
+	andl	%ebx,%eax
+	xorl	%esi,%ecx
+	addl	44(%esp),%edx
+	xorl	%edi,%eax
+	shrdl	$2,%ecx,%ecx
+	addl	%edx,%eax
+	addl	(%esp),%edx
+	addl	%ecx,%eax
+	vmovdqa	%xmm6,32(%esp)
+	vpalignr	$4,%xmm1,%xmm2,%xmm4
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	4(%esp),%esi
+	vpalignr	$4,%xmm3,%xmm0,%xmm7
+	xorl	%ecx,%edx
+	movl	8(%esp),%edi
+	xorl	%edi,%esi
+	vpsrld	$7,%xmm4,%xmm6
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,(%esp)
+	vpaddd	%xmm7,%xmm1,%xmm1
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	vpsrld	$3,%xmm4,%xmm7
+	movl	%eax,%ecx
+	addl	%edi,%edx
+	movl	20(%esp),%edi
+	vpslld	$14,%xmm4,%xmm5
+	movl	%eax,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%eax,16(%esp)
+	vpxor	%xmm6,%xmm7,%xmm4
+	xorl	%eax,%ecx
+	xorl	%edi,%eax
+	addl	12(%esp),%edx
+	vpshufd	$250,%xmm0,%xmm7
+	shrdl	$11,%ecx,%ecx
+	andl	%eax,%ebx
+	xorl	%esi,%ecx
+	vpsrld	$11,%xmm6,%xmm6
+	addl	48(%esp),%edx
+	xorl	%edi,%ebx
+	shrdl	$2,%ecx,%ecx
+	vpxor	%xmm5,%xmm4,%xmm4
+	addl	%edx,%ebx
+	addl	28(%esp),%edx
+	addl	%ecx,%ebx
+	vpslld	$11,%xmm5,%xmm5
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	(%esp),%esi
+	vpxor	%xmm6,%xmm4,%xmm4
+	xorl	%ecx,%edx
+	movl	4(%esp),%edi
+	xorl	%edi,%esi
+	vpsrld	$10,%xmm7,%xmm6
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,28(%esp)
+	vpxor	%xmm5,%xmm4,%xmm4
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	vpsrlq	$17,%xmm7,%xmm5
+	movl	%ebx,%ecx
+	addl	%edi,%edx
+	movl	16(%esp),%edi
+	vpaddd	%xmm4,%xmm1,%xmm1
+	movl	%ebx,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%ebx,12(%esp)
+	vpxor	%xmm5,%xmm6,%xmm6
+	xorl	%ebx,%ecx
+	xorl	%edi,%ebx
+	addl	8(%esp),%edx
+	vpsrlq	$19,%xmm7,%xmm7
+	shrdl	$11,%ecx,%ecx
+	andl	%ebx,%eax
+	xorl	%esi,%ecx
+	vpxor	%xmm7,%xmm6,%xmm6
+	addl	52(%esp),%edx
+	xorl	%edi,%eax
+	shrdl	$2,%ecx,%ecx
+	vpshufd	$132,%xmm6,%xmm7
+	addl	%edx,%eax
+	addl	24(%esp),%edx
+	addl	%ecx,%eax
+	vpsrldq	$8,%xmm7,%xmm7
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	28(%esp),%esi
+	vpaddd	%xmm7,%xmm1,%xmm1
+	xorl	%ecx,%edx
+	movl	(%esp),%edi
+	xorl	%edi,%esi
+	vpshufd	$80,%xmm1,%xmm7
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,24(%esp)
+	vpsrld	$10,%xmm7,%xmm6
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	vpsrlq	$17,%xmm7,%xmm5
+	movl	%eax,%ecx
+	addl	%edi,%edx
+	movl	12(%esp),%edi
+	vpxor	%xmm5,%xmm6,%xmm6
+	movl	%eax,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%eax,8(%esp)
+	vpsrlq	$19,%xmm7,%xmm7
+	xorl	%eax,%ecx
+	xorl	%edi,%eax
+	addl	4(%esp),%edx
+	vpxor	%xmm7,%xmm6,%xmm6
+	shrdl	$11,%ecx,%ecx
+	andl	%eax,%ebx
+	xorl	%esi,%ecx
+	vpshufd	$232,%xmm6,%xmm7
+	addl	56(%esp),%edx
+	xorl	%edi,%ebx
+	shrdl	$2,%ecx,%ecx
+	vpslldq	$8,%xmm7,%xmm7
+	addl	%edx,%ebx
+	addl	20(%esp),%edx
+	addl	%ecx,%ebx
+	vpaddd	%xmm7,%xmm1,%xmm1
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	24(%esp),%esi
+	vpaddd	16(%ebp),%xmm1,%xmm6
+	xorl	%ecx,%edx
+	movl	28(%esp),%edi
+	xorl	%edi,%esi
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,20(%esp)
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	movl	%ebx,%ecx
+	addl	%edi,%edx
+	movl	8(%esp),%edi
+	movl	%ebx,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%ebx,4(%esp)
+	xorl	%ebx,%ecx
+	xorl	%edi,%ebx
+	addl	(%esp),%edx
+	shrdl	$11,%ecx,%ecx
+	andl	%ebx,%eax
+	xorl	%esi,%ecx
+	addl	60(%esp),%edx
+	xorl	%edi,%eax
+	shrdl	$2,%ecx,%ecx
+	addl	%edx,%eax
+	addl	16(%esp),%edx
+	addl	%ecx,%eax
+	vmovdqa	%xmm6,48(%esp)
+	vpalignr	$4,%xmm2,%xmm3,%xmm4
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	20(%esp),%esi
+	vpalignr	$4,%xmm0,%xmm1,%xmm7
+	xorl	%ecx,%edx
+	movl	24(%esp),%edi
+	xorl	%edi,%esi
+	vpsrld	$7,%xmm4,%xmm6
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,16(%esp)
+	vpaddd	%xmm7,%xmm2,%xmm2
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	vpsrld	$3,%xmm4,%xmm7
+	movl	%eax,%ecx
+	addl	%edi,%edx
+	movl	4(%esp),%edi
+	vpslld	$14,%xmm4,%xmm5
+	movl	%eax,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%eax,(%esp)
+	vpxor	%xmm6,%xmm7,%xmm4
+	xorl	%eax,%ecx
+	xorl	%edi,%eax
+	addl	28(%esp),%edx
+	vpshufd	$250,%xmm1,%xmm7
+	shrdl	$11,%ecx,%ecx
+	andl	%eax,%ebx
+	xorl	%esi,%ecx
+	vpsrld	$11,%xmm6,%xmm6
+	addl	64(%esp),%edx
+	xorl	%edi,%ebx
+	shrdl	$2,%ecx,%ecx
+	vpxor	%xmm5,%xmm4,%xmm4
+	addl	%edx,%ebx
+	addl	12(%esp),%edx
+	addl	%ecx,%ebx
+	vpslld	$11,%xmm5,%xmm5
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	16(%esp),%esi
+	vpxor	%xmm6,%xmm4,%xmm4
+	xorl	%ecx,%edx
+	movl	20(%esp),%edi
+	xorl	%edi,%esi
+	vpsrld	$10,%xmm7,%xmm6
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,12(%esp)
+	vpxor	%xmm5,%xmm4,%xmm4
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	vpsrlq	$17,%xmm7,%xmm5
+	movl	%ebx,%ecx
+	addl	%edi,%edx
+	movl	(%esp),%edi
+	vpaddd	%xmm4,%xmm2,%xmm2
+	movl	%ebx,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%ebx,28(%esp)
+	vpxor	%xmm5,%xmm6,%xmm6
+	xorl	%ebx,%ecx
+	xorl	%edi,%ebx
+	addl	24(%esp),%edx
+	vpsrlq	$19,%xmm7,%xmm7
+	shrdl	$11,%ecx,%ecx
+	andl	%ebx,%eax
+	xorl	%esi,%ecx
+	vpxor	%xmm7,%xmm6,%xmm6
+	addl	68(%esp),%edx
+	xorl	%edi,%eax
+	shrdl	$2,%ecx,%ecx
+	vpshufd	$132,%xmm6,%xmm7
+	addl	%edx,%eax
+	addl	8(%esp),%edx
+	addl	%ecx,%eax
+	vpsrldq	$8,%xmm7,%xmm7
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	12(%esp),%esi
+	vpaddd	%xmm7,%xmm2,%xmm2
+	xorl	%ecx,%edx
+	movl	16(%esp),%edi
+	xorl	%edi,%esi
+	vpshufd	$80,%xmm2,%xmm7
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,8(%esp)
+	vpsrld	$10,%xmm7,%xmm6
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	vpsrlq	$17,%xmm7,%xmm5
+	movl	%eax,%ecx
+	addl	%edi,%edx
+	movl	28(%esp),%edi
+	vpxor	%xmm5,%xmm6,%xmm6
+	movl	%eax,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%eax,24(%esp)
+	vpsrlq	$19,%xmm7,%xmm7
+	xorl	%eax,%ecx
+	xorl	%edi,%eax
+	addl	20(%esp),%edx
+	vpxor	%xmm7,%xmm6,%xmm6
+	shrdl	$11,%ecx,%ecx
+	andl	%eax,%ebx
+	xorl	%esi,%ecx
+	vpshufd	$232,%xmm6,%xmm7
+	addl	72(%esp),%edx
+	xorl	%edi,%ebx
+	shrdl	$2,%ecx,%ecx
+	vpslldq	$8,%xmm7,%xmm7
+	addl	%edx,%ebx
+	addl	4(%esp),%edx
+	addl	%ecx,%ebx
+	vpaddd	%xmm7,%xmm2,%xmm2
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	8(%esp),%esi
+	vpaddd	32(%ebp),%xmm2,%xmm6
+	xorl	%ecx,%edx
+	movl	12(%esp),%edi
+	xorl	%edi,%esi
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,4(%esp)
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	movl	%ebx,%ecx
+	addl	%edi,%edx
+	movl	24(%esp),%edi
+	movl	%ebx,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%ebx,20(%esp)
+	xorl	%ebx,%ecx
+	xorl	%edi,%ebx
+	addl	16(%esp),%edx
+	shrdl	$11,%ecx,%ecx
+	andl	%ebx,%eax
+	xorl	%esi,%ecx
+	addl	76(%esp),%edx
+	xorl	%edi,%eax
+	shrdl	$2,%ecx,%ecx
+	addl	%edx,%eax
+	addl	(%esp),%edx
+	addl	%ecx,%eax
+	vmovdqa	%xmm6,64(%esp)
+	vpalignr	$4,%xmm3,%xmm0,%xmm4
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	4(%esp),%esi
+	vpalignr	$4,%xmm1,%xmm2,%xmm7
+	xorl	%ecx,%edx
+	movl	8(%esp),%edi
+	xorl	%edi,%esi
+	vpsrld	$7,%xmm4,%xmm6
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,(%esp)
+	vpaddd	%xmm7,%xmm3,%xmm3
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	vpsrld	$3,%xmm4,%xmm7
+	movl	%eax,%ecx
+	addl	%edi,%edx
+	movl	20(%esp),%edi
+	vpslld	$14,%xmm4,%xmm5
+	movl	%eax,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%eax,16(%esp)
+	vpxor	%xmm6,%xmm7,%xmm4
+	xorl	%eax,%ecx
+	xorl	%edi,%eax
+	addl	12(%esp),%edx
+	vpshufd	$250,%xmm2,%xmm7
+	shrdl	$11,%ecx,%ecx
+	andl	%eax,%ebx
+	xorl	%esi,%ecx
+	vpsrld	$11,%xmm6,%xmm6
+	addl	80(%esp),%edx
+	xorl	%edi,%ebx
+	shrdl	$2,%ecx,%ecx
+	vpxor	%xmm5,%xmm4,%xmm4
+	addl	%edx,%ebx
+	addl	28(%esp),%edx
+	addl	%ecx,%ebx
+	vpslld	$11,%xmm5,%xmm5
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	(%esp),%esi
+	vpxor	%xmm6,%xmm4,%xmm4
+	xorl	%ecx,%edx
+	movl	4(%esp),%edi
+	xorl	%edi,%esi
+	vpsrld	$10,%xmm7,%xmm6
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,28(%esp)
+	vpxor	%xmm5,%xmm4,%xmm4
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	vpsrlq	$17,%xmm7,%xmm5
+	movl	%ebx,%ecx
+	addl	%edi,%edx
+	movl	16(%esp),%edi
+	vpaddd	%xmm4,%xmm3,%xmm3
+	movl	%ebx,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%ebx,12(%esp)
+	vpxor	%xmm5,%xmm6,%xmm6
+	xorl	%ebx,%ecx
+	xorl	%edi,%ebx
+	addl	8(%esp),%edx
+	vpsrlq	$19,%xmm7,%xmm7
+	shrdl	$11,%ecx,%ecx
+	andl	%ebx,%eax
+	xorl	%esi,%ecx
+	vpxor	%xmm7,%xmm6,%xmm6
+	addl	84(%esp),%edx
+	xorl	%edi,%eax
+	shrdl	$2,%ecx,%ecx
+	vpshufd	$132,%xmm6,%xmm7
+	addl	%edx,%eax
+	addl	24(%esp),%edx
+	addl	%ecx,%eax
+	vpsrldq	$8,%xmm7,%xmm7
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	28(%esp),%esi
+	vpaddd	%xmm7,%xmm3,%xmm3
+	xorl	%ecx,%edx
+	movl	(%esp),%edi
+	xorl	%edi,%esi
+	vpshufd	$80,%xmm3,%xmm7
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,24(%esp)
+	vpsrld	$10,%xmm7,%xmm6
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	vpsrlq	$17,%xmm7,%xmm5
+	movl	%eax,%ecx
+	addl	%edi,%edx
+	movl	12(%esp),%edi
+	vpxor	%xmm5,%xmm6,%xmm6
+	movl	%eax,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%eax,8(%esp)
+	vpsrlq	$19,%xmm7,%xmm7
+	xorl	%eax,%ecx
+	xorl	%edi,%eax
+	addl	4(%esp),%edx
+	vpxor	%xmm7,%xmm6,%xmm6
+	shrdl	$11,%ecx,%ecx
+	andl	%eax,%ebx
+	xorl	%esi,%ecx
+	vpshufd	$232,%xmm6,%xmm7
+	addl	88(%esp),%edx
+	xorl	%edi,%ebx
+	shrdl	$2,%ecx,%ecx
+	vpslldq	$8,%xmm7,%xmm7
+	addl	%edx,%ebx
+	addl	20(%esp),%edx
+	addl	%ecx,%ebx
+	vpaddd	%xmm7,%xmm3,%xmm3
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	24(%esp),%esi
+	vpaddd	48(%ebp),%xmm3,%xmm6
+	xorl	%ecx,%edx
+	movl	28(%esp),%edi
+	xorl	%edi,%esi
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,20(%esp)
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	movl	%ebx,%ecx
+	addl	%edi,%edx
+	movl	8(%esp),%edi
+	movl	%ebx,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%ebx,4(%esp)
+	xorl	%ebx,%ecx
+	xorl	%edi,%ebx
+	addl	(%esp),%edx
+	shrdl	$11,%ecx,%ecx
+	andl	%ebx,%eax
+	xorl	%esi,%ecx
+	addl	92(%esp),%edx
+	xorl	%edi,%eax
+	shrdl	$2,%ecx,%ecx
+	addl	%edx,%eax
+	addl	16(%esp),%edx
+	addl	%ecx,%eax
+	vmovdqa	%xmm6,80(%esp)
+	cmpl	$66051,64(%ebp)
+	jne	L013avx_00_47
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	20(%esp),%esi
+	xorl	%ecx,%edx
+	movl	24(%esp),%edi
+	xorl	%edi,%esi
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,16(%esp)
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	movl	%eax,%ecx
+	addl	%edi,%edx
+	movl	4(%esp),%edi
+	movl	%eax,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%eax,(%esp)
+	xorl	%eax,%ecx
+	xorl	%edi,%eax
+	addl	28(%esp),%edx
+	shrdl	$11,%ecx,%ecx
+	andl	%eax,%ebx
+	xorl	%esi,%ecx
+	addl	32(%esp),%edx
+	xorl	%edi,%ebx
+	shrdl	$2,%ecx,%ecx
+	addl	%edx,%ebx
+	addl	12(%esp),%edx
+	addl	%ecx,%ebx
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	16(%esp),%esi
+	xorl	%ecx,%edx
+	movl	20(%esp),%edi
+	xorl	%edi,%esi
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,12(%esp)
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	movl	%ebx,%ecx
+	addl	%edi,%edx
+	movl	(%esp),%edi
+	movl	%ebx,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%ebx,28(%esp)
+	xorl	%ebx,%ecx
+	xorl	%edi,%ebx
+	addl	24(%esp),%edx
+	shrdl	$11,%ecx,%ecx
+	andl	%ebx,%eax
+	xorl	%esi,%ecx
+	addl	36(%esp),%edx
+	xorl	%edi,%eax
+	shrdl	$2,%ecx,%ecx
+	addl	%edx,%eax
+	addl	8(%esp),%edx
+	addl	%ecx,%eax
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	12(%esp),%esi
+	xorl	%ecx,%edx
+	movl	16(%esp),%edi
+	xorl	%edi,%esi
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,8(%esp)
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	movl	%eax,%ecx
+	addl	%edi,%edx
+	movl	28(%esp),%edi
+	movl	%eax,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%eax,24(%esp)
+	xorl	%eax,%ecx
+	xorl	%edi,%eax
+	addl	20(%esp),%edx
+	shrdl	$11,%ecx,%ecx
+	andl	%eax,%ebx
+	xorl	%esi,%ecx
+	addl	40(%esp),%edx
+	xorl	%edi,%ebx
+	shrdl	$2,%ecx,%ecx
+	addl	%edx,%ebx
+	addl	4(%esp),%edx
+	addl	%ecx,%ebx
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	8(%esp),%esi
+	xorl	%ecx,%edx
+	movl	12(%esp),%edi
+	xorl	%edi,%esi
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,4(%esp)
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	movl	%ebx,%ecx
+	addl	%edi,%edx
+	movl	24(%esp),%edi
+	movl	%ebx,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%ebx,20(%esp)
+	xorl	%ebx,%ecx
+	xorl	%edi,%ebx
+	addl	16(%esp),%edx
+	shrdl	$11,%ecx,%ecx
+	andl	%ebx,%eax
+	xorl	%esi,%ecx
+	addl	44(%esp),%edx
+	xorl	%edi,%eax
+	shrdl	$2,%ecx,%ecx
+	addl	%edx,%eax
+	addl	(%esp),%edx
+	addl	%ecx,%eax
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	4(%esp),%esi
+	xorl	%ecx,%edx
+	movl	8(%esp),%edi
+	xorl	%edi,%esi
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,(%esp)
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	movl	%eax,%ecx
+	addl	%edi,%edx
+	movl	20(%esp),%edi
+	movl	%eax,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%eax,16(%esp)
+	xorl	%eax,%ecx
+	xorl	%edi,%eax
+	addl	12(%esp),%edx
+	shrdl	$11,%ecx,%ecx
+	andl	%eax,%ebx
+	xorl	%esi,%ecx
+	addl	48(%esp),%edx
+	xorl	%edi,%ebx
+	shrdl	$2,%ecx,%ecx
+	addl	%edx,%ebx
+	addl	28(%esp),%edx
+	addl	%ecx,%ebx
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	(%esp),%esi
+	xorl	%ecx,%edx
+	movl	4(%esp),%edi
+	xorl	%edi,%esi
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,28(%esp)
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	movl	%ebx,%ecx
+	addl	%edi,%edx
+	movl	16(%esp),%edi
+	movl	%ebx,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%ebx,12(%esp)
+	xorl	%ebx,%ecx
+	xorl	%edi,%ebx
+	addl	8(%esp),%edx
+	shrdl	$11,%ecx,%ecx
+	andl	%ebx,%eax
+	xorl	%esi,%ecx
+	addl	52(%esp),%edx
+	xorl	%edi,%eax
+	shrdl	$2,%ecx,%ecx
+	addl	%edx,%eax
+	addl	24(%esp),%edx
+	addl	%ecx,%eax
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	28(%esp),%esi
+	xorl	%ecx,%edx
+	movl	(%esp),%edi
+	xorl	%edi,%esi
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,24(%esp)
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	movl	%eax,%ecx
+	addl	%edi,%edx
+	movl	12(%esp),%edi
+	movl	%eax,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%eax,8(%esp)
+	xorl	%eax,%ecx
+	xorl	%edi,%eax
+	addl	4(%esp),%edx
+	shrdl	$11,%ecx,%ecx
+	andl	%eax,%ebx
+	xorl	%esi,%ecx
+	addl	56(%esp),%edx
+	xorl	%edi,%ebx
+	shrdl	$2,%ecx,%ecx
+	addl	%edx,%ebx
+	addl	20(%esp),%edx
+	addl	%ecx,%ebx
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	24(%esp),%esi
+	xorl	%ecx,%edx
+	movl	28(%esp),%edi
+	xorl	%edi,%esi
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,20(%esp)
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	movl	%ebx,%ecx
+	addl	%edi,%edx
+	movl	8(%esp),%edi
+	movl	%ebx,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%ebx,4(%esp)
+	xorl	%ebx,%ecx
+	xorl	%edi,%ebx
+	addl	(%esp),%edx
+	shrdl	$11,%ecx,%ecx
+	andl	%ebx,%eax
+	xorl	%esi,%ecx
+	addl	60(%esp),%edx
+	xorl	%edi,%eax
+	shrdl	$2,%ecx,%ecx
+	addl	%edx,%eax
+	addl	16(%esp),%edx
+	addl	%ecx,%eax
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	20(%esp),%esi
+	xorl	%ecx,%edx
+	movl	24(%esp),%edi
+	xorl	%edi,%esi
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,16(%esp)
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	movl	%eax,%ecx
+	addl	%edi,%edx
+	movl	4(%esp),%edi
+	movl	%eax,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%eax,(%esp)
+	xorl	%eax,%ecx
+	xorl	%edi,%eax
+	addl	28(%esp),%edx
+	shrdl	$11,%ecx,%ecx
+	andl	%eax,%ebx
+	xorl	%esi,%ecx
+	addl	64(%esp),%edx
+	xorl	%edi,%ebx
+	shrdl	$2,%ecx,%ecx
+	addl	%edx,%ebx
+	addl	12(%esp),%edx
+	addl	%ecx,%ebx
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	16(%esp),%esi
+	xorl	%ecx,%edx
+	movl	20(%esp),%edi
+	xorl	%edi,%esi
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,12(%esp)
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	movl	%ebx,%ecx
+	addl	%edi,%edx
+	movl	(%esp),%edi
+	movl	%ebx,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%ebx,28(%esp)
+	xorl	%ebx,%ecx
+	xorl	%edi,%ebx
+	addl	24(%esp),%edx
+	shrdl	$11,%ecx,%ecx
+	andl	%ebx,%eax
+	xorl	%esi,%ecx
+	addl	68(%esp),%edx
+	xorl	%edi,%eax
+	shrdl	$2,%ecx,%ecx
+	addl	%edx,%eax
+	addl	8(%esp),%edx
+	addl	%ecx,%eax
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	12(%esp),%esi
+	xorl	%ecx,%edx
+	movl	16(%esp),%edi
+	xorl	%edi,%esi
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,8(%esp)
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	movl	%eax,%ecx
+	addl	%edi,%edx
+	movl	28(%esp),%edi
+	movl	%eax,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%eax,24(%esp)
+	xorl	%eax,%ecx
+	xorl	%edi,%eax
+	addl	20(%esp),%edx
+	shrdl	$11,%ecx,%ecx
+	andl	%eax,%ebx
+	xorl	%esi,%ecx
+	addl	72(%esp),%edx
+	xorl	%edi,%ebx
+	shrdl	$2,%ecx,%ecx
+	addl	%edx,%ebx
+	addl	4(%esp),%edx
+	addl	%ecx,%ebx
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	8(%esp),%esi
+	xorl	%ecx,%edx
+	movl	12(%esp),%edi
+	xorl	%edi,%esi
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,4(%esp)
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	movl	%ebx,%ecx
+	addl	%edi,%edx
+	movl	24(%esp),%edi
+	movl	%ebx,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%ebx,20(%esp)
+	xorl	%ebx,%ecx
+	xorl	%edi,%ebx
+	addl	16(%esp),%edx
+	shrdl	$11,%ecx,%ecx
+	andl	%ebx,%eax
+	xorl	%esi,%ecx
+	addl	76(%esp),%edx
+	xorl	%edi,%eax
+	shrdl	$2,%ecx,%ecx
+	addl	%edx,%eax
+	addl	(%esp),%edx
+	addl	%ecx,%eax
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	4(%esp),%esi
+	xorl	%ecx,%edx
+	movl	8(%esp),%edi
+	xorl	%edi,%esi
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,(%esp)
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	movl	%eax,%ecx
+	addl	%edi,%edx
+	movl	20(%esp),%edi
+	movl	%eax,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%eax,16(%esp)
+	xorl	%eax,%ecx
+	xorl	%edi,%eax
+	addl	12(%esp),%edx
+	shrdl	$11,%ecx,%ecx
+	andl	%eax,%ebx
+	xorl	%esi,%ecx
+	addl	80(%esp),%edx
+	xorl	%edi,%ebx
+	shrdl	$2,%ecx,%ecx
+	addl	%edx,%ebx
+	addl	28(%esp),%edx
+	addl	%ecx,%ebx
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	(%esp),%esi
+	xorl	%ecx,%edx
+	movl	4(%esp),%edi
+	xorl	%edi,%esi
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,28(%esp)
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	movl	%ebx,%ecx
+	addl	%edi,%edx
+	movl	16(%esp),%edi
+	movl	%ebx,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%ebx,12(%esp)
+	xorl	%ebx,%ecx
+	xorl	%edi,%ebx
+	addl	8(%esp),%edx
+	shrdl	$11,%ecx,%ecx
+	andl	%ebx,%eax
+	xorl	%esi,%ecx
+	addl	84(%esp),%edx
+	xorl	%edi,%eax
+	shrdl	$2,%ecx,%ecx
+	addl	%edx,%eax
+	addl	24(%esp),%edx
+	addl	%ecx,%eax
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	28(%esp),%esi
+	xorl	%ecx,%edx
+	movl	(%esp),%edi
+	xorl	%edi,%esi
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,24(%esp)
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	movl	%eax,%ecx
+	addl	%edi,%edx
+	movl	12(%esp),%edi
+	movl	%eax,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%eax,8(%esp)
+	xorl	%eax,%ecx
+	xorl	%edi,%eax
+	addl	4(%esp),%edx
+	shrdl	$11,%ecx,%ecx
+	andl	%eax,%ebx
+	xorl	%esi,%ecx
+	addl	88(%esp),%edx
+	xorl	%edi,%ebx
+	shrdl	$2,%ecx,%ecx
+	addl	%edx,%ebx
+	addl	20(%esp),%edx
+	addl	%ecx,%ebx
+	movl	%edx,%ecx
+	shrdl	$14,%edx,%edx
+	movl	24(%esp),%esi
+	xorl	%ecx,%edx
+	movl	28(%esp),%edi
+	xorl	%edi,%esi
+	shrdl	$5,%edx,%edx
+	andl	%ecx,%esi
+	movl	%ecx,20(%esp)
+	xorl	%ecx,%edx
+	xorl	%esi,%edi
+	shrdl	$6,%edx,%edx
+	movl	%ebx,%ecx
+	addl	%edi,%edx
+	movl	8(%esp),%edi
+	movl	%ebx,%esi
+	shrdl	$9,%ecx,%ecx
+	movl	%ebx,4(%esp)
+	xorl	%ebx,%ecx
+	xorl	%edi,%ebx
+	addl	(%esp),%edx
+	shrdl	$11,%ecx,%ecx
+	andl	%ebx,%eax
+	xorl	%esi,%ecx
+	addl	92(%esp),%edx
+	xorl	%edi,%eax
+	shrdl	$2,%ecx,%ecx
+	addl	%edx,%eax
+	addl	16(%esp),%edx
+	addl	%ecx,%eax
+	movl	96(%esp),%esi
+	xorl	%edi,%ebx
+	movl	12(%esp),%ecx
+	addl	(%esi),%eax
+	addl	4(%esi),%ebx
+	addl	8(%esi),%edi
+	addl	12(%esi),%ecx
+	movl	%eax,(%esi)
+	movl	%ebx,4(%esi)
+	movl	%edi,8(%esi)
+	movl	%ecx,12(%esi)
+	movl	%ebx,4(%esp)
+	xorl	%edi,%ebx
+	movl	%edi,8(%esp)
+	movl	%ecx,12(%esp)
+	movl	20(%esp),%edi
+	movl	24(%esp),%ecx
+	addl	16(%esi),%edx
+	addl	20(%esi),%edi
+	addl	24(%esi),%ecx
+	movl	%edx,16(%esi)
+	movl	%edi,20(%esi)
+	movl	%edi,20(%esp)
+	movl	28(%esp),%edi
+	movl	%ecx,24(%esi)
+	addl	28(%esi),%edi
+	movl	%ecx,24(%esp)
+	movl	%edi,28(%esi)
+	movl	%edi,28(%esp)
+	movl	100(%esp),%edi
+	vmovdqa	64(%ebp),%xmm7
+	subl	$192,%ebp
+	cmpl	104(%esp),%edi
+	jb	L012grand_avx
+	movl	108(%esp),%esp
+	vzeroall
+	popl	%edi
+	popl	%esi
+	popl	%ebx
+	popl	%ebp
+	ret
 .section __IMPORT,__pointers,non_lazy_symbol_pointers
 L_OPENSSL_ia32cap_P$non_lazy_ptr:
 .indirect_symbol	_OPENSSL_ia32cap_P
diff --git a/packager/third_party/boringssl/mac-x86_64/crypto/aes/aes-x86_64.S b/packager/third_party/boringssl/mac-x86_64/crypto/aes/aes-x86_64.S
index 02f378bd67..b5d188a0f3 100644
--- a/packager/third_party/boringssl/mac-x86_64/crypto/aes/aes-x86_64.S
+++ b/packager/third_party/boringssl/mac-x86_64/crypto/aes/aes-x86_64.S
@@ -82,8 +82,8 @@ L$enc_loop:
 	movl	0(%r14,%rdi,8),%edi
 	movl	0(%r14,%rbp,8),%ebp
 
-	andl	$65280,%edi
-	andl	$65280,%ebp
+	andl	$0x0000ff00,%edi
+	andl	$0x0000ff00,%ebp
 
 	xorl	%edi,%r10d
 	xorl	%ebp,%r11d
@@ -95,8 +95,8 @@ L$enc_loop:
 	movl	0(%r14,%rsi,8),%esi
 	movl	0(%r14,%rdi,8),%edi
 
-	andl	$65280,%esi
-	andl	$65280,%edi
+	andl	$0x0000ff00,%esi
+	andl	$0x0000ff00,%edi
 	shrl	$16,%ebx
 	xorl	%esi,%r12d
 	xorl	%edi,%r8d
@@ -109,9 +109,9 @@ L$enc_loop:
 	movl	0(%r14,%rdi,8),%edi
 	movl	0(%r14,%rbp,8),%ebp
 
-	andl	$16711680,%esi
-	andl	$16711680,%edi
-	andl	$16711680,%ebp
+	andl	$0x00ff0000,%esi
+	andl	$0x00ff0000,%edi
+	andl	$0x00ff0000,%ebp
 
 	xorl	%esi,%r10d
 	xorl	%edi,%r11d
@@ -124,9 +124,9 @@ L$enc_loop:
 	movl	2(%r14,%rdi,8),%edi
 	movl	2(%r14,%rbp,8),%ebp
 
-	andl	$16711680,%esi
-	andl	$4278190080,%edi
-	andl	$4278190080,%ebp
+	andl	$0x00ff0000,%esi
+	andl	$0xff000000,%edi
+	andl	$0xff000000,%ebp
 
 	xorl	%esi,%r8d
 	xorl	%edi,%r10d
@@ -139,8 +139,8 @@ L$enc_loop:
 	movl	2(%r14,%rdi,8),%edi
 	movl	16+0(%r15),%eax
 
-	andl	$4278190080,%esi
-	andl	$4278190080,%edi
+	andl	$0xff000000,%esi
+	andl	$0xff000000,%edi
 
 	xorl	%esi,%r12d
 	xorl	%edi,%r8d
@@ -242,8 +242,8 @@ L$enc_loop_compact:
 	xorl	%r8d,%edx
 	cmpq	16(%rsp),%r15
 	je	L$enc_compact_done
-	movl	$2155905152,%r10d
-	movl	$2155905152,%r11d
+	movl	$0x80808080,%r10d
+	movl	$0x80808080,%r11d
 	andl	%eax,%r10d
 	andl	%ebx,%r11d
 	movl	%r10d,%esi
@@ -254,10 +254,10 @@ L$enc_loop_compact:
 	leal	(%rbx,%rbx,1),%r9d
 	subl	%r10d,%esi
 	subl	%r11d,%edi
-	andl	$4278124286,%r8d
-	andl	$4278124286,%r9d
-	andl	$454761243,%esi
-	andl	$454761243,%edi
+	andl	$0xfefefefe,%r8d
+	andl	$0xfefefefe,%r9d
+	andl	$0x1b1b1b1b,%esi
+	andl	$0x1b1b1b1b,%edi
 	movl	%eax,%r10d
 	movl	%ebx,%r11d
 	xorl	%esi,%r8d
@@ -265,9 +265,9 @@ L$enc_loop_compact:
 
 	xorl	%r8d,%eax
 	xorl	%r9d,%ebx
-	movl	$2155905152,%r12d
+	movl	$0x80808080,%r12d
 	roll	$24,%eax
-	movl	$2155905152,%ebp
+	movl	$0x80808080,%ebp
 	roll	$24,%ebx
 	andl	%ecx,%r12d
 	andl	%edx,%ebp
@@ -290,10 +290,10 @@ L$enc_loop_compact:
 	xorl	%r10d,%eax
 	xorl	%r11d,%ebx
 
-	andl	$4278124286,%r8d
-	andl	$4278124286,%r9d
-	andl	$454761243,%esi
-	andl	$454761243,%edi
+	andl	$0xfefefefe,%r8d
+	andl	$0xfefefefe,%r9d
+	andl	$0x1b1b1b1b,%esi
+	andl	$0x1b1b1b1b,%edi
 	movl	%ecx,%r12d
 	movl	%edx,%ebp
 	xorl	%esi,%r8d
@@ -345,7 +345,7 @@ _asm_AES_encrypt:
 	andq	$-64,%rsp
 	subq	%rsp,%rcx
 	negq	%rcx
-	andq	$960,%rcx
+	andq	$0x3c0,%rcx
 	subq	%rcx,%rsp
 	subq	$32,%rsp
 
@@ -370,7 +370,7 @@ L$enc_prologue:
 	leaq	L$AES_Te+2048(%rip),%r14
 	leaq	768(%rsp),%rbp
 	subq	%r14,%rbp
-	andq	$768,%rbp
+	andq	$0x300,%rbp
 	leaq	(%r14,%rbp,1),%r14
 
 	call	_x86_64_AES_encrypt_compact
@@ -791,7 +791,7 @@ _asm_AES_decrypt:
 	andq	$-64,%rsp
 	subq	%rsp,%rcx
 	negq	%rcx
-	andq	$960,%rcx
+	andq	$0x3c0,%rcx
 	subq	%rcx,%rsp
 	subq	$32,%rsp
 
@@ -816,7 +816,7 @@ L$dec_prologue:
 	leaq	L$AES_Td+2048(%rip),%r14
 	leaq	768(%rsp),%rbp
 	subq	%r14,%rbp
-	andq	$768,%rbp
+	andq	$0x300,%rbp
 	leaq	(%r14,%rbp,1),%r14
 	shrq	$3,%rbp
 	addq	%rbp,%r14
@@ -1333,9 +1333,9 @@ L$cbc_picked_te:
 	movq	%r14,%r10
 	leaq	2304(%r14),%r11
 	movq	%r15,%r12
-	andq	$4095,%r10
-	andq	$4095,%r11
-	andq	$4095,%r12
+	andq	$0xFFF,%r10
+	andq	$0xFFF,%r11
+	andq	$0xFFF,%r12
 
 	cmpq	%r11,%r12
 	jb	L$cbc_te_break_out
@@ -1344,7 +1344,7 @@ L$cbc_picked_te:
 	jmp	L$cbc_te_ok
 L$cbc_te_break_out:
 	subq	%r10,%r12
-	andq	$4095,%r12
+	andq	$0xFFF,%r12
 	addq	$320,%r12
 	subq	%r12,%r15
 .p2align	2
@@ -1370,7 +1370,7 @@ L$cbc_fast_body:
 
 	movq	%r15,%r10
 	subq	%r14,%r10
-	andq	$4095,%r10
+	andq	$0xfff,%r10
 	cmpq	$2304,%r10
 	jb	L$cbc_do_ecopy
 	cmpq	$4096-248,%r10
@@ -1557,7 +1557,7 @@ L$cbc_slow_prologue:
 	leaq	-88-63(%rcx),%r10
 	subq	%rbp,%r10
 	negq	%r10
-	andq	$960,%r10
+	andq	$0x3c0,%r10
 	subq	%r10,%rbp
 
 	xchgq	%rsp,%rbp
@@ -1586,7 +1586,7 @@ L$cbc_slow_body:
 	leaq	2048(%r14),%r14
 	leaq	768-8(%rsp),%rax
 	subq	%r14,%rax
-	andq	$768,%rax
+	andq	$0x300,%rax
 	leaq	(%r14,%rax,1),%r14
 
 	cmpq	$0,%rbx
diff --git a/packager/third_party/boringssl/mac-x86_64/crypto/aes/aesni-x86_64.S b/packager/third_party/boringssl/mac-x86_64/crypto/aes/aesni-x86_64.S
index 69b22c26b9..3d98fa12b6 100644
--- a/packager/third_party/boringssl/mac-x86_64/crypto/aes/aesni-x86_64.S
+++ b/packager/third_party/boringssl/mac-x86_64/crypto/aes/aesni-x86_64.S
@@ -507,7 +507,7 @@ _aesni_ecb_encrypt:
 	testl	%r8d,%r8d
 	jz	L$ecb_decrypt
 
-	cmpq	$128,%rdx
+	cmpq	$0x80,%rdx
 	jb	L$ecb_enc_tail
 
 	movdqu	(%rdi),%xmm2
@@ -519,7 +519,7 @@ _aesni_ecb_encrypt:
 	movdqu	96(%rdi),%xmm8
 	movdqu	112(%rdi),%xmm9
 	leaq	128(%rdi),%rdi
-	subq	$128,%rdx
+	subq	$0x80,%rdx
 	jmp	L$ecb_enc_loop8_enter
 .p2align	4
 L$ecb_enc_loop8:
@@ -547,7 +547,7 @@ L$ecb_enc_loop8_enter:
 
 	call	_aesni_encrypt8
 
-	subq	$128,%rdx
+	subq	$0x80,%rdx
 	jnc	L$ecb_enc_loop8
 
 	movups	%xmm2,(%rsi)
@@ -561,22 +561,22 @@ L$ecb_enc_loop8_enter:
 	movups	%xmm8,96(%rsi)
 	movups	%xmm9,112(%rsi)
 	leaq	128(%rsi),%rsi
-	addq	$128,%rdx
+	addq	$0x80,%rdx
 	jz	L$ecb_ret
 
 L$ecb_enc_tail:
 	movups	(%rdi),%xmm2
-	cmpq	$32,%rdx
+	cmpq	$0x20,%rdx
 	jb	L$ecb_enc_one
 	movups	16(%rdi),%xmm3
 	je	L$ecb_enc_two
 	movups	32(%rdi),%xmm4
-	cmpq	$64,%rdx
+	cmpq	$0x40,%rdx
 	jb	L$ecb_enc_three
 	movups	48(%rdi),%xmm5
 	je	L$ecb_enc_four
 	movups	64(%rdi),%xmm6
-	cmpq	$96,%rdx
+	cmpq	$0x60,%rdx
 	jb	L$ecb_enc_five
 	movups	80(%rdi),%xmm7
 	je	L$ecb_enc_six
@@ -650,7 +650,7 @@ L$ecb_enc_six:
 
 .p2align	4
 L$ecb_decrypt:
-	cmpq	$128,%rdx
+	cmpq	$0x80,%rdx
 	jb	L$ecb_dec_tail
 
 	movdqu	(%rdi),%xmm2
@@ -662,7 +662,7 @@ L$ecb_decrypt:
 	movdqu	96(%rdi),%xmm8
 	movdqu	112(%rdi),%xmm9
 	leaq	128(%rdi),%rdi
-	subq	$128,%rdx
+	subq	$0x80,%rdx
 	jmp	L$ecb_dec_loop8_enter
 .p2align	4
 L$ecb_dec_loop8:
@@ -691,7 +691,7 @@ L$ecb_dec_loop8_enter:
 	call	_aesni_decrypt8
 
 	movups	(%r11),%xmm0
-	subq	$128,%rdx
+	subq	$0x80,%rdx
 	jnc	L$ecb_dec_loop8
 
 	movups	%xmm2,(%rsi)
@@ -713,22 +713,22 @@ L$ecb_dec_loop8_enter:
 	movups	%xmm9,112(%rsi)
 	pxor	%xmm9,%xmm9
 	leaq	128(%rsi),%rsi
-	addq	$128,%rdx
+	addq	$0x80,%rdx
 	jz	L$ecb_ret
 
 L$ecb_dec_tail:
 	movups	(%rdi),%xmm2
-	cmpq	$32,%rdx
+	cmpq	$0x20,%rdx
 	jb	L$ecb_dec_one
 	movups	16(%rdi),%xmm3
 	je	L$ecb_dec_two
 	movups	32(%rdi),%xmm4
-	cmpq	$64,%rdx
+	cmpq	$0x40,%rdx
 	jb	L$ecb_dec_three
 	movups	48(%rdi),%xmm5
 	je	L$ecb_dec_four
 	movups	64(%rdi),%xmm6
-	cmpq	$96,%rdx
+	cmpq	$0x60,%rdx
 	jb	L$ecb_dec_five
 	movups	80(%rdi),%xmm7
 	je	L$ecb_dec_six
@@ -1606,7 +1606,7 @@ L$oop_enc1_8:
 
 	movdqa	L$xts_magic(%rip),%xmm8
 	movdqa	%xmm2,%xmm15
-	pshufd	$95,%xmm2,%xmm9
+	pshufd	$0x5f,%xmm2,%xmm9
 	pxor	%xmm0,%xmm1
 	movdqa	%xmm9,%xmm14
 	paddd	%xmm9,%xmm9
@@ -1705,7 +1705,7 @@ L$xts_enc_grandloop:
 .byte	102,15,56,220,248
 	movups	64(%r11),%xmm0
 	movdqa	%xmm8,80(%rsp)
-	pshufd	$95,%xmm15,%xmm9
+	pshufd	$0x5f,%xmm15,%xmm9
 	jmp	L$xts_enc_loop6
 .p2align	5
 L$xts_enc_loop6:
@@ -1844,13 +1844,13 @@ L$xts_enc_short:
 	jz	L$xts_enc_done
 
 	pxor	%xmm0,%xmm11
-	cmpq	$32,%rdx
+	cmpq	$0x20,%rdx
 	jb	L$xts_enc_one
 	pxor	%xmm0,%xmm12
 	je	L$xts_enc_two
 
 	pxor	%xmm0,%xmm13
-	cmpq	$64,%rdx
+	cmpq	$0x40,%rdx
 	jb	L$xts_enc_three
 	pxor	%xmm0,%xmm14
 	je	L$xts_enc_four
@@ -2078,7 +2078,7 @@ L$oop_enc1_11:
 
 	movdqa	L$xts_magic(%rip),%xmm8
 	movdqa	%xmm2,%xmm15
-	pshufd	$95,%xmm2,%xmm9
+	pshufd	$0x5f,%xmm2,%xmm9
 	pxor	%xmm0,%xmm1
 	movdqa	%xmm9,%xmm14
 	paddd	%xmm9,%xmm9
@@ -2177,7 +2177,7 @@ L$xts_dec_grandloop:
 .byte	102,15,56,222,248
 	movups	64(%r11),%xmm0
 	movdqa	%xmm8,80(%rsp)
-	pshufd	$95,%xmm15,%xmm9
+	pshufd	$0x5f,%xmm15,%xmm9
 	jmp	L$xts_dec_loop6
 .p2align	5
 L$xts_dec_loop6:
@@ -2317,13 +2317,13 @@ L$xts_dec_short:
 	jz	L$xts_dec_done
 
 	pxor	%xmm0,%xmm12
-	cmpq	$32,%rdx
+	cmpq	$0x20,%rdx
 	jb	L$xts_dec_one
 	pxor	%xmm0,%xmm13
 	je	L$xts_dec_two
 
 	pxor	%xmm0,%xmm14
-	cmpq	$64,%rdx
+	cmpq	$0x40,%rdx
 	jb	L$xts_dec_three
 	je	L$xts_dec_four
 
@@ -2354,7 +2354,7 @@ L$xts_dec_short:
 	pcmpgtd	%xmm15,%xmm14
 	movdqu	%xmm6,64(%rsi)
 	leaq	80(%rsi),%rsi
-	pshufd	$19,%xmm14,%xmm11
+	pshufd	$0x13,%xmm14,%xmm11
 	andq	$15,%r9
 	jz	L$xts_dec_ret
 
@@ -2644,7 +2644,7 @@ L$cbc_decrypt_bulk:
 	leaq	-8(%rax),%rbp
 	movups	(%r8),%xmm10
 	movl	%r10d,%eax
-	cmpq	$80,%rdx
+	cmpq	$0x50,%rdx
 	jbe	L$cbc_dec_tail
 
 	movups	(%rcx),%xmm0
@@ -2660,14 +2660,14 @@ L$cbc_decrypt_bulk:
 	movdqu	80(%rdi),%xmm7
 	movdqa	%xmm6,%xmm15
 	movl	_OPENSSL_ia32cap_P+4(%rip),%r9d
-	cmpq	$112,%rdx
+	cmpq	$0x70,%rdx
 	jbe	L$cbc_dec_six_or_seven
 
 	andl	$71303168,%r9d
-	subq	$80,%rdx
+	subq	$0x50,%rdx
 	cmpl	$4194304,%r9d
 	je	L$cbc_dec_loop6_enter
-	subq	$32,%rdx
+	subq	$0x20,%rdx
 	leaq	112(%rcx),%rcx
 	jmp	L$cbc_dec_loop8_enter
 .p2align	4
@@ -2682,7 +2682,7 @@ L$cbc_dec_loop8_enter:
 	movups	16-112(%rcx),%xmm1
 	pxor	%xmm0,%xmm4
 	xorq	%r11,%r11
-	cmpq	$112,%rdx
+	cmpq	$0x70,%rdx
 	pxor	%xmm0,%xmm5
 	pxor	%xmm0,%xmm6
 	pxor	%xmm0,%xmm7
@@ -2867,21 +2867,21 @@ L$cbc_dec_done:
 	movups	%xmm8,96(%rsi)
 	leaq	112(%rsi),%rsi
 
-	subq	$128,%rdx
+	subq	$0x80,%rdx
 	ja	L$cbc_dec_loop8
 
 	movaps	%xmm9,%xmm2
 	leaq	-112(%rcx),%rcx
-	addq	$112,%rdx
+	addq	$0x70,%rdx
 	jle	L$cbc_dec_clear_tail_collected
 	movups	%xmm9,(%rsi)
 	leaq	16(%rsi),%rsi
-	cmpq	$80,%rdx
+	cmpq	$0x50,%rdx
 	jbe	L$cbc_dec_tail
 
 	movaps	%xmm11,%xmm2
 L$cbc_dec_six_or_seven:
-	cmpq	$96,%rdx
+	cmpq	$0x60,%rdx
 	ja	L$cbc_dec_seven
 
 	movaps	%xmm7,%xmm8
@@ -2974,33 +2974,33 @@ L$cbc_dec_loop6_enter:
 	movl	%r10d,%eax
 	movdqu	%xmm6,64(%rsi)
 	leaq	80(%rsi),%rsi
-	subq	$96,%rdx
+	subq	$0x60,%rdx
 	ja	L$cbc_dec_loop6
 
 	movdqa	%xmm7,%xmm2
-	addq	$80,%rdx
+	addq	$0x50,%rdx
 	jle	L$cbc_dec_clear_tail_collected
 	movups	%xmm7,(%rsi)
 	leaq	16(%rsi),%rsi
 
 L$cbc_dec_tail:
 	movups	(%rdi),%xmm2
-	subq	$16,%rdx
+	subq	$0x10,%rdx
 	jbe	L$cbc_dec_one
 
 	movups	16(%rdi),%xmm3
 	movaps	%xmm2,%xmm11
-	subq	$16,%rdx
+	subq	$0x10,%rdx
 	jbe	L$cbc_dec_two
 
 	movups	32(%rdi),%xmm4
 	movaps	%xmm3,%xmm12
-	subq	$16,%rdx
+	subq	$0x10,%rdx
 	jbe	L$cbc_dec_three
 
 	movups	48(%rdi),%xmm5
 	movaps	%xmm4,%xmm13
-	subq	$16,%rdx
+	subq	$0x10,%rdx
 	jbe	L$cbc_dec_four
 
 	movups	64(%rdi),%xmm6
@@ -3025,7 +3025,7 @@ L$cbc_dec_tail:
 	movdqa	%xmm6,%xmm2
 	pxor	%xmm6,%xmm6
 	pxor	%xmm7,%xmm7
-	subq	$16,%rdx
+	subq	$0x10,%rdx
 	jmp	L$cbc_dec_tail_collected
 
 .p2align	4
@@ -3344,7 +3344,7 @@ L$oop_key192:
 	pslldq	$4,%xmm0
 	pxor	%xmm3,%xmm0
 
-	pshufd	$255,%xmm0,%xmm3
+	pshufd	$0xff,%xmm0,%xmm3
 	pxor	%xmm1,%xmm3
 	pslldq	$4,%xmm1
 	pxor	%xmm1,%xmm3
@@ -3431,7 +3431,7 @@ L$oop_key256:
 	decl	%r10d
 	jz	L$done_key256
 
-	pshufd	$255,%xmm0,%xmm2
+	pshufd	$0xff,%xmm0,%xmm2
 	pxor	%xmm3,%xmm3
 .byte	102,15,56,221,211
 
diff --git a/packager/third_party/boringssl/mac-x86_64/crypto/aes/bsaes-x86_64.S b/packager/third_party/boringssl/mac-x86_64/crypto/aes/bsaes-x86_64.S
index c2d04776a9..ad802e3d5d 100644
--- a/packager/third_party/boringssl/mac-x86_64/crypto/aes/bsaes-x86_64.S
+++ b/packager/third_party/boringssl/mac-x86_64/crypto/aes/bsaes-x86_64.S
@@ -325,45 +325,45 @@ L$enc_sbox:
 	pxor	%xmm2,%xmm5
 	decl	%r10d
 	jl	L$enc_done
-	pshufd	$147,%xmm15,%xmm7
-	pshufd	$147,%xmm0,%xmm8
+	pshufd	$0x93,%xmm15,%xmm7
+	pshufd	$0x93,%xmm0,%xmm8
 	pxor	%xmm7,%xmm15
-	pshufd	$147,%xmm3,%xmm9
+	pshufd	$0x93,%xmm3,%xmm9
 	pxor	%xmm8,%xmm0
-	pshufd	$147,%xmm5,%xmm10
+	pshufd	$0x93,%xmm5,%xmm10
 	pxor	%xmm9,%xmm3
-	pshufd	$147,%xmm2,%xmm11
+	pshufd	$0x93,%xmm2,%xmm11
 	pxor	%xmm10,%xmm5
-	pshufd	$147,%xmm6,%xmm12
+	pshufd	$0x93,%xmm6,%xmm12
 	pxor	%xmm11,%xmm2
-	pshufd	$147,%xmm1,%xmm13
+	pshufd	$0x93,%xmm1,%xmm13
 	pxor	%xmm12,%xmm6
-	pshufd	$147,%xmm4,%xmm14
+	pshufd	$0x93,%xmm4,%xmm14
 	pxor	%xmm13,%xmm1
 	pxor	%xmm14,%xmm4
 
 	pxor	%xmm15,%xmm8
 	pxor	%xmm4,%xmm7
 	pxor	%xmm4,%xmm8
-	pshufd	$78,%xmm15,%xmm15
+	pshufd	$0x4E,%xmm15,%xmm15
 	pxor	%xmm0,%xmm9
-	pshufd	$78,%xmm0,%xmm0
+	pshufd	$0x4E,%xmm0,%xmm0
 	pxor	%xmm2,%xmm12
 	pxor	%xmm7,%xmm15
 	pxor	%xmm6,%xmm13
 	pxor	%xmm8,%xmm0
 	pxor	%xmm5,%xmm11
-	pshufd	$78,%xmm2,%xmm7
+	pshufd	$0x4E,%xmm2,%xmm7
 	pxor	%xmm1,%xmm14
-	pshufd	$78,%xmm6,%xmm8
+	pshufd	$0x4E,%xmm6,%xmm8
 	pxor	%xmm3,%xmm10
-	pshufd	$78,%xmm5,%xmm2
+	pshufd	$0x4E,%xmm5,%xmm2
 	pxor	%xmm4,%xmm10
-	pshufd	$78,%xmm4,%xmm6
+	pshufd	$0x4E,%xmm4,%xmm6
 	pxor	%xmm4,%xmm11
-	pshufd	$78,%xmm1,%xmm5
+	pshufd	$0x4E,%xmm1,%xmm5
 	pxor	%xmm11,%xmm7
-	pshufd	$78,%xmm3,%xmm1
+	pshufd	$0x4E,%xmm3,%xmm1
 	pxor	%xmm12,%xmm8
 	pxor	%xmm10,%xmm2
 	pxor	%xmm14,%xmm6
@@ -797,24 +797,24 @@ L$dec_sbox:
 	decl	%r10d
 	jl	L$dec_done
 
-	pshufd	$78,%xmm15,%xmm7
-	pshufd	$78,%xmm2,%xmm13
+	pshufd	$0x4E,%xmm15,%xmm7
+	pshufd	$0x4E,%xmm2,%xmm13
 	pxor	%xmm15,%xmm7
-	pshufd	$78,%xmm4,%xmm14
+	pshufd	$0x4E,%xmm4,%xmm14
 	pxor	%xmm2,%xmm13
-	pshufd	$78,%xmm0,%xmm8
+	pshufd	$0x4E,%xmm0,%xmm8
 	pxor	%xmm4,%xmm14
-	pshufd	$78,%xmm5,%xmm9
+	pshufd	$0x4E,%xmm5,%xmm9
 	pxor	%xmm0,%xmm8
-	pshufd	$78,%xmm3,%xmm10
+	pshufd	$0x4E,%xmm3,%xmm10
 	pxor	%xmm5,%xmm9
 	pxor	%xmm13,%xmm15
 	pxor	%xmm13,%xmm0
-	pshufd	$78,%xmm1,%xmm11
+	pshufd	$0x4E,%xmm1,%xmm11
 	pxor	%xmm3,%xmm10
 	pxor	%xmm7,%xmm5
 	pxor	%xmm8,%xmm3
-	pshufd	$78,%xmm6,%xmm12
+	pshufd	$0x4E,%xmm6,%xmm12
 	pxor	%xmm1,%xmm11
 	pxor	%xmm14,%xmm0
 	pxor	%xmm9,%xmm1
@@ -828,45 +828,45 @@ L$dec_sbox:
 	pxor	%xmm14,%xmm1
 	pxor	%xmm14,%xmm6
 	pxor	%xmm12,%xmm4
-	pshufd	$147,%xmm15,%xmm7
-	pshufd	$147,%xmm0,%xmm8
+	pshufd	$0x93,%xmm15,%xmm7
+	pshufd	$0x93,%xmm0,%xmm8
 	pxor	%xmm7,%xmm15
-	pshufd	$147,%xmm5,%xmm9
+	pshufd	$0x93,%xmm5,%xmm9
 	pxor	%xmm8,%xmm0
-	pshufd	$147,%xmm3,%xmm10
+	pshufd	$0x93,%xmm3,%xmm10
 	pxor	%xmm9,%xmm5
-	pshufd	$147,%xmm1,%xmm11
+	pshufd	$0x93,%xmm1,%xmm11
 	pxor	%xmm10,%xmm3
-	pshufd	$147,%xmm6,%xmm12
+	pshufd	$0x93,%xmm6,%xmm12
 	pxor	%xmm11,%xmm1
-	pshufd	$147,%xmm2,%xmm13
+	pshufd	$0x93,%xmm2,%xmm13
 	pxor	%xmm12,%xmm6
-	pshufd	$147,%xmm4,%xmm14
+	pshufd	$0x93,%xmm4,%xmm14
 	pxor	%xmm13,%xmm2
 	pxor	%xmm14,%xmm4
 
 	pxor	%xmm15,%xmm8
 	pxor	%xmm4,%xmm7
 	pxor	%xmm4,%xmm8
-	pshufd	$78,%xmm15,%xmm15
+	pshufd	$0x4E,%xmm15,%xmm15
 	pxor	%xmm0,%xmm9
-	pshufd	$78,%xmm0,%xmm0
+	pshufd	$0x4E,%xmm0,%xmm0
 	pxor	%xmm1,%xmm12
 	pxor	%xmm7,%xmm15
 	pxor	%xmm6,%xmm13
 	pxor	%xmm8,%xmm0
 	pxor	%xmm3,%xmm11
-	pshufd	$78,%xmm1,%xmm7
+	pshufd	$0x4E,%xmm1,%xmm7
 	pxor	%xmm2,%xmm14
-	pshufd	$78,%xmm6,%xmm8
+	pshufd	$0x4E,%xmm6,%xmm8
 	pxor	%xmm5,%xmm10
-	pshufd	$78,%xmm3,%xmm1
+	pshufd	$0x4E,%xmm3,%xmm1
 	pxor	%xmm4,%xmm10
-	pshufd	$78,%xmm4,%xmm6
+	pshufd	$0x4E,%xmm4,%xmm6
 	pxor	%xmm4,%xmm11
-	pshufd	$78,%xmm2,%xmm3
+	pshufd	$0x4E,%xmm2,%xmm3
 	pxor	%xmm11,%xmm7
-	pshufd	$78,%xmm5,%xmm2
+	pshufd	$0x4E,%xmm5,%xmm2
 	pxor	%xmm12,%xmm8
 	pxor	%xmm1,%xmm10
 	pxor	%xmm14,%xmm6
@@ -1556,20 +1556,20 @@ L$xts_enc_prologue:
 	movdqa	%xmm7,(%rax)
 
 	andq	$-16,%r14
-	subq	$128,%rsp
+	subq	$0x80,%rsp
 	movdqa	32(%rbp),%xmm6
 
 	pxor	%xmm14,%xmm14
 	movdqa	L$xts_magic(%rip),%xmm12
 	pcmpgtd	%xmm6,%xmm14
 
-	subq	$128,%r14
+	subq	$0x80,%r14
 	jc	L$xts_enc_short
 	jmp	L$xts_enc_loop
 
 .p2align	4
 L$xts_enc_loop:
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm15
 	movdqa	%xmm6,0(%rsp)
@@ -1577,7 +1577,7 @@ L$xts_enc_loop:
 	pand	%xmm12,%xmm13
 	pcmpgtd	%xmm6,%xmm14
 	pxor	%xmm13,%xmm6
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm0
 	movdqa	%xmm6,16(%rsp)
@@ -1586,7 +1586,7 @@ L$xts_enc_loop:
 	pcmpgtd	%xmm6,%xmm14
 	pxor	%xmm13,%xmm6
 	movdqu	0(%r12),%xmm7
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm1
 	movdqa	%xmm6,32(%rsp)
@@ -1596,7 +1596,7 @@ L$xts_enc_loop:
 	pxor	%xmm13,%xmm6
 	movdqu	16(%r12),%xmm8
 	pxor	%xmm7,%xmm15
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm2
 	movdqa	%xmm6,48(%rsp)
@@ -1606,7 +1606,7 @@ L$xts_enc_loop:
 	pxor	%xmm13,%xmm6
 	movdqu	32(%r12),%xmm9
 	pxor	%xmm8,%xmm0
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm3
 	movdqa	%xmm6,64(%rsp)
@@ -1616,7 +1616,7 @@ L$xts_enc_loop:
 	pxor	%xmm13,%xmm6
 	movdqu	48(%r12),%xmm10
 	pxor	%xmm9,%xmm1
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm4
 	movdqa	%xmm6,80(%rsp)
@@ -1626,7 +1626,7 @@ L$xts_enc_loop:
 	pxor	%xmm13,%xmm6
 	movdqu	64(%r12),%xmm11
 	pxor	%xmm10,%xmm2
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm5
 	movdqa	%xmm6,96(%rsp)
@@ -1670,20 +1670,20 @@ L$xts_enc_loop:
 	pxor	%xmm14,%xmm14
 	movdqa	L$xts_magic(%rip),%xmm12
 	pcmpgtd	%xmm6,%xmm14
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	paddq	%xmm6,%xmm6
 	pand	%xmm12,%xmm13
 	pcmpgtd	%xmm6,%xmm14
 	pxor	%xmm13,%xmm6
 
-	subq	$128,%r14
+	subq	$0x80,%r14
 	jnc	L$xts_enc_loop
 
 L$xts_enc_short:
-	addq	$128,%r14
+	addq	$0x80,%r14
 	jz	L$xts_enc_done
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm15
 	movdqa	%xmm6,0(%rsp)
@@ -1691,7 +1691,7 @@ L$xts_enc_short:
 	pand	%xmm12,%xmm13
 	pcmpgtd	%xmm6,%xmm14
 	pxor	%xmm13,%xmm6
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm0
 	movdqa	%xmm6,16(%rsp)
@@ -1702,7 +1702,7 @@ L$xts_enc_short:
 	movdqu	0(%r12),%xmm7
 	cmpq	$16,%r14
 	je	L$xts_enc_1
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm1
 	movdqa	%xmm6,32(%rsp)
@@ -1714,7 +1714,7 @@ L$xts_enc_short:
 	cmpq	$32,%r14
 	je	L$xts_enc_2
 	pxor	%xmm7,%xmm15
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm2
 	movdqa	%xmm6,48(%rsp)
@@ -1726,7 +1726,7 @@ L$xts_enc_short:
 	cmpq	$48,%r14
 	je	L$xts_enc_3
 	pxor	%xmm8,%xmm0
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm3
 	movdqa	%xmm6,64(%rsp)
@@ -1738,7 +1738,7 @@ L$xts_enc_short:
 	cmpq	$64,%r14
 	je	L$xts_enc_4
 	pxor	%xmm9,%xmm1
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm4
 	movdqa	%xmm6,80(%rsp)
@@ -1750,7 +1750,7 @@ L$xts_enc_short:
 	cmpq	$80,%r14
 	je	L$xts_enc_5
 	pxor	%xmm10,%xmm2
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm5
 	movdqa	%xmm6,96(%rsp)
@@ -2016,20 +2016,20 @@ L$xts_dec_prologue:
 	shlq	$4,%rax
 	subq	%rax,%r14
 
-	subq	$128,%rsp
+	subq	$0x80,%rsp
 	movdqa	32(%rbp),%xmm6
 
 	pxor	%xmm14,%xmm14
 	movdqa	L$xts_magic(%rip),%xmm12
 	pcmpgtd	%xmm6,%xmm14
 
-	subq	$128,%r14
+	subq	$0x80,%r14
 	jc	L$xts_dec_short
 	jmp	L$xts_dec_loop
 
 .p2align	4
 L$xts_dec_loop:
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm15
 	movdqa	%xmm6,0(%rsp)
@@ -2037,7 +2037,7 @@ L$xts_dec_loop:
 	pand	%xmm12,%xmm13
 	pcmpgtd	%xmm6,%xmm14
 	pxor	%xmm13,%xmm6
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm0
 	movdqa	%xmm6,16(%rsp)
@@ -2046,7 +2046,7 @@ L$xts_dec_loop:
 	pcmpgtd	%xmm6,%xmm14
 	pxor	%xmm13,%xmm6
 	movdqu	0(%r12),%xmm7
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm1
 	movdqa	%xmm6,32(%rsp)
@@ -2056,7 +2056,7 @@ L$xts_dec_loop:
 	pxor	%xmm13,%xmm6
 	movdqu	16(%r12),%xmm8
 	pxor	%xmm7,%xmm15
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm2
 	movdqa	%xmm6,48(%rsp)
@@ -2066,7 +2066,7 @@ L$xts_dec_loop:
 	pxor	%xmm13,%xmm6
 	movdqu	32(%r12),%xmm9
 	pxor	%xmm8,%xmm0
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm3
 	movdqa	%xmm6,64(%rsp)
@@ -2076,7 +2076,7 @@ L$xts_dec_loop:
 	pxor	%xmm13,%xmm6
 	movdqu	48(%r12),%xmm10
 	pxor	%xmm9,%xmm1
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm4
 	movdqa	%xmm6,80(%rsp)
@@ -2086,7 +2086,7 @@ L$xts_dec_loop:
 	pxor	%xmm13,%xmm6
 	movdqu	64(%r12),%xmm11
 	pxor	%xmm10,%xmm2
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm5
 	movdqa	%xmm6,96(%rsp)
@@ -2130,20 +2130,20 @@ L$xts_dec_loop:
 	pxor	%xmm14,%xmm14
 	movdqa	L$xts_magic(%rip),%xmm12
 	pcmpgtd	%xmm6,%xmm14
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	paddq	%xmm6,%xmm6
 	pand	%xmm12,%xmm13
 	pcmpgtd	%xmm6,%xmm14
 	pxor	%xmm13,%xmm6
 
-	subq	$128,%r14
+	subq	$0x80,%r14
 	jnc	L$xts_dec_loop
 
 L$xts_dec_short:
-	addq	$128,%r14
+	addq	$0x80,%r14
 	jz	L$xts_dec_done
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm15
 	movdqa	%xmm6,0(%rsp)
@@ -2151,7 +2151,7 @@ L$xts_dec_short:
 	pand	%xmm12,%xmm13
 	pcmpgtd	%xmm6,%xmm14
 	pxor	%xmm13,%xmm6
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm0
 	movdqa	%xmm6,16(%rsp)
@@ -2162,7 +2162,7 @@ L$xts_dec_short:
 	movdqu	0(%r12),%xmm7
 	cmpq	$16,%r14
 	je	L$xts_dec_1
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm1
 	movdqa	%xmm6,32(%rsp)
@@ -2174,7 +2174,7 @@ L$xts_dec_short:
 	cmpq	$32,%r14
 	je	L$xts_dec_2
 	pxor	%xmm7,%xmm15
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm2
 	movdqa	%xmm6,48(%rsp)
@@ -2186,7 +2186,7 @@ L$xts_dec_short:
 	cmpq	$48,%r14
 	je	L$xts_dec_3
 	pxor	%xmm8,%xmm0
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm3
 	movdqa	%xmm6,64(%rsp)
@@ -2198,7 +2198,7 @@ L$xts_dec_short:
 	cmpq	$64,%r14
 	je	L$xts_dec_4
 	pxor	%xmm9,%xmm1
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm4
 	movdqa	%xmm6,80(%rsp)
@@ -2210,7 +2210,7 @@ L$xts_dec_short:
 	cmpq	$80,%r14
 	je	L$xts_dec_5
 	pxor	%xmm10,%xmm2
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm5
 	movdqa	%xmm6,96(%rsp)
@@ -2387,7 +2387,7 @@ L$xts_dec_done:
 	pxor	%xmm14,%xmm14
 	movdqa	L$xts_magic(%rip),%xmm12
 	pcmpgtd	%xmm6,%xmm14
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	movdqa	%xmm6,%xmm5
 	paddq	%xmm6,%xmm6
 	pand	%xmm12,%xmm13
diff --git a/packager/third_party/boringssl/mac-x86_64/crypto/aes/vpaes-x86_64.S b/packager/third_party/boringssl/mac-x86_64/crypto/aes/vpaes-x86_64.S
index 711ea43726..997cde807a 100644
--- a/packager/third_party/boringssl/mac-x86_64/crypto/aes/vpaes-x86_64.S
+++ b/packager/third_party/boringssl/mac-x86_64/crypto/aes/vpaes-x86_64.S
@@ -61,7 +61,7 @@ L$enc_loop:
 	addq	$16,%r11
 	pxor	%xmm0,%xmm3
 .byte	102,15,56,0,193
-	andq	$48,%r11
+	andq	$0x30,%r11
 	subq	$1,%rax
 	pxor	%xmm3,%xmm0
 
@@ -121,10 +121,10 @@ _vpaes_decrypt_core:
 	pand	%xmm9,%xmm0
 .byte	102,15,56,0,208
 	movdqa	L$k_dipt+16(%rip),%xmm0
-	xorq	$48,%r11
+	xorq	$0x30,%r11
 	leaq	L$k_dsbd(%rip),%r10
 .byte	102,15,56,0,193
-	andq	$48,%r11
+	andq	$0x30,%r11
 	pxor	%xmm5,%xmm2
 	movdqa	L$k_mc_forward+48(%rip),%xmm5
 	pxor	%xmm2,%xmm0
@@ -243,7 +243,7 @@ L$schedule_am_decrypting:
 	movdqa	(%r8,%r10,1),%xmm1
 .byte	102,15,56,0,217
 	movdqu	%xmm3,(%rdx)
-	xorq	$48,%r8
+	xorq	$0x30,%r8
 
 L$schedule_go:
 	cmpl	$192,%esi
@@ -333,7 +333,7 @@ L$oop_schedule_256:
 	call	_vpaes_schedule_mangle
 
 
-	pshufd	$255,%xmm0,%xmm0
+	pshufd	$0xFF,%xmm0,%xmm0
 	movdqa	%xmm7,%xmm5
 	movdqa	%xmm6,%xmm7
 	call	_vpaes_schedule_low_round
@@ -400,8 +400,8 @@ L$schedule_mangle_last_dec:
 
 .p2align	4
 _vpaes_schedule_192_smear:
-	pshufd	$128,%xmm6,%xmm1
-	pshufd	$254,%xmm7,%xmm0
+	pshufd	$0x80,%xmm6,%xmm1
+	pshufd	$0xFE,%xmm7,%xmm0
 	pxor	%xmm1,%xmm6
 	pxor	%xmm1,%xmm1
 	pxor	%xmm0,%xmm6
@@ -438,7 +438,7 @@ _vpaes_schedule_round:
 	pxor	%xmm1,%xmm7
 
 
-	pshufd	$255,%xmm0,%xmm0
+	pshufd	$0xFF,%xmm0,%xmm0
 .byte	102,15,58,15,192,1
 
 
@@ -597,7 +597,7 @@ L$schedule_mangle_both:
 	movdqa	(%r8,%r10,1),%xmm1
 .byte	102,15,56,0,217
 	addq	$-16,%r8
-	andq	$48,%r8
+	andq	$0x30,%r8
 	movdqu	%xmm3,(%rdx)
 	.byte	0xf3,0xc3
 
@@ -616,7 +616,7 @@ _vpaes_set_encrypt_key:
 	movl	%eax,240(%rdx)
 
 	movl	$0,%ecx
-	movl	$48,%r8d
+	movl	$0x30,%r8d
 	call	_vpaes_schedule_core
 	xorl	%eax,%eax
 	.byte	0xf3,0xc3
diff --git a/packager/third_party/boringssl/mac-x86_64/crypto/bn/rsaz-x86_64.S b/packager/third_party/boringssl/mac-x86_64/crypto/bn/rsaz-x86_64.S
index 5e9e82feb0..337276f9cb 100644
--- a/packager/third_party/boringssl/mac-x86_64/crypto/bn/rsaz-x86_64.S
+++ b/packager/third_party/boringssl/mac-x86_64/crypto/bn/rsaz-x86_64.S
@@ -465,48 +465,94 @@ _rsaz_512_mul_gather4:
 	pushq	%r14
 	pushq	%r15
 
-	movl	%r9d,%r9d
-	subq	$128+24,%rsp
+	subq	$152,%rsp
 L$mul_gather4_body:
-	movl	64(%rdx,%r9,4),%eax
-.byte	102,72,15,110,199
-	movl	(%rdx,%r9,4),%ebx
-.byte	102,72,15,110,201
-	movq	%r8,128(%rsp)
+	movd	%r9d,%xmm8
+	movdqa	L$inc+16(%rip),%xmm1
+	movdqa	L$inc(%rip),%xmm0
+
+	pshufd	$0,%xmm8,%xmm8
+	movdqa	%xmm1,%xmm7
+	movdqa	%xmm1,%xmm2
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm8,%xmm0
+	movdqa	%xmm7,%xmm3
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm8,%xmm1
+	movdqa	%xmm7,%xmm4
+	paddd	%xmm2,%xmm3
+	pcmpeqd	%xmm8,%xmm2
+	movdqa	%xmm7,%xmm5
+	paddd	%xmm3,%xmm4
+	pcmpeqd	%xmm8,%xmm3
+	movdqa	%xmm7,%xmm6
+	paddd	%xmm4,%xmm5
+	pcmpeqd	%xmm8,%xmm4
+	paddd	%xmm5,%xmm6
+	pcmpeqd	%xmm8,%xmm5
+	paddd	%xmm6,%xmm7
+	pcmpeqd	%xmm8,%xmm6
+	pcmpeqd	%xmm8,%xmm7
+
+	movdqa	0(%rdx),%xmm8
+	movdqa	16(%rdx),%xmm9
+	movdqa	32(%rdx),%xmm10
+	movdqa	48(%rdx),%xmm11
+	pand	%xmm0,%xmm8
+	movdqa	64(%rdx),%xmm12
+	pand	%xmm1,%xmm9
+	movdqa	80(%rdx),%xmm13
+	pand	%xmm2,%xmm10
+	movdqa	96(%rdx),%xmm14
+	pand	%xmm3,%xmm11
+	movdqa	112(%rdx),%xmm15
+	leaq	128(%rdx),%rbp
+	pand	%xmm4,%xmm12
+	pand	%xmm5,%xmm13
+	pand	%xmm6,%xmm14
+	pand	%xmm7,%xmm15
+	por	%xmm10,%xmm8
+	por	%xmm11,%xmm9
+	por	%xmm12,%xmm8
+	por	%xmm13,%xmm9
+	por	%xmm14,%xmm8
+	por	%xmm15,%xmm9
+
+	por	%xmm9,%xmm8
+	pshufd	$0x4e,%xmm8,%xmm9
+	por	%xmm9,%xmm8
+.byte	102,76,15,126,195
+
+	movq	%r8,128(%rsp)
+	movq	%rdi,128+8(%rsp)
+	movq	%rcx,128+16(%rsp)
 
-	shlq	$32,%rax
-	orq	%rax,%rbx
 	movq	(%rsi),%rax
 	movq	8(%rsi),%rcx
-	leaq	128(%rdx,%r9,4),%rbp
 	mulq	%rbx
 	movq	%rax,(%rsp)
 	movq	%rcx,%rax
 	movq	%rdx,%r8
 
 	mulq	%rbx
-	movd	(%rbp),%xmm4
 	addq	%rax,%r8
 	movq	16(%rsi),%rax
 	movq	%rdx,%r9
 	adcq	$0,%r9
 
 	mulq	%rbx
-	movd	64(%rbp),%xmm5
 	addq	%rax,%r9
 	movq	24(%rsi),%rax
 	movq	%rdx,%r10
 	adcq	$0,%r10
 
 	mulq	%rbx
-	pslldq	$4,%xmm5
 	addq	%rax,%r10
 	movq	32(%rsi),%rax
 	movq	%rdx,%r11
 	adcq	$0,%r11
 
 	mulq	%rbx
-	por	%xmm5,%xmm4
 	addq	%rax,%r11
 	movq	40(%rsi),%rax
 	movq	%rdx,%r12
@@ -519,14 +565,12 @@ L$mul_gather4_body:
 	adcq	$0,%r13
 
 	mulq	%rbx
-	leaq	128(%rbp),%rbp
 	addq	%rax,%r13
 	movq	56(%rsi),%rax
 	movq	%rdx,%r14
 	adcq	$0,%r14
 
 	mulq	%rbx
-.byte	102,72,15,126,227
 	addq	%rax,%r14
 	movq	(%rsi),%rax
 	movq	%rdx,%r15
@@ -538,6 +582,35 @@ L$mul_gather4_body:
 
 .p2align	5
 L$oop_mul_gather:
+	movdqa	0(%rbp),%xmm8
+	movdqa	16(%rbp),%xmm9
+	movdqa	32(%rbp),%xmm10
+	movdqa	48(%rbp),%xmm11
+	pand	%xmm0,%xmm8
+	movdqa	64(%rbp),%xmm12
+	pand	%xmm1,%xmm9
+	movdqa	80(%rbp),%xmm13
+	pand	%xmm2,%xmm10
+	movdqa	96(%rbp),%xmm14
+	pand	%xmm3,%xmm11
+	movdqa	112(%rbp),%xmm15
+	leaq	128(%rbp),%rbp
+	pand	%xmm4,%xmm12
+	pand	%xmm5,%xmm13
+	pand	%xmm6,%xmm14
+	pand	%xmm7,%xmm15
+	por	%xmm10,%xmm8
+	por	%xmm11,%xmm9
+	por	%xmm12,%xmm8
+	por	%xmm13,%xmm9
+	por	%xmm14,%xmm8
+	por	%xmm15,%xmm9
+
+	por	%xmm9,%xmm8
+	pshufd	$0x4e,%xmm8,%xmm9
+	por	%xmm9,%xmm8
+.byte	102,76,15,126,195
+
 	mulq	%rbx
 	addq	%rax,%r8
 	movq	8(%rsi),%rax
@@ -546,7 +619,6 @@ L$oop_mul_gather:
 	adcq	$0,%r8
 
 	mulq	%rbx
-	movd	(%rbp),%xmm4
 	addq	%rax,%r9
 	movq	16(%rsi),%rax
 	adcq	$0,%rdx
@@ -555,7 +627,6 @@ L$oop_mul_gather:
 	adcq	$0,%r9
 
 	mulq	%rbx
-	movd	64(%rbp),%xmm5
 	addq	%rax,%r10
 	movq	24(%rsi),%rax
 	adcq	$0,%rdx
@@ -564,7 +635,6 @@ L$oop_mul_gather:
 	adcq	$0,%r10
 
 	mulq	%rbx
-	pslldq	$4,%xmm5
 	addq	%rax,%r11
 	movq	32(%rsi),%rax
 	adcq	$0,%rdx
@@ -573,7 +643,6 @@ L$oop_mul_gather:
 	adcq	$0,%r11
 
 	mulq	%rbx
-	por	%xmm5,%xmm4
 	addq	%rax,%r12
 	movq	40(%rsi),%rax
 	adcq	$0,%rdx
@@ -598,7 +667,6 @@ L$oop_mul_gather:
 	adcq	$0,%r14
 
 	mulq	%rbx
-.byte	102,72,15,126,227
 	addq	%rax,%r15
 	movq	(%rsi),%rax
 	adcq	$0,%rdx
@@ -606,7 +674,6 @@ L$oop_mul_gather:
 	movq	%rdx,%r15
 	adcq	$0,%r15
 
-	leaq	128(%rbp),%rbp
 	leaq	8(%rdi),%rdi
 
 	decl	%ecx
@@ -621,8 +688,8 @@ L$oop_mul_gather:
 	movq	%r14,48(%rdi)
 	movq	%r15,56(%rdi)
 
-.byte	102,72,15,126,199
-.byte	102,72,15,126,205
+	movq	128+8(%rsp),%rdi
+	movq	128+16(%rsp),%rbp
 
 	movq	(%rsp),%r8
 	movq	8(%rsp),%r9
@@ -672,7 +739,7 @@ _rsaz_512_mul_scatter4:
 	movl	%r9d,%r9d
 	subq	$128+24,%rsp
 L$mul_scatter4_body:
-	leaq	(%r8,%r9,4),%r8
+	leaq	(%r8,%r9,8),%r8
 .byte	102,72,15,110,199
 .byte	102,72,15,110,202
 .byte	102,73,15,110,208
@@ -708,30 +775,14 @@ L$mul_scatter4_body:
 
 	call	__rsaz_512_subtract
 
-	movl	%r8d,0(%rsi)
-	shrq	$32,%r8
-	movl	%r9d,128(%rsi)
-	shrq	$32,%r9
-	movl	%r10d,256(%rsi)
-	shrq	$32,%r10
-	movl	%r11d,384(%rsi)
-	shrq	$32,%r11
-	movl	%r12d,512(%rsi)
-	shrq	$32,%r12
-	movl	%r13d,640(%rsi)
-	shrq	$32,%r13
-	movl	%r14d,768(%rsi)
-	shrq	$32,%r14
-	movl	%r15d,896(%rsi)
-	shrq	$32,%r15
-	movl	%r8d,64(%rsi)
-	movl	%r9d,192(%rsi)
-	movl	%r10d,320(%rsi)
-	movl	%r11d,448(%rsi)
-	movl	%r12d,576(%rsi)
-	movl	%r13d,704(%rsi)
-	movl	%r14d,832(%rsi)
-	movl	%r15d,960(%rsi)
+	movq	%r8,0(%rsi)
+	movq	%r9,128(%rsi)
+	movq	%r10,256(%rsi)
+	movq	%r11,384(%rsi)
+	movq	%r12,512(%rsi)
+	movq	%r13,640(%rsi)
+	movq	%r14,768(%rsi)
+	movq	%r15,896(%rsi)
 
 	leaq	128+24+48(%rsp),%rax
 	movq	-48(%rax),%r15
@@ -1086,16 +1137,14 @@ L$oop_mul:
 
 .p2align	4
 _rsaz_512_scatter4:
-	leaq	(%rdi,%rdx,4),%rdi
+	leaq	(%rdi,%rdx,8),%rdi
 	movl	$8,%r9d
 	jmp	L$oop_scatter
 .p2align	4
 L$oop_scatter:
 	movq	(%rsi),%rax
 	leaq	8(%rsi),%rsi
-	movl	%eax,(%rdi)
-	shrq	$32,%rax
-	movl	%eax,64(%rdi)
+	movq	%rax,(%rdi)
 	leaq	128(%rdi),%rdi
 	decl	%r9d
 	jnz	L$oop_scatter
@@ -1107,20 +1156,73 @@ L$oop_scatter:
 
 .p2align	4
 _rsaz_512_gather4:
-	leaq	(%rsi,%rdx,4),%rsi
+	movd	%edx,%xmm8
+	movdqa	L$inc+16(%rip),%xmm1
+	movdqa	L$inc(%rip),%xmm0
+
+	pshufd	$0,%xmm8,%xmm8
+	movdqa	%xmm1,%xmm7
+	movdqa	%xmm1,%xmm2
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm8,%xmm0
+	movdqa	%xmm7,%xmm3
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm8,%xmm1
+	movdqa	%xmm7,%xmm4
+	paddd	%xmm2,%xmm3
+	pcmpeqd	%xmm8,%xmm2
+	movdqa	%xmm7,%xmm5
+	paddd	%xmm3,%xmm4
+	pcmpeqd	%xmm8,%xmm3
+	movdqa	%xmm7,%xmm6
+	paddd	%xmm4,%xmm5
+	pcmpeqd	%xmm8,%xmm4
+	paddd	%xmm5,%xmm6
+	pcmpeqd	%xmm8,%xmm5
+	paddd	%xmm6,%xmm7
+	pcmpeqd	%xmm8,%xmm6
+	pcmpeqd	%xmm8,%xmm7
 	movl	$8,%r9d
 	jmp	L$oop_gather
 .p2align	4
 L$oop_gather:
-	movl	(%rsi),%eax
-	movl	64(%rsi),%r8d
+	movdqa	0(%rsi),%xmm8
+	movdqa	16(%rsi),%xmm9
+	movdqa	32(%rsi),%xmm10
+	movdqa	48(%rsi),%xmm11
+	pand	%xmm0,%xmm8
+	movdqa	64(%rsi),%xmm12
+	pand	%xmm1,%xmm9
+	movdqa	80(%rsi),%xmm13
+	pand	%xmm2,%xmm10
+	movdqa	96(%rsi),%xmm14
+	pand	%xmm3,%xmm11
+	movdqa	112(%rsi),%xmm15
 	leaq	128(%rsi),%rsi
-	shlq	$32,%r8
-	orq	%r8,%rax
-	movq	%rax,(%rdi)
+	pand	%xmm4,%xmm12
+	pand	%xmm5,%xmm13
+	pand	%xmm6,%xmm14
+	pand	%xmm7,%xmm15
+	por	%xmm10,%xmm8
+	por	%xmm11,%xmm9
+	por	%xmm12,%xmm8
+	por	%xmm13,%xmm9
+	por	%xmm14,%xmm8
+	por	%xmm15,%xmm9
+
+	por	%xmm9,%xmm8
+	pshufd	$0x4e,%xmm8,%xmm9
+	por	%xmm9,%xmm8
+	movq	%xmm8,(%rdi)
 	leaq	8(%rdi),%rdi
 	decl	%r9d
 	jnz	L$oop_gather
 	.byte	0xf3,0xc3
+L$SEH_end_rsaz_512_gather4:
 
+
+.p2align	6
+L$inc:
+.long	0,0, 1,1
+.long	2,2, 2,2
 #endif
diff --git a/packager/third_party/boringssl/mac-x86_64/crypto/bn/x86_64-mont.S b/packager/third_party/boringssl/mac-x86_64/crypto/bn/x86_64-mont.S
index 6b9bc05bf4..51e5d19931 100644
--- a/packager/third_party/boringssl/mac-x86_64/crypto/bn/x86_64-mont.S
+++ b/packager/third_party/boringssl/mac-x86_64/crypto/bn/x86_64-mont.S
@@ -634,20 +634,20 @@ L$sqr8x_enter:
 
 
 
-	leaq	-64(%rsp,%r9,4),%r11
+	leaq	-64(%rsp,%r9,2),%r11
 	movq	(%r8),%r8
 	subq	%rsi,%r11
 	andq	$4095,%r11
 	cmpq	%r11,%r10
 	jb	L$sqr8x_sp_alt
 	subq	%r11,%rsp
-	leaq	-64(%rsp,%r9,4),%rsp
+	leaq	-64(%rsp,%r9,2),%rsp
 	jmp	L$sqr8x_sp_done
 
 .p2align	5
 L$sqr8x_sp_alt:
-	leaq	4096-64(,%r9,4),%r10
-	leaq	-64(%rsp,%r9,4),%rsp
+	leaq	4096-64(,%r9,2),%r10
+	leaq	-64(%rsp,%r9,2),%rsp
 	subq	%r10,%r11
 	movq	$0,%r10
 	cmovcq	%r10,%r11
@@ -657,58 +657,80 @@ L$sqr8x_sp_done:
 	movq	%r9,%r10
 	negq	%r9
 
-	leaq	64(%rsp,%r9,2),%r11
 	movq	%r8,32(%rsp)
 	movq	%rax,40(%rsp)
 L$sqr8x_body:
 
-	movq	%r9,%rbp
-.byte	102,73,15,110,211
-	shrq	$3+2,%rbp
-	movl	_OPENSSL_ia32cap_P+8(%rip),%eax
-	jmp	L$sqr8x_copy_n
-
-.p2align	5
-L$sqr8x_copy_n:
-	movq	0(%rcx),%xmm0
-	movq	8(%rcx),%xmm1
-	movq	16(%rcx),%xmm3
-	movq	24(%rcx),%xmm4
-	leaq	32(%rcx),%rcx
-	movdqa	%xmm0,0(%r11)
-	movdqa	%xmm1,16(%r11)
-	movdqa	%xmm3,32(%r11)
-	movdqa	%xmm4,48(%r11)
-	leaq	64(%r11),%r11
-	decq	%rbp
-	jnz	L$sqr8x_copy_n
-
+.byte	102,72,15,110,209
 	pxor	%xmm0,%xmm0
 .byte	102,72,15,110,207
 .byte	102,73,15,110,218
 	call	_bn_sqr8x_internal
 
-	pxor	%xmm0,%xmm0
-	leaq	48(%rsp),%rax
-	leaq	64(%rsp,%r9,2),%rdx
-	shrq	$3+2,%r9
-	movq	40(%rsp),%rsi
-	jmp	L$sqr8x_zero
+
+
+
+	leaq	(%rdi,%r9,1),%rbx
+	movq	%r9,%rcx
+	movq	%r9,%rdx
+.byte	102,72,15,126,207
+	sarq	$3+2,%rcx
+	jmp	L$sqr8x_sub
 
 .p2align	5
-L$sqr8x_zero:
-	movdqa	%xmm0,0(%rax)
-	movdqa	%xmm0,16(%rax)
-	movdqa	%xmm0,32(%rax)
-	movdqa	%xmm0,48(%rax)
-	leaq	64(%rax),%rax
-	movdqa	%xmm0,0(%rdx)
-	movdqa	%xmm0,16(%rdx)
-	movdqa	%xmm0,32(%rdx)
-	movdqa	%xmm0,48(%rdx)
-	leaq	64(%rdx),%rdx
-	decq	%r9
-	jnz	L$sqr8x_zero
+L$sqr8x_sub:
+	movq	0(%rbx),%r12
+	movq	8(%rbx),%r13
+	movq	16(%rbx),%r14
+	movq	24(%rbx),%r15
+	leaq	32(%rbx),%rbx
+	sbbq	0(%rbp),%r12
+	sbbq	8(%rbp),%r13
+	sbbq	16(%rbp),%r14
+	sbbq	24(%rbp),%r15
+	leaq	32(%rbp),%rbp
+	movq	%r12,0(%rdi)
+	movq	%r13,8(%rdi)
+	movq	%r14,16(%rdi)
+	movq	%r15,24(%rdi)
+	leaq	32(%rdi),%rdi
+	incq	%rcx
+	jnz	L$sqr8x_sub
+
+	sbbq	$0,%rax
+	leaq	(%rbx,%r9,1),%rbx
+	leaq	(%rdi,%r9,1),%rdi
+
+.byte	102,72,15,110,200
+	pxor	%xmm0,%xmm0
+	pshufd	$0,%xmm1,%xmm1
+	movq	40(%rsp),%rsi
+	jmp	L$sqr8x_cond_copy
+
+.p2align	5
+L$sqr8x_cond_copy:
+	movdqa	0(%rbx),%xmm2
+	movdqa	16(%rbx),%xmm3
+	leaq	32(%rbx),%rbx
+	movdqu	0(%rdi),%xmm4
+	movdqu	16(%rdi),%xmm5
+	leaq	32(%rdi),%rdi
+	movdqa	%xmm0,-32(%rbx)
+	movdqa	%xmm0,-16(%rbx)
+	movdqa	%xmm0,-32(%rbx,%rdx,1)
+	movdqa	%xmm0,-16(%rbx,%rdx,1)
+	pcmpeqd	%xmm1,%xmm0
+	pand	%xmm1,%xmm2
+	pand	%xmm1,%xmm3
+	pand	%xmm0,%xmm4
+	pand	%xmm0,%xmm5
+	pxor	%xmm0,%xmm0
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+	movdqu	%xmm4,-32(%rdi)
+	movdqu	%xmm5,-16(%rdi)
+	addq	$32,%r9
+	jnz	L$sqr8x_cond_copy
 
 	movq	$1,%rax
 	movq	-48(%rsi),%r15
diff --git a/packager/third_party/boringssl/mac-x86_64/crypto/bn/x86_64-mont5.S b/packager/third_party/boringssl/mac-x86_64/crypto/bn/x86_64-mont5.S
index 2e8f469c14..f3ad8d783f 100644
--- a/packager/third_party/boringssl/mac-x86_64/crypto/bn/x86_64-mont5.S
+++ b/packager/third_party/boringssl/mac-x86_64/crypto/bn/x86_64-mont5.S
@@ -16,46 +16,151 @@ _bn_mul_mont_gather5:
 L$mul_enter:
 	movl	%r9d,%r9d
 	movq	%rsp,%rax
-	movl	8(%rsp),%r10d
+	movd	8(%rsp),%xmm5
+	leaq	L$inc(%rip),%r10
 	pushq	%rbx
 	pushq	%rbp
 	pushq	%r12
 	pushq	%r13
 	pushq	%r14
 	pushq	%r15
+
 	leaq	2(%r9),%r11
 	negq	%r11
-	leaq	(%rsp,%r11,8),%rsp
+	leaq	-264(%rsp,%r11,8),%rsp
 	andq	$-1024,%rsp
 
 	movq	%rax,8(%rsp,%r9,8)
 L$mul_body:
-	movq	%rdx,%r12
-	movq	%r10,%r11
-	shrq	$3,%r10
-	andq	$7,%r11
-	notq	%r10
-	leaq	L$magic_masks(%rip),%rax
-	andq	$3,%r10
-	leaq	96(%r12,%r11,8),%r12
-	movq	0(%rax,%r10,8),%xmm4
-	movq	8(%rax,%r10,8),%xmm5
-	movq	16(%rax,%r10,8),%xmm6
-	movq	24(%rax,%r10,8),%xmm7
+	leaq	128(%rdx),%r12
+	movdqa	0(%r10),%xmm0
+	movdqa	16(%r10),%xmm1
+	leaq	24-112(%rsp,%r9,8),%r10
+	andq	$-16,%r10
 
-	movq	-96(%r12),%xmm0
-	movq	-32(%r12),%xmm1
-	pand	%xmm4,%xmm0
-	movq	32(%r12),%xmm2
-	pand	%xmm5,%xmm1
-	movq	96(%r12),%xmm3
-	pand	%xmm6,%xmm2
-	por	%xmm1,%xmm0
-	pand	%xmm7,%xmm3
+	pshufd	$0,%xmm5,%xmm5
+	movdqa	%xmm1,%xmm4
+	movdqa	%xmm1,%xmm2
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0
+.byte	0x67
+	movdqa	%xmm4,%xmm3
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1
+	movdqa	%xmm0,112(%r10)
+	movdqa	%xmm4,%xmm0
+
+	paddd	%xmm2,%xmm3
+	pcmpeqd	%xmm5,%xmm2
+	movdqa	%xmm1,128(%r10)
+	movdqa	%xmm4,%xmm1
+
+	paddd	%xmm3,%xmm0
+	pcmpeqd	%xmm5,%xmm3
+	movdqa	%xmm2,144(%r10)
+	movdqa	%xmm4,%xmm2
+
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0
+	movdqa	%xmm3,160(%r10)
+	movdqa	%xmm4,%xmm3
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1
+	movdqa	%xmm0,176(%r10)
+	movdqa	%xmm4,%xmm0
+
+	paddd	%xmm2,%xmm3
+	pcmpeqd	%xmm5,%xmm2
+	movdqa	%xmm1,192(%r10)
+	movdqa	%xmm4,%xmm1
+
+	paddd	%xmm3,%xmm0
+	pcmpeqd	%xmm5,%xmm3
+	movdqa	%xmm2,208(%r10)
+	movdqa	%xmm4,%xmm2
+
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0
+	movdqa	%xmm3,224(%r10)
+	movdqa	%xmm4,%xmm3
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1
+	movdqa	%xmm0,240(%r10)
+	movdqa	%xmm4,%xmm0
+
+	paddd	%xmm2,%xmm3
+	pcmpeqd	%xmm5,%xmm2
+	movdqa	%xmm1,256(%r10)
+	movdqa	%xmm4,%xmm1
+
+	paddd	%xmm3,%xmm0
+	pcmpeqd	%xmm5,%xmm3
+	movdqa	%xmm2,272(%r10)
+	movdqa	%xmm4,%xmm2
+
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0
+	movdqa	%xmm3,288(%r10)
+	movdqa	%xmm4,%xmm3
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1
+	movdqa	%xmm0,304(%r10)
+
+	paddd	%xmm2,%xmm3
+.byte	0x67
+	pcmpeqd	%xmm5,%xmm2
+	movdqa	%xmm1,320(%r10)
+
+	pcmpeqd	%xmm5,%xmm3
+	movdqa	%xmm2,336(%r10)
+	pand	64(%r12),%xmm0
+
+	pand	80(%r12),%xmm1
+	pand	96(%r12),%xmm2
+	movdqa	%xmm3,352(%r10)
+	pand	112(%r12),%xmm3
 	por	%xmm2,%xmm0
+	por	%xmm3,%xmm1
+	movdqa	-128(%r12),%xmm4
+	movdqa	-112(%r12),%xmm5
+	movdqa	-96(%r12),%xmm2
+	pand	112(%r10),%xmm4
+	movdqa	-80(%r12),%xmm3
+	pand	128(%r10),%xmm5
+	por	%xmm4,%xmm0
+	pand	144(%r10),%xmm2
+	por	%xmm5,%xmm1
+	pand	160(%r10),%xmm3
+	por	%xmm2,%xmm0
+	por	%xmm3,%xmm1
+	movdqa	-64(%r12),%xmm4
+	movdqa	-48(%r12),%xmm5
+	movdqa	-32(%r12),%xmm2
+	pand	176(%r10),%xmm4
+	movdqa	-16(%r12),%xmm3
+	pand	192(%r10),%xmm5
+	por	%xmm4,%xmm0
+	pand	208(%r10),%xmm2
+	por	%xmm5,%xmm1
+	pand	224(%r10),%xmm3
+	por	%xmm2,%xmm0
+	por	%xmm3,%xmm1
+	movdqa	0(%r12),%xmm4
+	movdqa	16(%r12),%xmm5
+	movdqa	32(%r12),%xmm2
+	pand	240(%r10),%xmm4
+	movdqa	48(%r12),%xmm3
+	pand	256(%r10),%xmm5
+	por	%xmm4,%xmm0
+	pand	272(%r10),%xmm2
+	por	%xmm5,%xmm1
+	pand	288(%r10),%xmm3
+	por	%xmm2,%xmm0
+	por	%xmm3,%xmm1
+	por	%xmm1,%xmm0
+	pshufd	$0x4e,%xmm0,%xmm1
+	por	%xmm1,%xmm0
 	leaq	256(%r12),%r12
-	por	%xmm3,%xmm0
-
 .byte	102,72,15,126,195
 
 	movq	(%r8),%r8
@@ -64,29 +169,14 @@ L$mul_body:
 	xorq	%r14,%r14
 	xorq	%r15,%r15
 
-	movq	-96(%r12),%xmm0
-	movq	-32(%r12),%xmm1
-	pand	%xmm4,%xmm0
-	movq	32(%r12),%xmm2
-	pand	%xmm5,%xmm1
-
 	movq	%r8,%rbp
 	mulq	%rbx
 	movq	%rax,%r10
 	movq	(%rcx),%rax
 
-	movq	96(%r12),%xmm3
-	pand	%xmm6,%xmm2
-	por	%xmm1,%xmm0
-	pand	%xmm7,%xmm3
-
 	imulq	%r10,%rbp
 	movq	%rdx,%r11
 
-	por	%xmm2,%xmm0
-	leaq	256(%r12),%r12
-	por	%xmm3,%xmm0
-
 	mulq	%rbp
 	addq	%rax,%r10
 	movq	8(%rsi),%rax
@@ -119,14 +209,12 @@ L$1st_enter:
 	cmpq	%r9,%r15
 	jne	L$1st
 
-.byte	102,72,15,126,195
 
 	addq	%rax,%r13
-	movq	(%rsi),%rax
 	adcq	$0,%rdx
 	addq	%r11,%r13
 	adcq	$0,%rdx
-	movq	%r13,-16(%rsp,%r15,8)
+	movq	%r13,-16(%rsp,%r9,8)
 	movq	%rdx,%r13
 	movq	%r10,%r11
 
@@ -140,33 +228,78 @@ L$1st_enter:
 	jmp	L$outer
 .p2align	4
 L$outer:
+	leaq	24+128(%rsp,%r9,8),%rdx
+	andq	$-16,%rdx
+	pxor	%xmm4,%xmm4
+	pxor	%xmm5,%xmm5
+	movdqa	-128(%r12),%xmm0
+	movdqa	-112(%r12),%xmm1
+	movdqa	-96(%r12),%xmm2
+	movdqa	-80(%r12),%xmm3
+	pand	-128(%rdx),%xmm0
+	pand	-112(%rdx),%xmm1
+	por	%xmm0,%xmm4
+	pand	-96(%rdx),%xmm2
+	por	%xmm1,%xmm5
+	pand	-80(%rdx),%xmm3
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+	movdqa	-64(%r12),%xmm0
+	movdqa	-48(%r12),%xmm1
+	movdqa	-32(%r12),%xmm2
+	movdqa	-16(%r12),%xmm3
+	pand	-64(%rdx),%xmm0
+	pand	-48(%rdx),%xmm1
+	por	%xmm0,%xmm4
+	pand	-32(%rdx),%xmm2
+	por	%xmm1,%xmm5
+	pand	-16(%rdx),%xmm3
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+	movdqa	0(%r12),%xmm0
+	movdqa	16(%r12),%xmm1
+	movdqa	32(%r12),%xmm2
+	movdqa	48(%r12),%xmm3
+	pand	0(%rdx),%xmm0
+	pand	16(%rdx),%xmm1
+	por	%xmm0,%xmm4
+	pand	32(%rdx),%xmm2
+	por	%xmm1,%xmm5
+	pand	48(%rdx),%xmm3
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+	movdqa	64(%r12),%xmm0
+	movdqa	80(%r12),%xmm1
+	movdqa	96(%r12),%xmm2
+	movdqa	112(%r12),%xmm3
+	pand	64(%rdx),%xmm0
+	pand	80(%rdx),%xmm1
+	por	%xmm0,%xmm4
+	pand	96(%rdx),%xmm2
+	por	%xmm1,%xmm5
+	pand	112(%rdx),%xmm3
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+	por	%xmm5,%xmm4
+	pshufd	$0x4e,%xmm4,%xmm0
+	por	%xmm4,%xmm0
+	leaq	256(%r12),%r12
+
+	movq	(%rsi),%rax
+.byte	102,72,15,126,195
+
 	xorq	%r15,%r15
 	movq	%r8,%rbp
 	movq	(%rsp),%r10
 
-	movq	-96(%r12),%xmm0
-	movq	-32(%r12),%xmm1
-	pand	%xmm4,%xmm0
-	movq	32(%r12),%xmm2
-	pand	%xmm5,%xmm1
-
 	mulq	%rbx
 	addq	%rax,%r10
 	movq	(%rcx),%rax
 	adcq	$0,%rdx
 
-	movq	96(%r12),%xmm3
-	pand	%xmm6,%xmm2
-	por	%xmm1,%xmm0
-	pand	%xmm7,%xmm3
-
 	imulq	%r10,%rbp
 	movq	%rdx,%r11
 
-	por	%xmm2,%xmm0
-	leaq	256(%r12),%r12
-	por	%xmm3,%xmm0
-
 	mulq	%rbp
 	addq	%rax,%r10
 	movq	8(%rsi),%rax
@@ -202,15 +335,12 @@ L$inner_enter:
 	cmpq	%r9,%r15
 	jne	L$inner
 
-.byte	102,72,15,126,195
-
 	addq	%rax,%r13
-	movq	(%rsi),%rax
 	adcq	$0,%rdx
 	addq	%r10,%r13
-	movq	(%rsp,%r15,8),%r10
+	movq	(%rsp,%r9,8),%r10
 	adcq	$0,%rdx
-	movq	%r13,-16(%rsp,%r15,8)
+	movq	%r13,-16(%rsp,%r9,8)
 	movq	%rdx,%r13
 
 	xorq	%rdx,%rdx
@@ -256,6 +386,7 @@ L$copy:
 
 	movq	8(%rsp,%r9,8),%rsi
 	movq	$1,%rax
+
 	movq	-48(%rsi),%r15
 	movq	-40(%rsi),%r14
 	movq	-32(%rsi),%r13
@@ -278,10 +409,10 @@ L$mul4x_enter:
 	pushq	%r13
 	pushq	%r14
 	pushq	%r15
+
 .byte	0x67
-	movl	%r9d,%r10d
 	shll	$3,%r9d
-	shll	$3+2,%r10d
+	leaq	(%r9,%r9,2),%r10
 	negq	%r9
 
 
@@ -291,19 +422,21 @@ L$mul4x_enter:
 
 
 
-	leaq	-64(%rsp,%r9,2),%r11
-	subq	%rsi,%r11
+
+
+	leaq	-320(%rsp,%r9,2),%r11
+	subq	%rdi,%r11
 	andq	$4095,%r11
 	cmpq	%r11,%r10
 	jb	L$mul4xsp_alt
 	subq	%r11,%rsp
-	leaq	-64(%rsp,%r9,2),%rsp
+	leaq	-320(%rsp,%r9,2),%rsp
 	jmp	L$mul4xsp_done
 
 .p2align	5
 L$mul4xsp_alt:
-	leaq	4096-64(,%r9,2),%r10
-	leaq	-64(%rsp,%r9,2),%rsp
+	leaq	4096-320(,%r9,2),%r10
+	leaq	-320(%rsp,%r9,2),%rsp
 	subq	%r10,%r11
 	movq	$0,%r10
 	cmovcq	%r10,%r11
@@ -319,6 +452,7 @@ L$mul4x_body:
 
 	movq	40(%rsp),%rsi
 	movq	$1,%rax
+
 	movq	-48(%rsi),%r15
 	movq	-40(%rsi),%r14
 	movq	-32(%rsi),%r13
@@ -334,47 +468,141 @@ L$mul4x_epilogue:
 .p2align	5
 mul4x_internal:
 	shlq	$5,%r9
-	movl	8(%rax),%r10d
-	leaq	256(%rdx,%r9,1),%r13
+	movd	8(%rax),%xmm5
+	leaq	L$inc(%rip),%rax
+	leaq	128(%rdx,%r9,1),%r13
 	shrq	$5,%r9
-	movq	%r10,%r11
-	shrq	$3,%r10
-	andq	$7,%r11
-	notq	%r10
-	leaq	L$magic_masks(%rip),%rax
-	andq	$3,%r10
-	leaq	96(%rdx,%r11,8),%r12
-	movq	0(%rax,%r10,8),%xmm4
-	movq	8(%rax,%r10,8),%xmm5
-	addq	$7,%r11
-	movq	16(%rax,%r10,8),%xmm6
-	movq	24(%rax,%r10,8),%xmm7
-	andq	$7,%r11
+	movdqa	0(%rax),%xmm0
+	movdqa	16(%rax),%xmm1
+	leaq	88-112(%rsp,%r9,1),%r10
+	leaq	128(%rdx),%r12
 
-	movq	-96(%r12),%xmm0
-	leaq	256(%r12),%r14
-	movq	-32(%r12),%xmm1
-	pand	%xmm4,%xmm0
-	movq	32(%r12),%xmm2
-	pand	%xmm5,%xmm1
-	movq	96(%r12),%xmm3
-	pand	%xmm6,%xmm2
+	pshufd	$0,%xmm5,%xmm5
+	movdqa	%xmm1,%xmm4
+.byte	0x67,0x67
+	movdqa	%xmm1,%xmm2
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0
 .byte	0x67
-	por	%xmm1,%xmm0
-	movq	-96(%r14),%xmm1
-.byte	0x67
-	pand	%xmm7,%xmm3
+	movdqa	%xmm4,%xmm3
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1
+	movdqa	%xmm0,112(%r10)
+	movdqa	%xmm4,%xmm0
+
+	paddd	%xmm2,%xmm3
+	pcmpeqd	%xmm5,%xmm2
+	movdqa	%xmm1,128(%r10)
+	movdqa	%xmm4,%xmm1
+
+	paddd	%xmm3,%xmm0
+	pcmpeqd	%xmm5,%xmm3
+	movdqa	%xmm2,144(%r10)
+	movdqa	%xmm4,%xmm2
+
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0
+	movdqa	%xmm3,160(%r10)
+	movdqa	%xmm4,%xmm3
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1
+	movdqa	%xmm0,176(%r10)
+	movdqa	%xmm4,%xmm0
+
+	paddd	%xmm2,%xmm3
+	pcmpeqd	%xmm5,%xmm2
+	movdqa	%xmm1,192(%r10)
+	movdqa	%xmm4,%xmm1
+
+	paddd	%xmm3,%xmm0
+	pcmpeqd	%xmm5,%xmm3
+	movdqa	%xmm2,208(%r10)
+	movdqa	%xmm4,%xmm2
+
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0
+	movdqa	%xmm3,224(%r10)
+	movdqa	%xmm4,%xmm3
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1
+	movdqa	%xmm0,240(%r10)
+	movdqa	%xmm4,%xmm0
+
+	paddd	%xmm2,%xmm3
+	pcmpeqd	%xmm5,%xmm2
+	movdqa	%xmm1,256(%r10)
+	movdqa	%xmm4,%xmm1
+
+	paddd	%xmm3,%xmm0
+	pcmpeqd	%xmm5,%xmm3
+	movdqa	%xmm2,272(%r10)
+	movdqa	%xmm4,%xmm2
+
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0
+	movdqa	%xmm3,288(%r10)
+	movdqa	%xmm4,%xmm3
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1
+	movdqa	%xmm0,304(%r10)
+
+	paddd	%xmm2,%xmm3
 .byte	0x67
+	pcmpeqd	%xmm5,%xmm2
+	movdqa	%xmm1,320(%r10)
+
+	pcmpeqd	%xmm5,%xmm3
+	movdqa	%xmm2,336(%r10)
+	pand	64(%r12),%xmm0
+
+	pand	80(%r12),%xmm1
+	pand	96(%r12),%xmm2
+	movdqa	%xmm3,352(%r10)
+	pand	112(%r12),%xmm3
 	por	%xmm2,%xmm0
-	movq	-32(%r14),%xmm2
-.byte	0x67
-	pand	%xmm4,%xmm1
-.byte	0x67
-	por	%xmm3,%xmm0
-	movq	32(%r14),%xmm3
-
+	por	%xmm3,%xmm1
+	movdqa	-128(%r12),%xmm4
+	movdqa	-112(%r12),%xmm5
+	movdqa	-96(%r12),%xmm2
+	pand	112(%r10),%xmm4
+	movdqa	-80(%r12),%xmm3
+	pand	128(%r10),%xmm5
+	por	%xmm4,%xmm0
+	pand	144(%r10),%xmm2
+	por	%xmm5,%xmm1
+	pand	160(%r10),%xmm3
+	por	%xmm2,%xmm0
+	por	%xmm3,%xmm1
+	movdqa	-64(%r12),%xmm4
+	movdqa	-48(%r12),%xmm5
+	movdqa	-32(%r12),%xmm2
+	pand	176(%r10),%xmm4
+	movdqa	-16(%r12),%xmm3
+	pand	192(%r10),%xmm5
+	por	%xmm4,%xmm0
+	pand	208(%r10),%xmm2
+	por	%xmm5,%xmm1
+	pand	224(%r10),%xmm3
+	por	%xmm2,%xmm0
+	por	%xmm3,%xmm1
+	movdqa	0(%r12),%xmm4
+	movdqa	16(%r12),%xmm5
+	movdqa	32(%r12),%xmm2
+	pand	240(%r10),%xmm4
+	movdqa	48(%r12),%xmm3
+	pand	256(%r10),%xmm5
+	por	%xmm4,%xmm0
+	pand	272(%r10),%xmm2
+	por	%xmm5,%xmm1
+	pand	288(%r10),%xmm3
+	por	%xmm2,%xmm0
+	por	%xmm3,%xmm1
+	por	%xmm1,%xmm0
+	pshufd	$0x4e,%xmm0,%xmm1
+	por	%xmm1,%xmm0
+	leaq	256(%r12),%r12
 .byte	102,72,15,126,195
-	movq	96(%r14),%xmm0
+
 	movq	%r13,16+8(%rsp)
 	movq	%rdi,56+8(%rsp)
 
@@ -388,26 +616,10 @@ mul4x_internal:
 	movq	%rax,%r10
 	movq	(%rcx),%rax
 
-	pand	%xmm5,%xmm2
-	pand	%xmm6,%xmm3
-	por	%xmm2,%xmm1
-
 	imulq	%r10,%rbp
-
-
-
-
-
-
-
-	leaq	64+8(%rsp,%r11,8),%r14
+	leaq	64+8(%rsp),%r14
 	movq	%rdx,%r11
 
-	pand	%xmm7,%xmm0
-	por	%xmm3,%xmm1
-	leaq	512(%r12),%r12
-	por	%xmm1,%xmm0
-
 	mulq	%rbp
 	addq	%rax,%r10
 	movq	8(%rsi,%r9,1),%rax
@@ -416,7 +628,7 @@ mul4x_internal:
 
 	mulq	%rbx
 	addq	%rax,%r11
-	movq	16(%rcx),%rax
+	movq	8(%rcx),%rax
 	adcq	$0,%rdx
 	movq	%rdx,%r10
 
@@ -426,7 +638,7 @@ mul4x_internal:
 	adcq	$0,%rdx
 	addq	%r11,%rdi
 	leaq	32(%r9),%r15
-	leaq	64(%rcx),%rcx
+	leaq	32(%rcx),%rcx
 	adcq	$0,%rdx
 	movq	%rdi,(%r14)
 	movq	%rdx,%r13
@@ -436,7 +648,7 @@ mul4x_internal:
 L$1st4x:
 	mulq	%rbx
 	addq	%rax,%r10
-	movq	-32(%rcx),%rax
+	movq	-16(%rcx),%rax
 	leaq	32(%r14),%r14
 	adcq	$0,%rdx
 	movq	%rdx,%r11
@@ -452,7 +664,7 @@ L$1st4x:
 
 	mulq	%rbx
 	addq	%rax,%r11
-	movq	-16(%rcx),%rax
+	movq	-8(%rcx),%rax
 	adcq	$0,%rdx
 	movq	%rdx,%r10
 
@@ -482,7 +694,7 @@ L$1st4x:
 
 	mulq	%rbx
 	addq	%rax,%r11
-	movq	16(%rcx),%rax
+	movq	8(%rcx),%rax
 	adcq	$0,%rdx
 	movq	%rdx,%r10
 
@@ -491,7 +703,7 @@ L$1st4x:
 	movq	16(%rsi,%r15,1),%rax
 	adcq	$0,%rdx
 	addq	%r11,%rdi
-	leaq	64(%rcx),%rcx
+	leaq	32(%rcx),%rcx
 	adcq	$0,%rdx
 	movq	%rdi,(%r14)
 	movq	%rdx,%r13
@@ -501,7 +713,7 @@ L$1st4x:
 
 	mulq	%rbx
 	addq	%rax,%r10
-	movq	-32(%rcx),%rax
+	movq	-16(%rcx),%rax
 	leaq	32(%r14),%r14
 	adcq	$0,%rdx
 	movq	%rdx,%r11
@@ -517,7 +729,7 @@ L$1st4x:
 
 	mulq	%rbx
 	addq	%rax,%r11
-	movq	-16(%rcx),%rax
+	movq	-8(%rcx),%rax
 	adcq	$0,%rdx
 	movq	%rdx,%r10
 
@@ -530,8 +742,7 @@ L$1st4x:
 	movq	%rdi,-16(%r14)
 	movq	%rdx,%r13
 
-.byte	102,72,15,126,195
-	leaq	(%rcx,%r9,2),%rcx
+	leaq	(%rcx,%r9,1),%rcx
 
 	xorq	%rdi,%rdi
 	addq	%r10,%r13
@@ -542,6 +753,63 @@ L$1st4x:
 
 .p2align	5
 L$outer4x:
+	leaq	16+128(%r14),%rdx
+	pxor	%xmm4,%xmm4
+	pxor	%xmm5,%xmm5
+	movdqa	-128(%r12),%xmm0
+	movdqa	-112(%r12),%xmm1
+	movdqa	-96(%r12),%xmm2
+	movdqa	-80(%r12),%xmm3
+	pand	-128(%rdx),%xmm0
+	pand	-112(%rdx),%xmm1
+	por	%xmm0,%xmm4
+	pand	-96(%rdx),%xmm2
+	por	%xmm1,%xmm5
+	pand	-80(%rdx),%xmm3
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+	movdqa	-64(%r12),%xmm0
+	movdqa	-48(%r12),%xmm1
+	movdqa	-32(%r12),%xmm2
+	movdqa	-16(%r12),%xmm3
+	pand	-64(%rdx),%xmm0
+	pand	-48(%rdx),%xmm1
+	por	%xmm0,%xmm4
+	pand	-32(%rdx),%xmm2
+	por	%xmm1,%xmm5
+	pand	-16(%rdx),%xmm3
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+	movdqa	0(%r12),%xmm0
+	movdqa	16(%r12),%xmm1
+	movdqa	32(%r12),%xmm2
+	movdqa	48(%r12),%xmm3
+	pand	0(%rdx),%xmm0
+	pand	16(%rdx),%xmm1
+	por	%xmm0,%xmm4
+	pand	32(%rdx),%xmm2
+	por	%xmm1,%xmm5
+	pand	48(%rdx),%xmm3
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+	movdqa	64(%r12),%xmm0
+	movdqa	80(%r12),%xmm1
+	movdqa	96(%r12),%xmm2
+	movdqa	112(%r12),%xmm3
+	pand	64(%rdx),%xmm0
+	pand	80(%rdx),%xmm1
+	por	%xmm0,%xmm4
+	pand	96(%rdx),%xmm2
+	por	%xmm1,%xmm5
+	pand	112(%rdx),%xmm3
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+	por	%xmm5,%xmm4
+	pshufd	$0x4e,%xmm4,%xmm0
+	por	%xmm4,%xmm0
+	leaq	256(%r12),%r12
+.byte	102,72,15,126,195
+
 	movq	(%r14,%r9,1),%r10
 	movq	%r8,%rbp
 	mulq	%rbx
@@ -549,25 +817,11 @@ L$outer4x:
 	movq	(%rcx),%rax
 	adcq	$0,%rdx
 
-	movq	-96(%r12),%xmm0
-	movq	-32(%r12),%xmm1
-	pand	%xmm4,%xmm0
-	movq	32(%r12),%xmm2
-	pand	%xmm5,%xmm1
-	movq	96(%r12),%xmm3
-
 	imulq	%r10,%rbp
-.byte	0x67
 	movq	%rdx,%r11
 	movq	%rdi,(%r14)
 
-	pand	%xmm6,%xmm2
-	por	%xmm1,%xmm0
-	pand	%xmm7,%xmm3
-	por	%xmm2,%xmm0
 	leaq	(%r14,%r9,1),%r14
-	leaq	256(%r12),%r12
-	por	%xmm3,%xmm0
 
 	mulq	%rbp
 	addq	%rax,%r10
@@ -577,7 +831,7 @@ L$outer4x:
 
 	mulq	%rbx
 	addq	%rax,%r11
-	movq	16(%rcx),%rax
+	movq	8(%rcx),%rax
 	adcq	$0,%rdx
 	addq	8(%r14),%r11
 	adcq	$0,%rdx
@@ -589,7 +843,7 @@ L$outer4x:
 	adcq	$0,%rdx
 	addq	%r11,%rdi
 	leaq	32(%r9),%r15
-	leaq	64(%rcx),%rcx
+	leaq	32(%rcx),%rcx
 	adcq	$0,%rdx
 	movq	%rdx,%r13
 	jmp	L$inner4x
@@ -598,7 +852,7 @@ L$outer4x:
 L$inner4x:
 	mulq	%rbx
 	addq	%rax,%r10
-	movq	-32(%rcx),%rax
+	movq	-16(%rcx),%rax
 	adcq	$0,%rdx
 	addq	16(%r14),%r10
 	leaq	32(%r14),%r14
@@ -616,7 +870,7 @@ L$inner4x:
 
 	mulq	%rbx
 	addq	%rax,%r11
-	movq	-16(%rcx),%rax
+	movq	-8(%rcx),%rax
 	adcq	$0,%rdx
 	addq	-8(%r14),%r11
 	adcq	$0,%rdx
@@ -650,7 +904,7 @@ L$inner4x:
 
 	mulq	%rbx
 	addq	%rax,%r11
-	movq	16(%rcx),%rax
+	movq	8(%rcx),%rax
 	adcq	$0,%rdx
 	addq	8(%r14),%r11
 	adcq	$0,%rdx
@@ -661,7 +915,7 @@ L$inner4x:
 	movq	16(%rsi,%r15,1),%rax
 	adcq	$0,%rdx
 	addq	%r11,%rdi
-	leaq	64(%rcx),%rcx
+	leaq	32(%rcx),%rcx
 	adcq	$0,%rdx
 	movq	%r13,-8(%r14)
 	movq	%rdx,%r13
@@ -671,7 +925,7 @@ L$inner4x:
 
 	mulq	%rbx
 	addq	%rax,%r10
-	movq	-32(%rcx),%rax
+	movq	-16(%rcx),%rax
 	adcq	$0,%rdx
 	addq	16(%r14),%r10
 	leaq	32(%r14),%r14
@@ -690,7 +944,7 @@ L$inner4x:
 	mulq	%rbx
 	addq	%rax,%r11
 	movq	%rbp,%rax
-	movq	-16(%rcx),%rbp
+	movq	-8(%rcx),%rbp
 	adcq	$0,%rdx
 	addq	-8(%r14),%r11
 	adcq	$0,%rdx
@@ -705,9 +959,8 @@ L$inner4x:
 	movq	%r13,-24(%r14)
 	movq	%rdx,%r13
 
-.byte	102,72,15,126,195
 	movq	%rdi,-16(%r14)
-	leaq	(%rcx,%r9,2),%rcx
+	leaq	(%rcx,%r9,1),%rcx
 
 	xorq	%rdi,%rdi
 	addq	%r10,%r13
@@ -718,16 +971,23 @@ L$inner4x:
 
 	cmpq	16+8(%rsp),%r12
 	jb	L$outer4x
+	xorq	%rax,%rax
 	subq	%r13,%rbp
 	adcq	%r15,%r15
 	orq	%r15,%rdi
-	xorq	$1,%rdi
+	subq	%rdi,%rax
 	leaq	(%r14,%r9,1),%rbx
-	leaq	(%rcx,%rdi,8),%rbp
+	movq	(%rcx),%r12
+	leaq	(%rcx),%rbp
 	movq	%r9,%rcx
 	sarq	$3+2,%rcx
 	movq	56+8(%rsp),%rdi
-	jmp	L$sqr4x_sub
+	decq	%r12
+	xorq	%r10,%r10
+	movq	8(%rbp),%r13
+	movq	16(%rbp),%r14
+	movq	24(%rbp),%r15
+	jmp	L$sqr4x_sub_entry
 
 .globl	_bn_power5
 .private_extern _bn_power5
@@ -741,9 +1001,9 @@ _bn_power5:
 	pushq	%r13
 	pushq	%r14
 	pushq	%r15
-	movl	%r9d,%r10d
+
 	shll	$3,%r9d
-	shll	$3+2,%r10d
+	leal	(%r9,%r9,2),%r10d
 	negq	%r9
 	movq	(%r8),%r8
 
@@ -753,19 +1013,20 @@ _bn_power5:
 
 
 
-	leaq	-64(%rsp,%r9,2),%r11
-	subq	%rsi,%r11
+
+	leaq	-320(%rsp,%r9,2),%r11
+	subq	%rdi,%r11
 	andq	$4095,%r11
 	cmpq	%r11,%r10
 	jb	L$pwr_sp_alt
 	subq	%r11,%rsp
-	leaq	-64(%rsp,%r9,2),%rsp
+	leaq	-320(%rsp,%r9,2),%rsp
 	jmp	L$pwr_sp_done
 
 .p2align	5
 L$pwr_sp_alt:
-	leaq	4096-64(,%r9,2),%r10
-	leaq	-64(%rsp,%r9,2),%rsp
+	leaq	4096-320(,%r9,2),%r10
+	leaq	-320(%rsp,%r9,2),%rsp
 	subq	%r10,%r11
 	movq	$0,%r10
 	cmovcq	%r10,%r11
@@ -793,10 +1054,15 @@ L$power5_body:
 .byte	102,72,15,110,226
 
 	call	__bn_sqr8x_internal
+	call	__bn_post4x_internal
 	call	__bn_sqr8x_internal
+	call	__bn_post4x_internal
 	call	__bn_sqr8x_internal
+	call	__bn_post4x_internal
 	call	__bn_sqr8x_internal
+	call	__bn_post4x_internal
 	call	__bn_sqr8x_internal
+	call	__bn_post4x_internal
 
 .byte	102,72,15,126,209
 .byte	102,72,15,126,226
@@ -1341,9 +1607,9 @@ L$sqr4x_shift_n_add:
 	movq	%rbx,-16(%rdi)
 	movq	%r8,-8(%rdi)
 .byte	102,72,15,126,213
-sqr8x_reduction:
+__bn_sqr8x_reduction:
 	xorq	%rax,%rax
-	leaq	(%rbp,%r9,2),%rcx
+	leaq	(%r9,%rbp,1),%rcx
 	leaq	48+8(%rsp,%r9,2),%rdx
 	movq	%rcx,0+8(%rsp)
 	leaq	48+8(%rsp,%r9,1),%rdi
@@ -1376,14 +1642,14 @@ L$8x_reduction_loop:
 .p2align	5
 L$8x_reduce:
 	mulq	%rbx
-	movq	16(%rbp),%rax
+	movq	8(%rbp),%rax
 	negq	%r8
 	movq	%rdx,%r8
 	adcq	$0,%r8
 
 	mulq	%rbx
 	addq	%rax,%r9
-	movq	32(%rbp),%rax
+	movq	16(%rbp),%rax
 	adcq	$0,%rdx
 	addq	%r9,%r8
 	movq	%rbx,48-8+8(%rsp,%rcx,8)
@@ -1392,7 +1658,7 @@ L$8x_reduce:
 
 	mulq	%rbx
 	addq	%rax,%r10
-	movq	48(%rbp),%rax
+	movq	24(%rbp),%rax
 	adcq	$0,%rdx
 	addq	%r10,%r9
 	movq	32+8(%rsp),%rsi
@@ -1401,7 +1667,7 @@ L$8x_reduce:
 
 	mulq	%rbx
 	addq	%rax,%r11
-	movq	64(%rbp),%rax
+	movq	32(%rbp),%rax
 	adcq	$0,%rdx
 	imulq	%r8,%rsi
 	addq	%r11,%r10
@@ -1410,7 +1676,7 @@ L$8x_reduce:
 
 	mulq	%rbx
 	addq	%rax,%r12
-	movq	80(%rbp),%rax
+	movq	40(%rbp),%rax
 	adcq	$0,%rdx
 	addq	%r12,%r11
 	movq	%rdx,%r12
@@ -1418,7 +1684,7 @@ L$8x_reduce:
 
 	mulq	%rbx
 	addq	%rax,%r13
-	movq	96(%rbp),%rax
+	movq	48(%rbp),%rax
 	adcq	$0,%rdx
 	addq	%r13,%r12
 	movq	%rdx,%r13
@@ -1426,7 +1692,7 @@ L$8x_reduce:
 
 	mulq	%rbx
 	addq	%rax,%r14
-	movq	112(%rbp),%rax
+	movq	56(%rbp),%rax
 	adcq	$0,%rdx
 	addq	%r14,%r13
 	movq	%rdx,%r14
@@ -1444,7 +1710,7 @@ L$8x_reduce:
 	decl	%ecx
 	jnz	L$8x_reduce
 
-	leaq	128(%rbp),%rbp
+	leaq	64(%rbp),%rbp
 	xorq	%rax,%rax
 	movq	8+8(%rsp),%rdx
 	cmpq	0+8(%rsp),%rbp
@@ -1470,14 +1736,14 @@ L$8x_reduce:
 L$8x_tail:
 	mulq	%rbx
 	addq	%rax,%r8
-	movq	16(%rbp),%rax
+	movq	8(%rbp),%rax
 	movq	%r8,(%rdi)
 	movq	%rdx,%r8
 	adcq	$0,%r8
 
 	mulq	%rbx
 	addq	%rax,%r9
-	movq	32(%rbp),%rax
+	movq	16(%rbp),%rax
 	adcq	$0,%rdx
 	addq	%r9,%r8
 	leaq	8(%rdi),%rdi
@@ -1486,7 +1752,7 @@ L$8x_tail:
 
 	mulq	%rbx
 	addq	%rax,%r10
-	movq	48(%rbp),%rax
+	movq	24(%rbp),%rax
 	adcq	$0,%rdx
 	addq	%r10,%r9
 	movq	%rdx,%r10
@@ -1494,7 +1760,7 @@ L$8x_tail:
 
 	mulq	%rbx
 	addq	%rax,%r11
-	movq	64(%rbp),%rax
+	movq	32(%rbp),%rax
 	adcq	$0,%rdx
 	addq	%r11,%r10
 	movq	%rdx,%r11
@@ -1502,7 +1768,7 @@ L$8x_tail:
 
 	mulq	%rbx
 	addq	%rax,%r12
-	movq	80(%rbp),%rax
+	movq	40(%rbp),%rax
 	adcq	$0,%rdx
 	addq	%r12,%r11
 	movq	%rdx,%r12
@@ -1510,7 +1776,7 @@ L$8x_tail:
 
 	mulq	%rbx
 	addq	%rax,%r13
-	movq	96(%rbp),%rax
+	movq	48(%rbp),%rax
 	adcq	$0,%rdx
 	addq	%r13,%r12
 	movq	%rdx,%r13
@@ -1518,7 +1784,7 @@ L$8x_tail:
 
 	mulq	%rbx
 	addq	%rax,%r14
-	movq	112(%rbp),%rax
+	movq	56(%rbp),%rax
 	adcq	$0,%rdx
 	addq	%r14,%r13
 	movq	%rdx,%r14
@@ -1536,7 +1802,7 @@ L$8x_tail:
 	decl	%ecx
 	jnz	L$8x_tail
 
-	leaq	128(%rbp),%rbp
+	leaq	64(%rbp),%rbp
 	movq	8+8(%rsp),%rdx
 	cmpq	0+8(%rsp),%rbp
 	jae	L$8x_tail_done
@@ -1560,6 +1826,15 @@ L$8x_tail:
 .p2align	5
 L$8x_tail_done:
 	addq	(%rdx),%r8
+	adcq	$0,%r9
+	adcq	$0,%r10
+	adcq	$0,%r11
+	adcq	$0,%r12
+	adcq	$0,%r13
+	adcq	$0,%r14
+	adcq	$0,%r15
+
+
 	xorq	%rax,%rax
 
 	negq	%rsi
@@ -1573,7 +1848,7 @@ L$8x_no_tail:
 	adcq	48(%rdi),%r14
 	adcq	56(%rdi),%r15
 	adcq	$0,%rax
-	movq	-16(%rbp),%rcx
+	movq	-8(%rbp),%rcx
 	xorq	%rsi,%rsi
 
 .byte	102,72,15,126,213
@@ -1591,40 +1866,58 @@ L$8x_no_tail:
 
 	cmpq	%rdx,%rdi
 	jb	L$8x_reduction_loop
+	.byte	0xf3,0xc3
 
-	subq	%r15,%rcx
-	leaq	(%rdi,%r9,1),%rbx
-	adcq	%rsi,%rsi
-	movq	%r9,%rcx
-	orq	%rsi,%rax
-.byte	102,72,15,126,207
-	xorq	$1,%rax
-.byte	102,72,15,126,206
-	leaq	(%rbp,%rax,8),%rbp
-	sarq	$3+2,%rcx
-	jmp	L$sqr4x_sub
 
 .p2align	5
+__bn_post4x_internal:
+	movq	0(%rbp),%r12
+	leaq	(%rdi,%r9,1),%rbx
+	movq	%r9,%rcx
+.byte	102,72,15,126,207
+	negq	%rax
+.byte	102,72,15,126,206
+	sarq	$3+2,%rcx
+	decq	%r12
+	xorq	%r10,%r10
+	movq	8(%rbp),%r13
+	movq	16(%rbp),%r14
+	movq	24(%rbp),%r15
+	jmp	L$sqr4x_sub_entry
+
+.p2align	4
 L$sqr4x_sub:
-.byte	0x66
-	movq	0(%rbx),%r12
-	movq	8(%rbx),%r13
-	sbbq	0(%rbp),%r12
-	movq	16(%rbx),%r14
-	sbbq	16(%rbp),%r13
-	movq	24(%rbx),%r15
-	leaq	32(%rbx),%rbx
-	sbbq	32(%rbp),%r14
+	movq	0(%rbp),%r12
+	movq	8(%rbp),%r13
+	movq	16(%rbp),%r14
+	movq	24(%rbp),%r15
+L$sqr4x_sub_entry:
+	leaq	32(%rbp),%rbp
+	notq	%r12
+	notq	%r13
+	notq	%r14
+	notq	%r15
+	andq	%rax,%r12
+	andq	%rax,%r13
+	andq	%rax,%r14
+	andq	%rax,%r15
+
+	negq	%r10
+	adcq	0(%rbx),%r12
+	adcq	8(%rbx),%r13
+	adcq	16(%rbx),%r14
+	adcq	24(%rbx),%r15
 	movq	%r12,0(%rdi)
-	sbbq	48(%rbp),%r15
-	leaq	64(%rbp),%rbp
+	leaq	32(%rbx),%rbx
 	movq	%r13,8(%rdi)
+	sbbq	%r10,%r10
 	movq	%r14,16(%rdi)
 	movq	%r15,24(%rdi)
 	leaq	32(%rdi),%rdi
 
 	incq	%rcx
 	jnz	L$sqr4x_sub
+
 	movq	%r9,%r10
 	negq	%r9
 	.byte	0xf3,0xc3
@@ -1651,10 +1944,9 @@ bn_from_mont8x:
 	pushq	%r13
 	pushq	%r14
 	pushq	%r15
-.byte	0x67
-	movl	%r9d,%r10d
+
 	shll	$3,%r9d
-	shll	$3+2,%r10d
+	leaq	(%r9,%r9,2),%r10
 	negq	%r9
 	movq	(%r8),%r8
 
@@ -1664,19 +1956,20 @@ bn_from_mont8x:
 
 
 
-	leaq	-64(%rsp,%r9,2),%r11
-	subq	%rsi,%r11
+
+	leaq	-320(%rsp,%r9,2),%r11
+	subq	%rdi,%r11
 	andq	$4095,%r11
 	cmpq	%r11,%r10
 	jb	L$from_sp_alt
 	subq	%r11,%rsp
-	leaq	-64(%rsp,%r9,2),%rsp
+	leaq	-320(%rsp,%r9,2),%rsp
 	jmp	L$from_sp_done
 
 .p2align	5
 L$from_sp_alt:
-	leaq	4096-64(,%r9,2),%r10
-	leaq	-64(%rsp,%r9,2),%rsp
+	leaq	4096-320(,%r9,2),%r10
+	leaq	-320(%rsp,%r9,2),%rsp
 	subq	%r10,%r11
 	movq	$0,%r10
 	cmovcq	%r10,%r11
@@ -1727,7 +2020,8 @@ L$mul_by_1:
 .byte	0x67
 	movq	%rcx,%rbp
 .byte	102,73,15,110,218
-	call	sqr8x_reduction
+	call	__bn_sqr8x_reduction
+	call	__bn_post4x_internal
 
 	pxor	%xmm0,%xmm0
 	leaq	48(%rsp),%rax
@@ -1777,46 +2071,170 @@ L$scatter_epilogue:
 .globl	_bn_gather5
 .private_extern _bn_gather5
 
-.p2align	4
+.p2align	5
 _bn_gather5:
-	movl	%ecx,%r11d
-	shrl	$3,%ecx
-	andq	$7,%r11
-	notl	%ecx
-	leaq	L$magic_masks(%rip),%rax
-	andl	$3,%ecx
-	leaq	128(%rdx,%r11,8),%rdx
-	movq	0(%rax,%rcx,8),%xmm4
-	movq	8(%rax,%rcx,8),%xmm5
-	movq	16(%rax,%rcx,8),%xmm6
-	movq	24(%rax,%rcx,8),%xmm7
-	jmp	L$gather
-.p2align	4
-L$gather:
-	movq	-128(%rdx),%xmm0
-	movq	-64(%rdx),%xmm1
-	pand	%xmm4,%xmm0
-	movq	0(%rdx),%xmm2
-	pand	%xmm5,%xmm1
-	movq	64(%rdx),%xmm3
-	pand	%xmm6,%xmm2
-	por	%xmm1,%xmm0
-	pand	%xmm7,%xmm3
-.byte	0x67,0x67
-	por	%xmm2,%xmm0
-	leaq	256(%rdx),%rdx
-	por	%xmm3,%xmm0
+L$SEH_begin_bn_gather5:
 
+.byte	0x4c,0x8d,0x14,0x24
+.byte	0x48,0x81,0xec,0x08,0x01,0x00,0x00
+	leaq	L$inc(%rip),%rax
+	andq	$-16,%rsp
+
+	movd	%ecx,%xmm5
+	movdqa	0(%rax),%xmm0
+	movdqa	16(%rax),%xmm1
+	leaq	128(%rdx),%r11
+	leaq	128(%rsp),%rax
+
+	pshufd	$0,%xmm5,%xmm5
+	movdqa	%xmm1,%xmm4
+	movdqa	%xmm1,%xmm2
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0
+	movdqa	%xmm4,%xmm3
+
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1
+	movdqa	%xmm0,-128(%rax)
+	movdqa	%xmm4,%xmm0
+
+	paddd	%xmm2,%xmm3
+	pcmpeqd	%xmm5,%xmm2
+	movdqa	%xmm1,-112(%rax)
+	movdqa	%xmm4,%xmm1
+
+	paddd	%xmm3,%xmm0
+	pcmpeqd	%xmm5,%xmm3
+	movdqa	%xmm2,-96(%rax)
+	movdqa	%xmm4,%xmm2
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0
+	movdqa	%xmm3,-80(%rax)
+	movdqa	%xmm4,%xmm3
+
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1
+	movdqa	%xmm0,-64(%rax)
+	movdqa	%xmm4,%xmm0
+
+	paddd	%xmm2,%xmm3
+	pcmpeqd	%xmm5,%xmm2
+	movdqa	%xmm1,-48(%rax)
+	movdqa	%xmm4,%xmm1
+
+	paddd	%xmm3,%xmm0
+	pcmpeqd	%xmm5,%xmm3
+	movdqa	%xmm2,-32(%rax)
+	movdqa	%xmm4,%xmm2
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0
+	movdqa	%xmm3,-16(%rax)
+	movdqa	%xmm4,%xmm3
+
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1
+	movdqa	%xmm0,0(%rax)
+	movdqa	%xmm4,%xmm0
+
+	paddd	%xmm2,%xmm3
+	pcmpeqd	%xmm5,%xmm2
+	movdqa	%xmm1,16(%rax)
+	movdqa	%xmm4,%xmm1
+
+	paddd	%xmm3,%xmm0
+	pcmpeqd	%xmm5,%xmm3
+	movdqa	%xmm2,32(%rax)
+	movdqa	%xmm4,%xmm2
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0
+	movdqa	%xmm3,48(%rax)
+	movdqa	%xmm4,%xmm3
+
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1
+	movdqa	%xmm0,64(%rax)
+	movdqa	%xmm4,%xmm0
+
+	paddd	%xmm2,%xmm3
+	pcmpeqd	%xmm5,%xmm2
+	movdqa	%xmm1,80(%rax)
+	movdqa	%xmm4,%xmm1
+
+	paddd	%xmm3,%xmm0
+	pcmpeqd	%xmm5,%xmm3
+	movdqa	%xmm2,96(%rax)
+	movdqa	%xmm4,%xmm2
+	movdqa	%xmm3,112(%rax)
+	jmp	L$gather
+
+.p2align	5
+L$gather:
+	pxor	%xmm4,%xmm4
+	pxor	%xmm5,%xmm5
+	movdqa	-128(%r11),%xmm0
+	movdqa	-112(%r11),%xmm1
+	movdqa	-96(%r11),%xmm2
+	pand	-128(%rax),%xmm0
+	movdqa	-80(%r11),%xmm3
+	pand	-112(%rax),%xmm1
+	por	%xmm0,%xmm4
+	pand	-96(%rax),%xmm2
+	por	%xmm1,%xmm5
+	pand	-80(%rax),%xmm3
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+	movdqa	-64(%r11),%xmm0
+	movdqa	-48(%r11),%xmm1
+	movdqa	-32(%r11),%xmm2
+	pand	-64(%rax),%xmm0
+	movdqa	-16(%r11),%xmm3
+	pand	-48(%rax),%xmm1
+	por	%xmm0,%xmm4
+	pand	-32(%rax),%xmm2
+	por	%xmm1,%xmm5
+	pand	-16(%rax),%xmm3
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+	movdqa	0(%r11),%xmm0
+	movdqa	16(%r11),%xmm1
+	movdqa	32(%r11),%xmm2
+	pand	0(%rax),%xmm0
+	movdqa	48(%r11),%xmm3
+	pand	16(%rax),%xmm1
+	por	%xmm0,%xmm4
+	pand	32(%rax),%xmm2
+	por	%xmm1,%xmm5
+	pand	48(%rax),%xmm3
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+	movdqa	64(%r11),%xmm0
+	movdqa	80(%r11),%xmm1
+	movdqa	96(%r11),%xmm2
+	pand	64(%rax),%xmm0
+	movdqa	112(%r11),%xmm3
+	pand	80(%rax),%xmm1
+	por	%xmm0,%xmm4
+	pand	96(%rax),%xmm2
+	por	%xmm1,%xmm5
+	pand	112(%rax),%xmm3
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+	por	%xmm5,%xmm4
+	leaq	256(%r11),%r11
+	pshufd	$0x4e,%xmm4,%xmm0
+	por	%xmm4,%xmm0
 	movq	%xmm0,(%rdi)
 	leaq	8(%rdi),%rdi
 	subl	$1,%esi
 	jnz	L$gather
+
+	leaq	(%r10),%rsp
 	.byte	0xf3,0xc3
 L$SEH_end_bn_gather5:
 
 .p2align	6
-L$magic_masks:
-.long	0,0, 0,0, 0,0, -1,-1
-.long	0,0, 0,0, 0,0,  0,0
+L$inc:
+.long	0,0, 1,1
+.long	2,2, 2,2
 .byte	77,111,110,116,103,111,109,101,114,121,32,77,117,108,116,105,112,108,105,99,97,116,105,111,110,32,119,105,116,104,32,115,99,97,116,116,101,114,47,103,97,116,104,101,114,32,102,111,114,32,120,56,54,95,54,52,44,32,67,82,89,80,84,79,71,65,77,83,32,98,121,32,60,97,112,112,114,111,64,111,112,101,110,115,115,108,46,111,114,103,62,0
 #endif
diff --git a/packager/third_party/boringssl/mac-x86_64/crypto/chacha/chacha-x86_64.S b/packager/third_party/boringssl/mac-x86_64/crypto/chacha/chacha-x86_64.S
new file mode 100644
index 0000000000..c3554c8d13
--- /dev/null
+++ b/packager/third_party/boringssl/mac-x86_64/crypto/chacha/chacha-x86_64.S
@@ -0,0 +1,1584 @@
+#if defined(__x86_64__)
+.text	
+
+
+
+.p2align	6
+L$zero:
+.long	0,0,0,0
+L$one:
+.long	1,0,0,0
+L$inc:
+.long	0,1,2,3
+L$four:
+.long	4,4,4,4
+L$incy:
+.long	0,2,4,6,1,3,5,7
+L$eight:
+.long	8,8,8,8,8,8,8,8
+L$rot16:
+.byte	0x2,0x3,0x0,0x1, 0x6,0x7,0x4,0x5, 0xa,0xb,0x8,0x9, 0xe,0xf,0xc,0xd
+L$rot24:
+.byte	0x3,0x0,0x1,0x2, 0x7,0x4,0x5,0x6, 0xb,0x8,0x9,0xa, 0xf,0xc,0xd,0xe
+L$sigma:
+.byte	101,120,112,97,110,100,32,51,50,45,98,121,116,101,32,107,0
+.byte	67,104,97,67,104,97,50,48,32,102,111,114,32,120,56,54,95,54,52,44,32,67,82,89,80,84,79,71,65,77,83,32,98,121,32,60,97,112,112,114,111,64,111,112,101,110,115,115,108,46,111,114,103,62,0
+.globl	_ChaCha20_ctr32
+.private_extern _ChaCha20_ctr32
+
+.p2align	6
+_ChaCha20_ctr32:
+	cmpq	$0,%rdx
+	je	L$no_data
+	movq	_OPENSSL_ia32cap_P+4(%rip),%r10
+	testl	$512,%r10d
+	jnz	L$ChaCha20_ssse3
+
+	pushq	%rbx
+	pushq	%rbp
+	pushq	%r12
+	pushq	%r13
+	pushq	%r14
+	pushq	%r15
+	subq	$64+24,%rsp
+
+
+	movdqu	(%rcx),%xmm1
+	movdqu	16(%rcx),%xmm2
+	movdqu	(%r8),%xmm3
+	movdqa	L$one(%rip),%xmm4
+
+
+	movdqa	%xmm1,16(%rsp)
+	movdqa	%xmm2,32(%rsp)
+	movdqa	%xmm3,48(%rsp)
+	movq	%rdx,%rbp
+	jmp	L$oop_outer
+
+.p2align	5
+L$oop_outer:
+	movl	$0x61707865,%eax
+	movl	$0x3320646e,%ebx
+	movl	$0x79622d32,%ecx
+	movl	$0x6b206574,%edx
+	movl	16(%rsp),%r8d
+	movl	20(%rsp),%r9d
+	movl	24(%rsp),%r10d
+	movl	28(%rsp),%r11d
+	movd	%xmm3,%r12d
+	movl	52(%rsp),%r13d
+	movl	56(%rsp),%r14d
+	movl	60(%rsp),%r15d
+
+	movq	%rbp,64+0(%rsp)
+	movl	$10,%ebp
+	movq	%rsi,64+8(%rsp)
+.byte	102,72,15,126,214
+	movq	%rdi,64+16(%rsp)
+	movq	%rsi,%rdi
+	shrq	$32,%rdi
+	jmp	L$oop
+
+.p2align	5
+L$oop:
+	addl	%r8d,%eax
+	xorl	%eax,%r12d
+	roll	$16,%r12d
+	addl	%r9d,%ebx
+	xorl	%ebx,%r13d
+	roll	$16,%r13d
+	addl	%r12d,%esi
+	xorl	%esi,%r8d
+	roll	$12,%r8d
+	addl	%r13d,%edi
+	xorl	%edi,%r9d
+	roll	$12,%r9d
+	addl	%r8d,%eax
+	xorl	%eax,%r12d
+	roll	$8,%r12d
+	addl	%r9d,%ebx
+	xorl	%ebx,%r13d
+	roll	$8,%r13d
+	addl	%r12d,%esi
+	xorl	%esi,%r8d
+	roll	$7,%r8d
+	addl	%r13d,%edi
+	xorl	%edi,%r9d
+	roll	$7,%r9d
+	movl	%esi,32(%rsp)
+	movl	%edi,36(%rsp)
+	movl	40(%rsp),%esi
+	movl	44(%rsp),%edi
+	addl	%r10d,%ecx
+	xorl	%ecx,%r14d
+	roll	$16,%r14d
+	addl	%r11d,%edx
+	xorl	%edx,%r15d
+	roll	$16,%r15d
+	addl	%r14d,%esi
+	xorl	%esi,%r10d
+	roll	$12,%r10d
+	addl	%r15d,%edi
+	xorl	%edi,%r11d
+	roll	$12,%r11d
+	addl	%r10d,%ecx
+	xorl	%ecx,%r14d
+	roll	$8,%r14d
+	addl	%r11d,%edx
+	xorl	%edx,%r15d
+	roll	$8,%r15d
+	addl	%r14d,%esi
+	xorl	%esi,%r10d
+	roll	$7,%r10d
+	addl	%r15d,%edi
+	xorl	%edi,%r11d
+	roll	$7,%r11d
+	addl	%r9d,%eax
+	xorl	%eax,%r15d
+	roll	$16,%r15d
+	addl	%r10d,%ebx
+	xorl	%ebx,%r12d
+	roll	$16,%r12d
+	addl	%r15d,%esi
+	xorl	%esi,%r9d
+	roll	$12,%r9d
+	addl	%r12d,%edi
+	xorl	%edi,%r10d
+	roll	$12,%r10d
+	addl	%r9d,%eax
+	xorl	%eax,%r15d
+	roll	$8,%r15d
+	addl	%r10d,%ebx
+	xorl	%ebx,%r12d
+	roll	$8,%r12d
+	addl	%r15d,%esi
+	xorl	%esi,%r9d
+	roll	$7,%r9d
+	addl	%r12d,%edi
+	xorl	%edi,%r10d
+	roll	$7,%r10d
+	movl	%esi,40(%rsp)
+	movl	%edi,44(%rsp)
+	movl	32(%rsp),%esi
+	movl	36(%rsp),%edi
+	addl	%r11d,%ecx
+	xorl	%ecx,%r13d
+	roll	$16,%r13d
+	addl	%r8d,%edx
+	xorl	%edx,%r14d
+	roll	$16,%r14d
+	addl	%r13d,%esi
+	xorl	%esi,%r11d
+	roll	$12,%r11d
+	addl	%r14d,%edi
+	xorl	%edi,%r8d
+	roll	$12,%r8d
+	addl	%r11d,%ecx
+	xorl	%ecx,%r13d
+	roll	$8,%r13d
+	addl	%r8d,%edx
+	xorl	%edx,%r14d
+	roll	$8,%r14d
+	addl	%r13d,%esi
+	xorl	%esi,%r11d
+	roll	$7,%r11d
+	addl	%r14d,%edi
+	xorl	%edi,%r8d
+	roll	$7,%r8d
+	decl	%ebp
+	jnz	L$oop
+	movl	%edi,36(%rsp)
+	movl	%esi,32(%rsp)
+	movq	64(%rsp),%rbp
+	movdqa	%xmm2,%xmm1
+	movq	64+8(%rsp),%rsi
+	paddd	%xmm4,%xmm3
+	movq	64+16(%rsp),%rdi
+
+	addl	$0x61707865,%eax
+	addl	$0x3320646e,%ebx
+	addl	$0x79622d32,%ecx
+	addl	$0x6b206574,%edx
+	addl	16(%rsp),%r8d
+	addl	20(%rsp),%r9d
+	addl	24(%rsp),%r10d
+	addl	28(%rsp),%r11d
+	addl	48(%rsp),%r12d
+	addl	52(%rsp),%r13d
+	addl	56(%rsp),%r14d
+	addl	60(%rsp),%r15d
+	paddd	32(%rsp),%xmm1
+
+	cmpq	$64,%rbp
+	jb	L$tail
+
+	xorl	0(%rsi),%eax
+	xorl	4(%rsi),%ebx
+	xorl	8(%rsi),%ecx
+	xorl	12(%rsi),%edx
+	xorl	16(%rsi),%r8d
+	xorl	20(%rsi),%r9d
+	xorl	24(%rsi),%r10d
+	xorl	28(%rsi),%r11d
+	movdqu	32(%rsi),%xmm0
+	xorl	48(%rsi),%r12d
+	xorl	52(%rsi),%r13d
+	xorl	56(%rsi),%r14d
+	xorl	60(%rsi),%r15d
+	leaq	64(%rsi),%rsi
+	pxor	%xmm1,%xmm0
+
+	movdqa	%xmm2,32(%rsp)
+	movd	%xmm3,48(%rsp)
+
+	movl	%eax,0(%rdi)
+	movl	%ebx,4(%rdi)
+	movl	%ecx,8(%rdi)
+	movl	%edx,12(%rdi)
+	movl	%r8d,16(%rdi)
+	movl	%r9d,20(%rdi)
+	movl	%r10d,24(%rdi)
+	movl	%r11d,28(%rdi)
+	movdqu	%xmm0,32(%rdi)
+	movl	%r12d,48(%rdi)
+	movl	%r13d,52(%rdi)
+	movl	%r14d,56(%rdi)
+	movl	%r15d,60(%rdi)
+	leaq	64(%rdi),%rdi
+
+	subq	$64,%rbp
+	jnz	L$oop_outer
+
+	jmp	L$done
+
+.p2align	4
+L$tail:
+	movl	%eax,0(%rsp)
+	movl	%ebx,4(%rsp)
+	xorq	%rbx,%rbx
+	movl	%ecx,8(%rsp)
+	movl	%edx,12(%rsp)
+	movl	%r8d,16(%rsp)
+	movl	%r9d,20(%rsp)
+	movl	%r10d,24(%rsp)
+	movl	%r11d,28(%rsp)
+	movdqa	%xmm1,32(%rsp)
+	movl	%r12d,48(%rsp)
+	movl	%r13d,52(%rsp)
+	movl	%r14d,56(%rsp)
+	movl	%r15d,60(%rsp)
+
+L$oop_tail:
+	movzbl	(%rsi,%rbx,1),%eax
+	movzbl	(%rsp,%rbx,1),%edx
+	leaq	1(%rbx),%rbx
+	xorl	%edx,%eax
+	movb	%al,-1(%rdi,%rbx,1)
+	decq	%rbp
+	jnz	L$oop_tail
+
+L$done:
+	addq	$64+24,%rsp
+	popq	%r15
+	popq	%r14
+	popq	%r13
+	popq	%r12
+	popq	%rbp
+	popq	%rbx
+L$no_data:
+	.byte	0xf3,0xc3
+
+
+.p2align	5
+ChaCha20_ssse3:
+L$ChaCha20_ssse3:
+	cmpq	$128,%rdx
+	ja	L$ChaCha20_4x
+
+L$do_sse3_after_all:
+	pushq	%rbx
+	pushq	%rbp
+	pushq	%r12
+	pushq	%r13
+	pushq	%r14
+	pushq	%r15
+
+	subq	$64+24,%rsp
+	movdqa	L$sigma(%rip),%xmm0
+	movdqu	(%rcx),%xmm1
+	movdqu	16(%rcx),%xmm2
+	movdqu	(%r8),%xmm3
+	movdqa	L$rot16(%rip),%xmm6
+	movdqa	L$rot24(%rip),%xmm7
+
+	movdqa	%xmm0,0(%rsp)
+	movdqa	%xmm1,16(%rsp)
+	movdqa	%xmm2,32(%rsp)
+	movdqa	%xmm3,48(%rsp)
+	movl	$10,%ebp
+	jmp	L$oop_ssse3
+
+.p2align	5
+L$oop_outer_ssse3:
+	movdqa	L$one(%rip),%xmm3
+	movdqa	0(%rsp),%xmm0
+	movdqa	16(%rsp),%xmm1
+	movdqa	32(%rsp),%xmm2
+	paddd	48(%rsp),%xmm3
+	movl	$10,%ebp
+	movdqa	%xmm3,48(%rsp)
+	jmp	L$oop_ssse3
+
+.p2align	5
+L$oop_ssse3:
+	paddd	%xmm1,%xmm0
+	pxor	%xmm0,%xmm3
+.byte	102,15,56,0,222
+	paddd	%xmm3,%xmm2
+	pxor	%xmm2,%xmm1
+	movdqa	%xmm1,%xmm4
+	psrld	$20,%xmm1
+	pslld	$12,%xmm4
+	por	%xmm4,%xmm1
+	paddd	%xmm1,%xmm0
+	pxor	%xmm0,%xmm3
+.byte	102,15,56,0,223
+	paddd	%xmm3,%xmm2
+	pxor	%xmm2,%xmm1
+	movdqa	%xmm1,%xmm4
+	psrld	$25,%xmm1
+	pslld	$7,%xmm4
+	por	%xmm4,%xmm1
+	pshufd	$78,%xmm2,%xmm2
+	pshufd	$57,%xmm1,%xmm1
+	pshufd	$147,%xmm3,%xmm3
+	nop
+	paddd	%xmm1,%xmm0
+	pxor	%xmm0,%xmm3
+.byte	102,15,56,0,222
+	paddd	%xmm3,%xmm2
+	pxor	%xmm2,%xmm1
+	movdqa	%xmm1,%xmm4
+	psrld	$20,%xmm1
+	pslld	$12,%xmm4
+	por	%xmm4,%xmm1
+	paddd	%xmm1,%xmm0
+	pxor	%xmm0,%xmm3
+.byte	102,15,56,0,223
+	paddd	%xmm3,%xmm2
+	pxor	%xmm2,%xmm1
+	movdqa	%xmm1,%xmm4
+	psrld	$25,%xmm1
+	pslld	$7,%xmm4
+	por	%xmm4,%xmm1
+	pshufd	$78,%xmm2,%xmm2
+	pshufd	$147,%xmm1,%xmm1
+	pshufd	$57,%xmm3,%xmm3
+	decl	%ebp
+	jnz	L$oop_ssse3
+	paddd	0(%rsp),%xmm0
+	paddd	16(%rsp),%xmm1
+	paddd	32(%rsp),%xmm2
+	paddd	48(%rsp),%xmm3
+
+	cmpq	$64,%rdx
+	jb	L$tail_ssse3
+
+	movdqu	0(%rsi),%xmm4
+	movdqu	16(%rsi),%xmm5
+	pxor	%xmm4,%xmm0
+	movdqu	32(%rsi),%xmm4
+	pxor	%xmm5,%xmm1
+	movdqu	48(%rsi),%xmm5
+	leaq	64(%rsi),%rsi
+	pxor	%xmm4,%xmm2
+	pxor	%xmm5,%xmm3
+
+	movdqu	%xmm0,0(%rdi)
+	movdqu	%xmm1,16(%rdi)
+	movdqu	%xmm2,32(%rdi)
+	movdqu	%xmm3,48(%rdi)
+	leaq	64(%rdi),%rdi
+
+	subq	$64,%rdx
+	jnz	L$oop_outer_ssse3
+
+	jmp	L$done_ssse3
+
+.p2align	4
+L$tail_ssse3:
+	movdqa	%xmm0,0(%rsp)
+	movdqa	%xmm1,16(%rsp)
+	movdqa	%xmm2,32(%rsp)
+	movdqa	%xmm3,48(%rsp)
+	xorq	%rbx,%rbx
+
+L$oop_tail_ssse3:
+	movzbl	(%rsi,%rbx,1),%eax
+	movzbl	(%rsp,%rbx,1),%ecx
+	leaq	1(%rbx),%rbx
+	xorl	%ecx,%eax
+	movb	%al,-1(%rdi,%rbx,1)
+	decq	%rdx
+	jnz	L$oop_tail_ssse3
+
+L$done_ssse3:
+	addq	$64+24,%rsp
+	popq	%r15
+	popq	%r14
+	popq	%r13
+	popq	%r12
+	popq	%rbp
+	popq	%rbx
+	.byte	0xf3,0xc3
+
+
+.p2align	5
+ChaCha20_4x:
+L$ChaCha20_4x:
+	movq	%r10,%r11
+	shrq	$32,%r10
+	testq	$32,%r10
+	jnz	L$ChaCha20_8x
+	cmpq	$192,%rdx
+	ja	L$proceed4x
+
+	andq	$71303168,%r11
+	cmpq	$4194304,%r11
+	je	L$do_sse3_after_all
+
+L$proceed4x:
+	leaq	-120(%rsp),%r11
+	subq	$0x148+0,%rsp
+	movdqa	L$sigma(%rip),%xmm11
+	movdqu	(%rcx),%xmm15
+	movdqu	16(%rcx),%xmm7
+	movdqu	(%r8),%xmm3
+	leaq	256(%rsp),%rcx
+	leaq	L$rot16(%rip),%r10
+	leaq	L$rot24(%rip),%r11
+
+	pshufd	$0x00,%xmm11,%xmm8
+	pshufd	$0x55,%xmm11,%xmm9
+	movdqa	%xmm8,64(%rsp)
+	pshufd	$0xaa,%xmm11,%xmm10
+	movdqa	%xmm9,80(%rsp)
+	pshufd	$0xff,%xmm11,%xmm11
+	movdqa	%xmm10,96(%rsp)
+	movdqa	%xmm11,112(%rsp)
+
+	pshufd	$0x00,%xmm15,%xmm12
+	pshufd	$0x55,%xmm15,%xmm13
+	movdqa	%xmm12,128-256(%rcx)
+	pshufd	$0xaa,%xmm15,%xmm14
+	movdqa	%xmm13,144-256(%rcx)
+	pshufd	$0xff,%xmm15,%xmm15
+	movdqa	%xmm14,160-256(%rcx)
+	movdqa	%xmm15,176-256(%rcx)
+
+	pshufd	$0x00,%xmm7,%xmm4
+	pshufd	$0x55,%xmm7,%xmm5
+	movdqa	%xmm4,192-256(%rcx)
+	pshufd	$0xaa,%xmm7,%xmm6
+	movdqa	%xmm5,208-256(%rcx)
+	pshufd	$0xff,%xmm7,%xmm7
+	movdqa	%xmm6,224-256(%rcx)
+	movdqa	%xmm7,240-256(%rcx)
+
+	pshufd	$0x00,%xmm3,%xmm0
+	pshufd	$0x55,%xmm3,%xmm1
+	paddd	L$inc(%rip),%xmm0
+	pshufd	$0xaa,%xmm3,%xmm2
+	movdqa	%xmm1,272-256(%rcx)
+	pshufd	$0xff,%xmm3,%xmm3
+	movdqa	%xmm2,288-256(%rcx)
+	movdqa	%xmm3,304-256(%rcx)
+
+	jmp	L$oop_enter4x
+
+.p2align	5
+L$oop_outer4x:
+	movdqa	64(%rsp),%xmm8
+	movdqa	80(%rsp),%xmm9
+	movdqa	96(%rsp),%xmm10
+	movdqa	112(%rsp),%xmm11
+	movdqa	128-256(%rcx),%xmm12
+	movdqa	144-256(%rcx),%xmm13
+	movdqa	160-256(%rcx),%xmm14
+	movdqa	176-256(%rcx),%xmm15
+	movdqa	192-256(%rcx),%xmm4
+	movdqa	208-256(%rcx),%xmm5
+	movdqa	224-256(%rcx),%xmm6
+	movdqa	240-256(%rcx),%xmm7
+	movdqa	256-256(%rcx),%xmm0
+	movdqa	272-256(%rcx),%xmm1
+	movdqa	288-256(%rcx),%xmm2
+	movdqa	304-256(%rcx),%xmm3
+	paddd	L$four(%rip),%xmm0
+
+L$oop_enter4x:
+	movdqa	%xmm6,32(%rsp)
+	movdqa	%xmm7,48(%rsp)
+	movdqa	(%r10),%xmm7
+	movl	$10,%eax
+	movdqa	%xmm0,256-256(%rcx)
+	jmp	L$oop4x
+
+.p2align	5
+L$oop4x:
+	paddd	%xmm12,%xmm8
+	paddd	%xmm13,%xmm9
+	pxor	%xmm8,%xmm0
+	pxor	%xmm9,%xmm1
+.byte	102,15,56,0,199
+.byte	102,15,56,0,207
+	paddd	%xmm0,%xmm4
+	paddd	%xmm1,%xmm5
+	pxor	%xmm4,%xmm12
+	pxor	%xmm5,%xmm13
+	movdqa	%xmm12,%xmm6
+	pslld	$12,%xmm12
+	psrld	$20,%xmm6
+	movdqa	%xmm13,%xmm7
+	pslld	$12,%xmm13
+	por	%xmm6,%xmm12
+	psrld	$20,%xmm7
+	movdqa	(%r11),%xmm6
+	por	%xmm7,%xmm13
+	paddd	%xmm12,%xmm8
+	paddd	%xmm13,%xmm9
+	pxor	%xmm8,%xmm0
+	pxor	%xmm9,%xmm1
+.byte	102,15,56,0,198
+.byte	102,15,56,0,206
+	paddd	%xmm0,%xmm4
+	paddd	%xmm1,%xmm5
+	pxor	%xmm4,%xmm12
+	pxor	%xmm5,%xmm13
+	movdqa	%xmm12,%xmm7
+	pslld	$7,%xmm12
+	psrld	$25,%xmm7
+	movdqa	%xmm13,%xmm6
+	pslld	$7,%xmm13
+	por	%xmm7,%xmm12
+	psrld	$25,%xmm6
+	movdqa	(%r10),%xmm7
+	por	%xmm6,%xmm13
+	movdqa	%xmm4,0(%rsp)
+	movdqa	%xmm5,16(%rsp)
+	movdqa	32(%rsp),%xmm4
+	movdqa	48(%rsp),%xmm5
+	paddd	%xmm14,%xmm10
+	paddd	%xmm15,%xmm11
+	pxor	%xmm10,%xmm2
+	pxor	%xmm11,%xmm3
+.byte	102,15,56,0,215
+.byte	102,15,56,0,223
+	paddd	%xmm2,%xmm4
+	paddd	%xmm3,%xmm5
+	pxor	%xmm4,%xmm14
+	pxor	%xmm5,%xmm15
+	movdqa	%xmm14,%xmm6
+	pslld	$12,%xmm14
+	psrld	$20,%xmm6
+	movdqa	%xmm15,%xmm7
+	pslld	$12,%xmm15
+	por	%xmm6,%xmm14
+	psrld	$20,%xmm7
+	movdqa	(%r11),%xmm6
+	por	%xmm7,%xmm15
+	paddd	%xmm14,%xmm10
+	paddd	%xmm15,%xmm11
+	pxor	%xmm10,%xmm2
+	pxor	%xmm11,%xmm3
+.byte	102,15,56,0,214
+.byte	102,15,56,0,222
+	paddd	%xmm2,%xmm4
+	paddd	%xmm3,%xmm5
+	pxor	%xmm4,%xmm14
+	pxor	%xmm5,%xmm15
+	movdqa	%xmm14,%xmm7
+	pslld	$7,%xmm14
+	psrld	$25,%xmm7
+	movdqa	%xmm15,%xmm6
+	pslld	$7,%xmm15
+	por	%xmm7,%xmm14
+	psrld	$25,%xmm6
+	movdqa	(%r10),%xmm7
+	por	%xmm6,%xmm15
+	paddd	%xmm13,%xmm8
+	paddd	%xmm14,%xmm9
+	pxor	%xmm8,%xmm3
+	pxor	%xmm9,%xmm0
+.byte	102,15,56,0,223
+.byte	102,15,56,0,199
+	paddd	%xmm3,%xmm4
+	paddd	%xmm0,%xmm5
+	pxor	%xmm4,%xmm13
+	pxor	%xmm5,%xmm14
+	movdqa	%xmm13,%xmm6
+	pslld	$12,%xmm13
+	psrld	$20,%xmm6
+	movdqa	%xmm14,%xmm7
+	pslld	$12,%xmm14
+	por	%xmm6,%xmm13
+	psrld	$20,%xmm7
+	movdqa	(%r11),%xmm6
+	por	%xmm7,%xmm14
+	paddd	%xmm13,%xmm8
+	paddd	%xmm14,%xmm9
+	pxor	%xmm8,%xmm3
+	pxor	%xmm9,%xmm0
+.byte	102,15,56,0,222
+.byte	102,15,56,0,198
+	paddd	%xmm3,%xmm4
+	paddd	%xmm0,%xmm5
+	pxor	%xmm4,%xmm13
+	pxor	%xmm5,%xmm14
+	movdqa	%xmm13,%xmm7
+	pslld	$7,%xmm13
+	psrld	$25,%xmm7
+	movdqa	%xmm14,%xmm6
+	pslld	$7,%xmm14
+	por	%xmm7,%xmm13
+	psrld	$25,%xmm6
+	movdqa	(%r10),%xmm7
+	por	%xmm6,%xmm14
+	movdqa	%xmm4,32(%rsp)
+	movdqa	%xmm5,48(%rsp)
+	movdqa	0(%rsp),%xmm4
+	movdqa	16(%rsp),%xmm5
+	paddd	%xmm15,%xmm10
+	paddd	%xmm12,%xmm11
+	pxor	%xmm10,%xmm1
+	pxor	%xmm11,%xmm2
+.byte	102,15,56,0,207
+.byte	102,15,56,0,215
+	paddd	%xmm1,%xmm4
+	paddd	%xmm2,%xmm5
+	pxor	%xmm4,%xmm15
+	pxor	%xmm5,%xmm12
+	movdqa	%xmm15,%xmm6
+	pslld	$12,%xmm15
+	psrld	$20,%xmm6
+	movdqa	%xmm12,%xmm7
+	pslld	$12,%xmm12
+	por	%xmm6,%xmm15
+	psrld	$20,%xmm7
+	movdqa	(%r11),%xmm6
+	por	%xmm7,%xmm12
+	paddd	%xmm15,%xmm10
+	paddd	%xmm12,%xmm11
+	pxor	%xmm10,%xmm1
+	pxor	%xmm11,%xmm2
+.byte	102,15,56,0,206
+.byte	102,15,56,0,214
+	paddd	%xmm1,%xmm4
+	paddd	%xmm2,%xmm5
+	pxor	%xmm4,%xmm15
+	pxor	%xmm5,%xmm12
+	movdqa	%xmm15,%xmm7
+	pslld	$7,%xmm15
+	psrld	$25,%xmm7
+	movdqa	%xmm12,%xmm6
+	pslld	$7,%xmm12
+	por	%xmm7,%xmm15
+	psrld	$25,%xmm6
+	movdqa	(%r10),%xmm7
+	por	%xmm6,%xmm12
+	decl	%eax
+	jnz	L$oop4x
+
+	paddd	64(%rsp),%xmm8
+	paddd	80(%rsp),%xmm9
+	paddd	96(%rsp),%xmm10
+	paddd	112(%rsp),%xmm11
+
+	movdqa	%xmm8,%xmm6
+	punpckldq	%xmm9,%xmm8
+	movdqa	%xmm10,%xmm7
+	punpckldq	%xmm11,%xmm10
+	punpckhdq	%xmm9,%xmm6
+	punpckhdq	%xmm11,%xmm7
+	movdqa	%xmm8,%xmm9
+	punpcklqdq	%xmm10,%xmm8
+	movdqa	%xmm6,%xmm11
+	punpcklqdq	%xmm7,%xmm6
+	punpckhqdq	%xmm10,%xmm9
+	punpckhqdq	%xmm7,%xmm11
+	paddd	128-256(%rcx),%xmm12
+	paddd	144-256(%rcx),%xmm13
+	paddd	160-256(%rcx),%xmm14
+	paddd	176-256(%rcx),%xmm15
+
+	movdqa	%xmm8,0(%rsp)
+	movdqa	%xmm9,16(%rsp)
+	movdqa	32(%rsp),%xmm8
+	movdqa	48(%rsp),%xmm9
+
+	movdqa	%xmm12,%xmm10
+	punpckldq	%xmm13,%xmm12
+	movdqa	%xmm14,%xmm7
+	punpckldq	%xmm15,%xmm14
+	punpckhdq	%xmm13,%xmm10
+	punpckhdq	%xmm15,%xmm7
+	movdqa	%xmm12,%xmm13
+	punpcklqdq	%xmm14,%xmm12
+	movdqa	%xmm10,%xmm15
+	punpcklqdq	%xmm7,%xmm10
+	punpckhqdq	%xmm14,%xmm13
+	punpckhqdq	%xmm7,%xmm15
+	paddd	192-256(%rcx),%xmm4
+	paddd	208-256(%rcx),%xmm5
+	paddd	224-256(%rcx),%xmm8
+	paddd	240-256(%rcx),%xmm9
+
+	movdqa	%xmm6,32(%rsp)
+	movdqa	%xmm11,48(%rsp)
+
+	movdqa	%xmm4,%xmm14
+	punpckldq	%xmm5,%xmm4
+	movdqa	%xmm8,%xmm7
+	punpckldq	%xmm9,%xmm8
+	punpckhdq	%xmm5,%xmm14
+	punpckhdq	%xmm9,%xmm7
+	movdqa	%xmm4,%xmm5
+	punpcklqdq	%xmm8,%xmm4
+	movdqa	%xmm14,%xmm9
+	punpcklqdq	%xmm7,%xmm14
+	punpckhqdq	%xmm8,%xmm5
+	punpckhqdq	%xmm7,%xmm9
+	paddd	256-256(%rcx),%xmm0
+	paddd	272-256(%rcx),%xmm1
+	paddd	288-256(%rcx),%xmm2
+	paddd	304-256(%rcx),%xmm3
+
+	movdqa	%xmm0,%xmm8
+	punpckldq	%xmm1,%xmm0
+	movdqa	%xmm2,%xmm7
+	punpckldq	%xmm3,%xmm2
+	punpckhdq	%xmm1,%xmm8
+	punpckhdq	%xmm3,%xmm7
+	movdqa	%xmm0,%xmm1
+	punpcklqdq	%xmm2,%xmm0
+	movdqa	%xmm8,%xmm3
+	punpcklqdq	%xmm7,%xmm8
+	punpckhqdq	%xmm2,%xmm1
+	punpckhqdq	%xmm7,%xmm3
+	cmpq	$256,%rdx
+	jb	L$tail4x
+
+	movdqu	0(%rsi),%xmm6
+	movdqu	16(%rsi),%xmm11
+	movdqu	32(%rsi),%xmm2
+	movdqu	48(%rsi),%xmm7
+	pxor	0(%rsp),%xmm6
+	pxor	%xmm12,%xmm11
+	pxor	%xmm4,%xmm2
+	pxor	%xmm0,%xmm7
+
+	movdqu	%xmm6,0(%rdi)
+	movdqu	64(%rsi),%xmm6
+	movdqu	%xmm11,16(%rdi)
+	movdqu	80(%rsi),%xmm11
+	movdqu	%xmm2,32(%rdi)
+	movdqu	96(%rsi),%xmm2
+	movdqu	%xmm7,48(%rdi)
+	movdqu	112(%rsi),%xmm7
+	leaq	128(%rsi),%rsi
+	pxor	16(%rsp),%xmm6
+	pxor	%xmm13,%xmm11
+	pxor	%xmm5,%xmm2
+	pxor	%xmm1,%xmm7
+
+	movdqu	%xmm6,64(%rdi)
+	movdqu	0(%rsi),%xmm6
+	movdqu	%xmm11,80(%rdi)
+	movdqu	16(%rsi),%xmm11
+	movdqu	%xmm2,96(%rdi)
+	movdqu	32(%rsi),%xmm2
+	movdqu	%xmm7,112(%rdi)
+	leaq	128(%rdi),%rdi
+	movdqu	48(%rsi),%xmm7
+	pxor	32(%rsp),%xmm6
+	pxor	%xmm10,%xmm11
+	pxor	%xmm14,%xmm2
+	pxor	%xmm8,%xmm7
+
+	movdqu	%xmm6,0(%rdi)
+	movdqu	64(%rsi),%xmm6
+	movdqu	%xmm11,16(%rdi)
+	movdqu	80(%rsi),%xmm11
+	movdqu	%xmm2,32(%rdi)
+	movdqu	96(%rsi),%xmm2
+	movdqu	%xmm7,48(%rdi)
+	movdqu	112(%rsi),%xmm7
+	leaq	128(%rsi),%rsi
+	pxor	48(%rsp),%xmm6
+	pxor	%xmm15,%xmm11
+	pxor	%xmm9,%xmm2
+	pxor	%xmm3,%xmm7
+	movdqu	%xmm6,64(%rdi)
+	movdqu	%xmm11,80(%rdi)
+	movdqu	%xmm2,96(%rdi)
+	movdqu	%xmm7,112(%rdi)
+	leaq	128(%rdi),%rdi
+
+	subq	$256,%rdx
+	jnz	L$oop_outer4x
+
+	jmp	L$done4x
+
+L$tail4x:
+	cmpq	$192,%rdx
+	jae	L$192_or_more4x
+	cmpq	$128,%rdx
+	jae	L$128_or_more4x
+	cmpq	$64,%rdx
+	jae	L$64_or_more4x
+
+
+	xorq	%r10,%r10
+
+	movdqa	%xmm12,16(%rsp)
+	movdqa	%xmm4,32(%rsp)
+	movdqa	%xmm0,48(%rsp)
+	jmp	L$oop_tail4x
+
+.p2align	5
+L$64_or_more4x:
+	movdqu	0(%rsi),%xmm6
+	movdqu	16(%rsi),%xmm11
+	movdqu	32(%rsi),%xmm2
+	movdqu	48(%rsi),%xmm7
+	pxor	0(%rsp),%xmm6
+	pxor	%xmm12,%xmm11
+	pxor	%xmm4,%xmm2
+	pxor	%xmm0,%xmm7
+	movdqu	%xmm6,0(%rdi)
+	movdqu	%xmm11,16(%rdi)
+	movdqu	%xmm2,32(%rdi)
+	movdqu	%xmm7,48(%rdi)
+	je	L$done4x
+
+	movdqa	16(%rsp),%xmm6
+	leaq	64(%rsi),%rsi
+	xorq	%r10,%r10
+	movdqa	%xmm6,0(%rsp)
+	movdqa	%xmm13,16(%rsp)
+	leaq	64(%rdi),%rdi
+	movdqa	%xmm5,32(%rsp)
+	subq	$64,%rdx
+	movdqa	%xmm1,48(%rsp)
+	jmp	L$oop_tail4x
+
+.p2align	5
+L$128_or_more4x:
+	movdqu	0(%rsi),%xmm6
+	movdqu	16(%rsi),%xmm11
+	movdqu	32(%rsi),%xmm2
+	movdqu	48(%rsi),%xmm7
+	pxor	0(%rsp),%xmm6
+	pxor	%xmm12,%xmm11
+	pxor	%xmm4,%xmm2
+	pxor	%xmm0,%xmm7
+
+	movdqu	%xmm6,0(%rdi)
+	movdqu	64(%rsi),%xmm6
+	movdqu	%xmm11,16(%rdi)
+	movdqu	80(%rsi),%xmm11
+	movdqu	%xmm2,32(%rdi)
+	movdqu	96(%rsi),%xmm2
+	movdqu	%xmm7,48(%rdi)
+	movdqu	112(%rsi),%xmm7
+	pxor	16(%rsp),%xmm6
+	pxor	%xmm13,%xmm11
+	pxor	%xmm5,%xmm2
+	pxor	%xmm1,%xmm7
+	movdqu	%xmm6,64(%rdi)
+	movdqu	%xmm11,80(%rdi)
+	movdqu	%xmm2,96(%rdi)
+	movdqu	%xmm7,112(%rdi)
+	je	L$done4x
+
+	movdqa	32(%rsp),%xmm6
+	leaq	128(%rsi),%rsi
+	xorq	%r10,%r10
+	movdqa	%xmm6,0(%rsp)
+	movdqa	%xmm10,16(%rsp)
+	leaq	128(%rdi),%rdi
+	movdqa	%xmm14,32(%rsp)
+	subq	$128,%rdx
+	movdqa	%xmm8,48(%rsp)
+	jmp	L$oop_tail4x
+
+.p2align	5
+L$192_or_more4x:
+	movdqu	0(%rsi),%xmm6
+	movdqu	16(%rsi),%xmm11
+	movdqu	32(%rsi),%xmm2
+	movdqu	48(%rsi),%xmm7
+	pxor	0(%rsp),%xmm6
+	pxor	%xmm12,%xmm11
+	pxor	%xmm4,%xmm2
+	pxor	%xmm0,%xmm7
+
+	movdqu	%xmm6,0(%rdi)
+	movdqu	64(%rsi),%xmm6
+	movdqu	%xmm11,16(%rdi)
+	movdqu	80(%rsi),%xmm11
+	movdqu	%xmm2,32(%rdi)
+	movdqu	96(%rsi),%xmm2
+	movdqu	%xmm7,48(%rdi)
+	movdqu	112(%rsi),%xmm7
+	leaq	128(%rsi),%rsi
+	pxor	16(%rsp),%xmm6
+	pxor	%xmm13,%xmm11
+	pxor	%xmm5,%xmm2
+	pxor	%xmm1,%xmm7
+
+	movdqu	%xmm6,64(%rdi)
+	movdqu	0(%rsi),%xmm6
+	movdqu	%xmm11,80(%rdi)
+	movdqu	16(%rsi),%xmm11
+	movdqu	%xmm2,96(%rdi)
+	movdqu	32(%rsi),%xmm2
+	movdqu	%xmm7,112(%rdi)
+	leaq	128(%rdi),%rdi
+	movdqu	48(%rsi),%xmm7
+	pxor	32(%rsp),%xmm6
+	pxor	%xmm10,%xmm11
+	pxor	%xmm14,%xmm2
+	pxor	%xmm8,%xmm7
+	movdqu	%xmm6,0(%rdi)
+	movdqu	%xmm11,16(%rdi)
+	movdqu	%xmm2,32(%rdi)
+	movdqu	%xmm7,48(%rdi)
+	je	L$done4x
+
+	movdqa	48(%rsp),%xmm6
+	leaq	64(%rsi),%rsi
+	xorq	%r10,%r10
+	movdqa	%xmm6,0(%rsp)
+	movdqa	%xmm15,16(%rsp)
+	leaq	64(%rdi),%rdi
+	movdqa	%xmm9,32(%rsp)
+	subq	$192,%rdx
+	movdqa	%xmm3,48(%rsp)
+
+L$oop_tail4x:
+	movzbl	(%rsi,%r10,1),%eax
+	movzbl	(%rsp,%r10,1),%ecx
+	leaq	1(%r10),%r10
+	xorl	%ecx,%eax
+	movb	%al,-1(%rdi,%r10,1)
+	decq	%rdx
+	jnz	L$oop_tail4x
+
+L$done4x:
+	addq	$0x148+0,%rsp
+	.byte	0xf3,0xc3
+
+
+.p2align	5
+ChaCha20_8x:
+L$ChaCha20_8x:
+	movq	%rsp,%r10
+	subq	$0x280+8,%rsp
+	andq	$-32,%rsp
+	vzeroupper
+	movq	%r10,640(%rsp)
+
+
+
+
+
+
+
+
+
+
+	vbroadcasti128	L$sigma(%rip),%ymm11
+	vbroadcasti128	(%rcx),%ymm3
+	vbroadcasti128	16(%rcx),%ymm15
+	vbroadcasti128	(%r8),%ymm7
+	leaq	256(%rsp),%rcx
+	leaq	512(%rsp),%rax
+	leaq	L$rot16(%rip),%r10
+	leaq	L$rot24(%rip),%r11
+
+	vpshufd	$0x00,%ymm11,%ymm8
+	vpshufd	$0x55,%ymm11,%ymm9
+	vmovdqa	%ymm8,128-256(%rcx)
+	vpshufd	$0xaa,%ymm11,%ymm10
+	vmovdqa	%ymm9,160-256(%rcx)
+	vpshufd	$0xff,%ymm11,%ymm11
+	vmovdqa	%ymm10,192-256(%rcx)
+	vmovdqa	%ymm11,224-256(%rcx)
+
+	vpshufd	$0x00,%ymm3,%ymm0
+	vpshufd	$0x55,%ymm3,%ymm1
+	vmovdqa	%ymm0,256-256(%rcx)
+	vpshufd	$0xaa,%ymm3,%ymm2
+	vmovdqa	%ymm1,288-256(%rcx)
+	vpshufd	$0xff,%ymm3,%ymm3
+	vmovdqa	%ymm2,320-256(%rcx)
+	vmovdqa	%ymm3,352-256(%rcx)
+
+	vpshufd	$0x00,%ymm15,%ymm12
+	vpshufd	$0x55,%ymm15,%ymm13
+	vmovdqa	%ymm12,384-512(%rax)
+	vpshufd	$0xaa,%ymm15,%ymm14
+	vmovdqa	%ymm13,416-512(%rax)
+	vpshufd	$0xff,%ymm15,%ymm15
+	vmovdqa	%ymm14,448-512(%rax)
+	vmovdqa	%ymm15,480-512(%rax)
+
+	vpshufd	$0x00,%ymm7,%ymm4
+	vpshufd	$0x55,%ymm7,%ymm5
+	vpaddd	L$incy(%rip),%ymm4,%ymm4
+	vpshufd	$0xaa,%ymm7,%ymm6
+	vmovdqa	%ymm5,544-512(%rax)
+	vpshufd	$0xff,%ymm7,%ymm7
+	vmovdqa	%ymm6,576-512(%rax)
+	vmovdqa	%ymm7,608-512(%rax)
+
+	jmp	L$oop_enter8x
+
+.p2align	5
+L$oop_outer8x:
+	vmovdqa	128-256(%rcx),%ymm8
+	vmovdqa	160-256(%rcx),%ymm9
+	vmovdqa	192-256(%rcx),%ymm10
+	vmovdqa	224-256(%rcx),%ymm11
+	vmovdqa	256-256(%rcx),%ymm0
+	vmovdqa	288-256(%rcx),%ymm1
+	vmovdqa	320-256(%rcx),%ymm2
+	vmovdqa	352-256(%rcx),%ymm3
+	vmovdqa	384-512(%rax),%ymm12
+	vmovdqa	416-512(%rax),%ymm13
+	vmovdqa	448-512(%rax),%ymm14
+	vmovdqa	480-512(%rax),%ymm15
+	vmovdqa	512-512(%rax),%ymm4
+	vmovdqa	544-512(%rax),%ymm5
+	vmovdqa	576-512(%rax),%ymm6
+	vmovdqa	608-512(%rax),%ymm7
+	vpaddd	L$eight(%rip),%ymm4,%ymm4
+
+L$oop_enter8x:
+	vmovdqa	%ymm14,64(%rsp)
+	vmovdqa	%ymm15,96(%rsp)
+	vbroadcasti128	(%r10),%ymm15
+	vmovdqa	%ymm4,512-512(%rax)
+	movl	$10,%eax
+	jmp	L$oop8x
+
+.p2align	5
+L$oop8x:
+	vpaddd	%ymm0,%ymm8,%ymm8
+	vpxor	%ymm4,%ymm8,%ymm4
+	vpshufb	%ymm15,%ymm4,%ymm4
+	vpaddd	%ymm1,%ymm9,%ymm9
+	vpxor	%ymm5,%ymm9,%ymm5
+	vpshufb	%ymm15,%ymm5,%ymm5
+	vpaddd	%ymm4,%ymm12,%ymm12
+	vpxor	%ymm0,%ymm12,%ymm0
+	vpslld	$12,%ymm0,%ymm14
+	vpsrld	$20,%ymm0,%ymm0
+	vpor	%ymm0,%ymm14,%ymm0
+	vbroadcasti128	(%r11),%ymm14
+	vpaddd	%ymm5,%ymm13,%ymm13
+	vpxor	%ymm1,%ymm13,%ymm1
+	vpslld	$12,%ymm1,%ymm15
+	vpsrld	$20,%ymm1,%ymm1
+	vpor	%ymm1,%ymm15,%ymm1
+	vpaddd	%ymm0,%ymm8,%ymm8
+	vpxor	%ymm4,%ymm8,%ymm4
+	vpshufb	%ymm14,%ymm4,%ymm4
+	vpaddd	%ymm1,%ymm9,%ymm9
+	vpxor	%ymm5,%ymm9,%ymm5
+	vpshufb	%ymm14,%ymm5,%ymm5
+	vpaddd	%ymm4,%ymm12,%ymm12
+	vpxor	%ymm0,%ymm12,%ymm0
+	vpslld	$7,%ymm0,%ymm15
+	vpsrld	$25,%ymm0,%ymm0
+	vpor	%ymm0,%ymm15,%ymm0
+	vbroadcasti128	(%r10),%ymm15
+	vpaddd	%ymm5,%ymm13,%ymm13
+	vpxor	%ymm1,%ymm13,%ymm1
+	vpslld	$7,%ymm1,%ymm14
+	vpsrld	$25,%ymm1,%ymm1
+	vpor	%ymm1,%ymm14,%ymm1
+	vmovdqa	%ymm12,0(%rsp)
+	vmovdqa	%ymm13,32(%rsp)
+	vmovdqa	64(%rsp),%ymm12
+	vmovdqa	96(%rsp),%ymm13
+	vpaddd	%ymm2,%ymm10,%ymm10
+	vpxor	%ymm6,%ymm10,%ymm6
+	vpshufb	%ymm15,%ymm6,%ymm6
+	vpaddd	%ymm3,%ymm11,%ymm11
+	vpxor	%ymm7,%ymm11,%ymm7
+	vpshufb	%ymm15,%ymm7,%ymm7
+	vpaddd	%ymm6,%ymm12,%ymm12
+	vpxor	%ymm2,%ymm12,%ymm2
+	vpslld	$12,%ymm2,%ymm14
+	vpsrld	$20,%ymm2,%ymm2
+	vpor	%ymm2,%ymm14,%ymm2
+	vbroadcasti128	(%r11),%ymm14
+	vpaddd	%ymm7,%ymm13,%ymm13
+	vpxor	%ymm3,%ymm13,%ymm3
+	vpslld	$12,%ymm3,%ymm15
+	vpsrld	$20,%ymm3,%ymm3
+	vpor	%ymm3,%ymm15,%ymm3
+	vpaddd	%ymm2,%ymm10,%ymm10
+	vpxor	%ymm6,%ymm10,%ymm6
+	vpshufb	%ymm14,%ymm6,%ymm6
+	vpaddd	%ymm3,%ymm11,%ymm11
+	vpxor	%ymm7,%ymm11,%ymm7
+	vpshufb	%ymm14,%ymm7,%ymm7
+	vpaddd	%ymm6,%ymm12,%ymm12
+	vpxor	%ymm2,%ymm12,%ymm2
+	vpslld	$7,%ymm2,%ymm15
+	vpsrld	$25,%ymm2,%ymm2
+	vpor	%ymm2,%ymm15,%ymm2
+	vbroadcasti128	(%r10),%ymm15
+	vpaddd	%ymm7,%ymm13,%ymm13
+	vpxor	%ymm3,%ymm13,%ymm3
+	vpslld	$7,%ymm3,%ymm14
+	vpsrld	$25,%ymm3,%ymm3
+	vpor	%ymm3,%ymm14,%ymm3
+	vpaddd	%ymm1,%ymm8,%ymm8
+	vpxor	%ymm7,%ymm8,%ymm7
+	vpshufb	%ymm15,%ymm7,%ymm7
+	vpaddd	%ymm2,%ymm9,%ymm9
+	vpxor	%ymm4,%ymm9,%ymm4
+	vpshufb	%ymm15,%ymm4,%ymm4
+	vpaddd	%ymm7,%ymm12,%ymm12
+	vpxor	%ymm1,%ymm12,%ymm1
+	vpslld	$12,%ymm1,%ymm14
+	vpsrld	$20,%ymm1,%ymm1
+	vpor	%ymm1,%ymm14,%ymm1
+	vbroadcasti128	(%r11),%ymm14
+	vpaddd	%ymm4,%ymm13,%ymm13
+	vpxor	%ymm2,%ymm13,%ymm2
+	vpslld	$12,%ymm2,%ymm15
+	vpsrld	$20,%ymm2,%ymm2
+	vpor	%ymm2,%ymm15,%ymm2
+	vpaddd	%ymm1,%ymm8,%ymm8
+	vpxor	%ymm7,%ymm8,%ymm7
+	vpshufb	%ymm14,%ymm7,%ymm7
+	vpaddd	%ymm2,%ymm9,%ymm9
+	vpxor	%ymm4,%ymm9,%ymm4
+	vpshufb	%ymm14,%ymm4,%ymm4
+	vpaddd	%ymm7,%ymm12,%ymm12
+	vpxor	%ymm1,%ymm12,%ymm1
+	vpslld	$7,%ymm1,%ymm15
+	vpsrld	$25,%ymm1,%ymm1
+	vpor	%ymm1,%ymm15,%ymm1
+	vbroadcasti128	(%r10),%ymm15
+	vpaddd	%ymm4,%ymm13,%ymm13
+	vpxor	%ymm2,%ymm13,%ymm2
+	vpslld	$7,%ymm2,%ymm14
+	vpsrld	$25,%ymm2,%ymm2
+	vpor	%ymm2,%ymm14,%ymm2
+	vmovdqa	%ymm12,64(%rsp)
+	vmovdqa	%ymm13,96(%rsp)
+	vmovdqa	0(%rsp),%ymm12
+	vmovdqa	32(%rsp),%ymm13
+	vpaddd	%ymm3,%ymm10,%ymm10
+	vpxor	%ymm5,%ymm10,%ymm5
+	vpshufb	%ymm15,%ymm5,%ymm5
+	vpaddd	%ymm0,%ymm11,%ymm11
+	vpxor	%ymm6,%ymm11,%ymm6
+	vpshufb	%ymm15,%ymm6,%ymm6
+	vpaddd	%ymm5,%ymm12,%ymm12
+	vpxor	%ymm3,%ymm12,%ymm3
+	vpslld	$12,%ymm3,%ymm14
+	vpsrld	$20,%ymm3,%ymm3
+	vpor	%ymm3,%ymm14,%ymm3
+	vbroadcasti128	(%r11),%ymm14
+	vpaddd	%ymm6,%ymm13,%ymm13
+	vpxor	%ymm0,%ymm13,%ymm0
+	vpslld	$12,%ymm0,%ymm15
+	vpsrld	$20,%ymm0,%ymm0
+	vpor	%ymm0,%ymm15,%ymm0
+	vpaddd	%ymm3,%ymm10,%ymm10
+	vpxor	%ymm5,%ymm10,%ymm5
+	vpshufb	%ymm14,%ymm5,%ymm5
+	vpaddd	%ymm0,%ymm11,%ymm11
+	vpxor	%ymm6,%ymm11,%ymm6
+	vpshufb	%ymm14,%ymm6,%ymm6
+	vpaddd	%ymm5,%ymm12,%ymm12
+	vpxor	%ymm3,%ymm12,%ymm3
+	vpslld	$7,%ymm3,%ymm15
+	vpsrld	$25,%ymm3,%ymm3
+	vpor	%ymm3,%ymm15,%ymm3
+	vbroadcasti128	(%r10),%ymm15
+	vpaddd	%ymm6,%ymm13,%ymm13
+	vpxor	%ymm0,%ymm13,%ymm0
+	vpslld	$7,%ymm0,%ymm14
+	vpsrld	$25,%ymm0,%ymm0
+	vpor	%ymm0,%ymm14,%ymm0
+	decl	%eax
+	jnz	L$oop8x
+
+	leaq	512(%rsp),%rax
+	vpaddd	128-256(%rcx),%ymm8,%ymm8
+	vpaddd	160-256(%rcx),%ymm9,%ymm9
+	vpaddd	192-256(%rcx),%ymm10,%ymm10
+	vpaddd	224-256(%rcx),%ymm11,%ymm11
+
+	vpunpckldq	%ymm9,%ymm8,%ymm14
+	vpunpckldq	%ymm11,%ymm10,%ymm15
+	vpunpckhdq	%ymm9,%ymm8,%ymm8
+	vpunpckhdq	%ymm11,%ymm10,%ymm10
+	vpunpcklqdq	%ymm15,%ymm14,%ymm9
+	vpunpckhqdq	%ymm15,%ymm14,%ymm14
+	vpunpcklqdq	%ymm10,%ymm8,%ymm11
+	vpunpckhqdq	%ymm10,%ymm8,%ymm8
+	vpaddd	256-256(%rcx),%ymm0,%ymm0
+	vpaddd	288-256(%rcx),%ymm1,%ymm1
+	vpaddd	320-256(%rcx),%ymm2,%ymm2
+	vpaddd	352-256(%rcx),%ymm3,%ymm3
+
+	vpunpckldq	%ymm1,%ymm0,%ymm10
+	vpunpckldq	%ymm3,%ymm2,%ymm15
+	vpunpckhdq	%ymm1,%ymm0,%ymm0
+	vpunpckhdq	%ymm3,%ymm2,%ymm2
+	vpunpcklqdq	%ymm15,%ymm10,%ymm1
+	vpunpckhqdq	%ymm15,%ymm10,%ymm10
+	vpunpcklqdq	%ymm2,%ymm0,%ymm3
+	vpunpckhqdq	%ymm2,%ymm0,%ymm0
+	vperm2i128	$0x20,%ymm1,%ymm9,%ymm15
+	vperm2i128	$0x31,%ymm1,%ymm9,%ymm1
+	vperm2i128	$0x20,%ymm10,%ymm14,%ymm9
+	vperm2i128	$0x31,%ymm10,%ymm14,%ymm10
+	vperm2i128	$0x20,%ymm3,%ymm11,%ymm14
+	vperm2i128	$0x31,%ymm3,%ymm11,%ymm3
+	vperm2i128	$0x20,%ymm0,%ymm8,%ymm11
+	vperm2i128	$0x31,%ymm0,%ymm8,%ymm0
+	vmovdqa	%ymm15,0(%rsp)
+	vmovdqa	%ymm9,32(%rsp)
+	vmovdqa	64(%rsp),%ymm15
+	vmovdqa	96(%rsp),%ymm9
+
+	vpaddd	384-512(%rax),%ymm12,%ymm12
+	vpaddd	416-512(%rax),%ymm13,%ymm13
+	vpaddd	448-512(%rax),%ymm15,%ymm15
+	vpaddd	480-512(%rax),%ymm9,%ymm9
+
+	vpunpckldq	%ymm13,%ymm12,%ymm2
+	vpunpckldq	%ymm9,%ymm15,%ymm8
+	vpunpckhdq	%ymm13,%ymm12,%ymm12
+	vpunpckhdq	%ymm9,%ymm15,%ymm15
+	vpunpcklqdq	%ymm8,%ymm2,%ymm13
+	vpunpckhqdq	%ymm8,%ymm2,%ymm2
+	vpunpcklqdq	%ymm15,%ymm12,%ymm9
+	vpunpckhqdq	%ymm15,%ymm12,%ymm12
+	vpaddd	512-512(%rax),%ymm4,%ymm4
+	vpaddd	544-512(%rax),%ymm5,%ymm5
+	vpaddd	576-512(%rax),%ymm6,%ymm6
+	vpaddd	608-512(%rax),%ymm7,%ymm7
+
+	vpunpckldq	%ymm5,%ymm4,%ymm15
+	vpunpckldq	%ymm7,%ymm6,%ymm8
+	vpunpckhdq	%ymm5,%ymm4,%ymm4
+	vpunpckhdq	%ymm7,%ymm6,%ymm6
+	vpunpcklqdq	%ymm8,%ymm15,%ymm5
+	vpunpckhqdq	%ymm8,%ymm15,%ymm15
+	vpunpcklqdq	%ymm6,%ymm4,%ymm7
+	vpunpckhqdq	%ymm6,%ymm4,%ymm4
+	vperm2i128	$0x20,%ymm5,%ymm13,%ymm8
+	vperm2i128	$0x31,%ymm5,%ymm13,%ymm5
+	vperm2i128	$0x20,%ymm15,%ymm2,%ymm13
+	vperm2i128	$0x31,%ymm15,%ymm2,%ymm15
+	vperm2i128	$0x20,%ymm7,%ymm9,%ymm2
+	vperm2i128	$0x31,%ymm7,%ymm9,%ymm7
+	vperm2i128	$0x20,%ymm4,%ymm12,%ymm9
+	vperm2i128	$0x31,%ymm4,%ymm12,%ymm4
+	vmovdqa	0(%rsp),%ymm6
+	vmovdqa	32(%rsp),%ymm12
+
+	cmpq	$512,%rdx
+	jb	L$tail8x
+
+	vpxor	0(%rsi),%ymm6,%ymm6
+	vpxor	32(%rsi),%ymm8,%ymm8
+	vpxor	64(%rsi),%ymm1,%ymm1
+	vpxor	96(%rsi),%ymm5,%ymm5
+	leaq	128(%rsi),%rsi
+	vmovdqu	%ymm6,0(%rdi)
+	vmovdqu	%ymm8,32(%rdi)
+	vmovdqu	%ymm1,64(%rdi)
+	vmovdqu	%ymm5,96(%rdi)
+	leaq	128(%rdi),%rdi
+
+	vpxor	0(%rsi),%ymm12,%ymm12
+	vpxor	32(%rsi),%ymm13,%ymm13
+	vpxor	64(%rsi),%ymm10,%ymm10
+	vpxor	96(%rsi),%ymm15,%ymm15
+	leaq	128(%rsi),%rsi
+	vmovdqu	%ymm12,0(%rdi)
+	vmovdqu	%ymm13,32(%rdi)
+	vmovdqu	%ymm10,64(%rdi)
+	vmovdqu	%ymm15,96(%rdi)
+	leaq	128(%rdi),%rdi
+
+	vpxor	0(%rsi),%ymm14,%ymm14
+	vpxor	32(%rsi),%ymm2,%ymm2
+	vpxor	64(%rsi),%ymm3,%ymm3
+	vpxor	96(%rsi),%ymm7,%ymm7
+	leaq	128(%rsi),%rsi
+	vmovdqu	%ymm14,0(%rdi)
+	vmovdqu	%ymm2,32(%rdi)
+	vmovdqu	%ymm3,64(%rdi)
+	vmovdqu	%ymm7,96(%rdi)
+	leaq	128(%rdi),%rdi
+
+	vpxor	0(%rsi),%ymm11,%ymm11
+	vpxor	32(%rsi),%ymm9,%ymm9
+	vpxor	64(%rsi),%ymm0,%ymm0
+	vpxor	96(%rsi),%ymm4,%ymm4
+	leaq	128(%rsi),%rsi
+	vmovdqu	%ymm11,0(%rdi)
+	vmovdqu	%ymm9,32(%rdi)
+	vmovdqu	%ymm0,64(%rdi)
+	vmovdqu	%ymm4,96(%rdi)
+	leaq	128(%rdi),%rdi
+
+	subq	$512,%rdx
+	jnz	L$oop_outer8x
+
+	jmp	L$done8x
+
+L$tail8x:
+	cmpq	$448,%rdx
+	jae	L$448_or_more8x
+	cmpq	$384,%rdx
+	jae	L$384_or_more8x
+	cmpq	$320,%rdx
+	jae	L$320_or_more8x
+	cmpq	$256,%rdx
+	jae	L$256_or_more8x
+	cmpq	$192,%rdx
+	jae	L$192_or_more8x
+	cmpq	$128,%rdx
+	jae	L$128_or_more8x
+	cmpq	$64,%rdx
+	jae	L$64_or_more8x
+
+	xorq	%r10,%r10
+	vmovdqa	%ymm6,0(%rsp)
+	vmovdqa	%ymm8,32(%rsp)
+	jmp	L$oop_tail8x
+
+.p2align	5
+L$64_or_more8x:
+	vpxor	0(%rsi),%ymm6,%ymm6
+	vpxor	32(%rsi),%ymm8,%ymm8
+	vmovdqu	%ymm6,0(%rdi)
+	vmovdqu	%ymm8,32(%rdi)
+	je	L$done8x
+
+	leaq	64(%rsi),%rsi
+	xorq	%r10,%r10
+	vmovdqa	%ymm1,0(%rsp)
+	leaq	64(%rdi),%rdi
+	subq	$64,%rdx
+	vmovdqa	%ymm5,32(%rsp)
+	jmp	L$oop_tail8x
+
+.p2align	5
+L$128_or_more8x:
+	vpxor	0(%rsi),%ymm6,%ymm6
+	vpxor	32(%rsi),%ymm8,%ymm8
+	vpxor	64(%rsi),%ymm1,%ymm1
+	vpxor	96(%rsi),%ymm5,%ymm5
+	vmovdqu	%ymm6,0(%rdi)
+	vmovdqu	%ymm8,32(%rdi)
+	vmovdqu	%ymm1,64(%rdi)
+	vmovdqu	%ymm5,96(%rdi)
+	je	L$done8x
+
+	leaq	128(%rsi),%rsi
+	xorq	%r10,%r10
+	vmovdqa	%ymm12,0(%rsp)
+	leaq	128(%rdi),%rdi
+	subq	$128,%rdx
+	vmovdqa	%ymm13,32(%rsp)
+	jmp	L$oop_tail8x
+
+.p2align	5
+L$192_or_more8x:
+	vpxor	0(%rsi),%ymm6,%ymm6
+	vpxor	32(%rsi),%ymm8,%ymm8
+	vpxor	64(%rsi),%ymm1,%ymm1
+	vpxor	96(%rsi),%ymm5,%ymm5
+	vpxor	128(%rsi),%ymm12,%ymm12
+	vpxor	160(%rsi),%ymm13,%ymm13
+	vmovdqu	%ymm6,0(%rdi)
+	vmovdqu	%ymm8,32(%rdi)
+	vmovdqu	%ymm1,64(%rdi)
+	vmovdqu	%ymm5,96(%rdi)
+	vmovdqu	%ymm12,128(%rdi)
+	vmovdqu	%ymm13,160(%rdi)
+	je	L$done8x
+
+	leaq	192(%rsi),%rsi
+	xorq	%r10,%r10
+	vmovdqa	%ymm10,0(%rsp)
+	leaq	192(%rdi),%rdi
+	subq	$192,%rdx
+	vmovdqa	%ymm15,32(%rsp)
+	jmp	L$oop_tail8x
+
+.p2align	5
+L$256_or_more8x:
+	vpxor	0(%rsi),%ymm6,%ymm6
+	vpxor	32(%rsi),%ymm8,%ymm8
+	vpxor	64(%rsi),%ymm1,%ymm1
+	vpxor	96(%rsi),%ymm5,%ymm5
+	vpxor	128(%rsi),%ymm12,%ymm12
+	vpxor	160(%rsi),%ymm13,%ymm13
+	vpxor	192(%rsi),%ymm10,%ymm10
+	vpxor	224(%rsi),%ymm15,%ymm15
+	vmovdqu	%ymm6,0(%rdi)
+	vmovdqu	%ymm8,32(%rdi)
+	vmovdqu	%ymm1,64(%rdi)
+	vmovdqu	%ymm5,96(%rdi)
+	vmovdqu	%ymm12,128(%rdi)
+	vmovdqu	%ymm13,160(%rdi)
+	vmovdqu	%ymm10,192(%rdi)
+	vmovdqu	%ymm15,224(%rdi)
+	je	L$done8x
+
+	leaq	256(%rsi),%rsi
+	xorq	%r10,%r10
+	vmovdqa	%ymm14,0(%rsp)
+	leaq	256(%rdi),%rdi
+	subq	$256,%rdx
+	vmovdqa	%ymm2,32(%rsp)
+	jmp	L$oop_tail8x
+
+.p2align	5
+L$320_or_more8x:
+	vpxor	0(%rsi),%ymm6,%ymm6
+	vpxor	32(%rsi),%ymm8,%ymm8
+	vpxor	64(%rsi),%ymm1,%ymm1
+	vpxor	96(%rsi),%ymm5,%ymm5
+	vpxor	128(%rsi),%ymm12,%ymm12
+	vpxor	160(%rsi),%ymm13,%ymm13
+	vpxor	192(%rsi),%ymm10,%ymm10
+	vpxor	224(%rsi),%ymm15,%ymm15
+	vpxor	256(%rsi),%ymm14,%ymm14
+	vpxor	288(%rsi),%ymm2,%ymm2
+	vmovdqu	%ymm6,0(%rdi)
+	vmovdqu	%ymm8,32(%rdi)
+	vmovdqu	%ymm1,64(%rdi)
+	vmovdqu	%ymm5,96(%rdi)
+	vmovdqu	%ymm12,128(%rdi)
+	vmovdqu	%ymm13,160(%rdi)
+	vmovdqu	%ymm10,192(%rdi)
+	vmovdqu	%ymm15,224(%rdi)
+	vmovdqu	%ymm14,256(%rdi)
+	vmovdqu	%ymm2,288(%rdi)
+	je	L$done8x
+
+	leaq	320(%rsi),%rsi
+	xorq	%r10,%r10
+	vmovdqa	%ymm3,0(%rsp)
+	leaq	320(%rdi),%rdi
+	subq	$320,%rdx
+	vmovdqa	%ymm7,32(%rsp)
+	jmp	L$oop_tail8x
+
+.p2align	5
+L$384_or_more8x:
+	vpxor	0(%rsi),%ymm6,%ymm6
+	vpxor	32(%rsi),%ymm8,%ymm8
+	vpxor	64(%rsi),%ymm1,%ymm1
+	vpxor	96(%rsi),%ymm5,%ymm5
+	vpxor	128(%rsi),%ymm12,%ymm12
+	vpxor	160(%rsi),%ymm13,%ymm13
+	vpxor	192(%rsi),%ymm10,%ymm10
+	vpxor	224(%rsi),%ymm15,%ymm15
+	vpxor	256(%rsi),%ymm14,%ymm14
+	vpxor	288(%rsi),%ymm2,%ymm2
+	vpxor	320(%rsi),%ymm3,%ymm3
+	vpxor	352(%rsi),%ymm7,%ymm7
+	vmovdqu	%ymm6,0(%rdi)
+	vmovdqu	%ymm8,32(%rdi)
+	vmovdqu	%ymm1,64(%rdi)
+	vmovdqu	%ymm5,96(%rdi)
+	vmovdqu	%ymm12,128(%rdi)
+	vmovdqu	%ymm13,160(%rdi)
+	vmovdqu	%ymm10,192(%rdi)
+	vmovdqu	%ymm15,224(%rdi)
+	vmovdqu	%ymm14,256(%rdi)
+	vmovdqu	%ymm2,288(%rdi)
+	vmovdqu	%ymm3,320(%rdi)
+	vmovdqu	%ymm7,352(%rdi)
+	je	L$done8x
+
+	leaq	384(%rsi),%rsi
+	xorq	%r10,%r10
+	vmovdqa	%ymm11,0(%rsp)
+	leaq	384(%rdi),%rdi
+	subq	$384,%rdx
+	vmovdqa	%ymm9,32(%rsp)
+	jmp	L$oop_tail8x
+
+.p2align	5
+L$448_or_more8x:
+	vpxor	0(%rsi),%ymm6,%ymm6
+	vpxor	32(%rsi),%ymm8,%ymm8
+	vpxor	64(%rsi),%ymm1,%ymm1
+	vpxor	96(%rsi),%ymm5,%ymm5
+	vpxor	128(%rsi),%ymm12,%ymm12
+	vpxor	160(%rsi),%ymm13,%ymm13
+	vpxor	192(%rsi),%ymm10,%ymm10
+	vpxor	224(%rsi),%ymm15,%ymm15
+	vpxor	256(%rsi),%ymm14,%ymm14
+	vpxor	288(%rsi),%ymm2,%ymm2
+	vpxor	320(%rsi),%ymm3,%ymm3
+	vpxor	352(%rsi),%ymm7,%ymm7
+	vpxor	384(%rsi),%ymm11,%ymm11
+	vpxor	416(%rsi),%ymm9,%ymm9
+	vmovdqu	%ymm6,0(%rdi)
+	vmovdqu	%ymm8,32(%rdi)
+	vmovdqu	%ymm1,64(%rdi)
+	vmovdqu	%ymm5,96(%rdi)
+	vmovdqu	%ymm12,128(%rdi)
+	vmovdqu	%ymm13,160(%rdi)
+	vmovdqu	%ymm10,192(%rdi)
+	vmovdqu	%ymm15,224(%rdi)
+	vmovdqu	%ymm14,256(%rdi)
+	vmovdqu	%ymm2,288(%rdi)
+	vmovdqu	%ymm3,320(%rdi)
+	vmovdqu	%ymm7,352(%rdi)
+	vmovdqu	%ymm11,384(%rdi)
+	vmovdqu	%ymm9,416(%rdi)
+	je	L$done8x
+
+	leaq	448(%rsi),%rsi
+	xorq	%r10,%r10
+	vmovdqa	%ymm0,0(%rsp)
+	leaq	448(%rdi),%rdi
+	subq	$448,%rdx
+	vmovdqa	%ymm4,32(%rsp)
+
+L$oop_tail8x:
+	movzbl	(%rsi,%r10,1),%eax
+	movzbl	(%rsp,%r10,1),%ecx
+	leaq	1(%r10),%r10
+	xorl	%ecx,%eax
+	movb	%al,-1(%rdi,%r10,1)
+	decq	%rdx
+	jnz	L$oop_tail8x
+
+L$done8x:
+	vzeroall
+	movq	640(%rsp),%rsp
+	.byte	0xf3,0xc3
+
+#endif
diff --git a/packager/third_party/boringssl/mac-x86_64/crypto/ec/p256-x86_64-asm.S b/packager/third_party/boringssl/mac-x86_64/crypto/ec/p256-x86_64-asm.S
new file mode 100644
index 0000000000..1cd0cc3f5c
--- /dev/null
+++ b/packager/third_party/boringssl/mac-x86_64/crypto/ec/p256-x86_64-asm.S
@@ -0,0 +1,1788 @@
+#if defined(__x86_64__)
+.text	
+
+
+
+.p2align	6
+L$poly:
+.quad	0xffffffffffffffff, 0x00000000ffffffff, 0x0000000000000000, 0xffffffff00000001
+
+L$One:
+.long	1,1,1,1,1,1,1,1
+L$Two:
+.long	2,2,2,2,2,2,2,2
+L$Three:
+.long	3,3,3,3,3,3,3,3
+L$ONE_mont:
+.quad	0x0000000000000001, 0xffffffff00000000, 0xffffffffffffffff, 0x00000000fffffffe
+
+
+.p2align	6
+ecp_nistz256_mul_by_2:
+	pushq	%r12
+	pushq	%r13
+
+	movq	0(%rsi),%r8
+	movq	8(%rsi),%r9
+	addq	%r8,%r8
+	movq	16(%rsi),%r10
+	adcq	%r9,%r9
+	movq	24(%rsi),%r11
+	leaq	L$poly(%rip),%rsi
+	movq	%r8,%rax
+	adcq	%r10,%r10
+	adcq	%r11,%r11
+	movq	%r9,%rdx
+	sbbq	%r13,%r13
+
+	subq	0(%rsi),%r8
+	movq	%r10,%rcx
+	sbbq	8(%rsi),%r9
+	sbbq	16(%rsi),%r10
+	movq	%r11,%r12
+	sbbq	24(%rsi),%r11
+	testq	%r13,%r13
+
+	cmovzq	%rax,%r8
+	cmovzq	%rdx,%r9
+	movq	%r8,0(%rdi)
+	cmovzq	%rcx,%r10
+	movq	%r9,8(%rdi)
+	cmovzq	%r12,%r11
+	movq	%r10,16(%rdi)
+	movq	%r11,24(%rdi)
+
+	popq	%r13
+	popq	%r12
+	.byte	0xf3,0xc3
+
+
+
+
+.globl	_ecp_nistz256_neg
+.private_extern _ecp_nistz256_neg
+
+.p2align	5
+_ecp_nistz256_neg:
+	pushq	%r12
+	pushq	%r13
+
+	xorq	%r8,%r8
+	xorq	%r9,%r9
+	xorq	%r10,%r10
+	xorq	%r11,%r11
+	xorq	%r13,%r13
+
+	subq	0(%rsi),%r8
+	sbbq	8(%rsi),%r9
+	sbbq	16(%rsi),%r10
+	movq	%r8,%rax
+	sbbq	24(%rsi),%r11
+	leaq	L$poly(%rip),%rsi
+	movq	%r9,%rdx
+	sbbq	$0,%r13
+
+	addq	0(%rsi),%r8
+	movq	%r10,%rcx
+	adcq	8(%rsi),%r9
+	adcq	16(%rsi),%r10
+	movq	%r11,%r12
+	adcq	24(%rsi),%r11
+	testq	%r13,%r13
+
+	cmovzq	%rax,%r8
+	cmovzq	%rdx,%r9
+	movq	%r8,0(%rdi)
+	cmovzq	%rcx,%r10
+	movq	%r9,8(%rdi)
+	cmovzq	%r12,%r11
+	movq	%r10,16(%rdi)
+	movq	%r11,24(%rdi)
+
+	popq	%r13
+	popq	%r12
+	.byte	0xf3,0xc3
+
+
+
+
+
+
+
+.globl	_ecp_nistz256_mul_mont
+.private_extern _ecp_nistz256_mul_mont
+
+.p2align	5
+_ecp_nistz256_mul_mont:
+L$mul_mont:
+	pushq	%rbp
+	pushq	%rbx
+	pushq	%r12
+	pushq	%r13
+	pushq	%r14
+	pushq	%r15
+	movq	%rdx,%rbx
+	movq	0(%rdx),%rax
+	movq	0(%rsi),%r9
+	movq	8(%rsi),%r10
+	movq	16(%rsi),%r11
+	movq	24(%rsi),%r12
+
+	call	__ecp_nistz256_mul_montq
+L$mul_mont_done:
+	popq	%r15
+	popq	%r14
+	popq	%r13
+	popq	%r12
+	popq	%rbx
+	popq	%rbp
+	.byte	0xf3,0xc3
+
+
+
+.p2align	5
+__ecp_nistz256_mul_montq:
+
+
+	movq	%rax,%rbp
+	mulq	%r9
+	movq	L$poly+8(%rip),%r14
+	movq	%rax,%r8
+	movq	%rbp,%rax
+	movq	%rdx,%r9
+
+	mulq	%r10
+	movq	L$poly+24(%rip),%r15
+	addq	%rax,%r9
+	movq	%rbp,%rax
+	adcq	$0,%rdx
+	movq	%rdx,%r10
+
+	mulq	%r11
+	addq	%rax,%r10
+	movq	%rbp,%rax
+	adcq	$0,%rdx
+	movq	%rdx,%r11
+
+	mulq	%r12
+	addq	%rax,%r11
+	movq	%r8,%rax
+	adcq	$0,%rdx
+	xorq	%r13,%r13
+	movq	%rdx,%r12
+
+
+
+
+
+
+
+
+
+
+	movq	%r8,%rbp
+	shlq	$32,%r8
+	mulq	%r15
+	shrq	$32,%rbp
+	addq	%r8,%r9
+	adcq	%rbp,%r10
+	adcq	%rax,%r11
+	movq	8(%rbx),%rax
+	adcq	%rdx,%r12
+	adcq	$0,%r13
+	xorq	%r8,%r8
+
+
+
+	movq	%rax,%rbp
+	mulq	0(%rsi)
+	addq	%rax,%r9
+	movq	%rbp,%rax
+	adcq	$0,%rdx
+	movq	%rdx,%rcx
+
+	mulq	8(%rsi)
+	addq	%rcx,%r10
+	adcq	$0,%rdx
+	addq	%rax,%r10
+	movq	%rbp,%rax
+	adcq	$0,%rdx
+	movq	%rdx,%rcx
+
+	mulq	16(%rsi)
+	addq	%rcx,%r11
+	adcq	$0,%rdx
+	addq	%rax,%r11
+	movq	%rbp,%rax
+	adcq	$0,%rdx
+	movq	%rdx,%rcx
+
+	mulq	24(%rsi)
+	addq	%rcx,%r12
+	adcq	$0,%rdx
+	addq	%rax,%r12
+	movq	%r9,%rax
+	adcq	%rdx,%r13
+	adcq	$0,%r8
+
+
+
+	movq	%r9,%rbp
+	shlq	$32,%r9
+	mulq	%r15
+	shrq	$32,%rbp
+	addq	%r9,%r10
+	adcq	%rbp,%r11
+	adcq	%rax,%r12
+	movq	16(%rbx),%rax
+	adcq	%rdx,%r13
+	adcq	$0,%r8
+	xorq	%r9,%r9
+
+
+
+	movq	%rax,%rbp
+	mulq	0(%rsi)
+	addq	%rax,%r10
+	movq	%rbp,%rax
+	adcq	$0,%rdx
+	movq	%rdx,%rcx
+
+	mulq	8(%rsi)
+	addq	%rcx,%r11
+	adcq	$0,%rdx
+	addq	%rax,%r11
+	movq	%rbp,%rax
+	adcq	$0,%rdx
+	movq	%rdx,%rcx
+
+	mulq	16(%rsi)
+	addq	%rcx,%r12
+	adcq	$0,%rdx
+	addq	%rax,%r12
+	movq	%rbp,%rax
+	adcq	$0,%rdx
+	movq	%rdx,%rcx
+
+	mulq	24(%rsi)
+	addq	%rcx,%r13
+	adcq	$0,%rdx
+	addq	%rax,%r13
+	movq	%r10,%rax
+	adcq	%rdx,%r8
+	adcq	$0,%r9
+
+
+
+	movq	%r10,%rbp
+	shlq	$32,%r10
+	mulq	%r15
+	shrq	$32,%rbp
+	addq	%r10,%r11
+	adcq	%rbp,%r12
+	adcq	%rax,%r13
+	movq	24(%rbx),%rax
+	adcq	%rdx,%r8
+	adcq	$0,%r9
+	xorq	%r10,%r10
+
+
+
+	movq	%rax,%rbp
+	mulq	0(%rsi)
+	addq	%rax,%r11
+	movq	%rbp,%rax
+	adcq	$0,%rdx
+	movq	%rdx,%rcx
+
+	mulq	8(%rsi)
+	addq	%rcx,%r12
+	adcq	$0,%rdx
+	addq	%rax,%r12
+	movq	%rbp,%rax
+	adcq	$0,%rdx
+	movq	%rdx,%rcx
+
+	mulq	16(%rsi)
+	addq	%rcx,%r13
+	adcq	$0,%rdx
+	addq	%rax,%r13
+	movq	%rbp,%rax
+	adcq	$0,%rdx
+	movq	%rdx,%rcx
+
+	mulq	24(%rsi)
+	addq	%rcx,%r8
+	adcq	$0,%rdx
+	addq	%rax,%r8
+	movq	%r11,%rax
+	adcq	%rdx,%r9
+	adcq	$0,%r10
+
+
+
+	movq	%r11,%rbp
+	shlq	$32,%r11
+	mulq	%r15
+	shrq	$32,%rbp
+	addq	%r11,%r12
+	adcq	%rbp,%r13
+	movq	%r12,%rcx
+	adcq	%rax,%r8
+	adcq	%rdx,%r9
+	movq	%r13,%rbp
+	adcq	$0,%r10
+
+
+
+	subq	$-1,%r12
+	movq	%r8,%rbx
+	sbbq	%r14,%r13
+	sbbq	$0,%r8
+	movq	%r9,%rdx
+	sbbq	%r15,%r9
+	sbbq	$0,%r10
+
+	cmovcq	%rcx,%r12
+	cmovcq	%rbp,%r13
+	movq	%r12,0(%rdi)
+	cmovcq	%rbx,%r8
+	movq	%r13,8(%rdi)
+	cmovcq	%rdx,%r9
+	movq	%r8,16(%rdi)
+	movq	%r9,24(%rdi)
+
+	.byte	0xf3,0xc3
+
+
+
+
+
+
+
+
+
+.globl	_ecp_nistz256_sqr_mont
+.private_extern _ecp_nistz256_sqr_mont
+
+.p2align	5
+_ecp_nistz256_sqr_mont:
+	pushq	%rbp
+	pushq	%rbx
+	pushq	%r12
+	pushq	%r13
+	pushq	%r14
+	pushq	%r15
+	movq	0(%rsi),%rax
+	movq	8(%rsi),%r14
+	movq	16(%rsi),%r15
+	movq	24(%rsi),%r8
+
+	call	__ecp_nistz256_sqr_montq
+L$sqr_mont_done:
+	popq	%r15
+	popq	%r14
+	popq	%r13
+	popq	%r12
+	popq	%rbx
+	popq	%rbp
+	.byte	0xf3,0xc3
+
+
+
+.p2align	5
+__ecp_nistz256_sqr_montq:
+	movq	%rax,%r13
+	mulq	%r14
+	movq	%rax,%r9
+	movq	%r15,%rax
+	movq	%rdx,%r10
+
+	mulq	%r13
+	addq	%rax,%r10
+	movq	%r8,%rax
+	adcq	$0,%rdx
+	movq	%rdx,%r11
+
+	mulq	%r13
+	addq	%rax,%r11
+	movq	%r15,%rax
+	adcq	$0,%rdx
+	movq	%rdx,%r12
+
+
+	mulq	%r14
+	addq	%rax,%r11
+	movq	%r8,%rax
+	adcq	$0,%rdx
+	movq	%rdx,%rbp
+
+	mulq	%r14
+	addq	%rax,%r12
+	movq	%r8,%rax
+	adcq	$0,%rdx
+	addq	%rbp,%r12
+	movq	%rdx,%r13
+	adcq	$0,%r13
+
+
+	mulq	%r15
+	xorq	%r15,%r15
+	addq	%rax,%r13
+	movq	0(%rsi),%rax
+	movq	%rdx,%r14
+	adcq	$0,%r14
+
+	addq	%r9,%r9
+	adcq	%r10,%r10
+	adcq	%r11,%r11
+	adcq	%r12,%r12
+	adcq	%r13,%r13
+	adcq	%r14,%r14
+	adcq	$0,%r15
+
+	mulq	%rax
+	movq	%rax,%r8
+	movq	8(%rsi),%rax
+	movq	%rdx,%rcx
+
+	mulq	%rax
+	addq	%rcx,%r9
+	adcq	%rax,%r10
+	movq	16(%rsi),%rax
+	adcq	$0,%rdx
+	movq	%rdx,%rcx
+
+	mulq	%rax
+	addq	%rcx,%r11
+	adcq	%rax,%r12
+	movq	24(%rsi),%rax
+	adcq	$0,%rdx
+	movq	%rdx,%rcx
+
+	mulq	%rax
+	addq	%rcx,%r13
+	adcq	%rax,%r14
+	movq	%r8,%rax
+	adcq	%rdx,%r15
+
+	movq	L$poly+8(%rip),%rsi
+	movq	L$poly+24(%rip),%rbp
+
+
+
+
+	movq	%r8,%rcx
+	shlq	$32,%r8
+	mulq	%rbp
+	shrq	$32,%rcx
+	addq	%r8,%r9
+	adcq	%rcx,%r10
+	adcq	%rax,%r11
+	movq	%r9,%rax
+	adcq	$0,%rdx
+
+
+
+	movq	%r9,%rcx
+	shlq	$32,%r9
+	movq	%rdx,%r8
+	mulq	%rbp
+	shrq	$32,%rcx
+	addq	%r9,%r10
+	adcq	%rcx,%r11
+	adcq	%rax,%r8
+	movq	%r10,%rax
+	adcq	$0,%rdx
+
+
+
+	movq	%r10,%rcx
+	shlq	$32,%r10
+	movq	%rdx,%r9
+	mulq	%rbp
+	shrq	$32,%rcx
+	addq	%r10,%r11
+	adcq	%rcx,%r8
+	adcq	%rax,%r9
+	movq	%r11,%rax
+	adcq	$0,%rdx
+
+
+
+	movq	%r11,%rcx
+	shlq	$32,%r11
+	movq	%rdx,%r10
+	mulq	%rbp
+	shrq	$32,%rcx
+	addq	%r11,%r8
+	adcq	%rcx,%r9
+	adcq	%rax,%r10
+	adcq	$0,%rdx
+	xorq	%r11,%r11
+
+
+
+	addq	%r8,%r12
+	adcq	%r9,%r13
+	movq	%r12,%r8
+	adcq	%r10,%r14
+	adcq	%rdx,%r15
+	movq	%r13,%r9
+	adcq	$0,%r11
+
+	subq	$-1,%r12
+	movq	%r14,%r10
+	sbbq	%rsi,%r13
+	sbbq	$0,%r14
+	movq	%r15,%rcx
+	sbbq	%rbp,%r15
+	sbbq	$0,%r11
+
+	cmovcq	%r8,%r12
+	cmovcq	%r9,%r13
+	movq	%r12,0(%rdi)
+	cmovcq	%r10,%r14
+	movq	%r13,8(%rdi)
+	cmovcq	%rcx,%r15
+	movq	%r14,16(%rdi)
+	movq	%r15,24(%rdi)
+
+	.byte	0xf3,0xc3
+
+
+
+
+
+
+
+.globl	_ecp_nistz256_from_mont
+.private_extern _ecp_nistz256_from_mont
+
+.p2align	5
+_ecp_nistz256_from_mont:
+	pushq	%r12
+	pushq	%r13
+
+	movq	0(%rsi),%rax
+	movq	L$poly+24(%rip),%r13
+	movq	8(%rsi),%r9
+	movq	16(%rsi),%r10
+	movq	24(%rsi),%r11
+	movq	%rax,%r8
+	movq	L$poly+8(%rip),%r12
+
+
+
+	movq	%rax,%rcx
+	shlq	$32,%r8
+	mulq	%r13
+	shrq	$32,%rcx
+	addq	%r8,%r9
+	adcq	%rcx,%r10
+	adcq	%rax,%r11
+	movq	%r9,%rax
+	adcq	$0,%rdx
+
+
+
+	movq	%r9,%rcx
+	shlq	$32,%r9
+	movq	%rdx,%r8
+	mulq	%r13
+	shrq	$32,%rcx
+	addq	%r9,%r10
+	adcq	%rcx,%r11
+	adcq	%rax,%r8
+	movq	%r10,%rax
+	adcq	$0,%rdx
+
+
+
+	movq	%r10,%rcx
+	shlq	$32,%r10
+	movq	%rdx,%r9
+	mulq	%r13
+	shrq	$32,%rcx
+	addq	%r10,%r11
+	adcq	%rcx,%r8
+	adcq	%rax,%r9
+	movq	%r11,%rax
+	adcq	$0,%rdx
+
+
+
+	movq	%r11,%rcx
+	shlq	$32,%r11
+	movq	%rdx,%r10
+	mulq	%r13
+	shrq	$32,%rcx
+	addq	%r11,%r8
+	adcq	%rcx,%r9
+	movq	%r8,%rcx
+	adcq	%rax,%r10
+	movq	%r9,%rsi
+	adcq	$0,%rdx
+
+	subq	$-1,%r8
+	movq	%r10,%rax
+	sbbq	%r12,%r9
+	sbbq	$0,%r10
+	movq	%rdx,%r11
+	sbbq	%r13,%rdx
+	sbbq	%r13,%r13
+
+	cmovnzq	%rcx,%r8
+	cmovnzq	%rsi,%r9
+	movq	%r8,0(%rdi)
+	cmovnzq	%rax,%r10
+	movq	%r9,8(%rdi)
+	cmovzq	%rdx,%r11
+	movq	%r10,16(%rdi)
+	movq	%r11,24(%rdi)
+
+	popq	%r13
+	popq	%r12
+	.byte	0xf3,0xc3
+
+
+
+.globl	_ecp_nistz256_select_w5
+.private_extern _ecp_nistz256_select_w5
+
+.p2align	5
+_ecp_nistz256_select_w5:
+	movdqa	L$One(%rip),%xmm0
+	movd	%edx,%xmm1
+
+	pxor	%xmm2,%xmm2
+	pxor	%xmm3,%xmm3
+	pxor	%xmm4,%xmm4
+	pxor	%xmm5,%xmm5
+	pxor	%xmm6,%xmm6
+	pxor	%xmm7,%xmm7
+
+	movdqa	%xmm0,%xmm8
+	pshufd	$0,%xmm1,%xmm1
+
+	movq	$16,%rax
+L$select_loop_sse_w5:
+
+	movdqa	%xmm8,%xmm15
+	paddd	%xmm0,%xmm8
+	pcmpeqd	%xmm1,%xmm15
+
+	movdqa	0(%rsi),%xmm9
+	movdqa	16(%rsi),%xmm10
+	movdqa	32(%rsi),%xmm11
+	movdqa	48(%rsi),%xmm12
+	movdqa	64(%rsi),%xmm13
+	movdqa	80(%rsi),%xmm14
+	leaq	96(%rsi),%rsi
+
+	pand	%xmm15,%xmm9
+	pand	%xmm15,%xmm10
+	por	%xmm9,%xmm2
+	pand	%xmm15,%xmm11
+	por	%xmm10,%xmm3
+	pand	%xmm15,%xmm12
+	por	%xmm11,%xmm4
+	pand	%xmm15,%xmm13
+	por	%xmm12,%xmm5
+	pand	%xmm15,%xmm14
+	por	%xmm13,%xmm6
+	por	%xmm14,%xmm7
+
+	decq	%rax
+	jnz	L$select_loop_sse_w5
+
+	movdqu	%xmm2,0(%rdi)
+	movdqu	%xmm3,16(%rdi)
+	movdqu	%xmm4,32(%rdi)
+	movdqu	%xmm5,48(%rdi)
+	movdqu	%xmm6,64(%rdi)
+	movdqu	%xmm7,80(%rdi)
+	.byte	0xf3,0xc3
+
+
+
+
+.globl	_ecp_nistz256_select_w7
+.private_extern _ecp_nistz256_select_w7
+
+.p2align	5
+_ecp_nistz256_select_w7:
+	movdqa	L$One(%rip),%xmm8
+	movd	%edx,%xmm1
+
+	pxor	%xmm2,%xmm2
+	pxor	%xmm3,%xmm3
+	pxor	%xmm4,%xmm4
+	pxor	%xmm5,%xmm5
+
+	movdqa	%xmm8,%xmm0
+	pshufd	$0,%xmm1,%xmm1
+	movq	$64,%rax
+
+L$select_loop_sse_w7:
+	movdqa	%xmm8,%xmm15
+	paddd	%xmm0,%xmm8
+	movdqa	0(%rsi),%xmm9
+	movdqa	16(%rsi),%xmm10
+	pcmpeqd	%xmm1,%xmm15
+	movdqa	32(%rsi),%xmm11
+	movdqa	48(%rsi),%xmm12
+	leaq	64(%rsi),%rsi
+
+	pand	%xmm15,%xmm9
+	pand	%xmm15,%xmm10
+	por	%xmm9,%xmm2
+	pand	%xmm15,%xmm11
+	por	%xmm10,%xmm3
+	pand	%xmm15,%xmm12
+	por	%xmm11,%xmm4
+	prefetcht0	255(%rsi)
+	por	%xmm12,%xmm5
+
+	decq	%rax
+	jnz	L$select_loop_sse_w7
+
+	movdqu	%xmm2,0(%rdi)
+	movdqu	%xmm3,16(%rdi)
+	movdqu	%xmm4,32(%rdi)
+	movdqu	%xmm5,48(%rdi)
+	.byte	0xf3,0xc3
+
+.globl	_ecp_nistz256_avx2_select_w7
+.private_extern _ecp_nistz256_avx2_select_w7
+
+.p2align	5
+_ecp_nistz256_avx2_select_w7:
+.byte	0x0f,0x0b
+	.byte	0xf3,0xc3
+
+
+.p2align	5
+__ecp_nistz256_add_toq:
+	addq	0(%rbx),%r12
+	adcq	8(%rbx),%r13
+	movq	%r12,%rax
+	adcq	16(%rbx),%r8
+	adcq	24(%rbx),%r9
+	movq	%r13,%rbp
+	sbbq	%r11,%r11
+
+	subq	$-1,%r12
+	movq	%r8,%rcx
+	sbbq	%r14,%r13
+	sbbq	$0,%r8
+	movq	%r9,%r10
+	sbbq	%r15,%r9
+	testq	%r11,%r11
+
+	cmovzq	%rax,%r12
+	cmovzq	%rbp,%r13
+	movq	%r12,0(%rdi)
+	cmovzq	%rcx,%r8
+	movq	%r13,8(%rdi)
+	cmovzq	%r10,%r9
+	movq	%r8,16(%rdi)
+	movq	%r9,24(%rdi)
+
+	.byte	0xf3,0xc3
+
+
+
+.p2align	5
+__ecp_nistz256_sub_fromq:
+	subq	0(%rbx),%r12
+	sbbq	8(%rbx),%r13
+	movq	%r12,%rax
+	sbbq	16(%rbx),%r8
+	sbbq	24(%rbx),%r9
+	movq	%r13,%rbp
+	sbbq	%r11,%r11
+
+	addq	$-1,%r12
+	movq	%r8,%rcx
+	adcq	%r14,%r13
+	adcq	$0,%r8
+	movq	%r9,%r10
+	adcq	%r15,%r9
+	testq	%r11,%r11
+
+	cmovzq	%rax,%r12
+	cmovzq	%rbp,%r13
+	movq	%r12,0(%rdi)
+	cmovzq	%rcx,%r8
+	movq	%r13,8(%rdi)
+	cmovzq	%r10,%r9
+	movq	%r8,16(%rdi)
+	movq	%r9,24(%rdi)
+
+	.byte	0xf3,0xc3
+
+
+
+.p2align	5
+__ecp_nistz256_subq:
+	subq	%r12,%rax
+	sbbq	%r13,%rbp
+	movq	%rax,%r12
+	sbbq	%r8,%rcx
+	sbbq	%r9,%r10
+	movq	%rbp,%r13
+	sbbq	%r11,%r11
+
+	addq	$-1,%rax
+	movq	%rcx,%r8
+	adcq	%r14,%rbp
+	adcq	$0,%rcx
+	movq	%r10,%r9
+	adcq	%r15,%r10
+	testq	%r11,%r11
+
+	cmovnzq	%rax,%r12
+	cmovnzq	%rbp,%r13
+	cmovnzq	%rcx,%r8
+	cmovnzq	%r10,%r9
+
+	.byte	0xf3,0xc3
+
+
+
+.p2align	5
+__ecp_nistz256_mul_by_2q:
+	addq	%r12,%r12
+	adcq	%r13,%r13
+	movq	%r12,%rax
+	adcq	%r8,%r8
+	adcq	%r9,%r9
+	movq	%r13,%rbp
+	sbbq	%r11,%r11
+
+	subq	$-1,%r12
+	movq	%r8,%rcx
+	sbbq	%r14,%r13
+	sbbq	$0,%r8
+	movq	%r9,%r10
+	sbbq	%r15,%r9
+	testq	%r11,%r11
+
+	cmovzq	%rax,%r12
+	cmovzq	%rbp,%r13
+	movq	%r12,0(%rdi)
+	cmovzq	%rcx,%r8
+	movq	%r13,8(%rdi)
+	cmovzq	%r10,%r9
+	movq	%r8,16(%rdi)
+	movq	%r9,24(%rdi)
+
+	.byte	0xf3,0xc3
+
+.globl	_ecp_nistz256_point_double
+.private_extern _ecp_nistz256_point_double
+
+.p2align	5
+_ecp_nistz256_point_double:
+	pushq	%rbp
+	pushq	%rbx
+	pushq	%r12
+	pushq	%r13
+	pushq	%r14
+	pushq	%r15
+	subq	$160+8,%rsp
+
+L$point_double_shortcutq:
+	movdqu	0(%rsi),%xmm0
+	movq	%rsi,%rbx
+	movdqu	16(%rsi),%xmm1
+	movq	32+0(%rsi),%r12
+	movq	32+8(%rsi),%r13
+	movq	32+16(%rsi),%r8
+	movq	32+24(%rsi),%r9
+	movq	L$poly+8(%rip),%r14
+	movq	L$poly+24(%rip),%r15
+	movdqa	%xmm0,96(%rsp)
+	movdqa	%xmm1,96+16(%rsp)
+	leaq	32(%rdi),%r10
+	leaq	64(%rdi),%r11
+.byte	102,72,15,110,199
+.byte	102,73,15,110,202
+.byte	102,73,15,110,211
+
+	leaq	0(%rsp),%rdi
+	call	__ecp_nistz256_mul_by_2q
+
+	movq	64+0(%rsi),%rax
+	movq	64+8(%rsi),%r14
+	movq	64+16(%rsi),%r15
+	movq	64+24(%rsi),%r8
+	leaq	64-0(%rsi),%rsi
+	leaq	64(%rsp),%rdi
+	call	__ecp_nistz256_sqr_montq
+
+	movq	0+0(%rsp),%rax
+	movq	8+0(%rsp),%r14
+	leaq	0+0(%rsp),%rsi
+	movq	16+0(%rsp),%r15
+	movq	24+0(%rsp),%r8
+	leaq	0(%rsp),%rdi
+	call	__ecp_nistz256_sqr_montq
+
+	movq	32(%rbx),%rax
+	movq	64+0(%rbx),%r9
+	movq	64+8(%rbx),%r10
+	movq	64+16(%rbx),%r11
+	movq	64+24(%rbx),%r12
+	leaq	64-0(%rbx),%rsi
+	leaq	32(%rbx),%rbx
+.byte	102,72,15,126,215
+	call	__ecp_nistz256_mul_montq
+	call	__ecp_nistz256_mul_by_2q
+
+	movq	96+0(%rsp),%r12
+	movq	96+8(%rsp),%r13
+	leaq	64(%rsp),%rbx
+	movq	96+16(%rsp),%r8
+	movq	96+24(%rsp),%r9
+	leaq	32(%rsp),%rdi
+	call	__ecp_nistz256_add_toq
+
+	movq	96+0(%rsp),%r12
+	movq	96+8(%rsp),%r13
+	leaq	64(%rsp),%rbx
+	movq	96+16(%rsp),%r8
+	movq	96+24(%rsp),%r9
+	leaq	64(%rsp),%rdi
+	call	__ecp_nistz256_sub_fromq
+
+	movq	0+0(%rsp),%rax
+	movq	8+0(%rsp),%r14
+	leaq	0+0(%rsp),%rsi
+	movq	16+0(%rsp),%r15
+	movq	24+0(%rsp),%r8
+.byte	102,72,15,126,207
+	call	__ecp_nistz256_sqr_montq
+	xorq	%r9,%r9
+	movq	%r12,%rax
+	addq	$-1,%r12
+	movq	%r13,%r10
+	adcq	%rsi,%r13
+	movq	%r14,%rcx
+	adcq	$0,%r14
+	movq	%r15,%r8
+	adcq	%rbp,%r15
+	adcq	$0,%r9
+	xorq	%rsi,%rsi
+	testq	$1,%rax
+
+	cmovzq	%rax,%r12
+	cmovzq	%r10,%r13
+	cmovzq	%rcx,%r14
+	cmovzq	%r8,%r15
+	cmovzq	%rsi,%r9
+
+	movq	%r13,%rax
+	shrq	$1,%r12
+	shlq	$63,%rax
+	movq	%r14,%r10
+	shrq	$1,%r13
+	orq	%rax,%r12
+	shlq	$63,%r10
+	movq	%r15,%rcx
+	shrq	$1,%r14
+	orq	%r10,%r13
+	shlq	$63,%rcx
+	movq	%r12,0(%rdi)
+	shrq	$1,%r15
+	movq	%r13,8(%rdi)
+	shlq	$63,%r9
+	orq	%rcx,%r14
+	orq	%r9,%r15
+	movq	%r14,16(%rdi)
+	movq	%r15,24(%rdi)
+	movq	64(%rsp),%rax
+	leaq	64(%rsp),%rbx
+	movq	0+32(%rsp),%r9
+	movq	8+32(%rsp),%r10
+	leaq	0+32(%rsp),%rsi
+	movq	16+32(%rsp),%r11
+	movq	24+32(%rsp),%r12
+	leaq	32(%rsp),%rdi
+	call	__ecp_nistz256_mul_montq
+
+	leaq	128(%rsp),%rdi
+	call	__ecp_nistz256_mul_by_2q
+
+	leaq	32(%rsp),%rbx
+	leaq	32(%rsp),%rdi
+	call	__ecp_nistz256_add_toq
+
+	movq	96(%rsp),%rax
+	leaq	96(%rsp),%rbx
+	movq	0+0(%rsp),%r9
+	movq	8+0(%rsp),%r10
+	leaq	0+0(%rsp),%rsi
+	movq	16+0(%rsp),%r11
+	movq	24+0(%rsp),%r12
+	leaq	0(%rsp),%rdi
+	call	__ecp_nistz256_mul_montq
+
+	leaq	128(%rsp),%rdi
+	call	__ecp_nistz256_mul_by_2q
+
+	movq	0+32(%rsp),%rax
+	movq	8+32(%rsp),%r14
+	leaq	0+32(%rsp),%rsi
+	movq	16+32(%rsp),%r15
+	movq	24+32(%rsp),%r8
+.byte	102,72,15,126,199
+	call	__ecp_nistz256_sqr_montq
+
+	leaq	128(%rsp),%rbx
+	movq	%r14,%r8
+	movq	%r15,%r9
+	movq	%rsi,%r14
+	movq	%rbp,%r15
+	call	__ecp_nistz256_sub_fromq
+
+	movq	0+0(%rsp),%rax
+	movq	0+8(%rsp),%rbp
+	movq	0+16(%rsp),%rcx
+	movq	0+24(%rsp),%r10
+	leaq	0(%rsp),%rdi
+	call	__ecp_nistz256_subq
+
+	movq	32(%rsp),%rax
+	leaq	32(%rsp),%rbx
+	movq	%r12,%r14
+	xorl	%ecx,%ecx
+	movq	%r12,0+0(%rsp)
+	movq	%r13,%r10
+	movq	%r13,0+8(%rsp)
+	cmovzq	%r8,%r11
+	movq	%r8,0+16(%rsp)
+	leaq	0-0(%rsp),%rsi
+	cmovzq	%r9,%r12
+	movq	%r9,0+24(%rsp)
+	movq	%r14,%r9
+	leaq	0(%rsp),%rdi
+	call	__ecp_nistz256_mul_montq
+
+.byte	102,72,15,126,203
+.byte	102,72,15,126,207
+	call	__ecp_nistz256_sub_fromq
+
+	addq	$160+8,%rsp
+	popq	%r15
+	popq	%r14
+	popq	%r13
+	popq	%r12
+	popq	%rbx
+	popq	%rbp
+	.byte	0xf3,0xc3
+
+.globl	_ecp_nistz256_point_add
+.private_extern _ecp_nistz256_point_add
+
+.p2align	5
+_ecp_nistz256_point_add:
+	pushq	%rbp
+	pushq	%rbx
+	pushq	%r12
+	pushq	%r13
+	pushq	%r14
+	pushq	%r15
+	subq	$576+8,%rsp
+
+	movdqu	0(%rsi),%xmm0
+	movdqu	16(%rsi),%xmm1
+	movdqu	32(%rsi),%xmm2
+	movdqu	48(%rsi),%xmm3
+	movdqu	64(%rsi),%xmm4
+	movdqu	80(%rsi),%xmm5
+	movq	%rsi,%rbx
+	movq	%rdx,%rsi
+	movdqa	%xmm0,384(%rsp)
+	movdqa	%xmm1,384+16(%rsp)
+	por	%xmm0,%xmm1
+	movdqa	%xmm2,416(%rsp)
+	movdqa	%xmm3,416+16(%rsp)
+	por	%xmm2,%xmm3
+	movdqa	%xmm4,448(%rsp)
+	movdqa	%xmm5,448+16(%rsp)
+	por	%xmm1,%xmm3
+
+	movdqu	0(%rsi),%xmm0
+	pshufd	$0xb1,%xmm3,%xmm5
+	movdqu	16(%rsi),%xmm1
+	movdqu	32(%rsi),%xmm2
+	por	%xmm3,%xmm5
+	movdqu	48(%rsi),%xmm3
+	movq	64+0(%rsi),%rax
+	movq	64+8(%rsi),%r14
+	movq	64+16(%rsi),%r15
+	movq	64+24(%rsi),%r8
+	movdqa	%xmm0,480(%rsp)
+	pshufd	$0x1e,%xmm5,%xmm4
+	movdqa	%xmm1,480+16(%rsp)
+	por	%xmm0,%xmm1
+.byte	102,72,15,110,199
+	movdqa	%xmm2,512(%rsp)
+	movdqa	%xmm3,512+16(%rsp)
+	por	%xmm2,%xmm3
+	por	%xmm4,%xmm5
+	pxor	%xmm4,%xmm4
+	por	%xmm1,%xmm3
+
+	leaq	64-0(%rsi),%rsi
+	movq	%rax,544+0(%rsp)
+	movq	%r14,544+8(%rsp)
+	movq	%r15,544+16(%rsp)
+	movq	%r8,544+24(%rsp)
+	leaq	96(%rsp),%rdi
+	call	__ecp_nistz256_sqr_montq
+
+	pcmpeqd	%xmm4,%xmm5
+	pshufd	$0xb1,%xmm3,%xmm4
+	por	%xmm3,%xmm4
+	pshufd	$0,%xmm5,%xmm5
+	pshufd	$0x1e,%xmm4,%xmm3
+	por	%xmm3,%xmm4
+	pxor	%xmm3,%xmm3
+	pcmpeqd	%xmm3,%xmm4
+	pshufd	$0,%xmm4,%xmm4
+	movq	64+0(%rbx),%rax
+	movq	64+8(%rbx),%r14
+	movq	64+16(%rbx),%r15
+	movq	64+24(%rbx),%r8
+.byte	102,72,15,110,203
+
+	leaq	64-0(%rbx),%rsi
+	leaq	32(%rsp),%rdi
+	call	__ecp_nistz256_sqr_montq
+
+	movq	544(%rsp),%rax
+	leaq	544(%rsp),%rbx
+	movq	0+96(%rsp),%r9
+	movq	8+96(%rsp),%r10
+	leaq	0+96(%rsp),%rsi
+	movq	16+96(%rsp),%r11
+	movq	24+96(%rsp),%r12
+	leaq	224(%rsp),%rdi
+	call	__ecp_nistz256_mul_montq
+
+	movq	448(%rsp),%rax
+	leaq	448(%rsp),%rbx
+	movq	0+32(%rsp),%r9
+	movq	8+32(%rsp),%r10
+	leaq	0+32(%rsp),%rsi
+	movq	16+32(%rsp),%r11
+	movq	24+32(%rsp),%r12
+	leaq	256(%rsp),%rdi
+	call	__ecp_nistz256_mul_montq
+
+	movq	416(%rsp),%rax
+	leaq	416(%rsp),%rbx
+	movq	0+224(%rsp),%r9
+	movq	8+224(%rsp),%r10
+	leaq	0+224(%rsp),%rsi
+	movq	16+224(%rsp),%r11
+	movq	24+224(%rsp),%r12
+	leaq	224(%rsp),%rdi
+	call	__ecp_nistz256_mul_montq
+
+	movq	512(%rsp),%rax
+	leaq	512(%rsp),%rbx
+	movq	0+256(%rsp),%r9
+	movq	8+256(%rsp),%r10
+	leaq	0+256(%rsp),%rsi
+	movq	16+256(%rsp),%r11
+	movq	24+256(%rsp),%r12
+	leaq	256(%rsp),%rdi
+	call	__ecp_nistz256_mul_montq
+
+	leaq	224(%rsp),%rbx
+	leaq	64(%rsp),%rdi
+	call	__ecp_nistz256_sub_fromq
+
+	orq	%r13,%r12
+	movdqa	%xmm4,%xmm2
+	orq	%r8,%r12
+	orq	%r9,%r12
+	por	%xmm5,%xmm2
+.byte	102,73,15,110,220
+
+	movq	384(%rsp),%rax
+	leaq	384(%rsp),%rbx
+	movq	0+96(%rsp),%r9
+	movq	8+96(%rsp),%r10
+	leaq	0+96(%rsp),%rsi
+	movq	16+96(%rsp),%r11
+	movq	24+96(%rsp),%r12
+	leaq	160(%rsp),%rdi
+	call	__ecp_nistz256_mul_montq
+
+	movq	480(%rsp),%rax
+	leaq	480(%rsp),%rbx
+	movq	0+32(%rsp),%r9
+	movq	8+32(%rsp),%r10
+	leaq	0+32(%rsp),%rsi
+	movq	16+32(%rsp),%r11
+	movq	24+32(%rsp),%r12
+	leaq	192(%rsp),%rdi
+	call	__ecp_nistz256_mul_montq
+
+	leaq	160(%rsp),%rbx
+	leaq	0(%rsp),%rdi
+	call	__ecp_nistz256_sub_fromq
+
+	orq	%r13,%r12
+	orq	%r8,%r12
+	orq	%r9,%r12
+
+.byte	0x3e
+	jnz	L$add_proceedq
+.byte	102,73,15,126,208
+.byte	102,73,15,126,217
+	testq	%r8,%r8
+	jnz	L$add_proceedq
+	testq	%r9,%r9
+	jz	L$add_doubleq
+
+.byte	102,72,15,126,199
+	pxor	%xmm0,%xmm0
+	movdqu	%xmm0,0(%rdi)
+	movdqu	%xmm0,16(%rdi)
+	movdqu	%xmm0,32(%rdi)
+	movdqu	%xmm0,48(%rdi)
+	movdqu	%xmm0,64(%rdi)
+	movdqu	%xmm0,80(%rdi)
+	jmp	L$add_doneq
+
+.p2align	5
+L$add_doubleq:
+.byte	102,72,15,126,206
+.byte	102,72,15,126,199
+	addq	$416,%rsp
+	jmp	L$point_double_shortcutq
+
+.p2align	5
+L$add_proceedq:
+	movq	0+64(%rsp),%rax
+	movq	8+64(%rsp),%r14
+	leaq	0+64(%rsp),%rsi
+	movq	16+64(%rsp),%r15
+	movq	24+64(%rsp),%r8
+	leaq	96(%rsp),%rdi
+	call	__ecp_nistz256_sqr_montq
+
+	movq	448(%rsp),%rax
+	leaq	448(%rsp),%rbx
+	movq	0+0(%rsp),%r9
+	movq	8+0(%rsp),%r10
+	leaq	0+0(%rsp),%rsi
+	movq	16+0(%rsp),%r11
+	movq	24+0(%rsp),%r12
+	leaq	352(%rsp),%rdi
+	call	__ecp_nistz256_mul_montq
+
+	movq	0+0(%rsp),%rax
+	movq	8+0(%rsp),%r14
+	leaq	0+0(%rsp),%rsi
+	movq	16+0(%rsp),%r15
+	movq	24+0(%rsp),%r8
+	leaq	32(%rsp),%rdi
+	call	__ecp_nistz256_sqr_montq
+
+	movq	544(%rsp),%rax
+	leaq	544(%rsp),%rbx
+	movq	0+352(%rsp),%r9
+	movq	8+352(%rsp),%r10
+	leaq	0+352(%rsp),%rsi
+	movq	16+352(%rsp),%r11
+	movq	24+352(%rsp),%r12
+	leaq	352(%rsp),%rdi
+	call	__ecp_nistz256_mul_montq
+
+	movq	0(%rsp),%rax
+	leaq	0(%rsp),%rbx
+	movq	0+32(%rsp),%r9
+	movq	8+32(%rsp),%r10
+	leaq	0+32(%rsp),%rsi
+	movq	16+32(%rsp),%r11
+	movq	24+32(%rsp),%r12
+	leaq	128(%rsp),%rdi
+	call	__ecp_nistz256_mul_montq
+
+	movq	160(%rsp),%rax
+	leaq	160(%rsp),%rbx
+	movq	0+32(%rsp),%r9
+	movq	8+32(%rsp),%r10
+	leaq	0+32(%rsp),%rsi
+	movq	16+32(%rsp),%r11
+	movq	24+32(%rsp),%r12
+	leaq	192(%rsp),%rdi
+	call	__ecp_nistz256_mul_montq
+
+
+
+
+	addq	%r12,%r12
+	leaq	96(%rsp),%rsi
+	adcq	%r13,%r13
+	movq	%r12,%rax
+	adcq	%r8,%r8
+	adcq	%r9,%r9
+	movq	%r13,%rbp
+	sbbq	%r11,%r11
+
+	subq	$-1,%r12
+	movq	%r8,%rcx
+	sbbq	%r14,%r13
+	sbbq	$0,%r8
+	movq	%r9,%r10
+	sbbq	%r15,%r9
+	testq	%r11,%r11
+
+	cmovzq	%rax,%r12
+	movq	0(%rsi),%rax
+	cmovzq	%rbp,%r13
+	movq	8(%rsi),%rbp
+	cmovzq	%rcx,%r8
+	movq	16(%rsi),%rcx
+	cmovzq	%r10,%r9
+	movq	24(%rsi),%r10
+
+	call	__ecp_nistz256_subq
+
+	leaq	128(%rsp),%rbx
+	leaq	288(%rsp),%rdi
+	call	__ecp_nistz256_sub_fromq
+
+	movq	192+0(%rsp),%rax
+	movq	192+8(%rsp),%rbp
+	movq	192+16(%rsp),%rcx
+	movq	192+24(%rsp),%r10
+	leaq	320(%rsp),%rdi
+
+	call	__ecp_nistz256_subq
+
+	movq	%r12,0(%rdi)
+	movq	%r13,8(%rdi)
+	movq	%r8,16(%rdi)
+	movq	%r9,24(%rdi)
+	movq	128(%rsp),%rax
+	leaq	128(%rsp),%rbx
+	movq	0+224(%rsp),%r9
+	movq	8+224(%rsp),%r10
+	leaq	0+224(%rsp),%rsi
+	movq	16+224(%rsp),%r11
+	movq	24+224(%rsp),%r12
+	leaq	256(%rsp),%rdi
+	call	__ecp_nistz256_mul_montq
+
+	movq	320(%rsp),%rax
+	leaq	320(%rsp),%rbx
+	movq	0+64(%rsp),%r9
+	movq	8+64(%rsp),%r10
+	leaq	0+64(%rsp),%rsi
+	movq	16+64(%rsp),%r11
+	movq	24+64(%rsp),%r12
+	leaq	320(%rsp),%rdi
+	call	__ecp_nistz256_mul_montq
+
+	leaq	256(%rsp),%rbx
+	leaq	320(%rsp),%rdi
+	call	__ecp_nistz256_sub_fromq
+
+.byte	102,72,15,126,199
+
+	movdqa	%xmm5,%xmm0
+	movdqa	%xmm5,%xmm1
+	pandn	352(%rsp),%xmm0
+	movdqa	%xmm5,%xmm2
+	pandn	352+16(%rsp),%xmm1
+	movdqa	%xmm5,%xmm3
+	pand	544(%rsp),%xmm2
+	pand	544+16(%rsp),%xmm3
+	por	%xmm0,%xmm2
+	por	%xmm1,%xmm3
+
+	movdqa	%xmm4,%xmm0
+	movdqa	%xmm4,%xmm1
+	pandn	%xmm2,%xmm0
+	movdqa	%xmm4,%xmm2
+	pandn	%xmm3,%xmm1
+	movdqa	%xmm4,%xmm3
+	pand	448(%rsp),%xmm2
+	pand	448+16(%rsp),%xmm3
+	por	%xmm0,%xmm2
+	por	%xmm1,%xmm3
+	movdqu	%xmm2,64(%rdi)
+	movdqu	%xmm3,80(%rdi)
+
+	movdqa	%xmm5,%xmm0
+	movdqa	%xmm5,%xmm1
+	pandn	288(%rsp),%xmm0
+	movdqa	%xmm5,%xmm2
+	pandn	288+16(%rsp),%xmm1
+	movdqa	%xmm5,%xmm3
+	pand	480(%rsp),%xmm2
+	pand	480+16(%rsp),%xmm3
+	por	%xmm0,%xmm2
+	por	%xmm1,%xmm3
+
+	movdqa	%xmm4,%xmm0
+	movdqa	%xmm4,%xmm1
+	pandn	%xmm2,%xmm0
+	movdqa	%xmm4,%xmm2
+	pandn	%xmm3,%xmm1
+	movdqa	%xmm4,%xmm3
+	pand	384(%rsp),%xmm2
+	pand	384+16(%rsp),%xmm3
+	por	%xmm0,%xmm2
+	por	%xmm1,%xmm3
+	movdqu	%xmm2,0(%rdi)
+	movdqu	%xmm3,16(%rdi)
+
+	movdqa	%xmm5,%xmm0
+	movdqa	%xmm5,%xmm1
+	pandn	320(%rsp),%xmm0
+	movdqa	%xmm5,%xmm2
+	pandn	320+16(%rsp),%xmm1
+	movdqa	%xmm5,%xmm3
+	pand	512(%rsp),%xmm2
+	pand	512+16(%rsp),%xmm3
+	por	%xmm0,%xmm2
+	por	%xmm1,%xmm3
+
+	movdqa	%xmm4,%xmm0
+	movdqa	%xmm4,%xmm1
+	pandn	%xmm2,%xmm0
+	movdqa	%xmm4,%xmm2
+	pandn	%xmm3,%xmm1
+	movdqa	%xmm4,%xmm3
+	pand	416(%rsp),%xmm2
+	pand	416+16(%rsp),%xmm3
+	por	%xmm0,%xmm2
+	por	%xmm1,%xmm3
+	movdqu	%xmm2,32(%rdi)
+	movdqu	%xmm3,48(%rdi)
+
+L$add_doneq:
+	addq	$576+8,%rsp
+	popq	%r15
+	popq	%r14
+	popq	%r13
+	popq	%r12
+	popq	%rbx
+	popq	%rbp
+	.byte	0xf3,0xc3
+
+.globl	_ecp_nistz256_point_add_affine
+.private_extern _ecp_nistz256_point_add_affine
+
+.p2align	5
+_ecp_nistz256_point_add_affine:
+	pushq	%rbp
+	pushq	%rbx
+	pushq	%r12
+	pushq	%r13
+	pushq	%r14
+	pushq	%r15
+	subq	$480+8,%rsp
+
+	movdqu	0(%rsi),%xmm0
+	movq	%rdx,%rbx
+	movdqu	16(%rsi),%xmm1
+	movdqu	32(%rsi),%xmm2
+	movdqu	48(%rsi),%xmm3
+	movdqu	64(%rsi),%xmm4
+	movdqu	80(%rsi),%xmm5
+	movq	64+0(%rsi),%rax
+	movq	64+8(%rsi),%r14
+	movq	64+16(%rsi),%r15
+	movq	64+24(%rsi),%r8
+	movdqa	%xmm0,320(%rsp)
+	movdqa	%xmm1,320+16(%rsp)
+	por	%xmm0,%xmm1
+	movdqa	%xmm2,352(%rsp)
+	movdqa	%xmm3,352+16(%rsp)
+	por	%xmm2,%xmm3
+	movdqa	%xmm4,384(%rsp)
+	movdqa	%xmm5,384+16(%rsp)
+	por	%xmm1,%xmm3
+
+	movdqu	0(%rbx),%xmm0
+	pshufd	$0xb1,%xmm3,%xmm5
+	movdqu	16(%rbx),%xmm1
+	movdqu	32(%rbx),%xmm2
+	por	%xmm3,%xmm5
+	movdqu	48(%rbx),%xmm3
+	movdqa	%xmm0,416(%rsp)
+	pshufd	$0x1e,%xmm5,%xmm4
+	movdqa	%xmm1,416+16(%rsp)
+	por	%xmm0,%xmm1
+.byte	102,72,15,110,199
+	movdqa	%xmm2,448(%rsp)
+	movdqa	%xmm3,448+16(%rsp)
+	por	%xmm2,%xmm3
+	por	%xmm4,%xmm5
+	pxor	%xmm4,%xmm4
+	por	%xmm1,%xmm3
+
+	leaq	64-0(%rsi),%rsi
+	leaq	32(%rsp),%rdi
+	call	__ecp_nistz256_sqr_montq
+
+	pcmpeqd	%xmm4,%xmm5
+	pshufd	$0xb1,%xmm3,%xmm4
+	movq	0(%rbx),%rax
+
+	movq	%r12,%r9
+	por	%xmm3,%xmm4
+	pshufd	$0,%xmm5,%xmm5
+	pshufd	$0x1e,%xmm4,%xmm3
+	movq	%r13,%r10
+	por	%xmm3,%xmm4
+	pxor	%xmm3,%xmm3
+	movq	%r14,%r11
+	pcmpeqd	%xmm3,%xmm4
+	pshufd	$0,%xmm4,%xmm4
+
+	leaq	32-0(%rsp),%rsi
+	movq	%r15,%r12
+	leaq	0(%rsp),%rdi
+	call	__ecp_nistz256_mul_montq
+
+	leaq	320(%rsp),%rbx
+	leaq	64(%rsp),%rdi
+	call	__ecp_nistz256_sub_fromq
+
+	movq	384(%rsp),%rax
+	leaq	384(%rsp),%rbx
+	movq	0+32(%rsp),%r9
+	movq	8+32(%rsp),%r10
+	leaq	0+32(%rsp),%rsi
+	movq	16+32(%rsp),%r11
+	movq	24+32(%rsp),%r12
+	leaq	32(%rsp),%rdi
+	call	__ecp_nistz256_mul_montq
+
+	movq	384(%rsp),%rax
+	leaq	384(%rsp),%rbx
+	movq	0+64(%rsp),%r9
+	movq	8+64(%rsp),%r10
+	leaq	0+64(%rsp),%rsi
+	movq	16+64(%rsp),%r11
+	movq	24+64(%rsp),%r12
+	leaq	288(%rsp),%rdi
+	call	__ecp_nistz256_mul_montq
+
+	movq	448(%rsp),%rax
+	leaq	448(%rsp),%rbx
+	movq	0+32(%rsp),%r9
+	movq	8+32(%rsp),%r10
+	leaq	0+32(%rsp),%rsi
+	movq	16+32(%rsp),%r11
+	movq	24+32(%rsp),%r12
+	leaq	32(%rsp),%rdi
+	call	__ecp_nistz256_mul_montq
+
+	leaq	352(%rsp),%rbx
+	leaq	96(%rsp),%rdi
+	call	__ecp_nistz256_sub_fromq
+
+	movq	0+64(%rsp),%rax
+	movq	8+64(%rsp),%r14
+	leaq	0+64(%rsp),%rsi
+	movq	16+64(%rsp),%r15
+	movq	24+64(%rsp),%r8
+	leaq	128(%rsp),%rdi
+	call	__ecp_nistz256_sqr_montq
+
+	movq	0+96(%rsp),%rax
+	movq	8+96(%rsp),%r14
+	leaq	0+96(%rsp),%rsi
+	movq	16+96(%rsp),%r15
+	movq	24+96(%rsp),%r8
+	leaq	192(%rsp),%rdi
+	call	__ecp_nistz256_sqr_montq
+
+	movq	128(%rsp),%rax
+	leaq	128(%rsp),%rbx
+	movq	0+64(%rsp),%r9
+	movq	8+64(%rsp),%r10
+	leaq	0+64(%rsp),%rsi
+	movq	16+64(%rsp),%r11
+	movq	24+64(%rsp),%r12
+	leaq	160(%rsp),%rdi
+	call	__ecp_nistz256_mul_montq
+
+	movq	320(%rsp),%rax
+	leaq	320(%rsp),%rbx
+	movq	0+128(%rsp),%r9
+	movq	8+128(%rsp),%r10
+	leaq	0+128(%rsp),%rsi
+	movq	16+128(%rsp),%r11
+	movq	24+128(%rsp),%r12
+	leaq	0(%rsp),%rdi
+	call	__ecp_nistz256_mul_montq
+
+
+
+
+	addq	%r12,%r12
+	leaq	192(%rsp),%rsi
+	adcq	%r13,%r13
+	movq	%r12,%rax
+	adcq	%r8,%r8
+	adcq	%r9,%r9
+	movq	%r13,%rbp
+	sbbq	%r11,%r11
+
+	subq	$-1,%r12
+	movq	%r8,%rcx
+	sbbq	%r14,%r13
+	sbbq	$0,%r8
+	movq	%r9,%r10
+	sbbq	%r15,%r9
+	testq	%r11,%r11
+
+	cmovzq	%rax,%r12
+	movq	0(%rsi),%rax
+	cmovzq	%rbp,%r13
+	movq	8(%rsi),%rbp
+	cmovzq	%rcx,%r8
+	movq	16(%rsi),%rcx
+	cmovzq	%r10,%r9
+	movq	24(%rsi),%r10
+
+	call	__ecp_nistz256_subq
+
+	leaq	160(%rsp),%rbx
+	leaq	224(%rsp),%rdi
+	call	__ecp_nistz256_sub_fromq
+
+	movq	0+0(%rsp),%rax
+	movq	0+8(%rsp),%rbp
+	movq	0+16(%rsp),%rcx
+	movq	0+24(%rsp),%r10
+	leaq	64(%rsp),%rdi
+
+	call	__ecp_nistz256_subq
+
+	movq	%r12,0(%rdi)
+	movq	%r13,8(%rdi)
+	movq	%r8,16(%rdi)
+	movq	%r9,24(%rdi)
+	movq	352(%rsp),%rax
+	leaq	352(%rsp),%rbx
+	movq	0+160(%rsp),%r9
+	movq	8+160(%rsp),%r10
+	leaq	0+160(%rsp),%rsi
+	movq	16+160(%rsp),%r11
+	movq	24+160(%rsp),%r12
+	leaq	32(%rsp),%rdi
+	call	__ecp_nistz256_mul_montq
+
+	movq	96(%rsp),%rax
+	leaq	96(%rsp),%rbx
+	movq	0+64(%rsp),%r9
+	movq	8+64(%rsp),%r10
+	leaq	0+64(%rsp),%rsi
+	movq	16+64(%rsp),%r11
+	movq	24+64(%rsp),%r12
+	leaq	64(%rsp),%rdi
+	call	__ecp_nistz256_mul_montq
+
+	leaq	32(%rsp),%rbx
+	leaq	256(%rsp),%rdi
+	call	__ecp_nistz256_sub_fromq
+
+.byte	102,72,15,126,199
+
+	movdqa	%xmm5,%xmm0
+	movdqa	%xmm5,%xmm1
+	pandn	288(%rsp),%xmm0
+	movdqa	%xmm5,%xmm2
+	pandn	288+16(%rsp),%xmm1
+	movdqa	%xmm5,%xmm3
+	pand	L$ONE_mont(%rip),%xmm2
+	pand	L$ONE_mont+16(%rip),%xmm3
+	por	%xmm0,%xmm2
+	por	%xmm1,%xmm3
+
+	movdqa	%xmm4,%xmm0
+	movdqa	%xmm4,%xmm1
+	pandn	%xmm2,%xmm0
+	movdqa	%xmm4,%xmm2
+	pandn	%xmm3,%xmm1
+	movdqa	%xmm4,%xmm3
+	pand	384(%rsp),%xmm2
+	pand	384+16(%rsp),%xmm3
+	por	%xmm0,%xmm2
+	por	%xmm1,%xmm3
+	movdqu	%xmm2,64(%rdi)
+	movdqu	%xmm3,80(%rdi)
+
+	movdqa	%xmm5,%xmm0
+	movdqa	%xmm5,%xmm1
+	pandn	224(%rsp),%xmm0
+	movdqa	%xmm5,%xmm2
+	pandn	224+16(%rsp),%xmm1
+	movdqa	%xmm5,%xmm3
+	pand	416(%rsp),%xmm2
+	pand	416+16(%rsp),%xmm3
+	por	%xmm0,%xmm2
+	por	%xmm1,%xmm3
+
+	movdqa	%xmm4,%xmm0
+	movdqa	%xmm4,%xmm1
+	pandn	%xmm2,%xmm0
+	movdqa	%xmm4,%xmm2
+	pandn	%xmm3,%xmm1
+	movdqa	%xmm4,%xmm3
+	pand	320(%rsp),%xmm2
+	pand	320+16(%rsp),%xmm3
+	por	%xmm0,%xmm2
+	por	%xmm1,%xmm3
+	movdqu	%xmm2,0(%rdi)
+	movdqu	%xmm3,16(%rdi)
+
+	movdqa	%xmm5,%xmm0
+	movdqa	%xmm5,%xmm1
+	pandn	256(%rsp),%xmm0
+	movdqa	%xmm5,%xmm2
+	pandn	256+16(%rsp),%xmm1
+	movdqa	%xmm5,%xmm3
+	pand	448(%rsp),%xmm2
+	pand	448+16(%rsp),%xmm3
+	por	%xmm0,%xmm2
+	por	%xmm1,%xmm3
+
+	movdqa	%xmm4,%xmm0
+	movdqa	%xmm4,%xmm1
+	pandn	%xmm2,%xmm0
+	movdqa	%xmm4,%xmm2
+	pandn	%xmm3,%xmm1
+	movdqa	%xmm4,%xmm3
+	pand	352(%rsp),%xmm2
+	pand	352+16(%rsp),%xmm3
+	por	%xmm0,%xmm2
+	por	%xmm1,%xmm3
+	movdqu	%xmm2,32(%rdi)
+	movdqu	%xmm3,48(%rdi)
+
+	addq	$480+8,%rsp
+	popq	%r15
+	popq	%r14
+	popq	%r13
+	popq	%r12
+	popq	%rbx
+	popq	%rbp
+	.byte	0xf3,0xc3
+
+#endif
diff --git a/packager/third_party/boringssl/mac-x86_64/crypto/md5/md5-x86_64.S b/packager/third_party/boringssl/mac-x86_64/crypto/md5/md5-x86_64.S
index 1e61479bc4..16fd2ccef8 100644
--- a/packager/third_party/boringssl/mac-x86_64/crypto/md5/md5-x86_64.S
+++ b/packager/third_party/boringssl/mac-x86_64/crypto/md5/md5-x86_64.S
@@ -495,14 +495,14 @@ L$loop:
 	movl	%ecx,%r11d
 	addl	%ecx,%ebx
 	movl	0(%rsi),%r10d
-	movl	$4294967295,%r11d
+	movl	$0xffffffff,%r11d
 	xorl	%edx,%r11d
 	leal	-198630844(%rax,%r10,1),%eax
 	orl	%ebx,%r11d
 	xorl	%ecx,%r11d
 	addl	%r11d,%eax
 	movl	28(%rsi),%r10d
-	movl	$4294967295,%r11d
+	movl	$0xffffffff,%r11d
 	roll	$6,%eax
 	xorl	%ecx,%r11d
 	addl	%ebx,%eax
@@ -511,7 +511,7 @@ L$loop:
 	xorl	%ebx,%r11d
 	addl	%r11d,%edx
 	movl	56(%rsi),%r10d
-	movl	$4294967295,%r11d
+	movl	$0xffffffff,%r11d
 	roll	$10,%edx
 	xorl	%ebx,%r11d
 	addl	%eax,%edx
@@ -520,7 +520,7 @@ L$loop:
 	xorl	%eax,%r11d
 	addl	%r11d,%ecx
 	movl	20(%rsi),%r10d
-	movl	$4294967295,%r11d
+	movl	$0xffffffff,%r11d
 	roll	$15,%ecx
 	xorl	%eax,%r11d
 	addl	%edx,%ecx
@@ -529,7 +529,7 @@ L$loop:
 	xorl	%edx,%r11d
 	addl	%r11d,%ebx
 	movl	48(%rsi),%r10d
-	movl	$4294967295,%r11d
+	movl	$0xffffffff,%r11d
 	roll	$21,%ebx
 	xorl	%edx,%r11d
 	addl	%ecx,%ebx
@@ -538,7 +538,7 @@ L$loop:
 	xorl	%ecx,%r11d
 	addl	%r11d,%eax
 	movl	12(%rsi),%r10d
-	movl	$4294967295,%r11d
+	movl	$0xffffffff,%r11d
 	roll	$6,%eax
 	xorl	%ecx,%r11d
 	addl	%ebx,%eax
@@ -547,7 +547,7 @@ L$loop:
 	xorl	%ebx,%r11d
 	addl	%r11d,%edx
 	movl	40(%rsi),%r10d
-	movl	$4294967295,%r11d
+	movl	$0xffffffff,%r11d
 	roll	$10,%edx
 	xorl	%ebx,%r11d
 	addl	%eax,%edx
@@ -556,7 +556,7 @@ L$loop:
 	xorl	%eax,%r11d
 	addl	%r11d,%ecx
 	movl	4(%rsi),%r10d
-	movl	$4294967295,%r11d
+	movl	$0xffffffff,%r11d
 	roll	$15,%ecx
 	xorl	%eax,%r11d
 	addl	%edx,%ecx
@@ -565,7 +565,7 @@ L$loop:
 	xorl	%edx,%r11d
 	addl	%r11d,%ebx
 	movl	32(%rsi),%r10d
-	movl	$4294967295,%r11d
+	movl	$0xffffffff,%r11d
 	roll	$21,%ebx
 	xorl	%edx,%r11d
 	addl	%ecx,%ebx
@@ -574,7 +574,7 @@ L$loop:
 	xorl	%ecx,%r11d
 	addl	%r11d,%eax
 	movl	60(%rsi),%r10d
-	movl	$4294967295,%r11d
+	movl	$0xffffffff,%r11d
 	roll	$6,%eax
 	xorl	%ecx,%r11d
 	addl	%ebx,%eax
@@ -583,7 +583,7 @@ L$loop:
 	xorl	%ebx,%r11d
 	addl	%r11d,%edx
 	movl	24(%rsi),%r10d
-	movl	$4294967295,%r11d
+	movl	$0xffffffff,%r11d
 	roll	$10,%edx
 	xorl	%ebx,%r11d
 	addl	%eax,%edx
@@ -592,7 +592,7 @@ L$loop:
 	xorl	%eax,%r11d
 	addl	%r11d,%ecx
 	movl	52(%rsi),%r10d
-	movl	$4294967295,%r11d
+	movl	$0xffffffff,%r11d
 	roll	$15,%ecx
 	xorl	%eax,%r11d
 	addl	%edx,%ecx
@@ -601,7 +601,7 @@ L$loop:
 	xorl	%edx,%r11d
 	addl	%r11d,%ebx
 	movl	16(%rsi),%r10d
-	movl	$4294967295,%r11d
+	movl	$0xffffffff,%r11d
 	roll	$21,%ebx
 	xorl	%edx,%r11d
 	addl	%ecx,%ebx
@@ -610,7 +610,7 @@ L$loop:
 	xorl	%ecx,%r11d
 	addl	%r11d,%eax
 	movl	44(%rsi),%r10d
-	movl	$4294967295,%r11d
+	movl	$0xffffffff,%r11d
 	roll	$6,%eax
 	xorl	%ecx,%r11d
 	addl	%ebx,%eax
@@ -619,7 +619,7 @@ L$loop:
 	xorl	%ebx,%r11d
 	addl	%r11d,%edx
 	movl	8(%rsi),%r10d
-	movl	$4294967295,%r11d
+	movl	$0xffffffff,%r11d
 	roll	$10,%edx
 	xorl	%ebx,%r11d
 	addl	%eax,%edx
@@ -628,7 +628,7 @@ L$loop:
 	xorl	%eax,%r11d
 	addl	%r11d,%ecx
 	movl	36(%rsi),%r10d
-	movl	$4294967295,%r11d
+	movl	$0xffffffff,%r11d
 	roll	$15,%ecx
 	xorl	%eax,%r11d
 	addl	%edx,%ecx
@@ -637,7 +637,7 @@ L$loop:
 	xorl	%edx,%r11d
 	addl	%r11d,%ebx
 	movl	0(%rsi),%r10d
-	movl	$4294967295,%r11d
+	movl	$0xffffffff,%r11d
 	roll	$21,%ebx
 	xorl	%edx,%r11d
 	addl	%ecx,%ebx
diff --git a/packager/third_party/boringssl/mac-x86_64/crypto/modes/ghash-x86_64.S b/packager/third_party/boringssl/mac-x86_64/crypto/modes/ghash-x86_64.S
index 305a91cb60..1072c7fcd3 100644
--- a/packager/third_party/boringssl/mac-x86_64/crypto/modes/ghash-x86_64.S
+++ b/packager/third_party/boringssl/mac-x86_64/crypto/modes/ghash-x86_64.S
@@ -22,14 +22,14 @@ L$gmult_prologue:
 	movq	$14,%rcx
 	movq	8(%rsi,%rax,1),%r8
 	movq	(%rsi,%rax,1),%r9
-	andb	$240,%bl
+	andb	$0xf0,%bl
 	movq	%r8,%rdx
 	jmp	L$oop1
 
 .p2align	4
 L$oop1:
 	shrq	$4,%r8
-	andq	$15,%rdx
+	andq	$0xf,%rdx
 	movq	%r9,%r10
 	movb	(%rdi,%rcx,1),%al
 	shrq	$4,%r9
@@ -45,13 +45,13 @@ L$oop1:
 	js	L$break1
 
 	shrq	$4,%r8
-	andq	$15,%rdx
+	andq	$0xf,%rdx
 	movq	%r9,%r10
 	shrq	$4,%r9
 	xorq	8(%rsi,%rax,1),%r8
 	shlq	$60,%r10
 	xorq	(%rsi,%rax,1),%r9
-	andb	$240,%bl
+	andb	$0xf0,%bl
 	xorq	(%r11,%rdx,8),%r9
 	movq	%r8,%rdx
 	xorq	%r10,%r8
@@ -60,19 +60,19 @@ L$oop1:
 .p2align	4
 L$break1:
 	shrq	$4,%r8
-	andq	$15,%rdx
+	andq	$0xf,%rdx
 	movq	%r9,%r10
 	shrq	$4,%r9
 	xorq	8(%rsi,%rax,1),%r8
 	shlq	$60,%r10
 	xorq	(%rsi,%rax,1),%r9
-	andb	$240,%bl
+	andb	$0xf0,%bl
 	xorq	(%r11,%rdx,8),%r9
 	movq	%r8,%rdx
 	xorq	%r10,%r8
 
 	shrq	$4,%r8
-	andq	$15,%rdx
+	andq	$0xf,%rdx
 	movq	%r9,%r10
 	shrq	$4,%r9
 	xorq	8(%rsi,%rbx,1),%r8
@@ -880,20 +880,20 @@ L$_ghash_clmul:
 	movdqu	32(%rsi),%xmm7
 .byte	102,65,15,56,0,194
 
-	subq	$16,%rcx
+	subq	$0x10,%rcx
 	jz	L$odd_tail
 
 	movdqu	16(%rsi),%xmm6
 	movl	_OPENSSL_ia32cap_P+4(%rip),%eax
-	cmpq	$48,%rcx
+	cmpq	$0x30,%rcx
 	jb	L$skip4x
 
 	andl	$71303168,%eax
 	cmpl	$4194304,%eax
 	je	L$skip4x
 
-	subq	$48,%rcx
-	movq	$11547335547999543296,%rax
+	subq	$0x30,%rcx
+	movq	$0xA040608020C0E000,%rax
 	movdqu	48(%rsi),%xmm14
 	movdqu	64(%rsi),%xmm15
 
@@ -940,7 +940,7 @@ L$_ghash_clmul:
 	xorps	%xmm13,%xmm5
 
 	leaq	64(%rdx),%rdx
-	subq	$64,%rcx
+	subq	$0x40,%rcx
 	jc	L$tail4x
 
 	jmp	L$mod4_loop
@@ -1023,7 +1023,7 @@ L$mod4_loop:
 	xorps	%xmm13,%xmm5
 
 	leaq	64(%rdx),%rdx
-	subq	$64,%rcx
+	subq	$0x40,%rcx
 	jnc	L$mod4_loop
 
 L$tail4x:
@@ -1067,10 +1067,10 @@ L$tail4x:
 	pxor	%xmm4,%xmm0
 	psrlq	$1,%xmm0
 	pxor	%xmm1,%xmm0
-	addq	$64,%rcx
+	addq	$0x40,%rcx
 	jz	L$done
 	movdqu	32(%rsi),%xmm7
-	subq	$16,%rcx
+	subq	$0x10,%rcx
 	jz	L$odd_tail
 L$skip4x:
 
@@ -1093,7 +1093,7 @@ L$skip4x:
 
 	leaq	32(%rdx),%rdx
 	nop
-	subq	$32,%rcx
+	subq	$0x20,%rcx
 	jbe	L$even_tail
 	nop
 	jmp	L$mod_loop
@@ -1156,7 +1156,7 @@ L$mod_loop:
 .byte	102,15,58,68,231,0
 	pxor	%xmm1,%xmm0
 
-	subq	$32,%rcx
+	subq	$0x20,%rcx
 	ja	L$mod_loop
 
 L$even_tail:
diff --git a/packager/third_party/boringssl/mac-x86_64/crypto/sha/sha1-x86_64.S b/packager/third_party/boringssl/mac-x86_64/crypto/sha/sha1-x86_64.S
index 044dc5b7cd..0509d45163 100644
--- a/packager/third_party/boringssl/mac-x86_64/crypto/sha/sha1-x86_64.S
+++ b/packager/third_party/boringssl/mac-x86_64/crypto/sha/sha1-x86_64.S
@@ -12,6 +12,11 @@ _sha1_block_data_order:
 	movl	_OPENSSL_ia32cap_P+8(%rip),%r10d
 	testl	$512,%r8d
 	jz	L$ialu
+	andl	$268435456,%r8d
+	andl	$1073741824,%r9d
+	orl	%r9d,%r8d
+	cmpl	$1342177280,%r8d
+	je	_avx_shortcut
 	jmp	_ssse3_shortcut
 
 .p2align	4
@@ -2407,6 +2412,1122 @@ L$done_ssse3:
 L$epilogue_ssse3:
 	.byte	0xf3,0xc3
 
+
+.p2align	4
+sha1_block_data_order_avx:
+_avx_shortcut:
+	movq	%rsp,%rax
+	pushq	%rbx
+	pushq	%rbp
+	pushq	%r12
+	pushq	%r13
+	pushq	%r14
+	leaq	-64(%rsp),%rsp
+	vzeroupper
+	movq	%rax,%r14
+	andq	$-64,%rsp
+	movq	%rdi,%r8
+	movq	%rsi,%r9
+	movq	%rdx,%r10
+
+	shlq	$6,%r10
+	addq	%r9,%r10
+	leaq	K_XX_XX+64(%rip),%r11
+
+	movl	0(%r8),%eax
+	movl	4(%r8),%ebx
+	movl	8(%r8),%ecx
+	movl	12(%r8),%edx
+	movl	%ebx,%esi
+	movl	16(%r8),%ebp
+	movl	%ecx,%edi
+	xorl	%edx,%edi
+	andl	%edi,%esi
+
+	vmovdqa	64(%r11),%xmm6
+	vmovdqa	-64(%r11),%xmm11
+	vmovdqu	0(%r9),%xmm0
+	vmovdqu	16(%r9),%xmm1
+	vmovdqu	32(%r9),%xmm2
+	vmovdqu	48(%r9),%xmm3
+	vpshufb	%xmm6,%xmm0,%xmm0
+	addq	$64,%r9
+	vpshufb	%xmm6,%xmm1,%xmm1
+	vpshufb	%xmm6,%xmm2,%xmm2
+	vpshufb	%xmm6,%xmm3,%xmm3
+	vpaddd	%xmm11,%xmm0,%xmm4
+	vpaddd	%xmm11,%xmm1,%xmm5
+	vpaddd	%xmm11,%xmm2,%xmm6
+	vmovdqa	%xmm4,0(%rsp)
+	vmovdqa	%xmm5,16(%rsp)
+	vmovdqa	%xmm6,32(%rsp)
+	jmp	L$oop_avx
+.p2align	4
+L$oop_avx:
+	shrdl	$2,%ebx,%ebx
+	xorl	%edx,%esi
+	vpalignr	$8,%xmm0,%xmm1,%xmm4
+	movl	%eax,%edi
+	addl	0(%rsp),%ebp
+	vpaddd	%xmm3,%xmm11,%xmm9
+	xorl	%ecx,%ebx
+	shldl	$5,%eax,%eax
+	vpsrldq	$4,%xmm3,%xmm8
+	addl	%esi,%ebp
+	andl	%ebx,%edi
+	vpxor	%xmm0,%xmm4,%xmm4
+	xorl	%ecx,%ebx
+	addl	%eax,%ebp
+	vpxor	%xmm2,%xmm8,%xmm8
+	shrdl	$7,%eax,%eax
+	xorl	%ecx,%edi
+	movl	%ebp,%esi
+	addl	4(%rsp),%edx
+	vpxor	%xmm8,%xmm4,%xmm4
+	xorl	%ebx,%eax
+	shldl	$5,%ebp,%ebp
+	vmovdqa	%xmm9,48(%rsp)
+	addl	%edi,%edx
+	andl	%eax,%esi
+	vpsrld	$31,%xmm4,%xmm8
+	xorl	%ebx,%eax
+	addl	%ebp,%edx
+	shrdl	$7,%ebp,%ebp
+	xorl	%ebx,%esi
+	vpslldq	$12,%xmm4,%xmm10
+	vpaddd	%xmm4,%xmm4,%xmm4
+	movl	%edx,%edi
+	addl	8(%rsp),%ecx
+	xorl	%eax,%ebp
+	shldl	$5,%edx,%edx
+	vpsrld	$30,%xmm10,%xmm9
+	vpor	%xmm8,%xmm4,%xmm4
+	addl	%esi,%ecx
+	andl	%ebp,%edi
+	xorl	%eax,%ebp
+	addl	%edx,%ecx
+	vpslld	$2,%xmm10,%xmm10
+	vpxor	%xmm9,%xmm4,%xmm4
+	shrdl	$7,%edx,%edx
+	xorl	%eax,%edi
+	movl	%ecx,%esi
+	addl	12(%rsp),%ebx
+	vpxor	%xmm10,%xmm4,%xmm4
+	xorl	%ebp,%edx
+	shldl	$5,%ecx,%ecx
+	addl	%edi,%ebx
+	andl	%edx,%esi
+	xorl	%ebp,%edx
+	addl	%ecx,%ebx
+	shrdl	$7,%ecx,%ecx
+	xorl	%ebp,%esi
+	vpalignr	$8,%xmm1,%xmm2,%xmm5
+	movl	%ebx,%edi
+	addl	16(%rsp),%eax
+	vpaddd	%xmm4,%xmm11,%xmm9
+	xorl	%edx,%ecx
+	shldl	$5,%ebx,%ebx
+	vpsrldq	$4,%xmm4,%xmm8
+	addl	%esi,%eax
+	andl	%ecx,%edi
+	vpxor	%xmm1,%xmm5,%xmm5
+	xorl	%edx,%ecx
+	addl	%ebx,%eax
+	vpxor	%xmm3,%xmm8,%xmm8
+	shrdl	$7,%ebx,%ebx
+	xorl	%edx,%edi
+	movl	%eax,%esi
+	addl	20(%rsp),%ebp
+	vpxor	%xmm8,%xmm5,%xmm5
+	xorl	%ecx,%ebx
+	shldl	$5,%eax,%eax
+	vmovdqa	%xmm9,0(%rsp)
+	addl	%edi,%ebp
+	andl	%ebx,%esi
+	vpsrld	$31,%xmm5,%xmm8
+	xorl	%ecx,%ebx
+	addl	%eax,%ebp
+	shrdl	$7,%eax,%eax
+	xorl	%ecx,%esi
+	vpslldq	$12,%xmm5,%xmm10
+	vpaddd	%xmm5,%xmm5,%xmm5
+	movl	%ebp,%edi
+	addl	24(%rsp),%edx
+	xorl	%ebx,%eax
+	shldl	$5,%ebp,%ebp
+	vpsrld	$30,%xmm10,%xmm9
+	vpor	%xmm8,%xmm5,%xmm5
+	addl	%esi,%edx
+	andl	%eax,%edi
+	xorl	%ebx,%eax
+	addl	%ebp,%edx
+	vpslld	$2,%xmm10,%xmm10
+	vpxor	%xmm9,%xmm5,%xmm5
+	shrdl	$7,%ebp,%ebp
+	xorl	%ebx,%edi
+	movl	%edx,%esi
+	addl	28(%rsp),%ecx
+	vpxor	%xmm10,%xmm5,%xmm5
+	xorl	%eax,%ebp
+	shldl	$5,%edx,%edx
+	vmovdqa	-32(%r11),%xmm11
+	addl	%edi,%ecx
+	andl	%ebp,%esi
+	xorl	%eax,%ebp
+	addl	%edx,%ecx
+	shrdl	$7,%edx,%edx
+	xorl	%eax,%esi
+	vpalignr	$8,%xmm2,%xmm3,%xmm6
+	movl	%ecx,%edi
+	addl	32(%rsp),%ebx
+	vpaddd	%xmm5,%xmm11,%xmm9
+	xorl	%ebp,%edx
+	shldl	$5,%ecx,%ecx
+	vpsrldq	$4,%xmm5,%xmm8
+	addl	%esi,%ebx
+	andl	%edx,%edi
+	vpxor	%xmm2,%xmm6,%xmm6
+	xorl	%ebp,%edx
+	addl	%ecx,%ebx
+	vpxor	%xmm4,%xmm8,%xmm8
+	shrdl	$7,%ecx,%ecx
+	xorl	%ebp,%edi
+	movl	%ebx,%esi
+	addl	36(%rsp),%eax
+	vpxor	%xmm8,%xmm6,%xmm6
+	xorl	%edx,%ecx
+	shldl	$5,%ebx,%ebx
+	vmovdqa	%xmm9,16(%rsp)
+	addl	%edi,%eax
+	andl	%ecx,%esi
+	vpsrld	$31,%xmm6,%xmm8
+	xorl	%edx,%ecx
+	addl	%ebx,%eax
+	shrdl	$7,%ebx,%ebx
+	xorl	%edx,%esi
+	vpslldq	$12,%xmm6,%xmm10
+	vpaddd	%xmm6,%xmm6,%xmm6
+	movl	%eax,%edi
+	addl	40(%rsp),%ebp
+	xorl	%ecx,%ebx
+	shldl	$5,%eax,%eax
+	vpsrld	$30,%xmm10,%xmm9
+	vpor	%xmm8,%xmm6,%xmm6
+	addl	%esi,%ebp
+	andl	%ebx,%edi
+	xorl	%ecx,%ebx
+	addl	%eax,%ebp
+	vpslld	$2,%xmm10,%xmm10
+	vpxor	%xmm9,%xmm6,%xmm6
+	shrdl	$7,%eax,%eax
+	xorl	%ecx,%edi
+	movl	%ebp,%esi
+	addl	44(%rsp),%edx
+	vpxor	%xmm10,%xmm6,%xmm6
+	xorl	%ebx,%eax
+	shldl	$5,%ebp,%ebp
+	addl	%edi,%edx
+	andl	%eax,%esi
+	xorl	%ebx,%eax
+	addl	%ebp,%edx
+	shrdl	$7,%ebp,%ebp
+	xorl	%ebx,%esi
+	vpalignr	$8,%xmm3,%xmm4,%xmm7
+	movl	%edx,%edi
+	addl	48(%rsp),%ecx
+	vpaddd	%xmm6,%xmm11,%xmm9
+	xorl	%eax,%ebp
+	shldl	$5,%edx,%edx
+	vpsrldq	$4,%xmm6,%xmm8
+	addl	%esi,%ecx
+	andl	%ebp,%edi
+	vpxor	%xmm3,%xmm7,%xmm7
+	xorl	%eax,%ebp
+	addl	%edx,%ecx
+	vpxor	%xmm5,%xmm8,%xmm8
+	shrdl	$7,%edx,%edx
+	xorl	%eax,%edi
+	movl	%ecx,%esi
+	addl	52(%rsp),%ebx
+	vpxor	%xmm8,%xmm7,%xmm7
+	xorl	%ebp,%edx
+	shldl	$5,%ecx,%ecx
+	vmovdqa	%xmm9,32(%rsp)
+	addl	%edi,%ebx
+	andl	%edx,%esi
+	vpsrld	$31,%xmm7,%xmm8
+	xorl	%ebp,%edx
+	addl	%ecx,%ebx
+	shrdl	$7,%ecx,%ecx
+	xorl	%ebp,%esi
+	vpslldq	$12,%xmm7,%xmm10
+	vpaddd	%xmm7,%xmm7,%xmm7
+	movl	%ebx,%edi
+	addl	56(%rsp),%eax
+	xorl	%edx,%ecx
+	shldl	$5,%ebx,%ebx
+	vpsrld	$30,%xmm10,%xmm9
+	vpor	%xmm8,%xmm7,%xmm7
+	addl	%esi,%eax
+	andl	%ecx,%edi
+	xorl	%edx,%ecx
+	addl	%ebx,%eax
+	vpslld	$2,%xmm10,%xmm10
+	vpxor	%xmm9,%xmm7,%xmm7
+	shrdl	$7,%ebx,%ebx
+	xorl	%edx,%edi
+	movl	%eax,%esi
+	addl	60(%rsp),%ebp
+	vpxor	%xmm10,%xmm7,%xmm7
+	xorl	%ecx,%ebx
+	shldl	$5,%eax,%eax
+	addl	%edi,%ebp
+	andl	%ebx,%esi
+	xorl	%ecx,%ebx
+	addl	%eax,%ebp
+	vpalignr	$8,%xmm6,%xmm7,%xmm8
+	vpxor	%xmm4,%xmm0,%xmm0
+	shrdl	$7,%eax,%eax
+	xorl	%ecx,%esi
+	movl	%ebp,%edi
+	addl	0(%rsp),%edx
+	vpxor	%xmm1,%xmm0,%xmm0
+	xorl	%ebx,%eax
+	shldl	$5,%ebp,%ebp
+	vpaddd	%xmm7,%xmm11,%xmm9
+	addl	%esi,%edx
+	andl	%eax,%edi
+	vpxor	%xmm8,%xmm0,%xmm0
+	xorl	%ebx,%eax
+	addl	%ebp,%edx
+	shrdl	$7,%ebp,%ebp
+	xorl	%ebx,%edi
+	vpsrld	$30,%xmm0,%xmm8
+	vmovdqa	%xmm9,48(%rsp)
+	movl	%edx,%esi
+	addl	4(%rsp),%ecx
+	xorl	%eax,%ebp
+	shldl	$5,%edx,%edx
+	vpslld	$2,%xmm0,%xmm0
+	addl	%edi,%ecx
+	andl	%ebp,%esi
+	xorl	%eax,%ebp
+	addl	%edx,%ecx
+	shrdl	$7,%edx,%edx
+	xorl	%eax,%esi
+	movl	%ecx,%edi
+	addl	8(%rsp),%ebx
+	vpor	%xmm8,%xmm0,%xmm0
+	xorl	%ebp,%edx
+	shldl	$5,%ecx,%ecx
+	addl	%esi,%ebx
+	andl	%edx,%edi
+	xorl	%ebp,%edx
+	addl	%ecx,%ebx
+	addl	12(%rsp),%eax
+	xorl	%ebp,%edi
+	movl	%ebx,%esi
+	shldl	$5,%ebx,%ebx
+	addl	%edi,%eax
+	xorl	%edx,%esi
+	shrdl	$7,%ecx,%ecx
+	addl	%ebx,%eax
+	vpalignr	$8,%xmm7,%xmm0,%xmm8
+	vpxor	%xmm5,%xmm1,%xmm1
+	addl	16(%rsp),%ebp
+	xorl	%ecx,%esi
+	movl	%eax,%edi
+	shldl	$5,%eax,%eax
+	vpxor	%xmm2,%xmm1,%xmm1
+	addl	%esi,%ebp
+	xorl	%ecx,%edi
+	vpaddd	%xmm0,%xmm11,%xmm9
+	shrdl	$7,%ebx,%ebx
+	addl	%eax,%ebp
+	vpxor	%xmm8,%xmm1,%xmm1
+	addl	20(%rsp),%edx
+	xorl	%ebx,%edi
+	movl	%ebp,%esi
+	shldl	$5,%ebp,%ebp
+	vpsrld	$30,%xmm1,%xmm8
+	vmovdqa	%xmm9,0(%rsp)
+	addl	%edi,%edx
+	xorl	%ebx,%esi
+	shrdl	$7,%eax,%eax
+	addl	%ebp,%edx
+	vpslld	$2,%xmm1,%xmm1
+	addl	24(%rsp),%ecx
+	xorl	%eax,%esi
+	movl	%edx,%edi
+	shldl	$5,%edx,%edx
+	addl	%esi,%ecx
+	xorl	%eax,%edi
+	shrdl	$7,%ebp,%ebp
+	addl	%edx,%ecx
+	vpor	%xmm8,%xmm1,%xmm1
+	addl	28(%rsp),%ebx
+	xorl	%ebp,%edi
+	movl	%ecx,%esi
+	shldl	$5,%ecx,%ecx
+	addl	%edi,%ebx
+	xorl	%ebp,%esi
+	shrdl	$7,%edx,%edx
+	addl	%ecx,%ebx
+	vpalignr	$8,%xmm0,%xmm1,%xmm8
+	vpxor	%xmm6,%xmm2,%xmm2
+	addl	32(%rsp),%eax
+	xorl	%edx,%esi
+	movl	%ebx,%edi
+	shldl	$5,%ebx,%ebx
+	vpxor	%xmm3,%xmm2,%xmm2
+	addl	%esi,%eax
+	xorl	%edx,%edi
+	vpaddd	%xmm1,%xmm11,%xmm9
+	vmovdqa	0(%r11),%xmm11
+	shrdl	$7,%ecx,%ecx
+	addl	%ebx,%eax
+	vpxor	%xmm8,%xmm2,%xmm2
+	addl	36(%rsp),%ebp
+	xorl	%ecx,%edi
+	movl	%eax,%esi
+	shldl	$5,%eax,%eax
+	vpsrld	$30,%xmm2,%xmm8
+	vmovdqa	%xmm9,16(%rsp)
+	addl	%edi,%ebp
+	xorl	%ecx,%esi
+	shrdl	$7,%ebx,%ebx
+	addl	%eax,%ebp
+	vpslld	$2,%xmm2,%xmm2
+	addl	40(%rsp),%edx
+	xorl	%ebx,%esi
+	movl	%ebp,%edi
+	shldl	$5,%ebp,%ebp
+	addl	%esi,%edx
+	xorl	%ebx,%edi
+	shrdl	$7,%eax,%eax
+	addl	%ebp,%edx
+	vpor	%xmm8,%xmm2,%xmm2
+	addl	44(%rsp),%ecx
+	xorl	%eax,%edi
+	movl	%edx,%esi
+	shldl	$5,%edx,%edx
+	addl	%edi,%ecx
+	xorl	%eax,%esi
+	shrdl	$7,%ebp,%ebp
+	addl	%edx,%ecx
+	vpalignr	$8,%xmm1,%xmm2,%xmm8
+	vpxor	%xmm7,%xmm3,%xmm3
+	addl	48(%rsp),%ebx
+	xorl	%ebp,%esi
+	movl	%ecx,%edi
+	shldl	$5,%ecx,%ecx
+	vpxor	%xmm4,%xmm3,%xmm3
+	addl	%esi,%ebx
+	xorl	%ebp,%edi
+	vpaddd	%xmm2,%xmm11,%xmm9
+	shrdl	$7,%edx,%edx
+	addl	%ecx,%ebx
+	vpxor	%xmm8,%xmm3,%xmm3
+	addl	52(%rsp),%eax
+	xorl	%edx,%edi
+	movl	%ebx,%esi
+	shldl	$5,%ebx,%ebx
+	vpsrld	$30,%xmm3,%xmm8
+	vmovdqa	%xmm9,32(%rsp)
+	addl	%edi,%eax
+	xorl	%edx,%esi
+	shrdl	$7,%ecx,%ecx
+	addl	%ebx,%eax
+	vpslld	$2,%xmm3,%xmm3
+	addl	56(%rsp),%ebp
+	xorl	%ecx,%esi
+	movl	%eax,%edi
+	shldl	$5,%eax,%eax
+	addl	%esi,%ebp
+	xorl	%ecx,%edi
+	shrdl	$7,%ebx,%ebx
+	addl	%eax,%ebp
+	vpor	%xmm8,%xmm3,%xmm3
+	addl	60(%rsp),%edx
+	xorl	%ebx,%edi
+	movl	%ebp,%esi
+	shldl	$5,%ebp,%ebp
+	addl	%edi,%edx
+	xorl	%ebx,%esi
+	shrdl	$7,%eax,%eax
+	addl	%ebp,%edx
+	vpalignr	$8,%xmm2,%xmm3,%xmm8
+	vpxor	%xmm0,%xmm4,%xmm4
+	addl	0(%rsp),%ecx
+	xorl	%eax,%esi
+	movl	%edx,%edi
+	shldl	$5,%edx,%edx
+	vpxor	%xmm5,%xmm4,%xmm4
+	addl	%esi,%ecx
+	xorl	%eax,%edi
+	vpaddd	%xmm3,%xmm11,%xmm9
+	shrdl	$7,%ebp,%ebp
+	addl	%edx,%ecx
+	vpxor	%xmm8,%xmm4,%xmm4
+	addl	4(%rsp),%ebx
+	xorl	%ebp,%edi
+	movl	%ecx,%esi
+	shldl	$5,%ecx,%ecx
+	vpsrld	$30,%xmm4,%xmm8
+	vmovdqa	%xmm9,48(%rsp)
+	addl	%edi,%ebx
+	xorl	%ebp,%esi
+	shrdl	$7,%edx,%edx
+	addl	%ecx,%ebx
+	vpslld	$2,%xmm4,%xmm4
+	addl	8(%rsp),%eax
+	xorl	%edx,%esi
+	movl	%ebx,%edi
+	shldl	$5,%ebx,%ebx
+	addl	%esi,%eax
+	xorl	%edx,%edi
+	shrdl	$7,%ecx,%ecx
+	addl	%ebx,%eax
+	vpor	%xmm8,%xmm4,%xmm4
+	addl	12(%rsp),%ebp
+	xorl	%ecx,%edi
+	movl	%eax,%esi
+	shldl	$5,%eax,%eax
+	addl	%edi,%ebp
+	xorl	%ecx,%esi
+	shrdl	$7,%ebx,%ebx
+	addl	%eax,%ebp
+	vpalignr	$8,%xmm3,%xmm4,%xmm8
+	vpxor	%xmm1,%xmm5,%xmm5
+	addl	16(%rsp),%edx
+	xorl	%ebx,%esi
+	movl	%ebp,%edi
+	shldl	$5,%ebp,%ebp
+	vpxor	%xmm6,%xmm5,%xmm5
+	addl	%esi,%edx
+	xorl	%ebx,%edi
+	vpaddd	%xmm4,%xmm11,%xmm9
+	shrdl	$7,%eax,%eax
+	addl	%ebp,%edx
+	vpxor	%xmm8,%xmm5,%xmm5
+	addl	20(%rsp),%ecx
+	xorl	%eax,%edi
+	movl	%edx,%esi
+	shldl	$5,%edx,%edx
+	vpsrld	$30,%xmm5,%xmm8
+	vmovdqa	%xmm9,0(%rsp)
+	addl	%edi,%ecx
+	xorl	%eax,%esi
+	shrdl	$7,%ebp,%ebp
+	addl	%edx,%ecx
+	vpslld	$2,%xmm5,%xmm5
+	addl	24(%rsp),%ebx
+	xorl	%ebp,%esi
+	movl	%ecx,%edi
+	shldl	$5,%ecx,%ecx
+	addl	%esi,%ebx
+	xorl	%ebp,%edi
+	shrdl	$7,%edx,%edx
+	addl	%ecx,%ebx
+	vpor	%xmm8,%xmm5,%xmm5
+	addl	28(%rsp),%eax
+	shrdl	$7,%ecx,%ecx
+	movl	%ebx,%esi
+	xorl	%edx,%edi
+	shldl	$5,%ebx,%ebx
+	addl	%edi,%eax
+	xorl	%ecx,%esi
+	xorl	%edx,%ecx
+	addl	%ebx,%eax
+	vpalignr	$8,%xmm4,%xmm5,%xmm8
+	vpxor	%xmm2,%xmm6,%xmm6
+	addl	32(%rsp),%ebp
+	andl	%ecx,%esi
+	xorl	%edx,%ecx
+	shrdl	$7,%ebx,%ebx
+	vpxor	%xmm7,%xmm6,%xmm6
+	movl	%eax,%edi
+	xorl	%ecx,%esi
+	vpaddd	%xmm5,%xmm11,%xmm9
+	shldl	$5,%eax,%eax
+	addl	%esi,%ebp
+	vpxor	%xmm8,%xmm6,%xmm6
+	xorl	%ebx,%edi
+	xorl	%ecx,%ebx
+	addl	%eax,%ebp
+	addl	36(%rsp),%edx
+	vpsrld	$30,%xmm6,%xmm8
+	vmovdqa	%xmm9,16(%rsp)
+	andl	%ebx,%edi
+	xorl	%ecx,%ebx
+	shrdl	$7,%eax,%eax
+	movl	%ebp,%esi
+	vpslld	$2,%xmm6,%xmm6
+	xorl	%ebx,%edi
+	shldl	$5,%ebp,%ebp
+	addl	%edi,%edx
+	xorl	%eax,%esi
+	xorl	%ebx,%eax
+	addl	%ebp,%edx
+	addl	40(%rsp),%ecx
+	andl	%eax,%esi
+	vpor	%xmm8,%xmm6,%xmm6
+	xorl	%ebx,%eax
+	shrdl	$7,%ebp,%ebp
+	movl	%edx,%edi
+	xorl	%eax,%esi
+	shldl	$5,%edx,%edx
+	addl	%esi,%ecx
+	xorl	%ebp,%edi
+	xorl	%eax,%ebp
+	addl	%edx,%ecx
+	addl	44(%rsp),%ebx
+	andl	%ebp,%edi
+	xorl	%eax,%ebp
+	shrdl	$7,%edx,%edx
+	movl	%ecx,%esi
+	xorl	%ebp,%edi
+	shldl	$5,%ecx,%ecx
+	addl	%edi,%ebx
+	xorl	%edx,%esi
+	xorl	%ebp,%edx
+	addl	%ecx,%ebx
+	vpalignr	$8,%xmm5,%xmm6,%xmm8
+	vpxor	%xmm3,%xmm7,%xmm7
+	addl	48(%rsp),%eax
+	andl	%edx,%esi
+	xorl	%ebp,%edx
+	shrdl	$7,%ecx,%ecx
+	vpxor	%xmm0,%xmm7,%xmm7
+	movl	%ebx,%edi
+	xorl	%edx,%esi
+	vpaddd	%xmm6,%xmm11,%xmm9
+	vmovdqa	32(%r11),%xmm11
+	shldl	$5,%ebx,%ebx
+	addl	%esi,%eax
+	vpxor	%xmm8,%xmm7,%xmm7
+	xorl	%ecx,%edi
+	xorl	%edx,%ecx
+	addl	%ebx,%eax
+	addl	52(%rsp),%ebp
+	vpsrld	$30,%xmm7,%xmm8
+	vmovdqa	%xmm9,32(%rsp)
+	andl	%ecx,%edi
+	xorl	%edx,%ecx
+	shrdl	$7,%ebx,%ebx
+	movl	%eax,%esi
+	vpslld	$2,%xmm7,%xmm7
+	xorl	%ecx,%edi
+	shldl	$5,%eax,%eax
+	addl	%edi,%ebp
+	xorl	%ebx,%esi
+	xorl	%ecx,%ebx
+	addl	%eax,%ebp
+	addl	56(%rsp),%edx
+	andl	%ebx,%esi
+	vpor	%xmm8,%xmm7,%xmm7
+	xorl	%ecx,%ebx
+	shrdl	$7,%eax,%eax
+	movl	%ebp,%edi
+	xorl	%ebx,%esi
+	shldl	$5,%ebp,%ebp
+	addl	%esi,%edx
+	xorl	%eax,%edi
+	xorl	%ebx,%eax
+	addl	%ebp,%edx
+	addl	60(%rsp),%ecx
+	andl	%eax,%edi
+	xorl	%ebx,%eax
+	shrdl	$7,%ebp,%ebp
+	movl	%edx,%esi
+	xorl	%eax,%edi
+	shldl	$5,%edx,%edx
+	addl	%edi,%ecx
+	xorl	%ebp,%esi
+	xorl	%eax,%ebp
+	addl	%edx,%ecx
+	vpalignr	$8,%xmm6,%xmm7,%xmm8
+	vpxor	%xmm4,%xmm0,%xmm0
+	addl	0(%rsp),%ebx
+	andl	%ebp,%esi
+	xorl	%eax,%ebp
+	shrdl	$7,%edx,%edx
+	vpxor	%xmm1,%xmm0,%xmm0
+	movl	%ecx,%edi
+	xorl	%ebp,%esi
+	vpaddd	%xmm7,%xmm11,%xmm9
+	shldl	$5,%ecx,%ecx
+	addl	%esi,%ebx
+	vpxor	%xmm8,%xmm0,%xmm0
+	xorl	%edx,%edi
+	xorl	%ebp,%edx
+	addl	%ecx,%ebx
+	addl	4(%rsp),%eax
+	vpsrld	$30,%xmm0,%xmm8
+	vmovdqa	%xmm9,48(%rsp)
+	andl	%edx,%edi
+	xorl	%ebp,%edx
+	shrdl	$7,%ecx,%ecx
+	movl	%ebx,%esi
+	vpslld	$2,%xmm0,%xmm0
+	xorl	%edx,%edi
+	shldl	$5,%ebx,%ebx
+	addl	%edi,%eax
+	xorl	%ecx,%esi
+	xorl	%edx,%ecx
+	addl	%ebx,%eax
+	addl	8(%rsp),%ebp
+	andl	%ecx,%esi
+	vpor	%xmm8,%xmm0,%xmm0
+	xorl	%edx,%ecx
+	shrdl	$7,%ebx,%ebx
+	movl	%eax,%edi
+	xorl	%ecx,%esi
+	shldl	$5,%eax,%eax
+	addl	%esi,%ebp
+	xorl	%ebx,%edi
+	xorl	%ecx,%ebx
+	addl	%eax,%ebp
+	addl	12(%rsp),%edx
+	andl	%ebx,%edi
+	xorl	%ecx,%ebx
+	shrdl	$7,%eax,%eax
+	movl	%ebp,%esi
+	xorl	%ebx,%edi
+	shldl	$5,%ebp,%ebp
+	addl	%edi,%edx
+	xorl	%eax,%esi
+	xorl	%ebx,%eax
+	addl	%ebp,%edx
+	vpalignr	$8,%xmm7,%xmm0,%xmm8
+	vpxor	%xmm5,%xmm1,%xmm1
+	addl	16(%rsp),%ecx
+	andl	%eax,%esi
+	xorl	%ebx,%eax
+	shrdl	$7,%ebp,%ebp
+	vpxor	%xmm2,%xmm1,%xmm1
+	movl	%edx,%edi
+	xorl	%eax,%esi
+	vpaddd	%xmm0,%xmm11,%xmm9
+	shldl	$5,%edx,%edx
+	addl	%esi,%ecx
+	vpxor	%xmm8,%xmm1,%xmm1
+	xorl	%ebp,%edi
+	xorl	%eax,%ebp
+	addl	%edx,%ecx
+	addl	20(%rsp),%ebx
+	vpsrld	$30,%xmm1,%xmm8
+	vmovdqa	%xmm9,0(%rsp)
+	andl	%ebp,%edi
+	xorl	%eax,%ebp
+	shrdl	$7,%edx,%edx
+	movl	%ecx,%esi
+	vpslld	$2,%xmm1,%xmm1
+	xorl	%ebp,%edi
+	shldl	$5,%ecx,%ecx
+	addl	%edi,%ebx
+	xorl	%edx,%esi
+	xorl	%ebp,%edx
+	addl	%ecx,%ebx
+	addl	24(%rsp),%eax
+	andl	%edx,%esi
+	vpor	%xmm8,%xmm1,%xmm1
+	xorl	%ebp,%edx
+	shrdl	$7,%ecx,%ecx
+	movl	%ebx,%edi
+	xorl	%edx,%esi
+	shldl	$5,%ebx,%ebx
+	addl	%esi,%eax
+	xorl	%ecx,%edi
+	xorl	%edx,%ecx
+	addl	%ebx,%eax
+	addl	28(%rsp),%ebp
+	andl	%ecx,%edi
+	xorl	%edx,%ecx
+	shrdl	$7,%ebx,%ebx
+	movl	%eax,%esi
+	xorl	%ecx,%edi
+	shldl	$5,%eax,%eax
+	addl	%edi,%ebp
+	xorl	%ebx,%esi
+	xorl	%ecx,%ebx
+	addl	%eax,%ebp
+	vpalignr	$8,%xmm0,%xmm1,%xmm8
+	vpxor	%xmm6,%xmm2,%xmm2
+	addl	32(%rsp),%edx
+	andl	%ebx,%esi
+	xorl	%ecx,%ebx
+	shrdl	$7,%eax,%eax
+	vpxor	%xmm3,%xmm2,%xmm2
+	movl	%ebp,%edi
+	xorl	%ebx,%esi
+	vpaddd	%xmm1,%xmm11,%xmm9
+	shldl	$5,%ebp,%ebp
+	addl	%esi,%edx
+	vpxor	%xmm8,%xmm2,%xmm2
+	xorl	%eax,%edi
+	xorl	%ebx,%eax
+	addl	%ebp,%edx
+	addl	36(%rsp),%ecx
+	vpsrld	$30,%xmm2,%xmm8
+	vmovdqa	%xmm9,16(%rsp)
+	andl	%eax,%edi
+	xorl	%ebx,%eax
+	shrdl	$7,%ebp,%ebp
+	movl	%edx,%esi
+	vpslld	$2,%xmm2,%xmm2
+	xorl	%eax,%edi
+	shldl	$5,%edx,%edx
+	addl	%edi,%ecx
+	xorl	%ebp,%esi
+	xorl	%eax,%ebp
+	addl	%edx,%ecx
+	addl	40(%rsp),%ebx
+	andl	%ebp,%esi
+	vpor	%xmm8,%xmm2,%xmm2
+	xorl	%eax,%ebp
+	shrdl	$7,%edx,%edx
+	movl	%ecx,%edi
+	xorl	%ebp,%esi
+	shldl	$5,%ecx,%ecx
+	addl	%esi,%ebx
+	xorl	%edx,%edi
+	xorl	%ebp,%edx
+	addl	%ecx,%ebx
+	addl	44(%rsp),%eax
+	andl	%edx,%edi
+	xorl	%ebp,%edx
+	shrdl	$7,%ecx,%ecx
+	movl	%ebx,%esi
+	xorl	%edx,%edi
+	shldl	$5,%ebx,%ebx
+	addl	%edi,%eax
+	xorl	%edx,%esi
+	addl	%ebx,%eax
+	vpalignr	$8,%xmm1,%xmm2,%xmm8
+	vpxor	%xmm7,%xmm3,%xmm3
+	addl	48(%rsp),%ebp
+	xorl	%ecx,%esi
+	movl	%eax,%edi
+	shldl	$5,%eax,%eax
+	vpxor	%xmm4,%xmm3,%xmm3
+	addl	%esi,%ebp
+	xorl	%ecx,%edi
+	vpaddd	%xmm2,%xmm11,%xmm9
+	shrdl	$7,%ebx,%ebx
+	addl	%eax,%ebp
+	vpxor	%xmm8,%xmm3,%xmm3
+	addl	52(%rsp),%edx
+	xorl	%ebx,%edi
+	movl	%ebp,%esi
+	shldl	$5,%ebp,%ebp
+	vpsrld	$30,%xmm3,%xmm8
+	vmovdqa	%xmm9,32(%rsp)
+	addl	%edi,%edx
+	xorl	%ebx,%esi
+	shrdl	$7,%eax,%eax
+	addl	%ebp,%edx
+	vpslld	$2,%xmm3,%xmm3
+	addl	56(%rsp),%ecx
+	xorl	%eax,%esi
+	movl	%edx,%edi
+	shldl	$5,%edx,%edx
+	addl	%esi,%ecx
+	xorl	%eax,%edi
+	shrdl	$7,%ebp,%ebp
+	addl	%edx,%ecx
+	vpor	%xmm8,%xmm3,%xmm3
+	addl	60(%rsp),%ebx
+	xorl	%ebp,%edi
+	movl	%ecx,%esi
+	shldl	$5,%ecx,%ecx
+	addl	%edi,%ebx
+	xorl	%ebp,%esi
+	shrdl	$7,%edx,%edx
+	addl	%ecx,%ebx
+	addl	0(%rsp),%eax
+	vpaddd	%xmm3,%xmm11,%xmm9
+	xorl	%edx,%esi
+	movl	%ebx,%edi
+	shldl	$5,%ebx,%ebx
+	addl	%esi,%eax
+	vmovdqa	%xmm9,48(%rsp)
+	xorl	%edx,%edi
+	shrdl	$7,%ecx,%ecx
+	addl	%ebx,%eax
+	addl	4(%rsp),%ebp
+	xorl	%ecx,%edi
+	movl	%eax,%esi
+	shldl	$5,%eax,%eax
+	addl	%edi,%ebp
+	xorl	%ecx,%esi
+	shrdl	$7,%ebx,%ebx
+	addl	%eax,%ebp
+	addl	8(%rsp),%edx
+	xorl	%ebx,%esi
+	movl	%ebp,%edi
+	shldl	$5,%ebp,%ebp
+	addl	%esi,%edx
+	xorl	%ebx,%edi
+	shrdl	$7,%eax,%eax
+	addl	%ebp,%edx
+	addl	12(%rsp),%ecx
+	xorl	%eax,%edi
+	movl	%edx,%esi
+	shldl	$5,%edx,%edx
+	addl	%edi,%ecx
+	xorl	%eax,%esi
+	shrdl	$7,%ebp,%ebp
+	addl	%edx,%ecx
+	cmpq	%r10,%r9
+	je	L$done_avx
+	vmovdqa	64(%r11),%xmm6
+	vmovdqa	-64(%r11),%xmm11
+	vmovdqu	0(%r9),%xmm0
+	vmovdqu	16(%r9),%xmm1
+	vmovdqu	32(%r9),%xmm2
+	vmovdqu	48(%r9),%xmm3
+	vpshufb	%xmm6,%xmm0,%xmm0
+	addq	$64,%r9
+	addl	16(%rsp),%ebx
+	xorl	%ebp,%esi
+	vpshufb	%xmm6,%xmm1,%xmm1
+	movl	%ecx,%edi
+	shldl	$5,%ecx,%ecx
+	vpaddd	%xmm11,%xmm0,%xmm4
+	addl	%esi,%ebx
+	xorl	%ebp,%edi
+	shrdl	$7,%edx,%edx
+	addl	%ecx,%ebx
+	vmovdqa	%xmm4,0(%rsp)
+	addl	20(%rsp),%eax
+	xorl	%edx,%edi
+	movl	%ebx,%esi
+	shldl	$5,%ebx,%ebx
+	addl	%edi,%eax
+	xorl	%edx,%esi
+	shrdl	$7,%ecx,%ecx
+	addl	%ebx,%eax
+	addl	24(%rsp),%ebp
+	xorl	%ecx,%esi
+	movl	%eax,%edi
+	shldl	$5,%eax,%eax
+	addl	%esi,%ebp
+	xorl	%ecx,%edi
+	shrdl	$7,%ebx,%ebx
+	addl	%eax,%ebp
+	addl	28(%rsp),%edx
+	xorl	%ebx,%edi
+	movl	%ebp,%esi
+	shldl	$5,%ebp,%ebp
+	addl	%edi,%edx
+	xorl	%ebx,%esi
+	shrdl	$7,%eax,%eax
+	addl	%ebp,%edx
+	addl	32(%rsp),%ecx
+	xorl	%eax,%esi
+	vpshufb	%xmm6,%xmm2,%xmm2
+	movl	%edx,%edi
+	shldl	$5,%edx,%edx
+	vpaddd	%xmm11,%xmm1,%xmm5
+	addl	%esi,%ecx
+	xorl	%eax,%edi
+	shrdl	$7,%ebp,%ebp
+	addl	%edx,%ecx
+	vmovdqa	%xmm5,16(%rsp)
+	addl	36(%rsp),%ebx
+	xorl	%ebp,%edi
+	movl	%ecx,%esi
+	shldl	$5,%ecx,%ecx
+	addl	%edi,%ebx
+	xorl	%ebp,%esi
+	shrdl	$7,%edx,%edx
+	addl	%ecx,%ebx
+	addl	40(%rsp),%eax
+	xorl	%edx,%esi
+	movl	%ebx,%edi
+	shldl	$5,%ebx,%ebx
+	addl	%esi,%eax
+	xorl	%edx,%edi
+	shrdl	$7,%ecx,%ecx
+	addl	%ebx,%eax
+	addl	44(%rsp),%ebp
+	xorl	%ecx,%edi
+	movl	%eax,%esi
+	shldl	$5,%eax,%eax
+	addl	%edi,%ebp
+	xorl	%ecx,%esi
+	shrdl	$7,%ebx,%ebx
+	addl	%eax,%ebp
+	addl	48(%rsp),%edx
+	xorl	%ebx,%esi
+	vpshufb	%xmm6,%xmm3,%xmm3
+	movl	%ebp,%edi
+	shldl	$5,%ebp,%ebp
+	vpaddd	%xmm11,%xmm2,%xmm6
+	addl	%esi,%edx
+	xorl	%ebx,%edi
+	shrdl	$7,%eax,%eax
+	addl	%ebp,%edx
+	vmovdqa	%xmm6,32(%rsp)
+	addl	52(%rsp),%ecx
+	xorl	%eax,%edi
+	movl	%edx,%esi
+	shldl	$5,%edx,%edx
+	addl	%edi,%ecx
+	xorl	%eax,%esi
+	shrdl	$7,%ebp,%ebp
+	addl	%edx,%ecx
+	addl	56(%rsp),%ebx
+	xorl	%ebp,%esi
+	movl	%ecx,%edi
+	shldl	$5,%ecx,%ecx
+	addl	%esi,%ebx
+	xorl	%ebp,%edi
+	shrdl	$7,%edx,%edx
+	addl	%ecx,%ebx
+	addl	60(%rsp),%eax
+	xorl	%edx,%edi
+	movl	%ebx,%esi
+	shldl	$5,%ebx,%ebx
+	addl	%edi,%eax
+	shrdl	$7,%ecx,%ecx
+	addl	%ebx,%eax
+	addl	0(%r8),%eax
+	addl	4(%r8),%esi
+	addl	8(%r8),%ecx
+	addl	12(%r8),%edx
+	movl	%eax,0(%r8)
+	addl	16(%r8),%ebp
+	movl	%esi,4(%r8)
+	movl	%esi,%ebx
+	movl	%ecx,8(%r8)
+	movl	%ecx,%edi
+	movl	%edx,12(%r8)
+	xorl	%edx,%edi
+	movl	%ebp,16(%r8)
+	andl	%edi,%esi
+	jmp	L$oop_avx
+
+.p2align	4
+L$done_avx:
+	addl	16(%rsp),%ebx
+	xorl	%ebp,%esi
+	movl	%ecx,%edi
+	shldl	$5,%ecx,%ecx
+	addl	%esi,%ebx
+	xorl	%ebp,%edi
+	shrdl	$7,%edx,%edx
+	addl	%ecx,%ebx
+	addl	20(%rsp),%eax
+	xorl	%edx,%edi
+	movl	%ebx,%esi
+	shldl	$5,%ebx,%ebx
+	addl	%edi,%eax
+	xorl	%edx,%esi
+	shrdl	$7,%ecx,%ecx
+	addl	%ebx,%eax
+	addl	24(%rsp),%ebp
+	xorl	%ecx,%esi
+	movl	%eax,%edi
+	shldl	$5,%eax,%eax
+	addl	%esi,%ebp
+	xorl	%ecx,%edi
+	shrdl	$7,%ebx,%ebx
+	addl	%eax,%ebp
+	addl	28(%rsp),%edx
+	xorl	%ebx,%edi
+	movl	%ebp,%esi
+	shldl	$5,%ebp,%ebp
+	addl	%edi,%edx
+	xorl	%ebx,%esi
+	shrdl	$7,%eax,%eax
+	addl	%ebp,%edx
+	addl	32(%rsp),%ecx
+	xorl	%eax,%esi
+	movl	%edx,%edi
+	shldl	$5,%edx,%edx
+	addl	%esi,%ecx
+	xorl	%eax,%edi
+	shrdl	$7,%ebp,%ebp
+	addl	%edx,%ecx
+	addl	36(%rsp),%ebx
+	xorl	%ebp,%edi
+	movl	%ecx,%esi
+	shldl	$5,%ecx,%ecx
+	addl	%edi,%ebx
+	xorl	%ebp,%esi
+	shrdl	$7,%edx,%edx
+	addl	%ecx,%ebx
+	addl	40(%rsp),%eax
+	xorl	%edx,%esi
+	movl	%ebx,%edi
+	shldl	$5,%ebx,%ebx
+	addl	%esi,%eax
+	xorl	%edx,%edi
+	shrdl	$7,%ecx,%ecx
+	addl	%ebx,%eax
+	addl	44(%rsp),%ebp
+	xorl	%ecx,%edi
+	movl	%eax,%esi
+	shldl	$5,%eax,%eax
+	addl	%edi,%ebp
+	xorl	%ecx,%esi
+	shrdl	$7,%ebx,%ebx
+	addl	%eax,%ebp
+	addl	48(%rsp),%edx
+	xorl	%ebx,%esi
+	movl	%ebp,%edi
+	shldl	$5,%ebp,%ebp
+	addl	%esi,%edx
+	xorl	%ebx,%edi
+	shrdl	$7,%eax,%eax
+	addl	%ebp,%edx
+	addl	52(%rsp),%ecx
+	xorl	%eax,%edi
+	movl	%edx,%esi
+	shldl	$5,%edx,%edx
+	addl	%edi,%ecx
+	xorl	%eax,%esi
+	shrdl	$7,%ebp,%ebp
+	addl	%edx,%ecx
+	addl	56(%rsp),%ebx
+	xorl	%ebp,%esi
+	movl	%ecx,%edi
+	shldl	$5,%ecx,%ecx
+	addl	%esi,%ebx
+	xorl	%ebp,%edi
+	shrdl	$7,%edx,%edx
+	addl	%ecx,%ebx
+	addl	60(%rsp),%eax
+	xorl	%edx,%edi
+	movl	%ebx,%esi
+	shldl	$5,%ebx,%ebx
+	addl	%edi,%eax
+	shrdl	$7,%ecx,%ecx
+	addl	%ebx,%eax
+	vzeroupper
+
+	addl	0(%r8),%eax
+	addl	4(%r8),%esi
+	addl	8(%r8),%ecx
+	movl	%eax,0(%r8)
+	addl	12(%r8),%edx
+	movl	%esi,4(%r8)
+	addl	16(%r8),%ebp
+	movl	%ecx,8(%r8)
+	movl	%edx,12(%r8)
+	movl	%ebp,16(%r8)
+	leaq	(%r14),%rsi
+	movq	-40(%rsi),%r14
+	movq	-32(%rsi),%r13
+	movq	-24(%rsi),%r12
+	movq	-16(%rsi),%rbp
+	movq	-8(%rsi),%rbx
+	leaq	(%rsi),%rsp
+L$epilogue_avx:
+	.byte	0xf3,0xc3
+
 .p2align	6
 K_XX_XX:
 .long	0x5a827999,0x5a827999,0x5a827999,0x5a827999
diff --git a/packager/third_party/boringssl/mac-x86_64/crypto/sha/sha256-x86_64.S b/packager/third_party/boringssl/mac-x86_64/crypto/sha/sha256-x86_64.S
index da02d4c2dc..0146ff5cfc 100644
--- a/packager/third_party/boringssl/mac-x86_64/crypto/sha/sha256-x86_64.S
+++ b/packager/third_party/boringssl/mac-x86_64/crypto/sha/sha256-x86_64.S
@@ -11,6 +11,11 @@ _sha256_block_data_order:
 	movl	0(%r11),%r9d
 	movl	4(%r11),%r10d
 	movl	8(%r11),%r11d
+	andl	$1073741824,%r9d
+	andl	$268435968,%r10d
+	orl	%r9d,%r10d
+	cmpl	$1342177792,%r10d
+	je	L$avx_shortcut
 	testl	$512,%r10d
 	jnz	L$ssse3_shortcut
 	pushq	%rbx
@@ -2840,4 +2845,1061 @@ L$ssse3_00_47:
 L$epilogue_ssse3:
 	.byte	0xf3,0xc3
 
+
+.p2align	6
+sha256_block_data_order_avx:
+L$avx_shortcut:
+	pushq	%rbx
+	pushq	%rbp
+	pushq	%r12
+	pushq	%r13
+	pushq	%r14
+	pushq	%r15
+	movq	%rsp,%r11
+	shlq	$4,%rdx
+	subq	$96,%rsp
+	leaq	(%rsi,%rdx,4),%rdx
+	andq	$-64,%rsp
+	movq	%rdi,64+0(%rsp)
+	movq	%rsi,64+8(%rsp)
+	movq	%rdx,64+16(%rsp)
+	movq	%r11,64+24(%rsp)
+L$prologue_avx:
+
+	vzeroupper
+	movl	0(%rdi),%eax
+	movl	4(%rdi),%ebx
+	movl	8(%rdi),%ecx
+	movl	12(%rdi),%edx
+	movl	16(%rdi),%r8d
+	movl	20(%rdi),%r9d
+	movl	24(%rdi),%r10d
+	movl	28(%rdi),%r11d
+	vmovdqa	K256+512+32(%rip),%xmm8
+	vmovdqa	K256+512+64(%rip),%xmm9
+	jmp	L$loop_avx
+.p2align	4
+L$loop_avx:
+	vmovdqa	K256+512(%rip),%xmm7
+	vmovdqu	0(%rsi),%xmm0
+	vmovdqu	16(%rsi),%xmm1
+	vmovdqu	32(%rsi),%xmm2
+	vmovdqu	48(%rsi),%xmm3
+	vpshufb	%xmm7,%xmm0,%xmm0
+	leaq	K256(%rip),%rbp
+	vpshufb	%xmm7,%xmm1,%xmm1
+	vpshufb	%xmm7,%xmm2,%xmm2
+	vpaddd	0(%rbp),%xmm0,%xmm4
+	vpshufb	%xmm7,%xmm3,%xmm3
+	vpaddd	32(%rbp),%xmm1,%xmm5
+	vpaddd	64(%rbp),%xmm2,%xmm6
+	vpaddd	96(%rbp),%xmm3,%xmm7
+	vmovdqa	%xmm4,0(%rsp)
+	movl	%eax,%r14d
+	vmovdqa	%xmm5,16(%rsp)
+	movl	%ebx,%edi
+	vmovdqa	%xmm6,32(%rsp)
+	xorl	%ecx,%edi
+	vmovdqa	%xmm7,48(%rsp)
+	movl	%r8d,%r13d
+	jmp	L$avx_00_47
+
+.p2align	4
+L$avx_00_47:
+	subq	$-128,%rbp
+	vpalignr	$4,%xmm0,%xmm1,%xmm4
+	shrdl	$14,%r13d,%r13d
+	movl	%r14d,%eax
+	movl	%r9d,%r12d
+	vpalignr	$4,%xmm2,%xmm3,%xmm7
+	shrdl	$9,%r14d,%r14d
+	xorl	%r8d,%r13d
+	xorl	%r10d,%r12d
+	vpsrld	$7,%xmm4,%xmm6
+	shrdl	$5,%r13d,%r13d
+	xorl	%eax,%r14d
+	andl	%r8d,%r12d
+	vpaddd	%xmm7,%xmm0,%xmm0
+	xorl	%r8d,%r13d
+	addl	0(%rsp),%r11d
+	movl	%eax,%r15d
+	vpsrld	$3,%xmm4,%xmm7
+	xorl	%r10d,%r12d
+	shrdl	$11,%r14d,%r14d
+	xorl	%ebx,%r15d
+	vpslld	$14,%xmm4,%xmm5
+	addl	%r12d,%r11d
+	shrdl	$6,%r13d,%r13d
+	andl	%r15d,%edi
+	vpxor	%xmm6,%xmm7,%xmm4
+	xorl	%eax,%r14d
+	addl	%r13d,%r11d
+	xorl	%ebx,%edi
+	vpshufd	$250,%xmm3,%xmm7
+	shrdl	$2,%r14d,%r14d
+	addl	%r11d,%edx
+	addl	%edi,%r11d
+	vpsrld	$11,%xmm6,%xmm6
+	movl	%edx,%r13d
+	addl	%r11d,%r14d
+	shrdl	$14,%r13d,%r13d
+	vpxor	%xmm5,%xmm4,%xmm4
+	movl	%r14d,%r11d
+	movl	%r8d,%r12d
+	shrdl	$9,%r14d,%r14d
+	vpslld	$11,%xmm5,%xmm5
+	xorl	%edx,%r13d
+	xorl	%r9d,%r12d
+	shrdl	$5,%r13d,%r13d
+	vpxor	%xmm6,%xmm4,%xmm4
+	xorl	%r11d,%r14d
+	andl	%edx,%r12d
+	xorl	%edx,%r13d
+	vpsrld	$10,%xmm7,%xmm6
+	addl	4(%rsp),%r10d
+	movl	%r11d,%edi
+	xorl	%r9d,%r12d
+	vpxor	%xmm5,%xmm4,%xmm4
+	shrdl	$11,%r14d,%r14d
+	xorl	%eax,%edi
+	addl	%r12d,%r10d
+	vpsrlq	$17,%xmm7,%xmm7
+	shrdl	$6,%r13d,%r13d
+	andl	%edi,%r15d
+	xorl	%r11d,%r14d
+	vpaddd	%xmm4,%xmm0,%xmm0
+	addl	%r13d,%r10d
+	xorl	%eax,%r15d
+	shrdl	$2,%r14d,%r14d
+	vpxor	%xmm7,%xmm6,%xmm6
+	addl	%r10d,%ecx
+	addl	%r15d,%r10d
+	movl	%ecx,%r13d
+	vpsrlq	$2,%xmm7,%xmm7
+	addl	%r10d,%r14d
+	shrdl	$14,%r13d,%r13d
+	movl	%r14d,%r10d
+	vpxor	%xmm7,%xmm6,%xmm6
+	movl	%edx,%r12d
+	shrdl	$9,%r14d,%r14d
+	xorl	%ecx,%r13d
+	vpshufb	%xmm8,%xmm6,%xmm6
+	xorl	%r8d,%r12d
+	shrdl	$5,%r13d,%r13d
+	xorl	%r10d,%r14d
+	vpaddd	%xmm6,%xmm0,%xmm0
+	andl	%ecx,%r12d
+	xorl	%ecx,%r13d
+	addl	8(%rsp),%r9d
+	vpshufd	$80,%xmm0,%xmm7
+	movl	%r10d,%r15d
+	xorl	%r8d,%r12d
+	shrdl	$11,%r14d,%r14d
+	vpsrld	$10,%xmm7,%xmm6
+	xorl	%r11d,%r15d
+	addl	%r12d,%r9d
+	shrdl	$6,%r13d,%r13d
+	vpsrlq	$17,%xmm7,%xmm7
+	andl	%r15d,%edi
+	xorl	%r10d,%r14d
+	addl	%r13d,%r9d
+	vpxor	%xmm7,%xmm6,%xmm6
+	xorl	%r11d,%edi
+	shrdl	$2,%r14d,%r14d
+	addl	%r9d,%ebx
+	vpsrlq	$2,%xmm7,%xmm7
+	addl	%edi,%r9d
+	movl	%ebx,%r13d
+	addl	%r9d,%r14d
+	vpxor	%xmm7,%xmm6,%xmm6
+	shrdl	$14,%r13d,%r13d
+	movl	%r14d,%r9d
+	movl	%ecx,%r12d
+	vpshufb	%xmm9,%xmm6,%xmm6
+	shrdl	$9,%r14d,%r14d
+	xorl	%ebx,%r13d
+	xorl	%edx,%r12d
+	vpaddd	%xmm6,%xmm0,%xmm0
+	shrdl	$5,%r13d,%r13d
+	xorl	%r9d,%r14d
+	andl	%ebx,%r12d
+	vpaddd	0(%rbp),%xmm0,%xmm6
+	xorl	%ebx,%r13d
+	addl	12(%rsp),%r8d
+	movl	%r9d,%edi
+	xorl	%edx,%r12d
+	shrdl	$11,%r14d,%r14d
+	xorl	%r10d,%edi
+	addl	%r12d,%r8d
+	shrdl	$6,%r13d,%r13d
+	andl	%edi,%r15d
+	xorl	%r9d,%r14d
+	addl	%r13d,%r8d
+	xorl	%r10d,%r15d
+	shrdl	$2,%r14d,%r14d
+	addl	%r8d,%eax
+	addl	%r15d,%r8d
+	movl	%eax,%r13d
+	addl	%r8d,%r14d
+	vmovdqa	%xmm6,0(%rsp)
+	vpalignr	$4,%xmm1,%xmm2,%xmm4
+	shrdl	$14,%r13d,%r13d
+	movl	%r14d,%r8d
+	movl	%ebx,%r12d
+	vpalignr	$4,%xmm3,%xmm0,%xmm7
+	shrdl	$9,%r14d,%r14d
+	xorl	%eax,%r13d
+	xorl	%ecx,%r12d
+	vpsrld	$7,%xmm4,%xmm6
+	shrdl	$5,%r13d,%r13d
+	xorl	%r8d,%r14d
+	andl	%eax,%r12d
+	vpaddd	%xmm7,%xmm1,%xmm1
+	xorl	%eax,%r13d
+	addl	16(%rsp),%edx
+	movl	%r8d,%r15d
+	vpsrld	$3,%xmm4,%xmm7
+	xorl	%ecx,%r12d
+	shrdl	$11,%r14d,%r14d
+	xorl	%r9d,%r15d
+	vpslld	$14,%xmm4,%xmm5
+	addl	%r12d,%edx
+	shrdl	$6,%r13d,%r13d
+	andl	%r15d,%edi
+	vpxor	%xmm6,%xmm7,%xmm4
+	xorl	%r8d,%r14d
+	addl	%r13d,%edx
+	xorl	%r9d,%edi
+	vpshufd	$250,%xmm0,%xmm7
+	shrdl	$2,%r14d,%r14d
+	addl	%edx,%r11d
+	addl	%edi,%edx
+	vpsrld	$11,%xmm6,%xmm6
+	movl	%r11d,%r13d
+	addl	%edx,%r14d
+	shrdl	$14,%r13d,%r13d
+	vpxor	%xmm5,%xmm4,%xmm4
+	movl	%r14d,%edx
+	movl	%eax,%r12d
+	shrdl	$9,%r14d,%r14d
+	vpslld	$11,%xmm5,%xmm5
+	xorl	%r11d,%r13d
+	xorl	%ebx,%r12d
+	shrdl	$5,%r13d,%r13d
+	vpxor	%xmm6,%xmm4,%xmm4
+	xorl	%edx,%r14d
+	andl	%r11d,%r12d
+	xorl	%r11d,%r13d
+	vpsrld	$10,%xmm7,%xmm6
+	addl	20(%rsp),%ecx
+	movl	%edx,%edi
+	xorl	%ebx,%r12d
+	vpxor	%xmm5,%xmm4,%xmm4
+	shrdl	$11,%r14d,%r14d
+	xorl	%r8d,%edi
+	addl	%r12d,%ecx
+	vpsrlq	$17,%xmm7,%xmm7
+	shrdl	$6,%r13d,%r13d
+	andl	%edi,%r15d
+	xorl	%edx,%r14d
+	vpaddd	%xmm4,%xmm1,%xmm1
+	addl	%r13d,%ecx
+	xorl	%r8d,%r15d
+	shrdl	$2,%r14d,%r14d
+	vpxor	%xmm7,%xmm6,%xmm6
+	addl	%ecx,%r10d
+	addl	%r15d,%ecx
+	movl	%r10d,%r13d
+	vpsrlq	$2,%xmm7,%xmm7
+	addl	%ecx,%r14d
+	shrdl	$14,%r13d,%r13d
+	movl	%r14d,%ecx
+	vpxor	%xmm7,%xmm6,%xmm6
+	movl	%r11d,%r12d
+	shrdl	$9,%r14d,%r14d
+	xorl	%r10d,%r13d
+	vpshufb	%xmm8,%xmm6,%xmm6
+	xorl	%eax,%r12d
+	shrdl	$5,%r13d,%r13d
+	xorl	%ecx,%r14d
+	vpaddd	%xmm6,%xmm1,%xmm1
+	andl	%r10d,%r12d
+	xorl	%r10d,%r13d
+	addl	24(%rsp),%ebx
+	vpshufd	$80,%xmm1,%xmm7
+	movl	%ecx,%r15d
+	xorl	%eax,%r12d
+	shrdl	$11,%r14d,%r14d
+	vpsrld	$10,%xmm7,%xmm6
+	xorl	%edx,%r15d
+	addl	%r12d,%ebx
+	shrdl	$6,%r13d,%r13d
+	vpsrlq	$17,%xmm7,%xmm7
+	andl	%r15d,%edi
+	xorl	%ecx,%r14d
+	addl	%r13d,%ebx
+	vpxor	%xmm7,%xmm6,%xmm6
+	xorl	%edx,%edi
+	shrdl	$2,%r14d,%r14d
+	addl	%ebx,%r9d
+	vpsrlq	$2,%xmm7,%xmm7
+	addl	%edi,%ebx
+	movl	%r9d,%r13d
+	addl	%ebx,%r14d
+	vpxor	%xmm7,%xmm6,%xmm6
+	shrdl	$14,%r13d,%r13d
+	movl	%r14d,%ebx
+	movl	%r10d,%r12d
+	vpshufb	%xmm9,%xmm6,%xmm6
+	shrdl	$9,%r14d,%r14d
+	xorl	%r9d,%r13d
+	xorl	%r11d,%r12d
+	vpaddd	%xmm6,%xmm1,%xmm1
+	shrdl	$5,%r13d,%r13d
+	xorl	%ebx,%r14d
+	andl	%r9d,%r12d
+	vpaddd	32(%rbp),%xmm1,%xmm6
+	xorl	%r9d,%r13d
+	addl	28(%rsp),%eax
+	movl	%ebx,%edi
+	xorl	%r11d,%r12d
+	shrdl	$11,%r14d,%r14d
+	xorl	%ecx,%edi
+	addl	%r12d,%eax
+	shrdl	$6,%r13d,%r13d
+	andl	%edi,%r15d
+	xorl	%ebx,%r14d
+	addl	%r13d,%eax
+	xorl	%ecx,%r15d
+	shrdl	$2,%r14d,%r14d
+	addl	%eax,%r8d
+	addl	%r15d,%eax
+	movl	%r8d,%r13d
+	addl	%eax,%r14d
+	vmovdqa	%xmm6,16(%rsp)
+	vpalignr	$4,%xmm2,%xmm3,%xmm4
+	shrdl	$14,%r13d,%r13d
+	movl	%r14d,%eax
+	movl	%r9d,%r12d
+	vpalignr	$4,%xmm0,%xmm1,%xmm7
+	shrdl	$9,%r14d,%r14d
+	xorl	%r8d,%r13d
+	xorl	%r10d,%r12d
+	vpsrld	$7,%xmm4,%xmm6
+	shrdl	$5,%r13d,%r13d
+	xorl	%eax,%r14d
+	andl	%r8d,%r12d
+	vpaddd	%xmm7,%xmm2,%xmm2
+	xorl	%r8d,%r13d
+	addl	32(%rsp),%r11d
+	movl	%eax,%r15d
+	vpsrld	$3,%xmm4,%xmm7
+	xorl	%r10d,%r12d
+	shrdl	$11,%r14d,%r14d
+	xorl	%ebx,%r15d
+	vpslld	$14,%xmm4,%xmm5
+	addl	%r12d,%r11d
+	shrdl	$6,%r13d,%r13d
+	andl	%r15d,%edi
+	vpxor	%xmm6,%xmm7,%xmm4
+	xorl	%eax,%r14d
+	addl	%r13d,%r11d
+	xorl	%ebx,%edi
+	vpshufd	$250,%xmm1,%xmm7
+	shrdl	$2,%r14d,%r14d
+	addl	%r11d,%edx
+	addl	%edi,%r11d
+	vpsrld	$11,%xmm6,%xmm6
+	movl	%edx,%r13d
+	addl	%r11d,%r14d
+	shrdl	$14,%r13d,%r13d
+	vpxor	%xmm5,%xmm4,%xmm4
+	movl	%r14d,%r11d
+	movl	%r8d,%r12d
+	shrdl	$9,%r14d,%r14d
+	vpslld	$11,%xmm5,%xmm5
+	xorl	%edx,%r13d
+	xorl	%r9d,%r12d
+	shrdl	$5,%r13d,%r13d
+	vpxor	%xmm6,%xmm4,%xmm4
+	xorl	%r11d,%r14d
+	andl	%edx,%r12d
+	xorl	%edx,%r13d
+	vpsrld	$10,%xmm7,%xmm6
+	addl	36(%rsp),%r10d
+	movl	%r11d,%edi
+	xorl	%r9d,%r12d
+	vpxor	%xmm5,%xmm4,%xmm4
+	shrdl	$11,%r14d,%r14d
+	xorl	%eax,%edi
+	addl	%r12d,%r10d
+	vpsrlq	$17,%xmm7,%xmm7
+	shrdl	$6,%r13d,%r13d
+	andl	%edi,%r15d
+	xorl	%r11d,%r14d
+	vpaddd	%xmm4,%xmm2,%xmm2
+	addl	%r13d,%r10d
+	xorl	%eax,%r15d
+	shrdl	$2,%r14d,%r14d
+	vpxor	%xmm7,%xmm6,%xmm6
+	addl	%r10d,%ecx
+	addl	%r15d,%r10d
+	movl	%ecx,%r13d
+	vpsrlq	$2,%xmm7,%xmm7
+	addl	%r10d,%r14d
+	shrdl	$14,%r13d,%r13d
+	movl	%r14d,%r10d
+	vpxor	%xmm7,%xmm6,%xmm6
+	movl	%edx,%r12d
+	shrdl	$9,%r14d,%r14d
+	xorl	%ecx,%r13d
+	vpshufb	%xmm8,%xmm6,%xmm6
+	xorl	%r8d,%r12d
+	shrdl	$5,%r13d,%r13d
+	xorl	%r10d,%r14d
+	vpaddd	%xmm6,%xmm2,%xmm2
+	andl	%ecx,%r12d
+	xorl	%ecx,%r13d
+	addl	40(%rsp),%r9d
+	vpshufd	$80,%xmm2,%xmm7
+	movl	%r10d,%r15d
+	xorl	%r8d,%r12d
+	shrdl	$11,%r14d,%r14d
+	vpsrld	$10,%xmm7,%xmm6
+	xorl	%r11d,%r15d
+	addl	%r12d,%r9d
+	shrdl	$6,%r13d,%r13d
+	vpsrlq	$17,%xmm7,%xmm7
+	andl	%r15d,%edi
+	xorl	%r10d,%r14d
+	addl	%r13d,%r9d
+	vpxor	%xmm7,%xmm6,%xmm6
+	xorl	%r11d,%edi
+	shrdl	$2,%r14d,%r14d
+	addl	%r9d,%ebx
+	vpsrlq	$2,%xmm7,%xmm7
+	addl	%edi,%r9d
+	movl	%ebx,%r13d
+	addl	%r9d,%r14d
+	vpxor	%xmm7,%xmm6,%xmm6
+	shrdl	$14,%r13d,%r13d
+	movl	%r14d,%r9d
+	movl	%ecx,%r12d
+	vpshufb	%xmm9,%xmm6,%xmm6
+	shrdl	$9,%r14d,%r14d
+	xorl	%ebx,%r13d
+	xorl	%edx,%r12d
+	vpaddd	%xmm6,%xmm2,%xmm2
+	shrdl	$5,%r13d,%r13d
+	xorl	%r9d,%r14d
+	andl	%ebx,%r12d
+	vpaddd	64(%rbp),%xmm2,%xmm6
+	xorl	%ebx,%r13d
+	addl	44(%rsp),%r8d
+	movl	%r9d,%edi
+	xorl	%edx,%r12d
+	shrdl	$11,%r14d,%r14d
+	xorl	%r10d,%edi
+	addl	%r12d,%r8d
+	shrdl	$6,%r13d,%r13d
+	andl	%edi,%r15d
+	xorl	%r9d,%r14d
+	addl	%r13d,%r8d
+	xorl	%r10d,%r15d
+	shrdl	$2,%r14d,%r14d
+	addl	%r8d,%eax
+	addl	%r15d,%r8d
+	movl	%eax,%r13d
+	addl	%r8d,%r14d
+	vmovdqa	%xmm6,32(%rsp)
+	vpalignr	$4,%xmm3,%xmm0,%xmm4
+	shrdl	$14,%r13d,%r13d
+	movl	%r14d,%r8d
+	movl	%ebx,%r12d
+	vpalignr	$4,%xmm1,%xmm2,%xmm7
+	shrdl	$9,%r14d,%r14d
+	xorl	%eax,%r13d
+	xorl	%ecx,%r12d
+	vpsrld	$7,%xmm4,%xmm6
+	shrdl	$5,%r13d,%r13d
+	xorl	%r8d,%r14d
+	andl	%eax,%r12d
+	vpaddd	%xmm7,%xmm3,%xmm3
+	xorl	%eax,%r13d
+	addl	48(%rsp),%edx
+	movl	%r8d,%r15d
+	vpsrld	$3,%xmm4,%xmm7
+	xorl	%ecx,%r12d
+	shrdl	$11,%r14d,%r14d
+	xorl	%r9d,%r15d
+	vpslld	$14,%xmm4,%xmm5
+	addl	%r12d,%edx
+	shrdl	$6,%r13d,%r13d
+	andl	%r15d,%edi
+	vpxor	%xmm6,%xmm7,%xmm4
+	xorl	%r8d,%r14d
+	addl	%r13d,%edx
+	xorl	%r9d,%edi
+	vpshufd	$250,%xmm2,%xmm7
+	shrdl	$2,%r14d,%r14d
+	addl	%edx,%r11d
+	addl	%edi,%edx
+	vpsrld	$11,%xmm6,%xmm6
+	movl	%r11d,%r13d
+	addl	%edx,%r14d
+	shrdl	$14,%r13d,%r13d
+	vpxor	%xmm5,%xmm4,%xmm4
+	movl	%r14d,%edx
+	movl	%eax,%r12d
+	shrdl	$9,%r14d,%r14d
+	vpslld	$11,%xmm5,%xmm5
+	xorl	%r11d,%r13d
+	xorl	%ebx,%r12d
+	shrdl	$5,%r13d,%r13d
+	vpxor	%xmm6,%xmm4,%xmm4
+	xorl	%edx,%r14d
+	andl	%r11d,%r12d
+	xorl	%r11d,%r13d
+	vpsrld	$10,%xmm7,%xmm6
+	addl	52(%rsp),%ecx
+	movl	%edx,%edi
+	xorl	%ebx,%r12d
+	vpxor	%xmm5,%xmm4,%xmm4
+	shrdl	$11,%r14d,%r14d
+	xorl	%r8d,%edi
+	addl	%r12d,%ecx
+	vpsrlq	$17,%xmm7,%xmm7
+	shrdl	$6,%r13d,%r13d
+	andl	%edi,%r15d
+	xorl	%edx,%r14d
+	vpaddd	%xmm4,%xmm3,%xmm3
+	addl	%r13d,%ecx
+	xorl	%r8d,%r15d
+	shrdl	$2,%r14d,%r14d
+	vpxor	%xmm7,%xmm6,%xmm6
+	addl	%ecx,%r10d
+	addl	%r15d,%ecx
+	movl	%r10d,%r13d
+	vpsrlq	$2,%xmm7,%xmm7
+	addl	%ecx,%r14d
+	shrdl	$14,%r13d,%r13d
+	movl	%r14d,%ecx
+	vpxor	%xmm7,%xmm6,%xmm6
+	movl	%r11d,%r12d
+	shrdl	$9,%r14d,%r14d
+	xorl	%r10d,%r13d
+	vpshufb	%xmm8,%xmm6,%xmm6
+	xorl	%eax,%r12d
+	shrdl	$5,%r13d,%r13d
+	xorl	%ecx,%r14d
+	vpaddd	%xmm6,%xmm3,%xmm3
+	andl	%r10d,%r12d
+	xorl	%r10d,%r13d
+	addl	56(%rsp),%ebx
+	vpshufd	$80,%xmm3,%xmm7
+	movl	%ecx,%r15d
+	xorl	%eax,%r12d
+	shrdl	$11,%r14d,%r14d
+	vpsrld	$10,%xmm7,%xmm6
+	xorl	%edx,%r15d
+	addl	%r12d,%ebx
+	shrdl	$6,%r13d,%r13d
+	vpsrlq	$17,%xmm7,%xmm7
+	andl	%r15d,%edi
+	xorl	%ecx,%r14d
+	addl	%r13d,%ebx
+	vpxor	%xmm7,%xmm6,%xmm6
+	xorl	%edx,%edi
+	shrdl	$2,%r14d,%r14d
+	addl	%ebx,%r9d
+	vpsrlq	$2,%xmm7,%xmm7
+	addl	%edi,%ebx
+	movl	%r9d,%r13d
+	addl	%ebx,%r14d
+	vpxor	%xmm7,%xmm6,%xmm6
+	shrdl	$14,%r13d,%r13d
+	movl	%r14d,%ebx
+	movl	%r10d,%r12d
+	vpshufb	%xmm9,%xmm6,%xmm6
+	shrdl	$9,%r14d,%r14d
+	xorl	%r9d,%r13d
+	xorl	%r11d,%r12d
+	vpaddd	%xmm6,%xmm3,%xmm3
+	shrdl	$5,%r13d,%r13d
+	xorl	%ebx,%r14d
+	andl	%r9d,%r12d
+	vpaddd	96(%rbp),%xmm3,%xmm6
+	xorl	%r9d,%r13d
+	addl	60(%rsp),%eax
+	movl	%ebx,%edi
+	xorl	%r11d,%r12d
+	shrdl	$11,%r14d,%r14d
+	xorl	%ecx,%edi
+	addl	%r12d,%eax
+	shrdl	$6,%r13d,%r13d
+	andl	%edi,%r15d
+	xorl	%ebx,%r14d
+	addl	%r13d,%eax
+	xorl	%ecx,%r15d
+	shrdl	$2,%r14d,%r14d
+	addl	%eax,%r8d
+	addl	%r15d,%eax
+	movl	%r8d,%r13d
+	addl	%eax,%r14d
+	vmovdqa	%xmm6,48(%rsp)
+	cmpb	$0,131(%rbp)
+	jne	L$avx_00_47
+	shrdl	$14,%r13d,%r13d
+	movl	%r14d,%eax
+	movl	%r9d,%r12d
+	shrdl	$9,%r14d,%r14d
+	xorl	%r8d,%r13d
+	xorl	%r10d,%r12d
+	shrdl	$5,%r13d,%r13d
+	xorl	%eax,%r14d
+	andl	%r8d,%r12d
+	xorl	%r8d,%r13d
+	addl	0(%rsp),%r11d
+	movl	%eax,%r15d
+	xorl	%r10d,%r12d
+	shrdl	$11,%r14d,%r14d
+	xorl	%ebx,%r15d
+	addl	%r12d,%r11d
+	shrdl	$6,%r13d,%r13d
+	andl	%r15d,%edi
+	xorl	%eax,%r14d
+	addl	%r13d,%r11d
+	xorl	%ebx,%edi
+	shrdl	$2,%r14d,%r14d
+	addl	%r11d,%edx
+	addl	%edi,%r11d
+	movl	%edx,%r13d
+	addl	%r11d,%r14d
+	shrdl	$14,%r13d,%r13d
+	movl	%r14d,%r11d
+	movl	%r8d,%r12d
+	shrdl	$9,%r14d,%r14d
+	xorl	%edx,%r13d
+	xorl	%r9d,%r12d
+	shrdl	$5,%r13d,%r13d
+	xorl	%r11d,%r14d
+	andl	%edx,%r12d
+	xorl	%edx,%r13d
+	addl	4(%rsp),%r10d
+	movl	%r11d,%edi
+	xorl	%r9d,%r12d
+	shrdl	$11,%r14d,%r14d
+	xorl	%eax,%edi
+	addl	%r12d,%r10d
+	shrdl	$6,%r13d,%r13d
+	andl	%edi,%r15d
+	xorl	%r11d,%r14d
+	addl	%r13d,%r10d
+	xorl	%eax,%r15d
+	shrdl	$2,%r14d,%r14d
+	addl	%r10d,%ecx
+	addl	%r15d,%r10d
+	movl	%ecx,%r13d
+	addl	%r10d,%r14d
+	shrdl	$14,%r13d,%r13d
+	movl	%r14d,%r10d
+	movl	%edx,%r12d
+	shrdl	$9,%r14d,%r14d
+	xorl	%ecx,%r13d
+	xorl	%r8d,%r12d
+	shrdl	$5,%r13d,%r13d
+	xorl	%r10d,%r14d
+	andl	%ecx,%r12d
+	xorl	%ecx,%r13d
+	addl	8(%rsp),%r9d
+	movl	%r10d,%r15d
+	xorl	%r8d,%r12d
+	shrdl	$11,%r14d,%r14d
+	xorl	%r11d,%r15d
+	addl	%r12d,%r9d
+	shrdl	$6,%r13d,%r13d
+	andl	%r15d,%edi
+	xorl	%r10d,%r14d
+	addl	%r13d,%r9d
+	xorl	%r11d,%edi
+	shrdl	$2,%r14d,%r14d
+	addl	%r9d,%ebx
+	addl	%edi,%r9d
+	movl	%ebx,%r13d
+	addl	%r9d,%r14d
+	shrdl	$14,%r13d,%r13d
+	movl	%r14d,%r9d
+	movl	%ecx,%r12d
+	shrdl	$9,%r14d,%r14d
+	xorl	%ebx,%r13d
+	xorl	%edx,%r12d
+	shrdl	$5,%r13d,%r13d
+	xorl	%r9d,%r14d
+	andl	%ebx,%r12d
+	xorl	%ebx,%r13d
+	addl	12(%rsp),%r8d
+	movl	%r9d,%edi
+	xorl	%edx,%r12d
+	shrdl	$11,%r14d,%r14d
+	xorl	%r10d,%edi
+	addl	%r12d,%r8d
+	shrdl	$6,%r13d,%r13d
+	andl	%edi,%r15d
+	xorl	%r9d,%r14d
+	addl	%r13d,%r8d
+	xorl	%r10d,%r15d
+	shrdl	$2,%r14d,%r14d
+	addl	%r8d,%eax
+	addl	%r15d,%r8d
+	movl	%eax,%r13d
+	addl	%r8d,%r14d
+	shrdl	$14,%r13d,%r13d
+	movl	%r14d,%r8d
+	movl	%ebx,%r12d
+	shrdl	$9,%r14d,%r14d
+	xorl	%eax,%r13d
+	xorl	%ecx,%r12d
+	shrdl	$5,%r13d,%r13d
+	xorl	%r8d,%r14d
+	andl	%eax,%r12d
+	xorl	%eax,%r13d
+	addl	16(%rsp),%edx
+	movl	%r8d,%r15d
+	xorl	%ecx,%r12d
+	shrdl	$11,%r14d,%r14d
+	xorl	%r9d,%r15d
+	addl	%r12d,%edx
+	shrdl	$6,%r13d,%r13d
+	andl	%r15d,%edi
+	xorl	%r8d,%r14d
+	addl	%r13d,%edx
+	xorl	%r9d,%edi
+	shrdl	$2,%r14d,%r14d
+	addl	%edx,%r11d
+	addl	%edi,%edx
+	movl	%r11d,%r13d
+	addl	%edx,%r14d
+	shrdl	$14,%r13d,%r13d
+	movl	%r14d,%edx
+	movl	%eax,%r12d
+	shrdl	$9,%r14d,%r14d
+	xorl	%r11d,%r13d
+	xorl	%ebx,%r12d
+	shrdl	$5,%r13d,%r13d
+	xorl	%edx,%r14d
+	andl	%r11d,%r12d
+	xorl	%r11d,%r13d
+	addl	20(%rsp),%ecx
+	movl	%edx,%edi
+	xorl	%ebx,%r12d
+	shrdl	$11,%r14d,%r14d
+	xorl	%r8d,%edi
+	addl	%r12d,%ecx
+	shrdl	$6,%r13d,%r13d
+	andl	%edi,%r15d
+	xorl	%edx,%r14d
+	addl	%r13d,%ecx
+	xorl	%r8d,%r15d
+	shrdl	$2,%r14d,%r14d
+	addl	%ecx,%r10d
+	addl	%r15d,%ecx
+	movl	%r10d,%r13d
+	addl	%ecx,%r14d
+	shrdl	$14,%r13d,%r13d
+	movl	%r14d,%ecx
+	movl	%r11d,%r12d
+	shrdl	$9,%r14d,%r14d
+	xorl	%r10d,%r13d
+	xorl	%eax,%r12d
+	shrdl	$5,%r13d,%r13d
+	xorl	%ecx,%r14d
+	andl	%r10d,%r12d
+	xorl	%r10d,%r13d
+	addl	24(%rsp),%ebx
+	movl	%ecx,%r15d
+	xorl	%eax,%r12d
+	shrdl	$11,%r14d,%r14d
+	xorl	%edx,%r15d
+	addl	%r12d,%ebx
+	shrdl	$6,%r13d,%r13d
+	andl	%r15d,%edi
+	xorl	%ecx,%r14d
+	addl	%r13d,%ebx
+	xorl	%edx,%edi
+	shrdl	$2,%r14d,%r14d
+	addl	%ebx,%r9d
+	addl	%edi,%ebx
+	movl	%r9d,%r13d
+	addl	%ebx,%r14d
+	shrdl	$14,%r13d,%r13d
+	movl	%r14d,%ebx
+	movl	%r10d,%r12d
+	shrdl	$9,%r14d,%r14d
+	xorl	%r9d,%r13d
+	xorl	%r11d,%r12d
+	shrdl	$5,%r13d,%r13d
+	xorl	%ebx,%r14d
+	andl	%r9d,%r12d
+	xorl	%r9d,%r13d
+	addl	28(%rsp),%eax
+	movl	%ebx,%edi
+	xorl	%r11d,%r12d
+	shrdl	$11,%r14d,%r14d
+	xorl	%ecx,%edi
+	addl	%r12d,%eax
+	shrdl	$6,%r13d,%r13d
+	andl	%edi,%r15d
+	xorl	%ebx,%r14d
+	addl	%r13d,%eax
+	xorl	%ecx,%r15d
+	shrdl	$2,%r14d,%r14d
+	addl	%eax,%r8d
+	addl	%r15d,%eax
+	movl	%r8d,%r13d
+	addl	%eax,%r14d
+	shrdl	$14,%r13d,%r13d
+	movl	%r14d,%eax
+	movl	%r9d,%r12d
+	shrdl	$9,%r14d,%r14d
+	xorl	%r8d,%r13d
+	xorl	%r10d,%r12d
+	shrdl	$5,%r13d,%r13d
+	xorl	%eax,%r14d
+	andl	%r8d,%r12d
+	xorl	%r8d,%r13d
+	addl	32(%rsp),%r11d
+	movl	%eax,%r15d
+	xorl	%r10d,%r12d
+	shrdl	$11,%r14d,%r14d
+	xorl	%ebx,%r15d
+	addl	%r12d,%r11d
+	shrdl	$6,%r13d,%r13d
+	andl	%r15d,%edi
+	xorl	%eax,%r14d
+	addl	%r13d,%r11d
+	xorl	%ebx,%edi
+	shrdl	$2,%r14d,%r14d
+	addl	%r11d,%edx
+	addl	%edi,%r11d
+	movl	%edx,%r13d
+	addl	%r11d,%r14d
+	shrdl	$14,%r13d,%r13d
+	movl	%r14d,%r11d
+	movl	%r8d,%r12d
+	shrdl	$9,%r14d,%r14d
+	xorl	%edx,%r13d
+	xorl	%r9d,%r12d
+	shrdl	$5,%r13d,%r13d
+	xorl	%r11d,%r14d
+	andl	%edx,%r12d
+	xorl	%edx,%r13d
+	addl	36(%rsp),%r10d
+	movl	%r11d,%edi
+	xorl	%r9d,%r12d
+	shrdl	$11,%r14d,%r14d
+	xorl	%eax,%edi
+	addl	%r12d,%r10d
+	shrdl	$6,%r13d,%r13d
+	andl	%edi,%r15d
+	xorl	%r11d,%r14d
+	addl	%r13d,%r10d
+	xorl	%eax,%r15d
+	shrdl	$2,%r14d,%r14d
+	addl	%r10d,%ecx
+	addl	%r15d,%r10d
+	movl	%ecx,%r13d
+	addl	%r10d,%r14d
+	shrdl	$14,%r13d,%r13d
+	movl	%r14d,%r10d
+	movl	%edx,%r12d
+	shrdl	$9,%r14d,%r14d
+	xorl	%ecx,%r13d
+	xorl	%r8d,%r12d
+	shrdl	$5,%r13d,%r13d
+	xorl	%r10d,%r14d
+	andl	%ecx,%r12d
+	xorl	%ecx,%r13d
+	addl	40(%rsp),%r9d
+	movl	%r10d,%r15d
+	xorl	%r8d,%r12d
+	shrdl	$11,%r14d,%r14d
+	xorl	%r11d,%r15d
+	addl	%r12d,%r9d
+	shrdl	$6,%r13d,%r13d
+	andl	%r15d,%edi
+	xorl	%r10d,%r14d
+	addl	%r13d,%r9d
+	xorl	%r11d,%edi
+	shrdl	$2,%r14d,%r14d
+	addl	%r9d,%ebx
+	addl	%edi,%r9d
+	movl	%ebx,%r13d
+	addl	%r9d,%r14d
+	shrdl	$14,%r13d,%r13d
+	movl	%r14d,%r9d
+	movl	%ecx,%r12d
+	shrdl	$9,%r14d,%r14d
+	xorl	%ebx,%r13d
+	xorl	%edx,%r12d
+	shrdl	$5,%r13d,%r13d
+	xorl	%r9d,%r14d
+	andl	%ebx,%r12d
+	xorl	%ebx,%r13d
+	addl	44(%rsp),%r8d
+	movl	%r9d,%edi
+	xorl	%edx,%r12d
+	shrdl	$11,%r14d,%r14d
+	xorl	%r10d,%edi
+	addl	%r12d,%r8d
+	shrdl	$6,%r13d,%r13d
+	andl	%edi,%r15d
+	xorl	%r9d,%r14d
+	addl	%r13d,%r8d
+	xorl	%r10d,%r15d
+	shrdl	$2,%r14d,%r14d
+	addl	%r8d,%eax
+	addl	%r15d,%r8d
+	movl	%eax,%r13d
+	addl	%r8d,%r14d
+	shrdl	$14,%r13d,%r13d
+	movl	%r14d,%r8d
+	movl	%ebx,%r12d
+	shrdl	$9,%r14d,%r14d
+	xorl	%eax,%r13d
+	xorl	%ecx,%r12d
+	shrdl	$5,%r13d,%r13d
+	xorl	%r8d,%r14d
+	andl	%eax,%r12d
+	xorl	%eax,%r13d
+	addl	48(%rsp),%edx
+	movl	%r8d,%r15d
+	xorl	%ecx,%r12d
+	shrdl	$11,%r14d,%r14d
+	xorl	%r9d,%r15d
+	addl	%r12d,%edx
+	shrdl	$6,%r13d,%r13d
+	andl	%r15d,%edi
+	xorl	%r8d,%r14d
+	addl	%r13d,%edx
+	xorl	%r9d,%edi
+	shrdl	$2,%r14d,%r14d
+	addl	%edx,%r11d
+	addl	%edi,%edx
+	movl	%r11d,%r13d
+	addl	%edx,%r14d
+	shrdl	$14,%r13d,%r13d
+	movl	%r14d,%edx
+	movl	%eax,%r12d
+	shrdl	$9,%r14d,%r14d
+	xorl	%r11d,%r13d
+	xorl	%ebx,%r12d
+	shrdl	$5,%r13d,%r13d
+	xorl	%edx,%r14d
+	andl	%r11d,%r12d
+	xorl	%r11d,%r13d
+	addl	52(%rsp),%ecx
+	movl	%edx,%edi
+	xorl	%ebx,%r12d
+	shrdl	$11,%r14d,%r14d
+	xorl	%r8d,%edi
+	addl	%r12d,%ecx
+	shrdl	$6,%r13d,%r13d
+	andl	%edi,%r15d
+	xorl	%edx,%r14d
+	addl	%r13d,%ecx
+	xorl	%r8d,%r15d
+	shrdl	$2,%r14d,%r14d
+	addl	%ecx,%r10d
+	addl	%r15d,%ecx
+	movl	%r10d,%r13d
+	addl	%ecx,%r14d
+	shrdl	$14,%r13d,%r13d
+	movl	%r14d,%ecx
+	movl	%r11d,%r12d
+	shrdl	$9,%r14d,%r14d
+	xorl	%r10d,%r13d
+	xorl	%eax,%r12d
+	shrdl	$5,%r13d,%r13d
+	xorl	%ecx,%r14d
+	andl	%r10d,%r12d
+	xorl	%r10d,%r13d
+	addl	56(%rsp),%ebx
+	movl	%ecx,%r15d
+	xorl	%eax,%r12d
+	shrdl	$11,%r14d,%r14d
+	xorl	%edx,%r15d
+	addl	%r12d,%ebx
+	shrdl	$6,%r13d,%r13d
+	andl	%r15d,%edi
+	xorl	%ecx,%r14d
+	addl	%r13d,%ebx
+	xorl	%edx,%edi
+	shrdl	$2,%r14d,%r14d
+	addl	%ebx,%r9d
+	addl	%edi,%ebx
+	movl	%r9d,%r13d
+	addl	%ebx,%r14d
+	shrdl	$14,%r13d,%r13d
+	movl	%r14d,%ebx
+	movl	%r10d,%r12d
+	shrdl	$9,%r14d,%r14d
+	xorl	%r9d,%r13d
+	xorl	%r11d,%r12d
+	shrdl	$5,%r13d,%r13d
+	xorl	%ebx,%r14d
+	andl	%r9d,%r12d
+	xorl	%r9d,%r13d
+	addl	60(%rsp),%eax
+	movl	%ebx,%edi
+	xorl	%r11d,%r12d
+	shrdl	$11,%r14d,%r14d
+	xorl	%ecx,%edi
+	addl	%r12d,%eax
+	shrdl	$6,%r13d,%r13d
+	andl	%edi,%r15d
+	xorl	%ebx,%r14d
+	addl	%r13d,%eax
+	xorl	%ecx,%r15d
+	shrdl	$2,%r14d,%r14d
+	addl	%eax,%r8d
+	addl	%r15d,%eax
+	movl	%r8d,%r13d
+	addl	%eax,%r14d
+	movq	64+0(%rsp),%rdi
+	movl	%r14d,%eax
+
+	addl	0(%rdi),%eax
+	leaq	64(%rsi),%rsi
+	addl	4(%rdi),%ebx
+	addl	8(%rdi),%ecx
+	addl	12(%rdi),%edx
+	addl	16(%rdi),%r8d
+	addl	20(%rdi),%r9d
+	addl	24(%rdi),%r10d
+	addl	28(%rdi),%r11d
+
+	cmpq	64+16(%rsp),%rsi
+
+	movl	%eax,0(%rdi)
+	movl	%ebx,4(%rdi)
+	movl	%ecx,8(%rdi)
+	movl	%edx,12(%rdi)
+	movl	%r8d,16(%rdi)
+	movl	%r9d,20(%rdi)
+	movl	%r10d,24(%rdi)
+	movl	%r11d,28(%rdi)
+	jb	L$loop_avx
+
+	movq	64+24(%rsp),%rsi
+	vzeroupper
+	movq	(%rsi),%r15
+	movq	8(%rsi),%r14
+	movq	16(%rsi),%r13
+	movq	24(%rsi),%r12
+	movq	32(%rsi),%rbp
+	movq	40(%rsi),%rbx
+	leaq	48(%rsi),%rsp
+L$epilogue_avx:
+	.byte	0xf3,0xc3
+
 #endif
diff --git a/packager/third_party/boringssl/mac-x86_64/crypto/sha/sha512-x86_64.S b/packager/third_party/boringssl/mac-x86_64/crypto/sha/sha512-x86_64.S
index 2f5d912425..aeabd3f43a 100644
--- a/packager/third_party/boringssl/mac-x86_64/crypto/sha/sha512-x86_64.S
+++ b/packager/third_party/boringssl/mac-x86_64/crypto/sha/sha512-x86_64.S
@@ -7,6 +7,17 @@
 
 .p2align	4
 _sha512_block_data_order:
+	leaq	_OPENSSL_ia32cap_P(%rip),%r11
+	movl	0(%r11),%r9d
+	movl	4(%r11),%r10d
+	movl	8(%r11),%r11d
+	testl	$2048,%r10d
+	jnz	L$xop_shortcut
+	andl	$1073741824,%r9d
+	andl	$268435968,%r10d
+	orl	%r9d,%r10d
+	cmpl	$1342177792,%r10d
+	je	L$avx_shortcut
 	pushq	%rbx
 	pushq	%rbp
 	pushq	%r12
@@ -1783,4 +1794,2234 @@ K512:
 .quad	0x0001020304050607,0x08090a0b0c0d0e0f
 .quad	0x0001020304050607,0x08090a0b0c0d0e0f
 .byte	83,72,65,53,49,50,32,98,108,111,99,107,32,116,114,97,110,115,102,111,114,109,32,102,111,114,32,120,56,54,95,54,52,44,32,67,82,89,80,84,79,71,65,77,83,32,98,121,32,60,97,112,112,114,111,64,111,112,101,110,115,115,108,46,111,114,103,62,0
+
+.p2align	6
+sha512_block_data_order_xop:
+L$xop_shortcut:
+	pushq	%rbx
+	pushq	%rbp
+	pushq	%r12
+	pushq	%r13
+	pushq	%r14
+	pushq	%r15
+	movq	%rsp,%r11
+	shlq	$4,%rdx
+	subq	$160,%rsp
+	leaq	(%rsi,%rdx,8),%rdx
+	andq	$-64,%rsp
+	movq	%rdi,128+0(%rsp)
+	movq	%rsi,128+8(%rsp)
+	movq	%rdx,128+16(%rsp)
+	movq	%r11,128+24(%rsp)
+L$prologue_xop:
+
+	vzeroupper
+	movq	0(%rdi),%rax
+	movq	8(%rdi),%rbx
+	movq	16(%rdi),%rcx
+	movq	24(%rdi),%rdx
+	movq	32(%rdi),%r8
+	movq	40(%rdi),%r9
+	movq	48(%rdi),%r10
+	movq	56(%rdi),%r11
+	jmp	L$loop_xop
+.p2align	4
+L$loop_xop:
+	vmovdqa	K512+1280(%rip),%xmm11
+	vmovdqu	0(%rsi),%xmm0
+	leaq	K512+128(%rip),%rbp
+	vmovdqu	16(%rsi),%xmm1
+	vmovdqu	32(%rsi),%xmm2
+	vpshufb	%xmm11,%xmm0,%xmm0
+	vmovdqu	48(%rsi),%xmm3
+	vpshufb	%xmm11,%xmm1,%xmm1
+	vmovdqu	64(%rsi),%xmm4
+	vpshufb	%xmm11,%xmm2,%xmm2
+	vmovdqu	80(%rsi),%xmm5
+	vpshufb	%xmm11,%xmm3,%xmm3
+	vmovdqu	96(%rsi),%xmm6
+	vpshufb	%xmm11,%xmm4,%xmm4
+	vmovdqu	112(%rsi),%xmm7
+	vpshufb	%xmm11,%xmm5,%xmm5
+	vpaddq	-128(%rbp),%xmm0,%xmm8
+	vpshufb	%xmm11,%xmm6,%xmm6
+	vpaddq	-96(%rbp),%xmm1,%xmm9
+	vpshufb	%xmm11,%xmm7,%xmm7
+	vpaddq	-64(%rbp),%xmm2,%xmm10
+	vpaddq	-32(%rbp),%xmm3,%xmm11
+	vmovdqa	%xmm8,0(%rsp)
+	vpaddq	0(%rbp),%xmm4,%xmm8
+	vmovdqa	%xmm9,16(%rsp)
+	vpaddq	32(%rbp),%xmm5,%xmm9
+	vmovdqa	%xmm10,32(%rsp)
+	vpaddq	64(%rbp),%xmm6,%xmm10
+	vmovdqa	%xmm11,48(%rsp)
+	vpaddq	96(%rbp),%xmm7,%xmm11
+	vmovdqa	%xmm8,64(%rsp)
+	movq	%rax,%r14
+	vmovdqa	%xmm9,80(%rsp)
+	movq	%rbx,%rdi
+	vmovdqa	%xmm10,96(%rsp)
+	xorq	%rcx,%rdi
+	vmovdqa	%xmm11,112(%rsp)
+	movq	%r8,%r13
+	jmp	L$xop_00_47
+
+.p2align	4
+L$xop_00_47:
+	addq	$256,%rbp
+	vpalignr	$8,%xmm0,%xmm1,%xmm8
+	rorq	$23,%r13
+	movq	%r14,%rax
+	vpalignr	$8,%xmm4,%xmm5,%xmm11
+	movq	%r9,%r12
+	rorq	$5,%r14
+.byte	143,72,120,195,200,56
+	xorq	%r8,%r13
+	xorq	%r10,%r12
+	vpsrlq	$7,%xmm8,%xmm8
+	rorq	$4,%r13
+	xorq	%rax,%r14
+	vpaddq	%xmm11,%xmm0,%xmm0
+	andq	%r8,%r12
+	xorq	%r8,%r13
+	addq	0(%rsp),%r11
+	movq	%rax,%r15
+.byte	143,72,120,195,209,7
+	xorq	%r10,%r12
+	rorq	$6,%r14
+	vpxor	%xmm9,%xmm8,%xmm8
+	xorq	%rbx,%r15
+	addq	%r12,%r11
+	rorq	$14,%r13
+	andq	%r15,%rdi
+.byte	143,104,120,195,223,3
+	xorq	%rax,%r14
+	addq	%r13,%r11
+	vpxor	%xmm10,%xmm8,%xmm8
+	xorq	%rbx,%rdi
+	rorq	$28,%r14
+	vpsrlq	$6,%xmm7,%xmm10
+	addq	%r11,%rdx
+	addq	%rdi,%r11
+	vpaddq	%xmm8,%xmm0,%xmm0
+	movq	%rdx,%r13
+	addq	%r11,%r14
+.byte	143,72,120,195,203,42
+	rorq	$23,%r13
+	movq	%r14,%r11
+	vpxor	%xmm10,%xmm11,%xmm11
+	movq	%r8,%r12
+	rorq	$5,%r14
+	xorq	%rdx,%r13
+	xorq	%r9,%r12
+	vpxor	%xmm9,%xmm11,%xmm11
+	rorq	$4,%r13
+	xorq	%r11,%r14
+	andq	%rdx,%r12
+	xorq	%rdx,%r13
+	vpaddq	%xmm11,%xmm0,%xmm0
+	addq	8(%rsp),%r10
+	movq	%r11,%rdi
+	xorq	%r9,%r12
+	rorq	$6,%r14
+	vpaddq	-128(%rbp),%xmm0,%xmm10
+	xorq	%rax,%rdi
+	addq	%r12,%r10
+	rorq	$14,%r13
+	andq	%rdi,%r15
+	xorq	%r11,%r14
+	addq	%r13,%r10
+	xorq	%rax,%r15
+	rorq	$28,%r14
+	addq	%r10,%rcx
+	addq	%r15,%r10
+	movq	%rcx,%r13
+	addq	%r10,%r14
+	vmovdqa	%xmm10,0(%rsp)
+	vpalignr	$8,%xmm1,%xmm2,%xmm8
+	rorq	$23,%r13
+	movq	%r14,%r10
+	vpalignr	$8,%xmm5,%xmm6,%xmm11
+	movq	%rdx,%r12
+	rorq	$5,%r14
+.byte	143,72,120,195,200,56
+	xorq	%rcx,%r13
+	xorq	%r8,%r12
+	vpsrlq	$7,%xmm8,%xmm8
+	rorq	$4,%r13
+	xorq	%r10,%r14
+	vpaddq	%xmm11,%xmm1,%xmm1
+	andq	%rcx,%r12
+	xorq	%rcx,%r13
+	addq	16(%rsp),%r9
+	movq	%r10,%r15
+.byte	143,72,120,195,209,7
+	xorq	%r8,%r12
+	rorq	$6,%r14
+	vpxor	%xmm9,%xmm8,%xmm8
+	xorq	%r11,%r15
+	addq	%r12,%r9
+	rorq	$14,%r13
+	andq	%r15,%rdi
+.byte	143,104,120,195,216,3
+	xorq	%r10,%r14
+	addq	%r13,%r9
+	vpxor	%xmm10,%xmm8,%xmm8
+	xorq	%r11,%rdi
+	rorq	$28,%r14
+	vpsrlq	$6,%xmm0,%xmm10
+	addq	%r9,%rbx
+	addq	%rdi,%r9
+	vpaddq	%xmm8,%xmm1,%xmm1
+	movq	%rbx,%r13
+	addq	%r9,%r14
+.byte	143,72,120,195,203,42
+	rorq	$23,%r13
+	movq	%r14,%r9
+	vpxor	%xmm10,%xmm11,%xmm11
+	movq	%rcx,%r12
+	rorq	$5,%r14
+	xorq	%rbx,%r13
+	xorq	%rdx,%r12
+	vpxor	%xmm9,%xmm11,%xmm11
+	rorq	$4,%r13
+	xorq	%r9,%r14
+	andq	%rbx,%r12
+	xorq	%rbx,%r13
+	vpaddq	%xmm11,%xmm1,%xmm1
+	addq	24(%rsp),%r8
+	movq	%r9,%rdi
+	xorq	%rdx,%r12
+	rorq	$6,%r14
+	vpaddq	-96(%rbp),%xmm1,%xmm10
+	xorq	%r10,%rdi
+	addq	%r12,%r8
+	rorq	$14,%r13
+	andq	%rdi,%r15
+	xorq	%r9,%r14
+	addq	%r13,%r8
+	xorq	%r10,%r15
+	rorq	$28,%r14
+	addq	%r8,%rax
+	addq	%r15,%r8
+	movq	%rax,%r13
+	addq	%r8,%r14
+	vmovdqa	%xmm10,16(%rsp)
+	vpalignr	$8,%xmm2,%xmm3,%xmm8
+	rorq	$23,%r13
+	movq	%r14,%r8
+	vpalignr	$8,%xmm6,%xmm7,%xmm11
+	movq	%rbx,%r12
+	rorq	$5,%r14
+.byte	143,72,120,195,200,56
+	xorq	%rax,%r13
+	xorq	%rcx,%r12
+	vpsrlq	$7,%xmm8,%xmm8
+	rorq	$4,%r13
+	xorq	%r8,%r14
+	vpaddq	%xmm11,%xmm2,%xmm2
+	andq	%rax,%r12
+	xorq	%rax,%r13
+	addq	32(%rsp),%rdx
+	movq	%r8,%r15
+.byte	143,72,120,195,209,7
+	xorq	%rcx,%r12
+	rorq	$6,%r14
+	vpxor	%xmm9,%xmm8,%xmm8
+	xorq	%r9,%r15
+	addq	%r12,%rdx
+	rorq	$14,%r13
+	andq	%r15,%rdi
+.byte	143,104,120,195,217,3
+	xorq	%r8,%r14
+	addq	%r13,%rdx
+	vpxor	%xmm10,%xmm8,%xmm8
+	xorq	%r9,%rdi
+	rorq	$28,%r14
+	vpsrlq	$6,%xmm1,%xmm10
+	addq	%rdx,%r11
+	addq	%rdi,%rdx
+	vpaddq	%xmm8,%xmm2,%xmm2
+	movq	%r11,%r13
+	addq	%rdx,%r14
+.byte	143,72,120,195,203,42
+	rorq	$23,%r13
+	movq	%r14,%rdx
+	vpxor	%xmm10,%xmm11,%xmm11
+	movq	%rax,%r12
+	rorq	$5,%r14
+	xorq	%r11,%r13
+	xorq	%rbx,%r12
+	vpxor	%xmm9,%xmm11,%xmm11
+	rorq	$4,%r13
+	xorq	%rdx,%r14
+	andq	%r11,%r12
+	xorq	%r11,%r13
+	vpaddq	%xmm11,%xmm2,%xmm2
+	addq	40(%rsp),%rcx
+	movq	%rdx,%rdi
+	xorq	%rbx,%r12
+	rorq	$6,%r14
+	vpaddq	-64(%rbp),%xmm2,%xmm10
+	xorq	%r8,%rdi
+	addq	%r12,%rcx
+	rorq	$14,%r13
+	andq	%rdi,%r15
+	xorq	%rdx,%r14
+	addq	%r13,%rcx
+	xorq	%r8,%r15
+	rorq	$28,%r14
+	addq	%rcx,%r10
+	addq	%r15,%rcx
+	movq	%r10,%r13
+	addq	%rcx,%r14
+	vmovdqa	%xmm10,32(%rsp)
+	vpalignr	$8,%xmm3,%xmm4,%xmm8
+	rorq	$23,%r13
+	movq	%r14,%rcx
+	vpalignr	$8,%xmm7,%xmm0,%xmm11
+	movq	%r11,%r12
+	rorq	$5,%r14
+.byte	143,72,120,195,200,56
+	xorq	%r10,%r13
+	xorq	%rax,%r12
+	vpsrlq	$7,%xmm8,%xmm8
+	rorq	$4,%r13
+	xorq	%rcx,%r14
+	vpaddq	%xmm11,%xmm3,%xmm3
+	andq	%r10,%r12
+	xorq	%r10,%r13
+	addq	48(%rsp),%rbx
+	movq	%rcx,%r15
+.byte	143,72,120,195,209,7
+	xorq	%rax,%r12
+	rorq	$6,%r14
+	vpxor	%xmm9,%xmm8,%xmm8
+	xorq	%rdx,%r15
+	addq	%r12,%rbx
+	rorq	$14,%r13
+	andq	%r15,%rdi
+.byte	143,104,120,195,218,3
+	xorq	%rcx,%r14
+	addq	%r13,%rbx
+	vpxor	%xmm10,%xmm8,%xmm8
+	xorq	%rdx,%rdi
+	rorq	$28,%r14
+	vpsrlq	$6,%xmm2,%xmm10
+	addq	%rbx,%r9
+	addq	%rdi,%rbx
+	vpaddq	%xmm8,%xmm3,%xmm3
+	movq	%r9,%r13
+	addq	%rbx,%r14
+.byte	143,72,120,195,203,42
+	rorq	$23,%r13
+	movq	%r14,%rbx
+	vpxor	%xmm10,%xmm11,%xmm11
+	movq	%r10,%r12
+	rorq	$5,%r14
+	xorq	%r9,%r13
+	xorq	%r11,%r12
+	vpxor	%xmm9,%xmm11,%xmm11
+	rorq	$4,%r13
+	xorq	%rbx,%r14
+	andq	%r9,%r12
+	xorq	%r9,%r13
+	vpaddq	%xmm11,%xmm3,%xmm3
+	addq	56(%rsp),%rax
+	movq	%rbx,%rdi
+	xorq	%r11,%r12
+	rorq	$6,%r14
+	vpaddq	-32(%rbp),%xmm3,%xmm10
+	xorq	%rcx,%rdi
+	addq	%r12,%rax
+	rorq	$14,%r13
+	andq	%rdi,%r15
+	xorq	%rbx,%r14
+	addq	%r13,%rax
+	xorq	%rcx,%r15
+	rorq	$28,%r14
+	addq	%rax,%r8
+	addq	%r15,%rax
+	movq	%r8,%r13
+	addq	%rax,%r14
+	vmovdqa	%xmm10,48(%rsp)
+	vpalignr	$8,%xmm4,%xmm5,%xmm8
+	rorq	$23,%r13
+	movq	%r14,%rax
+	vpalignr	$8,%xmm0,%xmm1,%xmm11
+	movq	%r9,%r12
+	rorq	$5,%r14
+.byte	143,72,120,195,200,56
+	xorq	%r8,%r13
+	xorq	%r10,%r12
+	vpsrlq	$7,%xmm8,%xmm8
+	rorq	$4,%r13
+	xorq	%rax,%r14
+	vpaddq	%xmm11,%xmm4,%xmm4
+	andq	%r8,%r12
+	xorq	%r8,%r13
+	addq	64(%rsp),%r11
+	movq	%rax,%r15
+.byte	143,72,120,195,209,7
+	xorq	%r10,%r12
+	rorq	$6,%r14
+	vpxor	%xmm9,%xmm8,%xmm8
+	xorq	%rbx,%r15
+	addq	%r12,%r11
+	rorq	$14,%r13
+	andq	%r15,%rdi
+.byte	143,104,120,195,219,3
+	xorq	%rax,%r14
+	addq	%r13,%r11
+	vpxor	%xmm10,%xmm8,%xmm8
+	xorq	%rbx,%rdi
+	rorq	$28,%r14
+	vpsrlq	$6,%xmm3,%xmm10
+	addq	%r11,%rdx
+	addq	%rdi,%r11
+	vpaddq	%xmm8,%xmm4,%xmm4
+	movq	%rdx,%r13
+	addq	%r11,%r14
+.byte	143,72,120,195,203,42
+	rorq	$23,%r13
+	movq	%r14,%r11
+	vpxor	%xmm10,%xmm11,%xmm11
+	movq	%r8,%r12
+	rorq	$5,%r14
+	xorq	%rdx,%r13
+	xorq	%r9,%r12
+	vpxor	%xmm9,%xmm11,%xmm11
+	rorq	$4,%r13
+	xorq	%r11,%r14
+	andq	%rdx,%r12
+	xorq	%rdx,%r13
+	vpaddq	%xmm11,%xmm4,%xmm4
+	addq	72(%rsp),%r10
+	movq	%r11,%rdi
+	xorq	%r9,%r12
+	rorq	$6,%r14
+	vpaddq	0(%rbp),%xmm4,%xmm10
+	xorq	%rax,%rdi
+	addq	%r12,%r10
+	rorq	$14,%r13
+	andq	%rdi,%r15
+	xorq	%r11,%r14
+	addq	%r13,%r10
+	xorq	%rax,%r15
+	rorq	$28,%r14
+	addq	%r10,%rcx
+	addq	%r15,%r10
+	movq	%rcx,%r13
+	addq	%r10,%r14
+	vmovdqa	%xmm10,64(%rsp)
+	vpalignr	$8,%xmm5,%xmm6,%xmm8
+	rorq	$23,%r13
+	movq	%r14,%r10
+	vpalignr	$8,%xmm1,%xmm2,%xmm11
+	movq	%rdx,%r12
+	rorq	$5,%r14
+.byte	143,72,120,195,200,56
+	xorq	%rcx,%r13
+	xorq	%r8,%r12
+	vpsrlq	$7,%xmm8,%xmm8
+	rorq	$4,%r13
+	xorq	%r10,%r14
+	vpaddq	%xmm11,%xmm5,%xmm5
+	andq	%rcx,%r12
+	xorq	%rcx,%r13
+	addq	80(%rsp),%r9
+	movq	%r10,%r15
+.byte	143,72,120,195,209,7
+	xorq	%r8,%r12
+	rorq	$6,%r14
+	vpxor	%xmm9,%xmm8,%xmm8
+	xorq	%r11,%r15
+	addq	%r12,%r9
+	rorq	$14,%r13
+	andq	%r15,%rdi
+.byte	143,104,120,195,220,3
+	xorq	%r10,%r14
+	addq	%r13,%r9
+	vpxor	%xmm10,%xmm8,%xmm8
+	xorq	%r11,%rdi
+	rorq	$28,%r14
+	vpsrlq	$6,%xmm4,%xmm10
+	addq	%r9,%rbx
+	addq	%rdi,%r9
+	vpaddq	%xmm8,%xmm5,%xmm5
+	movq	%rbx,%r13
+	addq	%r9,%r14
+.byte	143,72,120,195,203,42
+	rorq	$23,%r13
+	movq	%r14,%r9
+	vpxor	%xmm10,%xmm11,%xmm11
+	movq	%rcx,%r12
+	rorq	$5,%r14
+	xorq	%rbx,%r13
+	xorq	%rdx,%r12
+	vpxor	%xmm9,%xmm11,%xmm11
+	rorq	$4,%r13
+	xorq	%r9,%r14
+	andq	%rbx,%r12
+	xorq	%rbx,%r13
+	vpaddq	%xmm11,%xmm5,%xmm5
+	addq	88(%rsp),%r8
+	movq	%r9,%rdi
+	xorq	%rdx,%r12
+	rorq	$6,%r14
+	vpaddq	32(%rbp),%xmm5,%xmm10
+	xorq	%r10,%rdi
+	addq	%r12,%r8
+	rorq	$14,%r13
+	andq	%rdi,%r15
+	xorq	%r9,%r14
+	addq	%r13,%r8
+	xorq	%r10,%r15
+	rorq	$28,%r14
+	addq	%r8,%rax
+	addq	%r15,%r8
+	movq	%rax,%r13
+	addq	%r8,%r14
+	vmovdqa	%xmm10,80(%rsp)
+	vpalignr	$8,%xmm6,%xmm7,%xmm8
+	rorq	$23,%r13
+	movq	%r14,%r8
+	vpalignr	$8,%xmm2,%xmm3,%xmm11
+	movq	%rbx,%r12
+	rorq	$5,%r14
+.byte	143,72,120,195,200,56
+	xorq	%rax,%r13
+	xorq	%rcx,%r12
+	vpsrlq	$7,%xmm8,%xmm8
+	rorq	$4,%r13
+	xorq	%r8,%r14
+	vpaddq	%xmm11,%xmm6,%xmm6
+	andq	%rax,%r12
+	xorq	%rax,%r13
+	addq	96(%rsp),%rdx
+	movq	%r8,%r15
+.byte	143,72,120,195,209,7
+	xorq	%rcx,%r12
+	rorq	$6,%r14
+	vpxor	%xmm9,%xmm8,%xmm8
+	xorq	%r9,%r15
+	addq	%r12,%rdx
+	rorq	$14,%r13
+	andq	%r15,%rdi
+.byte	143,104,120,195,221,3
+	xorq	%r8,%r14
+	addq	%r13,%rdx
+	vpxor	%xmm10,%xmm8,%xmm8
+	xorq	%r9,%rdi
+	rorq	$28,%r14
+	vpsrlq	$6,%xmm5,%xmm10
+	addq	%rdx,%r11
+	addq	%rdi,%rdx
+	vpaddq	%xmm8,%xmm6,%xmm6
+	movq	%r11,%r13
+	addq	%rdx,%r14
+.byte	143,72,120,195,203,42
+	rorq	$23,%r13
+	movq	%r14,%rdx
+	vpxor	%xmm10,%xmm11,%xmm11
+	movq	%rax,%r12
+	rorq	$5,%r14
+	xorq	%r11,%r13
+	xorq	%rbx,%r12
+	vpxor	%xmm9,%xmm11,%xmm11
+	rorq	$4,%r13
+	xorq	%rdx,%r14
+	andq	%r11,%r12
+	xorq	%r11,%r13
+	vpaddq	%xmm11,%xmm6,%xmm6
+	addq	104(%rsp),%rcx
+	movq	%rdx,%rdi
+	xorq	%rbx,%r12
+	rorq	$6,%r14
+	vpaddq	64(%rbp),%xmm6,%xmm10
+	xorq	%r8,%rdi
+	addq	%r12,%rcx
+	rorq	$14,%r13
+	andq	%rdi,%r15
+	xorq	%rdx,%r14
+	addq	%r13,%rcx
+	xorq	%r8,%r15
+	rorq	$28,%r14
+	addq	%rcx,%r10
+	addq	%r15,%rcx
+	movq	%r10,%r13
+	addq	%rcx,%r14
+	vmovdqa	%xmm10,96(%rsp)
+	vpalignr	$8,%xmm7,%xmm0,%xmm8
+	rorq	$23,%r13
+	movq	%r14,%rcx
+	vpalignr	$8,%xmm3,%xmm4,%xmm11
+	movq	%r11,%r12
+	rorq	$5,%r14
+.byte	143,72,120,195,200,56
+	xorq	%r10,%r13
+	xorq	%rax,%r12
+	vpsrlq	$7,%xmm8,%xmm8
+	rorq	$4,%r13
+	xorq	%rcx,%r14
+	vpaddq	%xmm11,%xmm7,%xmm7
+	andq	%r10,%r12
+	xorq	%r10,%r13
+	addq	112(%rsp),%rbx
+	movq	%rcx,%r15
+.byte	143,72,120,195,209,7
+	xorq	%rax,%r12
+	rorq	$6,%r14
+	vpxor	%xmm9,%xmm8,%xmm8
+	xorq	%rdx,%r15
+	addq	%r12,%rbx
+	rorq	$14,%r13
+	andq	%r15,%rdi
+.byte	143,104,120,195,222,3
+	xorq	%rcx,%r14
+	addq	%r13,%rbx
+	vpxor	%xmm10,%xmm8,%xmm8
+	xorq	%rdx,%rdi
+	rorq	$28,%r14
+	vpsrlq	$6,%xmm6,%xmm10
+	addq	%rbx,%r9
+	addq	%rdi,%rbx
+	vpaddq	%xmm8,%xmm7,%xmm7
+	movq	%r9,%r13
+	addq	%rbx,%r14
+.byte	143,72,120,195,203,42
+	rorq	$23,%r13
+	movq	%r14,%rbx
+	vpxor	%xmm10,%xmm11,%xmm11
+	movq	%r10,%r12
+	rorq	$5,%r14
+	xorq	%r9,%r13
+	xorq	%r11,%r12
+	vpxor	%xmm9,%xmm11,%xmm11
+	rorq	$4,%r13
+	xorq	%rbx,%r14
+	andq	%r9,%r12
+	xorq	%r9,%r13
+	vpaddq	%xmm11,%xmm7,%xmm7
+	addq	120(%rsp),%rax
+	movq	%rbx,%rdi
+	xorq	%r11,%r12
+	rorq	$6,%r14
+	vpaddq	96(%rbp),%xmm7,%xmm10
+	xorq	%rcx,%rdi
+	addq	%r12,%rax
+	rorq	$14,%r13
+	andq	%rdi,%r15
+	xorq	%rbx,%r14
+	addq	%r13,%rax
+	xorq	%rcx,%r15
+	rorq	$28,%r14
+	addq	%rax,%r8
+	addq	%r15,%rax
+	movq	%r8,%r13
+	addq	%rax,%r14
+	vmovdqa	%xmm10,112(%rsp)
+	cmpb	$0,135(%rbp)
+	jne	L$xop_00_47
+	rorq	$23,%r13
+	movq	%r14,%rax
+	movq	%r9,%r12
+	rorq	$5,%r14
+	xorq	%r8,%r13
+	xorq	%r10,%r12
+	rorq	$4,%r13
+	xorq	%rax,%r14
+	andq	%r8,%r12
+	xorq	%r8,%r13
+	addq	0(%rsp),%r11
+	movq	%rax,%r15
+	xorq	%r10,%r12
+	rorq	$6,%r14
+	xorq	%rbx,%r15
+	addq	%r12,%r11
+	rorq	$14,%r13
+	andq	%r15,%rdi
+	xorq	%rax,%r14
+	addq	%r13,%r11
+	xorq	%rbx,%rdi
+	rorq	$28,%r14
+	addq	%r11,%rdx
+	addq	%rdi,%r11
+	movq	%rdx,%r13
+	addq	%r11,%r14
+	rorq	$23,%r13
+	movq	%r14,%r11
+	movq	%r8,%r12
+	rorq	$5,%r14
+	xorq	%rdx,%r13
+	xorq	%r9,%r12
+	rorq	$4,%r13
+	xorq	%r11,%r14
+	andq	%rdx,%r12
+	xorq	%rdx,%r13
+	addq	8(%rsp),%r10
+	movq	%r11,%rdi
+	xorq	%r9,%r12
+	rorq	$6,%r14
+	xorq	%rax,%rdi
+	addq	%r12,%r10
+	rorq	$14,%r13
+	andq	%rdi,%r15
+	xorq	%r11,%r14
+	addq	%r13,%r10
+	xorq	%rax,%r15
+	rorq	$28,%r14
+	addq	%r10,%rcx
+	addq	%r15,%r10
+	movq	%rcx,%r13
+	addq	%r10,%r14
+	rorq	$23,%r13
+	movq	%r14,%r10
+	movq	%rdx,%r12
+	rorq	$5,%r14
+	xorq	%rcx,%r13
+	xorq	%r8,%r12
+	rorq	$4,%r13
+	xorq	%r10,%r14
+	andq	%rcx,%r12
+	xorq	%rcx,%r13
+	addq	16(%rsp),%r9
+	movq	%r10,%r15
+	xorq	%r8,%r12
+	rorq	$6,%r14
+	xorq	%r11,%r15
+	addq	%r12,%r9
+	rorq	$14,%r13
+	andq	%r15,%rdi
+	xorq	%r10,%r14
+	addq	%r13,%r9
+	xorq	%r11,%rdi
+	rorq	$28,%r14
+	addq	%r9,%rbx
+	addq	%rdi,%r9
+	movq	%rbx,%r13
+	addq	%r9,%r14
+	rorq	$23,%r13
+	movq	%r14,%r9
+	movq	%rcx,%r12
+	rorq	$5,%r14
+	xorq	%rbx,%r13
+	xorq	%rdx,%r12
+	rorq	$4,%r13
+	xorq	%r9,%r14
+	andq	%rbx,%r12
+	xorq	%rbx,%r13
+	addq	24(%rsp),%r8
+	movq	%r9,%rdi
+	xorq	%rdx,%r12
+	rorq	$6,%r14
+	xorq	%r10,%rdi
+	addq	%r12,%r8
+	rorq	$14,%r13
+	andq	%rdi,%r15
+	xorq	%r9,%r14
+	addq	%r13,%r8
+	xorq	%r10,%r15
+	rorq	$28,%r14
+	addq	%r8,%rax
+	addq	%r15,%r8
+	movq	%rax,%r13
+	addq	%r8,%r14
+	rorq	$23,%r13
+	movq	%r14,%r8
+	movq	%rbx,%r12
+	rorq	$5,%r14
+	xorq	%rax,%r13
+	xorq	%rcx,%r12
+	rorq	$4,%r13
+	xorq	%r8,%r14
+	andq	%rax,%r12
+	xorq	%rax,%r13
+	addq	32(%rsp),%rdx
+	movq	%r8,%r15
+	xorq	%rcx,%r12
+	rorq	$6,%r14
+	xorq	%r9,%r15
+	addq	%r12,%rdx
+	rorq	$14,%r13
+	andq	%r15,%rdi
+	xorq	%r8,%r14
+	addq	%r13,%rdx
+	xorq	%r9,%rdi
+	rorq	$28,%r14
+	addq	%rdx,%r11
+	addq	%rdi,%rdx
+	movq	%r11,%r13
+	addq	%rdx,%r14
+	rorq	$23,%r13
+	movq	%r14,%rdx
+	movq	%rax,%r12
+	rorq	$5,%r14
+	xorq	%r11,%r13
+	xorq	%rbx,%r12
+	rorq	$4,%r13
+	xorq	%rdx,%r14
+	andq	%r11,%r12
+	xorq	%r11,%r13
+	addq	40(%rsp),%rcx
+	movq	%rdx,%rdi
+	xorq	%rbx,%r12
+	rorq	$6,%r14
+	xorq	%r8,%rdi
+	addq	%r12,%rcx
+	rorq	$14,%r13
+	andq	%rdi,%r15
+	xorq	%rdx,%r14
+	addq	%r13,%rcx
+	xorq	%r8,%r15
+	rorq	$28,%r14
+	addq	%rcx,%r10
+	addq	%r15,%rcx
+	movq	%r10,%r13
+	addq	%rcx,%r14
+	rorq	$23,%r13
+	movq	%r14,%rcx
+	movq	%r11,%r12
+	rorq	$5,%r14
+	xorq	%r10,%r13
+	xorq	%rax,%r12
+	rorq	$4,%r13
+	xorq	%rcx,%r14
+	andq	%r10,%r12
+	xorq	%r10,%r13
+	addq	48(%rsp),%rbx
+	movq	%rcx,%r15
+	xorq	%rax,%r12
+	rorq	$6,%r14
+	xorq	%rdx,%r15
+	addq	%r12,%rbx
+	rorq	$14,%r13
+	andq	%r15,%rdi
+	xorq	%rcx,%r14
+	addq	%r13,%rbx
+	xorq	%rdx,%rdi
+	rorq	$28,%r14
+	addq	%rbx,%r9
+	addq	%rdi,%rbx
+	movq	%r9,%r13
+	addq	%rbx,%r14
+	rorq	$23,%r13
+	movq	%r14,%rbx
+	movq	%r10,%r12
+	rorq	$5,%r14
+	xorq	%r9,%r13
+	xorq	%r11,%r12
+	rorq	$4,%r13
+	xorq	%rbx,%r14
+	andq	%r9,%r12
+	xorq	%r9,%r13
+	addq	56(%rsp),%rax
+	movq	%rbx,%rdi
+	xorq	%r11,%r12
+	rorq	$6,%r14
+	xorq	%rcx,%rdi
+	addq	%r12,%rax
+	rorq	$14,%r13
+	andq	%rdi,%r15
+	xorq	%rbx,%r14
+	addq	%r13,%rax
+	xorq	%rcx,%r15
+	rorq	$28,%r14
+	addq	%rax,%r8
+	addq	%r15,%rax
+	movq	%r8,%r13
+	addq	%rax,%r14
+	rorq	$23,%r13
+	movq	%r14,%rax
+	movq	%r9,%r12
+	rorq	$5,%r14
+	xorq	%r8,%r13
+	xorq	%r10,%r12
+	rorq	$4,%r13
+	xorq	%rax,%r14
+	andq	%r8,%r12
+	xorq	%r8,%r13
+	addq	64(%rsp),%r11
+	movq	%rax,%r15
+	xorq	%r10,%r12
+	rorq	$6,%r14
+	xorq	%rbx,%r15
+	addq	%r12,%r11
+	rorq	$14,%r13
+	andq	%r15,%rdi
+	xorq	%rax,%r14
+	addq	%r13,%r11
+	xorq	%rbx,%rdi
+	rorq	$28,%r14
+	addq	%r11,%rdx
+	addq	%rdi,%r11
+	movq	%rdx,%r13
+	addq	%r11,%r14
+	rorq	$23,%r13
+	movq	%r14,%r11
+	movq	%r8,%r12
+	rorq	$5,%r14
+	xorq	%rdx,%r13
+	xorq	%r9,%r12
+	rorq	$4,%r13
+	xorq	%r11,%r14
+	andq	%rdx,%r12
+	xorq	%rdx,%r13
+	addq	72(%rsp),%r10
+	movq	%r11,%rdi
+	xorq	%r9,%r12
+	rorq	$6,%r14
+	xorq	%rax,%rdi
+	addq	%r12,%r10
+	rorq	$14,%r13
+	andq	%rdi,%r15
+	xorq	%r11,%r14
+	addq	%r13,%r10
+	xorq	%rax,%r15
+	rorq	$28,%r14
+	addq	%r10,%rcx
+	addq	%r15,%r10
+	movq	%rcx,%r13
+	addq	%r10,%r14
+	rorq	$23,%r13
+	movq	%r14,%r10
+	movq	%rdx,%r12
+	rorq	$5,%r14
+	xorq	%rcx,%r13
+	xorq	%r8,%r12
+	rorq	$4,%r13
+	xorq	%r10,%r14
+	andq	%rcx,%r12
+	xorq	%rcx,%r13
+	addq	80(%rsp),%r9
+	movq	%r10,%r15
+	xorq	%r8,%r12
+	rorq	$6,%r14
+	xorq	%r11,%r15
+	addq	%r12,%r9
+	rorq	$14,%r13
+	andq	%r15,%rdi
+	xorq	%r10,%r14
+	addq	%r13,%r9
+	xorq	%r11,%rdi
+	rorq	$28,%r14
+	addq	%r9,%rbx
+	addq	%rdi,%r9
+	movq	%rbx,%r13
+	addq	%r9,%r14
+	rorq	$23,%r13
+	movq	%r14,%r9
+	movq	%rcx,%r12
+	rorq	$5,%r14
+	xorq	%rbx,%r13
+	xorq	%rdx,%r12
+	rorq	$4,%r13
+	xorq	%r9,%r14
+	andq	%rbx,%r12
+	xorq	%rbx,%r13
+	addq	88(%rsp),%r8
+	movq	%r9,%rdi
+	xorq	%rdx,%r12
+	rorq	$6,%r14
+	xorq	%r10,%rdi
+	addq	%r12,%r8
+	rorq	$14,%r13
+	andq	%rdi,%r15
+	xorq	%r9,%r14
+	addq	%r13,%r8
+	xorq	%r10,%r15
+	rorq	$28,%r14
+	addq	%r8,%rax
+	addq	%r15,%r8
+	movq	%rax,%r13
+	addq	%r8,%r14
+	rorq	$23,%r13
+	movq	%r14,%r8
+	movq	%rbx,%r12
+	rorq	$5,%r14
+	xorq	%rax,%r13
+	xorq	%rcx,%r12
+	rorq	$4,%r13
+	xorq	%r8,%r14
+	andq	%rax,%r12
+	xorq	%rax,%r13
+	addq	96(%rsp),%rdx
+	movq	%r8,%r15
+	xorq	%rcx,%r12
+	rorq	$6,%r14
+	xorq	%r9,%r15
+	addq	%r12,%rdx
+	rorq	$14,%r13
+	andq	%r15,%rdi
+	xorq	%r8,%r14
+	addq	%r13,%rdx
+	xorq	%r9,%rdi
+	rorq	$28,%r14
+	addq	%rdx,%r11
+	addq	%rdi,%rdx
+	movq	%r11,%r13
+	addq	%rdx,%r14
+	rorq	$23,%r13
+	movq	%r14,%rdx
+	movq	%rax,%r12
+	rorq	$5,%r14
+	xorq	%r11,%r13
+	xorq	%rbx,%r12
+	rorq	$4,%r13
+	xorq	%rdx,%r14
+	andq	%r11,%r12
+	xorq	%r11,%r13
+	addq	104(%rsp),%rcx
+	movq	%rdx,%rdi
+	xorq	%rbx,%r12
+	rorq	$6,%r14
+	xorq	%r8,%rdi
+	addq	%r12,%rcx
+	rorq	$14,%r13
+	andq	%rdi,%r15
+	xorq	%rdx,%r14
+	addq	%r13,%rcx
+	xorq	%r8,%r15
+	rorq	$28,%r14
+	addq	%rcx,%r10
+	addq	%r15,%rcx
+	movq	%r10,%r13
+	addq	%rcx,%r14
+	rorq	$23,%r13
+	movq	%r14,%rcx
+	movq	%r11,%r12
+	rorq	$5,%r14
+	xorq	%r10,%r13
+	xorq	%rax,%r12
+	rorq	$4,%r13
+	xorq	%rcx,%r14
+	andq	%r10,%r12
+	xorq	%r10,%r13
+	addq	112(%rsp),%rbx
+	movq	%rcx,%r15
+	xorq	%rax,%r12
+	rorq	$6,%r14
+	xorq	%rdx,%r15
+	addq	%r12,%rbx
+	rorq	$14,%r13
+	andq	%r15,%rdi
+	xorq	%rcx,%r14
+	addq	%r13,%rbx
+	xorq	%rdx,%rdi
+	rorq	$28,%r14
+	addq	%rbx,%r9
+	addq	%rdi,%rbx
+	movq	%r9,%r13
+	addq	%rbx,%r14
+	rorq	$23,%r13
+	movq	%r14,%rbx
+	movq	%r10,%r12
+	rorq	$5,%r14
+	xorq	%r9,%r13
+	xorq	%r11,%r12
+	rorq	$4,%r13
+	xorq	%rbx,%r14
+	andq	%r9,%r12
+	xorq	%r9,%r13
+	addq	120(%rsp),%rax
+	movq	%rbx,%rdi
+	xorq	%r11,%r12
+	rorq	$6,%r14
+	xorq	%rcx,%rdi
+	addq	%r12,%rax
+	rorq	$14,%r13
+	andq	%rdi,%r15
+	xorq	%rbx,%r14
+	addq	%r13,%rax
+	xorq	%rcx,%r15
+	rorq	$28,%r14
+	addq	%rax,%r8
+	addq	%r15,%rax
+	movq	%r8,%r13
+	addq	%rax,%r14
+	movq	128+0(%rsp),%rdi
+	movq	%r14,%rax
+
+	addq	0(%rdi),%rax
+	leaq	128(%rsi),%rsi
+	addq	8(%rdi),%rbx
+	addq	16(%rdi),%rcx
+	addq	24(%rdi),%rdx
+	addq	32(%rdi),%r8
+	addq	40(%rdi),%r9
+	addq	48(%rdi),%r10
+	addq	56(%rdi),%r11
+
+	cmpq	128+16(%rsp),%rsi
+
+	movq	%rax,0(%rdi)
+	movq	%rbx,8(%rdi)
+	movq	%rcx,16(%rdi)
+	movq	%rdx,24(%rdi)
+	movq	%r8,32(%rdi)
+	movq	%r9,40(%rdi)
+	movq	%r10,48(%rdi)
+	movq	%r11,56(%rdi)
+	jb	L$loop_xop
+
+	movq	128+24(%rsp),%rsi
+	vzeroupper
+	movq	(%rsi),%r15
+	movq	8(%rsi),%r14
+	movq	16(%rsi),%r13
+	movq	24(%rsi),%r12
+	movq	32(%rsi),%rbp
+	movq	40(%rsi),%rbx
+	leaq	48(%rsi),%rsp
+L$epilogue_xop:
+	.byte	0xf3,0xc3
+
+
+.p2align	6
+sha512_block_data_order_avx:
+L$avx_shortcut:
+	pushq	%rbx
+	pushq	%rbp
+	pushq	%r12
+	pushq	%r13
+	pushq	%r14
+	pushq	%r15
+	movq	%rsp,%r11
+	shlq	$4,%rdx
+	subq	$160,%rsp
+	leaq	(%rsi,%rdx,8),%rdx
+	andq	$-64,%rsp
+	movq	%rdi,128+0(%rsp)
+	movq	%rsi,128+8(%rsp)
+	movq	%rdx,128+16(%rsp)
+	movq	%r11,128+24(%rsp)
+L$prologue_avx:
+
+	vzeroupper
+	movq	0(%rdi),%rax
+	movq	8(%rdi),%rbx
+	movq	16(%rdi),%rcx
+	movq	24(%rdi),%rdx
+	movq	32(%rdi),%r8
+	movq	40(%rdi),%r9
+	movq	48(%rdi),%r10
+	movq	56(%rdi),%r11
+	jmp	L$loop_avx
+.p2align	4
+L$loop_avx:
+	vmovdqa	K512+1280(%rip),%xmm11
+	vmovdqu	0(%rsi),%xmm0
+	leaq	K512+128(%rip),%rbp
+	vmovdqu	16(%rsi),%xmm1
+	vmovdqu	32(%rsi),%xmm2
+	vpshufb	%xmm11,%xmm0,%xmm0
+	vmovdqu	48(%rsi),%xmm3
+	vpshufb	%xmm11,%xmm1,%xmm1
+	vmovdqu	64(%rsi),%xmm4
+	vpshufb	%xmm11,%xmm2,%xmm2
+	vmovdqu	80(%rsi),%xmm5
+	vpshufb	%xmm11,%xmm3,%xmm3
+	vmovdqu	96(%rsi),%xmm6
+	vpshufb	%xmm11,%xmm4,%xmm4
+	vmovdqu	112(%rsi),%xmm7
+	vpshufb	%xmm11,%xmm5,%xmm5
+	vpaddq	-128(%rbp),%xmm0,%xmm8
+	vpshufb	%xmm11,%xmm6,%xmm6
+	vpaddq	-96(%rbp),%xmm1,%xmm9
+	vpshufb	%xmm11,%xmm7,%xmm7
+	vpaddq	-64(%rbp),%xmm2,%xmm10
+	vpaddq	-32(%rbp),%xmm3,%xmm11
+	vmovdqa	%xmm8,0(%rsp)
+	vpaddq	0(%rbp),%xmm4,%xmm8
+	vmovdqa	%xmm9,16(%rsp)
+	vpaddq	32(%rbp),%xmm5,%xmm9
+	vmovdqa	%xmm10,32(%rsp)
+	vpaddq	64(%rbp),%xmm6,%xmm10
+	vmovdqa	%xmm11,48(%rsp)
+	vpaddq	96(%rbp),%xmm7,%xmm11
+	vmovdqa	%xmm8,64(%rsp)
+	movq	%rax,%r14
+	vmovdqa	%xmm9,80(%rsp)
+	movq	%rbx,%rdi
+	vmovdqa	%xmm10,96(%rsp)
+	xorq	%rcx,%rdi
+	vmovdqa	%xmm11,112(%rsp)
+	movq	%r8,%r13
+	jmp	L$avx_00_47
+
+.p2align	4
+L$avx_00_47:
+	addq	$256,%rbp
+	vpalignr	$8,%xmm0,%xmm1,%xmm8
+	shrdq	$23,%r13,%r13
+	movq	%r14,%rax
+	vpalignr	$8,%xmm4,%xmm5,%xmm11
+	movq	%r9,%r12
+	shrdq	$5,%r14,%r14
+	vpsrlq	$1,%xmm8,%xmm10
+	xorq	%r8,%r13
+	xorq	%r10,%r12
+	vpaddq	%xmm11,%xmm0,%xmm0
+	shrdq	$4,%r13,%r13
+	xorq	%rax,%r14
+	vpsrlq	$7,%xmm8,%xmm11
+	andq	%r8,%r12
+	xorq	%r8,%r13
+	vpsllq	$56,%xmm8,%xmm9
+	addq	0(%rsp),%r11
+	movq	%rax,%r15
+	vpxor	%xmm10,%xmm11,%xmm8
+	xorq	%r10,%r12
+	shrdq	$6,%r14,%r14
+	vpsrlq	$7,%xmm10,%xmm10
+	xorq	%rbx,%r15
+	addq	%r12,%r11
+	vpxor	%xmm9,%xmm8,%xmm8
+	shrdq	$14,%r13,%r13
+	andq	%r15,%rdi
+	vpsllq	$7,%xmm9,%xmm9
+	xorq	%rax,%r14
+	addq	%r13,%r11
+	vpxor	%xmm10,%xmm8,%xmm8
+	xorq	%rbx,%rdi
+	shrdq	$28,%r14,%r14
+	vpsrlq	$6,%xmm7,%xmm11
+	addq	%r11,%rdx
+	addq	%rdi,%r11
+	vpxor	%xmm9,%xmm8,%xmm8
+	movq	%rdx,%r13
+	addq	%r11,%r14
+	vpsllq	$3,%xmm7,%xmm10
+	shrdq	$23,%r13,%r13
+	movq	%r14,%r11
+	vpaddq	%xmm8,%xmm0,%xmm0
+	movq	%r8,%r12
+	shrdq	$5,%r14,%r14
+	vpsrlq	$19,%xmm7,%xmm9
+	xorq	%rdx,%r13
+	xorq	%r9,%r12
+	vpxor	%xmm10,%xmm11,%xmm11
+	shrdq	$4,%r13,%r13
+	xorq	%r11,%r14
+	vpsllq	$42,%xmm10,%xmm10
+	andq	%rdx,%r12
+	xorq	%rdx,%r13
+	vpxor	%xmm9,%xmm11,%xmm11
+	addq	8(%rsp),%r10
+	movq	%r11,%rdi
+	vpsrlq	$42,%xmm9,%xmm9
+	xorq	%r9,%r12
+	shrdq	$6,%r14,%r14
+	vpxor	%xmm10,%xmm11,%xmm11
+	xorq	%rax,%rdi
+	addq	%r12,%r10
+	vpxor	%xmm9,%xmm11,%xmm11
+	shrdq	$14,%r13,%r13
+	andq	%rdi,%r15
+	vpaddq	%xmm11,%xmm0,%xmm0
+	xorq	%r11,%r14
+	addq	%r13,%r10
+	vpaddq	-128(%rbp),%xmm0,%xmm10
+	xorq	%rax,%r15
+	shrdq	$28,%r14,%r14
+	addq	%r10,%rcx
+	addq	%r15,%r10
+	movq	%rcx,%r13
+	addq	%r10,%r14
+	vmovdqa	%xmm10,0(%rsp)
+	vpalignr	$8,%xmm1,%xmm2,%xmm8
+	shrdq	$23,%r13,%r13
+	movq	%r14,%r10
+	vpalignr	$8,%xmm5,%xmm6,%xmm11
+	movq	%rdx,%r12
+	shrdq	$5,%r14,%r14
+	vpsrlq	$1,%xmm8,%xmm10
+	xorq	%rcx,%r13
+	xorq	%r8,%r12
+	vpaddq	%xmm11,%xmm1,%xmm1
+	shrdq	$4,%r13,%r13
+	xorq	%r10,%r14
+	vpsrlq	$7,%xmm8,%xmm11
+	andq	%rcx,%r12
+	xorq	%rcx,%r13
+	vpsllq	$56,%xmm8,%xmm9
+	addq	16(%rsp),%r9
+	movq	%r10,%r15
+	vpxor	%xmm10,%xmm11,%xmm8
+	xorq	%r8,%r12
+	shrdq	$6,%r14,%r14
+	vpsrlq	$7,%xmm10,%xmm10
+	xorq	%r11,%r15
+	addq	%r12,%r9
+	vpxor	%xmm9,%xmm8,%xmm8
+	shrdq	$14,%r13,%r13
+	andq	%r15,%rdi
+	vpsllq	$7,%xmm9,%xmm9
+	xorq	%r10,%r14
+	addq	%r13,%r9
+	vpxor	%xmm10,%xmm8,%xmm8
+	xorq	%r11,%rdi
+	shrdq	$28,%r14,%r14
+	vpsrlq	$6,%xmm0,%xmm11
+	addq	%r9,%rbx
+	addq	%rdi,%r9
+	vpxor	%xmm9,%xmm8,%xmm8
+	movq	%rbx,%r13
+	addq	%r9,%r14
+	vpsllq	$3,%xmm0,%xmm10
+	shrdq	$23,%r13,%r13
+	movq	%r14,%r9
+	vpaddq	%xmm8,%xmm1,%xmm1
+	movq	%rcx,%r12
+	shrdq	$5,%r14,%r14
+	vpsrlq	$19,%xmm0,%xmm9
+	xorq	%rbx,%r13
+	xorq	%rdx,%r12
+	vpxor	%xmm10,%xmm11,%xmm11
+	shrdq	$4,%r13,%r13
+	xorq	%r9,%r14
+	vpsllq	$42,%xmm10,%xmm10
+	andq	%rbx,%r12
+	xorq	%rbx,%r13
+	vpxor	%xmm9,%xmm11,%xmm11
+	addq	24(%rsp),%r8
+	movq	%r9,%rdi
+	vpsrlq	$42,%xmm9,%xmm9
+	xorq	%rdx,%r12
+	shrdq	$6,%r14,%r14
+	vpxor	%xmm10,%xmm11,%xmm11
+	xorq	%r10,%rdi
+	addq	%r12,%r8
+	vpxor	%xmm9,%xmm11,%xmm11
+	shrdq	$14,%r13,%r13
+	andq	%rdi,%r15
+	vpaddq	%xmm11,%xmm1,%xmm1
+	xorq	%r9,%r14
+	addq	%r13,%r8
+	vpaddq	-96(%rbp),%xmm1,%xmm10
+	xorq	%r10,%r15
+	shrdq	$28,%r14,%r14
+	addq	%r8,%rax
+	addq	%r15,%r8
+	movq	%rax,%r13
+	addq	%r8,%r14
+	vmovdqa	%xmm10,16(%rsp)
+	vpalignr	$8,%xmm2,%xmm3,%xmm8
+	shrdq	$23,%r13,%r13
+	movq	%r14,%r8
+	vpalignr	$8,%xmm6,%xmm7,%xmm11
+	movq	%rbx,%r12
+	shrdq	$5,%r14,%r14
+	vpsrlq	$1,%xmm8,%xmm10
+	xorq	%rax,%r13
+	xorq	%rcx,%r12
+	vpaddq	%xmm11,%xmm2,%xmm2
+	shrdq	$4,%r13,%r13
+	xorq	%r8,%r14
+	vpsrlq	$7,%xmm8,%xmm11
+	andq	%rax,%r12
+	xorq	%rax,%r13
+	vpsllq	$56,%xmm8,%xmm9
+	addq	32(%rsp),%rdx
+	movq	%r8,%r15
+	vpxor	%xmm10,%xmm11,%xmm8
+	xorq	%rcx,%r12
+	shrdq	$6,%r14,%r14
+	vpsrlq	$7,%xmm10,%xmm10
+	xorq	%r9,%r15
+	addq	%r12,%rdx
+	vpxor	%xmm9,%xmm8,%xmm8
+	shrdq	$14,%r13,%r13
+	andq	%r15,%rdi
+	vpsllq	$7,%xmm9,%xmm9
+	xorq	%r8,%r14
+	addq	%r13,%rdx
+	vpxor	%xmm10,%xmm8,%xmm8
+	xorq	%r9,%rdi
+	shrdq	$28,%r14,%r14
+	vpsrlq	$6,%xmm1,%xmm11
+	addq	%rdx,%r11
+	addq	%rdi,%rdx
+	vpxor	%xmm9,%xmm8,%xmm8
+	movq	%r11,%r13
+	addq	%rdx,%r14
+	vpsllq	$3,%xmm1,%xmm10
+	shrdq	$23,%r13,%r13
+	movq	%r14,%rdx
+	vpaddq	%xmm8,%xmm2,%xmm2
+	movq	%rax,%r12
+	shrdq	$5,%r14,%r14
+	vpsrlq	$19,%xmm1,%xmm9
+	xorq	%r11,%r13
+	xorq	%rbx,%r12
+	vpxor	%xmm10,%xmm11,%xmm11
+	shrdq	$4,%r13,%r13
+	xorq	%rdx,%r14
+	vpsllq	$42,%xmm10,%xmm10
+	andq	%r11,%r12
+	xorq	%r11,%r13
+	vpxor	%xmm9,%xmm11,%xmm11
+	addq	40(%rsp),%rcx
+	movq	%rdx,%rdi
+	vpsrlq	$42,%xmm9,%xmm9
+	xorq	%rbx,%r12
+	shrdq	$6,%r14,%r14
+	vpxor	%xmm10,%xmm11,%xmm11
+	xorq	%r8,%rdi
+	addq	%r12,%rcx
+	vpxor	%xmm9,%xmm11,%xmm11
+	shrdq	$14,%r13,%r13
+	andq	%rdi,%r15
+	vpaddq	%xmm11,%xmm2,%xmm2
+	xorq	%rdx,%r14
+	addq	%r13,%rcx
+	vpaddq	-64(%rbp),%xmm2,%xmm10
+	xorq	%r8,%r15
+	shrdq	$28,%r14,%r14
+	addq	%rcx,%r10
+	addq	%r15,%rcx
+	movq	%r10,%r13
+	addq	%rcx,%r14
+	vmovdqa	%xmm10,32(%rsp)
+	vpalignr	$8,%xmm3,%xmm4,%xmm8
+	shrdq	$23,%r13,%r13
+	movq	%r14,%rcx
+	vpalignr	$8,%xmm7,%xmm0,%xmm11
+	movq	%r11,%r12
+	shrdq	$5,%r14,%r14
+	vpsrlq	$1,%xmm8,%xmm10
+	xorq	%r10,%r13
+	xorq	%rax,%r12
+	vpaddq	%xmm11,%xmm3,%xmm3
+	shrdq	$4,%r13,%r13
+	xorq	%rcx,%r14
+	vpsrlq	$7,%xmm8,%xmm11
+	andq	%r10,%r12
+	xorq	%r10,%r13
+	vpsllq	$56,%xmm8,%xmm9
+	addq	48(%rsp),%rbx
+	movq	%rcx,%r15
+	vpxor	%xmm10,%xmm11,%xmm8
+	xorq	%rax,%r12
+	shrdq	$6,%r14,%r14
+	vpsrlq	$7,%xmm10,%xmm10
+	xorq	%rdx,%r15
+	addq	%r12,%rbx
+	vpxor	%xmm9,%xmm8,%xmm8
+	shrdq	$14,%r13,%r13
+	andq	%r15,%rdi
+	vpsllq	$7,%xmm9,%xmm9
+	xorq	%rcx,%r14
+	addq	%r13,%rbx
+	vpxor	%xmm10,%xmm8,%xmm8
+	xorq	%rdx,%rdi
+	shrdq	$28,%r14,%r14
+	vpsrlq	$6,%xmm2,%xmm11
+	addq	%rbx,%r9
+	addq	%rdi,%rbx
+	vpxor	%xmm9,%xmm8,%xmm8
+	movq	%r9,%r13
+	addq	%rbx,%r14
+	vpsllq	$3,%xmm2,%xmm10
+	shrdq	$23,%r13,%r13
+	movq	%r14,%rbx
+	vpaddq	%xmm8,%xmm3,%xmm3
+	movq	%r10,%r12
+	shrdq	$5,%r14,%r14
+	vpsrlq	$19,%xmm2,%xmm9
+	xorq	%r9,%r13
+	xorq	%r11,%r12
+	vpxor	%xmm10,%xmm11,%xmm11
+	shrdq	$4,%r13,%r13
+	xorq	%rbx,%r14
+	vpsllq	$42,%xmm10,%xmm10
+	andq	%r9,%r12
+	xorq	%r9,%r13
+	vpxor	%xmm9,%xmm11,%xmm11
+	addq	56(%rsp),%rax
+	movq	%rbx,%rdi
+	vpsrlq	$42,%xmm9,%xmm9
+	xorq	%r11,%r12
+	shrdq	$6,%r14,%r14
+	vpxor	%xmm10,%xmm11,%xmm11
+	xorq	%rcx,%rdi
+	addq	%r12,%rax
+	vpxor	%xmm9,%xmm11,%xmm11
+	shrdq	$14,%r13,%r13
+	andq	%rdi,%r15
+	vpaddq	%xmm11,%xmm3,%xmm3
+	xorq	%rbx,%r14
+	addq	%r13,%rax
+	vpaddq	-32(%rbp),%xmm3,%xmm10
+	xorq	%rcx,%r15
+	shrdq	$28,%r14,%r14
+	addq	%rax,%r8
+	addq	%r15,%rax
+	movq	%r8,%r13
+	addq	%rax,%r14
+	vmovdqa	%xmm10,48(%rsp)
+	vpalignr	$8,%xmm4,%xmm5,%xmm8
+	shrdq	$23,%r13,%r13
+	movq	%r14,%rax
+	vpalignr	$8,%xmm0,%xmm1,%xmm11
+	movq	%r9,%r12
+	shrdq	$5,%r14,%r14
+	vpsrlq	$1,%xmm8,%xmm10
+	xorq	%r8,%r13
+	xorq	%r10,%r12
+	vpaddq	%xmm11,%xmm4,%xmm4
+	shrdq	$4,%r13,%r13
+	xorq	%rax,%r14
+	vpsrlq	$7,%xmm8,%xmm11
+	andq	%r8,%r12
+	xorq	%r8,%r13
+	vpsllq	$56,%xmm8,%xmm9
+	addq	64(%rsp),%r11
+	movq	%rax,%r15
+	vpxor	%xmm10,%xmm11,%xmm8
+	xorq	%r10,%r12
+	shrdq	$6,%r14,%r14
+	vpsrlq	$7,%xmm10,%xmm10
+	xorq	%rbx,%r15
+	addq	%r12,%r11
+	vpxor	%xmm9,%xmm8,%xmm8
+	shrdq	$14,%r13,%r13
+	andq	%r15,%rdi
+	vpsllq	$7,%xmm9,%xmm9
+	xorq	%rax,%r14
+	addq	%r13,%r11
+	vpxor	%xmm10,%xmm8,%xmm8
+	xorq	%rbx,%rdi
+	shrdq	$28,%r14,%r14
+	vpsrlq	$6,%xmm3,%xmm11
+	addq	%r11,%rdx
+	addq	%rdi,%r11
+	vpxor	%xmm9,%xmm8,%xmm8
+	movq	%rdx,%r13
+	addq	%r11,%r14
+	vpsllq	$3,%xmm3,%xmm10
+	shrdq	$23,%r13,%r13
+	movq	%r14,%r11
+	vpaddq	%xmm8,%xmm4,%xmm4
+	movq	%r8,%r12
+	shrdq	$5,%r14,%r14
+	vpsrlq	$19,%xmm3,%xmm9
+	xorq	%rdx,%r13
+	xorq	%r9,%r12
+	vpxor	%xmm10,%xmm11,%xmm11
+	shrdq	$4,%r13,%r13
+	xorq	%r11,%r14
+	vpsllq	$42,%xmm10,%xmm10
+	andq	%rdx,%r12
+	xorq	%rdx,%r13
+	vpxor	%xmm9,%xmm11,%xmm11
+	addq	72(%rsp),%r10
+	movq	%r11,%rdi
+	vpsrlq	$42,%xmm9,%xmm9
+	xorq	%r9,%r12
+	shrdq	$6,%r14,%r14
+	vpxor	%xmm10,%xmm11,%xmm11
+	xorq	%rax,%rdi
+	addq	%r12,%r10
+	vpxor	%xmm9,%xmm11,%xmm11
+	shrdq	$14,%r13,%r13
+	andq	%rdi,%r15
+	vpaddq	%xmm11,%xmm4,%xmm4
+	xorq	%r11,%r14
+	addq	%r13,%r10
+	vpaddq	0(%rbp),%xmm4,%xmm10
+	xorq	%rax,%r15
+	shrdq	$28,%r14,%r14
+	addq	%r10,%rcx
+	addq	%r15,%r10
+	movq	%rcx,%r13
+	addq	%r10,%r14
+	vmovdqa	%xmm10,64(%rsp)
+	vpalignr	$8,%xmm5,%xmm6,%xmm8
+	shrdq	$23,%r13,%r13
+	movq	%r14,%r10
+	vpalignr	$8,%xmm1,%xmm2,%xmm11
+	movq	%rdx,%r12
+	shrdq	$5,%r14,%r14
+	vpsrlq	$1,%xmm8,%xmm10
+	xorq	%rcx,%r13
+	xorq	%r8,%r12
+	vpaddq	%xmm11,%xmm5,%xmm5
+	shrdq	$4,%r13,%r13
+	xorq	%r10,%r14
+	vpsrlq	$7,%xmm8,%xmm11
+	andq	%rcx,%r12
+	xorq	%rcx,%r13
+	vpsllq	$56,%xmm8,%xmm9
+	addq	80(%rsp),%r9
+	movq	%r10,%r15
+	vpxor	%xmm10,%xmm11,%xmm8
+	xorq	%r8,%r12
+	shrdq	$6,%r14,%r14
+	vpsrlq	$7,%xmm10,%xmm10
+	xorq	%r11,%r15
+	addq	%r12,%r9
+	vpxor	%xmm9,%xmm8,%xmm8
+	shrdq	$14,%r13,%r13
+	andq	%r15,%rdi
+	vpsllq	$7,%xmm9,%xmm9
+	xorq	%r10,%r14
+	addq	%r13,%r9
+	vpxor	%xmm10,%xmm8,%xmm8
+	xorq	%r11,%rdi
+	shrdq	$28,%r14,%r14
+	vpsrlq	$6,%xmm4,%xmm11
+	addq	%r9,%rbx
+	addq	%rdi,%r9
+	vpxor	%xmm9,%xmm8,%xmm8
+	movq	%rbx,%r13
+	addq	%r9,%r14
+	vpsllq	$3,%xmm4,%xmm10
+	shrdq	$23,%r13,%r13
+	movq	%r14,%r9
+	vpaddq	%xmm8,%xmm5,%xmm5
+	movq	%rcx,%r12
+	shrdq	$5,%r14,%r14
+	vpsrlq	$19,%xmm4,%xmm9
+	xorq	%rbx,%r13
+	xorq	%rdx,%r12
+	vpxor	%xmm10,%xmm11,%xmm11
+	shrdq	$4,%r13,%r13
+	xorq	%r9,%r14
+	vpsllq	$42,%xmm10,%xmm10
+	andq	%rbx,%r12
+	xorq	%rbx,%r13
+	vpxor	%xmm9,%xmm11,%xmm11
+	addq	88(%rsp),%r8
+	movq	%r9,%rdi
+	vpsrlq	$42,%xmm9,%xmm9
+	xorq	%rdx,%r12
+	shrdq	$6,%r14,%r14
+	vpxor	%xmm10,%xmm11,%xmm11
+	xorq	%r10,%rdi
+	addq	%r12,%r8
+	vpxor	%xmm9,%xmm11,%xmm11
+	shrdq	$14,%r13,%r13
+	andq	%rdi,%r15
+	vpaddq	%xmm11,%xmm5,%xmm5
+	xorq	%r9,%r14
+	addq	%r13,%r8
+	vpaddq	32(%rbp),%xmm5,%xmm10
+	xorq	%r10,%r15
+	shrdq	$28,%r14,%r14
+	addq	%r8,%rax
+	addq	%r15,%r8
+	movq	%rax,%r13
+	addq	%r8,%r14
+	vmovdqa	%xmm10,80(%rsp)
+	vpalignr	$8,%xmm6,%xmm7,%xmm8
+	shrdq	$23,%r13,%r13
+	movq	%r14,%r8
+	vpalignr	$8,%xmm2,%xmm3,%xmm11
+	movq	%rbx,%r12
+	shrdq	$5,%r14,%r14
+	vpsrlq	$1,%xmm8,%xmm10
+	xorq	%rax,%r13
+	xorq	%rcx,%r12
+	vpaddq	%xmm11,%xmm6,%xmm6
+	shrdq	$4,%r13,%r13
+	xorq	%r8,%r14
+	vpsrlq	$7,%xmm8,%xmm11
+	andq	%rax,%r12
+	xorq	%rax,%r13
+	vpsllq	$56,%xmm8,%xmm9
+	addq	96(%rsp),%rdx
+	movq	%r8,%r15
+	vpxor	%xmm10,%xmm11,%xmm8
+	xorq	%rcx,%r12
+	shrdq	$6,%r14,%r14
+	vpsrlq	$7,%xmm10,%xmm10
+	xorq	%r9,%r15
+	addq	%r12,%rdx
+	vpxor	%xmm9,%xmm8,%xmm8
+	shrdq	$14,%r13,%r13
+	andq	%r15,%rdi
+	vpsllq	$7,%xmm9,%xmm9
+	xorq	%r8,%r14
+	addq	%r13,%rdx
+	vpxor	%xmm10,%xmm8,%xmm8
+	xorq	%r9,%rdi
+	shrdq	$28,%r14,%r14
+	vpsrlq	$6,%xmm5,%xmm11
+	addq	%rdx,%r11
+	addq	%rdi,%rdx
+	vpxor	%xmm9,%xmm8,%xmm8
+	movq	%r11,%r13
+	addq	%rdx,%r14
+	vpsllq	$3,%xmm5,%xmm10
+	shrdq	$23,%r13,%r13
+	movq	%r14,%rdx
+	vpaddq	%xmm8,%xmm6,%xmm6
+	movq	%rax,%r12
+	shrdq	$5,%r14,%r14
+	vpsrlq	$19,%xmm5,%xmm9
+	xorq	%r11,%r13
+	xorq	%rbx,%r12
+	vpxor	%xmm10,%xmm11,%xmm11
+	shrdq	$4,%r13,%r13
+	xorq	%rdx,%r14
+	vpsllq	$42,%xmm10,%xmm10
+	andq	%r11,%r12
+	xorq	%r11,%r13
+	vpxor	%xmm9,%xmm11,%xmm11
+	addq	104(%rsp),%rcx
+	movq	%rdx,%rdi
+	vpsrlq	$42,%xmm9,%xmm9
+	xorq	%rbx,%r12
+	shrdq	$6,%r14,%r14
+	vpxor	%xmm10,%xmm11,%xmm11
+	xorq	%r8,%rdi
+	addq	%r12,%rcx
+	vpxor	%xmm9,%xmm11,%xmm11
+	shrdq	$14,%r13,%r13
+	andq	%rdi,%r15
+	vpaddq	%xmm11,%xmm6,%xmm6
+	xorq	%rdx,%r14
+	addq	%r13,%rcx
+	vpaddq	64(%rbp),%xmm6,%xmm10
+	xorq	%r8,%r15
+	shrdq	$28,%r14,%r14
+	addq	%rcx,%r10
+	addq	%r15,%rcx
+	movq	%r10,%r13
+	addq	%rcx,%r14
+	vmovdqa	%xmm10,96(%rsp)
+	vpalignr	$8,%xmm7,%xmm0,%xmm8
+	shrdq	$23,%r13,%r13
+	movq	%r14,%rcx
+	vpalignr	$8,%xmm3,%xmm4,%xmm11
+	movq	%r11,%r12
+	shrdq	$5,%r14,%r14
+	vpsrlq	$1,%xmm8,%xmm10
+	xorq	%r10,%r13
+	xorq	%rax,%r12
+	vpaddq	%xmm11,%xmm7,%xmm7
+	shrdq	$4,%r13,%r13
+	xorq	%rcx,%r14
+	vpsrlq	$7,%xmm8,%xmm11
+	andq	%r10,%r12
+	xorq	%r10,%r13
+	vpsllq	$56,%xmm8,%xmm9
+	addq	112(%rsp),%rbx
+	movq	%rcx,%r15
+	vpxor	%xmm10,%xmm11,%xmm8
+	xorq	%rax,%r12
+	shrdq	$6,%r14,%r14
+	vpsrlq	$7,%xmm10,%xmm10
+	xorq	%rdx,%r15
+	addq	%r12,%rbx
+	vpxor	%xmm9,%xmm8,%xmm8
+	shrdq	$14,%r13,%r13
+	andq	%r15,%rdi
+	vpsllq	$7,%xmm9,%xmm9
+	xorq	%rcx,%r14
+	addq	%r13,%rbx
+	vpxor	%xmm10,%xmm8,%xmm8
+	xorq	%rdx,%rdi
+	shrdq	$28,%r14,%r14
+	vpsrlq	$6,%xmm6,%xmm11
+	addq	%rbx,%r9
+	addq	%rdi,%rbx
+	vpxor	%xmm9,%xmm8,%xmm8
+	movq	%r9,%r13
+	addq	%rbx,%r14
+	vpsllq	$3,%xmm6,%xmm10
+	shrdq	$23,%r13,%r13
+	movq	%r14,%rbx
+	vpaddq	%xmm8,%xmm7,%xmm7
+	movq	%r10,%r12
+	shrdq	$5,%r14,%r14
+	vpsrlq	$19,%xmm6,%xmm9
+	xorq	%r9,%r13
+	xorq	%r11,%r12
+	vpxor	%xmm10,%xmm11,%xmm11
+	shrdq	$4,%r13,%r13
+	xorq	%rbx,%r14
+	vpsllq	$42,%xmm10,%xmm10
+	andq	%r9,%r12
+	xorq	%r9,%r13
+	vpxor	%xmm9,%xmm11,%xmm11
+	addq	120(%rsp),%rax
+	movq	%rbx,%rdi
+	vpsrlq	$42,%xmm9,%xmm9
+	xorq	%r11,%r12
+	shrdq	$6,%r14,%r14
+	vpxor	%xmm10,%xmm11,%xmm11
+	xorq	%rcx,%rdi
+	addq	%r12,%rax
+	vpxor	%xmm9,%xmm11,%xmm11
+	shrdq	$14,%r13,%r13
+	andq	%rdi,%r15
+	vpaddq	%xmm11,%xmm7,%xmm7
+	xorq	%rbx,%r14
+	addq	%r13,%rax
+	vpaddq	96(%rbp),%xmm7,%xmm10
+	xorq	%rcx,%r15
+	shrdq	$28,%r14,%r14
+	addq	%rax,%r8
+	addq	%r15,%rax
+	movq	%r8,%r13
+	addq	%rax,%r14
+	vmovdqa	%xmm10,112(%rsp)
+	cmpb	$0,135(%rbp)
+	jne	L$avx_00_47
+	shrdq	$23,%r13,%r13
+	movq	%r14,%rax
+	movq	%r9,%r12
+	shrdq	$5,%r14,%r14
+	xorq	%r8,%r13
+	xorq	%r10,%r12
+	shrdq	$4,%r13,%r13
+	xorq	%rax,%r14
+	andq	%r8,%r12
+	xorq	%r8,%r13
+	addq	0(%rsp),%r11
+	movq	%rax,%r15
+	xorq	%r10,%r12
+	shrdq	$6,%r14,%r14
+	xorq	%rbx,%r15
+	addq	%r12,%r11
+	shrdq	$14,%r13,%r13
+	andq	%r15,%rdi
+	xorq	%rax,%r14
+	addq	%r13,%r11
+	xorq	%rbx,%rdi
+	shrdq	$28,%r14,%r14
+	addq	%r11,%rdx
+	addq	%rdi,%r11
+	movq	%rdx,%r13
+	addq	%r11,%r14
+	shrdq	$23,%r13,%r13
+	movq	%r14,%r11
+	movq	%r8,%r12
+	shrdq	$5,%r14,%r14
+	xorq	%rdx,%r13
+	xorq	%r9,%r12
+	shrdq	$4,%r13,%r13
+	xorq	%r11,%r14
+	andq	%rdx,%r12
+	xorq	%rdx,%r13
+	addq	8(%rsp),%r10
+	movq	%r11,%rdi
+	xorq	%r9,%r12
+	shrdq	$6,%r14,%r14
+	xorq	%rax,%rdi
+	addq	%r12,%r10
+	shrdq	$14,%r13,%r13
+	andq	%rdi,%r15
+	xorq	%r11,%r14
+	addq	%r13,%r10
+	xorq	%rax,%r15
+	shrdq	$28,%r14,%r14
+	addq	%r10,%rcx
+	addq	%r15,%r10
+	movq	%rcx,%r13
+	addq	%r10,%r14
+	shrdq	$23,%r13,%r13
+	movq	%r14,%r10
+	movq	%rdx,%r12
+	shrdq	$5,%r14,%r14
+	xorq	%rcx,%r13
+	xorq	%r8,%r12
+	shrdq	$4,%r13,%r13
+	xorq	%r10,%r14
+	andq	%rcx,%r12
+	xorq	%rcx,%r13
+	addq	16(%rsp),%r9
+	movq	%r10,%r15
+	xorq	%r8,%r12
+	shrdq	$6,%r14,%r14
+	xorq	%r11,%r15
+	addq	%r12,%r9
+	shrdq	$14,%r13,%r13
+	andq	%r15,%rdi
+	xorq	%r10,%r14
+	addq	%r13,%r9
+	xorq	%r11,%rdi
+	shrdq	$28,%r14,%r14
+	addq	%r9,%rbx
+	addq	%rdi,%r9
+	movq	%rbx,%r13
+	addq	%r9,%r14
+	shrdq	$23,%r13,%r13
+	movq	%r14,%r9
+	movq	%rcx,%r12
+	shrdq	$5,%r14,%r14
+	xorq	%rbx,%r13
+	xorq	%rdx,%r12
+	shrdq	$4,%r13,%r13
+	xorq	%r9,%r14
+	andq	%rbx,%r12
+	xorq	%rbx,%r13
+	addq	24(%rsp),%r8
+	movq	%r9,%rdi
+	xorq	%rdx,%r12
+	shrdq	$6,%r14,%r14
+	xorq	%r10,%rdi
+	addq	%r12,%r8
+	shrdq	$14,%r13,%r13
+	andq	%rdi,%r15
+	xorq	%r9,%r14
+	addq	%r13,%r8
+	xorq	%r10,%r15
+	shrdq	$28,%r14,%r14
+	addq	%r8,%rax
+	addq	%r15,%r8
+	movq	%rax,%r13
+	addq	%r8,%r14
+	shrdq	$23,%r13,%r13
+	movq	%r14,%r8
+	movq	%rbx,%r12
+	shrdq	$5,%r14,%r14
+	xorq	%rax,%r13
+	xorq	%rcx,%r12
+	shrdq	$4,%r13,%r13
+	xorq	%r8,%r14
+	andq	%rax,%r12
+	xorq	%rax,%r13
+	addq	32(%rsp),%rdx
+	movq	%r8,%r15
+	xorq	%rcx,%r12
+	shrdq	$6,%r14,%r14
+	xorq	%r9,%r15
+	addq	%r12,%rdx
+	shrdq	$14,%r13,%r13
+	andq	%r15,%rdi
+	xorq	%r8,%r14
+	addq	%r13,%rdx
+	xorq	%r9,%rdi
+	shrdq	$28,%r14,%r14
+	addq	%rdx,%r11
+	addq	%rdi,%rdx
+	movq	%r11,%r13
+	addq	%rdx,%r14
+	shrdq	$23,%r13,%r13
+	movq	%r14,%rdx
+	movq	%rax,%r12
+	shrdq	$5,%r14,%r14
+	xorq	%r11,%r13
+	xorq	%rbx,%r12
+	shrdq	$4,%r13,%r13
+	xorq	%rdx,%r14
+	andq	%r11,%r12
+	xorq	%r11,%r13
+	addq	40(%rsp),%rcx
+	movq	%rdx,%rdi
+	xorq	%rbx,%r12
+	shrdq	$6,%r14,%r14
+	xorq	%r8,%rdi
+	addq	%r12,%rcx
+	shrdq	$14,%r13,%r13
+	andq	%rdi,%r15
+	xorq	%rdx,%r14
+	addq	%r13,%rcx
+	xorq	%r8,%r15
+	shrdq	$28,%r14,%r14
+	addq	%rcx,%r10
+	addq	%r15,%rcx
+	movq	%r10,%r13
+	addq	%rcx,%r14
+	shrdq	$23,%r13,%r13
+	movq	%r14,%rcx
+	movq	%r11,%r12
+	shrdq	$5,%r14,%r14
+	xorq	%r10,%r13
+	xorq	%rax,%r12
+	shrdq	$4,%r13,%r13
+	xorq	%rcx,%r14
+	andq	%r10,%r12
+	xorq	%r10,%r13
+	addq	48(%rsp),%rbx
+	movq	%rcx,%r15
+	xorq	%rax,%r12
+	shrdq	$6,%r14,%r14
+	xorq	%rdx,%r15
+	addq	%r12,%rbx
+	shrdq	$14,%r13,%r13
+	andq	%r15,%rdi
+	xorq	%rcx,%r14
+	addq	%r13,%rbx
+	xorq	%rdx,%rdi
+	shrdq	$28,%r14,%r14
+	addq	%rbx,%r9
+	addq	%rdi,%rbx
+	movq	%r9,%r13
+	addq	%rbx,%r14
+	shrdq	$23,%r13,%r13
+	movq	%r14,%rbx
+	movq	%r10,%r12
+	shrdq	$5,%r14,%r14
+	xorq	%r9,%r13
+	xorq	%r11,%r12
+	shrdq	$4,%r13,%r13
+	xorq	%rbx,%r14
+	andq	%r9,%r12
+	xorq	%r9,%r13
+	addq	56(%rsp),%rax
+	movq	%rbx,%rdi
+	xorq	%r11,%r12
+	shrdq	$6,%r14,%r14
+	xorq	%rcx,%rdi
+	addq	%r12,%rax
+	shrdq	$14,%r13,%r13
+	andq	%rdi,%r15
+	xorq	%rbx,%r14
+	addq	%r13,%rax
+	xorq	%rcx,%r15
+	shrdq	$28,%r14,%r14
+	addq	%rax,%r8
+	addq	%r15,%rax
+	movq	%r8,%r13
+	addq	%rax,%r14
+	shrdq	$23,%r13,%r13
+	movq	%r14,%rax
+	movq	%r9,%r12
+	shrdq	$5,%r14,%r14
+	xorq	%r8,%r13
+	xorq	%r10,%r12
+	shrdq	$4,%r13,%r13
+	xorq	%rax,%r14
+	andq	%r8,%r12
+	xorq	%r8,%r13
+	addq	64(%rsp),%r11
+	movq	%rax,%r15
+	xorq	%r10,%r12
+	shrdq	$6,%r14,%r14
+	xorq	%rbx,%r15
+	addq	%r12,%r11
+	shrdq	$14,%r13,%r13
+	andq	%r15,%rdi
+	xorq	%rax,%r14
+	addq	%r13,%r11
+	xorq	%rbx,%rdi
+	shrdq	$28,%r14,%r14
+	addq	%r11,%rdx
+	addq	%rdi,%r11
+	movq	%rdx,%r13
+	addq	%r11,%r14
+	shrdq	$23,%r13,%r13
+	movq	%r14,%r11
+	movq	%r8,%r12
+	shrdq	$5,%r14,%r14
+	xorq	%rdx,%r13
+	xorq	%r9,%r12
+	shrdq	$4,%r13,%r13
+	xorq	%r11,%r14
+	andq	%rdx,%r12
+	xorq	%rdx,%r13
+	addq	72(%rsp),%r10
+	movq	%r11,%rdi
+	xorq	%r9,%r12
+	shrdq	$6,%r14,%r14
+	xorq	%rax,%rdi
+	addq	%r12,%r10
+	shrdq	$14,%r13,%r13
+	andq	%rdi,%r15
+	xorq	%r11,%r14
+	addq	%r13,%r10
+	xorq	%rax,%r15
+	shrdq	$28,%r14,%r14
+	addq	%r10,%rcx
+	addq	%r15,%r10
+	movq	%rcx,%r13
+	addq	%r10,%r14
+	shrdq	$23,%r13,%r13
+	movq	%r14,%r10
+	movq	%rdx,%r12
+	shrdq	$5,%r14,%r14
+	xorq	%rcx,%r13
+	xorq	%r8,%r12
+	shrdq	$4,%r13,%r13
+	xorq	%r10,%r14
+	andq	%rcx,%r12
+	xorq	%rcx,%r13
+	addq	80(%rsp),%r9
+	movq	%r10,%r15
+	xorq	%r8,%r12
+	shrdq	$6,%r14,%r14
+	xorq	%r11,%r15
+	addq	%r12,%r9
+	shrdq	$14,%r13,%r13
+	andq	%r15,%rdi
+	xorq	%r10,%r14
+	addq	%r13,%r9
+	xorq	%r11,%rdi
+	shrdq	$28,%r14,%r14
+	addq	%r9,%rbx
+	addq	%rdi,%r9
+	movq	%rbx,%r13
+	addq	%r9,%r14
+	shrdq	$23,%r13,%r13
+	movq	%r14,%r9
+	movq	%rcx,%r12
+	shrdq	$5,%r14,%r14
+	xorq	%rbx,%r13
+	xorq	%rdx,%r12
+	shrdq	$4,%r13,%r13
+	xorq	%r9,%r14
+	andq	%rbx,%r12
+	xorq	%rbx,%r13
+	addq	88(%rsp),%r8
+	movq	%r9,%rdi
+	xorq	%rdx,%r12
+	shrdq	$6,%r14,%r14
+	xorq	%r10,%rdi
+	addq	%r12,%r8
+	shrdq	$14,%r13,%r13
+	andq	%rdi,%r15
+	xorq	%r9,%r14
+	addq	%r13,%r8
+	xorq	%r10,%r15
+	shrdq	$28,%r14,%r14
+	addq	%r8,%rax
+	addq	%r15,%r8
+	movq	%rax,%r13
+	addq	%r8,%r14
+	shrdq	$23,%r13,%r13
+	movq	%r14,%r8
+	movq	%rbx,%r12
+	shrdq	$5,%r14,%r14
+	xorq	%rax,%r13
+	xorq	%rcx,%r12
+	shrdq	$4,%r13,%r13
+	xorq	%r8,%r14
+	andq	%rax,%r12
+	xorq	%rax,%r13
+	addq	96(%rsp),%rdx
+	movq	%r8,%r15
+	xorq	%rcx,%r12
+	shrdq	$6,%r14,%r14
+	xorq	%r9,%r15
+	addq	%r12,%rdx
+	shrdq	$14,%r13,%r13
+	andq	%r15,%rdi
+	xorq	%r8,%r14
+	addq	%r13,%rdx
+	xorq	%r9,%rdi
+	shrdq	$28,%r14,%r14
+	addq	%rdx,%r11
+	addq	%rdi,%rdx
+	movq	%r11,%r13
+	addq	%rdx,%r14
+	shrdq	$23,%r13,%r13
+	movq	%r14,%rdx
+	movq	%rax,%r12
+	shrdq	$5,%r14,%r14
+	xorq	%r11,%r13
+	xorq	%rbx,%r12
+	shrdq	$4,%r13,%r13
+	xorq	%rdx,%r14
+	andq	%r11,%r12
+	xorq	%r11,%r13
+	addq	104(%rsp),%rcx
+	movq	%rdx,%rdi
+	xorq	%rbx,%r12
+	shrdq	$6,%r14,%r14
+	xorq	%r8,%rdi
+	addq	%r12,%rcx
+	shrdq	$14,%r13,%r13
+	andq	%rdi,%r15
+	xorq	%rdx,%r14
+	addq	%r13,%rcx
+	xorq	%r8,%r15
+	shrdq	$28,%r14,%r14
+	addq	%rcx,%r10
+	addq	%r15,%rcx
+	movq	%r10,%r13
+	addq	%rcx,%r14
+	shrdq	$23,%r13,%r13
+	movq	%r14,%rcx
+	movq	%r11,%r12
+	shrdq	$5,%r14,%r14
+	xorq	%r10,%r13
+	xorq	%rax,%r12
+	shrdq	$4,%r13,%r13
+	xorq	%rcx,%r14
+	andq	%r10,%r12
+	xorq	%r10,%r13
+	addq	112(%rsp),%rbx
+	movq	%rcx,%r15
+	xorq	%rax,%r12
+	shrdq	$6,%r14,%r14
+	xorq	%rdx,%r15
+	addq	%r12,%rbx
+	shrdq	$14,%r13,%r13
+	andq	%r15,%rdi
+	xorq	%rcx,%r14
+	addq	%r13,%rbx
+	xorq	%rdx,%rdi
+	shrdq	$28,%r14,%r14
+	addq	%rbx,%r9
+	addq	%rdi,%rbx
+	movq	%r9,%r13
+	addq	%rbx,%r14
+	shrdq	$23,%r13,%r13
+	movq	%r14,%rbx
+	movq	%r10,%r12
+	shrdq	$5,%r14,%r14
+	xorq	%r9,%r13
+	xorq	%r11,%r12
+	shrdq	$4,%r13,%r13
+	xorq	%rbx,%r14
+	andq	%r9,%r12
+	xorq	%r9,%r13
+	addq	120(%rsp),%rax
+	movq	%rbx,%rdi
+	xorq	%r11,%r12
+	shrdq	$6,%r14,%r14
+	xorq	%rcx,%rdi
+	addq	%r12,%rax
+	shrdq	$14,%r13,%r13
+	andq	%rdi,%r15
+	xorq	%rbx,%r14
+	addq	%r13,%rax
+	xorq	%rcx,%r15
+	shrdq	$28,%r14,%r14
+	addq	%rax,%r8
+	addq	%r15,%rax
+	movq	%r8,%r13
+	addq	%rax,%r14
+	movq	128+0(%rsp),%rdi
+	movq	%r14,%rax
+
+	addq	0(%rdi),%rax
+	leaq	128(%rsi),%rsi
+	addq	8(%rdi),%rbx
+	addq	16(%rdi),%rcx
+	addq	24(%rdi),%rdx
+	addq	32(%rdi),%r8
+	addq	40(%rdi),%r9
+	addq	48(%rdi),%r10
+	addq	56(%rdi),%r11
+
+	cmpq	128+16(%rsp),%rsi
+
+	movq	%rax,0(%rdi)
+	movq	%rbx,8(%rdi)
+	movq	%rcx,16(%rdi)
+	movq	%rdx,24(%rdi)
+	movq	%r8,32(%rdi)
+	movq	%r9,40(%rdi)
+	movq	%r10,48(%rdi)
+	movq	%r11,56(%rdi)
+	jb	L$loop_avx
+
+	movq	128+24(%rsp),%rsi
+	vzeroupper
+	movq	(%rsi),%r15
+	movq	8(%rsi),%r14
+	movq	16(%rsi),%r13
+	movq	24(%rsi),%r12
+	movq	32(%rsi),%rbp
+	movq	40(%rsi),%rbx
+	leaq	48(%rsi),%rsp
+L$epilogue_avx:
+	.byte	0xf3,0xc3
+
 #endif
diff --git a/packager/third_party/boringssl/roll_boringssl.py b/packager/third_party/boringssl/roll_boringssl.py
new file mode 100755
index 0000000000..13fe24c775
--- /dev/null
+++ b/packager/third_party/boringssl/roll_boringssl.py
@@ -0,0 +1,126 @@
+#!/usr/bin/env python
+# Copyright 2015 The Chromium Authors. All rights reserved.
+# Use of this source code is governed by a BSD-style license that can be
+# found in the LICENSE file.
+
+"""Rolls third_party/boringssl/src in DEPS and updates generated build files."""
+
+import os
+import os.path
+import shutil
+import subprocess
+import sys
+
+
+SCRIPT_PATH = os.path.abspath(__file__)
+SRC_PATH = os.path.dirname(os.path.dirname(os.path.dirname(SCRIPT_PATH)))
+DEPS_PATH = os.path.join(SRC_PATH, 'DEPS')
+BORINGSSL_PATH = os.path.join(SRC_PATH, 'third_party', 'boringssl')
+BORINGSSL_SRC_PATH = os.path.join(BORINGSSL_PATH, 'src')
+
+if not os.path.isfile(DEPS_PATH) or not os.path.isdir(BORINGSSL_SRC_PATH):
+  raise Exception('Could not find Chromium checkout')
+
+# Pull OS_ARCH_COMBOS out of the BoringSSL script.
+sys.path.append(os.path.join(BORINGSSL_SRC_PATH, 'util'))
+import generate_build_files
+
+GENERATED_FILES = [
+    'BUILD.generated.gni',
+    'BUILD.generated_tests.gni',
+    'boringssl.gypi',
+    'boringssl_tests.gypi',
+    'err_data.c',
+]
+
+
+def IsPristine(repo):
+  """Returns True if a git checkout is pristine."""
+  cmd = ['git', 'diff', '--ignore-submodules']
+  return not (subprocess.check_output(cmd, cwd=repo).strip() or
+              subprocess.check_output(cmd + ['--cached'], cwd=repo).strip())
+
+
+def RevParse(repo, rev):
+  """Resolves a string to a git commit."""
+  return subprocess.check_output(['git', 'rev-parse', rev], cwd=repo).strip()
+
+
+def UpdateDEPS(deps, from_hash, to_hash):
+  """Updates all references of |from_hash| to |to_hash| in |deps|."""
+  with open(deps, 'rb') as f:
+    contents = f.read()
+    if from_hash not in contents:
+      raise Exception('%s not in DEPS' % from_hash)
+  contents = contents.replace(from_hash, to_hash)
+  with open(deps, 'wb') as f:
+    f.write(contents)
+
+
+def main():
+  if len(sys.argv) > 2:
+    sys.stderr.write('Usage: %s [COMMIT]' % sys.argv[0])
+    return 1
+
+  if not IsPristine(SRC_PATH):
+    print >>sys.stderr, 'Chromium checkout not pristine.'
+    return 0
+  if not IsPristine(BORINGSSL_SRC_PATH):
+    print >>sys.stderr, 'BoringSSL checkout not pristine.'
+    return 0
+
+  if len(sys.argv) > 1:
+    commit = RevParse(BORINGSSL_SRC_PATH, sys.argv[1])
+  else:
+    subprocess.check_call(['git', 'fetch', 'origin'], cwd=BORINGSSL_SRC_PATH)
+    commit = RevParse(BORINGSSL_SRC_PATH, 'origin/master')
+
+  head = RevParse(BORINGSSL_SRC_PATH, 'HEAD')
+  if head == commit:
+    print 'BoringSSL already up to date.'
+    return 0
+
+  print 'Rolling BoringSSL from %s to %s...' % (head, commit)
+
+  UpdateDEPS(DEPS_PATH, head, commit)
+
+  # Checkout third_party/boringssl/src to generate new files.
+  subprocess.check_call(['git', 'checkout', commit], cwd=BORINGSSL_SRC_PATH)
+
+  # Clear the old generated files.
+  for (osname, arch, _, _, _) in generate_build_files.OS_ARCH_COMBOS:
+    path = os.path.join(BORINGSSL_PATH, osname + '-' + arch)
+    shutil.rmtree(path)
+  for file in GENERATED_FILES:
+    path = os.path.join(BORINGSSL_PATH, file)
+    os.unlink(path)
+
+  # Generate new ones.
+  subprocess.check_call(['python',
+                         os.path.join(BORINGSSL_SRC_PATH, 'util',
+                                      'generate_build_files.py'),
+                         'gn', 'gyp'],
+                        cwd=BORINGSSL_PATH)
+
+  # Commit everything.
+  subprocess.check_call(['git', 'add', DEPS_PATH], cwd=SRC_PATH)
+  for (osname, arch, _, _, _) in generate_build_files.OS_ARCH_COMBOS:
+    path = os.path.join(BORINGSSL_PATH, osname + '-' + arch)
+    subprocess.check_call(['git', 'add', path], cwd=SRC_PATH)
+  for file in GENERATED_FILES:
+    path = os.path.join(BORINGSSL_PATH, file)
+    subprocess.check_call(['git', 'add', path], cwd=SRC_PATH)
+
+  message = """Roll src/third_party/boringssl/src %s..%s
+
+https://boringssl.googlesource.com/boringssl/+log/%s..%s
+
+BUG=none
+""" % (head[:9], commit[:9], head, commit)
+  subprocess.check_call(['git', 'commit', '-m', message], cwd=SRC_PATH)
+
+  return 0
+
+
+if __name__ == '__main__':
+  sys.exit(main())
diff --git a/packager/third_party/boringssl/win-x86/crypto/chacha/chacha-x86.asm b/packager/third_party/boringssl/win-x86/crypto/chacha/chacha-x86.asm
new file mode 100644
index 0000000000..3ba31a2b35
--- /dev/null
+++ b/packager/third_party/boringssl/win-x86/crypto/chacha/chacha-x86.asm
@@ -0,0 +1,977 @@
+%ifidn __OUTPUT_FORMAT__,obj
+section	code	use32 class=code align=64
+%elifidn __OUTPUT_FORMAT__,win32
+%ifdef __YASM_VERSION_ID__
+%if __YASM_VERSION_ID__ < 01010000h
+%error yasm version 1.1.0 or later needed.
+%endif
+; Yasm automatically includes .00 and complains about redefining it.
+; https://www.tortall.net/projects/yasm/manual/html/objfmt-win32-safeseh.html
+%else
+$@feat.00 equ 1
+%endif
+section	.text	code align=64
+%else
+section	.text	code
+%endif
+global	_ChaCha20_ctr32
+align	16
+_ChaCha20_ctr32:
+L$_ChaCha20_ctr32_begin:
+	push	ebp
+	push	ebx
+	push	esi
+	push	edi
+	xor	eax,eax
+	cmp	eax,DWORD [28+esp]
+	je	NEAR L$000no_data
+	call	L$pic_point
+L$pic_point:
+	pop	eax
+	lea	ebp,[_OPENSSL_ia32cap_P]
+	test	DWORD [ebp],16777216
+	jz	NEAR L$001x86
+	test	DWORD [4+ebp],512
+	jz	NEAR L$001x86
+	jmp	NEAR L$ssse3_shortcut
+L$001x86:
+	mov	esi,DWORD [32+esp]
+	mov	edi,DWORD [36+esp]
+	sub	esp,132
+	mov	eax,DWORD [esi]
+	mov	ebx,DWORD [4+esi]
+	mov	ecx,DWORD [8+esi]
+	mov	edx,DWORD [12+esi]
+	mov	DWORD [80+esp],eax
+	mov	DWORD [84+esp],ebx
+	mov	DWORD [88+esp],ecx
+	mov	DWORD [92+esp],edx
+	mov	eax,DWORD [16+esi]
+	mov	ebx,DWORD [20+esi]
+	mov	ecx,DWORD [24+esi]
+	mov	edx,DWORD [28+esi]
+	mov	DWORD [96+esp],eax
+	mov	DWORD [100+esp],ebx
+	mov	DWORD [104+esp],ecx
+	mov	DWORD [108+esp],edx
+	mov	eax,DWORD [edi]
+	mov	ebx,DWORD [4+edi]
+	mov	ecx,DWORD [8+edi]
+	mov	edx,DWORD [12+edi]
+	sub	eax,1
+	mov	DWORD [112+esp],eax
+	mov	DWORD [116+esp],ebx
+	mov	DWORD [120+esp],ecx
+	mov	DWORD [124+esp],edx
+	jmp	NEAR L$002entry
+align	16
+L$003outer_loop:
+	mov	DWORD [156+esp],ebx
+	mov	DWORD [152+esp],eax
+	mov	DWORD [160+esp],ecx
+L$002entry:
+	mov	eax,1634760805
+	mov	DWORD [4+esp],857760878
+	mov	DWORD [8+esp],2036477234
+	mov	DWORD [12+esp],1797285236
+	mov	ebx,DWORD [84+esp]
+	mov	ebp,DWORD [88+esp]
+	mov	ecx,DWORD [104+esp]
+	mov	esi,DWORD [108+esp]
+	mov	edx,DWORD [116+esp]
+	mov	edi,DWORD [120+esp]
+	mov	DWORD [20+esp],ebx
+	mov	DWORD [24+esp],ebp
+	mov	DWORD [40+esp],ecx
+	mov	DWORD [44+esp],esi
+	mov	DWORD [52+esp],edx
+	mov	DWORD [56+esp],edi
+	mov	ebx,DWORD [92+esp]
+	mov	edi,DWORD [124+esp]
+	mov	edx,DWORD [112+esp]
+	mov	ebp,DWORD [80+esp]
+	mov	ecx,DWORD [96+esp]
+	mov	esi,DWORD [100+esp]
+	add	edx,1
+	mov	DWORD [28+esp],ebx
+	mov	DWORD [60+esp],edi
+	mov	DWORD [112+esp],edx
+	mov	ebx,10
+	jmp	NEAR L$004loop
+align	16
+L$004loop:
+	add	eax,ebp
+	mov	DWORD [128+esp],ebx
+	mov	ebx,ebp
+	xor	edx,eax
+	rol	edx,16
+	add	ecx,edx
+	xor	ebx,ecx
+	mov	edi,DWORD [52+esp]
+	rol	ebx,12
+	mov	ebp,DWORD [20+esp]
+	add	eax,ebx
+	xor	edx,eax
+	mov	DWORD [esp],eax
+	rol	edx,8
+	mov	eax,DWORD [4+esp]
+	add	ecx,edx
+	mov	DWORD [48+esp],edx
+	xor	ebx,ecx
+	add	eax,ebp
+	rol	ebx,7
+	xor	edi,eax
+	mov	DWORD [32+esp],ecx
+	rol	edi,16
+	mov	DWORD [16+esp],ebx
+	add	esi,edi
+	mov	ecx,DWORD [40+esp]
+	xor	ebp,esi
+	mov	edx,DWORD [56+esp]
+	rol	ebp,12
+	mov	ebx,DWORD [24+esp]
+	add	eax,ebp
+	xor	edi,eax
+	mov	DWORD [4+esp],eax
+	rol	edi,8
+	mov	eax,DWORD [8+esp]
+	add	esi,edi
+	mov	DWORD [52+esp],edi
+	xor	ebp,esi
+	add	eax,ebx
+	rol	ebp,7
+	xor	edx,eax
+	mov	DWORD [36+esp],esi
+	rol	edx,16
+	mov	DWORD [20+esp],ebp
+	add	ecx,edx
+	mov	esi,DWORD [44+esp]
+	xor	ebx,ecx
+	mov	edi,DWORD [60+esp]
+	rol	ebx,12
+	mov	ebp,DWORD [28+esp]
+	add	eax,ebx
+	xor	edx,eax
+	mov	DWORD [8+esp],eax
+	rol	edx,8
+	mov	eax,DWORD [12+esp]
+	add	ecx,edx
+	mov	DWORD [56+esp],edx
+	xor	ebx,ecx
+	add	eax,ebp
+	rol	ebx,7
+	xor	edi,eax
+	rol	edi,16
+	mov	DWORD [24+esp],ebx
+	add	esi,edi
+	xor	ebp,esi
+	rol	ebp,12
+	mov	ebx,DWORD [20+esp]
+	add	eax,ebp
+	xor	edi,eax
+	mov	DWORD [12+esp],eax
+	rol	edi,8
+	mov	eax,DWORD [esp]
+	add	esi,edi
+	mov	edx,edi
+	xor	ebp,esi
+	add	eax,ebx
+	rol	ebp,7
+	xor	edx,eax
+	rol	edx,16
+	mov	DWORD [28+esp],ebp
+	add	ecx,edx
+	xor	ebx,ecx
+	mov	edi,DWORD [48+esp]
+	rol	ebx,12
+	mov	ebp,DWORD [24+esp]
+	add	eax,ebx
+	xor	edx,eax
+	mov	DWORD [esp],eax
+	rol	edx,8
+	mov	eax,DWORD [4+esp]
+	add	ecx,edx
+	mov	DWORD [60+esp],edx
+	xor	ebx,ecx
+	add	eax,ebp
+	rol	ebx,7
+	xor	edi,eax
+	mov	DWORD [40+esp],ecx
+	rol	edi,16
+	mov	DWORD [20+esp],ebx
+	add	esi,edi
+	mov	ecx,DWORD [32+esp]
+	xor	ebp,esi
+	mov	edx,DWORD [52+esp]
+	rol	ebp,12
+	mov	ebx,DWORD [28+esp]
+	add	eax,ebp
+	xor	edi,eax
+	mov	DWORD [4+esp],eax
+	rol	edi,8
+	mov	eax,DWORD [8+esp]
+	add	esi,edi
+	mov	DWORD [48+esp],edi
+	xor	ebp,esi
+	add	eax,ebx
+	rol	ebp,7
+	xor	edx,eax
+	mov	DWORD [44+esp],esi
+	rol	edx,16
+	mov	DWORD [24+esp],ebp
+	add	ecx,edx
+	mov	esi,DWORD [36+esp]
+	xor	ebx,ecx
+	mov	edi,DWORD [56+esp]
+	rol	ebx,12
+	mov	ebp,DWORD [16+esp]
+	add	eax,ebx
+	xor	edx,eax
+	mov	DWORD [8+esp],eax
+	rol	edx,8
+	mov	eax,DWORD [12+esp]
+	add	ecx,edx
+	mov	DWORD [52+esp],edx
+	xor	ebx,ecx
+	add	eax,ebp
+	rol	ebx,7
+	xor	edi,eax
+	rol	edi,16
+	mov	DWORD [28+esp],ebx
+	add	esi,edi
+	xor	ebp,esi
+	mov	edx,DWORD [48+esp]
+	rol	ebp,12
+	mov	ebx,DWORD [128+esp]
+	add	eax,ebp
+	xor	edi,eax
+	mov	DWORD [12+esp],eax
+	rol	edi,8
+	mov	eax,DWORD [esp]
+	add	esi,edi
+	mov	DWORD [56+esp],edi
+	xor	ebp,esi
+	rol	ebp,7
+	dec	ebx
+	jnz	NEAR L$004loop
+	mov	ebx,DWORD [160+esp]
+	add	eax,1634760805
+	add	ebp,DWORD [80+esp]
+	add	ecx,DWORD [96+esp]
+	add	esi,DWORD [100+esp]
+	cmp	ebx,64
+	jb	NEAR L$005tail
+	mov	ebx,DWORD [156+esp]
+	add	edx,DWORD [112+esp]
+	add	edi,DWORD [120+esp]
+	xor	eax,DWORD [ebx]
+	xor	ebp,DWORD [16+ebx]
+	mov	DWORD [esp],eax
+	mov	eax,DWORD [152+esp]
+	xor	ecx,DWORD [32+ebx]
+	xor	esi,DWORD [36+ebx]
+	xor	edx,DWORD [48+ebx]
+	xor	edi,DWORD [56+ebx]
+	mov	DWORD [16+eax],ebp
+	mov	DWORD [32+eax],ecx
+	mov	DWORD [36+eax],esi
+	mov	DWORD [48+eax],edx
+	mov	DWORD [56+eax],edi
+	mov	ebp,DWORD [4+esp]
+	mov	ecx,DWORD [8+esp]
+	mov	esi,DWORD [12+esp]
+	mov	edx,DWORD [20+esp]
+	mov	edi,DWORD [24+esp]
+	add	ebp,857760878
+	add	ecx,2036477234
+	add	esi,1797285236
+	add	edx,DWORD [84+esp]
+	add	edi,DWORD [88+esp]
+	xor	ebp,DWORD [4+ebx]
+	xor	ecx,DWORD [8+ebx]
+	xor	esi,DWORD [12+ebx]
+	xor	edx,DWORD [20+ebx]
+	xor	edi,DWORD [24+ebx]
+	mov	DWORD [4+eax],ebp
+	mov	DWORD [8+eax],ecx
+	mov	DWORD [12+eax],esi
+	mov	DWORD [20+eax],edx
+	mov	DWORD [24+eax],edi
+	mov	ebp,DWORD [28+esp]
+	mov	ecx,DWORD [40+esp]
+	mov	esi,DWORD [44+esp]
+	mov	edx,DWORD [52+esp]
+	mov	edi,DWORD [60+esp]
+	add	ebp,DWORD [92+esp]
+	add	ecx,DWORD [104+esp]
+	add	esi,DWORD [108+esp]
+	add	edx,DWORD [116+esp]
+	add	edi,DWORD [124+esp]
+	xor	ebp,DWORD [28+ebx]
+	xor	ecx,DWORD [40+ebx]
+	xor	esi,DWORD [44+ebx]
+	xor	edx,DWORD [52+ebx]
+	xor	edi,DWORD [60+ebx]
+	lea	ebx,[64+ebx]
+	mov	DWORD [28+eax],ebp
+	mov	ebp,DWORD [esp]
+	mov	DWORD [40+eax],ecx
+	mov	ecx,DWORD [160+esp]
+	mov	DWORD [44+eax],esi
+	mov	DWORD [52+eax],edx
+	mov	DWORD [60+eax],edi
+	mov	DWORD [eax],ebp
+	lea	eax,[64+eax]
+	sub	ecx,64
+	jnz	NEAR L$003outer_loop
+	jmp	NEAR L$006done
+L$005tail:
+	add	edx,DWORD [112+esp]
+	add	edi,DWORD [120+esp]
+	mov	DWORD [esp],eax
+	mov	DWORD [16+esp],ebp
+	mov	DWORD [32+esp],ecx
+	mov	DWORD [36+esp],esi
+	mov	DWORD [48+esp],edx
+	mov	DWORD [56+esp],edi
+	mov	ebp,DWORD [4+esp]
+	mov	ecx,DWORD [8+esp]
+	mov	esi,DWORD [12+esp]
+	mov	edx,DWORD [20+esp]
+	mov	edi,DWORD [24+esp]
+	add	ebp,857760878
+	add	ecx,2036477234
+	add	esi,1797285236
+	add	edx,DWORD [84+esp]
+	add	edi,DWORD [88+esp]
+	mov	DWORD [4+esp],ebp
+	mov	DWORD [8+esp],ecx
+	mov	DWORD [12+esp],esi
+	mov	DWORD [20+esp],edx
+	mov	DWORD [24+esp],edi
+	mov	ebp,DWORD [28+esp]
+	mov	ecx,DWORD [40+esp]
+	mov	esi,DWORD [44+esp]
+	mov	edx,DWORD [52+esp]
+	mov	edi,DWORD [60+esp]
+	add	ebp,DWORD [92+esp]
+	add	ecx,DWORD [104+esp]
+	add	esi,DWORD [108+esp]
+	add	edx,DWORD [116+esp]
+	add	edi,DWORD [124+esp]
+	mov	DWORD [28+esp],ebp
+	mov	ebp,DWORD [156+esp]
+	mov	DWORD [40+esp],ecx
+	mov	ecx,DWORD [152+esp]
+	mov	DWORD [44+esp],esi
+	xor	esi,esi
+	mov	DWORD [52+esp],edx
+	mov	DWORD [60+esp],edi
+	xor	eax,eax
+	xor	edx,edx
+L$007tail_loop:
+	mov	al,BYTE [ebp*1+esi]
+	mov	dl,BYTE [esi*1+esp]
+	lea	esi,[1+esi]
+	xor	al,dl
+	mov	BYTE [esi*1+ecx-1],al
+	dec	ebx
+	jnz	NEAR L$007tail_loop
+L$006done:
+	add	esp,132
+L$000no_data:
+	pop	edi
+	pop	esi
+	pop	ebx
+	pop	ebp
+	ret
+global	_ChaCha20_ssse3
+align	16
+_ChaCha20_ssse3:
+L$_ChaCha20_ssse3_begin:
+	push	ebp
+	push	ebx
+	push	esi
+	push	edi
+L$ssse3_shortcut:
+	mov	edi,DWORD [20+esp]
+	mov	esi,DWORD [24+esp]
+	mov	ecx,DWORD [28+esp]
+	mov	edx,DWORD [32+esp]
+	mov	ebx,DWORD [36+esp]
+	mov	ebp,esp
+	sub	esp,524
+	and	esp,-64
+	mov	DWORD [512+esp],ebp
+	lea	eax,[(L$ssse3_data-L$pic_point)+eax]
+	movdqu	xmm3,[ebx]
+	cmp	ecx,256
+	jb	NEAR L$0081x
+	mov	DWORD [516+esp],edx
+	mov	DWORD [520+esp],ebx
+	sub	ecx,256
+	lea	ebp,[384+esp]
+	movdqu	xmm7,[edx]
+	pshufd	xmm0,xmm3,0
+	pshufd	xmm1,xmm3,85
+	pshufd	xmm2,xmm3,170
+	pshufd	xmm3,xmm3,255
+	paddd	xmm0,[48+eax]
+	pshufd	xmm4,xmm7,0
+	pshufd	xmm5,xmm7,85
+	psubd	xmm0,[64+eax]
+	pshufd	xmm6,xmm7,170
+	pshufd	xmm7,xmm7,255
+	movdqa	[64+ebp],xmm0
+	movdqa	[80+ebp],xmm1
+	movdqa	[96+ebp],xmm2
+	movdqa	[112+ebp],xmm3
+	movdqu	xmm3,[16+edx]
+	movdqa	[ebp-64],xmm4
+	movdqa	[ebp-48],xmm5
+	movdqa	[ebp-32],xmm6
+	movdqa	[ebp-16],xmm7
+	movdqa	xmm7,[32+eax]
+	lea	ebx,[128+esp]
+	pshufd	xmm0,xmm3,0
+	pshufd	xmm1,xmm3,85
+	pshufd	xmm2,xmm3,170
+	pshufd	xmm3,xmm3,255
+	pshufd	xmm4,xmm7,0
+	pshufd	xmm5,xmm7,85
+	pshufd	xmm6,xmm7,170
+	pshufd	xmm7,xmm7,255
+	movdqa	[ebp],xmm0
+	movdqa	[16+ebp],xmm1
+	movdqa	[32+ebp],xmm2
+	movdqa	[48+ebp],xmm3
+	movdqa	[ebp-128],xmm4
+	movdqa	[ebp-112],xmm5
+	movdqa	[ebp-96],xmm6
+	movdqa	[ebp-80],xmm7
+	lea	esi,[128+esi]
+	lea	edi,[128+edi]
+	jmp	NEAR L$009outer_loop
+align	16
+L$009outer_loop:
+	movdqa	xmm1,[ebp-112]
+	movdqa	xmm2,[ebp-96]
+	movdqa	xmm3,[ebp-80]
+	movdqa	xmm5,[ebp-48]
+	movdqa	xmm6,[ebp-32]
+	movdqa	xmm7,[ebp-16]
+	movdqa	[ebx-112],xmm1
+	movdqa	[ebx-96],xmm2
+	movdqa	[ebx-80],xmm3
+	movdqa	[ebx-48],xmm5
+	movdqa	[ebx-32],xmm6
+	movdqa	[ebx-16],xmm7
+	movdqa	xmm2,[32+ebp]
+	movdqa	xmm3,[48+ebp]
+	movdqa	xmm4,[64+ebp]
+	movdqa	xmm5,[80+ebp]
+	movdqa	xmm6,[96+ebp]
+	movdqa	xmm7,[112+ebp]
+	paddd	xmm4,[64+eax]
+	movdqa	[32+ebx],xmm2
+	movdqa	[48+ebx],xmm3
+	movdqa	[64+ebx],xmm4
+	movdqa	[80+ebx],xmm5
+	movdqa	[96+ebx],xmm6
+	movdqa	[112+ebx],xmm7
+	movdqa	[64+ebp],xmm4
+	movdqa	xmm0,[ebp-128]
+	movdqa	xmm6,xmm4
+	movdqa	xmm3,[ebp-64]
+	movdqa	xmm4,[ebp]
+	movdqa	xmm5,[16+ebp]
+	mov	edx,10
+	nop
+align	16
+L$010loop:
+	paddd	xmm0,xmm3
+	movdqa	xmm2,xmm3
+	pxor	xmm6,xmm0
+	pshufb	xmm6,[eax]
+	paddd	xmm4,xmm6
+	pxor	xmm2,xmm4
+	movdqa	xmm3,[ebx-48]
+	movdqa	xmm1,xmm2
+	pslld	xmm2,12
+	psrld	xmm1,20
+	por	xmm2,xmm1
+	movdqa	xmm1,[ebx-112]
+	paddd	xmm0,xmm2
+	movdqa	xmm7,[80+ebx]
+	pxor	xmm6,xmm0
+	movdqa	[ebx-128],xmm0
+	pshufb	xmm6,[16+eax]
+	paddd	xmm4,xmm6
+	movdqa	[64+ebx],xmm6
+	pxor	xmm2,xmm4
+	paddd	xmm1,xmm3
+	movdqa	xmm0,xmm2
+	pslld	xmm2,7
+	psrld	xmm0,25
+	pxor	xmm7,xmm1
+	por	xmm2,xmm0
+	movdqa	[ebx],xmm4
+	pshufb	xmm7,[eax]
+	movdqa	[ebx-64],xmm2
+	paddd	xmm5,xmm7
+	movdqa	xmm4,[32+ebx]
+	pxor	xmm3,xmm5
+	movdqa	xmm2,[ebx-32]
+	movdqa	xmm0,xmm3
+	pslld	xmm3,12
+	psrld	xmm0,20
+	por	xmm3,xmm0
+	movdqa	xmm0,[ebx-96]
+	paddd	xmm1,xmm3
+	movdqa	xmm6,[96+ebx]
+	pxor	xmm7,xmm1
+	movdqa	[ebx-112],xmm1
+	pshufb	xmm7,[16+eax]
+	paddd	xmm5,xmm7
+	movdqa	[80+ebx],xmm7
+	pxor	xmm3,xmm5
+	paddd	xmm0,xmm2
+	movdqa	xmm1,xmm3
+	pslld	xmm3,7
+	psrld	xmm1,25
+	pxor	xmm6,xmm0
+	por	xmm3,xmm1
+	movdqa	[16+ebx],xmm5
+	pshufb	xmm6,[eax]
+	movdqa	[ebx-48],xmm3
+	paddd	xmm4,xmm6
+	movdqa	xmm5,[48+ebx]
+	pxor	xmm2,xmm4
+	movdqa	xmm3,[ebx-16]
+	movdqa	xmm1,xmm2
+	pslld	xmm2,12
+	psrld	xmm1,20
+	por	xmm2,xmm1
+	movdqa	xmm1,[ebx-80]
+	paddd	xmm0,xmm2
+	movdqa	xmm7,[112+ebx]
+	pxor	xmm6,xmm0
+	movdqa	[ebx-96],xmm0
+	pshufb	xmm6,[16+eax]
+	paddd	xmm4,xmm6
+	movdqa	[96+ebx],xmm6
+	pxor	xmm2,xmm4
+	paddd	xmm1,xmm3
+	movdqa	xmm0,xmm2
+	pslld	xmm2,7
+	psrld	xmm0,25
+	pxor	xmm7,xmm1
+	por	xmm2,xmm0
+	pshufb	xmm7,[eax]
+	movdqa	[ebx-32],xmm2
+	paddd	xmm5,xmm7
+	pxor	xmm3,xmm5
+	movdqa	xmm2,[ebx-48]
+	movdqa	xmm0,xmm3
+	pslld	xmm3,12
+	psrld	xmm0,20
+	por	xmm3,xmm0
+	movdqa	xmm0,[ebx-128]
+	paddd	xmm1,xmm3
+	pxor	xmm7,xmm1
+	movdqa	[ebx-80],xmm1
+	pshufb	xmm7,[16+eax]
+	paddd	xmm5,xmm7
+	movdqa	xmm6,xmm7
+	pxor	xmm3,xmm5
+	paddd	xmm0,xmm2
+	movdqa	xmm1,xmm3
+	pslld	xmm3,7
+	psrld	xmm1,25
+	pxor	xmm6,xmm0
+	por	xmm3,xmm1
+	pshufb	xmm6,[eax]
+	movdqa	[ebx-16],xmm3
+	paddd	xmm4,xmm6
+	pxor	xmm2,xmm4
+	movdqa	xmm3,[ebx-32]
+	movdqa	xmm1,xmm2
+	pslld	xmm2,12
+	psrld	xmm1,20
+	por	xmm2,xmm1
+	movdqa	xmm1,[ebx-112]
+	paddd	xmm0,xmm2
+	movdqa	xmm7,[64+ebx]
+	pxor	xmm6,xmm0
+	movdqa	[ebx-128],xmm0
+	pshufb	xmm6,[16+eax]
+	paddd	xmm4,xmm6
+	movdqa	[112+ebx],xmm6
+	pxor	xmm2,xmm4
+	paddd	xmm1,xmm3
+	movdqa	xmm0,xmm2
+	pslld	xmm2,7
+	psrld	xmm0,25
+	pxor	xmm7,xmm1
+	por	xmm2,xmm0
+	movdqa	[32+ebx],xmm4
+	pshufb	xmm7,[eax]
+	movdqa	[ebx-48],xmm2
+	paddd	xmm5,xmm7
+	movdqa	xmm4,[ebx]
+	pxor	xmm3,xmm5
+	movdqa	xmm2,[ebx-16]
+	movdqa	xmm0,xmm3
+	pslld	xmm3,12
+	psrld	xmm0,20
+	por	xmm3,xmm0
+	movdqa	xmm0,[ebx-96]
+	paddd	xmm1,xmm3
+	movdqa	xmm6,[80+ebx]
+	pxor	xmm7,xmm1
+	movdqa	[ebx-112],xmm1
+	pshufb	xmm7,[16+eax]
+	paddd	xmm5,xmm7
+	movdqa	[64+ebx],xmm7
+	pxor	xmm3,xmm5
+	paddd	xmm0,xmm2
+	movdqa	xmm1,xmm3
+	pslld	xmm3,7
+	psrld	xmm1,25
+	pxor	xmm6,xmm0
+	por	xmm3,xmm1
+	movdqa	[48+ebx],xmm5
+	pshufb	xmm6,[eax]
+	movdqa	[ebx-32],xmm3
+	paddd	xmm4,xmm6
+	movdqa	xmm5,[16+ebx]
+	pxor	xmm2,xmm4
+	movdqa	xmm3,[ebx-64]
+	movdqa	xmm1,xmm2
+	pslld	xmm2,12
+	psrld	xmm1,20
+	por	xmm2,xmm1
+	movdqa	xmm1,[ebx-80]
+	paddd	xmm0,xmm2
+	movdqa	xmm7,[96+ebx]
+	pxor	xmm6,xmm0
+	movdqa	[ebx-96],xmm0
+	pshufb	xmm6,[16+eax]
+	paddd	xmm4,xmm6
+	movdqa	[80+ebx],xmm6
+	pxor	xmm2,xmm4
+	paddd	xmm1,xmm3
+	movdqa	xmm0,xmm2
+	pslld	xmm2,7
+	psrld	xmm0,25
+	pxor	xmm7,xmm1
+	por	xmm2,xmm0
+	pshufb	xmm7,[eax]
+	movdqa	[ebx-16],xmm2
+	paddd	xmm5,xmm7
+	pxor	xmm3,xmm5
+	movdqa	xmm0,xmm3
+	pslld	xmm3,12
+	psrld	xmm0,20
+	por	xmm3,xmm0
+	movdqa	xmm0,[ebx-128]
+	paddd	xmm1,xmm3
+	movdqa	xmm6,[64+ebx]
+	pxor	xmm7,xmm1
+	movdqa	[ebx-80],xmm1
+	pshufb	xmm7,[16+eax]
+	paddd	xmm5,xmm7
+	movdqa	[96+ebx],xmm7
+	pxor	xmm3,xmm5
+	movdqa	xmm1,xmm3
+	pslld	xmm3,7
+	psrld	xmm1,25
+	por	xmm3,xmm1
+	dec	edx
+	jnz	NEAR L$010loop
+	movdqa	[ebx-64],xmm3
+	movdqa	[ebx],xmm4
+	movdqa	[16+ebx],xmm5
+	movdqa	[64+ebx],xmm6
+	movdqa	[96+ebx],xmm7
+	movdqa	xmm1,[ebx-112]
+	movdqa	xmm2,[ebx-96]
+	movdqa	xmm3,[ebx-80]
+	paddd	xmm0,[ebp-128]
+	paddd	xmm1,[ebp-112]
+	paddd	xmm2,[ebp-96]
+	paddd	xmm3,[ebp-80]
+	movdqa	xmm6,xmm0
+	punpckldq	xmm0,xmm1
+	movdqa	xmm7,xmm2
+	punpckldq	xmm2,xmm3
+	punpckhdq	xmm6,xmm1
+	punpckhdq	xmm7,xmm3
+	movdqa	xmm1,xmm0
+	punpcklqdq	xmm0,xmm2
+	movdqa	xmm3,xmm6
+	punpcklqdq	xmm6,xmm7
+	punpckhqdq	xmm1,xmm2
+	punpckhqdq	xmm3,xmm7
+	movdqu	xmm4,[esi-128]
+	movdqu	xmm5,[esi-64]
+	movdqu	xmm2,[esi]
+	movdqu	xmm7,[64+esi]
+	lea	esi,[16+esi]
+	pxor	xmm4,xmm0
+	movdqa	xmm0,[ebx-64]
+	pxor	xmm5,xmm1
+	movdqa	xmm1,[ebx-48]
+	pxor	xmm6,xmm2
+	movdqa	xmm2,[ebx-32]
+	pxor	xmm7,xmm3
+	movdqa	xmm3,[ebx-16]
+	movdqu	[edi-128],xmm4
+	movdqu	[edi-64],xmm5
+	movdqu	[edi],xmm6
+	movdqu	[64+edi],xmm7
+	lea	edi,[16+edi]
+	paddd	xmm0,[ebp-64]
+	paddd	xmm1,[ebp-48]
+	paddd	xmm2,[ebp-32]
+	paddd	xmm3,[ebp-16]
+	movdqa	xmm6,xmm0
+	punpckldq	xmm0,xmm1
+	movdqa	xmm7,xmm2
+	punpckldq	xmm2,xmm3
+	punpckhdq	xmm6,xmm1
+	punpckhdq	xmm7,xmm3
+	movdqa	xmm1,xmm0
+	punpcklqdq	xmm0,xmm2
+	movdqa	xmm3,xmm6
+	punpcklqdq	xmm6,xmm7
+	punpckhqdq	xmm1,xmm2
+	punpckhqdq	xmm3,xmm7
+	movdqu	xmm4,[esi-128]
+	movdqu	xmm5,[esi-64]
+	movdqu	xmm2,[esi]
+	movdqu	xmm7,[64+esi]
+	lea	esi,[16+esi]
+	pxor	xmm4,xmm0
+	movdqa	xmm0,[ebx]
+	pxor	xmm5,xmm1
+	movdqa	xmm1,[16+ebx]
+	pxor	xmm6,xmm2
+	movdqa	xmm2,[32+ebx]
+	pxor	xmm7,xmm3
+	movdqa	xmm3,[48+ebx]
+	movdqu	[edi-128],xmm4
+	movdqu	[edi-64],xmm5
+	movdqu	[edi],xmm6
+	movdqu	[64+edi],xmm7
+	lea	edi,[16+edi]
+	paddd	xmm0,[ebp]
+	paddd	xmm1,[16+ebp]
+	paddd	xmm2,[32+ebp]
+	paddd	xmm3,[48+ebp]
+	movdqa	xmm6,xmm0
+	punpckldq	xmm0,xmm1
+	movdqa	xmm7,xmm2
+	punpckldq	xmm2,xmm3
+	punpckhdq	xmm6,xmm1
+	punpckhdq	xmm7,xmm3
+	movdqa	xmm1,xmm0
+	punpcklqdq	xmm0,xmm2
+	movdqa	xmm3,xmm6
+	punpcklqdq	xmm6,xmm7
+	punpckhqdq	xmm1,xmm2
+	punpckhqdq	xmm3,xmm7
+	movdqu	xmm4,[esi-128]
+	movdqu	xmm5,[esi-64]
+	movdqu	xmm2,[esi]
+	movdqu	xmm7,[64+esi]
+	lea	esi,[16+esi]
+	pxor	xmm4,xmm0
+	movdqa	xmm0,[64+ebx]
+	pxor	xmm5,xmm1
+	movdqa	xmm1,[80+ebx]
+	pxor	xmm6,xmm2
+	movdqa	xmm2,[96+ebx]
+	pxor	xmm7,xmm3
+	movdqa	xmm3,[112+ebx]
+	movdqu	[edi-128],xmm4
+	movdqu	[edi-64],xmm5
+	movdqu	[edi],xmm6
+	movdqu	[64+edi],xmm7
+	lea	edi,[16+edi]
+	paddd	xmm0,[64+ebp]
+	paddd	xmm1,[80+ebp]
+	paddd	xmm2,[96+ebp]
+	paddd	xmm3,[112+ebp]
+	movdqa	xmm6,xmm0
+	punpckldq	xmm0,xmm1
+	movdqa	xmm7,xmm2
+	punpckldq	xmm2,xmm3
+	punpckhdq	xmm6,xmm1
+	punpckhdq	xmm7,xmm3
+	movdqa	xmm1,xmm0
+	punpcklqdq	xmm0,xmm2
+	movdqa	xmm3,xmm6
+	punpcklqdq	xmm6,xmm7
+	punpckhqdq	xmm1,xmm2
+	punpckhqdq	xmm3,xmm7
+	movdqu	xmm4,[esi-128]
+	movdqu	xmm5,[esi-64]
+	movdqu	xmm2,[esi]
+	movdqu	xmm7,[64+esi]
+	lea	esi,[208+esi]
+	pxor	xmm4,xmm0
+	pxor	xmm5,xmm1
+	pxor	xmm6,xmm2
+	pxor	xmm7,xmm3
+	movdqu	[edi-128],xmm4
+	movdqu	[edi-64],xmm5
+	movdqu	[edi],xmm6
+	movdqu	[64+edi],xmm7
+	lea	edi,[208+edi]
+	sub	ecx,256
+	jnc	NEAR L$009outer_loop
+	add	ecx,256
+	jz	NEAR L$011done
+	mov	ebx,DWORD [520+esp]
+	lea	esi,[esi-128]
+	mov	edx,DWORD [516+esp]
+	lea	edi,[edi-128]
+	movd	xmm2,DWORD [64+ebp]
+	movdqu	xmm3,[ebx]
+	paddd	xmm2,[96+eax]
+	pand	xmm3,[112+eax]
+	por	xmm3,xmm2
+L$0081x:
+	movdqa	xmm0,[32+eax]
+	movdqu	xmm1,[edx]
+	movdqu	xmm2,[16+edx]
+	movdqa	xmm6,[eax]
+	movdqa	xmm7,[16+eax]
+	mov	DWORD [48+esp],ebp
+	movdqa	[esp],xmm0
+	movdqa	[16+esp],xmm1
+	movdqa	[32+esp],xmm2
+	movdqa	[48+esp],xmm3
+	mov	edx,10
+	jmp	NEAR L$012loop1x
+align	16
+L$013outer1x:
+	movdqa	xmm3,[80+eax]
+	movdqa	xmm0,[esp]
+	movdqa	xmm1,[16+esp]
+	movdqa	xmm2,[32+esp]
+	paddd	xmm3,[48+esp]
+	mov	edx,10
+	movdqa	[48+esp],xmm3
+	jmp	NEAR L$012loop1x
+align	16
+L$012loop1x:
+	paddd	xmm0,xmm1
+	pxor	xmm3,xmm0
+db	102,15,56,0,222
+	paddd	xmm2,xmm3
+	pxor	xmm1,xmm2
+	movdqa	xmm4,xmm1
+	psrld	xmm1,20
+	pslld	xmm4,12
+	por	xmm1,xmm4
+	paddd	xmm0,xmm1
+	pxor	xmm3,xmm0
+db	102,15,56,0,223
+	paddd	xmm2,xmm3
+	pxor	xmm1,xmm2
+	movdqa	xmm4,xmm1
+	psrld	xmm1,25
+	pslld	xmm4,7
+	por	xmm1,xmm4
+	pshufd	xmm2,xmm2,78
+	pshufd	xmm1,xmm1,57
+	pshufd	xmm3,xmm3,147
+	nop
+	paddd	xmm0,xmm1
+	pxor	xmm3,xmm0
+db	102,15,56,0,222
+	paddd	xmm2,xmm3
+	pxor	xmm1,xmm2
+	movdqa	xmm4,xmm1
+	psrld	xmm1,20
+	pslld	xmm4,12
+	por	xmm1,xmm4
+	paddd	xmm0,xmm1
+	pxor	xmm3,xmm0
+db	102,15,56,0,223
+	paddd	xmm2,xmm3
+	pxor	xmm1,xmm2
+	movdqa	xmm4,xmm1
+	psrld	xmm1,25
+	pslld	xmm4,7
+	por	xmm1,xmm4
+	pshufd	xmm2,xmm2,78
+	pshufd	xmm1,xmm1,147
+	pshufd	xmm3,xmm3,57
+	dec	edx
+	jnz	NEAR L$012loop1x
+	paddd	xmm0,[esp]
+	paddd	xmm1,[16+esp]
+	paddd	xmm2,[32+esp]
+	paddd	xmm3,[48+esp]
+	cmp	ecx,64
+	jb	NEAR L$014tail
+	movdqu	xmm4,[esi]
+	movdqu	xmm5,[16+esi]
+	pxor	xmm0,xmm4
+	movdqu	xmm4,[32+esi]
+	pxor	xmm1,xmm5
+	movdqu	xmm5,[48+esi]
+	pxor	xmm2,xmm4
+	pxor	xmm3,xmm5
+	lea	esi,[64+esi]
+	movdqu	[edi],xmm0
+	movdqu	[16+edi],xmm1
+	movdqu	[32+edi],xmm2
+	movdqu	[48+edi],xmm3
+	lea	edi,[64+edi]
+	sub	ecx,64
+	jnz	NEAR L$013outer1x
+	jmp	NEAR L$011done
+L$014tail:
+	movdqa	[esp],xmm0
+	movdqa	[16+esp],xmm1
+	movdqa	[32+esp],xmm2
+	movdqa	[48+esp],xmm3
+	xor	eax,eax
+	xor	edx,edx
+	xor	ebp,ebp
+L$015tail_loop:
+	mov	al,BYTE [ebp*1+esp]
+	mov	dl,BYTE [ebp*1+esi]
+	lea	ebp,[1+ebp]
+	xor	al,dl
+	mov	BYTE [ebp*1+edi-1],al
+	dec	ecx
+	jnz	NEAR L$015tail_loop
+L$011done:
+	mov	esp,DWORD [512+esp]
+	pop	edi
+	pop	esi
+	pop	ebx
+	pop	ebp
+	ret
+align	64
+L$ssse3_data:
+db	2,3,0,1,6,7,4,5,10,11,8,9,14,15,12,13
+db	3,0,1,2,7,4,5,6,11,8,9,10,15,12,13,14
+dd	1634760805,857760878,2036477234,1797285236
+dd	0,1,2,3
+dd	4,4,4,4
+dd	1,0,0,0
+dd	4,0,0,0
+dd	0,-1,-1,-1
+align	64
+db	67,104,97,67,104,97,50,48,32,102,111,114,32,120,56,54
+db	44,32,67,82,89,80,84,79,71,65,77,83,32,98,121,32
+db	60,97,112,112,114,111,64,111,112,101,110,115,115,108,46,111
+db	114,103,62,0
+segment	.bss
+common	_OPENSSL_ia32cap_P 16
diff --git a/packager/third_party/boringssl/win-x86/crypto/rc4/rc4-586.asm b/packager/third_party/boringssl/win-x86/crypto/rc4/rc4-586.asm
index 08cd9f6d70..0bab2bec85 100644
--- a/packager/third_party/boringssl/win-x86/crypto/rc4/rc4-586.asm
+++ b/packager/third_party/boringssl/win-x86/crypto/rc4/rc4-586.asm
@@ -349,34 +349,5 @@ L$013exit:
 	pop	ebx
 	pop	ebp
 	ret
-global	_RC4_options
-align	16
-_RC4_options:
-L$_RC4_options_begin:
-	call	L$016pic_point
-L$016pic_point:
-	pop	eax
-	lea	eax,[(L$017opts-L$016pic_point)+eax]
-	lea	edx,[_OPENSSL_ia32cap_P]
-	mov	edx,DWORD [edx]
-	bt	edx,20
-	jc	NEAR L$0181xchar
-	bt	edx,26
-	jnc	NEAR L$019ret
-	add	eax,25
-	ret
-L$0181xchar:
-	add	eax,12
-L$019ret:
-	ret
-align	64
-L$017opts:
-db	114,99,52,40,52,120,44,105,110,116,41,0
-db	114,99,52,40,49,120,44,99,104,97,114,41,0
-db	114,99,52,40,56,120,44,109,109,120,41,0
-db	82,67,52,32,102,111,114,32,120,56,54,44,32,67,82,89
-db	80,84,79,71,65,77,83,32,98,121,32,60,97,112,112,114
-db	111,64,111,112,101,110,115,115,108,46,111,114,103,62,0
-align	64
 segment	.bss
 common	_OPENSSL_ia32cap_P 16
diff --git a/packager/third_party/boringssl/win-x86/crypto/sha/sha1-586.asm b/packager/third_party/boringssl/win-x86/crypto/sha/sha1-586.asm
index e24449d200..cee8c62626 100644
--- a/packager/third_party/boringssl/win-x86/crypto/sha/sha1-586.asm
+++ b/packager/third_party/boringssl/win-x86/crypto/sha/sha1-586.asm
@@ -35,8 +35,11 @@ L$000pic_point:
 	mov	ecx,DWORD [8+esi]
 	test	eax,16777216
 	jz	NEAR L$001x86
-	test	ecx,536870912
-	jnz	NEAR L$shaext_shortcut
+	and	edx,268435456
+	and	eax,1073741824
+	or	eax,edx
+	cmp	eax,1342177280
+	je	NEAR L$avx_shortcut
 	jmp	NEAR L$ssse3_shortcut
 align	16
 L$001x86:
@@ -1405,7 +1408,7 @@ L$002loop:
 	pop	ebp
 	ret
 align	16
-__sha1_block_data_order_shaext:
+__sha1_block_data_order_ssse3:
 	push	ebp
 	push	ebx
 	push	esi
@@ -1414,174 +1417,6 @@ __sha1_block_data_order_shaext:
 L$003pic_point:
 	pop	ebp
 	lea	ebp,[(L$K_XX_XX-L$003pic_point)+ebp]
-L$shaext_shortcut:
-	mov	edi,DWORD [20+esp]
-	mov	ebx,esp
-	mov	esi,DWORD [24+esp]
-	mov	ecx,DWORD [28+esp]
-	sub	esp,32
-	movdqu	xmm0,[edi]
-	movd	xmm1,DWORD [16+edi]
-	and	esp,-32
-	movdqa	xmm3,[80+ebp]
-	movdqu	xmm4,[esi]
-	pshufd	xmm0,xmm0,27
-	movdqu	xmm5,[16+esi]
-	pshufd	xmm1,xmm1,27
-	movdqu	xmm6,[32+esi]
-db	102,15,56,0,227
-	movdqu	xmm7,[48+esi]
-db	102,15,56,0,235
-db	102,15,56,0,243
-db	102,15,56,0,251
-	jmp	NEAR L$004loop_shaext
-align	16
-L$004loop_shaext:
-	dec	ecx
-	lea	eax,[64+esi]
-	movdqa	[esp],xmm1
-	paddd	xmm1,xmm4
-	cmovne	esi,eax
-	movdqa	[16+esp],xmm0
-db	15,56,201,229
-	movdqa	xmm2,xmm0
-db	15,58,204,193,0
-db	15,56,200,213
-	pxor	xmm4,xmm6
-db	15,56,201,238
-db	15,56,202,231
-	movdqa	xmm1,xmm0
-db	15,58,204,194,0
-db	15,56,200,206
-	pxor	xmm5,xmm7
-db	15,56,202,236
-db	15,56,201,247
-	movdqa	xmm2,xmm0
-db	15,58,204,193,0
-db	15,56,200,215
-	pxor	xmm6,xmm4
-db	15,56,201,252
-db	15,56,202,245
-	movdqa	xmm1,xmm0
-db	15,58,204,194,0
-db	15,56,200,204
-	pxor	xmm7,xmm5
-db	15,56,202,254
-db	15,56,201,229
-	movdqa	xmm2,xmm0
-db	15,58,204,193,0
-db	15,56,200,213
-	pxor	xmm4,xmm6
-db	15,56,201,238
-db	15,56,202,231
-	movdqa	xmm1,xmm0
-db	15,58,204,194,1
-db	15,56,200,206
-	pxor	xmm5,xmm7
-db	15,56,202,236
-db	15,56,201,247
-	movdqa	xmm2,xmm0
-db	15,58,204,193,1
-db	15,56,200,215
-	pxor	xmm6,xmm4
-db	15,56,201,252
-db	15,56,202,245
-	movdqa	xmm1,xmm0
-db	15,58,204,194,1
-db	15,56,200,204
-	pxor	xmm7,xmm5
-db	15,56,202,254
-db	15,56,201,229
-	movdqa	xmm2,xmm0
-db	15,58,204,193,1
-db	15,56,200,213
-	pxor	xmm4,xmm6
-db	15,56,201,238
-db	15,56,202,231
-	movdqa	xmm1,xmm0
-db	15,58,204,194,1
-db	15,56,200,206
-	pxor	xmm5,xmm7
-db	15,56,202,236
-db	15,56,201,247
-	movdqa	xmm2,xmm0
-db	15,58,204,193,2
-db	15,56,200,215
-	pxor	xmm6,xmm4
-db	15,56,201,252
-db	15,56,202,245
-	movdqa	xmm1,xmm0
-db	15,58,204,194,2
-db	15,56,200,204
-	pxor	xmm7,xmm5
-db	15,56,202,254
-db	15,56,201,229
-	movdqa	xmm2,xmm0
-db	15,58,204,193,2
-db	15,56,200,213
-	pxor	xmm4,xmm6
-db	15,56,201,238
-db	15,56,202,231
-	movdqa	xmm1,xmm0
-db	15,58,204,194,2
-db	15,56,200,206
-	pxor	xmm5,xmm7
-db	15,56,202,236
-db	15,56,201,247
-	movdqa	xmm2,xmm0
-db	15,58,204,193,2
-db	15,56,200,215
-	pxor	xmm6,xmm4
-db	15,56,201,252
-db	15,56,202,245
-	movdqa	xmm1,xmm0
-db	15,58,204,194,3
-db	15,56,200,204
-	pxor	xmm7,xmm5
-db	15,56,202,254
-	movdqu	xmm4,[esi]
-	movdqa	xmm2,xmm0
-db	15,58,204,193,3
-db	15,56,200,213
-	movdqu	xmm5,[16+esi]
-db	102,15,56,0,227
-	movdqa	xmm1,xmm0
-db	15,58,204,194,3
-db	15,56,200,206
-	movdqu	xmm6,[32+esi]
-db	102,15,56,0,235
-	movdqa	xmm2,xmm0
-db	15,58,204,193,3
-db	15,56,200,215
-	movdqu	xmm7,[48+esi]
-db	102,15,56,0,243
-	movdqa	xmm1,xmm0
-db	15,58,204,194,3
-	movdqa	xmm2,[esp]
-db	102,15,56,0,251
-db	15,56,200,202
-	paddd	xmm0,[16+esp]
-	jnz	NEAR L$004loop_shaext
-	pshufd	xmm0,xmm0,27
-	pshufd	xmm1,xmm1,27
-	movdqu	[edi],xmm0
-	movd	DWORD [16+edi],xmm1
-	mov	esp,ebx
-	pop	edi
-	pop	esi
-	pop	ebx
-	pop	ebp
-	ret
-align	16
-__sha1_block_data_order_ssse3:
-	push	ebp
-	push	ebx
-	push	esi
-	push	edi
-	call	L$005pic_point
-L$005pic_point:
-	pop	ebp
-	lea	ebp,[(L$K_XX_XX-L$005pic_point)+ebp]
 L$ssse3_shortcut:
 	movdqa	xmm7,[ebp]
 	movdqa	xmm0,[16+ebp]
@@ -1634,9 +1469,9 @@ db	102,15,56,0,222
 	xor	ebp,edx
 	pshufd	xmm4,xmm0,238
 	and	esi,ebp
-	jmp	NEAR L$006loop
+	jmp	NEAR L$004loop
 align	16
-L$006loop:
+L$004loop:
 	ror	ebx,2
 	xor	esi,edx
 	mov	ebp,eax
@@ -2539,7 +2374,7 @@ L$006loop:
 	add	ecx,edx
 	mov	ebp,DWORD [196+esp]
 	cmp	ebp,DWORD [200+esp]
-	je	NEAR L$007done
+	je	NEAR L$005done
 	movdqa	xmm7,[160+esp]
 	movdqa	xmm6,[176+esp]
 	movdqu	xmm0,[ebp]
@@ -2674,9 +2509,9 @@ db	102,15,56,0,222
 	pshufd	xmm4,xmm0,238
 	and	esi,ebx
 	mov	ebx,ebp
-	jmp	NEAR L$006loop
+	jmp	NEAR L$004loop
 align	16
-L$007done:
+L$005done:
 	add	ebx,DWORD [16+esp]
 	xor	esi,edi
 	mov	ebp,ecx
@@ -2789,6 +2624,1174 @@ L$007done:
 	pop	ebx
 	pop	ebp
 	ret
+align	16
+__sha1_block_data_order_avx:
+	push	ebp
+	push	ebx
+	push	esi
+	push	edi
+	call	L$006pic_point
+L$006pic_point:
+	pop	ebp
+	lea	ebp,[(L$K_XX_XX-L$006pic_point)+ebp]
+L$avx_shortcut:
+	vzeroall
+	vmovdqa	xmm7,[ebp]
+	vmovdqa	xmm0,[16+ebp]
+	vmovdqa	xmm1,[32+ebp]
+	vmovdqa	xmm2,[48+ebp]
+	vmovdqa	xmm6,[64+ebp]
+	mov	edi,DWORD [20+esp]
+	mov	ebp,DWORD [24+esp]
+	mov	edx,DWORD [28+esp]
+	mov	esi,esp
+	sub	esp,208
+	and	esp,-64
+	vmovdqa	[112+esp],xmm0
+	vmovdqa	[128+esp],xmm1
+	vmovdqa	[144+esp],xmm2
+	shl	edx,6
+	vmovdqa	[160+esp],xmm7
+	add	edx,ebp
+	vmovdqa	[176+esp],xmm6
+	add	ebp,64
+	mov	DWORD [192+esp],edi
+	mov	DWORD [196+esp],ebp
+	mov	DWORD [200+esp],edx
+	mov	DWORD [204+esp],esi
+	mov	eax,DWORD [edi]
+	mov	ebx,DWORD [4+edi]
+	mov	ecx,DWORD [8+edi]
+	mov	edx,DWORD [12+edi]
+	mov	edi,DWORD [16+edi]
+	mov	esi,ebx
+	vmovdqu	xmm0,[ebp-64]
+	vmovdqu	xmm1,[ebp-48]
+	vmovdqu	xmm2,[ebp-32]
+	vmovdqu	xmm3,[ebp-16]
+	vpshufb	xmm0,xmm0,xmm6
+	vpshufb	xmm1,xmm1,xmm6
+	vpshufb	xmm2,xmm2,xmm6
+	vmovdqa	[96+esp],xmm7
+	vpshufb	xmm3,xmm3,xmm6
+	vpaddd	xmm4,xmm0,xmm7
+	vpaddd	xmm5,xmm1,xmm7
+	vpaddd	xmm6,xmm2,xmm7
+	vmovdqa	[esp],xmm4
+	mov	ebp,ecx
+	vmovdqa	[16+esp],xmm5
+	xor	ebp,edx
+	vmovdqa	[32+esp],xmm6
+	and	esi,ebp
+	jmp	NEAR L$007loop
+align	16
+L$007loop:
+	shrd	ebx,ebx,2
+	xor	esi,edx
+	vpalignr	xmm4,xmm1,xmm0,8
+	mov	ebp,eax
+	add	edi,DWORD [esp]
+	vpaddd	xmm7,xmm7,xmm3
+	vmovdqa	[64+esp],xmm0
+	xor	ebx,ecx
+	shld	eax,eax,5
+	vpsrldq	xmm6,xmm3,4
+	add	edi,esi
+	and	ebp,ebx
+	vpxor	xmm4,xmm4,xmm0
+	xor	ebx,ecx
+	add	edi,eax
+	vpxor	xmm6,xmm6,xmm2
+	shrd	eax,eax,7
+	xor	ebp,ecx
+	vmovdqa	[48+esp],xmm7
+	mov	esi,edi
+	add	edx,DWORD [4+esp]
+	vpxor	xmm4,xmm4,xmm6
+	xor	eax,ebx
+	shld	edi,edi,5
+	add	edx,ebp
+	and	esi,eax
+	vpsrld	xmm6,xmm4,31
+	xor	eax,ebx
+	add	edx,edi
+	shrd	edi,edi,7
+	xor	esi,ebx
+	vpslldq	xmm0,xmm4,12
+	vpaddd	xmm4,xmm4,xmm4
+	mov	ebp,edx
+	add	ecx,DWORD [8+esp]
+	xor	edi,eax
+	shld	edx,edx,5
+	vpsrld	xmm7,xmm0,30
+	vpor	xmm4,xmm4,xmm6
+	add	ecx,esi
+	and	ebp,edi
+	xor	edi,eax
+	add	ecx,edx
+	vpslld	xmm0,xmm0,2
+	shrd	edx,edx,7
+	xor	ebp,eax
+	vpxor	xmm4,xmm4,xmm7
+	mov	esi,ecx
+	add	ebx,DWORD [12+esp]
+	xor	edx,edi
+	shld	ecx,ecx,5
+	vpxor	xmm4,xmm4,xmm0
+	add	ebx,ebp
+	and	esi,edx
+	vmovdqa	xmm0,[96+esp]
+	xor	edx,edi
+	add	ebx,ecx
+	shrd	ecx,ecx,7
+	xor	esi,edi
+	vpalignr	xmm5,xmm2,xmm1,8
+	mov	ebp,ebx
+	add	eax,DWORD [16+esp]
+	vpaddd	xmm0,xmm0,xmm4
+	vmovdqa	[80+esp],xmm1
+	xor	ecx,edx
+	shld	ebx,ebx,5
+	vpsrldq	xmm7,xmm4,4
+	add	eax,esi
+	and	ebp,ecx
+	vpxor	xmm5,xmm5,xmm1
+	xor	ecx,edx
+	add	eax,ebx
+	vpxor	xmm7,xmm7,xmm3
+	shrd	ebx,ebx,7
+	xor	ebp,edx
+	vmovdqa	[esp],xmm0
+	mov	esi,eax
+	add	edi,DWORD [20+esp]
+	vpxor	xmm5,xmm5,xmm7
+	xor	ebx,ecx
+	shld	eax,eax,5
+	add	edi,ebp
+	and	esi,ebx
+	vpsrld	xmm7,xmm5,31
+	xor	ebx,ecx
+	add	edi,eax
+	shrd	eax,eax,7
+	xor	esi,ecx
+	vpslldq	xmm1,xmm5,12
+	vpaddd	xmm5,xmm5,xmm5
+	mov	ebp,edi
+	add	edx,DWORD [24+esp]
+	xor	eax,ebx
+	shld	edi,edi,5
+	vpsrld	xmm0,xmm1,30
+	vpor	xmm5,xmm5,xmm7
+	add	edx,esi
+	and	ebp,eax
+	xor	eax,ebx
+	add	edx,edi
+	vpslld	xmm1,xmm1,2
+	shrd	edi,edi,7
+	xor	ebp,ebx
+	vpxor	xmm5,xmm5,xmm0
+	mov	esi,edx
+	add	ecx,DWORD [28+esp]
+	xor	edi,eax
+	shld	edx,edx,5
+	vpxor	xmm5,xmm5,xmm1
+	add	ecx,ebp
+	and	esi,edi
+	vmovdqa	xmm1,[112+esp]
+	xor	edi,eax
+	add	ecx,edx
+	shrd	edx,edx,7
+	xor	esi,eax
+	vpalignr	xmm6,xmm3,xmm2,8
+	mov	ebp,ecx
+	add	ebx,DWORD [32+esp]
+	vpaddd	xmm1,xmm1,xmm5
+	vmovdqa	[96+esp],xmm2
+	xor	edx,edi
+	shld	ecx,ecx,5
+	vpsrldq	xmm0,xmm5,4
+	add	ebx,esi
+	and	ebp,edx
+	vpxor	xmm6,xmm6,xmm2
+	xor	edx,edi
+	add	ebx,ecx
+	vpxor	xmm0,xmm0,xmm4
+	shrd	ecx,ecx,7
+	xor	ebp,edi
+	vmovdqa	[16+esp],xmm1
+	mov	esi,ebx
+	add	eax,DWORD [36+esp]
+	vpxor	xmm6,xmm6,xmm0
+	xor	ecx,edx
+	shld	ebx,ebx,5
+	add	eax,ebp
+	and	esi,ecx
+	vpsrld	xmm0,xmm6,31
+	xor	ecx,edx
+	add	eax,ebx
+	shrd	ebx,ebx,7
+	xor	esi,edx
+	vpslldq	xmm2,xmm6,12
+	vpaddd	xmm6,xmm6,xmm6
+	mov	ebp,eax
+	add	edi,DWORD [40+esp]
+	xor	ebx,ecx
+	shld	eax,eax,5
+	vpsrld	xmm1,xmm2,30
+	vpor	xmm6,xmm6,xmm0
+	add	edi,esi
+	and	ebp,ebx
+	xor	ebx,ecx
+	add	edi,eax
+	vpslld	xmm2,xmm2,2
+	vmovdqa	xmm0,[64+esp]
+	shrd	eax,eax,7
+	xor	ebp,ecx
+	vpxor	xmm6,xmm6,xmm1
+	mov	esi,edi
+	add	edx,DWORD [44+esp]
+	xor	eax,ebx
+	shld	edi,edi,5
+	vpxor	xmm6,xmm6,xmm2
+	add	edx,ebp
+	and	esi,eax
+	vmovdqa	xmm2,[112+esp]
+	xor	eax,ebx
+	add	edx,edi
+	shrd	edi,edi,7
+	xor	esi,ebx
+	vpalignr	xmm7,xmm4,xmm3,8
+	mov	ebp,edx
+	add	ecx,DWORD [48+esp]
+	vpaddd	xmm2,xmm2,xmm6
+	vmovdqa	[64+esp],xmm3
+	xor	edi,eax
+	shld	edx,edx,5
+	vpsrldq	xmm1,xmm6,4
+	add	ecx,esi
+	and	ebp,edi
+	vpxor	xmm7,xmm7,xmm3
+	xor	edi,eax
+	add	ecx,edx
+	vpxor	xmm1,xmm1,xmm5
+	shrd	edx,edx,7
+	xor	ebp,eax
+	vmovdqa	[32+esp],xmm2
+	mov	esi,ecx
+	add	ebx,DWORD [52+esp]
+	vpxor	xmm7,xmm7,xmm1
+	xor	edx,edi
+	shld	ecx,ecx,5
+	add	ebx,ebp
+	and	esi,edx
+	vpsrld	xmm1,xmm7,31
+	xor	edx,edi
+	add	ebx,ecx
+	shrd	ecx,ecx,7
+	xor	esi,edi
+	vpslldq	xmm3,xmm7,12
+	vpaddd	xmm7,xmm7,xmm7
+	mov	ebp,ebx
+	add	eax,DWORD [56+esp]
+	xor	ecx,edx
+	shld	ebx,ebx,5
+	vpsrld	xmm2,xmm3,30
+	vpor	xmm7,xmm7,xmm1
+	add	eax,esi
+	and	ebp,ecx
+	xor	ecx,edx
+	add	eax,ebx
+	vpslld	xmm3,xmm3,2
+	vmovdqa	xmm1,[80+esp]
+	shrd	ebx,ebx,7
+	xor	ebp,edx
+	vpxor	xmm7,xmm7,xmm2
+	mov	esi,eax
+	add	edi,DWORD [60+esp]
+	xor	ebx,ecx
+	shld	eax,eax,5
+	vpxor	xmm7,xmm7,xmm3
+	add	edi,ebp
+	and	esi,ebx
+	vmovdqa	xmm3,[112+esp]
+	xor	ebx,ecx
+	add	edi,eax
+	vpalignr	xmm2,xmm7,xmm6,8
+	vpxor	xmm0,xmm0,xmm4
+	shrd	eax,eax,7
+	xor	esi,ecx
+	mov	ebp,edi
+	add	edx,DWORD [esp]
+	vpxor	xmm0,xmm0,xmm1
+	vmovdqa	[80+esp],xmm4
+	xor	eax,ebx
+	shld	edi,edi,5
+	vmovdqa	xmm4,xmm3
+	vpaddd	xmm3,xmm3,xmm7
+	add	edx,esi
+	and	ebp,eax
+	vpxor	xmm0,xmm0,xmm2
+	xor	eax,ebx
+	add	edx,edi
+	shrd	edi,edi,7
+	xor	ebp,ebx
+	vpsrld	xmm2,xmm0,30
+	vmovdqa	[48+esp],xmm3
+	mov	esi,edx
+	add	ecx,DWORD [4+esp]
+	xor	edi,eax
+	shld	edx,edx,5
+	vpslld	xmm0,xmm0,2
+	add	ecx,ebp
+	and	esi,edi
+	xor	edi,eax
+	add	ecx,edx
+	shrd	edx,edx,7
+	xor	esi,eax
+	mov	ebp,ecx
+	add	ebx,DWORD [8+esp]
+	vpor	xmm0,xmm0,xmm2
+	xor	edx,edi
+	shld	ecx,ecx,5
+	vmovdqa	xmm2,[96+esp]
+	add	ebx,esi
+	and	ebp,edx
+	xor	edx,edi
+	add	ebx,ecx
+	add	eax,DWORD [12+esp]
+	xor	ebp,edi
+	mov	esi,ebx
+	shld	ebx,ebx,5
+	add	eax,ebp
+	xor	esi,edx
+	shrd	ecx,ecx,7
+	add	eax,ebx
+	vpalignr	xmm3,xmm0,xmm7,8
+	vpxor	xmm1,xmm1,xmm5
+	add	edi,DWORD [16+esp]
+	xor	esi,ecx
+	mov	ebp,eax
+	shld	eax,eax,5
+	vpxor	xmm1,xmm1,xmm2
+	vmovdqa	[96+esp],xmm5
+	add	edi,esi
+	xor	ebp,ecx
+	vmovdqa	xmm5,xmm4
+	vpaddd	xmm4,xmm4,xmm0
+	shrd	ebx,ebx,7
+	add	edi,eax
+	vpxor	xmm1,xmm1,xmm3
+	add	edx,DWORD [20+esp]
+	xor	ebp,ebx
+	mov	esi,edi
+	shld	edi,edi,5
+	vpsrld	xmm3,xmm1,30
+	vmovdqa	[esp],xmm4
+	add	edx,ebp
+	xor	esi,ebx
+	shrd	eax,eax,7
+	add	edx,edi
+	vpslld	xmm1,xmm1,2
+	add	ecx,DWORD [24+esp]
+	xor	esi,eax
+	mov	ebp,edx
+	shld	edx,edx,5
+	add	ecx,esi
+	xor	ebp,eax
+	shrd	edi,edi,7
+	add	ecx,edx
+	vpor	xmm1,xmm1,xmm3
+	add	ebx,DWORD [28+esp]
+	xor	ebp,edi
+	vmovdqa	xmm3,[64+esp]
+	mov	esi,ecx
+	shld	ecx,ecx,5
+	add	ebx,ebp
+	xor	esi,edi
+	shrd	edx,edx,7
+	add	ebx,ecx
+	vpalignr	xmm4,xmm1,xmm0,8
+	vpxor	xmm2,xmm2,xmm6
+	add	eax,DWORD [32+esp]
+	xor	esi,edx
+	mov	ebp,ebx
+	shld	ebx,ebx,5
+	vpxor	xmm2,xmm2,xmm3
+	vmovdqa	[64+esp],xmm6
+	add	eax,esi
+	xor	ebp,edx
+	vmovdqa	xmm6,[128+esp]
+	vpaddd	xmm5,xmm5,xmm1
+	shrd	ecx,ecx,7
+	add	eax,ebx
+	vpxor	xmm2,xmm2,xmm4
+	add	edi,DWORD [36+esp]
+	xor	ebp,ecx
+	mov	esi,eax
+	shld	eax,eax,5
+	vpsrld	xmm4,xmm2,30
+	vmovdqa	[16+esp],xmm5
+	add	edi,ebp
+	xor	esi,ecx
+	shrd	ebx,ebx,7
+	add	edi,eax
+	vpslld	xmm2,xmm2,2
+	add	edx,DWORD [40+esp]
+	xor	esi,ebx
+	mov	ebp,edi
+	shld	edi,edi,5
+	add	edx,esi
+	xor	ebp,ebx
+	shrd	eax,eax,7
+	add	edx,edi
+	vpor	xmm2,xmm2,xmm4
+	add	ecx,DWORD [44+esp]
+	xor	ebp,eax
+	vmovdqa	xmm4,[80+esp]
+	mov	esi,edx
+	shld	edx,edx,5
+	add	ecx,ebp
+	xor	esi,eax
+	shrd	edi,edi,7
+	add	ecx,edx
+	vpalignr	xmm5,xmm2,xmm1,8
+	vpxor	xmm3,xmm3,xmm7
+	add	ebx,DWORD [48+esp]
+	xor	esi,edi
+	mov	ebp,ecx
+	shld	ecx,ecx,5
+	vpxor	xmm3,xmm3,xmm4
+	vmovdqa	[80+esp],xmm7
+	add	ebx,esi
+	xor	ebp,edi
+	vmovdqa	xmm7,xmm6
+	vpaddd	xmm6,xmm6,xmm2
+	shrd	edx,edx,7
+	add	ebx,ecx
+	vpxor	xmm3,xmm3,xmm5
+	add	eax,DWORD [52+esp]
+	xor	ebp,edx
+	mov	esi,ebx
+	shld	ebx,ebx,5
+	vpsrld	xmm5,xmm3,30
+	vmovdqa	[32+esp],xmm6
+	add	eax,ebp
+	xor	esi,edx
+	shrd	ecx,ecx,7
+	add	eax,ebx
+	vpslld	xmm3,xmm3,2
+	add	edi,DWORD [56+esp]
+	xor	esi,ecx
+	mov	ebp,eax
+	shld	eax,eax,5
+	add	edi,esi
+	xor	ebp,ecx
+	shrd	ebx,ebx,7
+	add	edi,eax
+	vpor	xmm3,xmm3,xmm5
+	add	edx,DWORD [60+esp]
+	xor	ebp,ebx
+	vmovdqa	xmm5,[96+esp]
+	mov	esi,edi
+	shld	edi,edi,5
+	add	edx,ebp
+	xor	esi,ebx
+	shrd	eax,eax,7
+	add	edx,edi
+	vpalignr	xmm6,xmm3,xmm2,8
+	vpxor	xmm4,xmm4,xmm0
+	add	ecx,DWORD [esp]
+	xor	esi,eax
+	mov	ebp,edx
+	shld	edx,edx,5
+	vpxor	xmm4,xmm4,xmm5
+	vmovdqa	[96+esp],xmm0
+	add	ecx,esi
+	xor	ebp,eax
+	vmovdqa	xmm0,xmm7
+	vpaddd	xmm7,xmm7,xmm3
+	shrd	edi,edi,7
+	add	ecx,edx
+	vpxor	xmm4,xmm4,xmm6
+	add	ebx,DWORD [4+esp]
+	xor	ebp,edi
+	mov	esi,ecx
+	shld	ecx,ecx,5
+	vpsrld	xmm6,xmm4,30
+	vmovdqa	[48+esp],xmm7
+	add	ebx,ebp
+	xor	esi,edi
+	shrd	edx,edx,7
+	add	ebx,ecx
+	vpslld	xmm4,xmm4,2
+	add	eax,DWORD [8+esp]
+	xor	esi,edx
+	mov	ebp,ebx
+	shld	ebx,ebx,5
+	add	eax,esi
+	xor	ebp,edx
+	shrd	ecx,ecx,7
+	add	eax,ebx
+	vpor	xmm4,xmm4,xmm6
+	add	edi,DWORD [12+esp]
+	xor	ebp,ecx
+	vmovdqa	xmm6,[64+esp]
+	mov	esi,eax
+	shld	eax,eax,5
+	add	edi,ebp
+	xor	esi,ecx
+	shrd	ebx,ebx,7
+	add	edi,eax
+	vpalignr	xmm7,xmm4,xmm3,8
+	vpxor	xmm5,xmm5,xmm1
+	add	edx,DWORD [16+esp]
+	xor	esi,ebx
+	mov	ebp,edi
+	shld	edi,edi,5
+	vpxor	xmm5,xmm5,xmm6
+	vmovdqa	[64+esp],xmm1
+	add	edx,esi
+	xor	ebp,ebx
+	vmovdqa	xmm1,xmm0
+	vpaddd	xmm0,xmm0,xmm4
+	shrd	eax,eax,7
+	add	edx,edi
+	vpxor	xmm5,xmm5,xmm7
+	add	ecx,DWORD [20+esp]
+	xor	ebp,eax
+	mov	esi,edx
+	shld	edx,edx,5
+	vpsrld	xmm7,xmm5,30
+	vmovdqa	[esp],xmm0
+	add	ecx,ebp
+	xor	esi,eax
+	shrd	edi,edi,7
+	add	ecx,edx
+	vpslld	xmm5,xmm5,2
+	add	ebx,DWORD [24+esp]
+	xor	esi,edi
+	mov	ebp,ecx
+	shld	ecx,ecx,5
+	add	ebx,esi
+	xor	ebp,edi
+	shrd	edx,edx,7
+	add	ebx,ecx
+	vpor	xmm5,xmm5,xmm7
+	add	eax,DWORD [28+esp]
+	vmovdqa	xmm7,[80+esp]
+	shrd	ecx,ecx,7
+	mov	esi,ebx
+	xor	ebp,edx
+	shld	ebx,ebx,5
+	add	eax,ebp
+	xor	esi,ecx
+	xor	ecx,edx
+	add	eax,ebx
+	vpalignr	xmm0,xmm5,xmm4,8
+	vpxor	xmm6,xmm6,xmm2
+	add	edi,DWORD [32+esp]
+	and	esi,ecx
+	xor	ecx,edx
+	shrd	ebx,ebx,7
+	vpxor	xmm6,xmm6,xmm7
+	vmovdqa	[80+esp],xmm2
+	mov	ebp,eax
+	xor	esi,ecx
+	vmovdqa	xmm2,xmm1
+	vpaddd	xmm1,xmm1,xmm5
+	shld	eax,eax,5
+	add	edi,esi
+	vpxor	xmm6,xmm6,xmm0
+	xor	ebp,ebx
+	xor	ebx,ecx
+	add	edi,eax
+	add	edx,DWORD [36+esp]
+	vpsrld	xmm0,xmm6,30
+	vmovdqa	[16+esp],xmm1
+	and	ebp,ebx
+	xor	ebx,ecx
+	shrd	eax,eax,7
+	mov	esi,edi
+	vpslld	xmm6,xmm6,2
+	xor	ebp,ebx
+	shld	edi,edi,5
+	add	edx,ebp
+	xor	esi,eax
+	xor	eax,ebx
+	add	edx,edi
+	add	ecx,DWORD [40+esp]
+	and	esi,eax
+	vpor	xmm6,xmm6,xmm0
+	xor	eax,ebx
+	shrd	edi,edi,7
+	vmovdqa	xmm0,[96+esp]
+	mov	ebp,edx
+	xor	esi,eax
+	shld	edx,edx,5
+	add	ecx,esi
+	xor	ebp,edi
+	xor	edi,eax
+	add	ecx,edx
+	add	ebx,DWORD [44+esp]
+	and	ebp,edi
+	xor	edi,eax
+	shrd	edx,edx,7
+	mov	esi,ecx
+	xor	ebp,edi
+	shld	ecx,ecx,5
+	add	ebx,ebp
+	xor	esi,edx
+	xor	edx,edi
+	add	ebx,ecx
+	vpalignr	xmm1,xmm6,xmm5,8
+	vpxor	xmm7,xmm7,xmm3
+	add	eax,DWORD [48+esp]
+	and	esi,edx
+	xor	edx,edi
+	shrd	ecx,ecx,7
+	vpxor	xmm7,xmm7,xmm0
+	vmovdqa	[96+esp],xmm3
+	mov	ebp,ebx
+	xor	esi,edx
+	vmovdqa	xmm3,[144+esp]
+	vpaddd	xmm2,xmm2,xmm6
+	shld	ebx,ebx,5
+	add	eax,esi
+	vpxor	xmm7,xmm7,xmm1
+	xor	ebp,ecx
+	xor	ecx,edx
+	add	eax,ebx
+	add	edi,DWORD [52+esp]
+	vpsrld	xmm1,xmm7,30
+	vmovdqa	[32+esp],xmm2
+	and	ebp,ecx
+	xor	ecx,edx
+	shrd	ebx,ebx,7
+	mov	esi,eax
+	vpslld	xmm7,xmm7,2
+	xor	ebp,ecx
+	shld	eax,eax,5
+	add	edi,ebp
+	xor	esi,ebx
+	xor	ebx,ecx
+	add	edi,eax
+	add	edx,DWORD [56+esp]
+	and	esi,ebx
+	vpor	xmm7,xmm7,xmm1
+	xor	ebx,ecx
+	shrd	eax,eax,7
+	vmovdqa	xmm1,[64+esp]
+	mov	ebp,edi
+	xor	esi,ebx
+	shld	edi,edi,5
+	add	edx,esi
+	xor	ebp,eax
+	xor	eax,ebx
+	add	edx,edi
+	add	ecx,DWORD [60+esp]
+	and	ebp,eax
+	xor	eax,ebx
+	shrd	edi,edi,7
+	mov	esi,edx
+	xor	ebp,eax
+	shld	edx,edx,5
+	add	ecx,ebp
+	xor	esi,edi
+	xor	edi,eax
+	add	ecx,edx
+	vpalignr	xmm2,xmm7,xmm6,8
+	vpxor	xmm0,xmm0,xmm4
+	add	ebx,DWORD [esp]
+	and	esi,edi
+	xor	edi,eax
+	shrd	edx,edx,7
+	vpxor	xmm0,xmm0,xmm1
+	vmovdqa	[64+esp],xmm4
+	mov	ebp,ecx
+	xor	esi,edi
+	vmovdqa	xmm4,xmm3
+	vpaddd	xmm3,xmm3,xmm7
+	shld	ecx,ecx,5
+	add	ebx,esi
+	vpxor	xmm0,xmm0,xmm2
+	xor	ebp,edx
+	xor	edx,edi
+	add	ebx,ecx
+	add	eax,DWORD [4+esp]
+	vpsrld	xmm2,xmm0,30
+	vmovdqa	[48+esp],xmm3
+	and	ebp,edx
+	xor	edx,edi
+	shrd	ecx,ecx,7
+	mov	esi,ebx
+	vpslld	xmm0,xmm0,2
+	xor	ebp,edx
+	shld	ebx,ebx,5
+	add	eax,ebp
+	xor	esi,ecx
+	xor	ecx,edx
+	add	eax,ebx
+	add	edi,DWORD [8+esp]
+	and	esi,ecx
+	vpor	xmm0,xmm0,xmm2
+	xor	ecx,edx
+	shrd	ebx,ebx,7
+	vmovdqa	xmm2,[80+esp]
+	mov	ebp,eax
+	xor	esi,ecx
+	shld	eax,eax,5
+	add	edi,esi
+	xor	ebp,ebx
+	xor	ebx,ecx
+	add	edi,eax
+	add	edx,DWORD [12+esp]
+	and	ebp,ebx
+	xor	ebx,ecx
+	shrd	eax,eax,7
+	mov	esi,edi
+	xor	ebp,ebx
+	shld	edi,edi,5
+	add	edx,ebp
+	xor	esi,eax
+	xor	eax,ebx
+	add	edx,edi
+	vpalignr	xmm3,xmm0,xmm7,8
+	vpxor	xmm1,xmm1,xmm5
+	add	ecx,DWORD [16+esp]
+	and	esi,eax
+	xor	eax,ebx
+	shrd	edi,edi,7
+	vpxor	xmm1,xmm1,xmm2
+	vmovdqa	[80+esp],xmm5
+	mov	ebp,edx
+	xor	esi,eax
+	vmovdqa	xmm5,xmm4
+	vpaddd	xmm4,xmm4,xmm0
+	shld	edx,edx,5
+	add	ecx,esi
+	vpxor	xmm1,xmm1,xmm3
+	xor	ebp,edi
+	xor	edi,eax
+	add	ecx,edx
+	add	ebx,DWORD [20+esp]
+	vpsrld	xmm3,xmm1,30
+	vmovdqa	[esp],xmm4
+	and	ebp,edi
+	xor	edi,eax
+	shrd	edx,edx,7
+	mov	esi,ecx
+	vpslld	xmm1,xmm1,2
+	xor	ebp,edi
+	shld	ecx,ecx,5
+	add	ebx,ebp
+	xor	esi,edx
+	xor	edx,edi
+	add	ebx,ecx
+	add	eax,DWORD [24+esp]
+	and	esi,edx
+	vpor	xmm1,xmm1,xmm3
+	xor	edx,edi
+	shrd	ecx,ecx,7
+	vmovdqa	xmm3,[96+esp]
+	mov	ebp,ebx
+	xor	esi,edx
+	shld	ebx,ebx,5
+	add	eax,esi
+	xor	ebp,ecx
+	xor	ecx,edx
+	add	eax,ebx
+	add	edi,DWORD [28+esp]
+	and	ebp,ecx
+	xor	ecx,edx
+	shrd	ebx,ebx,7
+	mov	esi,eax
+	xor	ebp,ecx
+	shld	eax,eax,5
+	add	edi,ebp
+	xor	esi,ebx
+	xor	ebx,ecx
+	add	edi,eax
+	vpalignr	xmm4,xmm1,xmm0,8
+	vpxor	xmm2,xmm2,xmm6
+	add	edx,DWORD [32+esp]
+	and	esi,ebx
+	xor	ebx,ecx
+	shrd	eax,eax,7
+	vpxor	xmm2,xmm2,xmm3
+	vmovdqa	[96+esp],xmm6
+	mov	ebp,edi
+	xor	esi,ebx
+	vmovdqa	xmm6,xmm5
+	vpaddd	xmm5,xmm5,xmm1
+	shld	edi,edi,5
+	add	edx,esi
+	vpxor	xmm2,xmm2,xmm4
+	xor	ebp,eax
+	xor	eax,ebx
+	add	edx,edi
+	add	ecx,DWORD [36+esp]
+	vpsrld	xmm4,xmm2,30
+	vmovdqa	[16+esp],xmm5
+	and	ebp,eax
+	xor	eax,ebx
+	shrd	edi,edi,7
+	mov	esi,edx
+	vpslld	xmm2,xmm2,2
+	xor	ebp,eax
+	shld	edx,edx,5
+	add	ecx,ebp
+	xor	esi,edi
+	xor	edi,eax
+	add	ecx,edx
+	add	ebx,DWORD [40+esp]
+	and	esi,edi
+	vpor	xmm2,xmm2,xmm4
+	xor	edi,eax
+	shrd	edx,edx,7
+	vmovdqa	xmm4,[64+esp]
+	mov	ebp,ecx
+	xor	esi,edi
+	shld	ecx,ecx,5
+	add	ebx,esi
+	xor	ebp,edx
+	xor	edx,edi
+	add	ebx,ecx
+	add	eax,DWORD [44+esp]
+	and	ebp,edx
+	xor	edx,edi
+	shrd	ecx,ecx,7
+	mov	esi,ebx
+	xor	ebp,edx
+	shld	ebx,ebx,5
+	add	eax,ebp
+	xor	esi,edx
+	add	eax,ebx
+	vpalignr	xmm5,xmm2,xmm1,8
+	vpxor	xmm3,xmm3,xmm7
+	add	edi,DWORD [48+esp]
+	xor	esi,ecx
+	mov	ebp,eax
+	shld	eax,eax,5
+	vpxor	xmm3,xmm3,xmm4
+	vmovdqa	[64+esp],xmm7
+	add	edi,esi
+	xor	ebp,ecx
+	vmovdqa	xmm7,xmm6
+	vpaddd	xmm6,xmm6,xmm2
+	shrd	ebx,ebx,7
+	add	edi,eax
+	vpxor	xmm3,xmm3,xmm5
+	add	edx,DWORD [52+esp]
+	xor	ebp,ebx
+	mov	esi,edi
+	shld	edi,edi,5
+	vpsrld	xmm5,xmm3,30
+	vmovdqa	[32+esp],xmm6
+	add	edx,ebp
+	xor	esi,ebx
+	shrd	eax,eax,7
+	add	edx,edi
+	vpslld	xmm3,xmm3,2
+	add	ecx,DWORD [56+esp]
+	xor	esi,eax
+	mov	ebp,edx
+	shld	edx,edx,5
+	add	ecx,esi
+	xor	ebp,eax
+	shrd	edi,edi,7
+	add	ecx,edx
+	vpor	xmm3,xmm3,xmm5
+	add	ebx,DWORD [60+esp]
+	xor	ebp,edi
+	mov	esi,ecx
+	shld	ecx,ecx,5
+	add	ebx,ebp
+	xor	esi,edi
+	shrd	edx,edx,7
+	add	ebx,ecx
+	add	eax,DWORD [esp]
+	vpaddd	xmm7,xmm7,xmm3
+	xor	esi,edx
+	mov	ebp,ebx
+	shld	ebx,ebx,5
+	add	eax,esi
+	vmovdqa	[48+esp],xmm7
+	xor	ebp,edx
+	shrd	ecx,ecx,7
+	add	eax,ebx
+	add	edi,DWORD [4+esp]
+	xor	ebp,ecx
+	mov	esi,eax
+	shld	eax,eax,5
+	add	edi,ebp
+	xor	esi,ecx
+	shrd	ebx,ebx,7
+	add	edi,eax
+	add	edx,DWORD [8+esp]
+	xor	esi,ebx
+	mov	ebp,edi
+	shld	edi,edi,5
+	add	edx,esi
+	xor	ebp,ebx
+	shrd	eax,eax,7
+	add	edx,edi
+	add	ecx,DWORD [12+esp]
+	xor	ebp,eax
+	mov	esi,edx
+	shld	edx,edx,5
+	add	ecx,ebp
+	xor	esi,eax
+	shrd	edi,edi,7
+	add	ecx,edx
+	mov	ebp,DWORD [196+esp]
+	cmp	ebp,DWORD [200+esp]
+	je	NEAR L$008done
+	vmovdqa	xmm7,[160+esp]
+	vmovdqa	xmm6,[176+esp]
+	vmovdqu	xmm0,[ebp]
+	vmovdqu	xmm1,[16+ebp]
+	vmovdqu	xmm2,[32+ebp]
+	vmovdqu	xmm3,[48+ebp]
+	add	ebp,64
+	vpshufb	xmm0,xmm0,xmm6
+	mov	DWORD [196+esp],ebp
+	vmovdqa	[96+esp],xmm7
+	add	ebx,DWORD [16+esp]
+	xor	esi,edi
+	vpshufb	xmm1,xmm1,xmm6
+	mov	ebp,ecx
+	shld	ecx,ecx,5
+	vpaddd	xmm4,xmm0,xmm7
+	add	ebx,esi
+	xor	ebp,edi
+	shrd	edx,edx,7
+	add	ebx,ecx
+	vmovdqa	[esp],xmm4
+	add	eax,DWORD [20+esp]
+	xor	ebp,edx
+	mov	esi,ebx
+	shld	ebx,ebx,5
+	add	eax,ebp
+	xor	esi,edx
+	shrd	ecx,ecx,7
+	add	eax,ebx
+	add	edi,DWORD [24+esp]
+	xor	esi,ecx
+	mov	ebp,eax
+	shld	eax,eax,5
+	add	edi,esi
+	xor	ebp,ecx
+	shrd	ebx,ebx,7
+	add	edi,eax
+	add	edx,DWORD [28+esp]
+	xor	ebp,ebx
+	mov	esi,edi
+	shld	edi,edi,5
+	add	edx,ebp
+	xor	esi,ebx
+	shrd	eax,eax,7
+	add	edx,edi
+	add	ecx,DWORD [32+esp]
+	xor	esi,eax
+	vpshufb	xmm2,xmm2,xmm6
+	mov	ebp,edx
+	shld	edx,edx,5
+	vpaddd	xmm5,xmm1,xmm7
+	add	ecx,esi
+	xor	ebp,eax
+	shrd	edi,edi,7
+	add	ecx,edx
+	vmovdqa	[16+esp],xmm5
+	add	ebx,DWORD [36+esp]
+	xor	ebp,edi
+	mov	esi,ecx
+	shld	ecx,ecx,5
+	add	ebx,ebp
+	xor	esi,edi
+	shrd	edx,edx,7
+	add	ebx,ecx
+	add	eax,DWORD [40+esp]
+	xor	esi,edx
+	mov	ebp,ebx
+	shld	ebx,ebx,5
+	add	eax,esi
+	xor	ebp,edx
+	shrd	ecx,ecx,7
+	add	eax,ebx
+	add	edi,DWORD [44+esp]
+	xor	ebp,ecx
+	mov	esi,eax
+	shld	eax,eax,5
+	add	edi,ebp
+	xor	esi,ecx
+	shrd	ebx,ebx,7
+	add	edi,eax
+	add	edx,DWORD [48+esp]
+	xor	esi,ebx
+	vpshufb	xmm3,xmm3,xmm6
+	mov	ebp,edi
+	shld	edi,edi,5
+	vpaddd	xmm6,xmm2,xmm7
+	add	edx,esi
+	xor	ebp,ebx
+	shrd	eax,eax,7
+	add	edx,edi
+	vmovdqa	[32+esp],xmm6
+	add	ecx,DWORD [52+esp]
+	xor	ebp,eax
+	mov	esi,edx
+	shld	edx,edx,5
+	add	ecx,ebp
+	xor	esi,eax
+	shrd	edi,edi,7
+	add	ecx,edx
+	add	ebx,DWORD [56+esp]
+	xor	esi,edi
+	mov	ebp,ecx
+	shld	ecx,ecx,5
+	add	ebx,esi
+	xor	ebp,edi
+	shrd	edx,edx,7
+	add	ebx,ecx
+	add	eax,DWORD [60+esp]
+	xor	ebp,edx
+	mov	esi,ebx
+	shld	ebx,ebx,5
+	add	eax,ebp
+	shrd	ecx,ecx,7
+	add	eax,ebx
+	mov	ebp,DWORD [192+esp]
+	add	eax,DWORD [ebp]
+	add	esi,DWORD [4+ebp]
+	add	ecx,DWORD [8+ebp]
+	mov	DWORD [ebp],eax
+	add	edx,DWORD [12+ebp]
+	mov	DWORD [4+ebp],esi
+	add	edi,DWORD [16+ebp]
+	mov	ebx,ecx
+	mov	DWORD [8+ebp],ecx
+	xor	ebx,edx
+	mov	DWORD [12+ebp],edx
+	mov	DWORD [16+ebp],edi
+	mov	ebp,esi
+	and	esi,ebx
+	mov	ebx,ebp
+	jmp	NEAR L$007loop
+align	16
+L$008done:
+	add	ebx,DWORD [16+esp]
+	xor	esi,edi
+	mov	ebp,ecx
+	shld	ecx,ecx,5
+	add	ebx,esi
+	xor	ebp,edi
+	shrd	edx,edx,7
+	add	ebx,ecx
+	add	eax,DWORD [20+esp]
+	xor	ebp,edx
+	mov	esi,ebx
+	shld	ebx,ebx,5
+	add	eax,ebp
+	xor	esi,edx
+	shrd	ecx,ecx,7
+	add	eax,ebx
+	add	edi,DWORD [24+esp]
+	xor	esi,ecx
+	mov	ebp,eax
+	shld	eax,eax,5
+	add	edi,esi
+	xor	ebp,ecx
+	shrd	ebx,ebx,7
+	add	edi,eax
+	add	edx,DWORD [28+esp]
+	xor	ebp,ebx
+	mov	esi,edi
+	shld	edi,edi,5
+	add	edx,ebp
+	xor	esi,ebx
+	shrd	eax,eax,7
+	add	edx,edi
+	add	ecx,DWORD [32+esp]
+	xor	esi,eax
+	mov	ebp,edx
+	shld	edx,edx,5
+	add	ecx,esi
+	xor	ebp,eax
+	shrd	edi,edi,7
+	add	ecx,edx
+	add	ebx,DWORD [36+esp]
+	xor	ebp,edi
+	mov	esi,ecx
+	shld	ecx,ecx,5
+	add	ebx,ebp
+	xor	esi,edi
+	shrd	edx,edx,7
+	add	ebx,ecx
+	add	eax,DWORD [40+esp]
+	xor	esi,edx
+	mov	ebp,ebx
+	shld	ebx,ebx,5
+	add	eax,esi
+	xor	ebp,edx
+	shrd	ecx,ecx,7
+	add	eax,ebx
+	add	edi,DWORD [44+esp]
+	xor	ebp,ecx
+	mov	esi,eax
+	shld	eax,eax,5
+	add	edi,ebp
+	xor	esi,ecx
+	shrd	ebx,ebx,7
+	add	edi,eax
+	add	edx,DWORD [48+esp]
+	xor	esi,ebx
+	mov	ebp,edi
+	shld	edi,edi,5
+	add	edx,esi
+	xor	ebp,ebx
+	shrd	eax,eax,7
+	add	edx,edi
+	add	ecx,DWORD [52+esp]
+	xor	ebp,eax
+	mov	esi,edx
+	shld	edx,edx,5
+	add	ecx,ebp
+	xor	esi,eax
+	shrd	edi,edi,7
+	add	ecx,edx
+	add	ebx,DWORD [56+esp]
+	xor	esi,edi
+	mov	ebp,ecx
+	shld	ecx,ecx,5
+	add	ebx,esi
+	xor	ebp,edi
+	shrd	edx,edx,7
+	add	ebx,ecx
+	add	eax,DWORD [60+esp]
+	xor	ebp,edx
+	mov	esi,ebx
+	shld	ebx,ebx,5
+	add	eax,ebp
+	shrd	ecx,ecx,7
+	add	eax,ebx
+	vzeroall
+	mov	ebp,DWORD [192+esp]
+	add	eax,DWORD [ebp]
+	mov	esp,DWORD [204+esp]
+	add	esi,DWORD [4+ebp]
+	add	ecx,DWORD [8+ebp]
+	mov	DWORD [ebp],eax
+	add	edx,DWORD [12+ebp]
+	mov	DWORD [4+ebp],esi
+	add	edi,DWORD [16+ebp]
+	mov	DWORD [8+ebp],ecx
+	mov	DWORD [12+ebp],edx
+	mov	DWORD [16+ebp],edi
+	pop	edi
+	pop	esi
+	pop	ebx
+	pop	ebp
+	ret
 align	64
 L$K_XX_XX:
 dd	1518500249,1518500249,1518500249,1518500249
diff --git a/packager/third_party/boringssl/win-x86/crypto/sha/sha256-586.asm b/packager/third_party/boringssl/win-x86/crypto/sha/sha256-586.asm
index fe36bc5c9a..3e7cfcca07 100644
--- a/packager/third_party/boringssl/win-x86/crypto/sha/sha256-586.asm
+++ b/packager/third_party/boringssl/win-x86/crypto/sha/sha256-586.asm
@@ -49,11 +49,10 @@ L$000pic_point:
 	jz	NEAR L$003no_xmm
 	and	ecx,1073741824
 	and	ebx,268435968
-	test	edx,536870912
-	jnz	NEAR L$004shaext
 	or	ecx,ebx
 	and	ecx,1342177280
 	cmp	ecx,1342177280
+	je	NEAR L$004AVX
 	test	ebx,512
 	jnz	NEAR L$005SSSE3
 L$003no_xmm:
@@ -3179,204 +3178,6 @@ L$009grand_loop:
 	pop	ebp
 	ret
 align	32
-L$004shaext:
-	sub	esp,32
-	movdqu	xmm1,[esi]
-	lea	ebp,[128+ebp]
-	movdqu	xmm2,[16+esi]
-	movdqa	xmm7,[128+ebp]
-	pshufd	xmm0,xmm1,27
-	pshufd	xmm1,xmm1,177
-	pshufd	xmm2,xmm2,27
-db	102,15,58,15,202,8
-	punpcklqdq	xmm2,xmm0
-	jmp	NEAR L$010loop_shaext
-align	16
-L$010loop_shaext:
-	movdqu	xmm3,[edi]
-	movdqu	xmm4,[16+edi]
-	movdqu	xmm5,[32+edi]
-db	102,15,56,0,223
-	movdqu	xmm6,[48+edi]
-	movdqa	[16+esp],xmm2
-	movdqa	xmm0,[ebp-128]
-	paddd	xmm0,xmm3
-db	102,15,56,0,231
-db	15,56,203,209
-	pshufd	xmm0,xmm0,14
-	nop
-	movdqa	[esp],xmm1
-db	15,56,203,202
-	movdqa	xmm0,[ebp-112]
-	paddd	xmm0,xmm4
-db	102,15,56,0,239
-db	15,56,203,209
-	pshufd	xmm0,xmm0,14
-	lea	edi,[64+edi]
-db	15,56,204,220
-db	15,56,203,202
-	movdqa	xmm0,[ebp-96]
-	paddd	xmm0,xmm5
-db	102,15,56,0,247
-db	15,56,203,209
-	pshufd	xmm0,xmm0,14
-	movdqa	xmm7,xmm6
-db	102,15,58,15,253,4
-	nop
-	paddd	xmm3,xmm7
-db	15,56,204,229
-db	15,56,203,202
-	movdqa	xmm0,[ebp-80]
-	paddd	xmm0,xmm6
-db	15,56,205,222
-db	15,56,203,209
-	pshufd	xmm0,xmm0,14
-	movdqa	xmm7,xmm3
-db	102,15,58,15,254,4
-	nop
-	paddd	xmm4,xmm7
-db	15,56,204,238
-db	15,56,203,202
-	movdqa	xmm0,[ebp-64]
-	paddd	xmm0,xmm3
-db	15,56,205,227
-db	15,56,203,209
-	pshufd	xmm0,xmm0,14
-	movdqa	xmm7,xmm4
-db	102,15,58,15,251,4
-	nop
-	paddd	xmm5,xmm7
-db	15,56,204,243
-db	15,56,203,202
-	movdqa	xmm0,[ebp-48]
-	paddd	xmm0,xmm4
-db	15,56,205,236
-db	15,56,203,209
-	pshufd	xmm0,xmm0,14
-	movdqa	xmm7,xmm5
-db	102,15,58,15,252,4
-	nop
-	paddd	xmm6,xmm7
-db	15,56,204,220
-db	15,56,203,202
-	movdqa	xmm0,[ebp-32]
-	paddd	xmm0,xmm5
-db	15,56,205,245
-db	15,56,203,209
-	pshufd	xmm0,xmm0,14
-	movdqa	xmm7,xmm6
-db	102,15,58,15,253,4
-	nop
-	paddd	xmm3,xmm7
-db	15,56,204,229
-db	15,56,203,202
-	movdqa	xmm0,[ebp-16]
-	paddd	xmm0,xmm6
-db	15,56,205,222
-db	15,56,203,209
-	pshufd	xmm0,xmm0,14
-	movdqa	xmm7,xmm3
-db	102,15,58,15,254,4
-	nop
-	paddd	xmm4,xmm7
-db	15,56,204,238
-db	15,56,203,202
-	movdqa	xmm0,[ebp]
-	paddd	xmm0,xmm3
-db	15,56,205,227
-db	15,56,203,209
-	pshufd	xmm0,xmm0,14
-	movdqa	xmm7,xmm4
-db	102,15,58,15,251,4
-	nop
-	paddd	xmm5,xmm7
-db	15,56,204,243
-db	15,56,203,202
-	movdqa	xmm0,[16+ebp]
-	paddd	xmm0,xmm4
-db	15,56,205,236
-db	15,56,203,209
-	pshufd	xmm0,xmm0,14
-	movdqa	xmm7,xmm5
-db	102,15,58,15,252,4
-	nop
-	paddd	xmm6,xmm7
-db	15,56,204,220
-db	15,56,203,202
-	movdqa	xmm0,[32+ebp]
-	paddd	xmm0,xmm5
-db	15,56,205,245
-db	15,56,203,209
-	pshufd	xmm0,xmm0,14
-	movdqa	xmm7,xmm6
-db	102,15,58,15,253,4
-	nop
-	paddd	xmm3,xmm7
-db	15,56,204,229
-db	15,56,203,202
-	movdqa	xmm0,[48+ebp]
-	paddd	xmm0,xmm6
-db	15,56,205,222
-db	15,56,203,209
-	pshufd	xmm0,xmm0,14
-	movdqa	xmm7,xmm3
-db	102,15,58,15,254,4
-	nop
-	paddd	xmm4,xmm7
-db	15,56,204,238
-db	15,56,203,202
-	movdqa	xmm0,[64+ebp]
-	paddd	xmm0,xmm3
-db	15,56,205,227
-db	15,56,203,209
-	pshufd	xmm0,xmm0,14
-	movdqa	xmm7,xmm4
-db	102,15,58,15,251,4
-	nop
-	paddd	xmm5,xmm7
-db	15,56,204,243
-db	15,56,203,202
-	movdqa	xmm0,[80+ebp]
-	paddd	xmm0,xmm4
-db	15,56,205,236
-db	15,56,203,209
-	pshufd	xmm0,xmm0,14
-	movdqa	xmm7,xmm5
-db	102,15,58,15,252,4
-db	15,56,203,202
-	paddd	xmm6,xmm7
-	movdqa	xmm0,[96+ebp]
-	paddd	xmm0,xmm5
-db	15,56,203,209
-	pshufd	xmm0,xmm0,14
-db	15,56,205,245
-	movdqa	xmm7,[128+ebp]
-db	15,56,203,202
-	movdqa	xmm0,[112+ebp]
-	paddd	xmm0,xmm6
-	nop
-db	15,56,203,209
-	pshufd	xmm0,xmm0,14
-	cmp	eax,edi
-	nop
-db	15,56,203,202
-	paddd	xmm2,[16+esp]
-	paddd	xmm1,[esp]
-	jnz	NEAR L$010loop_shaext
-	pshufd	xmm2,xmm2,177
-	pshufd	xmm7,xmm1,27
-	pshufd	xmm1,xmm1,177
-	punpckhqdq	xmm1,xmm2
-db	102,15,58,15,215,8
-	mov	esp,DWORD [44+esp]
-	movdqu	[esi],xmm1
-	movdqu	[16+esi],xmm2
-	pop	edi
-	pop	esi
-	pop	ebx
-	pop	ebp
-	ret
-align	32
 L$005SSSE3:
 	lea	esp,[esp-96]
 	mov	eax,DWORD [esi]
@@ -3396,9 +3197,9 @@ L$005SSSE3:
 	mov	DWORD [24+esp],ecx
 	mov	DWORD [28+esp],esi
 	movdqa	xmm7,[256+ebp]
-	jmp	NEAR L$011grand_ssse3
+	jmp	NEAR L$010grand_ssse3
 align	16
-L$011grand_ssse3:
+L$010grand_ssse3:
 	movdqu	xmm0,[edi]
 	movdqu	xmm1,[16+edi]
 	movdqu	xmm2,[32+edi]
@@ -3421,9 +3222,9 @@ db	102,15,56,0,223
 	paddd	xmm7,xmm3
 	movdqa	[64+esp],xmm6
 	movdqa	[80+esp],xmm7
-	jmp	NEAR L$012ssse3_00_47
+	jmp	NEAR L$011ssse3_00_47
 align	16
-L$012ssse3_00_47:
+L$011ssse3_00_47:
 	add	ebp,64
 	mov	ecx,edx
 	movdqa	xmm4,xmm1
@@ -4066,7 +3867,7 @@ db	102,15,58,15,249,4
 	add	eax,ecx
 	movdqa	[80+esp],xmm6
 	cmp	DWORD [64+ebp],66051
-	jne	NEAR L$012ssse3_00_47
+	jne	NEAR L$011ssse3_00_47
 	mov	ecx,edx
 	ror	edx,14
 	mov	esi,DWORD [20+esp]
@@ -4580,12 +4381,1193 @@ db	102,15,58,15,249,4
 	movdqa	xmm7,[64+ebp]
 	sub	ebp,192
 	cmp	edi,DWORD [104+esp]
-	jb	NEAR L$011grand_ssse3
+	jb	NEAR L$010grand_ssse3
 	mov	esp,DWORD [108+esp]
 	pop	edi
 	pop	esi
 	pop	ebx
 	pop	ebp
 	ret
+align	32
+L$004AVX:
+	lea	esp,[esp-96]
+	vzeroall
+	mov	eax,DWORD [esi]
+	mov	ebx,DWORD [4+esi]
+	mov	ecx,DWORD [8+esi]
+	mov	edi,DWORD [12+esi]
+	mov	DWORD [4+esp],ebx
+	xor	ebx,ecx
+	mov	DWORD [8+esp],ecx
+	mov	DWORD [12+esp],edi
+	mov	edx,DWORD [16+esi]
+	mov	edi,DWORD [20+esi]
+	mov	ecx,DWORD [24+esi]
+	mov	esi,DWORD [28+esi]
+	mov	DWORD [20+esp],edi
+	mov	edi,DWORD [100+esp]
+	mov	DWORD [24+esp],ecx
+	mov	DWORD [28+esp],esi
+	vmovdqa	xmm7,[256+ebp]
+	jmp	NEAR L$012grand_avx
+align	32
+L$012grand_avx:
+	vmovdqu	xmm0,[edi]
+	vmovdqu	xmm1,[16+edi]
+	vmovdqu	xmm2,[32+edi]
+	vmovdqu	xmm3,[48+edi]
+	add	edi,64
+	vpshufb	xmm0,xmm0,xmm7
+	mov	DWORD [100+esp],edi
+	vpshufb	xmm1,xmm1,xmm7
+	vpshufb	xmm2,xmm2,xmm7
+	vpaddd	xmm4,xmm0,[ebp]
+	vpshufb	xmm3,xmm3,xmm7
+	vpaddd	xmm5,xmm1,[16+ebp]
+	vpaddd	xmm6,xmm2,[32+ebp]
+	vpaddd	xmm7,xmm3,[48+ebp]
+	vmovdqa	[32+esp],xmm4
+	vmovdqa	[48+esp],xmm5
+	vmovdqa	[64+esp],xmm6
+	vmovdqa	[80+esp],xmm7
+	jmp	NEAR L$013avx_00_47
+align	16
+L$013avx_00_47:
+	add	ebp,64
+	vpalignr	xmm4,xmm1,xmm0,4
+	mov	ecx,edx
+	shrd	edx,edx,14
+	mov	esi,DWORD [20+esp]
+	vpalignr	xmm7,xmm3,xmm2,4
+	xor	edx,ecx
+	mov	edi,DWORD [24+esp]
+	xor	esi,edi
+	vpsrld	xmm6,xmm4,7
+	shrd	edx,edx,5
+	and	esi,ecx
+	mov	DWORD [16+esp],ecx
+	vpaddd	xmm0,xmm0,xmm7
+	xor	edx,ecx
+	xor	edi,esi
+	shrd	edx,edx,6
+	vpsrld	xmm7,xmm4,3
+	mov	ecx,eax
+	add	edx,edi
+	mov	edi,DWORD [4+esp]
+	vpslld	xmm5,xmm4,14
+	mov	esi,eax
+	shrd	ecx,ecx,9
+	mov	DWORD [esp],eax
+	vpxor	xmm4,xmm7,xmm6
+	xor	ecx,eax
+	xor	eax,edi
+	add	edx,DWORD [28+esp]
+	vpshufd	xmm7,xmm3,250
+	shrd	ecx,ecx,11
+	and	ebx,eax
+	xor	ecx,esi
+	vpsrld	xmm6,xmm6,11
+	add	edx,DWORD [32+esp]
+	xor	ebx,edi
+	shrd	ecx,ecx,2
+	vpxor	xmm4,xmm4,xmm5
+	add	ebx,edx
+	add	edx,DWORD [12+esp]
+	add	ebx,ecx
+	vpslld	xmm5,xmm5,11
+	mov	ecx,edx
+	shrd	edx,edx,14
+	mov	esi,DWORD [16+esp]
+	vpxor	xmm4,xmm4,xmm6
+	xor	edx,ecx
+	mov	edi,DWORD [20+esp]
+	xor	esi,edi
+	vpsrld	xmm6,xmm7,10
+	shrd	edx,edx,5
+	and	esi,ecx
+	mov	DWORD [12+esp],ecx
+	vpxor	xmm4,xmm4,xmm5
+	xor	edx,ecx
+	xor	edi,esi
+	shrd	edx,edx,6
+	vpsrlq	xmm5,xmm7,17
+	mov	ecx,ebx
+	add	edx,edi
+	mov	edi,DWORD [esp]
+	vpaddd	xmm0,xmm0,xmm4
+	mov	esi,ebx
+	shrd	ecx,ecx,9
+	mov	DWORD [28+esp],ebx
+	vpxor	xmm6,xmm6,xmm5
+	xor	ecx,ebx
+	xor	ebx,edi
+	add	edx,DWORD [24+esp]
+	vpsrlq	xmm7,xmm7,19
+	shrd	ecx,ecx,11
+	and	eax,ebx
+	xor	ecx,esi
+	vpxor	xmm6,xmm6,xmm7
+	add	edx,DWORD [36+esp]
+	xor	eax,edi
+	shrd	ecx,ecx,2
+	vpshufd	xmm7,xmm6,132
+	add	eax,edx
+	add	edx,DWORD [8+esp]
+	add	eax,ecx
+	vpsrldq	xmm7,xmm7,8
+	mov	ecx,edx
+	shrd	edx,edx,14
+	mov	esi,DWORD [12+esp]
+	vpaddd	xmm0,xmm0,xmm7
+	xor	edx,ecx
+	mov	edi,DWORD [16+esp]
+	xor	esi,edi
+	vpshufd	xmm7,xmm0,80
+	shrd	edx,edx,5
+	and	esi,ecx
+	mov	DWORD [8+esp],ecx
+	vpsrld	xmm6,xmm7,10
+	xor	edx,ecx
+	xor	edi,esi
+	shrd	edx,edx,6
+	vpsrlq	xmm5,xmm7,17
+	mov	ecx,eax
+	add	edx,edi
+	mov	edi,DWORD [28+esp]
+	vpxor	xmm6,xmm6,xmm5
+	mov	esi,eax
+	shrd	ecx,ecx,9
+	mov	DWORD [24+esp],eax
+	vpsrlq	xmm7,xmm7,19
+	xor	ecx,eax
+	xor	eax,edi
+	add	edx,DWORD [20+esp]
+	vpxor	xmm6,xmm6,xmm7
+	shrd	ecx,ecx,11
+	and	ebx,eax
+	xor	ecx,esi
+	vpshufd	xmm7,xmm6,232
+	add	edx,DWORD [40+esp]
+	xor	ebx,edi
+	shrd	ecx,ecx,2
+	vpslldq	xmm7,xmm7,8
+	add	ebx,edx
+	add	edx,DWORD [4+esp]
+	add	ebx,ecx
+	vpaddd	xmm0,xmm0,xmm7
+	mov	ecx,edx
+	shrd	edx,edx,14
+	mov	esi,DWORD [8+esp]
+	vpaddd	xmm6,xmm0,[ebp]
+	xor	edx,ecx
+	mov	edi,DWORD [12+esp]
+	xor	esi,edi
+	shrd	edx,edx,5
+	and	esi,ecx
+	mov	DWORD [4+esp],ecx
+	xor	edx,ecx
+	xor	edi,esi
+	shrd	edx,edx,6
+	mov	ecx,ebx
+	add	edx,edi
+	mov	edi,DWORD [24+esp]
+	mov	esi,ebx
+	shrd	ecx,ecx,9
+	mov	DWORD [20+esp],ebx
+	xor	ecx,ebx
+	xor	ebx,edi
+	add	edx,DWORD [16+esp]
+	shrd	ecx,ecx,11
+	and	eax,ebx
+	xor	ecx,esi
+	add	edx,DWORD [44+esp]
+	xor	eax,edi
+	shrd	ecx,ecx,2
+	add	eax,edx
+	add	edx,DWORD [esp]
+	add	eax,ecx
+	vmovdqa	[32+esp],xmm6
+	vpalignr	xmm4,xmm2,xmm1,4
+	mov	ecx,edx
+	shrd	edx,edx,14
+	mov	esi,DWORD [4+esp]
+	vpalignr	xmm7,xmm0,xmm3,4
+	xor	edx,ecx
+	mov	edi,DWORD [8+esp]
+	xor	esi,edi
+	vpsrld	xmm6,xmm4,7
+	shrd	edx,edx,5
+	and	esi,ecx
+	mov	DWORD [esp],ecx
+	vpaddd	xmm1,xmm1,xmm7
+	xor	edx,ecx
+	xor	edi,esi
+	shrd	edx,edx,6
+	vpsrld	xmm7,xmm4,3
+	mov	ecx,eax
+	add	edx,edi
+	mov	edi,DWORD [20+esp]
+	vpslld	xmm5,xmm4,14
+	mov	esi,eax
+	shrd	ecx,ecx,9
+	mov	DWORD [16+esp],eax
+	vpxor	xmm4,xmm7,xmm6
+	xor	ecx,eax
+	xor	eax,edi
+	add	edx,DWORD [12+esp]
+	vpshufd	xmm7,xmm0,250
+	shrd	ecx,ecx,11
+	and	ebx,eax
+	xor	ecx,esi
+	vpsrld	xmm6,xmm6,11
+	add	edx,DWORD [48+esp]
+	xor	ebx,edi
+	shrd	ecx,ecx,2
+	vpxor	xmm4,xmm4,xmm5
+	add	ebx,edx
+	add	edx,DWORD [28+esp]
+	add	ebx,ecx
+	vpslld	xmm5,xmm5,11
+	mov	ecx,edx
+	shrd	edx,edx,14
+	mov	esi,DWORD [esp]
+	vpxor	xmm4,xmm4,xmm6
+	xor	edx,ecx
+	mov	edi,DWORD [4+esp]
+	xor	esi,edi
+	vpsrld	xmm6,xmm7,10
+	shrd	edx,edx,5
+	and	esi,ecx
+	mov	DWORD [28+esp],ecx
+	vpxor	xmm4,xmm4,xmm5
+	xor	edx,ecx
+	xor	edi,esi
+	shrd	edx,edx,6
+	vpsrlq	xmm5,xmm7,17
+	mov	ecx,ebx
+	add	edx,edi
+	mov	edi,DWORD [16+esp]
+	vpaddd	xmm1,xmm1,xmm4
+	mov	esi,ebx
+	shrd	ecx,ecx,9
+	mov	DWORD [12+esp],ebx
+	vpxor	xmm6,xmm6,xmm5
+	xor	ecx,ebx
+	xor	ebx,edi
+	add	edx,DWORD [8+esp]
+	vpsrlq	xmm7,xmm7,19
+	shrd	ecx,ecx,11
+	and	eax,ebx
+	xor	ecx,esi
+	vpxor	xmm6,xmm6,xmm7
+	add	edx,DWORD [52+esp]
+	xor	eax,edi
+	shrd	ecx,ecx,2
+	vpshufd	xmm7,xmm6,132
+	add	eax,edx
+	add	edx,DWORD [24+esp]
+	add	eax,ecx
+	vpsrldq	xmm7,xmm7,8
+	mov	ecx,edx
+	shrd	edx,edx,14
+	mov	esi,DWORD [28+esp]
+	vpaddd	xmm1,xmm1,xmm7
+	xor	edx,ecx
+	mov	edi,DWORD [esp]
+	xor	esi,edi
+	vpshufd	xmm7,xmm1,80
+	shrd	edx,edx,5
+	and	esi,ecx
+	mov	DWORD [24+esp],ecx
+	vpsrld	xmm6,xmm7,10
+	xor	edx,ecx
+	xor	edi,esi
+	shrd	edx,edx,6
+	vpsrlq	xmm5,xmm7,17
+	mov	ecx,eax
+	add	edx,edi
+	mov	edi,DWORD [12+esp]
+	vpxor	xmm6,xmm6,xmm5
+	mov	esi,eax
+	shrd	ecx,ecx,9
+	mov	DWORD [8+esp],eax
+	vpsrlq	xmm7,xmm7,19
+	xor	ecx,eax
+	xor	eax,edi
+	add	edx,DWORD [4+esp]
+	vpxor	xmm6,xmm6,xmm7
+	shrd	ecx,ecx,11
+	and	ebx,eax
+	xor	ecx,esi
+	vpshufd	xmm7,xmm6,232
+	add	edx,DWORD [56+esp]
+	xor	ebx,edi
+	shrd	ecx,ecx,2
+	vpslldq	xmm7,xmm7,8
+	add	ebx,edx
+	add	edx,DWORD [20+esp]
+	add	ebx,ecx
+	vpaddd	xmm1,xmm1,xmm7
+	mov	ecx,edx
+	shrd	edx,edx,14
+	mov	esi,DWORD [24+esp]
+	vpaddd	xmm6,xmm1,[16+ebp]
+	xor	edx,ecx
+	mov	edi,DWORD [28+esp]
+	xor	esi,edi
+	shrd	edx,edx,5
+	and	esi,ecx
+	mov	DWORD [20+esp],ecx
+	xor	edx,ecx
+	xor	edi,esi
+	shrd	edx,edx,6
+	mov	ecx,ebx
+	add	edx,edi
+	mov	edi,DWORD [8+esp]
+	mov	esi,ebx
+	shrd	ecx,ecx,9
+	mov	DWORD [4+esp],ebx
+	xor	ecx,ebx
+	xor	ebx,edi
+	add	edx,DWORD [esp]
+	shrd	ecx,ecx,11
+	and	eax,ebx
+	xor	ecx,esi
+	add	edx,DWORD [60+esp]
+	xor	eax,edi
+	shrd	ecx,ecx,2
+	add	eax,edx
+	add	edx,DWORD [16+esp]
+	add	eax,ecx
+	vmovdqa	[48+esp],xmm6
+	vpalignr	xmm4,xmm3,xmm2,4
+	mov	ecx,edx
+	shrd	edx,edx,14
+	mov	esi,DWORD [20+esp]
+	vpalignr	xmm7,xmm1,xmm0,4
+	xor	edx,ecx
+	mov	edi,DWORD [24+esp]
+	xor	esi,edi
+	vpsrld	xmm6,xmm4,7
+	shrd	edx,edx,5
+	and	esi,ecx
+	mov	DWORD [16+esp],ecx
+	vpaddd	xmm2,xmm2,xmm7
+	xor	edx,ecx
+	xor	edi,esi
+	shrd	edx,edx,6
+	vpsrld	xmm7,xmm4,3
+	mov	ecx,eax
+	add	edx,edi
+	mov	edi,DWORD [4+esp]
+	vpslld	xmm5,xmm4,14
+	mov	esi,eax
+	shrd	ecx,ecx,9
+	mov	DWORD [esp],eax
+	vpxor	xmm4,xmm7,xmm6
+	xor	ecx,eax
+	xor	eax,edi
+	add	edx,DWORD [28+esp]
+	vpshufd	xmm7,xmm1,250
+	shrd	ecx,ecx,11
+	and	ebx,eax
+	xor	ecx,esi
+	vpsrld	xmm6,xmm6,11
+	add	edx,DWORD [64+esp]
+	xor	ebx,edi
+	shrd	ecx,ecx,2
+	vpxor	xmm4,xmm4,xmm5
+	add	ebx,edx
+	add	edx,DWORD [12+esp]
+	add	ebx,ecx
+	vpslld	xmm5,xmm5,11
+	mov	ecx,edx
+	shrd	edx,edx,14
+	mov	esi,DWORD [16+esp]
+	vpxor	xmm4,xmm4,xmm6
+	xor	edx,ecx
+	mov	edi,DWORD [20+esp]
+	xor	esi,edi
+	vpsrld	xmm6,xmm7,10
+	shrd	edx,edx,5
+	and	esi,ecx
+	mov	DWORD [12+esp],ecx
+	vpxor	xmm4,xmm4,xmm5
+	xor	edx,ecx
+	xor	edi,esi
+	shrd	edx,edx,6
+	vpsrlq	xmm5,xmm7,17
+	mov	ecx,ebx
+	add	edx,edi
+	mov	edi,DWORD [esp]
+	vpaddd	xmm2,xmm2,xmm4
+	mov	esi,ebx
+	shrd	ecx,ecx,9
+	mov	DWORD [28+esp],ebx
+	vpxor	xmm6,xmm6,xmm5
+	xor	ecx,ebx
+	xor	ebx,edi
+	add	edx,DWORD [24+esp]
+	vpsrlq	xmm7,xmm7,19
+	shrd	ecx,ecx,11
+	and	eax,ebx
+	xor	ecx,esi
+	vpxor	xmm6,xmm6,xmm7
+	add	edx,DWORD [68+esp]
+	xor	eax,edi
+	shrd	ecx,ecx,2
+	vpshufd	xmm7,xmm6,132
+	add	eax,edx
+	add	edx,DWORD [8+esp]
+	add	eax,ecx
+	vpsrldq	xmm7,xmm7,8
+	mov	ecx,edx
+	shrd	edx,edx,14
+	mov	esi,DWORD [12+esp]
+	vpaddd	xmm2,xmm2,xmm7
+	xor	edx,ecx
+	mov	edi,DWORD [16+esp]
+	xor	esi,edi
+	vpshufd	xmm7,xmm2,80
+	shrd	edx,edx,5
+	and	esi,ecx
+	mov	DWORD [8+esp],ecx
+	vpsrld	xmm6,xmm7,10
+	xor	edx,ecx
+	xor	edi,esi
+	shrd	edx,edx,6
+	vpsrlq	xmm5,xmm7,17
+	mov	ecx,eax
+	add	edx,edi
+	mov	edi,DWORD [28+esp]
+	vpxor	xmm6,xmm6,xmm5
+	mov	esi,eax
+	shrd	ecx,ecx,9
+	mov	DWORD [24+esp],eax
+	vpsrlq	xmm7,xmm7,19
+	xor	ecx,eax
+	xor	eax,edi
+	add	edx,DWORD [20+esp]
+	vpxor	xmm6,xmm6,xmm7
+	shrd	ecx,ecx,11
+	and	ebx,eax
+	xor	ecx,esi
+	vpshufd	xmm7,xmm6,232
+	add	edx,DWORD [72+esp]
+	xor	ebx,edi
+	shrd	ecx,ecx,2
+	vpslldq	xmm7,xmm7,8
+	add	ebx,edx
+	add	edx,DWORD [4+esp]
+	add	ebx,ecx
+	vpaddd	xmm2,xmm2,xmm7
+	mov	ecx,edx
+	shrd	edx,edx,14
+	mov	esi,DWORD [8+esp]
+	vpaddd	xmm6,xmm2,[32+ebp]
+	xor	edx,ecx
+	mov	edi,DWORD [12+esp]
+	xor	esi,edi
+	shrd	edx,edx,5
+	and	esi,ecx
+	mov	DWORD [4+esp],ecx
+	xor	edx,ecx
+	xor	edi,esi
+	shrd	edx,edx,6
+	mov	ecx,ebx
+	add	edx,edi
+	mov	edi,DWORD [24+esp]
+	mov	esi,ebx
+	shrd	ecx,ecx,9
+	mov	DWORD [20+esp],ebx
+	xor	ecx,ebx
+	xor	ebx,edi
+	add	edx,DWORD [16+esp]
+	shrd	ecx,ecx,11
+	and	eax,ebx
+	xor	ecx,esi
+	add	edx,DWORD [76+esp]
+	xor	eax,edi
+	shrd	ecx,ecx,2
+	add	eax,edx
+	add	edx,DWORD [esp]
+	add	eax,ecx
+	vmovdqa	[64+esp],xmm6
+	vpalignr	xmm4,xmm0,xmm3,4
+	mov	ecx,edx
+	shrd	edx,edx,14
+	mov	esi,DWORD [4+esp]
+	vpalignr	xmm7,xmm2,xmm1,4
+	xor	edx,ecx
+	mov	edi,DWORD [8+esp]
+	xor	esi,edi
+	vpsrld	xmm6,xmm4,7
+	shrd	edx,edx,5
+	and	esi,ecx
+	mov	DWORD [esp],ecx
+	vpaddd	xmm3,xmm3,xmm7
+	xor	edx,ecx
+	xor	edi,esi
+	shrd	edx,edx,6
+	vpsrld	xmm7,xmm4,3
+	mov	ecx,eax
+	add	edx,edi
+	mov	edi,DWORD [20+esp]
+	vpslld	xmm5,xmm4,14
+	mov	esi,eax
+	shrd	ecx,ecx,9
+	mov	DWORD [16+esp],eax
+	vpxor	xmm4,xmm7,xmm6
+	xor	ecx,eax
+	xor	eax,edi
+	add	edx,DWORD [12+esp]
+	vpshufd	xmm7,xmm2,250
+	shrd	ecx,ecx,11
+	and	ebx,eax
+	xor	ecx,esi
+	vpsrld	xmm6,xmm6,11
+	add	edx,DWORD [80+esp]
+	xor	ebx,edi
+	shrd	ecx,ecx,2
+	vpxor	xmm4,xmm4,xmm5
+	add	ebx,edx
+	add	edx,DWORD [28+esp]
+	add	ebx,ecx
+	vpslld	xmm5,xmm5,11
+	mov	ecx,edx
+	shrd	edx,edx,14
+	mov	esi,DWORD [esp]
+	vpxor	xmm4,xmm4,xmm6
+	xor	edx,ecx
+	mov	edi,DWORD [4+esp]
+	xor	esi,edi
+	vpsrld	xmm6,xmm7,10
+	shrd	edx,edx,5
+	and	esi,ecx
+	mov	DWORD [28+esp],ecx
+	vpxor	xmm4,xmm4,xmm5
+	xor	edx,ecx
+	xor	edi,esi
+	shrd	edx,edx,6
+	vpsrlq	xmm5,xmm7,17
+	mov	ecx,ebx
+	add	edx,edi
+	mov	edi,DWORD [16+esp]
+	vpaddd	xmm3,xmm3,xmm4
+	mov	esi,ebx
+	shrd	ecx,ecx,9
+	mov	DWORD [12+esp],ebx
+	vpxor	xmm6,xmm6,xmm5
+	xor	ecx,ebx
+	xor	ebx,edi
+	add	edx,DWORD [8+esp]
+	vpsrlq	xmm7,xmm7,19
+	shrd	ecx,ecx,11
+	and	eax,ebx
+	xor	ecx,esi
+	vpxor	xmm6,xmm6,xmm7
+	add	edx,DWORD [84+esp]
+	xor	eax,edi
+	shrd	ecx,ecx,2
+	vpshufd	xmm7,xmm6,132
+	add	eax,edx
+	add	edx,DWORD [24+esp]
+	add	eax,ecx
+	vpsrldq	xmm7,xmm7,8
+	mov	ecx,edx
+	shrd	edx,edx,14
+	mov	esi,DWORD [28+esp]
+	vpaddd	xmm3,xmm3,xmm7
+	xor	edx,ecx
+	mov	edi,DWORD [esp]
+	xor	esi,edi
+	vpshufd	xmm7,xmm3,80
+	shrd	edx,edx,5
+	and	esi,ecx
+	mov	DWORD [24+esp],ecx
+	vpsrld	xmm6,xmm7,10
+	xor	edx,ecx
+	xor	edi,esi
+	shrd	edx,edx,6
+	vpsrlq	xmm5,xmm7,17
+	mov	ecx,eax
+	add	edx,edi
+	mov	edi,DWORD [12+esp]
+	vpxor	xmm6,xmm6,xmm5
+	mov	esi,eax
+	shrd	ecx,ecx,9
+	mov	DWORD [8+esp],eax
+	vpsrlq	xmm7,xmm7,19
+	xor	ecx,eax
+	xor	eax,edi
+	add	edx,DWORD [4+esp]
+	vpxor	xmm6,xmm6,xmm7
+	shrd	ecx,ecx,11
+	and	ebx,eax
+	xor	ecx,esi
+	vpshufd	xmm7,xmm6,232
+	add	edx,DWORD [88+esp]
+	xor	ebx,edi
+	shrd	ecx,ecx,2
+	vpslldq	xmm7,xmm7,8
+	add	ebx,edx
+	add	edx,DWORD [20+esp]
+	add	ebx,ecx
+	vpaddd	xmm3,xmm3,xmm7
+	mov	ecx,edx
+	shrd	edx,edx,14
+	mov	esi,DWORD [24+esp]
+	vpaddd	xmm6,xmm3,[48+ebp]
+	xor	edx,ecx
+	mov	edi,DWORD [28+esp]
+	xor	esi,edi
+	shrd	edx,edx,5
+	and	esi,ecx
+	mov	DWORD [20+esp],ecx
+	xor	edx,ecx
+	xor	edi,esi
+	shrd	edx,edx,6
+	mov	ecx,ebx
+	add	edx,edi
+	mov	edi,DWORD [8+esp]
+	mov	esi,ebx
+	shrd	ecx,ecx,9
+	mov	DWORD [4+esp],ebx
+	xor	ecx,ebx
+	xor	ebx,edi
+	add	edx,DWORD [esp]
+	shrd	ecx,ecx,11
+	and	eax,ebx
+	xor	ecx,esi
+	add	edx,DWORD [92+esp]
+	xor	eax,edi
+	shrd	ecx,ecx,2
+	add	eax,edx
+	add	edx,DWORD [16+esp]
+	add	eax,ecx
+	vmovdqa	[80+esp],xmm6
+	cmp	DWORD [64+ebp],66051
+	jne	NEAR L$013avx_00_47
+	mov	ecx,edx
+	shrd	edx,edx,14
+	mov	esi,DWORD [20+esp]
+	xor	edx,ecx
+	mov	edi,DWORD [24+esp]
+	xor	esi,edi
+	shrd	edx,edx,5
+	and	esi,ecx
+	mov	DWORD [16+esp],ecx
+	xor	edx,ecx
+	xor	edi,esi
+	shrd	edx,edx,6
+	mov	ecx,eax
+	add	edx,edi
+	mov	edi,DWORD [4+esp]
+	mov	esi,eax
+	shrd	ecx,ecx,9
+	mov	DWORD [esp],eax
+	xor	ecx,eax
+	xor	eax,edi
+	add	edx,DWORD [28+esp]
+	shrd	ecx,ecx,11
+	and	ebx,eax
+	xor	ecx,esi
+	add	edx,DWORD [32+esp]
+	xor	ebx,edi
+	shrd	ecx,ecx,2
+	add	ebx,edx
+	add	edx,DWORD [12+esp]
+	add	ebx,ecx
+	mov	ecx,edx
+	shrd	edx,edx,14
+	mov	esi,DWORD [16+esp]
+	xor	edx,ecx
+	mov	edi,DWORD [20+esp]
+	xor	esi,edi
+	shrd	edx,edx,5
+	and	esi,ecx
+	mov	DWORD [12+esp],ecx
+	xor	edx,ecx
+	xor	edi,esi
+	shrd	edx,edx,6
+	mov	ecx,ebx
+	add	edx,edi
+	mov	edi,DWORD [esp]
+	mov	esi,ebx
+	shrd	ecx,ecx,9
+	mov	DWORD [28+esp],ebx
+	xor	ecx,ebx
+	xor	ebx,edi
+	add	edx,DWORD [24+esp]
+	shrd	ecx,ecx,11
+	and	eax,ebx
+	xor	ecx,esi
+	add	edx,DWORD [36+esp]
+	xor	eax,edi
+	shrd	ecx,ecx,2
+	add	eax,edx
+	add	edx,DWORD [8+esp]
+	add	eax,ecx
+	mov	ecx,edx
+	shrd	edx,edx,14
+	mov	esi,DWORD [12+esp]
+	xor	edx,ecx
+	mov	edi,DWORD [16+esp]
+	xor	esi,edi
+	shrd	edx,edx,5
+	and	esi,ecx
+	mov	DWORD [8+esp],ecx
+	xor	edx,ecx
+	xor	edi,esi
+	shrd	edx,edx,6
+	mov	ecx,eax
+	add	edx,edi
+	mov	edi,DWORD [28+esp]
+	mov	esi,eax
+	shrd	ecx,ecx,9
+	mov	DWORD [24+esp],eax
+	xor	ecx,eax
+	xor	eax,edi
+	add	edx,DWORD [20+esp]
+	shrd	ecx,ecx,11
+	and	ebx,eax
+	xor	ecx,esi
+	add	edx,DWORD [40+esp]
+	xor	ebx,edi
+	shrd	ecx,ecx,2
+	add	ebx,edx
+	add	edx,DWORD [4+esp]
+	add	ebx,ecx
+	mov	ecx,edx
+	shrd	edx,edx,14
+	mov	esi,DWORD [8+esp]
+	xor	edx,ecx
+	mov	edi,DWORD [12+esp]
+	xor	esi,edi
+	shrd	edx,edx,5
+	and	esi,ecx
+	mov	DWORD [4+esp],ecx
+	xor	edx,ecx
+	xor	edi,esi
+	shrd	edx,edx,6
+	mov	ecx,ebx
+	add	edx,edi
+	mov	edi,DWORD [24+esp]
+	mov	esi,ebx
+	shrd	ecx,ecx,9
+	mov	DWORD [20+esp],ebx
+	xor	ecx,ebx
+	xor	ebx,edi
+	add	edx,DWORD [16+esp]
+	shrd	ecx,ecx,11
+	and	eax,ebx
+	xor	ecx,esi
+	add	edx,DWORD [44+esp]
+	xor	eax,edi
+	shrd	ecx,ecx,2
+	add	eax,edx
+	add	edx,DWORD [esp]
+	add	eax,ecx
+	mov	ecx,edx
+	shrd	edx,edx,14
+	mov	esi,DWORD [4+esp]
+	xor	edx,ecx
+	mov	edi,DWORD [8+esp]
+	xor	esi,edi
+	shrd	edx,edx,5
+	and	esi,ecx
+	mov	DWORD [esp],ecx
+	xor	edx,ecx
+	xor	edi,esi
+	shrd	edx,edx,6
+	mov	ecx,eax
+	add	edx,edi
+	mov	edi,DWORD [20+esp]
+	mov	esi,eax
+	shrd	ecx,ecx,9
+	mov	DWORD [16+esp],eax
+	xor	ecx,eax
+	xor	eax,edi
+	add	edx,DWORD [12+esp]
+	shrd	ecx,ecx,11
+	and	ebx,eax
+	xor	ecx,esi
+	add	edx,DWORD [48+esp]
+	xor	ebx,edi
+	shrd	ecx,ecx,2
+	add	ebx,edx
+	add	edx,DWORD [28+esp]
+	add	ebx,ecx
+	mov	ecx,edx
+	shrd	edx,edx,14
+	mov	esi,DWORD [esp]
+	xor	edx,ecx
+	mov	edi,DWORD [4+esp]
+	xor	esi,edi
+	shrd	edx,edx,5
+	and	esi,ecx
+	mov	DWORD [28+esp],ecx
+	xor	edx,ecx
+	xor	edi,esi
+	shrd	edx,edx,6
+	mov	ecx,ebx
+	add	edx,edi
+	mov	edi,DWORD [16+esp]
+	mov	esi,ebx
+	shrd	ecx,ecx,9
+	mov	DWORD [12+esp],ebx
+	xor	ecx,ebx
+	xor	ebx,edi
+	add	edx,DWORD [8+esp]
+	shrd	ecx,ecx,11
+	and	eax,ebx
+	xor	ecx,esi
+	add	edx,DWORD [52+esp]
+	xor	eax,edi
+	shrd	ecx,ecx,2
+	add	eax,edx
+	add	edx,DWORD [24+esp]
+	add	eax,ecx
+	mov	ecx,edx
+	shrd	edx,edx,14
+	mov	esi,DWORD [28+esp]
+	xor	edx,ecx
+	mov	edi,DWORD [esp]
+	xor	esi,edi
+	shrd	edx,edx,5
+	and	esi,ecx
+	mov	DWORD [24+esp],ecx
+	xor	edx,ecx
+	xor	edi,esi
+	shrd	edx,edx,6
+	mov	ecx,eax
+	add	edx,edi
+	mov	edi,DWORD [12+esp]
+	mov	esi,eax
+	shrd	ecx,ecx,9
+	mov	DWORD [8+esp],eax
+	xor	ecx,eax
+	xor	eax,edi
+	add	edx,DWORD [4+esp]
+	shrd	ecx,ecx,11
+	and	ebx,eax
+	xor	ecx,esi
+	add	edx,DWORD [56+esp]
+	xor	ebx,edi
+	shrd	ecx,ecx,2
+	add	ebx,edx
+	add	edx,DWORD [20+esp]
+	add	ebx,ecx
+	mov	ecx,edx
+	shrd	edx,edx,14
+	mov	esi,DWORD [24+esp]
+	xor	edx,ecx
+	mov	edi,DWORD [28+esp]
+	xor	esi,edi
+	shrd	edx,edx,5
+	and	esi,ecx
+	mov	DWORD [20+esp],ecx
+	xor	edx,ecx
+	xor	edi,esi
+	shrd	edx,edx,6
+	mov	ecx,ebx
+	add	edx,edi
+	mov	edi,DWORD [8+esp]
+	mov	esi,ebx
+	shrd	ecx,ecx,9
+	mov	DWORD [4+esp],ebx
+	xor	ecx,ebx
+	xor	ebx,edi
+	add	edx,DWORD [esp]
+	shrd	ecx,ecx,11
+	and	eax,ebx
+	xor	ecx,esi
+	add	edx,DWORD [60+esp]
+	xor	eax,edi
+	shrd	ecx,ecx,2
+	add	eax,edx
+	add	edx,DWORD [16+esp]
+	add	eax,ecx
+	mov	ecx,edx
+	shrd	edx,edx,14
+	mov	esi,DWORD [20+esp]
+	xor	edx,ecx
+	mov	edi,DWORD [24+esp]
+	xor	esi,edi
+	shrd	edx,edx,5
+	and	esi,ecx
+	mov	DWORD [16+esp],ecx
+	xor	edx,ecx
+	xor	edi,esi
+	shrd	edx,edx,6
+	mov	ecx,eax
+	add	edx,edi
+	mov	edi,DWORD [4+esp]
+	mov	esi,eax
+	shrd	ecx,ecx,9
+	mov	DWORD [esp],eax
+	xor	ecx,eax
+	xor	eax,edi
+	add	edx,DWORD [28+esp]
+	shrd	ecx,ecx,11
+	and	ebx,eax
+	xor	ecx,esi
+	add	edx,DWORD [64+esp]
+	xor	ebx,edi
+	shrd	ecx,ecx,2
+	add	ebx,edx
+	add	edx,DWORD [12+esp]
+	add	ebx,ecx
+	mov	ecx,edx
+	shrd	edx,edx,14
+	mov	esi,DWORD [16+esp]
+	xor	edx,ecx
+	mov	edi,DWORD [20+esp]
+	xor	esi,edi
+	shrd	edx,edx,5
+	and	esi,ecx
+	mov	DWORD [12+esp],ecx
+	xor	edx,ecx
+	xor	edi,esi
+	shrd	edx,edx,6
+	mov	ecx,ebx
+	add	edx,edi
+	mov	edi,DWORD [esp]
+	mov	esi,ebx
+	shrd	ecx,ecx,9
+	mov	DWORD [28+esp],ebx
+	xor	ecx,ebx
+	xor	ebx,edi
+	add	edx,DWORD [24+esp]
+	shrd	ecx,ecx,11
+	and	eax,ebx
+	xor	ecx,esi
+	add	edx,DWORD [68+esp]
+	xor	eax,edi
+	shrd	ecx,ecx,2
+	add	eax,edx
+	add	edx,DWORD [8+esp]
+	add	eax,ecx
+	mov	ecx,edx
+	shrd	edx,edx,14
+	mov	esi,DWORD [12+esp]
+	xor	edx,ecx
+	mov	edi,DWORD [16+esp]
+	xor	esi,edi
+	shrd	edx,edx,5
+	and	esi,ecx
+	mov	DWORD [8+esp],ecx
+	xor	edx,ecx
+	xor	edi,esi
+	shrd	edx,edx,6
+	mov	ecx,eax
+	add	edx,edi
+	mov	edi,DWORD [28+esp]
+	mov	esi,eax
+	shrd	ecx,ecx,9
+	mov	DWORD [24+esp],eax
+	xor	ecx,eax
+	xor	eax,edi
+	add	edx,DWORD [20+esp]
+	shrd	ecx,ecx,11
+	and	ebx,eax
+	xor	ecx,esi
+	add	edx,DWORD [72+esp]
+	xor	ebx,edi
+	shrd	ecx,ecx,2
+	add	ebx,edx
+	add	edx,DWORD [4+esp]
+	add	ebx,ecx
+	mov	ecx,edx
+	shrd	edx,edx,14
+	mov	esi,DWORD [8+esp]
+	xor	edx,ecx
+	mov	edi,DWORD [12+esp]
+	xor	esi,edi
+	shrd	edx,edx,5
+	and	esi,ecx
+	mov	DWORD [4+esp],ecx
+	xor	edx,ecx
+	xor	edi,esi
+	shrd	edx,edx,6
+	mov	ecx,ebx
+	add	edx,edi
+	mov	edi,DWORD [24+esp]
+	mov	esi,ebx
+	shrd	ecx,ecx,9
+	mov	DWORD [20+esp],ebx
+	xor	ecx,ebx
+	xor	ebx,edi
+	add	edx,DWORD [16+esp]
+	shrd	ecx,ecx,11
+	and	eax,ebx
+	xor	ecx,esi
+	add	edx,DWORD [76+esp]
+	xor	eax,edi
+	shrd	ecx,ecx,2
+	add	eax,edx
+	add	edx,DWORD [esp]
+	add	eax,ecx
+	mov	ecx,edx
+	shrd	edx,edx,14
+	mov	esi,DWORD [4+esp]
+	xor	edx,ecx
+	mov	edi,DWORD [8+esp]
+	xor	esi,edi
+	shrd	edx,edx,5
+	and	esi,ecx
+	mov	DWORD [esp],ecx
+	xor	edx,ecx
+	xor	edi,esi
+	shrd	edx,edx,6
+	mov	ecx,eax
+	add	edx,edi
+	mov	edi,DWORD [20+esp]
+	mov	esi,eax
+	shrd	ecx,ecx,9
+	mov	DWORD [16+esp],eax
+	xor	ecx,eax
+	xor	eax,edi
+	add	edx,DWORD [12+esp]
+	shrd	ecx,ecx,11
+	and	ebx,eax
+	xor	ecx,esi
+	add	edx,DWORD [80+esp]
+	xor	ebx,edi
+	shrd	ecx,ecx,2
+	add	ebx,edx
+	add	edx,DWORD [28+esp]
+	add	ebx,ecx
+	mov	ecx,edx
+	shrd	edx,edx,14
+	mov	esi,DWORD [esp]
+	xor	edx,ecx
+	mov	edi,DWORD [4+esp]
+	xor	esi,edi
+	shrd	edx,edx,5
+	and	esi,ecx
+	mov	DWORD [28+esp],ecx
+	xor	edx,ecx
+	xor	edi,esi
+	shrd	edx,edx,6
+	mov	ecx,ebx
+	add	edx,edi
+	mov	edi,DWORD [16+esp]
+	mov	esi,ebx
+	shrd	ecx,ecx,9
+	mov	DWORD [12+esp],ebx
+	xor	ecx,ebx
+	xor	ebx,edi
+	add	edx,DWORD [8+esp]
+	shrd	ecx,ecx,11
+	and	eax,ebx
+	xor	ecx,esi
+	add	edx,DWORD [84+esp]
+	xor	eax,edi
+	shrd	ecx,ecx,2
+	add	eax,edx
+	add	edx,DWORD [24+esp]
+	add	eax,ecx
+	mov	ecx,edx
+	shrd	edx,edx,14
+	mov	esi,DWORD [28+esp]
+	xor	edx,ecx
+	mov	edi,DWORD [esp]
+	xor	esi,edi
+	shrd	edx,edx,5
+	and	esi,ecx
+	mov	DWORD [24+esp],ecx
+	xor	edx,ecx
+	xor	edi,esi
+	shrd	edx,edx,6
+	mov	ecx,eax
+	add	edx,edi
+	mov	edi,DWORD [12+esp]
+	mov	esi,eax
+	shrd	ecx,ecx,9
+	mov	DWORD [8+esp],eax
+	xor	ecx,eax
+	xor	eax,edi
+	add	edx,DWORD [4+esp]
+	shrd	ecx,ecx,11
+	and	ebx,eax
+	xor	ecx,esi
+	add	edx,DWORD [88+esp]
+	xor	ebx,edi
+	shrd	ecx,ecx,2
+	add	ebx,edx
+	add	edx,DWORD [20+esp]
+	add	ebx,ecx
+	mov	ecx,edx
+	shrd	edx,edx,14
+	mov	esi,DWORD [24+esp]
+	xor	edx,ecx
+	mov	edi,DWORD [28+esp]
+	xor	esi,edi
+	shrd	edx,edx,5
+	and	esi,ecx
+	mov	DWORD [20+esp],ecx
+	xor	edx,ecx
+	xor	edi,esi
+	shrd	edx,edx,6
+	mov	ecx,ebx
+	add	edx,edi
+	mov	edi,DWORD [8+esp]
+	mov	esi,ebx
+	shrd	ecx,ecx,9
+	mov	DWORD [4+esp],ebx
+	xor	ecx,ebx
+	xor	ebx,edi
+	add	edx,DWORD [esp]
+	shrd	ecx,ecx,11
+	and	eax,ebx
+	xor	ecx,esi
+	add	edx,DWORD [92+esp]
+	xor	eax,edi
+	shrd	ecx,ecx,2
+	add	eax,edx
+	add	edx,DWORD [16+esp]
+	add	eax,ecx
+	mov	esi,DWORD [96+esp]
+	xor	ebx,edi
+	mov	ecx,DWORD [12+esp]
+	add	eax,DWORD [esi]
+	add	ebx,DWORD [4+esi]
+	add	edi,DWORD [8+esi]
+	add	ecx,DWORD [12+esi]
+	mov	DWORD [esi],eax
+	mov	DWORD [4+esi],ebx
+	mov	DWORD [8+esi],edi
+	mov	DWORD [12+esi],ecx
+	mov	DWORD [4+esp],ebx
+	xor	ebx,edi
+	mov	DWORD [8+esp],edi
+	mov	DWORD [12+esp],ecx
+	mov	edi,DWORD [20+esp]
+	mov	ecx,DWORD [24+esp]
+	add	edx,DWORD [16+esi]
+	add	edi,DWORD [20+esi]
+	add	ecx,DWORD [24+esi]
+	mov	DWORD [16+esi],edx
+	mov	DWORD [20+esi],edi
+	mov	DWORD [20+esp],edi
+	mov	edi,DWORD [28+esp]
+	mov	DWORD [24+esi],ecx
+	add	edi,DWORD [28+esi]
+	mov	DWORD [24+esp],ecx
+	mov	DWORD [28+esi],edi
+	mov	DWORD [28+esp],edi
+	mov	edi,DWORD [100+esp]
+	vmovdqa	xmm7,[64+ebp]
+	sub	ebp,192
+	cmp	edi,DWORD [104+esp]
+	jb	NEAR L$012grand_avx
+	mov	esp,DWORD [108+esp]
+	vzeroall
+	pop	edi
+	pop	esi
+	pop	ebx
+	pop	ebp
+	ret
 segment	.bss
 common	_OPENSSL_ia32cap_P 16
diff --git a/packager/third_party/boringssl/win-x86_64/crypto/bn/rsaz-x86_64.asm b/packager/third_party/boringssl/win-x86_64/crypto/bn/rsaz-x86_64.asm
index 04d5e3915a..72ec505289 100644
--- a/packager/third_party/boringssl/win-x86_64/crypto/bn/rsaz-x86_64.asm
+++ b/packager/third_party/boringssl/win-x86_64/crypto/bn/rsaz-x86_64.asm
@@ -504,48 +504,104 @@ $L$SEH_begin_rsaz_512_mul_gather4:
 	push	r14
 	push	r15
 
-	mov	r9d,r9d
-	sub	rsp,128+24
+	sub	rsp,328
+	movaps	XMMWORD[160+rsp],xmm6
+	movaps	XMMWORD[176+rsp],xmm7
+	movaps	XMMWORD[192+rsp],xmm8
+	movaps	XMMWORD[208+rsp],xmm9
+	movaps	XMMWORD[224+rsp],xmm10
+	movaps	XMMWORD[240+rsp],xmm11
+	movaps	XMMWORD[256+rsp],xmm12
+	movaps	XMMWORD[272+rsp],xmm13
+	movaps	XMMWORD[288+rsp],xmm14
+	movaps	XMMWORD[304+rsp],xmm15
 $L$mul_gather4_body:
-	mov	eax,DWORD[64+r9*4+rdx]
-DB	102,72,15,110,199
-	mov	ebx,DWORD[r9*4+rdx]
-DB	102,72,15,110,201
-	mov	QWORD[128+rsp],r8
+	movd	xmm8,r9d
+	movdqa	xmm1,XMMWORD[(($L$inc+16))]
+	movdqa	xmm0,XMMWORD[$L$inc]
+
+	pshufd	xmm8,xmm8,0
+	movdqa	xmm7,xmm1
+	movdqa	xmm2,xmm1
+	paddd	xmm1,xmm0
+	pcmpeqd	xmm0,xmm8
+	movdqa	xmm3,xmm7
+	paddd	xmm2,xmm1
+	pcmpeqd	xmm1,xmm8
+	movdqa	xmm4,xmm7
+	paddd	xmm3,xmm2
+	pcmpeqd	xmm2,xmm8
+	movdqa	xmm5,xmm7
+	paddd	xmm4,xmm3
+	pcmpeqd	xmm3,xmm8
+	movdqa	xmm6,xmm7
+	paddd	xmm5,xmm4
+	pcmpeqd	xmm4,xmm8
+	paddd	xmm6,xmm5
+	pcmpeqd	xmm5,xmm8
+	paddd	xmm7,xmm6
+	pcmpeqd	xmm6,xmm8
+	pcmpeqd	xmm7,xmm8
+
+	movdqa	xmm8,XMMWORD[rdx]
+	movdqa	xmm9,XMMWORD[16+rdx]
+	movdqa	xmm10,XMMWORD[32+rdx]
+	movdqa	xmm11,XMMWORD[48+rdx]
+	pand	xmm8,xmm0
+	movdqa	xmm12,XMMWORD[64+rdx]
+	pand	xmm9,xmm1
+	movdqa	xmm13,XMMWORD[80+rdx]
+	pand	xmm10,xmm2
+	movdqa	xmm14,XMMWORD[96+rdx]
+	pand	xmm11,xmm3
+	movdqa	xmm15,XMMWORD[112+rdx]
+	lea	rbp,[128+rdx]
+	pand	xmm12,xmm4
+	pand	xmm13,xmm5
+	pand	xmm14,xmm6
+	pand	xmm15,xmm7
+	por	xmm8,xmm10
+	por	xmm9,xmm11
+	por	xmm8,xmm12
+	por	xmm9,xmm13
+	por	xmm8,xmm14
+	por	xmm9,xmm15
+
+	por	xmm8,xmm9
+	pshufd	xmm9,xmm8,0x4e
+	por	xmm8,xmm9
+DB	102,76,15,126,195
+
+	mov	QWORD[128+rsp],r8
+	mov	QWORD[((128+8))+rsp],rdi
+	mov	QWORD[((128+16))+rsp],rcx
 
-	shl	rax,32
-	or	rbx,rax
 	mov	rax,QWORD[rsi]
 	mov	rcx,QWORD[8+rsi]
-	lea	rbp,[128+r9*4+rdx]
 	mul	rbx
 	mov	QWORD[rsp],rax
 	mov	rax,rcx
 	mov	r8,rdx
 
 	mul	rbx
-	movd	xmm4,DWORD[rbp]
 	add	r8,rax
 	mov	rax,QWORD[16+rsi]
 	mov	r9,rdx
 	adc	r9,0
 
 	mul	rbx
-	movd	xmm5,DWORD[64+rbp]
 	add	r9,rax
 	mov	rax,QWORD[24+rsi]
 	mov	r10,rdx
 	adc	r10,0
 
 	mul	rbx
-	pslldq	xmm5,4
 	add	r10,rax
 	mov	rax,QWORD[32+rsi]
 	mov	r11,rdx
 	adc	r11,0
 
 	mul	rbx
-	por	xmm4,xmm5
 	add	r11,rax
 	mov	rax,QWORD[40+rsi]
 	mov	r12,rdx
@@ -558,14 +614,12 @@ DB	102,72,15,110,201
 	adc	r13,0
 
 	mul	rbx
-	lea	rbp,[128+rbp]
 	add	r13,rax
 	mov	rax,QWORD[56+rsi]
 	mov	r14,rdx
 	adc	r14,0
 
 	mul	rbx
-DB	102,72,15,126,227
 	add	r14,rax
 	mov	rax,QWORD[rsi]
 	mov	r15,rdx
@@ -577,6 +631,35 @@ DB	102,72,15,126,227
 
 ALIGN	32
 $L$oop_mul_gather:
+	movdqa	xmm8,XMMWORD[rbp]
+	movdqa	xmm9,XMMWORD[16+rbp]
+	movdqa	xmm10,XMMWORD[32+rbp]
+	movdqa	xmm11,XMMWORD[48+rbp]
+	pand	xmm8,xmm0
+	movdqa	xmm12,XMMWORD[64+rbp]
+	pand	xmm9,xmm1
+	movdqa	xmm13,XMMWORD[80+rbp]
+	pand	xmm10,xmm2
+	movdqa	xmm14,XMMWORD[96+rbp]
+	pand	xmm11,xmm3
+	movdqa	xmm15,XMMWORD[112+rbp]
+	lea	rbp,[128+rbp]
+	pand	xmm12,xmm4
+	pand	xmm13,xmm5
+	pand	xmm14,xmm6
+	pand	xmm15,xmm7
+	por	xmm8,xmm10
+	por	xmm9,xmm11
+	por	xmm8,xmm12
+	por	xmm9,xmm13
+	por	xmm8,xmm14
+	por	xmm9,xmm15
+
+	por	xmm8,xmm9
+	pshufd	xmm9,xmm8,0x4e
+	por	xmm8,xmm9
+DB	102,76,15,126,195
+
 	mul	rbx
 	add	r8,rax
 	mov	rax,QWORD[8+rsi]
@@ -585,7 +668,6 @@ $L$oop_mul_gather:
 	adc	r8,0
 
 	mul	rbx
-	movd	xmm4,DWORD[rbp]
 	add	r9,rax
 	mov	rax,QWORD[16+rsi]
 	adc	rdx,0
@@ -594,7 +676,6 @@ $L$oop_mul_gather:
 	adc	r9,0
 
 	mul	rbx
-	movd	xmm5,DWORD[64+rbp]
 	add	r10,rax
 	mov	rax,QWORD[24+rsi]
 	adc	rdx,0
@@ -603,7 +684,6 @@ $L$oop_mul_gather:
 	adc	r10,0
 
 	mul	rbx
-	pslldq	xmm5,4
 	add	r11,rax
 	mov	rax,QWORD[32+rsi]
 	adc	rdx,0
@@ -612,7 +692,6 @@ $L$oop_mul_gather:
 	adc	r11,0
 
 	mul	rbx
-	por	xmm4,xmm5
 	add	r12,rax
 	mov	rax,QWORD[40+rsi]
 	adc	rdx,0
@@ -637,7 +716,6 @@ $L$oop_mul_gather:
 	adc	r14,0
 
 	mul	rbx
-DB	102,72,15,126,227
 	add	r15,rax
 	mov	rax,QWORD[rsi]
 	adc	rdx,0
@@ -645,7 +723,6 @@ DB	102,72,15,126,227
 	mov	r15,rdx
 	adc	r15,0
 
-	lea	rbp,[128+rbp]
 	lea	rdi,[8+rdi]
 
 	dec	ecx
@@ -660,8 +737,8 @@ DB	102,72,15,126,227
 	mov	QWORD[48+rdi],r14
 	mov	QWORD[56+rdi],r15
 
-DB	102,72,15,126,199
-DB	102,72,15,126,205
+	mov	rdi,QWORD[((128+8))+rsp]
+	mov	rbp,QWORD[((128+16))+rsp]
 
 	mov	r8,QWORD[rsp]
 	mov	r9,QWORD[8+rsp]
@@ -686,6 +763,17 @@ DB	102,72,15,126,205
 	call	__rsaz_512_subtract
 
 	lea	rax,[((128+24+48))+rsp]
+	movaps	xmm6,XMMWORD[((160-200))+rax]
+	movaps	xmm7,XMMWORD[((176-200))+rax]
+	movaps	xmm8,XMMWORD[((192-200))+rax]
+	movaps	xmm9,XMMWORD[((208-200))+rax]
+	movaps	xmm10,XMMWORD[((224-200))+rax]
+	movaps	xmm11,XMMWORD[((240-200))+rax]
+	movaps	xmm12,XMMWORD[((256-200))+rax]
+	movaps	xmm13,XMMWORD[((272-200))+rax]
+	movaps	xmm14,XMMWORD[((288-200))+rax]
+	movaps	xmm15,XMMWORD[((304-200))+rax]
+	lea	rax,[176+rax]
 	mov	r15,QWORD[((-48))+rax]
 	mov	r14,QWORD[((-40))+rax]
 	mov	r13,QWORD[((-32))+rax]
@@ -724,7 +812,7 @@ $L$SEH_begin_rsaz_512_mul_scatter4:
 	mov	r9d,r9d
 	sub	rsp,128+24
 $L$mul_scatter4_body:
-	lea	r8,[r9*4+r8]
+	lea	r8,[r9*8+r8]
 DB	102,72,15,110,199
 DB	102,72,15,110,202
 DB	102,73,15,110,208
@@ -760,30 +848,14 @@ DB	102,72,15,126,214
 
 	call	__rsaz_512_subtract
 
-	mov	DWORD[rsi],r8d
-	shr	r8,32
-	mov	DWORD[128+rsi],r9d
-	shr	r9,32
-	mov	DWORD[256+rsi],r10d
-	shr	r10,32
-	mov	DWORD[384+rsi],r11d
-	shr	r11,32
-	mov	DWORD[512+rsi],r12d
-	shr	r12,32
-	mov	DWORD[640+rsi],r13d
-	shr	r13,32
-	mov	DWORD[768+rsi],r14d
-	shr	r14,32
-	mov	DWORD[896+rsi],r15d
-	shr	r15,32
-	mov	DWORD[64+rsi],r8d
-	mov	DWORD[192+rsi],r9d
-	mov	DWORD[320+rsi],r10d
-	mov	DWORD[448+rsi],r11d
-	mov	DWORD[576+rsi],r12d
-	mov	DWORD[704+rsi],r13d
-	mov	DWORD[832+rsi],r14d
-	mov	DWORD[960+rsi],r15d
+	mov	QWORD[rsi],r8
+	mov	QWORD[128+rsi],r9
+	mov	QWORD[256+rsi],r10
+	mov	QWORD[384+rsi],r11
+	mov	QWORD[512+rsi],r12
+	mov	QWORD[640+rsi],r13
+	mov	QWORD[768+rsi],r14
+	mov	QWORD[896+rsi],r15
 
 	lea	rax,[((128+24+48))+rsp]
 	mov	r15,QWORD[((-48))+rax]
@@ -1150,16 +1222,14 @@ global	rsaz_512_scatter4
 
 ALIGN	16
 rsaz_512_scatter4:
-	lea	rcx,[r8*4+rcx]
+	lea	rcx,[r8*8+rcx]
 	mov	r9d,8
 	jmp	NEAR $L$oop_scatter
 ALIGN	16
 $L$oop_scatter:
 	mov	rax,QWORD[rdx]
 	lea	rdx,[8+rdx]
-	mov	DWORD[rcx],eax
-	shr	rax,32
-	mov	DWORD[64+rcx],eax
+	mov	QWORD[rcx],rax
 	lea	rcx,[128+rcx]
 	dec	r9d
 	jnz	NEAR $L$oop_scatter
@@ -1170,22 +1240,98 @@ global	rsaz_512_gather4
 
 ALIGN	16
 rsaz_512_gather4:
-	lea	rdx,[r8*4+rdx]
+$L$SEH_begin_rsaz_512_gather4:
+DB	0x48,0x81,0xec,0xa8,0x00,0x00,0x00
+DB	0x0f,0x29,0x34,0x24
+DB	0x0f,0x29,0x7c,0x24,0x10
+DB	0x44,0x0f,0x29,0x44,0x24,0x20
+DB	0x44,0x0f,0x29,0x4c,0x24,0x30
+DB	0x44,0x0f,0x29,0x54,0x24,0x40
+DB	0x44,0x0f,0x29,0x5c,0x24,0x50
+DB	0x44,0x0f,0x29,0x64,0x24,0x60
+DB	0x44,0x0f,0x29,0x6c,0x24,0x70
+DB	0x44,0x0f,0x29,0xb4,0x24,0x80,0,0,0
+DB	0x44,0x0f,0x29,0xbc,0x24,0x90,0,0,0
+	movd	xmm8,r8d
+	movdqa	xmm1,XMMWORD[(($L$inc+16))]
+	movdqa	xmm0,XMMWORD[$L$inc]
+
+	pshufd	xmm8,xmm8,0
+	movdqa	xmm7,xmm1
+	movdqa	xmm2,xmm1
+	paddd	xmm1,xmm0
+	pcmpeqd	xmm0,xmm8
+	movdqa	xmm3,xmm7
+	paddd	xmm2,xmm1
+	pcmpeqd	xmm1,xmm8
+	movdqa	xmm4,xmm7
+	paddd	xmm3,xmm2
+	pcmpeqd	xmm2,xmm8
+	movdqa	xmm5,xmm7
+	paddd	xmm4,xmm3
+	pcmpeqd	xmm3,xmm8
+	movdqa	xmm6,xmm7
+	paddd	xmm5,xmm4
+	pcmpeqd	xmm4,xmm8
+	paddd	xmm6,xmm5
+	pcmpeqd	xmm5,xmm8
+	paddd	xmm7,xmm6
+	pcmpeqd	xmm6,xmm8
+	pcmpeqd	xmm7,xmm8
 	mov	r9d,8
 	jmp	NEAR $L$oop_gather
 ALIGN	16
 $L$oop_gather:
-	mov	eax,DWORD[rdx]
-	mov	r8d,DWORD[64+rdx]
+	movdqa	xmm8,XMMWORD[rdx]
+	movdqa	xmm9,XMMWORD[16+rdx]
+	movdqa	xmm10,XMMWORD[32+rdx]
+	movdqa	xmm11,XMMWORD[48+rdx]
+	pand	xmm8,xmm0
+	movdqa	xmm12,XMMWORD[64+rdx]
+	pand	xmm9,xmm1
+	movdqa	xmm13,XMMWORD[80+rdx]
+	pand	xmm10,xmm2
+	movdqa	xmm14,XMMWORD[96+rdx]
+	pand	xmm11,xmm3
+	movdqa	xmm15,XMMWORD[112+rdx]
 	lea	rdx,[128+rdx]
-	shl	r8,32
-	or	rax,r8
-	mov	QWORD[rcx],rax
+	pand	xmm12,xmm4
+	pand	xmm13,xmm5
+	pand	xmm14,xmm6
+	pand	xmm15,xmm7
+	por	xmm8,xmm10
+	por	xmm9,xmm11
+	por	xmm8,xmm12
+	por	xmm9,xmm13
+	por	xmm8,xmm14
+	por	xmm9,xmm15
+
+	por	xmm8,xmm9
+	pshufd	xmm9,xmm8,0x4e
+	por	xmm8,xmm9
+	movq	QWORD[rcx],xmm8
 	lea	rcx,[8+rcx]
 	dec	r9d
 	jnz	NEAR $L$oop_gather
+	movaps	xmm6,XMMWORD[rsp]
+	movaps	xmm7,XMMWORD[16+rsp]
+	movaps	xmm8,XMMWORD[32+rsp]
+	movaps	xmm9,XMMWORD[48+rsp]
+	movaps	xmm10,XMMWORD[64+rsp]
+	movaps	xmm11,XMMWORD[80+rsp]
+	movaps	xmm12,XMMWORD[96+rsp]
+	movaps	xmm13,XMMWORD[112+rsp]
+	movaps	xmm14,XMMWORD[128+rsp]
+	movaps	xmm15,XMMWORD[144+rsp]
+	add	rsp,0xa8
 	DB	0F3h,0C3h		;repret
+$L$SEH_end_rsaz_512_gather4:
 
+
+ALIGN	64
+$L$inc:
+	DD	0,0,1,1
+	DD	2,2,2,2
 EXTERN	__imp_RtlVirtualUnwind
 
 ALIGN	16
@@ -1221,6 +1367,18 @@ se_handler:
 
 	lea	rax,[((128+24+48))+rax]
 
+	lea	rbx,[$L$mul_gather4_epilogue]
+	cmp	rbx,r10
+	jne	NEAR $L$se_not_in_mul_gather4
+
+	lea	rax,[176+rax]
+
+	lea	rsi,[((-48-168))+rax]
+	lea	rdi,[512+r8]
+	mov	ecx,20
+	DD	0xa548f3fc
+
+$L$se_not_in_mul_gather4:
 	mov	rbx,QWORD[((-8))+rax]
 	mov	rbp,QWORD[((-16))+rax]
 	mov	r12,QWORD[((-24))+rax]
@@ -1296,6 +1454,10 @@ ALIGN	4
 	DD	$L$SEH_end_rsaz_512_mul_by_one wrt ..imagebase
 	DD	$L$SEH_info_rsaz_512_mul_by_one wrt ..imagebase
 
+	DD	$L$SEH_begin_rsaz_512_gather4 wrt ..imagebase
+	DD	$L$SEH_end_rsaz_512_gather4 wrt ..imagebase
+	DD	$L$SEH_info_rsaz_512_gather4 wrt ..imagebase
+
 section	.xdata rdata align=8
 ALIGN	8
 $L$SEH_info_rsaz_512_sqr:
@@ -1318,3 +1480,16 @@ $L$SEH_info_rsaz_512_mul_by_one:
 DB	9,0,0,0
 	DD	se_handler wrt ..imagebase
 	DD	$L$mul_by_one_body wrt ..imagebase,$L$mul_by_one_epilogue wrt ..imagebase
+$L$SEH_info_rsaz_512_gather4:
+DB	0x01,0x46,0x16,0x00
+DB	0x46,0xf8,0x09,0x00
+DB	0x3d,0xe8,0x08,0x00
+DB	0x34,0xd8,0x07,0x00
+DB	0x2e,0xc8,0x06,0x00
+DB	0x28,0xb8,0x05,0x00
+DB	0x22,0xa8,0x04,0x00
+DB	0x1c,0x98,0x03,0x00
+DB	0x16,0x88,0x02,0x00
+DB	0x10,0x78,0x01,0x00
+DB	0x0b,0x68,0x00,0x00
+DB	0x07,0x01,0x15,0x00
diff --git a/packager/third_party/boringssl/win-x86_64/crypto/bn/x86_64-mont.asm b/packager/third_party/boringssl/win-x86_64/crypto/bn/x86_64-mont.asm
index db0d1b976f..4d8e1cb72a 100644
--- a/packager/third_party/boringssl/win-x86_64/crypto/bn/x86_64-mont.asm
+++ b/packager/third_party/boringssl/win-x86_64/crypto/bn/x86_64-mont.asm
@@ -677,20 +677,20 @@ $L$sqr8x_enter:
 
 
 
-	lea	r11,[((-64))+r9*4+rsp]
+	lea	r11,[((-64))+r9*2+rsp]
 	mov	r8,QWORD[r8]
 	sub	r11,rsi
 	and	r11,4095
 	cmp	r10,r11
 	jb	NEAR $L$sqr8x_sp_alt
 	sub	rsp,r11
-	lea	rsp,[((-64))+r9*4+rsp]
+	lea	rsp,[((-64))+r9*2+rsp]
 	jmp	NEAR $L$sqr8x_sp_done
 
 ALIGN	32
 $L$sqr8x_sp_alt:
-	lea	r10,[((4096-64))+r9*4]
-	lea	rsp,[((-64))+r9*4+rsp]
+	lea	r10,[((4096-64))+r9*2]
+	lea	rsp,[((-64))+r9*2+rsp]
 	sub	r11,r10
 	mov	r10,0
 	cmovc	r11,r10
@@ -700,58 +700,80 @@ $L$sqr8x_sp_done:
 	mov	r10,r9
 	neg	r9
 
-	lea	r11,[64+r9*2+rsp]
 	mov	QWORD[32+rsp],r8
 	mov	QWORD[40+rsp],rax
 $L$sqr8x_body:
 
-	mov	rbp,r9
-DB	102,73,15,110,211
-	shr	rbp,3+2
-	mov	eax,DWORD[((OPENSSL_ia32cap_P+8))]
-	jmp	NEAR $L$sqr8x_copy_n
-
-ALIGN	32
-$L$sqr8x_copy_n:
-	movq	xmm0,QWORD[rcx]
-	movq	xmm1,QWORD[8+rcx]
-	movq	xmm3,QWORD[16+rcx]
-	movq	xmm4,QWORD[24+rcx]
-	lea	rcx,[32+rcx]
-	movdqa	XMMWORD[r11],xmm0
-	movdqa	XMMWORD[16+r11],xmm1
-	movdqa	XMMWORD[32+r11],xmm3
-	movdqa	XMMWORD[48+r11],xmm4
-	lea	r11,[64+r11]
-	dec	rbp
-	jnz	NEAR $L$sqr8x_copy_n
-
+DB	102,72,15,110,209
 	pxor	xmm0,xmm0
 DB	102,72,15,110,207
 DB	102,73,15,110,218
 	call	bn_sqr8x_internal
 
-	pxor	xmm0,xmm0
-	lea	rax,[48+rsp]
-	lea	rdx,[64+r9*2+rsp]
-	shr	r9,3+2
-	mov	rsi,QWORD[40+rsp]
-	jmp	NEAR $L$sqr8x_zero
+
+
+
+	lea	rbx,[r9*1+rdi]
+	mov	rcx,r9
+	mov	rdx,r9
+DB	102,72,15,126,207
+	sar	rcx,3+2
+	jmp	NEAR $L$sqr8x_sub
 
 ALIGN	32
-$L$sqr8x_zero:
-	movdqa	XMMWORD[rax],xmm0
-	movdqa	XMMWORD[16+rax],xmm0
-	movdqa	XMMWORD[32+rax],xmm0
-	movdqa	XMMWORD[48+rax],xmm0
-	lea	rax,[64+rax]
-	movdqa	XMMWORD[rdx],xmm0
-	movdqa	XMMWORD[16+rdx],xmm0
-	movdqa	XMMWORD[32+rdx],xmm0
-	movdqa	XMMWORD[48+rdx],xmm0
-	lea	rdx,[64+rdx]
-	dec	r9
-	jnz	NEAR $L$sqr8x_zero
+$L$sqr8x_sub:
+	mov	r12,QWORD[rbx]
+	mov	r13,QWORD[8+rbx]
+	mov	r14,QWORD[16+rbx]
+	mov	r15,QWORD[24+rbx]
+	lea	rbx,[32+rbx]
+	sbb	r12,QWORD[rbp]
+	sbb	r13,QWORD[8+rbp]
+	sbb	r14,QWORD[16+rbp]
+	sbb	r15,QWORD[24+rbp]
+	lea	rbp,[32+rbp]
+	mov	QWORD[rdi],r12
+	mov	QWORD[8+rdi],r13
+	mov	QWORD[16+rdi],r14
+	mov	QWORD[24+rdi],r15
+	lea	rdi,[32+rdi]
+	inc	rcx
+	jnz	NEAR $L$sqr8x_sub
+
+	sbb	rax,0
+	lea	rbx,[r9*1+rbx]
+	lea	rdi,[r9*1+rdi]
+
+DB	102,72,15,110,200
+	pxor	xmm0,xmm0
+	pshufd	xmm1,xmm1,0
+	mov	rsi,QWORD[40+rsp]
+	jmp	NEAR $L$sqr8x_cond_copy
+
+ALIGN	32
+$L$sqr8x_cond_copy:
+	movdqa	xmm2,XMMWORD[rbx]
+	movdqa	xmm3,XMMWORD[16+rbx]
+	lea	rbx,[32+rbx]
+	movdqu	xmm4,XMMWORD[rdi]
+	movdqu	xmm5,XMMWORD[16+rdi]
+	lea	rdi,[32+rdi]
+	movdqa	XMMWORD[(-32)+rbx],xmm0
+	movdqa	XMMWORD[(-16)+rbx],xmm0
+	movdqa	XMMWORD[(-32)+rdx*1+rbx],xmm0
+	movdqa	XMMWORD[(-16)+rdx*1+rbx],xmm0
+	pcmpeqd	xmm0,xmm1
+	pand	xmm2,xmm1
+	pand	xmm3,xmm1
+	pand	xmm4,xmm0
+	pand	xmm5,xmm0
+	pxor	xmm0,xmm0
+	por	xmm4,xmm2
+	por	xmm5,xmm3
+	movdqu	XMMWORD[(-32)+rdi],xmm4
+	movdqu	XMMWORD[(-16)+rdi],xmm5
+	add	r9,32
+	jnz	NEAR $L$sqr8x_cond_copy
 
 	mov	rax,1
 	mov	r15,QWORD[((-48))+rsi]
diff --git a/packager/third_party/boringssl/win-x86_64/crypto/bn/x86_64-mont5.asm b/packager/third_party/boringssl/win-x86_64/crypto/bn/x86_64-mont5.asm
index 284318aae3..cd9a6e5d4e 100644
--- a/packager/third_party/boringssl/win-x86_64/crypto/bn/x86_64-mont5.asm
+++ b/packager/third_party/boringssl/win-x86_64/crypto/bn/x86_64-mont5.asm
@@ -31,49 +31,151 @@ ALIGN	16
 $L$mul_enter:
 	mov	r9d,r9d
 	mov	rax,rsp
-	mov	r10d,DWORD[56+rsp]
+	movd	xmm5,DWORD[56+rsp]
+	lea	r10,[$L$inc]
 	push	rbx
 	push	rbp
 	push	r12
 	push	r13
 	push	r14
 	push	r15
-	lea	rsp,[((-40))+rsp]
-	movaps	XMMWORD[rsp],xmm6
-	movaps	XMMWORD[16+rsp],xmm7
+
 	lea	r11,[2+r9]
 	neg	r11
-	lea	rsp,[r11*8+rsp]
+	lea	rsp,[((-264))+r11*8+rsp]
 	and	rsp,-1024
 
 	mov	QWORD[8+r9*8+rsp],rax
 $L$mul_body:
-	mov	r12,rdx
-	mov	r11,r10
-	shr	r10,3
-	and	r11,7
-	not	r10
-	lea	rax,[$L$magic_masks]
-	and	r10,3
-	lea	r12,[96+r11*8+r12]
-	movq	xmm4,QWORD[r10*8+rax]
-	movq	xmm5,QWORD[8+r10*8+rax]
-	movq	xmm6,QWORD[16+r10*8+rax]
-	movq	xmm7,QWORD[24+r10*8+rax]
+	lea	r12,[128+rdx]
+	movdqa	xmm0,XMMWORD[r10]
+	movdqa	xmm1,XMMWORD[16+r10]
+	lea	r10,[((24-112))+r9*8+rsp]
+	and	r10,-16
 
-	movq	xmm0,QWORD[(((-96)))+r12]
-	movq	xmm1,QWORD[((-32))+r12]
-	pand	xmm0,xmm4
-	movq	xmm2,QWORD[32+r12]
-	pand	xmm1,xmm5
-	movq	xmm3,QWORD[96+r12]
-	pand	xmm2,xmm6
-	por	xmm0,xmm1
-	pand	xmm3,xmm7
+	pshufd	xmm5,xmm5,0
+	movdqa	xmm4,xmm1
+	movdqa	xmm2,xmm1
+	paddd	xmm1,xmm0
+	pcmpeqd	xmm0,xmm5
+DB	0x67
+	movdqa	xmm3,xmm4
+	paddd	xmm2,xmm1
+	pcmpeqd	xmm1,xmm5
+	movdqa	XMMWORD[112+r10],xmm0
+	movdqa	xmm0,xmm4
+
+	paddd	xmm3,xmm2
+	pcmpeqd	xmm2,xmm5
+	movdqa	XMMWORD[128+r10],xmm1
+	movdqa	xmm1,xmm4
+
+	paddd	xmm0,xmm3
+	pcmpeqd	xmm3,xmm5
+	movdqa	XMMWORD[144+r10],xmm2
+	movdqa	xmm2,xmm4
+
+	paddd	xmm1,xmm0
+	pcmpeqd	xmm0,xmm5
+	movdqa	XMMWORD[160+r10],xmm3
+	movdqa	xmm3,xmm4
+	paddd	xmm2,xmm1
+	pcmpeqd	xmm1,xmm5
+	movdqa	XMMWORD[176+r10],xmm0
+	movdqa	xmm0,xmm4
+
+	paddd	xmm3,xmm2
+	pcmpeqd	xmm2,xmm5
+	movdqa	XMMWORD[192+r10],xmm1
+	movdqa	xmm1,xmm4
+
+	paddd	xmm0,xmm3
+	pcmpeqd	xmm3,xmm5
+	movdqa	XMMWORD[208+r10],xmm2
+	movdqa	xmm2,xmm4
+
+	paddd	xmm1,xmm0
+	pcmpeqd	xmm0,xmm5
+	movdqa	XMMWORD[224+r10],xmm3
+	movdqa	xmm3,xmm4
+	paddd	xmm2,xmm1
+	pcmpeqd	xmm1,xmm5
+	movdqa	XMMWORD[240+r10],xmm0
+	movdqa	xmm0,xmm4
+
+	paddd	xmm3,xmm2
+	pcmpeqd	xmm2,xmm5
+	movdqa	XMMWORD[256+r10],xmm1
+	movdqa	xmm1,xmm4
+
+	paddd	xmm0,xmm3
+	pcmpeqd	xmm3,xmm5
+	movdqa	XMMWORD[272+r10],xmm2
+	movdqa	xmm2,xmm4
+
+	paddd	xmm1,xmm0
+	pcmpeqd	xmm0,xmm5
+	movdqa	XMMWORD[288+r10],xmm3
+	movdqa	xmm3,xmm4
+	paddd	xmm2,xmm1
+	pcmpeqd	xmm1,xmm5
+	movdqa	XMMWORD[304+r10],xmm0
+
+	paddd	xmm3,xmm2
+DB	0x67
+	pcmpeqd	xmm2,xmm5
+	movdqa	XMMWORD[320+r10],xmm1
+
+	pcmpeqd	xmm3,xmm5
+	movdqa	XMMWORD[336+r10],xmm2
+	pand	xmm0,XMMWORD[64+r12]
+
+	pand	xmm1,XMMWORD[80+r12]
+	pand	xmm2,XMMWORD[96+r12]
+	movdqa	XMMWORD[352+r10],xmm3
+	pand	xmm3,XMMWORD[112+r12]
 	por	xmm0,xmm2
+	por	xmm1,xmm3
+	movdqa	xmm4,XMMWORD[((-128))+r12]
+	movdqa	xmm5,XMMWORD[((-112))+r12]
+	movdqa	xmm2,XMMWORD[((-96))+r12]
+	pand	xmm4,XMMWORD[112+r10]
+	movdqa	xmm3,XMMWORD[((-80))+r12]
+	pand	xmm5,XMMWORD[128+r10]
+	por	xmm0,xmm4
+	pand	xmm2,XMMWORD[144+r10]
+	por	xmm1,xmm5
+	pand	xmm3,XMMWORD[160+r10]
+	por	xmm0,xmm2
+	por	xmm1,xmm3
+	movdqa	xmm4,XMMWORD[((-64))+r12]
+	movdqa	xmm5,XMMWORD[((-48))+r12]
+	movdqa	xmm2,XMMWORD[((-32))+r12]
+	pand	xmm4,XMMWORD[176+r10]
+	movdqa	xmm3,XMMWORD[((-16))+r12]
+	pand	xmm5,XMMWORD[192+r10]
+	por	xmm0,xmm4
+	pand	xmm2,XMMWORD[208+r10]
+	por	xmm1,xmm5
+	pand	xmm3,XMMWORD[224+r10]
+	por	xmm0,xmm2
+	por	xmm1,xmm3
+	movdqa	xmm4,XMMWORD[r12]
+	movdqa	xmm5,XMMWORD[16+r12]
+	movdqa	xmm2,XMMWORD[32+r12]
+	pand	xmm4,XMMWORD[240+r10]
+	movdqa	xmm3,XMMWORD[48+r12]
+	pand	xmm5,XMMWORD[256+r10]
+	por	xmm0,xmm4
+	pand	xmm2,XMMWORD[272+r10]
+	por	xmm1,xmm5
+	pand	xmm3,XMMWORD[288+r10]
+	por	xmm0,xmm2
+	por	xmm1,xmm3
+	por	xmm0,xmm1
+	pshufd	xmm1,xmm0,0x4e
+	por	xmm0,xmm1
 	lea	r12,[256+r12]
-	por	xmm0,xmm3
-
 DB	102,72,15,126,195
 
 	mov	r8,QWORD[r8]
@@ -82,29 +184,14 @@ DB	102,72,15,126,195
 	xor	r14,r14
 	xor	r15,r15
 
-	movq	xmm0,QWORD[(((-96)))+r12]
-	movq	xmm1,QWORD[((-32))+r12]
-	pand	xmm0,xmm4
-	movq	xmm2,QWORD[32+r12]
-	pand	xmm1,xmm5
-
 	mov	rbp,r8
 	mul	rbx
 	mov	r10,rax
 	mov	rax,QWORD[rcx]
 
-	movq	xmm3,QWORD[96+r12]
-	pand	xmm2,xmm6
-	por	xmm0,xmm1
-	pand	xmm3,xmm7
-
 	imul	rbp,r10
 	mov	r11,rdx
 
-	por	xmm0,xmm2
-	lea	r12,[256+r12]
-	por	xmm0,xmm3
-
 	mul	rbp
 	add	r10,rax
 	mov	rax,QWORD[8+rsi]
@@ -137,14 +224,12 @@ $L$1st_enter:
 	cmp	r15,r9
 	jne	NEAR $L$1st
 
-DB	102,72,15,126,195
 
 	add	r13,rax
-	mov	rax,QWORD[rsi]
 	adc	rdx,0
 	add	r13,r11
 	adc	rdx,0
-	mov	QWORD[((-16))+r15*8+rsp],r13
+	mov	QWORD[((-16))+r9*8+rsp],r13
 	mov	r13,rdx
 	mov	r11,r10
 
@@ -158,33 +243,78 @@ DB	102,72,15,126,195
 	jmp	NEAR $L$outer
 ALIGN	16
 $L$outer:
+	lea	rdx,[((24+128))+r9*8+rsp]
+	and	rdx,-16
+	pxor	xmm4,xmm4
+	pxor	xmm5,xmm5
+	movdqa	xmm0,XMMWORD[((-128))+r12]
+	movdqa	xmm1,XMMWORD[((-112))+r12]
+	movdqa	xmm2,XMMWORD[((-96))+r12]
+	movdqa	xmm3,XMMWORD[((-80))+r12]
+	pand	xmm0,XMMWORD[((-128))+rdx]
+	pand	xmm1,XMMWORD[((-112))+rdx]
+	por	xmm4,xmm0
+	pand	xmm2,XMMWORD[((-96))+rdx]
+	por	xmm5,xmm1
+	pand	xmm3,XMMWORD[((-80))+rdx]
+	por	xmm4,xmm2
+	por	xmm5,xmm3
+	movdqa	xmm0,XMMWORD[((-64))+r12]
+	movdqa	xmm1,XMMWORD[((-48))+r12]
+	movdqa	xmm2,XMMWORD[((-32))+r12]
+	movdqa	xmm3,XMMWORD[((-16))+r12]
+	pand	xmm0,XMMWORD[((-64))+rdx]
+	pand	xmm1,XMMWORD[((-48))+rdx]
+	por	xmm4,xmm0
+	pand	xmm2,XMMWORD[((-32))+rdx]
+	por	xmm5,xmm1
+	pand	xmm3,XMMWORD[((-16))+rdx]
+	por	xmm4,xmm2
+	por	xmm5,xmm3
+	movdqa	xmm0,XMMWORD[r12]
+	movdqa	xmm1,XMMWORD[16+r12]
+	movdqa	xmm2,XMMWORD[32+r12]
+	movdqa	xmm3,XMMWORD[48+r12]
+	pand	xmm0,XMMWORD[rdx]
+	pand	xmm1,XMMWORD[16+rdx]
+	por	xmm4,xmm0
+	pand	xmm2,XMMWORD[32+rdx]
+	por	xmm5,xmm1
+	pand	xmm3,XMMWORD[48+rdx]
+	por	xmm4,xmm2
+	por	xmm5,xmm3
+	movdqa	xmm0,XMMWORD[64+r12]
+	movdqa	xmm1,XMMWORD[80+r12]
+	movdqa	xmm2,XMMWORD[96+r12]
+	movdqa	xmm3,XMMWORD[112+r12]
+	pand	xmm0,XMMWORD[64+rdx]
+	pand	xmm1,XMMWORD[80+rdx]
+	por	xmm4,xmm0
+	pand	xmm2,XMMWORD[96+rdx]
+	por	xmm5,xmm1
+	pand	xmm3,XMMWORD[112+rdx]
+	por	xmm4,xmm2
+	por	xmm5,xmm3
+	por	xmm4,xmm5
+	pshufd	xmm0,xmm4,0x4e
+	por	xmm0,xmm4
+	lea	r12,[256+r12]
+
+	mov	rax,QWORD[rsi]
+DB	102,72,15,126,195
+
 	xor	r15,r15
 	mov	rbp,r8
 	mov	r10,QWORD[rsp]
 
-	movq	xmm0,QWORD[(((-96)))+r12]
-	movq	xmm1,QWORD[((-32))+r12]
-	pand	xmm0,xmm4
-	movq	xmm2,QWORD[32+r12]
-	pand	xmm1,xmm5
-
 	mul	rbx
 	add	r10,rax
 	mov	rax,QWORD[rcx]
 	adc	rdx,0
 
-	movq	xmm3,QWORD[96+r12]
-	pand	xmm2,xmm6
-	por	xmm0,xmm1
-	pand	xmm3,xmm7
-
 	imul	rbp,r10
 	mov	r11,rdx
 
-	por	xmm0,xmm2
-	lea	r12,[256+r12]
-	por	xmm0,xmm3
-
 	mul	rbp
 	add	r10,rax
 	mov	rax,QWORD[8+rsi]
@@ -220,15 +350,12 @@ $L$inner_enter:
 	cmp	r15,r9
 	jne	NEAR $L$inner
 
-DB	102,72,15,126,195
-
 	add	r13,rax
-	mov	rax,QWORD[rsi]
 	adc	rdx,0
 	add	r13,r10
-	mov	r10,QWORD[r15*8+rsp]
+	mov	r10,QWORD[r9*8+rsp]
 	adc	rdx,0
-	mov	QWORD[((-16))+r15*8+rsp],r13
+	mov	QWORD[((-16))+r9*8+rsp],r13
 	mov	r13,rdx
 
 	xor	rdx,rdx
@@ -274,8 +401,7 @@ $L$copy:
 
 	mov	rsi,QWORD[8+r9*8+rsp]
 	mov	rax,1
-	movaps	xmm6,XMMWORD[((-88))+rsi]
-	movaps	xmm7,XMMWORD[((-72))+rsi]
+
 	mov	r15,QWORD[((-48))+rsi]
 	mov	r14,QWORD[((-40))+rsi]
 	mov	r13,QWORD[((-32))+rsi]
@@ -312,13 +438,10 @@ DB	0x67
 	push	r13
 	push	r14
 	push	r15
-	lea	rsp,[((-40))+rsp]
-	movaps	XMMWORD[rsp],xmm6
-	movaps	XMMWORD[16+rsp],xmm7
+
 DB	0x67
-	mov	r10d,r9d
 	shl	r9d,3
-	shl	r10d,3+2
+	lea	r10,[r9*2+r9]
 	neg	r9
 
 
@@ -328,19 +451,21 @@ DB	0x67
 
 
 
-	lea	r11,[((-64))+r9*2+rsp]
-	sub	r11,rsi
+
+
+	lea	r11,[((-320))+r9*2+rsp]
+	sub	r11,rdi
 	and	r11,4095
 	cmp	r10,r11
 	jb	NEAR $L$mul4xsp_alt
 	sub	rsp,r11
-	lea	rsp,[((-64))+r9*2+rsp]
+	lea	rsp,[((-320))+r9*2+rsp]
 	jmp	NEAR $L$mul4xsp_done
 
 ALIGN	32
 $L$mul4xsp_alt:
-	lea	r10,[((4096-64))+r9*2]
-	lea	rsp,[((-64))+r9*2+rsp]
+	lea	r10,[((4096-320))+r9*2]
+	lea	rsp,[((-320))+r9*2+rsp]
 	sub	r11,r10
 	mov	r10,0
 	cmovc	r11,r10
@@ -356,8 +481,7 @@ $L$mul4x_body:
 
 	mov	rsi,QWORD[40+rsp]
 	mov	rax,1
-	movaps	xmm6,XMMWORD[((-88))+rsi]
-	movaps	xmm7,XMMWORD[((-72))+rsi]
+
 	mov	r15,QWORD[((-48))+rsi]
 	mov	r14,QWORD[((-40))+rsi]
 	mov	r13,QWORD[((-32))+rsi]
@@ -375,47 +499,141 @@ $L$SEH_end_bn_mul4x_mont_gather5:
 ALIGN	32
 mul4x_internal:
 	shl	r9,5
-	mov	r10d,DWORD[56+rax]
-	lea	r13,[256+r9*1+rdx]
+	movd	xmm5,DWORD[56+rax]
+	lea	rax,[$L$inc]
+	lea	r13,[128+r9*1+rdx]
 	shr	r9,5
-	mov	r11,r10
-	shr	r10,3
-	and	r11,7
-	not	r10
-	lea	rax,[$L$magic_masks]
-	and	r10,3
-	lea	r12,[96+r11*8+rdx]
-	movq	xmm4,QWORD[r10*8+rax]
-	movq	xmm5,QWORD[8+r10*8+rax]
-	add	r11,7
-	movq	xmm6,QWORD[16+r10*8+rax]
-	movq	xmm7,QWORD[24+r10*8+rax]
-	and	r11,7
+	movdqa	xmm0,XMMWORD[rax]
+	movdqa	xmm1,XMMWORD[16+rax]
+	lea	r10,[((88-112))+r9*1+rsp]
+	lea	r12,[128+rdx]
 
-	movq	xmm0,QWORD[(((-96)))+r12]
-	lea	r14,[256+r12]
-	movq	xmm1,QWORD[((-32))+r12]
-	pand	xmm0,xmm4
-	movq	xmm2,QWORD[32+r12]
-	pand	xmm1,xmm5
-	movq	xmm3,QWORD[96+r12]
-	pand	xmm2,xmm6
+	pshufd	xmm5,xmm5,0
+	movdqa	xmm4,xmm1
+DB	0x67,0x67
+	movdqa	xmm2,xmm1
+	paddd	xmm1,xmm0
+	pcmpeqd	xmm0,xmm5
 DB	0x67
-	por	xmm0,xmm1
-	movq	xmm1,QWORD[((-96))+r14]
-DB	0x67
-	pand	xmm3,xmm7
+	movdqa	xmm3,xmm4
+	paddd	xmm2,xmm1
+	pcmpeqd	xmm1,xmm5
+	movdqa	XMMWORD[112+r10],xmm0
+	movdqa	xmm0,xmm4
+
+	paddd	xmm3,xmm2
+	pcmpeqd	xmm2,xmm5
+	movdqa	XMMWORD[128+r10],xmm1
+	movdqa	xmm1,xmm4
+
+	paddd	xmm0,xmm3
+	pcmpeqd	xmm3,xmm5
+	movdqa	XMMWORD[144+r10],xmm2
+	movdqa	xmm2,xmm4
+
+	paddd	xmm1,xmm0
+	pcmpeqd	xmm0,xmm5
+	movdqa	XMMWORD[160+r10],xmm3
+	movdqa	xmm3,xmm4
+	paddd	xmm2,xmm1
+	pcmpeqd	xmm1,xmm5
+	movdqa	XMMWORD[176+r10],xmm0
+	movdqa	xmm0,xmm4
+
+	paddd	xmm3,xmm2
+	pcmpeqd	xmm2,xmm5
+	movdqa	XMMWORD[192+r10],xmm1
+	movdqa	xmm1,xmm4
+
+	paddd	xmm0,xmm3
+	pcmpeqd	xmm3,xmm5
+	movdqa	XMMWORD[208+r10],xmm2
+	movdqa	xmm2,xmm4
+
+	paddd	xmm1,xmm0
+	pcmpeqd	xmm0,xmm5
+	movdqa	XMMWORD[224+r10],xmm3
+	movdqa	xmm3,xmm4
+	paddd	xmm2,xmm1
+	pcmpeqd	xmm1,xmm5
+	movdqa	XMMWORD[240+r10],xmm0
+	movdqa	xmm0,xmm4
+
+	paddd	xmm3,xmm2
+	pcmpeqd	xmm2,xmm5
+	movdqa	XMMWORD[256+r10],xmm1
+	movdqa	xmm1,xmm4
+
+	paddd	xmm0,xmm3
+	pcmpeqd	xmm3,xmm5
+	movdqa	XMMWORD[272+r10],xmm2
+	movdqa	xmm2,xmm4
+
+	paddd	xmm1,xmm0
+	pcmpeqd	xmm0,xmm5
+	movdqa	XMMWORD[288+r10],xmm3
+	movdqa	xmm3,xmm4
+	paddd	xmm2,xmm1
+	pcmpeqd	xmm1,xmm5
+	movdqa	XMMWORD[304+r10],xmm0
+
+	paddd	xmm3,xmm2
 DB	0x67
+	pcmpeqd	xmm2,xmm5
+	movdqa	XMMWORD[320+r10],xmm1
+
+	pcmpeqd	xmm3,xmm5
+	movdqa	XMMWORD[336+r10],xmm2
+	pand	xmm0,XMMWORD[64+r12]
+
+	pand	xmm1,XMMWORD[80+r12]
+	pand	xmm2,XMMWORD[96+r12]
+	movdqa	XMMWORD[352+r10],xmm3
+	pand	xmm3,XMMWORD[112+r12]
 	por	xmm0,xmm2
-	movq	xmm2,QWORD[((-32))+r14]
-DB	0x67
-	pand	xmm1,xmm4
-DB	0x67
-	por	xmm0,xmm3
-	movq	xmm3,QWORD[32+r14]
-
+	por	xmm1,xmm3
+	movdqa	xmm4,XMMWORD[((-128))+r12]
+	movdqa	xmm5,XMMWORD[((-112))+r12]
+	movdqa	xmm2,XMMWORD[((-96))+r12]
+	pand	xmm4,XMMWORD[112+r10]
+	movdqa	xmm3,XMMWORD[((-80))+r12]
+	pand	xmm5,XMMWORD[128+r10]
+	por	xmm0,xmm4
+	pand	xmm2,XMMWORD[144+r10]
+	por	xmm1,xmm5
+	pand	xmm3,XMMWORD[160+r10]
+	por	xmm0,xmm2
+	por	xmm1,xmm3
+	movdqa	xmm4,XMMWORD[((-64))+r12]
+	movdqa	xmm5,XMMWORD[((-48))+r12]
+	movdqa	xmm2,XMMWORD[((-32))+r12]
+	pand	xmm4,XMMWORD[176+r10]
+	movdqa	xmm3,XMMWORD[((-16))+r12]
+	pand	xmm5,XMMWORD[192+r10]
+	por	xmm0,xmm4
+	pand	xmm2,XMMWORD[208+r10]
+	por	xmm1,xmm5
+	pand	xmm3,XMMWORD[224+r10]
+	por	xmm0,xmm2
+	por	xmm1,xmm3
+	movdqa	xmm4,XMMWORD[r12]
+	movdqa	xmm5,XMMWORD[16+r12]
+	movdqa	xmm2,XMMWORD[32+r12]
+	pand	xmm4,XMMWORD[240+r10]
+	movdqa	xmm3,XMMWORD[48+r12]
+	pand	xmm5,XMMWORD[256+r10]
+	por	xmm0,xmm4
+	pand	xmm2,XMMWORD[272+r10]
+	por	xmm1,xmm5
+	pand	xmm3,XMMWORD[288+r10]
+	por	xmm0,xmm2
+	por	xmm1,xmm3
+	por	xmm0,xmm1
+	pshufd	xmm1,xmm0,0x4e
+	por	xmm0,xmm1
+	lea	r12,[256+r12]
 DB	102,72,15,126,195
-	movq	xmm0,QWORD[96+r14]
+
 	mov	QWORD[((16+8))+rsp],r13
 	mov	QWORD[((56+8))+rsp],rdi
 
@@ -429,26 +647,10 @@ DB	102,72,15,126,195
 	mov	r10,rax
 	mov	rax,QWORD[rcx]
 
-	pand	xmm2,xmm5
-	pand	xmm3,xmm6
-	por	xmm1,xmm2
-
 	imul	rbp,r10
-
-
-
-
-
-
-
-	lea	r14,[((64+8))+r11*8+rsp]
+	lea	r14,[((64+8))+rsp]
 	mov	r11,rdx
 
-	pand	xmm0,xmm7
-	por	xmm1,xmm3
-	lea	r12,[512+r12]
-	por	xmm0,xmm1
-
 	mul	rbp
 	add	r10,rax
 	mov	rax,QWORD[8+r9*1+rsi]
@@ -457,7 +659,7 @@ DB	102,72,15,126,195
 
 	mul	rbx
 	add	r11,rax
-	mov	rax,QWORD[16+rcx]
+	mov	rax,QWORD[8+rcx]
 	adc	rdx,0
 	mov	r10,rdx
 
@@ -467,7 +669,7 @@ DB	102,72,15,126,195
 	adc	rdx,0
 	add	rdi,r11
 	lea	r15,[32+r9]
-	lea	rcx,[64+rcx]
+	lea	rcx,[32+rcx]
 	adc	rdx,0
 	mov	QWORD[r14],rdi
 	mov	r13,rdx
@@ -477,7 +679,7 @@ ALIGN	32
 $L$1st4x:
 	mul	rbx
 	add	r10,rax
-	mov	rax,QWORD[((-32))+rcx]
+	mov	rax,QWORD[((-16))+rcx]
 	lea	r14,[32+r14]
 	adc	rdx,0
 	mov	r11,rdx
@@ -493,7 +695,7 @@ $L$1st4x:
 
 	mul	rbx
 	add	r11,rax
-	mov	rax,QWORD[((-16))+rcx]
+	mov	rax,QWORD[((-8))+rcx]
 	adc	rdx,0
 	mov	r10,rdx
 
@@ -523,7 +725,7 @@ $L$1st4x:
 
 	mul	rbx
 	add	r11,rax
-	mov	rax,QWORD[16+rcx]
+	mov	rax,QWORD[8+rcx]
 	adc	rdx,0
 	mov	r10,rdx
 
@@ -532,7 +734,7 @@ $L$1st4x:
 	mov	rax,QWORD[16+r15*1+rsi]
 	adc	rdx,0
 	add	rdi,r11
-	lea	rcx,[64+rcx]
+	lea	rcx,[32+rcx]
 	adc	rdx,0
 	mov	QWORD[r14],rdi
 	mov	r13,rdx
@@ -542,7 +744,7 @@ $L$1st4x:
 
 	mul	rbx
 	add	r10,rax
-	mov	rax,QWORD[((-32))+rcx]
+	mov	rax,QWORD[((-16))+rcx]
 	lea	r14,[32+r14]
 	adc	rdx,0
 	mov	r11,rdx
@@ -558,7 +760,7 @@ $L$1st4x:
 
 	mul	rbx
 	add	r11,rax
-	mov	rax,QWORD[((-16))+rcx]
+	mov	rax,QWORD[((-8))+rcx]
 	adc	rdx,0
 	mov	r10,rdx
 
@@ -571,8 +773,7 @@ $L$1st4x:
 	mov	QWORD[((-16))+r14],rdi
 	mov	r13,rdx
 
-DB	102,72,15,126,195
-	lea	rcx,[r9*2+rcx]
+	lea	rcx,[r9*1+rcx]
 
 	xor	rdi,rdi
 	add	r13,r10
@@ -583,6 +784,63 @@ DB	102,72,15,126,195
 
 ALIGN	32
 $L$outer4x:
+	lea	rdx,[((16+128))+r14]
+	pxor	xmm4,xmm4
+	pxor	xmm5,xmm5
+	movdqa	xmm0,XMMWORD[((-128))+r12]
+	movdqa	xmm1,XMMWORD[((-112))+r12]
+	movdqa	xmm2,XMMWORD[((-96))+r12]
+	movdqa	xmm3,XMMWORD[((-80))+r12]
+	pand	xmm0,XMMWORD[((-128))+rdx]
+	pand	xmm1,XMMWORD[((-112))+rdx]
+	por	xmm4,xmm0
+	pand	xmm2,XMMWORD[((-96))+rdx]
+	por	xmm5,xmm1
+	pand	xmm3,XMMWORD[((-80))+rdx]
+	por	xmm4,xmm2
+	por	xmm5,xmm3
+	movdqa	xmm0,XMMWORD[((-64))+r12]
+	movdqa	xmm1,XMMWORD[((-48))+r12]
+	movdqa	xmm2,XMMWORD[((-32))+r12]
+	movdqa	xmm3,XMMWORD[((-16))+r12]
+	pand	xmm0,XMMWORD[((-64))+rdx]
+	pand	xmm1,XMMWORD[((-48))+rdx]
+	por	xmm4,xmm0
+	pand	xmm2,XMMWORD[((-32))+rdx]
+	por	xmm5,xmm1
+	pand	xmm3,XMMWORD[((-16))+rdx]
+	por	xmm4,xmm2
+	por	xmm5,xmm3
+	movdqa	xmm0,XMMWORD[r12]
+	movdqa	xmm1,XMMWORD[16+r12]
+	movdqa	xmm2,XMMWORD[32+r12]
+	movdqa	xmm3,XMMWORD[48+r12]
+	pand	xmm0,XMMWORD[rdx]
+	pand	xmm1,XMMWORD[16+rdx]
+	por	xmm4,xmm0
+	pand	xmm2,XMMWORD[32+rdx]
+	por	xmm5,xmm1
+	pand	xmm3,XMMWORD[48+rdx]
+	por	xmm4,xmm2
+	por	xmm5,xmm3
+	movdqa	xmm0,XMMWORD[64+r12]
+	movdqa	xmm1,XMMWORD[80+r12]
+	movdqa	xmm2,XMMWORD[96+r12]
+	movdqa	xmm3,XMMWORD[112+r12]
+	pand	xmm0,XMMWORD[64+rdx]
+	pand	xmm1,XMMWORD[80+rdx]
+	por	xmm4,xmm0
+	pand	xmm2,XMMWORD[96+rdx]
+	por	xmm5,xmm1
+	pand	xmm3,XMMWORD[112+rdx]
+	por	xmm4,xmm2
+	por	xmm5,xmm3
+	por	xmm4,xmm5
+	pshufd	xmm0,xmm4,0x4e
+	por	xmm0,xmm4
+	lea	r12,[256+r12]
+DB	102,72,15,126,195
+
 	mov	r10,QWORD[r9*1+r14]
 	mov	rbp,r8
 	mul	rbx
@@ -590,25 +848,11 @@ $L$outer4x:
 	mov	rax,QWORD[rcx]
 	adc	rdx,0
 
-	movq	xmm0,QWORD[(((-96)))+r12]
-	movq	xmm1,QWORD[((-32))+r12]
-	pand	xmm0,xmm4
-	movq	xmm2,QWORD[32+r12]
-	pand	xmm1,xmm5
-	movq	xmm3,QWORD[96+r12]
-
 	imul	rbp,r10
-DB	0x67
 	mov	r11,rdx
 	mov	QWORD[r14],rdi
 
-	pand	xmm2,xmm6
-	por	xmm0,xmm1
-	pand	xmm3,xmm7
-	por	xmm0,xmm2
 	lea	r14,[r9*1+r14]
-	lea	r12,[256+r12]
-	por	xmm0,xmm3
 
 	mul	rbp
 	add	r10,rax
@@ -618,7 +862,7 @@ DB	0x67
 
 	mul	rbx
 	add	r11,rax
-	mov	rax,QWORD[16+rcx]
+	mov	rax,QWORD[8+rcx]
 	adc	rdx,0
 	add	r11,QWORD[8+r14]
 	adc	rdx,0
@@ -630,7 +874,7 @@ DB	0x67
 	adc	rdx,0
 	add	rdi,r11
 	lea	r15,[32+r9]
-	lea	rcx,[64+rcx]
+	lea	rcx,[32+rcx]
 	adc	rdx,0
 	mov	r13,rdx
 	jmp	NEAR $L$inner4x
@@ -639,7 +883,7 @@ ALIGN	32
 $L$inner4x:
 	mul	rbx
 	add	r10,rax
-	mov	rax,QWORD[((-32))+rcx]
+	mov	rax,QWORD[((-16))+rcx]
 	adc	rdx,0
 	add	r10,QWORD[16+r14]
 	lea	r14,[32+r14]
@@ -657,7 +901,7 @@ $L$inner4x:
 
 	mul	rbx
 	add	r11,rax
-	mov	rax,QWORD[((-16))+rcx]
+	mov	rax,QWORD[((-8))+rcx]
 	adc	rdx,0
 	add	r11,QWORD[((-8))+r14]
 	adc	rdx,0
@@ -691,7 +935,7 @@ $L$inner4x:
 
 	mul	rbx
 	add	r11,rax
-	mov	rax,QWORD[16+rcx]
+	mov	rax,QWORD[8+rcx]
 	adc	rdx,0
 	add	r11,QWORD[8+r14]
 	adc	rdx,0
@@ -702,7 +946,7 @@ $L$inner4x:
 	mov	rax,QWORD[16+r15*1+rsi]
 	adc	rdx,0
 	add	rdi,r11
-	lea	rcx,[64+rcx]
+	lea	rcx,[32+rcx]
 	adc	rdx,0
 	mov	QWORD[((-8))+r14],r13
 	mov	r13,rdx
@@ -712,7 +956,7 @@ $L$inner4x:
 
 	mul	rbx
 	add	r10,rax
-	mov	rax,QWORD[((-32))+rcx]
+	mov	rax,QWORD[((-16))+rcx]
 	adc	rdx,0
 	add	r10,QWORD[16+r14]
 	lea	r14,[32+r14]
@@ -731,7 +975,7 @@ $L$inner4x:
 	mul	rbx
 	add	r11,rax
 	mov	rax,rbp
-	mov	rbp,QWORD[((-16))+rcx]
+	mov	rbp,QWORD[((-8))+rcx]
 	adc	rdx,0
 	add	r11,QWORD[((-8))+r14]
 	adc	rdx,0
@@ -746,9 +990,8 @@ $L$inner4x:
 	mov	QWORD[((-24))+r14],r13
 	mov	r13,rdx
 
-DB	102,72,15,126,195
 	mov	QWORD[((-16))+r14],rdi
-	lea	rcx,[r9*2+rcx]
+	lea	rcx,[r9*1+rcx]
 
 	xor	rdi,rdi
 	add	r13,r10
@@ -759,16 +1002,23 @@ DB	102,72,15,126,195
 
 	cmp	r12,QWORD[((16+8))+rsp]
 	jb	NEAR $L$outer4x
+	xor	rax,rax
 	sub	rbp,r13
 	adc	r15,r15
 	or	rdi,r15
-	xor	rdi,1
+	sub	rax,rdi
 	lea	rbx,[r9*1+r14]
-	lea	rbp,[rdi*8+rcx]
+	mov	r12,QWORD[rcx]
+	lea	rbp,[rcx]
 	mov	rcx,r9
 	sar	rcx,3+2
 	mov	rdi,QWORD[((56+8))+rsp]
-	jmp	NEAR $L$sqr4x_sub
+	dec	r12
+	xor	r10,r10
+	mov	r13,QWORD[8+rbp]
+	mov	r14,QWORD[16+rbp]
+	mov	r15,QWORD[24+rbp]
+	jmp	NEAR $L$sqr4x_sub_entry
 
 global	bn_power5
 
@@ -793,12 +1043,9 @@ $L$SEH_begin_bn_power5:
 	push	r13
 	push	r14
 	push	r15
-	lea	rsp,[((-40))+rsp]
-	movaps	XMMWORD[rsp],xmm6
-	movaps	XMMWORD[16+rsp],xmm7
-	mov	r10d,r9d
+
 	shl	r9d,3
-	shl	r10d,3+2
+	lea	r10d,[r9*2+r9]
 	neg	r9
 	mov	r8,QWORD[r8]
 
@@ -808,19 +1055,20 @@ $L$SEH_begin_bn_power5:
 
 
 
-	lea	r11,[((-64))+r9*2+rsp]
-	sub	r11,rsi
+
+	lea	r11,[((-320))+r9*2+rsp]
+	sub	r11,rdi
 	and	r11,4095
 	cmp	r10,r11
 	jb	NEAR $L$pwr_sp_alt
 	sub	rsp,r11
-	lea	rsp,[((-64))+r9*2+rsp]
+	lea	rsp,[((-320))+r9*2+rsp]
 	jmp	NEAR $L$pwr_sp_done
 
 ALIGN	32
 $L$pwr_sp_alt:
-	lea	r10,[((4096-64))+r9*2]
-	lea	rsp,[((-64))+r9*2+rsp]
+	lea	r10,[((4096-320))+r9*2]
+	lea	rsp,[((-320))+r9*2+rsp]
 	sub	r11,r10
 	mov	r10,0
 	cmovc	r11,r10
@@ -848,10 +1096,15 @@ DB	102,73,15,110,218
 DB	102,72,15,110,226
 
 	call	__bn_sqr8x_internal
+	call	__bn_post4x_internal
 	call	__bn_sqr8x_internal
+	call	__bn_post4x_internal
 	call	__bn_sqr8x_internal
+	call	__bn_post4x_internal
 	call	__bn_sqr8x_internal
+	call	__bn_post4x_internal
 	call	__bn_sqr8x_internal
+	call	__bn_post4x_internal
 
 DB	102,72,15,126,209
 DB	102,72,15,126,226
@@ -1397,9 +1650,9 @@ DB	0x67
 	mov	QWORD[((-16))+rdi],rbx
 	mov	QWORD[((-8))+rdi],r8
 DB	102,72,15,126,213
-sqr8x_reduction:
+__bn_sqr8x_reduction:
 	xor	rax,rax
-	lea	rcx,[r9*2+rbp]
+	lea	rcx,[rbp*1+r9]
 	lea	rdx,[((48+8))+r9*2+rsp]
 	mov	QWORD[((0+8))+rsp],rcx
 	lea	rdi,[((48+8))+r9*1+rsp]
@@ -1432,14 +1685,14 @@ DB	0x67
 ALIGN	32
 $L$8x_reduce:
 	mul	rbx
-	mov	rax,QWORD[16+rbp]
+	mov	rax,QWORD[8+rbp]
 	neg	r8
 	mov	r8,rdx
 	adc	r8,0
 
 	mul	rbx
 	add	r9,rax
-	mov	rax,QWORD[32+rbp]
+	mov	rax,QWORD[16+rbp]
 	adc	rdx,0
 	add	r8,r9
 	mov	QWORD[((48-8+8))+rcx*8+rsp],rbx
@@ -1448,7 +1701,7 @@ $L$8x_reduce:
 
 	mul	rbx
 	add	r10,rax
-	mov	rax,QWORD[48+rbp]
+	mov	rax,QWORD[24+rbp]
 	adc	rdx,0
 	add	r9,r10
 	mov	rsi,QWORD[((32+8))+rsp]
@@ -1457,7 +1710,7 @@ $L$8x_reduce:
 
 	mul	rbx
 	add	r11,rax
-	mov	rax,QWORD[64+rbp]
+	mov	rax,QWORD[32+rbp]
 	adc	rdx,0
 	imul	rsi,r8
 	add	r10,r11
@@ -1466,7 +1719,7 @@ $L$8x_reduce:
 
 	mul	rbx
 	add	r12,rax
-	mov	rax,QWORD[80+rbp]
+	mov	rax,QWORD[40+rbp]
 	adc	rdx,0
 	add	r11,r12
 	mov	r12,rdx
@@ -1474,7 +1727,7 @@ $L$8x_reduce:
 
 	mul	rbx
 	add	r13,rax
-	mov	rax,QWORD[96+rbp]
+	mov	rax,QWORD[48+rbp]
 	adc	rdx,0
 	add	r12,r13
 	mov	r13,rdx
@@ -1482,7 +1735,7 @@ $L$8x_reduce:
 
 	mul	rbx
 	add	r14,rax
-	mov	rax,QWORD[112+rbp]
+	mov	rax,QWORD[56+rbp]
 	adc	rdx,0
 	add	r13,r14
 	mov	r14,rdx
@@ -1500,7 +1753,7 @@ $L$8x_reduce:
 	dec	ecx
 	jnz	NEAR $L$8x_reduce
 
-	lea	rbp,[128+rbp]
+	lea	rbp,[64+rbp]
 	xor	rax,rax
 	mov	rdx,QWORD[((8+8))+rsp]
 	cmp	rbp,QWORD[((0+8))+rsp]
@@ -1526,14 +1779,14 @@ ALIGN	32
 $L$8x_tail:
 	mul	rbx
 	add	r8,rax
-	mov	rax,QWORD[16+rbp]
+	mov	rax,QWORD[8+rbp]
 	mov	QWORD[rdi],r8
 	mov	r8,rdx
 	adc	r8,0
 
 	mul	rbx
 	add	r9,rax
-	mov	rax,QWORD[32+rbp]
+	mov	rax,QWORD[16+rbp]
 	adc	rdx,0
 	add	r8,r9
 	lea	rdi,[8+rdi]
@@ -1542,7 +1795,7 @@ $L$8x_tail:
 
 	mul	rbx
 	add	r10,rax
-	mov	rax,QWORD[48+rbp]
+	mov	rax,QWORD[24+rbp]
 	adc	rdx,0
 	add	r9,r10
 	mov	r10,rdx
@@ -1550,7 +1803,7 @@ $L$8x_tail:
 
 	mul	rbx
 	add	r11,rax
-	mov	rax,QWORD[64+rbp]
+	mov	rax,QWORD[32+rbp]
 	adc	rdx,0
 	add	r10,r11
 	mov	r11,rdx
@@ -1558,7 +1811,7 @@ $L$8x_tail:
 
 	mul	rbx
 	add	r12,rax
-	mov	rax,QWORD[80+rbp]
+	mov	rax,QWORD[40+rbp]
 	adc	rdx,0
 	add	r11,r12
 	mov	r12,rdx
@@ -1566,7 +1819,7 @@ $L$8x_tail:
 
 	mul	rbx
 	add	r13,rax
-	mov	rax,QWORD[96+rbp]
+	mov	rax,QWORD[48+rbp]
 	adc	rdx,0
 	add	r12,r13
 	mov	r13,rdx
@@ -1574,7 +1827,7 @@ $L$8x_tail:
 
 	mul	rbx
 	add	r14,rax
-	mov	rax,QWORD[112+rbp]
+	mov	rax,QWORD[56+rbp]
 	adc	rdx,0
 	add	r13,r14
 	mov	r14,rdx
@@ -1592,7 +1845,7 @@ $L$8x_tail:
 	dec	ecx
 	jnz	NEAR $L$8x_tail
 
-	lea	rbp,[128+rbp]
+	lea	rbp,[64+rbp]
 	mov	rdx,QWORD[((8+8))+rsp]
 	cmp	rbp,QWORD[((0+8))+rsp]
 	jae	NEAR $L$8x_tail_done
@@ -1616,6 +1869,15 @@ $L$8x_tail:
 ALIGN	32
 $L$8x_tail_done:
 	add	r8,QWORD[rdx]
+	adc	r9,0
+	adc	r10,0
+	adc	r11,0
+	adc	r12,0
+	adc	r13,0
+	adc	r14,0
+	adc	r15,0
+
+
 	xor	rax,rax
 
 	neg	rsi
@@ -1629,7 +1891,7 @@ $L$8x_no_tail:
 	adc	r14,QWORD[48+rdi]
 	adc	r15,QWORD[56+rdi]
 	adc	rax,0
-	mov	rcx,QWORD[((-16))+rbp]
+	mov	rcx,QWORD[((-8))+rbp]
 	xor	rsi,rsi
 
 DB	102,72,15,126,213
@@ -1647,40 +1909,58 @@ DB	102,73,15,126,217
 
 	cmp	rdi,rdx
 	jb	NEAR $L$8x_reduction_loop
+	DB	0F3h,0C3h		;repret
 
-	sub	rcx,r15
-	lea	rbx,[r9*1+rdi]
-	adc	rsi,rsi
-	mov	rcx,r9
-	or	rax,rsi
-DB	102,72,15,126,207
-	xor	rax,1
-DB	102,72,15,126,206
-	lea	rbp,[rax*8+rbp]
-	sar	rcx,3+2
-	jmp	NEAR $L$sqr4x_sub
 
 ALIGN	32
+__bn_post4x_internal:
+	mov	r12,QWORD[rbp]
+	lea	rbx,[r9*1+rdi]
+	mov	rcx,r9
+DB	102,72,15,126,207
+	neg	rax
+DB	102,72,15,126,206
+	sar	rcx,3+2
+	dec	r12
+	xor	r10,r10
+	mov	r13,QWORD[8+rbp]
+	mov	r14,QWORD[16+rbp]
+	mov	r15,QWORD[24+rbp]
+	jmp	NEAR $L$sqr4x_sub_entry
+
+ALIGN	16
 $L$sqr4x_sub:
-DB	0x66
-	mov	r12,QWORD[rbx]
-	mov	r13,QWORD[8+rbx]
-	sbb	r12,QWORD[rbp]
-	mov	r14,QWORD[16+rbx]
-	sbb	r13,QWORD[16+rbp]
-	mov	r15,QWORD[24+rbx]
-	lea	rbx,[32+rbx]
-	sbb	r14,QWORD[32+rbp]
+	mov	r12,QWORD[rbp]
+	mov	r13,QWORD[8+rbp]
+	mov	r14,QWORD[16+rbp]
+	mov	r15,QWORD[24+rbp]
+$L$sqr4x_sub_entry:
+	lea	rbp,[32+rbp]
+	not	r12
+	not	r13
+	not	r14
+	not	r15
+	and	r12,rax
+	and	r13,rax
+	and	r14,rax
+	and	r15,rax
+
+	neg	r10
+	adc	r12,QWORD[rbx]
+	adc	r13,QWORD[8+rbx]
+	adc	r14,QWORD[16+rbx]
+	adc	r15,QWORD[24+rbx]
 	mov	QWORD[rdi],r12
-	sbb	r15,QWORD[48+rbp]
-	lea	rbp,[64+rbp]
+	lea	rbx,[32+rbx]
 	mov	QWORD[8+rdi],r13
+	sbb	r10,r10
 	mov	QWORD[16+rdi],r14
 	mov	QWORD[24+rdi],r15
 	lea	rdi,[32+rdi]
 
 	inc	rcx
 	jnz	NEAR $L$sqr4x_sub
+
 	mov	r10,r9
 	neg	r9
 	DB	0F3h,0C3h		;repret
@@ -1718,13 +1998,9 @@ DB	0x67
 	push	r13
 	push	r14
 	push	r15
-	lea	rsp,[((-40))+rsp]
-	movaps	XMMWORD[rsp],xmm6
-	movaps	XMMWORD[16+rsp],xmm7
-DB	0x67
-	mov	r10d,r9d
+
 	shl	r9d,3
-	shl	r10d,3+2
+	lea	r10,[r9*2+r9]
 	neg	r9
 	mov	r8,QWORD[r8]
 
@@ -1734,19 +2010,20 @@ DB	0x67
 
 
 
-	lea	r11,[((-64))+r9*2+rsp]
-	sub	r11,rsi
+
+	lea	r11,[((-320))+r9*2+rsp]
+	sub	r11,rdi
 	and	r11,4095
 	cmp	r10,r11
 	jb	NEAR $L$from_sp_alt
 	sub	rsp,r11
-	lea	rsp,[((-64))+r9*2+rsp]
+	lea	rsp,[((-320))+r9*2+rsp]
 	jmp	NEAR $L$from_sp_done
 
 ALIGN	32
 $L$from_sp_alt:
-	lea	r10,[((4096-64))+r9*2]
-	lea	rsp,[((-64))+r9*2+rsp]
+	lea	r10,[((4096-320))+r9*2]
+	lea	rsp,[((-320))+r9*2+rsp]
 	sub	r11,r10
 	mov	r10,0
 	cmovc	r11,r10
@@ -1797,7 +2074,8 @@ DB	102,72,15,110,209
 DB	0x67
 	mov	rbp,rcx
 DB	102,73,15,110,218
-	call	sqr8x_reduction
+	call	__bn_sqr8x_reduction
+	call	__bn_post4x_internal
 
 	pxor	xmm0,xmm0
 	lea	rax,[48+rsp]
@@ -1847,55 +2125,171 @@ $L$scatter_epilogue:
 
 global	bn_gather5
 
-ALIGN	16
+ALIGN	32
 bn_gather5:
 $L$SEH_begin_bn_gather5:
 
-DB	0x48,0x83,0xec,0x28
-DB	0x0f,0x29,0x34,0x24
-DB	0x0f,0x29,0x7c,0x24,0x10
-	mov	r11d,r9d
-	shr	r9d,3
-	and	r11,7
-	not	r9d
-	lea	rax,[$L$magic_masks]
-	and	r9d,3
-	lea	r8,[128+r11*8+r8]
-	movq	xmm4,QWORD[r9*8+rax]
-	movq	xmm5,QWORD[8+r9*8+rax]
-	movq	xmm6,QWORD[16+r9*8+rax]
-	movq	xmm7,QWORD[24+r9*8+rax]
-	jmp	NEAR $L$gather
-ALIGN	16
-$L$gather:
-	movq	xmm0,QWORD[(((-128)))+r8]
-	movq	xmm1,QWORD[((-64))+r8]
-	pand	xmm0,xmm4
-	movq	xmm2,QWORD[r8]
-	pand	xmm1,xmm5
-	movq	xmm3,QWORD[64+r8]
-	pand	xmm2,xmm6
-	por	xmm0,xmm1
-	pand	xmm3,xmm7
-DB	0x67,0x67
-	por	xmm0,xmm2
-	lea	r8,[256+r8]
-	por	xmm0,xmm3
+DB	0x4c,0x8d,0x14,0x24
+DB	0x48,0x81,0xec,0x08,0x01,0x00,0x00
+	lea	rax,[$L$inc]
+	and	rsp,-16
 
+	movd	xmm5,r9d
+	movdqa	xmm0,XMMWORD[rax]
+	movdqa	xmm1,XMMWORD[16+rax]
+	lea	r11,[128+r8]
+	lea	rax,[128+rsp]
+
+	pshufd	xmm5,xmm5,0
+	movdqa	xmm4,xmm1
+	movdqa	xmm2,xmm1
+	paddd	xmm1,xmm0
+	pcmpeqd	xmm0,xmm5
+	movdqa	xmm3,xmm4
+
+	paddd	xmm2,xmm1
+	pcmpeqd	xmm1,xmm5
+	movdqa	XMMWORD[(-128)+rax],xmm0
+	movdqa	xmm0,xmm4
+
+	paddd	xmm3,xmm2
+	pcmpeqd	xmm2,xmm5
+	movdqa	XMMWORD[(-112)+rax],xmm1
+	movdqa	xmm1,xmm4
+
+	paddd	xmm0,xmm3
+	pcmpeqd	xmm3,xmm5
+	movdqa	XMMWORD[(-96)+rax],xmm2
+	movdqa	xmm2,xmm4
+	paddd	xmm1,xmm0
+	pcmpeqd	xmm0,xmm5
+	movdqa	XMMWORD[(-80)+rax],xmm3
+	movdqa	xmm3,xmm4
+
+	paddd	xmm2,xmm1
+	pcmpeqd	xmm1,xmm5
+	movdqa	XMMWORD[(-64)+rax],xmm0
+	movdqa	xmm0,xmm4
+
+	paddd	xmm3,xmm2
+	pcmpeqd	xmm2,xmm5
+	movdqa	XMMWORD[(-48)+rax],xmm1
+	movdqa	xmm1,xmm4
+
+	paddd	xmm0,xmm3
+	pcmpeqd	xmm3,xmm5
+	movdqa	XMMWORD[(-32)+rax],xmm2
+	movdqa	xmm2,xmm4
+	paddd	xmm1,xmm0
+	pcmpeqd	xmm0,xmm5
+	movdqa	XMMWORD[(-16)+rax],xmm3
+	movdqa	xmm3,xmm4
+
+	paddd	xmm2,xmm1
+	pcmpeqd	xmm1,xmm5
+	movdqa	XMMWORD[rax],xmm0
+	movdqa	xmm0,xmm4
+
+	paddd	xmm3,xmm2
+	pcmpeqd	xmm2,xmm5
+	movdqa	XMMWORD[16+rax],xmm1
+	movdqa	xmm1,xmm4
+
+	paddd	xmm0,xmm3
+	pcmpeqd	xmm3,xmm5
+	movdqa	XMMWORD[32+rax],xmm2
+	movdqa	xmm2,xmm4
+	paddd	xmm1,xmm0
+	pcmpeqd	xmm0,xmm5
+	movdqa	XMMWORD[48+rax],xmm3
+	movdqa	xmm3,xmm4
+
+	paddd	xmm2,xmm1
+	pcmpeqd	xmm1,xmm5
+	movdqa	XMMWORD[64+rax],xmm0
+	movdqa	xmm0,xmm4
+
+	paddd	xmm3,xmm2
+	pcmpeqd	xmm2,xmm5
+	movdqa	XMMWORD[80+rax],xmm1
+	movdqa	xmm1,xmm4
+
+	paddd	xmm0,xmm3
+	pcmpeqd	xmm3,xmm5
+	movdqa	XMMWORD[96+rax],xmm2
+	movdqa	xmm2,xmm4
+	movdqa	XMMWORD[112+rax],xmm3
+	jmp	NEAR $L$gather
+
+ALIGN	32
+$L$gather:
+	pxor	xmm4,xmm4
+	pxor	xmm5,xmm5
+	movdqa	xmm0,XMMWORD[((-128))+r11]
+	movdqa	xmm1,XMMWORD[((-112))+r11]
+	movdqa	xmm2,XMMWORD[((-96))+r11]
+	pand	xmm0,XMMWORD[((-128))+rax]
+	movdqa	xmm3,XMMWORD[((-80))+r11]
+	pand	xmm1,XMMWORD[((-112))+rax]
+	por	xmm4,xmm0
+	pand	xmm2,XMMWORD[((-96))+rax]
+	por	xmm5,xmm1
+	pand	xmm3,XMMWORD[((-80))+rax]
+	por	xmm4,xmm2
+	por	xmm5,xmm3
+	movdqa	xmm0,XMMWORD[((-64))+r11]
+	movdqa	xmm1,XMMWORD[((-48))+r11]
+	movdqa	xmm2,XMMWORD[((-32))+r11]
+	pand	xmm0,XMMWORD[((-64))+rax]
+	movdqa	xmm3,XMMWORD[((-16))+r11]
+	pand	xmm1,XMMWORD[((-48))+rax]
+	por	xmm4,xmm0
+	pand	xmm2,XMMWORD[((-32))+rax]
+	por	xmm5,xmm1
+	pand	xmm3,XMMWORD[((-16))+rax]
+	por	xmm4,xmm2
+	por	xmm5,xmm3
+	movdqa	xmm0,XMMWORD[r11]
+	movdqa	xmm1,XMMWORD[16+r11]
+	movdqa	xmm2,XMMWORD[32+r11]
+	pand	xmm0,XMMWORD[rax]
+	movdqa	xmm3,XMMWORD[48+r11]
+	pand	xmm1,XMMWORD[16+rax]
+	por	xmm4,xmm0
+	pand	xmm2,XMMWORD[32+rax]
+	por	xmm5,xmm1
+	pand	xmm3,XMMWORD[48+rax]
+	por	xmm4,xmm2
+	por	xmm5,xmm3
+	movdqa	xmm0,XMMWORD[64+r11]
+	movdqa	xmm1,XMMWORD[80+r11]
+	movdqa	xmm2,XMMWORD[96+r11]
+	pand	xmm0,XMMWORD[64+rax]
+	movdqa	xmm3,XMMWORD[112+r11]
+	pand	xmm1,XMMWORD[80+rax]
+	por	xmm4,xmm0
+	pand	xmm2,XMMWORD[96+rax]
+	por	xmm5,xmm1
+	pand	xmm3,XMMWORD[112+rax]
+	por	xmm4,xmm2
+	por	xmm5,xmm3
+	por	xmm4,xmm5
+	lea	r11,[256+r11]
+	pshufd	xmm0,xmm4,0x4e
+	por	xmm0,xmm4
 	movq	QWORD[rcx],xmm0
 	lea	rcx,[8+rcx]
 	sub	edx,1
 	jnz	NEAR $L$gather
-	movaps	xmm6,XMMWORD[rsp]
-	movaps	xmm7,XMMWORD[16+rsp]
-	lea	rsp,[40+rsp]
+
+	lea	rsp,[r10]
 	DB	0F3h,0C3h		;repret
 $L$SEH_end_bn_gather5:
 
 ALIGN	64
-$L$magic_masks:
-	DD	0,0,0,0,0,0,-1,-1
-	DD	0,0,0,0,0,0,0,0
+$L$inc:
+	DD	0,0,1,1
+	DD	2,2,2,2
 DB	77,111,110,116,103,111,109,101,114,121,32,77,117,108,116,105
 DB	112,108,105,99,97,116,105,111,110,32,119,105,116,104,32,115
 DB	99,97,116,116,101,114,47,103,97,116,104,101,114,32,102,111
@@ -1937,19 +2331,16 @@ mul_handler:
 
 	lea	r10,[$L$mul_epilogue]
 	cmp	rbx,r10
-	jb	NEAR $L$body_40
+	ja	NEAR $L$body_40
 
 	mov	r10,QWORD[192+r8]
 	mov	rax,QWORD[8+r10*8+rax]
+
 	jmp	NEAR $L$body_proceed
 
 $L$body_40:
 	mov	rax,QWORD[40+rax]
 $L$body_proceed:
-
-	movaps	xmm0,XMMWORD[((-88))+rax]
-	movaps	xmm1,XMMWORD[((-72))+rax]
-
 	mov	rbx,QWORD[((-8))+rax]
 	mov	rbp,QWORD[((-16))+rax]
 	mov	r12,QWORD[((-24))+rax]
@@ -1962,8 +2353,6 @@ $L$body_proceed:
 	mov	QWORD[224+r8],r13
 	mov	QWORD[232+r8],r14
 	mov	QWORD[240+r8],r15
-	movups	XMMWORD[512+r8],xmm0
-	movups	XMMWORD[528+r8],xmm1
 
 $L$common_seh_tail:
 	mov	rdi,QWORD[8+rax]
@@ -2049,8 +2438,7 @@ DB	9,0,0,0
 	DD	$L$from_body wrt ..imagebase,$L$from_epilogue wrt ..imagebase
 ALIGN	8
 $L$SEH_info_bn_gather5:
-DB	0x01,0x0d,0x05,0x00
-DB	0x0d,0x78,0x01,0x00
-DB	0x08,0x68,0x00,0x00
-DB	0x04,0x42,0x00,0x00
+DB	0x01,0x0b,0x03,0x0a
+DB	0x0b,0x01,0x21,0x00
+DB	0x04,0xa3,0x00,0x00
 ALIGN	8
diff --git a/packager/third_party/boringssl/win-x86_64/crypto/chacha/chacha-x86_64.asm b/packager/third_party/boringssl/win-x86_64/crypto/chacha/chacha-x86_64.asm
new file mode 100644
index 0000000000..0ecbe95682
--- /dev/null
+++ b/packager/third_party/boringssl/win-x86_64/crypto/chacha/chacha-x86_64.asm
@@ -0,0 +1,1689 @@
+default	rel
+%define XMMWORD
+%define YMMWORD
+%define ZMMWORD
+section	.text code align=64
+
+
+EXTERN	OPENSSL_ia32cap_P
+
+ALIGN	64
+$L$zero:
+	DD	0,0,0,0
+$L$one:
+	DD	1,0,0,0
+$L$inc:
+	DD	0,1,2,3
+$L$four:
+	DD	4,4,4,4
+$L$incy:
+	DD	0,2,4,6,1,3,5,7
+$L$eight:
+	DD	8,8,8,8,8,8,8,8
+$L$rot16:
+DB	0x2,0x3,0x0,0x1,0x6,0x7,0x4,0x5,0xa,0xb,0x8,0x9,0xe,0xf,0xc,0xd
+$L$rot24:
+DB	0x3,0x0,0x1,0x2,0x7,0x4,0x5,0x6,0xb,0x8,0x9,0xa,0xf,0xc,0xd,0xe
+$L$sigma:
+DB	101,120,112,97,110,100,32,51,50,45,98,121,116,101,32,107
+DB	0
+DB	67,104,97,67,104,97,50,48,32,102,111,114,32,120,56,54
+DB	95,54,52,44,32,67,82,89,80,84,79,71,65,77,83,32
+DB	98,121,32,60,97,112,112,114,111,64,111,112,101,110,115,115
+DB	108,46,111,114,103,62,0
+global	ChaCha20_ctr32
+
+ALIGN	64
+ChaCha20_ctr32:
+	mov	QWORD[8+rsp],rdi	;WIN64 prologue
+	mov	QWORD[16+rsp],rsi
+	mov	rax,rsp
+$L$SEH_begin_ChaCha20_ctr32:
+	mov	rdi,rcx
+	mov	rsi,rdx
+	mov	rdx,r8
+	mov	rcx,r9
+	mov	r8,QWORD[40+rsp]
+
+
+	cmp	rdx,0
+	je	NEAR $L$no_data
+	mov	r10,QWORD[((OPENSSL_ia32cap_P+4))]
+	test	r10d,512
+	jnz	NEAR $L$ChaCha20_ssse3
+
+	push	rbx
+	push	rbp
+	push	r12
+	push	r13
+	push	r14
+	push	r15
+	sub	rsp,64+24
+
+
+	movdqu	xmm1,XMMWORD[rcx]
+	movdqu	xmm2,XMMWORD[16+rcx]
+	movdqu	xmm3,XMMWORD[r8]
+	movdqa	xmm4,XMMWORD[$L$one]
+
+
+	movdqa	XMMWORD[16+rsp],xmm1
+	movdqa	XMMWORD[32+rsp],xmm2
+	movdqa	XMMWORD[48+rsp],xmm3
+	mov	rbp,rdx
+	jmp	NEAR $L$oop_outer
+
+ALIGN	32
+$L$oop_outer:
+	mov	eax,0x61707865
+	mov	ebx,0x3320646e
+	mov	ecx,0x79622d32
+	mov	edx,0x6b206574
+	mov	r8d,DWORD[16+rsp]
+	mov	r9d,DWORD[20+rsp]
+	mov	r10d,DWORD[24+rsp]
+	mov	r11d,DWORD[28+rsp]
+	movd	r12d,xmm3
+	mov	r13d,DWORD[52+rsp]
+	mov	r14d,DWORD[56+rsp]
+	mov	r15d,DWORD[60+rsp]
+
+	mov	QWORD[((64+0))+rsp],rbp
+	mov	ebp,10
+	mov	QWORD[((64+8))+rsp],rsi
+DB	102,72,15,126,214
+	mov	QWORD[((64+16))+rsp],rdi
+	mov	rdi,rsi
+	shr	rdi,32
+	jmp	NEAR $L$oop
+
+ALIGN	32
+$L$oop:
+	add	eax,r8d
+	xor	r12d,eax
+	rol	r12d,16
+	add	ebx,r9d
+	xor	r13d,ebx
+	rol	r13d,16
+	add	esi,r12d
+	xor	r8d,esi
+	rol	r8d,12
+	add	edi,r13d
+	xor	r9d,edi
+	rol	r9d,12
+	add	eax,r8d
+	xor	r12d,eax
+	rol	r12d,8
+	add	ebx,r9d
+	xor	r13d,ebx
+	rol	r13d,8
+	add	esi,r12d
+	xor	r8d,esi
+	rol	r8d,7
+	add	edi,r13d
+	xor	r9d,edi
+	rol	r9d,7
+	mov	DWORD[32+rsp],esi
+	mov	DWORD[36+rsp],edi
+	mov	esi,DWORD[40+rsp]
+	mov	edi,DWORD[44+rsp]
+	add	ecx,r10d
+	xor	r14d,ecx
+	rol	r14d,16
+	add	edx,r11d
+	xor	r15d,edx
+	rol	r15d,16
+	add	esi,r14d
+	xor	r10d,esi
+	rol	r10d,12
+	add	edi,r15d
+	xor	r11d,edi
+	rol	r11d,12
+	add	ecx,r10d
+	xor	r14d,ecx
+	rol	r14d,8
+	add	edx,r11d
+	xor	r15d,edx
+	rol	r15d,8
+	add	esi,r14d
+	xor	r10d,esi
+	rol	r10d,7
+	add	edi,r15d
+	xor	r11d,edi
+	rol	r11d,7
+	add	eax,r9d
+	xor	r15d,eax
+	rol	r15d,16
+	add	ebx,r10d
+	xor	r12d,ebx
+	rol	r12d,16
+	add	esi,r15d
+	xor	r9d,esi
+	rol	r9d,12
+	add	edi,r12d
+	xor	r10d,edi
+	rol	r10d,12
+	add	eax,r9d
+	xor	r15d,eax
+	rol	r15d,8
+	add	ebx,r10d
+	xor	r12d,ebx
+	rol	r12d,8
+	add	esi,r15d
+	xor	r9d,esi
+	rol	r9d,7
+	add	edi,r12d
+	xor	r10d,edi
+	rol	r10d,7
+	mov	DWORD[40+rsp],esi
+	mov	DWORD[44+rsp],edi
+	mov	esi,DWORD[32+rsp]
+	mov	edi,DWORD[36+rsp]
+	add	ecx,r11d
+	xor	r13d,ecx
+	rol	r13d,16
+	add	edx,r8d
+	xor	r14d,edx
+	rol	r14d,16
+	add	esi,r13d
+	xor	r11d,esi
+	rol	r11d,12
+	add	edi,r14d
+	xor	r8d,edi
+	rol	r8d,12
+	add	ecx,r11d
+	xor	r13d,ecx
+	rol	r13d,8
+	add	edx,r8d
+	xor	r14d,edx
+	rol	r14d,8
+	add	esi,r13d
+	xor	r11d,esi
+	rol	r11d,7
+	add	edi,r14d
+	xor	r8d,edi
+	rol	r8d,7
+	dec	ebp
+	jnz	NEAR $L$oop
+	mov	DWORD[36+rsp],edi
+	mov	DWORD[32+rsp],esi
+	mov	rbp,QWORD[64+rsp]
+	movdqa	xmm1,xmm2
+	mov	rsi,QWORD[((64+8))+rsp]
+	paddd	xmm3,xmm4
+	mov	rdi,QWORD[((64+16))+rsp]
+
+	add	eax,0x61707865
+	add	ebx,0x3320646e
+	add	ecx,0x79622d32
+	add	edx,0x6b206574
+	add	r8d,DWORD[16+rsp]
+	add	r9d,DWORD[20+rsp]
+	add	r10d,DWORD[24+rsp]
+	add	r11d,DWORD[28+rsp]
+	add	r12d,DWORD[48+rsp]
+	add	r13d,DWORD[52+rsp]
+	add	r14d,DWORD[56+rsp]
+	add	r15d,DWORD[60+rsp]
+	paddd	xmm1,XMMWORD[32+rsp]
+
+	cmp	rbp,64
+	jb	NEAR $L$tail
+
+	xor	eax,DWORD[rsi]
+	xor	ebx,DWORD[4+rsi]
+	xor	ecx,DWORD[8+rsi]
+	xor	edx,DWORD[12+rsi]
+	xor	r8d,DWORD[16+rsi]
+	xor	r9d,DWORD[20+rsi]
+	xor	r10d,DWORD[24+rsi]
+	xor	r11d,DWORD[28+rsi]
+	movdqu	xmm0,XMMWORD[32+rsi]
+	xor	r12d,DWORD[48+rsi]
+	xor	r13d,DWORD[52+rsi]
+	xor	r14d,DWORD[56+rsi]
+	xor	r15d,DWORD[60+rsi]
+	lea	rsi,[64+rsi]
+	pxor	xmm0,xmm1
+
+	movdqa	XMMWORD[32+rsp],xmm2
+	movd	DWORD[48+rsp],xmm3
+
+	mov	DWORD[rdi],eax
+	mov	DWORD[4+rdi],ebx
+	mov	DWORD[8+rdi],ecx
+	mov	DWORD[12+rdi],edx
+	mov	DWORD[16+rdi],r8d
+	mov	DWORD[20+rdi],r9d
+	mov	DWORD[24+rdi],r10d
+	mov	DWORD[28+rdi],r11d
+	movdqu	XMMWORD[32+rdi],xmm0
+	mov	DWORD[48+rdi],r12d
+	mov	DWORD[52+rdi],r13d
+	mov	DWORD[56+rdi],r14d
+	mov	DWORD[60+rdi],r15d
+	lea	rdi,[64+rdi]
+
+	sub	rbp,64
+	jnz	NEAR $L$oop_outer
+
+	jmp	NEAR $L$done
+
+ALIGN	16
+$L$tail:
+	mov	DWORD[rsp],eax
+	mov	DWORD[4+rsp],ebx
+	xor	rbx,rbx
+	mov	DWORD[8+rsp],ecx
+	mov	DWORD[12+rsp],edx
+	mov	DWORD[16+rsp],r8d
+	mov	DWORD[20+rsp],r9d
+	mov	DWORD[24+rsp],r10d
+	mov	DWORD[28+rsp],r11d
+	movdqa	XMMWORD[32+rsp],xmm1
+	mov	DWORD[48+rsp],r12d
+	mov	DWORD[52+rsp],r13d
+	mov	DWORD[56+rsp],r14d
+	mov	DWORD[60+rsp],r15d
+
+$L$oop_tail:
+	movzx	eax,BYTE[rbx*1+rsi]
+	movzx	edx,BYTE[rbx*1+rsp]
+	lea	rbx,[1+rbx]
+	xor	eax,edx
+	mov	BYTE[((-1))+rbx*1+rdi],al
+	dec	rbp
+	jnz	NEAR $L$oop_tail
+
+$L$done:
+	add	rsp,64+24
+	pop	r15
+	pop	r14
+	pop	r13
+	pop	r12
+	pop	rbp
+	pop	rbx
+$L$no_data:
+	mov	rdi,QWORD[8+rsp]	;WIN64 epilogue
+	mov	rsi,QWORD[16+rsp]
+	DB	0F3h,0C3h		;repret
+$L$SEH_end_ChaCha20_ctr32:
+
+ALIGN	32
+ChaCha20_ssse3:
+	mov	QWORD[8+rsp],rdi	;WIN64 prologue
+	mov	QWORD[16+rsp],rsi
+	mov	rax,rsp
+$L$SEH_begin_ChaCha20_ssse3:
+	mov	rdi,rcx
+	mov	rsi,rdx
+	mov	rdx,r8
+	mov	rcx,r9
+	mov	r8,QWORD[40+rsp]
+
+
+$L$ChaCha20_ssse3:
+	cmp	rdx,128
+	ja	NEAR $L$ChaCha20_4x
+
+$L$do_sse3_after_all:
+	push	rbx
+	push	rbp
+	push	r12
+	push	r13
+	push	r14
+	push	r15
+
+	sub	rsp,64+72
+	movaps	XMMWORD[(64+32)+rsp],xmm6
+	movaps	XMMWORD[(64+48)+rsp],xmm7
+	movdqa	xmm0,XMMWORD[$L$sigma]
+	movdqu	xmm1,XMMWORD[rcx]
+	movdqu	xmm2,XMMWORD[16+rcx]
+	movdqu	xmm3,XMMWORD[r8]
+	movdqa	xmm6,XMMWORD[$L$rot16]
+	movdqa	xmm7,XMMWORD[$L$rot24]
+
+	movdqa	XMMWORD[rsp],xmm0
+	movdqa	XMMWORD[16+rsp],xmm1
+	movdqa	XMMWORD[32+rsp],xmm2
+	movdqa	XMMWORD[48+rsp],xmm3
+	mov	ebp,10
+	jmp	NEAR $L$oop_ssse3
+
+ALIGN	32
+$L$oop_outer_ssse3:
+	movdqa	xmm3,XMMWORD[$L$one]
+	movdqa	xmm0,XMMWORD[rsp]
+	movdqa	xmm1,XMMWORD[16+rsp]
+	movdqa	xmm2,XMMWORD[32+rsp]
+	paddd	xmm3,XMMWORD[48+rsp]
+	mov	ebp,10
+	movdqa	XMMWORD[48+rsp],xmm3
+	jmp	NEAR $L$oop_ssse3
+
+ALIGN	32
+$L$oop_ssse3:
+	paddd	xmm0,xmm1
+	pxor	xmm3,xmm0
+DB	102,15,56,0,222
+	paddd	xmm2,xmm3
+	pxor	xmm1,xmm2
+	movdqa	xmm4,xmm1
+	psrld	xmm1,20
+	pslld	xmm4,12
+	por	xmm1,xmm4
+	paddd	xmm0,xmm1
+	pxor	xmm3,xmm0
+DB	102,15,56,0,223
+	paddd	xmm2,xmm3
+	pxor	xmm1,xmm2
+	movdqa	xmm4,xmm1
+	psrld	xmm1,25
+	pslld	xmm4,7
+	por	xmm1,xmm4
+	pshufd	xmm2,xmm2,78
+	pshufd	xmm1,xmm1,57
+	pshufd	xmm3,xmm3,147
+	nop
+	paddd	xmm0,xmm1
+	pxor	xmm3,xmm0
+DB	102,15,56,0,222
+	paddd	xmm2,xmm3
+	pxor	xmm1,xmm2
+	movdqa	xmm4,xmm1
+	psrld	xmm1,20
+	pslld	xmm4,12
+	por	xmm1,xmm4
+	paddd	xmm0,xmm1
+	pxor	xmm3,xmm0
+DB	102,15,56,0,223
+	paddd	xmm2,xmm3
+	pxor	xmm1,xmm2
+	movdqa	xmm4,xmm1
+	psrld	xmm1,25
+	pslld	xmm4,7
+	por	xmm1,xmm4
+	pshufd	xmm2,xmm2,78
+	pshufd	xmm1,xmm1,147
+	pshufd	xmm3,xmm3,57
+	dec	ebp
+	jnz	NEAR $L$oop_ssse3
+	paddd	xmm0,XMMWORD[rsp]
+	paddd	xmm1,XMMWORD[16+rsp]
+	paddd	xmm2,XMMWORD[32+rsp]
+	paddd	xmm3,XMMWORD[48+rsp]
+
+	cmp	rdx,64
+	jb	NEAR $L$tail_ssse3
+
+	movdqu	xmm4,XMMWORD[rsi]
+	movdqu	xmm5,XMMWORD[16+rsi]
+	pxor	xmm0,xmm4
+	movdqu	xmm4,XMMWORD[32+rsi]
+	pxor	xmm1,xmm5
+	movdqu	xmm5,XMMWORD[48+rsi]
+	lea	rsi,[64+rsi]
+	pxor	xmm2,xmm4
+	pxor	xmm3,xmm5
+
+	movdqu	XMMWORD[rdi],xmm0
+	movdqu	XMMWORD[16+rdi],xmm1
+	movdqu	XMMWORD[32+rdi],xmm2
+	movdqu	XMMWORD[48+rdi],xmm3
+	lea	rdi,[64+rdi]
+
+	sub	rdx,64
+	jnz	NEAR $L$oop_outer_ssse3
+
+	jmp	NEAR $L$done_ssse3
+
+ALIGN	16
+$L$tail_ssse3:
+	movdqa	XMMWORD[rsp],xmm0
+	movdqa	XMMWORD[16+rsp],xmm1
+	movdqa	XMMWORD[32+rsp],xmm2
+	movdqa	XMMWORD[48+rsp],xmm3
+	xor	rbx,rbx
+
+$L$oop_tail_ssse3:
+	movzx	eax,BYTE[rbx*1+rsi]
+	movzx	ecx,BYTE[rbx*1+rsp]
+	lea	rbx,[1+rbx]
+	xor	eax,ecx
+	mov	BYTE[((-1))+rbx*1+rdi],al
+	dec	rdx
+	jnz	NEAR $L$oop_tail_ssse3
+
+$L$done_ssse3:
+	movaps	xmm6,XMMWORD[((64+32))+rsp]
+	movaps	xmm7,XMMWORD[((64+48))+rsp]
+	add	rsp,64+72
+	pop	r15
+	pop	r14
+	pop	r13
+	pop	r12
+	pop	rbp
+	pop	rbx
+	mov	rdi,QWORD[8+rsp]	;WIN64 epilogue
+	mov	rsi,QWORD[16+rsp]
+	DB	0F3h,0C3h		;repret
+$L$SEH_end_ChaCha20_ssse3:
+
+ALIGN	32
+ChaCha20_4x:
+	mov	QWORD[8+rsp],rdi	;WIN64 prologue
+	mov	QWORD[16+rsp],rsi
+	mov	rax,rsp
+$L$SEH_begin_ChaCha20_4x:
+	mov	rdi,rcx
+	mov	rsi,rdx
+	mov	rdx,r8
+	mov	rcx,r9
+	mov	r8,QWORD[40+rsp]
+
+
+$L$ChaCha20_4x:
+	mov	r11,r10
+	shr	r10,32
+	test	r10,32
+	jnz	NEAR $L$ChaCha20_8x
+	cmp	rdx,192
+	ja	NEAR $L$proceed4x
+
+	and	r11,71303168
+	cmp	r11,4194304
+	je	NEAR $L$do_sse3_after_all
+
+$L$proceed4x:
+	lea	r11,[((-120))+rsp]
+	sub	rsp,0x148+160
+	movaps	XMMWORD[(-48)+r11],xmm6
+	movaps	XMMWORD[(-32)+r11],xmm7
+	movaps	XMMWORD[(-16)+r11],xmm8
+	movaps	XMMWORD[r11],xmm9
+	movaps	XMMWORD[16+r11],xmm10
+	movaps	XMMWORD[32+r11],xmm11
+	movaps	XMMWORD[48+r11],xmm12
+	movaps	XMMWORD[64+r11],xmm13
+	movaps	XMMWORD[80+r11],xmm14
+	movaps	XMMWORD[96+r11],xmm15
+	movdqa	xmm11,XMMWORD[$L$sigma]
+	movdqu	xmm15,XMMWORD[rcx]
+	movdqu	xmm7,XMMWORD[16+rcx]
+	movdqu	xmm3,XMMWORD[r8]
+	lea	rcx,[256+rsp]
+	lea	r10,[$L$rot16]
+	lea	r11,[$L$rot24]
+
+	pshufd	xmm8,xmm11,0x00
+	pshufd	xmm9,xmm11,0x55
+	movdqa	XMMWORD[64+rsp],xmm8
+	pshufd	xmm10,xmm11,0xaa
+	movdqa	XMMWORD[80+rsp],xmm9
+	pshufd	xmm11,xmm11,0xff
+	movdqa	XMMWORD[96+rsp],xmm10
+	movdqa	XMMWORD[112+rsp],xmm11
+
+	pshufd	xmm12,xmm15,0x00
+	pshufd	xmm13,xmm15,0x55
+	movdqa	XMMWORD[(128-256)+rcx],xmm12
+	pshufd	xmm14,xmm15,0xaa
+	movdqa	XMMWORD[(144-256)+rcx],xmm13
+	pshufd	xmm15,xmm15,0xff
+	movdqa	XMMWORD[(160-256)+rcx],xmm14
+	movdqa	XMMWORD[(176-256)+rcx],xmm15
+
+	pshufd	xmm4,xmm7,0x00
+	pshufd	xmm5,xmm7,0x55
+	movdqa	XMMWORD[(192-256)+rcx],xmm4
+	pshufd	xmm6,xmm7,0xaa
+	movdqa	XMMWORD[(208-256)+rcx],xmm5
+	pshufd	xmm7,xmm7,0xff
+	movdqa	XMMWORD[(224-256)+rcx],xmm6
+	movdqa	XMMWORD[(240-256)+rcx],xmm7
+
+	pshufd	xmm0,xmm3,0x00
+	pshufd	xmm1,xmm3,0x55
+	paddd	xmm0,XMMWORD[$L$inc]
+	pshufd	xmm2,xmm3,0xaa
+	movdqa	XMMWORD[(272-256)+rcx],xmm1
+	pshufd	xmm3,xmm3,0xff
+	movdqa	XMMWORD[(288-256)+rcx],xmm2
+	movdqa	XMMWORD[(304-256)+rcx],xmm3
+
+	jmp	NEAR $L$oop_enter4x
+
+ALIGN	32
+$L$oop_outer4x:
+	movdqa	xmm8,XMMWORD[64+rsp]
+	movdqa	xmm9,XMMWORD[80+rsp]
+	movdqa	xmm10,XMMWORD[96+rsp]
+	movdqa	xmm11,XMMWORD[112+rsp]
+	movdqa	xmm12,XMMWORD[((128-256))+rcx]
+	movdqa	xmm13,XMMWORD[((144-256))+rcx]
+	movdqa	xmm14,XMMWORD[((160-256))+rcx]
+	movdqa	xmm15,XMMWORD[((176-256))+rcx]
+	movdqa	xmm4,XMMWORD[((192-256))+rcx]
+	movdqa	xmm5,XMMWORD[((208-256))+rcx]
+	movdqa	xmm6,XMMWORD[((224-256))+rcx]
+	movdqa	xmm7,XMMWORD[((240-256))+rcx]
+	movdqa	xmm0,XMMWORD[((256-256))+rcx]
+	movdqa	xmm1,XMMWORD[((272-256))+rcx]
+	movdqa	xmm2,XMMWORD[((288-256))+rcx]
+	movdqa	xmm3,XMMWORD[((304-256))+rcx]
+	paddd	xmm0,XMMWORD[$L$four]
+
+$L$oop_enter4x:
+	movdqa	XMMWORD[32+rsp],xmm6
+	movdqa	XMMWORD[48+rsp],xmm7
+	movdqa	xmm7,XMMWORD[r10]
+	mov	eax,10
+	movdqa	XMMWORD[(256-256)+rcx],xmm0
+	jmp	NEAR $L$oop4x
+
+ALIGN	32
+$L$oop4x:
+	paddd	xmm8,xmm12
+	paddd	xmm9,xmm13
+	pxor	xmm0,xmm8
+	pxor	xmm1,xmm9
+DB	102,15,56,0,199
+DB	102,15,56,0,207
+	paddd	xmm4,xmm0
+	paddd	xmm5,xmm1
+	pxor	xmm12,xmm4
+	pxor	xmm13,xmm5
+	movdqa	xmm6,xmm12
+	pslld	xmm12,12
+	psrld	xmm6,20
+	movdqa	xmm7,xmm13
+	pslld	xmm13,12
+	por	xmm12,xmm6
+	psrld	xmm7,20
+	movdqa	xmm6,XMMWORD[r11]
+	por	xmm13,xmm7
+	paddd	xmm8,xmm12
+	paddd	xmm9,xmm13
+	pxor	xmm0,xmm8
+	pxor	xmm1,xmm9
+DB	102,15,56,0,198
+DB	102,15,56,0,206
+	paddd	xmm4,xmm0
+	paddd	xmm5,xmm1
+	pxor	xmm12,xmm4
+	pxor	xmm13,xmm5
+	movdqa	xmm7,xmm12
+	pslld	xmm12,7
+	psrld	xmm7,25
+	movdqa	xmm6,xmm13
+	pslld	xmm13,7
+	por	xmm12,xmm7
+	psrld	xmm6,25
+	movdqa	xmm7,XMMWORD[r10]
+	por	xmm13,xmm6
+	movdqa	XMMWORD[rsp],xmm4
+	movdqa	XMMWORD[16+rsp],xmm5
+	movdqa	xmm4,XMMWORD[32+rsp]
+	movdqa	xmm5,XMMWORD[48+rsp]
+	paddd	xmm10,xmm14
+	paddd	xmm11,xmm15
+	pxor	xmm2,xmm10
+	pxor	xmm3,xmm11
+DB	102,15,56,0,215
+DB	102,15,56,0,223
+	paddd	xmm4,xmm2
+	paddd	xmm5,xmm3
+	pxor	xmm14,xmm4
+	pxor	xmm15,xmm5
+	movdqa	xmm6,xmm14
+	pslld	xmm14,12
+	psrld	xmm6,20
+	movdqa	xmm7,xmm15
+	pslld	xmm15,12
+	por	xmm14,xmm6
+	psrld	xmm7,20
+	movdqa	xmm6,XMMWORD[r11]
+	por	xmm15,xmm7
+	paddd	xmm10,xmm14
+	paddd	xmm11,xmm15
+	pxor	xmm2,xmm10
+	pxor	xmm3,xmm11
+DB	102,15,56,0,214
+DB	102,15,56,0,222
+	paddd	xmm4,xmm2
+	paddd	xmm5,xmm3
+	pxor	xmm14,xmm4
+	pxor	xmm15,xmm5
+	movdqa	xmm7,xmm14
+	pslld	xmm14,7
+	psrld	xmm7,25
+	movdqa	xmm6,xmm15
+	pslld	xmm15,7
+	por	xmm14,xmm7
+	psrld	xmm6,25
+	movdqa	xmm7,XMMWORD[r10]
+	por	xmm15,xmm6
+	paddd	xmm8,xmm13
+	paddd	xmm9,xmm14
+	pxor	xmm3,xmm8
+	pxor	xmm0,xmm9
+DB	102,15,56,0,223
+DB	102,15,56,0,199
+	paddd	xmm4,xmm3
+	paddd	xmm5,xmm0
+	pxor	xmm13,xmm4
+	pxor	xmm14,xmm5
+	movdqa	xmm6,xmm13
+	pslld	xmm13,12
+	psrld	xmm6,20
+	movdqa	xmm7,xmm14
+	pslld	xmm14,12
+	por	xmm13,xmm6
+	psrld	xmm7,20
+	movdqa	xmm6,XMMWORD[r11]
+	por	xmm14,xmm7
+	paddd	xmm8,xmm13
+	paddd	xmm9,xmm14
+	pxor	xmm3,xmm8
+	pxor	xmm0,xmm9
+DB	102,15,56,0,222
+DB	102,15,56,0,198
+	paddd	xmm4,xmm3
+	paddd	xmm5,xmm0
+	pxor	xmm13,xmm4
+	pxor	xmm14,xmm5
+	movdqa	xmm7,xmm13
+	pslld	xmm13,7
+	psrld	xmm7,25
+	movdqa	xmm6,xmm14
+	pslld	xmm14,7
+	por	xmm13,xmm7
+	psrld	xmm6,25
+	movdqa	xmm7,XMMWORD[r10]
+	por	xmm14,xmm6
+	movdqa	XMMWORD[32+rsp],xmm4
+	movdqa	XMMWORD[48+rsp],xmm5
+	movdqa	xmm4,XMMWORD[rsp]
+	movdqa	xmm5,XMMWORD[16+rsp]
+	paddd	xmm10,xmm15
+	paddd	xmm11,xmm12
+	pxor	xmm1,xmm10
+	pxor	xmm2,xmm11
+DB	102,15,56,0,207
+DB	102,15,56,0,215
+	paddd	xmm4,xmm1
+	paddd	xmm5,xmm2
+	pxor	xmm15,xmm4
+	pxor	xmm12,xmm5
+	movdqa	xmm6,xmm15
+	pslld	xmm15,12
+	psrld	xmm6,20
+	movdqa	xmm7,xmm12
+	pslld	xmm12,12
+	por	xmm15,xmm6
+	psrld	xmm7,20
+	movdqa	xmm6,XMMWORD[r11]
+	por	xmm12,xmm7
+	paddd	xmm10,xmm15
+	paddd	xmm11,xmm12
+	pxor	xmm1,xmm10
+	pxor	xmm2,xmm11
+DB	102,15,56,0,206
+DB	102,15,56,0,214
+	paddd	xmm4,xmm1
+	paddd	xmm5,xmm2
+	pxor	xmm15,xmm4
+	pxor	xmm12,xmm5
+	movdqa	xmm7,xmm15
+	pslld	xmm15,7
+	psrld	xmm7,25
+	movdqa	xmm6,xmm12
+	pslld	xmm12,7
+	por	xmm15,xmm7
+	psrld	xmm6,25
+	movdqa	xmm7,XMMWORD[r10]
+	por	xmm12,xmm6
+	dec	eax
+	jnz	NEAR $L$oop4x
+
+	paddd	xmm8,XMMWORD[64+rsp]
+	paddd	xmm9,XMMWORD[80+rsp]
+	paddd	xmm10,XMMWORD[96+rsp]
+	paddd	xmm11,XMMWORD[112+rsp]
+
+	movdqa	xmm6,xmm8
+	punpckldq	xmm8,xmm9
+	movdqa	xmm7,xmm10
+	punpckldq	xmm10,xmm11
+	punpckhdq	xmm6,xmm9
+	punpckhdq	xmm7,xmm11
+	movdqa	xmm9,xmm8
+	punpcklqdq	xmm8,xmm10
+	movdqa	xmm11,xmm6
+	punpcklqdq	xmm6,xmm7
+	punpckhqdq	xmm9,xmm10
+	punpckhqdq	xmm11,xmm7
+	paddd	xmm12,XMMWORD[((128-256))+rcx]
+	paddd	xmm13,XMMWORD[((144-256))+rcx]
+	paddd	xmm14,XMMWORD[((160-256))+rcx]
+	paddd	xmm15,XMMWORD[((176-256))+rcx]
+
+	movdqa	XMMWORD[rsp],xmm8
+	movdqa	XMMWORD[16+rsp],xmm9
+	movdqa	xmm8,XMMWORD[32+rsp]
+	movdqa	xmm9,XMMWORD[48+rsp]
+
+	movdqa	xmm10,xmm12
+	punpckldq	xmm12,xmm13
+	movdqa	xmm7,xmm14
+	punpckldq	xmm14,xmm15
+	punpckhdq	xmm10,xmm13
+	punpckhdq	xmm7,xmm15
+	movdqa	xmm13,xmm12
+	punpcklqdq	xmm12,xmm14
+	movdqa	xmm15,xmm10
+	punpcklqdq	xmm10,xmm7
+	punpckhqdq	xmm13,xmm14
+	punpckhqdq	xmm15,xmm7
+	paddd	xmm4,XMMWORD[((192-256))+rcx]
+	paddd	xmm5,XMMWORD[((208-256))+rcx]
+	paddd	xmm8,XMMWORD[((224-256))+rcx]
+	paddd	xmm9,XMMWORD[((240-256))+rcx]
+
+	movdqa	XMMWORD[32+rsp],xmm6
+	movdqa	XMMWORD[48+rsp],xmm11
+
+	movdqa	xmm14,xmm4
+	punpckldq	xmm4,xmm5
+	movdqa	xmm7,xmm8
+	punpckldq	xmm8,xmm9
+	punpckhdq	xmm14,xmm5
+	punpckhdq	xmm7,xmm9
+	movdqa	xmm5,xmm4
+	punpcklqdq	xmm4,xmm8
+	movdqa	xmm9,xmm14
+	punpcklqdq	xmm14,xmm7
+	punpckhqdq	xmm5,xmm8
+	punpckhqdq	xmm9,xmm7
+	paddd	xmm0,XMMWORD[((256-256))+rcx]
+	paddd	xmm1,XMMWORD[((272-256))+rcx]
+	paddd	xmm2,XMMWORD[((288-256))+rcx]
+	paddd	xmm3,XMMWORD[((304-256))+rcx]
+
+	movdqa	xmm8,xmm0
+	punpckldq	xmm0,xmm1
+	movdqa	xmm7,xmm2
+	punpckldq	xmm2,xmm3
+	punpckhdq	xmm8,xmm1
+	punpckhdq	xmm7,xmm3
+	movdqa	xmm1,xmm0
+	punpcklqdq	xmm0,xmm2
+	movdqa	xmm3,xmm8
+	punpcklqdq	xmm8,xmm7
+	punpckhqdq	xmm1,xmm2
+	punpckhqdq	xmm3,xmm7
+	cmp	rdx,64*4
+	jb	NEAR $L$tail4x
+
+	movdqu	xmm6,XMMWORD[rsi]
+	movdqu	xmm11,XMMWORD[16+rsi]
+	movdqu	xmm2,XMMWORD[32+rsi]
+	movdqu	xmm7,XMMWORD[48+rsi]
+	pxor	xmm6,XMMWORD[rsp]
+	pxor	xmm11,xmm12
+	pxor	xmm2,xmm4
+	pxor	xmm7,xmm0
+
+	movdqu	XMMWORD[rdi],xmm6
+	movdqu	xmm6,XMMWORD[64+rsi]
+	movdqu	XMMWORD[16+rdi],xmm11
+	movdqu	xmm11,XMMWORD[80+rsi]
+	movdqu	XMMWORD[32+rdi],xmm2
+	movdqu	xmm2,XMMWORD[96+rsi]
+	movdqu	XMMWORD[48+rdi],xmm7
+	movdqu	xmm7,XMMWORD[112+rsi]
+	lea	rsi,[128+rsi]
+	pxor	xmm6,XMMWORD[16+rsp]
+	pxor	xmm11,xmm13
+	pxor	xmm2,xmm5
+	pxor	xmm7,xmm1
+
+	movdqu	XMMWORD[64+rdi],xmm6
+	movdqu	xmm6,XMMWORD[rsi]
+	movdqu	XMMWORD[80+rdi],xmm11
+	movdqu	xmm11,XMMWORD[16+rsi]
+	movdqu	XMMWORD[96+rdi],xmm2
+	movdqu	xmm2,XMMWORD[32+rsi]
+	movdqu	XMMWORD[112+rdi],xmm7
+	lea	rdi,[128+rdi]
+	movdqu	xmm7,XMMWORD[48+rsi]
+	pxor	xmm6,XMMWORD[32+rsp]
+	pxor	xmm11,xmm10
+	pxor	xmm2,xmm14
+	pxor	xmm7,xmm8
+
+	movdqu	XMMWORD[rdi],xmm6
+	movdqu	xmm6,XMMWORD[64+rsi]
+	movdqu	XMMWORD[16+rdi],xmm11
+	movdqu	xmm11,XMMWORD[80+rsi]
+	movdqu	XMMWORD[32+rdi],xmm2
+	movdqu	xmm2,XMMWORD[96+rsi]
+	movdqu	XMMWORD[48+rdi],xmm7
+	movdqu	xmm7,XMMWORD[112+rsi]
+	lea	rsi,[128+rsi]
+	pxor	xmm6,XMMWORD[48+rsp]
+	pxor	xmm11,xmm15
+	pxor	xmm2,xmm9
+	pxor	xmm7,xmm3
+	movdqu	XMMWORD[64+rdi],xmm6
+	movdqu	XMMWORD[80+rdi],xmm11
+	movdqu	XMMWORD[96+rdi],xmm2
+	movdqu	XMMWORD[112+rdi],xmm7
+	lea	rdi,[128+rdi]
+
+	sub	rdx,64*4
+	jnz	NEAR $L$oop_outer4x
+
+	jmp	NEAR $L$done4x
+
+$L$tail4x:
+	cmp	rdx,192
+	jae	NEAR $L$192_or_more4x
+	cmp	rdx,128
+	jae	NEAR $L$128_or_more4x
+	cmp	rdx,64
+	jae	NEAR $L$64_or_more4x
+
+
+	xor	r10,r10
+
+	movdqa	XMMWORD[16+rsp],xmm12
+	movdqa	XMMWORD[32+rsp],xmm4
+	movdqa	XMMWORD[48+rsp],xmm0
+	jmp	NEAR $L$oop_tail4x
+
+ALIGN	32
+$L$64_or_more4x:
+	movdqu	xmm6,XMMWORD[rsi]
+	movdqu	xmm11,XMMWORD[16+rsi]
+	movdqu	xmm2,XMMWORD[32+rsi]
+	movdqu	xmm7,XMMWORD[48+rsi]
+	pxor	xmm6,XMMWORD[rsp]
+	pxor	xmm11,xmm12
+	pxor	xmm2,xmm4
+	pxor	xmm7,xmm0
+	movdqu	XMMWORD[rdi],xmm6
+	movdqu	XMMWORD[16+rdi],xmm11
+	movdqu	XMMWORD[32+rdi],xmm2
+	movdqu	XMMWORD[48+rdi],xmm7
+	je	NEAR $L$done4x
+
+	movdqa	xmm6,XMMWORD[16+rsp]
+	lea	rsi,[64+rsi]
+	xor	r10,r10
+	movdqa	XMMWORD[rsp],xmm6
+	movdqa	XMMWORD[16+rsp],xmm13
+	lea	rdi,[64+rdi]
+	movdqa	XMMWORD[32+rsp],xmm5
+	sub	rdx,64
+	movdqa	XMMWORD[48+rsp],xmm1
+	jmp	NEAR $L$oop_tail4x
+
+ALIGN	32
+$L$128_or_more4x:
+	movdqu	xmm6,XMMWORD[rsi]
+	movdqu	xmm11,XMMWORD[16+rsi]
+	movdqu	xmm2,XMMWORD[32+rsi]
+	movdqu	xmm7,XMMWORD[48+rsi]
+	pxor	xmm6,XMMWORD[rsp]
+	pxor	xmm11,xmm12
+	pxor	xmm2,xmm4
+	pxor	xmm7,xmm0
+
+	movdqu	XMMWORD[rdi],xmm6
+	movdqu	xmm6,XMMWORD[64+rsi]
+	movdqu	XMMWORD[16+rdi],xmm11
+	movdqu	xmm11,XMMWORD[80+rsi]
+	movdqu	XMMWORD[32+rdi],xmm2
+	movdqu	xmm2,XMMWORD[96+rsi]
+	movdqu	XMMWORD[48+rdi],xmm7
+	movdqu	xmm7,XMMWORD[112+rsi]
+	pxor	xmm6,XMMWORD[16+rsp]
+	pxor	xmm11,xmm13
+	pxor	xmm2,xmm5
+	pxor	xmm7,xmm1
+	movdqu	XMMWORD[64+rdi],xmm6
+	movdqu	XMMWORD[80+rdi],xmm11
+	movdqu	XMMWORD[96+rdi],xmm2
+	movdqu	XMMWORD[112+rdi],xmm7
+	je	NEAR $L$done4x
+
+	movdqa	xmm6,XMMWORD[32+rsp]
+	lea	rsi,[128+rsi]
+	xor	r10,r10
+	movdqa	XMMWORD[rsp],xmm6
+	movdqa	XMMWORD[16+rsp],xmm10
+	lea	rdi,[128+rdi]
+	movdqa	XMMWORD[32+rsp],xmm14
+	sub	rdx,128
+	movdqa	XMMWORD[48+rsp],xmm8
+	jmp	NEAR $L$oop_tail4x
+
+ALIGN	32
+$L$192_or_more4x:
+	movdqu	xmm6,XMMWORD[rsi]
+	movdqu	xmm11,XMMWORD[16+rsi]
+	movdqu	xmm2,XMMWORD[32+rsi]
+	movdqu	xmm7,XMMWORD[48+rsi]
+	pxor	xmm6,XMMWORD[rsp]
+	pxor	xmm11,xmm12
+	pxor	xmm2,xmm4
+	pxor	xmm7,xmm0
+
+	movdqu	XMMWORD[rdi],xmm6
+	movdqu	xmm6,XMMWORD[64+rsi]
+	movdqu	XMMWORD[16+rdi],xmm11
+	movdqu	xmm11,XMMWORD[80+rsi]
+	movdqu	XMMWORD[32+rdi],xmm2
+	movdqu	xmm2,XMMWORD[96+rsi]
+	movdqu	XMMWORD[48+rdi],xmm7
+	movdqu	xmm7,XMMWORD[112+rsi]
+	lea	rsi,[128+rsi]
+	pxor	xmm6,XMMWORD[16+rsp]
+	pxor	xmm11,xmm13
+	pxor	xmm2,xmm5
+	pxor	xmm7,xmm1
+
+	movdqu	XMMWORD[64+rdi],xmm6
+	movdqu	xmm6,XMMWORD[rsi]
+	movdqu	XMMWORD[80+rdi],xmm11
+	movdqu	xmm11,XMMWORD[16+rsi]
+	movdqu	XMMWORD[96+rdi],xmm2
+	movdqu	xmm2,XMMWORD[32+rsi]
+	movdqu	XMMWORD[112+rdi],xmm7
+	lea	rdi,[128+rdi]
+	movdqu	xmm7,XMMWORD[48+rsi]
+	pxor	xmm6,XMMWORD[32+rsp]
+	pxor	xmm11,xmm10
+	pxor	xmm2,xmm14
+	pxor	xmm7,xmm8
+	movdqu	XMMWORD[rdi],xmm6
+	movdqu	XMMWORD[16+rdi],xmm11
+	movdqu	XMMWORD[32+rdi],xmm2
+	movdqu	XMMWORD[48+rdi],xmm7
+	je	NEAR $L$done4x
+
+	movdqa	xmm6,XMMWORD[48+rsp]
+	lea	rsi,[64+rsi]
+	xor	r10,r10
+	movdqa	XMMWORD[rsp],xmm6
+	movdqa	XMMWORD[16+rsp],xmm15
+	lea	rdi,[64+rdi]
+	movdqa	XMMWORD[32+rsp],xmm9
+	sub	rdx,192
+	movdqa	XMMWORD[48+rsp],xmm3
+
+$L$oop_tail4x:
+	movzx	eax,BYTE[r10*1+rsi]
+	movzx	ecx,BYTE[r10*1+rsp]
+	lea	r10,[1+r10]
+	xor	eax,ecx
+	mov	BYTE[((-1))+r10*1+rdi],al
+	dec	rdx
+	jnz	NEAR $L$oop_tail4x
+
+$L$done4x:
+	lea	r11,[((320+48))+rsp]
+	movaps	xmm6,XMMWORD[((-48))+r11]
+	movaps	xmm7,XMMWORD[((-32))+r11]
+	movaps	xmm8,XMMWORD[((-16))+r11]
+	movaps	xmm9,XMMWORD[r11]
+	movaps	xmm10,XMMWORD[16+r11]
+	movaps	xmm11,XMMWORD[32+r11]
+	movaps	xmm12,XMMWORD[48+r11]
+	movaps	xmm13,XMMWORD[64+r11]
+	movaps	xmm14,XMMWORD[80+r11]
+	movaps	xmm15,XMMWORD[96+r11]
+	add	rsp,0x148+160
+	mov	rdi,QWORD[8+rsp]	;WIN64 epilogue
+	mov	rsi,QWORD[16+rsp]
+	DB	0F3h,0C3h		;repret
+$L$SEH_end_ChaCha20_4x:
+
+ALIGN	32
+ChaCha20_8x:
+	mov	QWORD[8+rsp],rdi	;WIN64 prologue
+	mov	QWORD[16+rsp],rsi
+	mov	rax,rsp
+$L$SEH_begin_ChaCha20_8x:
+	mov	rdi,rcx
+	mov	rsi,rdx
+	mov	rdx,r8
+	mov	rcx,r9
+	mov	r8,QWORD[40+rsp]
+
+
+$L$ChaCha20_8x:
+	mov	r10,rsp
+	sub	rsp,0x280+176
+	and	rsp,-32
+	lea	r11,[((656+48))+rsp]
+	movaps	XMMWORD[(-48)+r11],xmm6
+	movaps	XMMWORD[(-32)+r11],xmm7
+	movaps	XMMWORD[(-16)+r11],xmm8
+	movaps	XMMWORD[r11],xmm9
+	movaps	XMMWORD[16+r11],xmm10
+	movaps	XMMWORD[32+r11],xmm11
+	movaps	XMMWORD[48+r11],xmm12
+	movaps	XMMWORD[64+r11],xmm13
+	movaps	XMMWORD[80+r11],xmm14
+	movaps	XMMWORD[96+r11],xmm15
+	vzeroupper
+	mov	QWORD[640+rsp],r10
+
+
+
+
+
+
+
+
+
+
+	vbroadcasti128	ymm11,YMMWORD[$L$sigma]
+	vbroadcasti128	ymm3,YMMWORD[rcx]
+	vbroadcasti128	ymm15,YMMWORD[16+rcx]
+	vbroadcasti128	ymm7,YMMWORD[r8]
+	lea	rcx,[256+rsp]
+	lea	rax,[512+rsp]
+	lea	r10,[$L$rot16]
+	lea	r11,[$L$rot24]
+
+	vpshufd	ymm8,ymm11,0x00
+	vpshufd	ymm9,ymm11,0x55
+	vmovdqa	YMMWORD[(128-256)+rcx],ymm8
+	vpshufd	ymm10,ymm11,0xaa
+	vmovdqa	YMMWORD[(160-256)+rcx],ymm9
+	vpshufd	ymm11,ymm11,0xff
+	vmovdqa	YMMWORD[(192-256)+rcx],ymm10
+	vmovdqa	YMMWORD[(224-256)+rcx],ymm11
+
+	vpshufd	ymm0,ymm3,0x00
+	vpshufd	ymm1,ymm3,0x55
+	vmovdqa	YMMWORD[(256-256)+rcx],ymm0
+	vpshufd	ymm2,ymm3,0xaa
+	vmovdqa	YMMWORD[(288-256)+rcx],ymm1
+	vpshufd	ymm3,ymm3,0xff
+	vmovdqa	YMMWORD[(320-256)+rcx],ymm2
+	vmovdqa	YMMWORD[(352-256)+rcx],ymm3
+
+	vpshufd	ymm12,ymm15,0x00
+	vpshufd	ymm13,ymm15,0x55
+	vmovdqa	YMMWORD[(384-512)+rax],ymm12
+	vpshufd	ymm14,ymm15,0xaa
+	vmovdqa	YMMWORD[(416-512)+rax],ymm13
+	vpshufd	ymm15,ymm15,0xff
+	vmovdqa	YMMWORD[(448-512)+rax],ymm14
+	vmovdqa	YMMWORD[(480-512)+rax],ymm15
+
+	vpshufd	ymm4,ymm7,0x00
+	vpshufd	ymm5,ymm7,0x55
+	vpaddd	ymm4,ymm4,YMMWORD[$L$incy]
+	vpshufd	ymm6,ymm7,0xaa
+	vmovdqa	YMMWORD[(544-512)+rax],ymm5
+	vpshufd	ymm7,ymm7,0xff
+	vmovdqa	YMMWORD[(576-512)+rax],ymm6
+	vmovdqa	YMMWORD[(608-512)+rax],ymm7
+
+	jmp	NEAR $L$oop_enter8x
+
+ALIGN	32
+$L$oop_outer8x:
+	vmovdqa	ymm8,YMMWORD[((128-256))+rcx]
+	vmovdqa	ymm9,YMMWORD[((160-256))+rcx]
+	vmovdqa	ymm10,YMMWORD[((192-256))+rcx]
+	vmovdqa	ymm11,YMMWORD[((224-256))+rcx]
+	vmovdqa	ymm0,YMMWORD[((256-256))+rcx]
+	vmovdqa	ymm1,YMMWORD[((288-256))+rcx]
+	vmovdqa	ymm2,YMMWORD[((320-256))+rcx]
+	vmovdqa	ymm3,YMMWORD[((352-256))+rcx]
+	vmovdqa	ymm12,YMMWORD[((384-512))+rax]
+	vmovdqa	ymm13,YMMWORD[((416-512))+rax]
+	vmovdqa	ymm14,YMMWORD[((448-512))+rax]
+	vmovdqa	ymm15,YMMWORD[((480-512))+rax]
+	vmovdqa	ymm4,YMMWORD[((512-512))+rax]
+	vmovdqa	ymm5,YMMWORD[((544-512))+rax]
+	vmovdqa	ymm6,YMMWORD[((576-512))+rax]
+	vmovdqa	ymm7,YMMWORD[((608-512))+rax]
+	vpaddd	ymm4,ymm4,YMMWORD[$L$eight]
+
+$L$oop_enter8x:
+	vmovdqa	YMMWORD[64+rsp],ymm14
+	vmovdqa	YMMWORD[96+rsp],ymm15
+	vbroadcasti128	ymm15,YMMWORD[r10]
+	vmovdqa	YMMWORD[(512-512)+rax],ymm4
+	mov	eax,10
+	jmp	NEAR $L$oop8x
+
+ALIGN	32
+$L$oop8x:
+	vpaddd	ymm8,ymm8,ymm0
+	vpxor	ymm4,ymm8,ymm4
+	vpshufb	ymm4,ymm4,ymm15
+	vpaddd	ymm9,ymm9,ymm1
+	vpxor	ymm5,ymm9,ymm5
+	vpshufb	ymm5,ymm5,ymm15
+	vpaddd	ymm12,ymm12,ymm4
+	vpxor	ymm0,ymm12,ymm0
+	vpslld	ymm14,ymm0,12
+	vpsrld	ymm0,ymm0,20
+	vpor	ymm0,ymm14,ymm0
+	vbroadcasti128	ymm14,YMMWORD[r11]
+	vpaddd	ymm13,ymm13,ymm5
+	vpxor	ymm1,ymm13,ymm1
+	vpslld	ymm15,ymm1,12
+	vpsrld	ymm1,ymm1,20
+	vpor	ymm1,ymm15,ymm1
+	vpaddd	ymm8,ymm8,ymm0
+	vpxor	ymm4,ymm8,ymm4
+	vpshufb	ymm4,ymm4,ymm14
+	vpaddd	ymm9,ymm9,ymm1
+	vpxor	ymm5,ymm9,ymm5
+	vpshufb	ymm5,ymm5,ymm14
+	vpaddd	ymm12,ymm12,ymm4
+	vpxor	ymm0,ymm12,ymm0
+	vpslld	ymm15,ymm0,7
+	vpsrld	ymm0,ymm0,25
+	vpor	ymm0,ymm15,ymm0
+	vbroadcasti128	ymm15,YMMWORD[r10]
+	vpaddd	ymm13,ymm13,ymm5
+	vpxor	ymm1,ymm13,ymm1
+	vpslld	ymm14,ymm1,7
+	vpsrld	ymm1,ymm1,25
+	vpor	ymm1,ymm14,ymm1
+	vmovdqa	YMMWORD[rsp],ymm12
+	vmovdqa	YMMWORD[32+rsp],ymm13
+	vmovdqa	ymm12,YMMWORD[64+rsp]
+	vmovdqa	ymm13,YMMWORD[96+rsp]
+	vpaddd	ymm10,ymm10,ymm2
+	vpxor	ymm6,ymm10,ymm6
+	vpshufb	ymm6,ymm6,ymm15
+	vpaddd	ymm11,ymm11,ymm3
+	vpxor	ymm7,ymm11,ymm7
+	vpshufb	ymm7,ymm7,ymm15
+	vpaddd	ymm12,ymm12,ymm6
+	vpxor	ymm2,ymm12,ymm2
+	vpslld	ymm14,ymm2,12
+	vpsrld	ymm2,ymm2,20
+	vpor	ymm2,ymm14,ymm2
+	vbroadcasti128	ymm14,YMMWORD[r11]
+	vpaddd	ymm13,ymm13,ymm7
+	vpxor	ymm3,ymm13,ymm3
+	vpslld	ymm15,ymm3,12
+	vpsrld	ymm3,ymm3,20
+	vpor	ymm3,ymm15,ymm3
+	vpaddd	ymm10,ymm10,ymm2
+	vpxor	ymm6,ymm10,ymm6
+	vpshufb	ymm6,ymm6,ymm14
+	vpaddd	ymm11,ymm11,ymm3
+	vpxor	ymm7,ymm11,ymm7
+	vpshufb	ymm7,ymm7,ymm14
+	vpaddd	ymm12,ymm12,ymm6
+	vpxor	ymm2,ymm12,ymm2
+	vpslld	ymm15,ymm2,7
+	vpsrld	ymm2,ymm2,25
+	vpor	ymm2,ymm15,ymm2
+	vbroadcasti128	ymm15,YMMWORD[r10]
+	vpaddd	ymm13,ymm13,ymm7
+	vpxor	ymm3,ymm13,ymm3
+	vpslld	ymm14,ymm3,7
+	vpsrld	ymm3,ymm3,25
+	vpor	ymm3,ymm14,ymm3
+	vpaddd	ymm8,ymm8,ymm1
+	vpxor	ymm7,ymm8,ymm7
+	vpshufb	ymm7,ymm7,ymm15
+	vpaddd	ymm9,ymm9,ymm2
+	vpxor	ymm4,ymm9,ymm4
+	vpshufb	ymm4,ymm4,ymm15
+	vpaddd	ymm12,ymm12,ymm7
+	vpxor	ymm1,ymm12,ymm1
+	vpslld	ymm14,ymm1,12
+	vpsrld	ymm1,ymm1,20
+	vpor	ymm1,ymm14,ymm1
+	vbroadcasti128	ymm14,YMMWORD[r11]
+	vpaddd	ymm13,ymm13,ymm4
+	vpxor	ymm2,ymm13,ymm2
+	vpslld	ymm15,ymm2,12
+	vpsrld	ymm2,ymm2,20
+	vpor	ymm2,ymm15,ymm2
+	vpaddd	ymm8,ymm8,ymm1
+	vpxor	ymm7,ymm8,ymm7
+	vpshufb	ymm7,ymm7,ymm14
+	vpaddd	ymm9,ymm9,ymm2
+	vpxor	ymm4,ymm9,ymm4
+	vpshufb	ymm4,ymm4,ymm14
+	vpaddd	ymm12,ymm12,ymm7
+	vpxor	ymm1,ymm12,ymm1
+	vpslld	ymm15,ymm1,7
+	vpsrld	ymm1,ymm1,25
+	vpor	ymm1,ymm15,ymm1
+	vbroadcasti128	ymm15,YMMWORD[r10]
+	vpaddd	ymm13,ymm13,ymm4
+	vpxor	ymm2,ymm13,ymm2
+	vpslld	ymm14,ymm2,7
+	vpsrld	ymm2,ymm2,25
+	vpor	ymm2,ymm14,ymm2
+	vmovdqa	YMMWORD[64+rsp],ymm12
+	vmovdqa	YMMWORD[96+rsp],ymm13
+	vmovdqa	ymm12,YMMWORD[rsp]
+	vmovdqa	ymm13,YMMWORD[32+rsp]
+	vpaddd	ymm10,ymm10,ymm3
+	vpxor	ymm5,ymm10,ymm5
+	vpshufb	ymm5,ymm5,ymm15
+	vpaddd	ymm11,ymm11,ymm0
+	vpxor	ymm6,ymm11,ymm6
+	vpshufb	ymm6,ymm6,ymm15
+	vpaddd	ymm12,ymm12,ymm5
+	vpxor	ymm3,ymm12,ymm3
+	vpslld	ymm14,ymm3,12
+	vpsrld	ymm3,ymm3,20
+	vpor	ymm3,ymm14,ymm3
+	vbroadcasti128	ymm14,YMMWORD[r11]
+	vpaddd	ymm13,ymm13,ymm6
+	vpxor	ymm0,ymm13,ymm0
+	vpslld	ymm15,ymm0,12
+	vpsrld	ymm0,ymm0,20
+	vpor	ymm0,ymm15,ymm0
+	vpaddd	ymm10,ymm10,ymm3
+	vpxor	ymm5,ymm10,ymm5
+	vpshufb	ymm5,ymm5,ymm14
+	vpaddd	ymm11,ymm11,ymm0
+	vpxor	ymm6,ymm11,ymm6
+	vpshufb	ymm6,ymm6,ymm14
+	vpaddd	ymm12,ymm12,ymm5
+	vpxor	ymm3,ymm12,ymm3
+	vpslld	ymm15,ymm3,7
+	vpsrld	ymm3,ymm3,25
+	vpor	ymm3,ymm15,ymm3
+	vbroadcasti128	ymm15,YMMWORD[r10]
+	vpaddd	ymm13,ymm13,ymm6
+	vpxor	ymm0,ymm13,ymm0
+	vpslld	ymm14,ymm0,7
+	vpsrld	ymm0,ymm0,25
+	vpor	ymm0,ymm14,ymm0
+	dec	eax
+	jnz	NEAR $L$oop8x
+
+	lea	rax,[512+rsp]
+	vpaddd	ymm8,ymm8,YMMWORD[((128-256))+rcx]
+	vpaddd	ymm9,ymm9,YMMWORD[((160-256))+rcx]
+	vpaddd	ymm10,ymm10,YMMWORD[((192-256))+rcx]
+	vpaddd	ymm11,ymm11,YMMWORD[((224-256))+rcx]
+
+	vpunpckldq	ymm14,ymm8,ymm9
+	vpunpckldq	ymm15,ymm10,ymm11
+	vpunpckhdq	ymm8,ymm8,ymm9
+	vpunpckhdq	ymm10,ymm10,ymm11
+	vpunpcklqdq	ymm9,ymm14,ymm15
+	vpunpckhqdq	ymm14,ymm14,ymm15
+	vpunpcklqdq	ymm11,ymm8,ymm10
+	vpunpckhqdq	ymm8,ymm8,ymm10
+	vpaddd	ymm0,ymm0,YMMWORD[((256-256))+rcx]
+	vpaddd	ymm1,ymm1,YMMWORD[((288-256))+rcx]
+	vpaddd	ymm2,ymm2,YMMWORD[((320-256))+rcx]
+	vpaddd	ymm3,ymm3,YMMWORD[((352-256))+rcx]
+
+	vpunpckldq	ymm10,ymm0,ymm1
+	vpunpckldq	ymm15,ymm2,ymm3
+	vpunpckhdq	ymm0,ymm0,ymm1
+	vpunpckhdq	ymm2,ymm2,ymm3
+	vpunpcklqdq	ymm1,ymm10,ymm15
+	vpunpckhqdq	ymm10,ymm10,ymm15
+	vpunpcklqdq	ymm3,ymm0,ymm2
+	vpunpckhqdq	ymm0,ymm0,ymm2
+	vperm2i128	ymm15,ymm9,ymm1,0x20
+	vperm2i128	ymm1,ymm9,ymm1,0x31
+	vperm2i128	ymm9,ymm14,ymm10,0x20
+	vperm2i128	ymm10,ymm14,ymm10,0x31
+	vperm2i128	ymm14,ymm11,ymm3,0x20
+	vperm2i128	ymm3,ymm11,ymm3,0x31
+	vperm2i128	ymm11,ymm8,ymm0,0x20
+	vperm2i128	ymm0,ymm8,ymm0,0x31
+	vmovdqa	YMMWORD[rsp],ymm15
+	vmovdqa	YMMWORD[32+rsp],ymm9
+	vmovdqa	ymm15,YMMWORD[64+rsp]
+	vmovdqa	ymm9,YMMWORD[96+rsp]
+
+	vpaddd	ymm12,ymm12,YMMWORD[((384-512))+rax]
+	vpaddd	ymm13,ymm13,YMMWORD[((416-512))+rax]
+	vpaddd	ymm15,ymm15,YMMWORD[((448-512))+rax]
+	vpaddd	ymm9,ymm9,YMMWORD[((480-512))+rax]
+
+	vpunpckldq	ymm2,ymm12,ymm13
+	vpunpckldq	ymm8,ymm15,ymm9
+	vpunpckhdq	ymm12,ymm12,ymm13
+	vpunpckhdq	ymm15,ymm15,ymm9
+	vpunpcklqdq	ymm13,ymm2,ymm8
+	vpunpckhqdq	ymm2,ymm2,ymm8
+	vpunpcklqdq	ymm9,ymm12,ymm15
+	vpunpckhqdq	ymm12,ymm12,ymm15
+	vpaddd	ymm4,ymm4,YMMWORD[((512-512))+rax]
+	vpaddd	ymm5,ymm5,YMMWORD[((544-512))+rax]
+	vpaddd	ymm6,ymm6,YMMWORD[((576-512))+rax]
+	vpaddd	ymm7,ymm7,YMMWORD[((608-512))+rax]
+
+	vpunpckldq	ymm15,ymm4,ymm5
+	vpunpckldq	ymm8,ymm6,ymm7
+	vpunpckhdq	ymm4,ymm4,ymm5
+	vpunpckhdq	ymm6,ymm6,ymm7
+	vpunpcklqdq	ymm5,ymm15,ymm8
+	vpunpckhqdq	ymm15,ymm15,ymm8
+	vpunpcklqdq	ymm7,ymm4,ymm6
+	vpunpckhqdq	ymm4,ymm4,ymm6
+	vperm2i128	ymm8,ymm13,ymm5,0x20
+	vperm2i128	ymm5,ymm13,ymm5,0x31
+	vperm2i128	ymm13,ymm2,ymm15,0x20
+	vperm2i128	ymm15,ymm2,ymm15,0x31
+	vperm2i128	ymm2,ymm9,ymm7,0x20
+	vperm2i128	ymm7,ymm9,ymm7,0x31
+	vperm2i128	ymm9,ymm12,ymm4,0x20
+	vperm2i128	ymm4,ymm12,ymm4,0x31
+	vmovdqa	ymm6,YMMWORD[rsp]
+	vmovdqa	ymm12,YMMWORD[32+rsp]
+
+	cmp	rdx,64*8
+	jb	NEAR $L$tail8x
+
+	vpxor	ymm6,ymm6,YMMWORD[rsi]
+	vpxor	ymm8,ymm8,YMMWORD[32+rsi]
+	vpxor	ymm1,ymm1,YMMWORD[64+rsi]
+	vpxor	ymm5,ymm5,YMMWORD[96+rsi]
+	lea	rsi,[128+rsi]
+	vmovdqu	YMMWORD[rdi],ymm6
+	vmovdqu	YMMWORD[32+rdi],ymm8
+	vmovdqu	YMMWORD[64+rdi],ymm1
+	vmovdqu	YMMWORD[96+rdi],ymm5
+	lea	rdi,[128+rdi]
+
+	vpxor	ymm12,ymm12,YMMWORD[rsi]
+	vpxor	ymm13,ymm13,YMMWORD[32+rsi]
+	vpxor	ymm10,ymm10,YMMWORD[64+rsi]
+	vpxor	ymm15,ymm15,YMMWORD[96+rsi]
+	lea	rsi,[128+rsi]
+	vmovdqu	YMMWORD[rdi],ymm12
+	vmovdqu	YMMWORD[32+rdi],ymm13
+	vmovdqu	YMMWORD[64+rdi],ymm10
+	vmovdqu	YMMWORD[96+rdi],ymm15
+	lea	rdi,[128+rdi]
+
+	vpxor	ymm14,ymm14,YMMWORD[rsi]
+	vpxor	ymm2,ymm2,YMMWORD[32+rsi]
+	vpxor	ymm3,ymm3,YMMWORD[64+rsi]
+	vpxor	ymm7,ymm7,YMMWORD[96+rsi]
+	lea	rsi,[128+rsi]
+	vmovdqu	YMMWORD[rdi],ymm14
+	vmovdqu	YMMWORD[32+rdi],ymm2
+	vmovdqu	YMMWORD[64+rdi],ymm3
+	vmovdqu	YMMWORD[96+rdi],ymm7
+	lea	rdi,[128+rdi]
+
+	vpxor	ymm11,ymm11,YMMWORD[rsi]
+	vpxor	ymm9,ymm9,YMMWORD[32+rsi]
+	vpxor	ymm0,ymm0,YMMWORD[64+rsi]
+	vpxor	ymm4,ymm4,YMMWORD[96+rsi]
+	lea	rsi,[128+rsi]
+	vmovdqu	YMMWORD[rdi],ymm11
+	vmovdqu	YMMWORD[32+rdi],ymm9
+	vmovdqu	YMMWORD[64+rdi],ymm0
+	vmovdqu	YMMWORD[96+rdi],ymm4
+	lea	rdi,[128+rdi]
+
+	sub	rdx,64*8
+	jnz	NEAR $L$oop_outer8x
+
+	jmp	NEAR $L$done8x
+
+$L$tail8x:
+	cmp	rdx,448
+	jae	NEAR $L$448_or_more8x
+	cmp	rdx,384
+	jae	NEAR $L$384_or_more8x
+	cmp	rdx,320
+	jae	NEAR $L$320_or_more8x
+	cmp	rdx,256
+	jae	NEAR $L$256_or_more8x
+	cmp	rdx,192
+	jae	NEAR $L$192_or_more8x
+	cmp	rdx,128
+	jae	NEAR $L$128_or_more8x
+	cmp	rdx,64
+	jae	NEAR $L$64_or_more8x
+
+	xor	r10,r10
+	vmovdqa	YMMWORD[rsp],ymm6
+	vmovdqa	YMMWORD[32+rsp],ymm8
+	jmp	NEAR $L$oop_tail8x
+
+ALIGN	32
+$L$64_or_more8x:
+	vpxor	ymm6,ymm6,YMMWORD[rsi]
+	vpxor	ymm8,ymm8,YMMWORD[32+rsi]
+	vmovdqu	YMMWORD[rdi],ymm6
+	vmovdqu	YMMWORD[32+rdi],ymm8
+	je	NEAR $L$done8x
+
+	lea	rsi,[64+rsi]
+	xor	r10,r10
+	vmovdqa	YMMWORD[rsp],ymm1
+	lea	rdi,[64+rdi]
+	sub	rdx,64
+	vmovdqa	YMMWORD[32+rsp],ymm5
+	jmp	NEAR $L$oop_tail8x
+
+ALIGN	32
+$L$128_or_more8x:
+	vpxor	ymm6,ymm6,YMMWORD[rsi]
+	vpxor	ymm8,ymm8,YMMWORD[32+rsi]
+	vpxor	ymm1,ymm1,YMMWORD[64+rsi]
+	vpxor	ymm5,ymm5,YMMWORD[96+rsi]
+	vmovdqu	YMMWORD[rdi],ymm6
+	vmovdqu	YMMWORD[32+rdi],ymm8
+	vmovdqu	YMMWORD[64+rdi],ymm1
+	vmovdqu	YMMWORD[96+rdi],ymm5
+	je	NEAR $L$done8x
+
+	lea	rsi,[128+rsi]
+	xor	r10,r10
+	vmovdqa	YMMWORD[rsp],ymm12
+	lea	rdi,[128+rdi]
+	sub	rdx,128
+	vmovdqa	YMMWORD[32+rsp],ymm13
+	jmp	NEAR $L$oop_tail8x
+
+ALIGN	32
+$L$192_or_more8x:
+	vpxor	ymm6,ymm6,YMMWORD[rsi]
+	vpxor	ymm8,ymm8,YMMWORD[32+rsi]
+	vpxor	ymm1,ymm1,YMMWORD[64+rsi]
+	vpxor	ymm5,ymm5,YMMWORD[96+rsi]
+	vpxor	ymm12,ymm12,YMMWORD[128+rsi]
+	vpxor	ymm13,ymm13,YMMWORD[160+rsi]
+	vmovdqu	YMMWORD[rdi],ymm6
+	vmovdqu	YMMWORD[32+rdi],ymm8
+	vmovdqu	YMMWORD[64+rdi],ymm1
+	vmovdqu	YMMWORD[96+rdi],ymm5
+	vmovdqu	YMMWORD[128+rdi],ymm12
+	vmovdqu	YMMWORD[160+rdi],ymm13
+	je	NEAR $L$done8x
+
+	lea	rsi,[192+rsi]
+	xor	r10,r10
+	vmovdqa	YMMWORD[rsp],ymm10
+	lea	rdi,[192+rdi]
+	sub	rdx,192
+	vmovdqa	YMMWORD[32+rsp],ymm15
+	jmp	NEAR $L$oop_tail8x
+
+ALIGN	32
+$L$256_or_more8x:
+	vpxor	ymm6,ymm6,YMMWORD[rsi]
+	vpxor	ymm8,ymm8,YMMWORD[32+rsi]
+	vpxor	ymm1,ymm1,YMMWORD[64+rsi]
+	vpxor	ymm5,ymm5,YMMWORD[96+rsi]
+	vpxor	ymm12,ymm12,YMMWORD[128+rsi]
+	vpxor	ymm13,ymm13,YMMWORD[160+rsi]
+	vpxor	ymm10,ymm10,YMMWORD[192+rsi]
+	vpxor	ymm15,ymm15,YMMWORD[224+rsi]
+	vmovdqu	YMMWORD[rdi],ymm6
+	vmovdqu	YMMWORD[32+rdi],ymm8
+	vmovdqu	YMMWORD[64+rdi],ymm1
+	vmovdqu	YMMWORD[96+rdi],ymm5
+	vmovdqu	YMMWORD[128+rdi],ymm12
+	vmovdqu	YMMWORD[160+rdi],ymm13
+	vmovdqu	YMMWORD[192+rdi],ymm10
+	vmovdqu	YMMWORD[224+rdi],ymm15
+	je	NEAR $L$done8x
+
+	lea	rsi,[256+rsi]
+	xor	r10,r10
+	vmovdqa	YMMWORD[rsp],ymm14
+	lea	rdi,[256+rdi]
+	sub	rdx,256
+	vmovdqa	YMMWORD[32+rsp],ymm2
+	jmp	NEAR $L$oop_tail8x
+
+ALIGN	32
+$L$320_or_more8x:
+	vpxor	ymm6,ymm6,YMMWORD[rsi]
+	vpxor	ymm8,ymm8,YMMWORD[32+rsi]
+	vpxor	ymm1,ymm1,YMMWORD[64+rsi]
+	vpxor	ymm5,ymm5,YMMWORD[96+rsi]
+	vpxor	ymm12,ymm12,YMMWORD[128+rsi]
+	vpxor	ymm13,ymm13,YMMWORD[160+rsi]
+	vpxor	ymm10,ymm10,YMMWORD[192+rsi]
+	vpxor	ymm15,ymm15,YMMWORD[224+rsi]
+	vpxor	ymm14,ymm14,YMMWORD[256+rsi]
+	vpxor	ymm2,ymm2,YMMWORD[288+rsi]
+	vmovdqu	YMMWORD[rdi],ymm6
+	vmovdqu	YMMWORD[32+rdi],ymm8
+	vmovdqu	YMMWORD[64+rdi],ymm1
+	vmovdqu	YMMWORD[96+rdi],ymm5
+	vmovdqu	YMMWORD[128+rdi],ymm12
+	vmovdqu	YMMWORD[160+rdi],ymm13
+	vmovdqu	YMMWORD[192+rdi],ymm10
+	vmovdqu	YMMWORD[224+rdi],ymm15
+	vmovdqu	YMMWORD[256+rdi],ymm14
+	vmovdqu	YMMWORD[288+rdi],ymm2
+	je	NEAR $L$done8x
+
+	lea	rsi,[320+rsi]
+	xor	r10,r10
+	vmovdqa	YMMWORD[rsp],ymm3
+	lea	rdi,[320+rdi]
+	sub	rdx,320
+	vmovdqa	YMMWORD[32+rsp],ymm7
+	jmp	NEAR $L$oop_tail8x
+
+ALIGN	32
+$L$384_or_more8x:
+	vpxor	ymm6,ymm6,YMMWORD[rsi]
+	vpxor	ymm8,ymm8,YMMWORD[32+rsi]
+	vpxor	ymm1,ymm1,YMMWORD[64+rsi]
+	vpxor	ymm5,ymm5,YMMWORD[96+rsi]
+	vpxor	ymm12,ymm12,YMMWORD[128+rsi]
+	vpxor	ymm13,ymm13,YMMWORD[160+rsi]
+	vpxor	ymm10,ymm10,YMMWORD[192+rsi]
+	vpxor	ymm15,ymm15,YMMWORD[224+rsi]
+	vpxor	ymm14,ymm14,YMMWORD[256+rsi]
+	vpxor	ymm2,ymm2,YMMWORD[288+rsi]
+	vpxor	ymm3,ymm3,YMMWORD[320+rsi]
+	vpxor	ymm7,ymm7,YMMWORD[352+rsi]
+	vmovdqu	YMMWORD[rdi],ymm6
+	vmovdqu	YMMWORD[32+rdi],ymm8
+	vmovdqu	YMMWORD[64+rdi],ymm1
+	vmovdqu	YMMWORD[96+rdi],ymm5
+	vmovdqu	YMMWORD[128+rdi],ymm12
+	vmovdqu	YMMWORD[160+rdi],ymm13
+	vmovdqu	YMMWORD[192+rdi],ymm10
+	vmovdqu	YMMWORD[224+rdi],ymm15
+	vmovdqu	YMMWORD[256+rdi],ymm14
+	vmovdqu	YMMWORD[288+rdi],ymm2
+	vmovdqu	YMMWORD[320+rdi],ymm3
+	vmovdqu	YMMWORD[352+rdi],ymm7
+	je	NEAR $L$done8x
+
+	lea	rsi,[384+rsi]
+	xor	r10,r10
+	vmovdqa	YMMWORD[rsp],ymm11
+	lea	rdi,[384+rdi]
+	sub	rdx,384
+	vmovdqa	YMMWORD[32+rsp],ymm9
+	jmp	NEAR $L$oop_tail8x
+
+ALIGN	32
+$L$448_or_more8x:
+	vpxor	ymm6,ymm6,YMMWORD[rsi]
+	vpxor	ymm8,ymm8,YMMWORD[32+rsi]
+	vpxor	ymm1,ymm1,YMMWORD[64+rsi]
+	vpxor	ymm5,ymm5,YMMWORD[96+rsi]
+	vpxor	ymm12,ymm12,YMMWORD[128+rsi]
+	vpxor	ymm13,ymm13,YMMWORD[160+rsi]
+	vpxor	ymm10,ymm10,YMMWORD[192+rsi]
+	vpxor	ymm15,ymm15,YMMWORD[224+rsi]
+	vpxor	ymm14,ymm14,YMMWORD[256+rsi]
+	vpxor	ymm2,ymm2,YMMWORD[288+rsi]
+	vpxor	ymm3,ymm3,YMMWORD[320+rsi]
+	vpxor	ymm7,ymm7,YMMWORD[352+rsi]
+	vpxor	ymm11,ymm11,YMMWORD[384+rsi]
+	vpxor	ymm9,ymm9,YMMWORD[416+rsi]
+	vmovdqu	YMMWORD[rdi],ymm6
+	vmovdqu	YMMWORD[32+rdi],ymm8
+	vmovdqu	YMMWORD[64+rdi],ymm1
+	vmovdqu	YMMWORD[96+rdi],ymm5
+	vmovdqu	YMMWORD[128+rdi],ymm12
+	vmovdqu	YMMWORD[160+rdi],ymm13
+	vmovdqu	YMMWORD[192+rdi],ymm10
+	vmovdqu	YMMWORD[224+rdi],ymm15
+	vmovdqu	YMMWORD[256+rdi],ymm14
+	vmovdqu	YMMWORD[288+rdi],ymm2
+	vmovdqu	YMMWORD[320+rdi],ymm3
+	vmovdqu	YMMWORD[352+rdi],ymm7
+	vmovdqu	YMMWORD[384+rdi],ymm11
+	vmovdqu	YMMWORD[416+rdi],ymm9
+	je	NEAR $L$done8x
+
+	lea	rsi,[448+rsi]
+	xor	r10,r10
+	vmovdqa	YMMWORD[rsp],ymm0
+	lea	rdi,[448+rdi]
+	sub	rdx,448
+	vmovdqa	YMMWORD[32+rsp],ymm4
+
+$L$oop_tail8x:
+	movzx	eax,BYTE[r10*1+rsi]
+	movzx	ecx,BYTE[r10*1+rsp]
+	lea	r10,[1+r10]
+	xor	eax,ecx
+	mov	BYTE[((-1))+r10*1+rdi],al
+	dec	rdx
+	jnz	NEAR $L$oop_tail8x
+
+$L$done8x:
+	vzeroall
+	lea	r11,[((656+48))+rsp]
+	movaps	xmm6,XMMWORD[((-48))+r11]
+	movaps	xmm7,XMMWORD[((-32))+r11]
+	movaps	xmm8,XMMWORD[((-16))+r11]
+	movaps	xmm9,XMMWORD[r11]
+	movaps	xmm10,XMMWORD[16+r11]
+	movaps	xmm11,XMMWORD[32+r11]
+	movaps	xmm12,XMMWORD[48+r11]
+	movaps	xmm13,XMMWORD[64+r11]
+	movaps	xmm14,XMMWORD[80+r11]
+	movaps	xmm15,XMMWORD[96+r11]
+	mov	rsp,QWORD[640+rsp]
+	mov	rdi,QWORD[8+rsp]	;WIN64 epilogue
+	mov	rsi,QWORD[16+rsp]
+	DB	0F3h,0C3h		;repret
+$L$SEH_end_ChaCha20_8x:
diff --git a/packager/third_party/boringssl/win-x86_64/crypto/ec/p256-x86_64-asm.asm b/packager/third_party/boringssl/win-x86_64/crypto/ec/p256-x86_64-asm.asm
new file mode 100644
index 0000000000..a2e4075819
--- /dev/null
+++ b/packager/third_party/boringssl/win-x86_64/crypto/ec/p256-x86_64-asm.asm
@@ -0,0 +1,1925 @@
+default	rel
+%define XMMWORD
+%define YMMWORD
+%define ZMMWORD
+section	.text code align=64
+
+EXTERN	OPENSSL_ia32cap_P
+
+
+ALIGN	64
+$L$poly:
+	DQ	0xffffffffffffffff,0x00000000ffffffff,0x0000000000000000,0xffffffff00000001
+
+$L$One:
+	DD	1,1,1,1,1,1,1,1
+$L$Two:
+	DD	2,2,2,2,2,2,2,2
+$L$Three:
+	DD	3,3,3,3,3,3,3,3
+$L$ONE_mont:
+	DQ	0x0000000000000001,0xffffffff00000000,0xffffffffffffffff,0x00000000fffffffe
+
+
+ALIGN	64
+ecp_nistz256_mul_by_2:
+	mov	QWORD[8+rsp],rdi	;WIN64 prologue
+	mov	QWORD[16+rsp],rsi
+	mov	rax,rsp
+$L$SEH_begin_ecp_nistz256_mul_by_2:
+	mov	rdi,rcx
+	mov	rsi,rdx
+
+
+	push	r12
+	push	r13
+
+	mov	r8,QWORD[rsi]
+	mov	r9,QWORD[8+rsi]
+	add	r8,r8
+	mov	r10,QWORD[16+rsi]
+	adc	r9,r9
+	mov	r11,QWORD[24+rsi]
+	lea	rsi,[$L$poly]
+	mov	rax,r8
+	adc	r10,r10
+	adc	r11,r11
+	mov	rdx,r9
+	sbb	r13,r13
+
+	sub	r8,QWORD[rsi]
+	mov	rcx,r10
+	sbb	r9,QWORD[8+rsi]
+	sbb	r10,QWORD[16+rsi]
+	mov	r12,r11
+	sbb	r11,QWORD[24+rsi]
+	test	r13,r13
+
+	cmovz	r8,rax
+	cmovz	r9,rdx
+	mov	QWORD[rdi],r8
+	cmovz	r10,rcx
+	mov	QWORD[8+rdi],r9
+	cmovz	r11,r12
+	mov	QWORD[16+rdi],r10
+	mov	QWORD[24+rdi],r11
+
+	pop	r13
+	pop	r12
+	mov	rdi,QWORD[8+rsp]	;WIN64 epilogue
+	mov	rsi,QWORD[16+rsp]
+	DB	0F3h,0C3h		;repret
+$L$SEH_end_ecp_nistz256_mul_by_2:
+
+
+
+global	ecp_nistz256_neg
+
+ALIGN	32
+ecp_nistz256_neg:
+	mov	QWORD[8+rsp],rdi	;WIN64 prologue
+	mov	QWORD[16+rsp],rsi
+	mov	rax,rsp
+$L$SEH_begin_ecp_nistz256_neg:
+	mov	rdi,rcx
+	mov	rsi,rdx
+
+
+	push	r12
+	push	r13
+
+	xor	r8,r8
+	xor	r9,r9
+	xor	r10,r10
+	xor	r11,r11
+	xor	r13,r13
+
+	sub	r8,QWORD[rsi]
+	sbb	r9,QWORD[8+rsi]
+	sbb	r10,QWORD[16+rsi]
+	mov	rax,r8
+	sbb	r11,QWORD[24+rsi]
+	lea	rsi,[$L$poly]
+	mov	rdx,r9
+	sbb	r13,0
+
+	add	r8,QWORD[rsi]
+	mov	rcx,r10
+	adc	r9,QWORD[8+rsi]
+	adc	r10,QWORD[16+rsi]
+	mov	r12,r11
+	adc	r11,QWORD[24+rsi]
+	test	r13,r13
+
+	cmovz	r8,rax
+	cmovz	r9,rdx
+	mov	QWORD[rdi],r8
+	cmovz	r10,rcx
+	mov	QWORD[8+rdi],r9
+	cmovz	r11,r12
+	mov	QWORD[16+rdi],r10
+	mov	QWORD[24+rdi],r11
+
+	pop	r13
+	pop	r12
+	mov	rdi,QWORD[8+rsp]	;WIN64 epilogue
+	mov	rsi,QWORD[16+rsp]
+	DB	0F3h,0C3h		;repret
+$L$SEH_end_ecp_nistz256_neg:
+
+
+
+
+
+
+global	ecp_nistz256_mul_mont
+
+ALIGN	32
+ecp_nistz256_mul_mont:
+	mov	QWORD[8+rsp],rdi	;WIN64 prologue
+	mov	QWORD[16+rsp],rsi
+	mov	rax,rsp
+$L$SEH_begin_ecp_nistz256_mul_mont:
+	mov	rdi,rcx
+	mov	rsi,rdx
+	mov	rdx,r8
+
+
+$L$mul_mont:
+	push	rbp
+	push	rbx
+	push	r12
+	push	r13
+	push	r14
+	push	r15
+	mov	rbx,rdx
+	mov	rax,QWORD[rdx]
+	mov	r9,QWORD[rsi]
+	mov	r10,QWORD[8+rsi]
+	mov	r11,QWORD[16+rsi]
+	mov	r12,QWORD[24+rsi]
+
+	call	__ecp_nistz256_mul_montq
+$L$mul_mont_done:
+	pop	r15
+	pop	r14
+	pop	r13
+	pop	r12
+	pop	rbx
+	pop	rbp
+	mov	rdi,QWORD[8+rsp]	;WIN64 epilogue
+	mov	rsi,QWORD[16+rsp]
+	DB	0F3h,0C3h		;repret
+$L$SEH_end_ecp_nistz256_mul_mont:
+
+
+ALIGN	32
+__ecp_nistz256_mul_montq:
+
+
+	mov	rbp,rax
+	mul	r9
+	mov	r14,QWORD[(($L$poly+8))]
+	mov	r8,rax
+	mov	rax,rbp
+	mov	r9,rdx
+
+	mul	r10
+	mov	r15,QWORD[(($L$poly+24))]
+	add	r9,rax
+	mov	rax,rbp
+	adc	rdx,0
+	mov	r10,rdx
+
+	mul	r11
+	add	r10,rax
+	mov	rax,rbp
+	adc	rdx,0
+	mov	r11,rdx
+
+	mul	r12
+	add	r11,rax
+	mov	rax,r8
+	adc	rdx,0
+	xor	r13,r13
+	mov	r12,rdx
+
+
+
+
+
+
+
+
+
+
+	mov	rbp,r8
+	shl	r8,32
+	mul	r15
+	shr	rbp,32
+	add	r9,r8
+	adc	r10,rbp
+	adc	r11,rax
+	mov	rax,QWORD[8+rbx]
+	adc	r12,rdx
+	adc	r13,0
+	xor	r8,r8
+
+
+
+	mov	rbp,rax
+	mul	QWORD[rsi]
+	add	r9,rax
+	mov	rax,rbp
+	adc	rdx,0
+	mov	rcx,rdx
+
+	mul	QWORD[8+rsi]
+	add	r10,rcx
+	adc	rdx,0
+	add	r10,rax
+	mov	rax,rbp
+	adc	rdx,0
+	mov	rcx,rdx
+
+	mul	QWORD[16+rsi]
+	add	r11,rcx
+	adc	rdx,0
+	add	r11,rax
+	mov	rax,rbp
+	adc	rdx,0
+	mov	rcx,rdx
+
+	mul	QWORD[24+rsi]
+	add	r12,rcx
+	adc	rdx,0
+	add	r12,rax
+	mov	rax,r9
+	adc	r13,rdx
+	adc	r8,0
+
+
+
+	mov	rbp,r9
+	shl	r9,32
+	mul	r15
+	shr	rbp,32
+	add	r10,r9
+	adc	r11,rbp
+	adc	r12,rax
+	mov	rax,QWORD[16+rbx]
+	adc	r13,rdx
+	adc	r8,0
+	xor	r9,r9
+
+
+
+	mov	rbp,rax
+	mul	QWORD[rsi]
+	add	r10,rax
+	mov	rax,rbp
+	adc	rdx,0
+	mov	rcx,rdx
+
+	mul	QWORD[8+rsi]
+	add	r11,rcx
+	adc	rdx,0
+	add	r11,rax
+	mov	rax,rbp
+	adc	rdx,0
+	mov	rcx,rdx
+
+	mul	QWORD[16+rsi]
+	add	r12,rcx
+	adc	rdx,0
+	add	r12,rax
+	mov	rax,rbp
+	adc	rdx,0
+	mov	rcx,rdx
+
+	mul	QWORD[24+rsi]
+	add	r13,rcx
+	adc	rdx,0
+	add	r13,rax
+	mov	rax,r10
+	adc	r8,rdx
+	adc	r9,0
+
+
+
+	mov	rbp,r10
+	shl	r10,32
+	mul	r15
+	shr	rbp,32
+	add	r11,r10
+	adc	r12,rbp
+	adc	r13,rax
+	mov	rax,QWORD[24+rbx]
+	adc	r8,rdx
+	adc	r9,0
+	xor	r10,r10
+
+
+
+	mov	rbp,rax
+	mul	QWORD[rsi]
+	add	r11,rax
+	mov	rax,rbp
+	adc	rdx,0
+	mov	rcx,rdx
+
+	mul	QWORD[8+rsi]
+	add	r12,rcx
+	adc	rdx,0
+	add	r12,rax
+	mov	rax,rbp
+	adc	rdx,0
+	mov	rcx,rdx
+
+	mul	QWORD[16+rsi]
+	add	r13,rcx
+	adc	rdx,0
+	add	r13,rax
+	mov	rax,rbp
+	adc	rdx,0
+	mov	rcx,rdx
+
+	mul	QWORD[24+rsi]
+	add	r8,rcx
+	adc	rdx,0
+	add	r8,rax
+	mov	rax,r11
+	adc	r9,rdx
+	adc	r10,0
+
+
+
+	mov	rbp,r11
+	shl	r11,32
+	mul	r15
+	shr	rbp,32
+	add	r12,r11
+	adc	r13,rbp
+	mov	rcx,r12
+	adc	r8,rax
+	adc	r9,rdx
+	mov	rbp,r13
+	adc	r10,0
+
+
+
+	sub	r12,-1
+	mov	rbx,r8
+	sbb	r13,r14
+	sbb	r8,0
+	mov	rdx,r9
+	sbb	r9,r15
+	sbb	r10,0
+
+	cmovc	r12,rcx
+	cmovc	r13,rbp
+	mov	QWORD[rdi],r12
+	cmovc	r8,rbx
+	mov	QWORD[8+rdi],r13
+	cmovc	r9,rdx
+	mov	QWORD[16+rdi],r8
+	mov	QWORD[24+rdi],r9
+
+	DB	0F3h,0C3h		;repret
+
+
+
+
+
+
+
+
+
+global	ecp_nistz256_sqr_mont
+
+ALIGN	32
+ecp_nistz256_sqr_mont:
+	mov	QWORD[8+rsp],rdi	;WIN64 prologue
+	mov	QWORD[16+rsp],rsi
+	mov	rax,rsp
+$L$SEH_begin_ecp_nistz256_sqr_mont:
+	mov	rdi,rcx
+	mov	rsi,rdx
+
+
+	push	rbp
+	push	rbx
+	push	r12
+	push	r13
+	push	r14
+	push	r15
+	mov	rax,QWORD[rsi]
+	mov	r14,QWORD[8+rsi]
+	mov	r15,QWORD[16+rsi]
+	mov	r8,QWORD[24+rsi]
+
+	call	__ecp_nistz256_sqr_montq
+$L$sqr_mont_done:
+	pop	r15
+	pop	r14
+	pop	r13
+	pop	r12
+	pop	rbx
+	pop	rbp
+	mov	rdi,QWORD[8+rsp]	;WIN64 epilogue
+	mov	rsi,QWORD[16+rsp]
+	DB	0F3h,0C3h		;repret
+$L$SEH_end_ecp_nistz256_sqr_mont:
+
+
+ALIGN	32
+__ecp_nistz256_sqr_montq:
+	mov	r13,rax
+	mul	r14
+	mov	r9,rax
+	mov	rax,r15
+	mov	r10,rdx
+
+	mul	r13
+	add	r10,rax
+	mov	rax,r8
+	adc	rdx,0
+	mov	r11,rdx
+
+	mul	r13
+	add	r11,rax
+	mov	rax,r15
+	adc	rdx,0
+	mov	r12,rdx
+
+
+	mul	r14
+	add	r11,rax
+	mov	rax,r8
+	adc	rdx,0
+	mov	rbp,rdx
+
+	mul	r14
+	add	r12,rax
+	mov	rax,r8
+	adc	rdx,0
+	add	r12,rbp
+	mov	r13,rdx
+	adc	r13,0
+
+
+	mul	r15
+	xor	r15,r15
+	add	r13,rax
+	mov	rax,QWORD[rsi]
+	mov	r14,rdx
+	adc	r14,0
+
+	add	r9,r9
+	adc	r10,r10
+	adc	r11,r11
+	adc	r12,r12
+	adc	r13,r13
+	adc	r14,r14
+	adc	r15,0
+
+	mul	rax
+	mov	r8,rax
+	mov	rax,QWORD[8+rsi]
+	mov	rcx,rdx
+
+	mul	rax
+	add	r9,rcx
+	adc	r10,rax
+	mov	rax,QWORD[16+rsi]
+	adc	rdx,0
+	mov	rcx,rdx
+
+	mul	rax
+	add	r11,rcx
+	adc	r12,rax
+	mov	rax,QWORD[24+rsi]
+	adc	rdx,0
+	mov	rcx,rdx
+
+	mul	rax
+	add	r13,rcx
+	adc	r14,rax
+	mov	rax,r8
+	adc	r15,rdx
+
+	mov	rsi,QWORD[(($L$poly+8))]
+	mov	rbp,QWORD[(($L$poly+24))]
+
+
+
+
+	mov	rcx,r8
+	shl	r8,32
+	mul	rbp
+	shr	rcx,32
+	add	r9,r8
+	adc	r10,rcx
+	adc	r11,rax
+	mov	rax,r9
+	adc	rdx,0
+
+
+
+	mov	rcx,r9
+	shl	r9,32
+	mov	r8,rdx
+	mul	rbp
+	shr	rcx,32
+	add	r10,r9
+	adc	r11,rcx
+	adc	r8,rax
+	mov	rax,r10
+	adc	rdx,0
+
+
+
+	mov	rcx,r10
+	shl	r10,32
+	mov	r9,rdx
+	mul	rbp
+	shr	rcx,32
+	add	r11,r10
+	adc	r8,rcx
+	adc	r9,rax
+	mov	rax,r11
+	adc	rdx,0
+
+
+
+	mov	rcx,r11
+	shl	r11,32
+	mov	r10,rdx
+	mul	rbp
+	shr	rcx,32
+	add	r8,r11
+	adc	r9,rcx
+	adc	r10,rax
+	adc	rdx,0
+	xor	r11,r11
+
+
+
+	add	r12,r8
+	adc	r13,r9
+	mov	r8,r12
+	adc	r14,r10
+	adc	r15,rdx
+	mov	r9,r13
+	adc	r11,0
+
+	sub	r12,-1
+	mov	r10,r14
+	sbb	r13,rsi
+	sbb	r14,0
+	mov	rcx,r15
+	sbb	r15,rbp
+	sbb	r11,0
+
+	cmovc	r12,r8
+	cmovc	r13,r9
+	mov	QWORD[rdi],r12
+	cmovc	r14,r10
+	mov	QWORD[8+rdi],r13
+	cmovc	r15,rcx
+	mov	QWORD[16+rdi],r14
+	mov	QWORD[24+rdi],r15
+
+	DB	0F3h,0C3h		;repret
+
+
+
+
+
+
+
+global	ecp_nistz256_from_mont
+
+ALIGN	32
+ecp_nistz256_from_mont:
+	mov	QWORD[8+rsp],rdi	;WIN64 prologue
+	mov	QWORD[16+rsp],rsi
+	mov	rax,rsp
+$L$SEH_begin_ecp_nistz256_from_mont:
+	mov	rdi,rcx
+	mov	rsi,rdx
+
+
+	push	r12
+	push	r13
+
+	mov	rax,QWORD[rsi]
+	mov	r13,QWORD[(($L$poly+24))]
+	mov	r9,QWORD[8+rsi]
+	mov	r10,QWORD[16+rsi]
+	mov	r11,QWORD[24+rsi]
+	mov	r8,rax
+	mov	r12,QWORD[(($L$poly+8))]
+
+
+
+	mov	rcx,rax
+	shl	r8,32
+	mul	r13
+	shr	rcx,32
+	add	r9,r8
+	adc	r10,rcx
+	adc	r11,rax
+	mov	rax,r9
+	adc	rdx,0
+
+
+
+	mov	rcx,r9
+	shl	r9,32
+	mov	r8,rdx
+	mul	r13
+	shr	rcx,32
+	add	r10,r9
+	adc	r11,rcx
+	adc	r8,rax
+	mov	rax,r10
+	adc	rdx,0
+
+
+
+	mov	rcx,r10
+	shl	r10,32
+	mov	r9,rdx
+	mul	r13
+	shr	rcx,32
+	add	r11,r10
+	adc	r8,rcx
+	adc	r9,rax
+	mov	rax,r11
+	adc	rdx,0
+
+
+
+	mov	rcx,r11
+	shl	r11,32
+	mov	r10,rdx
+	mul	r13
+	shr	rcx,32
+	add	r8,r11
+	adc	r9,rcx
+	mov	rcx,r8
+	adc	r10,rax
+	mov	rsi,r9
+	adc	rdx,0
+
+	sub	r8,-1
+	mov	rax,r10
+	sbb	r9,r12
+	sbb	r10,0
+	mov	r11,rdx
+	sbb	rdx,r13
+	sbb	r13,r13
+
+	cmovnz	r8,rcx
+	cmovnz	r9,rsi
+	mov	QWORD[rdi],r8
+	cmovnz	r10,rax
+	mov	QWORD[8+rdi],r9
+	cmovz	r11,rdx
+	mov	QWORD[16+rdi],r10
+	mov	QWORD[24+rdi],r11
+
+	pop	r13
+	pop	r12
+	mov	rdi,QWORD[8+rsp]	;WIN64 epilogue
+	mov	rsi,QWORD[16+rsp]
+	DB	0F3h,0C3h		;repret
+$L$SEH_end_ecp_nistz256_from_mont:
+
+
+global	ecp_nistz256_select_w5
+
+ALIGN	32
+ecp_nistz256_select_w5:
+	lea	rax,[((-136))+rsp]
+$L$SEH_begin_ecp_nistz256_select_w5:
+DB	0x48,0x8d,0x60,0xe0
+DB	0x0f,0x29,0x70,0xe0
+DB	0x0f,0x29,0x78,0xf0
+DB	0x44,0x0f,0x29,0x00
+DB	0x44,0x0f,0x29,0x48,0x10
+DB	0x44,0x0f,0x29,0x50,0x20
+DB	0x44,0x0f,0x29,0x58,0x30
+DB	0x44,0x0f,0x29,0x60,0x40
+DB	0x44,0x0f,0x29,0x68,0x50
+DB	0x44,0x0f,0x29,0x70,0x60
+DB	0x44,0x0f,0x29,0x78,0x70
+	movdqa	xmm0,XMMWORD[$L$One]
+	movd	xmm1,r8d
+
+	pxor	xmm2,xmm2
+	pxor	xmm3,xmm3
+	pxor	xmm4,xmm4
+	pxor	xmm5,xmm5
+	pxor	xmm6,xmm6
+	pxor	xmm7,xmm7
+
+	movdqa	xmm8,xmm0
+	pshufd	xmm1,xmm1,0
+
+	mov	rax,16
+$L$select_loop_sse_w5:
+
+	movdqa	xmm15,xmm8
+	paddd	xmm8,xmm0
+	pcmpeqd	xmm15,xmm1
+
+	movdqa	xmm9,XMMWORD[rdx]
+	movdqa	xmm10,XMMWORD[16+rdx]
+	movdqa	xmm11,XMMWORD[32+rdx]
+	movdqa	xmm12,XMMWORD[48+rdx]
+	movdqa	xmm13,XMMWORD[64+rdx]
+	movdqa	xmm14,XMMWORD[80+rdx]
+	lea	rdx,[96+rdx]
+
+	pand	xmm9,xmm15
+	pand	xmm10,xmm15
+	por	xmm2,xmm9
+	pand	xmm11,xmm15
+	por	xmm3,xmm10
+	pand	xmm12,xmm15
+	por	xmm4,xmm11
+	pand	xmm13,xmm15
+	por	xmm5,xmm12
+	pand	xmm14,xmm15
+	por	xmm6,xmm13
+	por	xmm7,xmm14
+
+	dec	rax
+	jnz	NEAR $L$select_loop_sse_w5
+
+	movdqu	XMMWORD[rcx],xmm2
+	movdqu	XMMWORD[16+rcx],xmm3
+	movdqu	XMMWORD[32+rcx],xmm4
+	movdqu	XMMWORD[48+rcx],xmm5
+	movdqu	XMMWORD[64+rcx],xmm6
+	movdqu	XMMWORD[80+rcx],xmm7
+	movaps	xmm6,XMMWORD[rsp]
+	movaps	xmm7,XMMWORD[16+rsp]
+	movaps	xmm8,XMMWORD[32+rsp]
+	movaps	xmm9,XMMWORD[48+rsp]
+	movaps	xmm10,XMMWORD[64+rsp]
+	movaps	xmm11,XMMWORD[80+rsp]
+	movaps	xmm12,XMMWORD[96+rsp]
+	movaps	xmm13,XMMWORD[112+rsp]
+	movaps	xmm14,XMMWORD[128+rsp]
+	movaps	xmm15,XMMWORD[144+rsp]
+	lea	rsp,[168+rsp]
+$L$SEH_end_ecp_nistz256_select_w5:
+	DB	0F3h,0C3h		;repret
+
+
+
+
+global	ecp_nistz256_select_w7
+
+ALIGN	32
+ecp_nistz256_select_w7:
+	lea	rax,[((-136))+rsp]
+$L$SEH_begin_ecp_nistz256_select_w7:
+DB	0x48,0x8d,0x60,0xe0
+DB	0x0f,0x29,0x70,0xe0
+DB	0x0f,0x29,0x78,0xf0
+DB	0x44,0x0f,0x29,0x00
+DB	0x44,0x0f,0x29,0x48,0x10
+DB	0x44,0x0f,0x29,0x50,0x20
+DB	0x44,0x0f,0x29,0x58,0x30
+DB	0x44,0x0f,0x29,0x60,0x40
+DB	0x44,0x0f,0x29,0x68,0x50
+DB	0x44,0x0f,0x29,0x70,0x60
+DB	0x44,0x0f,0x29,0x78,0x70
+	movdqa	xmm8,XMMWORD[$L$One]
+	movd	xmm1,r8d
+
+	pxor	xmm2,xmm2
+	pxor	xmm3,xmm3
+	pxor	xmm4,xmm4
+	pxor	xmm5,xmm5
+
+	movdqa	xmm0,xmm8
+	pshufd	xmm1,xmm1,0
+	mov	rax,64
+
+$L$select_loop_sse_w7:
+	movdqa	xmm15,xmm8
+	paddd	xmm8,xmm0
+	movdqa	xmm9,XMMWORD[rdx]
+	movdqa	xmm10,XMMWORD[16+rdx]
+	pcmpeqd	xmm15,xmm1
+	movdqa	xmm11,XMMWORD[32+rdx]
+	movdqa	xmm12,XMMWORD[48+rdx]
+	lea	rdx,[64+rdx]
+
+	pand	xmm9,xmm15
+	pand	xmm10,xmm15
+	por	xmm2,xmm9
+	pand	xmm11,xmm15
+	por	xmm3,xmm10
+	pand	xmm12,xmm15
+	por	xmm4,xmm11
+	prefetcht0	[255+rdx]
+	por	xmm5,xmm12
+
+	dec	rax
+	jnz	NEAR $L$select_loop_sse_w7
+
+	movdqu	XMMWORD[rcx],xmm2
+	movdqu	XMMWORD[16+rcx],xmm3
+	movdqu	XMMWORD[32+rcx],xmm4
+	movdqu	XMMWORD[48+rcx],xmm5
+	movaps	xmm6,XMMWORD[rsp]
+	movaps	xmm7,XMMWORD[16+rsp]
+	movaps	xmm8,XMMWORD[32+rsp]
+	movaps	xmm9,XMMWORD[48+rsp]
+	movaps	xmm10,XMMWORD[64+rsp]
+	movaps	xmm11,XMMWORD[80+rsp]
+	movaps	xmm12,XMMWORD[96+rsp]
+	movaps	xmm13,XMMWORD[112+rsp]
+	movaps	xmm14,XMMWORD[128+rsp]
+	movaps	xmm15,XMMWORD[144+rsp]
+	lea	rsp,[168+rsp]
+$L$SEH_end_ecp_nistz256_select_w7:
+	DB	0F3h,0C3h		;repret
+
+global	ecp_nistz256_avx2_select_w7
+
+ALIGN	32
+ecp_nistz256_avx2_select_w7:
+	mov	QWORD[8+rsp],rdi	;WIN64 prologue
+	mov	QWORD[16+rsp],rsi
+	mov	rax,rsp
+$L$SEH_begin_ecp_nistz256_avx2_select_w7:
+	mov	rdi,rcx
+	mov	rsi,rdx
+	mov	rdx,r8
+
+
+DB	0x0f,0x0b
+	mov	rdi,QWORD[8+rsp]	;WIN64 epilogue
+	mov	rsi,QWORD[16+rsp]
+	DB	0F3h,0C3h		;repret
+$L$SEH_end_ecp_nistz256_avx2_select_w7:
+
+ALIGN	32
+__ecp_nistz256_add_toq:
+	add	r12,QWORD[rbx]
+	adc	r13,QWORD[8+rbx]
+	mov	rax,r12
+	adc	r8,QWORD[16+rbx]
+	adc	r9,QWORD[24+rbx]
+	mov	rbp,r13
+	sbb	r11,r11
+
+	sub	r12,-1
+	mov	rcx,r8
+	sbb	r13,r14
+	sbb	r8,0
+	mov	r10,r9
+	sbb	r9,r15
+	test	r11,r11
+
+	cmovz	r12,rax
+	cmovz	r13,rbp
+	mov	QWORD[rdi],r12
+	cmovz	r8,rcx
+	mov	QWORD[8+rdi],r13
+	cmovz	r9,r10
+	mov	QWORD[16+rdi],r8
+	mov	QWORD[24+rdi],r9
+
+	DB	0F3h,0C3h		;repret
+
+
+
+ALIGN	32
+__ecp_nistz256_sub_fromq:
+	sub	r12,QWORD[rbx]
+	sbb	r13,QWORD[8+rbx]
+	mov	rax,r12
+	sbb	r8,QWORD[16+rbx]
+	sbb	r9,QWORD[24+rbx]
+	mov	rbp,r13
+	sbb	r11,r11
+
+	add	r12,-1
+	mov	rcx,r8
+	adc	r13,r14
+	adc	r8,0
+	mov	r10,r9
+	adc	r9,r15
+	test	r11,r11
+
+	cmovz	r12,rax
+	cmovz	r13,rbp
+	mov	QWORD[rdi],r12
+	cmovz	r8,rcx
+	mov	QWORD[8+rdi],r13
+	cmovz	r9,r10
+	mov	QWORD[16+rdi],r8
+	mov	QWORD[24+rdi],r9
+
+	DB	0F3h,0C3h		;repret
+
+
+
+ALIGN	32
+__ecp_nistz256_subq:
+	sub	rax,r12
+	sbb	rbp,r13
+	mov	r12,rax
+	sbb	rcx,r8
+	sbb	r10,r9
+	mov	r13,rbp
+	sbb	r11,r11
+
+	add	rax,-1
+	mov	r8,rcx
+	adc	rbp,r14
+	adc	rcx,0
+	mov	r9,r10
+	adc	r10,r15
+	test	r11,r11
+
+	cmovnz	r12,rax
+	cmovnz	r13,rbp
+	cmovnz	r8,rcx
+	cmovnz	r9,r10
+
+	DB	0F3h,0C3h		;repret
+
+
+
+ALIGN	32
+__ecp_nistz256_mul_by_2q:
+	add	r12,r12
+	adc	r13,r13
+	mov	rax,r12
+	adc	r8,r8
+	adc	r9,r9
+	mov	rbp,r13
+	sbb	r11,r11
+
+	sub	r12,-1
+	mov	rcx,r8
+	sbb	r13,r14
+	sbb	r8,0
+	mov	r10,r9
+	sbb	r9,r15
+	test	r11,r11
+
+	cmovz	r12,rax
+	cmovz	r13,rbp
+	mov	QWORD[rdi],r12
+	cmovz	r8,rcx
+	mov	QWORD[8+rdi],r13
+	cmovz	r9,r10
+	mov	QWORD[16+rdi],r8
+	mov	QWORD[24+rdi],r9
+
+	DB	0F3h,0C3h		;repret
+
+global	ecp_nistz256_point_double
+
+ALIGN	32
+ecp_nistz256_point_double:
+	mov	QWORD[8+rsp],rdi	;WIN64 prologue
+	mov	QWORD[16+rsp],rsi
+	mov	rax,rsp
+$L$SEH_begin_ecp_nistz256_point_double:
+	mov	rdi,rcx
+	mov	rsi,rdx
+
+
+	push	rbp
+	push	rbx
+	push	r12
+	push	r13
+	push	r14
+	push	r15
+	sub	rsp,32*5+8
+
+$L$point_double_shortcutq:
+	movdqu	xmm0,XMMWORD[rsi]
+	mov	rbx,rsi
+	movdqu	xmm1,XMMWORD[16+rsi]
+	mov	r12,QWORD[((32+0))+rsi]
+	mov	r13,QWORD[((32+8))+rsi]
+	mov	r8,QWORD[((32+16))+rsi]
+	mov	r9,QWORD[((32+24))+rsi]
+	mov	r14,QWORD[(($L$poly+8))]
+	mov	r15,QWORD[(($L$poly+24))]
+	movdqa	XMMWORD[96+rsp],xmm0
+	movdqa	XMMWORD[(96+16)+rsp],xmm1
+	lea	r10,[32+rdi]
+	lea	r11,[64+rdi]
+DB	102,72,15,110,199
+DB	102,73,15,110,202
+DB	102,73,15,110,211
+
+	lea	rdi,[rsp]
+	call	__ecp_nistz256_mul_by_2q
+
+	mov	rax,QWORD[((64+0))+rsi]
+	mov	r14,QWORD[((64+8))+rsi]
+	mov	r15,QWORD[((64+16))+rsi]
+	mov	r8,QWORD[((64+24))+rsi]
+	lea	rsi,[((64-0))+rsi]
+	lea	rdi,[64+rsp]
+	call	__ecp_nistz256_sqr_montq
+
+	mov	rax,QWORD[((0+0))+rsp]
+	mov	r14,QWORD[((8+0))+rsp]
+	lea	rsi,[((0+0))+rsp]
+	mov	r15,QWORD[((16+0))+rsp]
+	mov	r8,QWORD[((24+0))+rsp]
+	lea	rdi,[rsp]
+	call	__ecp_nistz256_sqr_montq
+
+	mov	rax,QWORD[32+rbx]
+	mov	r9,QWORD[((64+0))+rbx]
+	mov	r10,QWORD[((64+8))+rbx]
+	mov	r11,QWORD[((64+16))+rbx]
+	mov	r12,QWORD[((64+24))+rbx]
+	lea	rsi,[((64-0))+rbx]
+	lea	rbx,[32+rbx]
+DB	102,72,15,126,215
+	call	__ecp_nistz256_mul_montq
+	call	__ecp_nistz256_mul_by_2q
+
+	mov	r12,QWORD[((96+0))+rsp]
+	mov	r13,QWORD[((96+8))+rsp]
+	lea	rbx,[64+rsp]
+	mov	r8,QWORD[((96+16))+rsp]
+	mov	r9,QWORD[((96+24))+rsp]
+	lea	rdi,[32+rsp]
+	call	__ecp_nistz256_add_toq
+
+	mov	r12,QWORD[((96+0))+rsp]
+	mov	r13,QWORD[((96+8))+rsp]
+	lea	rbx,[64+rsp]
+	mov	r8,QWORD[((96+16))+rsp]
+	mov	r9,QWORD[((96+24))+rsp]
+	lea	rdi,[64+rsp]
+	call	__ecp_nistz256_sub_fromq
+
+	mov	rax,QWORD[((0+0))+rsp]
+	mov	r14,QWORD[((8+0))+rsp]
+	lea	rsi,[((0+0))+rsp]
+	mov	r15,QWORD[((16+0))+rsp]
+	mov	r8,QWORD[((24+0))+rsp]
+DB	102,72,15,126,207
+	call	__ecp_nistz256_sqr_montq
+	xor	r9,r9
+	mov	rax,r12
+	add	r12,-1
+	mov	r10,r13
+	adc	r13,rsi
+	mov	rcx,r14
+	adc	r14,0
+	mov	r8,r15
+	adc	r15,rbp
+	adc	r9,0
+	xor	rsi,rsi
+	test	rax,1
+
+	cmovz	r12,rax
+	cmovz	r13,r10
+	cmovz	r14,rcx
+	cmovz	r15,r8
+	cmovz	r9,rsi
+
+	mov	rax,r13
+	shr	r12,1
+	shl	rax,63
+	mov	r10,r14
+	shr	r13,1
+	or	r12,rax
+	shl	r10,63
+	mov	rcx,r15
+	shr	r14,1
+	or	r13,r10
+	shl	rcx,63
+	mov	QWORD[rdi],r12
+	shr	r15,1
+	mov	QWORD[8+rdi],r13
+	shl	r9,63
+	or	r14,rcx
+	or	r15,r9
+	mov	QWORD[16+rdi],r14
+	mov	QWORD[24+rdi],r15
+	mov	rax,QWORD[64+rsp]
+	lea	rbx,[64+rsp]
+	mov	r9,QWORD[((0+32))+rsp]
+	mov	r10,QWORD[((8+32))+rsp]
+	lea	rsi,[((0+32))+rsp]
+	mov	r11,QWORD[((16+32))+rsp]
+	mov	r12,QWORD[((24+32))+rsp]
+	lea	rdi,[32+rsp]
+	call	__ecp_nistz256_mul_montq
+
+	lea	rdi,[128+rsp]
+	call	__ecp_nistz256_mul_by_2q
+
+	lea	rbx,[32+rsp]
+	lea	rdi,[32+rsp]
+	call	__ecp_nistz256_add_toq
+
+	mov	rax,QWORD[96+rsp]
+	lea	rbx,[96+rsp]
+	mov	r9,QWORD[((0+0))+rsp]
+	mov	r10,QWORD[((8+0))+rsp]
+	lea	rsi,[((0+0))+rsp]
+	mov	r11,QWORD[((16+0))+rsp]
+	mov	r12,QWORD[((24+0))+rsp]
+	lea	rdi,[rsp]
+	call	__ecp_nistz256_mul_montq
+
+	lea	rdi,[128+rsp]
+	call	__ecp_nistz256_mul_by_2q
+
+	mov	rax,QWORD[((0+32))+rsp]
+	mov	r14,QWORD[((8+32))+rsp]
+	lea	rsi,[((0+32))+rsp]
+	mov	r15,QWORD[((16+32))+rsp]
+	mov	r8,QWORD[((24+32))+rsp]
+DB	102,72,15,126,199
+	call	__ecp_nistz256_sqr_montq
+
+	lea	rbx,[128+rsp]
+	mov	r8,r14
+	mov	r9,r15
+	mov	r14,rsi
+	mov	r15,rbp
+	call	__ecp_nistz256_sub_fromq
+
+	mov	rax,QWORD[((0+0))+rsp]
+	mov	rbp,QWORD[((0+8))+rsp]
+	mov	rcx,QWORD[((0+16))+rsp]
+	mov	r10,QWORD[((0+24))+rsp]
+	lea	rdi,[rsp]
+	call	__ecp_nistz256_subq
+
+	mov	rax,QWORD[32+rsp]
+	lea	rbx,[32+rsp]
+	mov	r14,r12
+	xor	ecx,ecx
+	mov	QWORD[((0+0))+rsp],r12
+	mov	r10,r13
+	mov	QWORD[((0+8))+rsp],r13
+	cmovz	r11,r8
+	mov	QWORD[((0+16))+rsp],r8
+	lea	rsi,[((0-0))+rsp]
+	cmovz	r12,r9
+	mov	QWORD[((0+24))+rsp],r9
+	mov	r9,r14
+	lea	rdi,[rsp]
+	call	__ecp_nistz256_mul_montq
+
+DB	102,72,15,126,203
+DB	102,72,15,126,207
+	call	__ecp_nistz256_sub_fromq
+
+	add	rsp,32*5+8
+	pop	r15
+	pop	r14
+	pop	r13
+	pop	r12
+	pop	rbx
+	pop	rbp
+	mov	rdi,QWORD[8+rsp]	;WIN64 epilogue
+	mov	rsi,QWORD[16+rsp]
+	DB	0F3h,0C3h		;repret
+$L$SEH_end_ecp_nistz256_point_double:
+global	ecp_nistz256_point_add
+
+ALIGN	32
+ecp_nistz256_point_add:
+	mov	QWORD[8+rsp],rdi	;WIN64 prologue
+	mov	QWORD[16+rsp],rsi
+	mov	rax,rsp
+$L$SEH_begin_ecp_nistz256_point_add:
+	mov	rdi,rcx
+	mov	rsi,rdx
+	mov	rdx,r8
+
+
+	push	rbp
+	push	rbx
+	push	r12
+	push	r13
+	push	r14
+	push	r15
+	sub	rsp,32*18+8
+
+	movdqu	xmm0,XMMWORD[rsi]
+	movdqu	xmm1,XMMWORD[16+rsi]
+	movdqu	xmm2,XMMWORD[32+rsi]
+	movdqu	xmm3,XMMWORD[48+rsi]
+	movdqu	xmm4,XMMWORD[64+rsi]
+	movdqu	xmm5,XMMWORD[80+rsi]
+	mov	rbx,rsi
+	mov	rsi,rdx
+	movdqa	XMMWORD[384+rsp],xmm0
+	movdqa	XMMWORD[(384+16)+rsp],xmm1
+	por	xmm1,xmm0
+	movdqa	XMMWORD[416+rsp],xmm2
+	movdqa	XMMWORD[(416+16)+rsp],xmm3
+	por	xmm3,xmm2
+	movdqa	XMMWORD[448+rsp],xmm4
+	movdqa	XMMWORD[(448+16)+rsp],xmm5
+	por	xmm3,xmm1
+
+	movdqu	xmm0,XMMWORD[rsi]
+	pshufd	xmm5,xmm3,0xb1
+	movdqu	xmm1,XMMWORD[16+rsi]
+	movdqu	xmm2,XMMWORD[32+rsi]
+	por	xmm5,xmm3
+	movdqu	xmm3,XMMWORD[48+rsi]
+	mov	rax,QWORD[((64+0))+rsi]
+	mov	r14,QWORD[((64+8))+rsi]
+	mov	r15,QWORD[((64+16))+rsi]
+	mov	r8,QWORD[((64+24))+rsi]
+	movdqa	XMMWORD[480+rsp],xmm0
+	pshufd	xmm4,xmm5,0x1e
+	movdqa	XMMWORD[(480+16)+rsp],xmm1
+	por	xmm1,xmm0
+DB	102,72,15,110,199
+	movdqa	XMMWORD[512+rsp],xmm2
+	movdqa	XMMWORD[(512+16)+rsp],xmm3
+	por	xmm3,xmm2
+	por	xmm5,xmm4
+	pxor	xmm4,xmm4
+	por	xmm3,xmm1
+
+	lea	rsi,[((64-0))+rsi]
+	mov	QWORD[((544+0))+rsp],rax
+	mov	QWORD[((544+8))+rsp],r14
+	mov	QWORD[((544+16))+rsp],r15
+	mov	QWORD[((544+24))+rsp],r8
+	lea	rdi,[96+rsp]
+	call	__ecp_nistz256_sqr_montq
+
+	pcmpeqd	xmm5,xmm4
+	pshufd	xmm4,xmm3,0xb1
+	por	xmm4,xmm3
+	pshufd	xmm5,xmm5,0
+	pshufd	xmm3,xmm4,0x1e
+	por	xmm4,xmm3
+	pxor	xmm3,xmm3
+	pcmpeqd	xmm4,xmm3
+	pshufd	xmm4,xmm4,0
+	mov	rax,QWORD[((64+0))+rbx]
+	mov	r14,QWORD[((64+8))+rbx]
+	mov	r15,QWORD[((64+16))+rbx]
+	mov	r8,QWORD[((64+24))+rbx]
+DB	102,72,15,110,203
+
+	lea	rsi,[((64-0))+rbx]
+	lea	rdi,[32+rsp]
+	call	__ecp_nistz256_sqr_montq
+
+	mov	rax,QWORD[544+rsp]
+	lea	rbx,[544+rsp]
+	mov	r9,QWORD[((0+96))+rsp]
+	mov	r10,QWORD[((8+96))+rsp]
+	lea	rsi,[((0+96))+rsp]
+	mov	r11,QWORD[((16+96))+rsp]
+	mov	r12,QWORD[((24+96))+rsp]
+	lea	rdi,[224+rsp]
+	call	__ecp_nistz256_mul_montq
+
+	mov	rax,QWORD[448+rsp]
+	lea	rbx,[448+rsp]
+	mov	r9,QWORD[((0+32))+rsp]
+	mov	r10,QWORD[((8+32))+rsp]
+	lea	rsi,[((0+32))+rsp]
+	mov	r11,QWORD[((16+32))+rsp]
+	mov	r12,QWORD[((24+32))+rsp]
+	lea	rdi,[256+rsp]
+	call	__ecp_nistz256_mul_montq
+
+	mov	rax,QWORD[416+rsp]
+	lea	rbx,[416+rsp]
+	mov	r9,QWORD[((0+224))+rsp]
+	mov	r10,QWORD[((8+224))+rsp]
+	lea	rsi,[((0+224))+rsp]
+	mov	r11,QWORD[((16+224))+rsp]
+	mov	r12,QWORD[((24+224))+rsp]
+	lea	rdi,[224+rsp]
+	call	__ecp_nistz256_mul_montq
+
+	mov	rax,QWORD[512+rsp]
+	lea	rbx,[512+rsp]
+	mov	r9,QWORD[((0+256))+rsp]
+	mov	r10,QWORD[((8+256))+rsp]
+	lea	rsi,[((0+256))+rsp]
+	mov	r11,QWORD[((16+256))+rsp]
+	mov	r12,QWORD[((24+256))+rsp]
+	lea	rdi,[256+rsp]
+	call	__ecp_nistz256_mul_montq
+
+	lea	rbx,[224+rsp]
+	lea	rdi,[64+rsp]
+	call	__ecp_nistz256_sub_fromq
+
+	or	r12,r13
+	movdqa	xmm2,xmm4
+	or	r12,r8
+	or	r12,r9
+	por	xmm2,xmm5
+DB	102,73,15,110,220
+
+	mov	rax,QWORD[384+rsp]
+	lea	rbx,[384+rsp]
+	mov	r9,QWORD[((0+96))+rsp]
+	mov	r10,QWORD[((8+96))+rsp]
+	lea	rsi,[((0+96))+rsp]
+	mov	r11,QWORD[((16+96))+rsp]
+	mov	r12,QWORD[((24+96))+rsp]
+	lea	rdi,[160+rsp]
+	call	__ecp_nistz256_mul_montq
+
+	mov	rax,QWORD[480+rsp]
+	lea	rbx,[480+rsp]
+	mov	r9,QWORD[((0+32))+rsp]
+	mov	r10,QWORD[((8+32))+rsp]
+	lea	rsi,[((0+32))+rsp]
+	mov	r11,QWORD[((16+32))+rsp]
+	mov	r12,QWORD[((24+32))+rsp]
+	lea	rdi,[192+rsp]
+	call	__ecp_nistz256_mul_montq
+
+	lea	rbx,[160+rsp]
+	lea	rdi,[rsp]
+	call	__ecp_nistz256_sub_fromq
+
+	or	r12,r13
+	or	r12,r8
+	or	r12,r9
+
+DB	0x3e
+	jnz	NEAR $L$add_proceedq
+DB	102,73,15,126,208
+DB	102,73,15,126,217
+	test	r8,r8
+	jnz	NEAR $L$add_proceedq
+	test	r9,r9
+	jz	NEAR $L$add_doubleq
+
+DB	102,72,15,126,199
+	pxor	xmm0,xmm0
+	movdqu	XMMWORD[rdi],xmm0
+	movdqu	XMMWORD[16+rdi],xmm0
+	movdqu	XMMWORD[32+rdi],xmm0
+	movdqu	XMMWORD[48+rdi],xmm0
+	movdqu	XMMWORD[64+rdi],xmm0
+	movdqu	XMMWORD[80+rdi],xmm0
+	jmp	NEAR $L$add_doneq
+
+ALIGN	32
+$L$add_doubleq:
+DB	102,72,15,126,206
+DB	102,72,15,126,199
+	add	rsp,416
+	jmp	NEAR $L$point_double_shortcutq
+
+ALIGN	32
+$L$add_proceedq:
+	mov	rax,QWORD[((0+64))+rsp]
+	mov	r14,QWORD[((8+64))+rsp]
+	lea	rsi,[((0+64))+rsp]
+	mov	r15,QWORD[((16+64))+rsp]
+	mov	r8,QWORD[((24+64))+rsp]
+	lea	rdi,[96+rsp]
+	call	__ecp_nistz256_sqr_montq
+
+	mov	rax,QWORD[448+rsp]
+	lea	rbx,[448+rsp]
+	mov	r9,QWORD[((0+0))+rsp]
+	mov	r10,QWORD[((8+0))+rsp]
+	lea	rsi,[((0+0))+rsp]
+	mov	r11,QWORD[((16+0))+rsp]
+	mov	r12,QWORD[((24+0))+rsp]
+	lea	rdi,[352+rsp]
+	call	__ecp_nistz256_mul_montq
+
+	mov	rax,QWORD[((0+0))+rsp]
+	mov	r14,QWORD[((8+0))+rsp]
+	lea	rsi,[((0+0))+rsp]
+	mov	r15,QWORD[((16+0))+rsp]
+	mov	r8,QWORD[((24+0))+rsp]
+	lea	rdi,[32+rsp]
+	call	__ecp_nistz256_sqr_montq
+
+	mov	rax,QWORD[544+rsp]
+	lea	rbx,[544+rsp]
+	mov	r9,QWORD[((0+352))+rsp]
+	mov	r10,QWORD[((8+352))+rsp]
+	lea	rsi,[((0+352))+rsp]
+	mov	r11,QWORD[((16+352))+rsp]
+	mov	r12,QWORD[((24+352))+rsp]
+	lea	rdi,[352+rsp]
+	call	__ecp_nistz256_mul_montq
+
+	mov	rax,QWORD[rsp]
+	lea	rbx,[rsp]
+	mov	r9,QWORD[((0+32))+rsp]
+	mov	r10,QWORD[((8+32))+rsp]
+	lea	rsi,[((0+32))+rsp]
+	mov	r11,QWORD[((16+32))+rsp]
+	mov	r12,QWORD[((24+32))+rsp]
+	lea	rdi,[128+rsp]
+	call	__ecp_nistz256_mul_montq
+
+	mov	rax,QWORD[160+rsp]
+	lea	rbx,[160+rsp]
+	mov	r9,QWORD[((0+32))+rsp]
+	mov	r10,QWORD[((8+32))+rsp]
+	lea	rsi,[((0+32))+rsp]
+	mov	r11,QWORD[((16+32))+rsp]
+	mov	r12,QWORD[((24+32))+rsp]
+	lea	rdi,[192+rsp]
+	call	__ecp_nistz256_mul_montq
+
+
+
+
+	add	r12,r12
+	lea	rsi,[96+rsp]
+	adc	r13,r13
+	mov	rax,r12
+	adc	r8,r8
+	adc	r9,r9
+	mov	rbp,r13
+	sbb	r11,r11
+
+	sub	r12,-1
+	mov	rcx,r8
+	sbb	r13,r14
+	sbb	r8,0
+	mov	r10,r9
+	sbb	r9,r15
+	test	r11,r11
+
+	cmovz	r12,rax
+	mov	rax,QWORD[rsi]
+	cmovz	r13,rbp
+	mov	rbp,QWORD[8+rsi]
+	cmovz	r8,rcx
+	mov	rcx,QWORD[16+rsi]
+	cmovz	r9,r10
+	mov	r10,QWORD[24+rsi]
+
+	call	__ecp_nistz256_subq
+
+	lea	rbx,[128+rsp]
+	lea	rdi,[288+rsp]
+	call	__ecp_nistz256_sub_fromq
+
+	mov	rax,QWORD[((192+0))+rsp]
+	mov	rbp,QWORD[((192+8))+rsp]
+	mov	rcx,QWORD[((192+16))+rsp]
+	mov	r10,QWORD[((192+24))+rsp]
+	lea	rdi,[320+rsp]
+
+	call	__ecp_nistz256_subq
+
+	mov	QWORD[rdi],r12
+	mov	QWORD[8+rdi],r13
+	mov	QWORD[16+rdi],r8
+	mov	QWORD[24+rdi],r9
+	mov	rax,QWORD[128+rsp]
+	lea	rbx,[128+rsp]
+	mov	r9,QWORD[((0+224))+rsp]
+	mov	r10,QWORD[((8+224))+rsp]
+	lea	rsi,[((0+224))+rsp]
+	mov	r11,QWORD[((16+224))+rsp]
+	mov	r12,QWORD[((24+224))+rsp]
+	lea	rdi,[256+rsp]
+	call	__ecp_nistz256_mul_montq
+
+	mov	rax,QWORD[320+rsp]
+	lea	rbx,[320+rsp]
+	mov	r9,QWORD[((0+64))+rsp]
+	mov	r10,QWORD[((8+64))+rsp]
+	lea	rsi,[((0+64))+rsp]
+	mov	r11,QWORD[((16+64))+rsp]
+	mov	r12,QWORD[((24+64))+rsp]
+	lea	rdi,[320+rsp]
+	call	__ecp_nistz256_mul_montq
+
+	lea	rbx,[256+rsp]
+	lea	rdi,[320+rsp]
+	call	__ecp_nistz256_sub_fromq
+
+DB	102,72,15,126,199
+
+	movdqa	xmm0,xmm5
+	movdqa	xmm1,xmm5
+	pandn	xmm0,XMMWORD[352+rsp]
+	movdqa	xmm2,xmm5
+	pandn	xmm1,XMMWORD[((352+16))+rsp]
+	movdqa	xmm3,xmm5
+	pand	xmm2,XMMWORD[544+rsp]
+	pand	xmm3,XMMWORD[((544+16))+rsp]
+	por	xmm2,xmm0
+	por	xmm3,xmm1
+
+	movdqa	xmm0,xmm4
+	movdqa	xmm1,xmm4
+	pandn	xmm0,xmm2
+	movdqa	xmm2,xmm4
+	pandn	xmm1,xmm3
+	movdqa	xmm3,xmm4
+	pand	xmm2,XMMWORD[448+rsp]
+	pand	xmm3,XMMWORD[((448+16))+rsp]
+	por	xmm2,xmm0
+	por	xmm3,xmm1
+	movdqu	XMMWORD[64+rdi],xmm2
+	movdqu	XMMWORD[80+rdi],xmm3
+
+	movdqa	xmm0,xmm5
+	movdqa	xmm1,xmm5
+	pandn	xmm0,XMMWORD[288+rsp]
+	movdqa	xmm2,xmm5
+	pandn	xmm1,XMMWORD[((288+16))+rsp]
+	movdqa	xmm3,xmm5
+	pand	xmm2,XMMWORD[480+rsp]
+	pand	xmm3,XMMWORD[((480+16))+rsp]
+	por	xmm2,xmm0
+	por	xmm3,xmm1
+
+	movdqa	xmm0,xmm4
+	movdqa	xmm1,xmm4
+	pandn	xmm0,xmm2
+	movdqa	xmm2,xmm4
+	pandn	xmm1,xmm3
+	movdqa	xmm3,xmm4
+	pand	xmm2,XMMWORD[384+rsp]
+	pand	xmm3,XMMWORD[((384+16))+rsp]
+	por	xmm2,xmm0
+	por	xmm3,xmm1
+	movdqu	XMMWORD[rdi],xmm2
+	movdqu	XMMWORD[16+rdi],xmm3
+
+	movdqa	xmm0,xmm5
+	movdqa	xmm1,xmm5
+	pandn	xmm0,XMMWORD[320+rsp]
+	movdqa	xmm2,xmm5
+	pandn	xmm1,XMMWORD[((320+16))+rsp]
+	movdqa	xmm3,xmm5
+	pand	xmm2,XMMWORD[512+rsp]
+	pand	xmm3,XMMWORD[((512+16))+rsp]
+	por	xmm2,xmm0
+	por	xmm3,xmm1
+
+	movdqa	xmm0,xmm4
+	movdqa	xmm1,xmm4
+	pandn	xmm0,xmm2
+	movdqa	xmm2,xmm4
+	pandn	xmm1,xmm3
+	movdqa	xmm3,xmm4
+	pand	xmm2,XMMWORD[416+rsp]
+	pand	xmm3,XMMWORD[((416+16))+rsp]
+	por	xmm2,xmm0
+	por	xmm3,xmm1
+	movdqu	XMMWORD[32+rdi],xmm2
+	movdqu	XMMWORD[48+rdi],xmm3
+
+$L$add_doneq:
+	add	rsp,32*18+8
+	pop	r15
+	pop	r14
+	pop	r13
+	pop	r12
+	pop	rbx
+	pop	rbp
+	mov	rdi,QWORD[8+rsp]	;WIN64 epilogue
+	mov	rsi,QWORD[16+rsp]
+	DB	0F3h,0C3h		;repret
+$L$SEH_end_ecp_nistz256_point_add:
+global	ecp_nistz256_point_add_affine
+
+ALIGN	32
+ecp_nistz256_point_add_affine:
+	mov	QWORD[8+rsp],rdi	;WIN64 prologue
+	mov	QWORD[16+rsp],rsi
+	mov	rax,rsp
+$L$SEH_begin_ecp_nistz256_point_add_affine:
+	mov	rdi,rcx
+	mov	rsi,rdx
+	mov	rdx,r8
+
+
+	push	rbp
+	push	rbx
+	push	r12
+	push	r13
+	push	r14
+	push	r15
+	sub	rsp,32*15+8
+
+	movdqu	xmm0,XMMWORD[rsi]
+	mov	rbx,rdx
+	movdqu	xmm1,XMMWORD[16+rsi]
+	movdqu	xmm2,XMMWORD[32+rsi]
+	movdqu	xmm3,XMMWORD[48+rsi]
+	movdqu	xmm4,XMMWORD[64+rsi]
+	movdqu	xmm5,XMMWORD[80+rsi]
+	mov	rax,QWORD[((64+0))+rsi]
+	mov	r14,QWORD[((64+8))+rsi]
+	mov	r15,QWORD[((64+16))+rsi]
+	mov	r8,QWORD[((64+24))+rsi]
+	movdqa	XMMWORD[320+rsp],xmm0
+	movdqa	XMMWORD[(320+16)+rsp],xmm1
+	por	xmm1,xmm0
+	movdqa	XMMWORD[352+rsp],xmm2
+	movdqa	XMMWORD[(352+16)+rsp],xmm3
+	por	xmm3,xmm2
+	movdqa	XMMWORD[384+rsp],xmm4
+	movdqa	XMMWORD[(384+16)+rsp],xmm5
+	por	xmm3,xmm1
+
+	movdqu	xmm0,XMMWORD[rbx]
+	pshufd	xmm5,xmm3,0xb1
+	movdqu	xmm1,XMMWORD[16+rbx]
+	movdqu	xmm2,XMMWORD[32+rbx]
+	por	xmm5,xmm3
+	movdqu	xmm3,XMMWORD[48+rbx]
+	movdqa	XMMWORD[416+rsp],xmm0
+	pshufd	xmm4,xmm5,0x1e
+	movdqa	XMMWORD[(416+16)+rsp],xmm1
+	por	xmm1,xmm0
+DB	102,72,15,110,199
+	movdqa	XMMWORD[448+rsp],xmm2
+	movdqa	XMMWORD[(448+16)+rsp],xmm3
+	por	xmm3,xmm2
+	por	xmm5,xmm4
+	pxor	xmm4,xmm4
+	por	xmm3,xmm1
+
+	lea	rsi,[((64-0))+rsi]
+	lea	rdi,[32+rsp]
+	call	__ecp_nistz256_sqr_montq
+
+	pcmpeqd	xmm5,xmm4
+	pshufd	xmm4,xmm3,0xb1
+	mov	rax,QWORD[rbx]
+
+	mov	r9,r12
+	por	xmm4,xmm3
+	pshufd	xmm5,xmm5,0
+	pshufd	xmm3,xmm4,0x1e
+	mov	r10,r13
+	por	xmm4,xmm3
+	pxor	xmm3,xmm3
+	mov	r11,r14
+	pcmpeqd	xmm4,xmm3
+	pshufd	xmm4,xmm4,0
+
+	lea	rsi,[((32-0))+rsp]
+	mov	r12,r15
+	lea	rdi,[rsp]
+	call	__ecp_nistz256_mul_montq
+
+	lea	rbx,[320+rsp]
+	lea	rdi,[64+rsp]
+	call	__ecp_nistz256_sub_fromq
+
+	mov	rax,QWORD[384+rsp]
+	lea	rbx,[384+rsp]
+	mov	r9,QWORD[((0+32))+rsp]
+	mov	r10,QWORD[((8+32))+rsp]
+	lea	rsi,[((0+32))+rsp]
+	mov	r11,QWORD[((16+32))+rsp]
+	mov	r12,QWORD[((24+32))+rsp]
+	lea	rdi,[32+rsp]
+	call	__ecp_nistz256_mul_montq
+
+	mov	rax,QWORD[384+rsp]
+	lea	rbx,[384+rsp]
+	mov	r9,QWORD[((0+64))+rsp]
+	mov	r10,QWORD[((8+64))+rsp]
+	lea	rsi,[((0+64))+rsp]
+	mov	r11,QWORD[((16+64))+rsp]
+	mov	r12,QWORD[((24+64))+rsp]
+	lea	rdi,[288+rsp]
+	call	__ecp_nistz256_mul_montq
+
+	mov	rax,QWORD[448+rsp]
+	lea	rbx,[448+rsp]
+	mov	r9,QWORD[((0+32))+rsp]
+	mov	r10,QWORD[((8+32))+rsp]
+	lea	rsi,[((0+32))+rsp]
+	mov	r11,QWORD[((16+32))+rsp]
+	mov	r12,QWORD[((24+32))+rsp]
+	lea	rdi,[32+rsp]
+	call	__ecp_nistz256_mul_montq
+
+	lea	rbx,[352+rsp]
+	lea	rdi,[96+rsp]
+	call	__ecp_nistz256_sub_fromq
+
+	mov	rax,QWORD[((0+64))+rsp]
+	mov	r14,QWORD[((8+64))+rsp]
+	lea	rsi,[((0+64))+rsp]
+	mov	r15,QWORD[((16+64))+rsp]
+	mov	r8,QWORD[((24+64))+rsp]
+	lea	rdi,[128+rsp]
+	call	__ecp_nistz256_sqr_montq
+
+	mov	rax,QWORD[((0+96))+rsp]
+	mov	r14,QWORD[((8+96))+rsp]
+	lea	rsi,[((0+96))+rsp]
+	mov	r15,QWORD[((16+96))+rsp]
+	mov	r8,QWORD[((24+96))+rsp]
+	lea	rdi,[192+rsp]
+	call	__ecp_nistz256_sqr_montq
+
+	mov	rax,QWORD[128+rsp]
+	lea	rbx,[128+rsp]
+	mov	r9,QWORD[((0+64))+rsp]
+	mov	r10,QWORD[((8+64))+rsp]
+	lea	rsi,[((0+64))+rsp]
+	mov	r11,QWORD[((16+64))+rsp]
+	mov	r12,QWORD[((24+64))+rsp]
+	lea	rdi,[160+rsp]
+	call	__ecp_nistz256_mul_montq
+
+	mov	rax,QWORD[320+rsp]
+	lea	rbx,[320+rsp]
+	mov	r9,QWORD[((0+128))+rsp]
+	mov	r10,QWORD[((8+128))+rsp]
+	lea	rsi,[((0+128))+rsp]
+	mov	r11,QWORD[((16+128))+rsp]
+	mov	r12,QWORD[((24+128))+rsp]
+	lea	rdi,[rsp]
+	call	__ecp_nistz256_mul_montq
+
+
+
+
+	add	r12,r12
+	lea	rsi,[192+rsp]
+	adc	r13,r13
+	mov	rax,r12
+	adc	r8,r8
+	adc	r9,r9
+	mov	rbp,r13
+	sbb	r11,r11
+
+	sub	r12,-1
+	mov	rcx,r8
+	sbb	r13,r14
+	sbb	r8,0
+	mov	r10,r9
+	sbb	r9,r15
+	test	r11,r11
+
+	cmovz	r12,rax
+	mov	rax,QWORD[rsi]
+	cmovz	r13,rbp
+	mov	rbp,QWORD[8+rsi]
+	cmovz	r8,rcx
+	mov	rcx,QWORD[16+rsi]
+	cmovz	r9,r10
+	mov	r10,QWORD[24+rsi]
+
+	call	__ecp_nistz256_subq
+
+	lea	rbx,[160+rsp]
+	lea	rdi,[224+rsp]
+	call	__ecp_nistz256_sub_fromq
+
+	mov	rax,QWORD[((0+0))+rsp]
+	mov	rbp,QWORD[((0+8))+rsp]
+	mov	rcx,QWORD[((0+16))+rsp]
+	mov	r10,QWORD[((0+24))+rsp]
+	lea	rdi,[64+rsp]
+
+	call	__ecp_nistz256_subq
+
+	mov	QWORD[rdi],r12
+	mov	QWORD[8+rdi],r13
+	mov	QWORD[16+rdi],r8
+	mov	QWORD[24+rdi],r9
+	mov	rax,QWORD[352+rsp]
+	lea	rbx,[352+rsp]
+	mov	r9,QWORD[((0+160))+rsp]
+	mov	r10,QWORD[((8+160))+rsp]
+	lea	rsi,[((0+160))+rsp]
+	mov	r11,QWORD[((16+160))+rsp]
+	mov	r12,QWORD[((24+160))+rsp]
+	lea	rdi,[32+rsp]
+	call	__ecp_nistz256_mul_montq
+
+	mov	rax,QWORD[96+rsp]
+	lea	rbx,[96+rsp]
+	mov	r9,QWORD[((0+64))+rsp]
+	mov	r10,QWORD[((8+64))+rsp]
+	lea	rsi,[((0+64))+rsp]
+	mov	r11,QWORD[((16+64))+rsp]
+	mov	r12,QWORD[((24+64))+rsp]
+	lea	rdi,[64+rsp]
+	call	__ecp_nistz256_mul_montq
+
+	lea	rbx,[32+rsp]
+	lea	rdi,[256+rsp]
+	call	__ecp_nistz256_sub_fromq
+
+DB	102,72,15,126,199
+
+	movdqa	xmm0,xmm5
+	movdqa	xmm1,xmm5
+	pandn	xmm0,XMMWORD[288+rsp]
+	movdqa	xmm2,xmm5
+	pandn	xmm1,XMMWORD[((288+16))+rsp]
+	movdqa	xmm3,xmm5
+	pand	xmm2,XMMWORD[$L$ONE_mont]
+	pand	xmm3,XMMWORD[(($L$ONE_mont+16))]
+	por	xmm2,xmm0
+	por	xmm3,xmm1
+
+	movdqa	xmm0,xmm4
+	movdqa	xmm1,xmm4
+	pandn	xmm0,xmm2
+	movdqa	xmm2,xmm4
+	pandn	xmm1,xmm3
+	movdqa	xmm3,xmm4
+	pand	xmm2,XMMWORD[384+rsp]
+	pand	xmm3,XMMWORD[((384+16))+rsp]
+	por	xmm2,xmm0
+	por	xmm3,xmm1
+	movdqu	XMMWORD[64+rdi],xmm2
+	movdqu	XMMWORD[80+rdi],xmm3
+
+	movdqa	xmm0,xmm5
+	movdqa	xmm1,xmm5
+	pandn	xmm0,XMMWORD[224+rsp]
+	movdqa	xmm2,xmm5
+	pandn	xmm1,XMMWORD[((224+16))+rsp]
+	movdqa	xmm3,xmm5
+	pand	xmm2,XMMWORD[416+rsp]
+	pand	xmm3,XMMWORD[((416+16))+rsp]
+	por	xmm2,xmm0
+	por	xmm3,xmm1
+
+	movdqa	xmm0,xmm4
+	movdqa	xmm1,xmm4
+	pandn	xmm0,xmm2
+	movdqa	xmm2,xmm4
+	pandn	xmm1,xmm3
+	movdqa	xmm3,xmm4
+	pand	xmm2,XMMWORD[320+rsp]
+	pand	xmm3,XMMWORD[((320+16))+rsp]
+	por	xmm2,xmm0
+	por	xmm3,xmm1
+	movdqu	XMMWORD[rdi],xmm2
+	movdqu	XMMWORD[16+rdi],xmm3
+
+	movdqa	xmm0,xmm5
+	movdqa	xmm1,xmm5
+	pandn	xmm0,XMMWORD[256+rsp]
+	movdqa	xmm2,xmm5
+	pandn	xmm1,XMMWORD[((256+16))+rsp]
+	movdqa	xmm3,xmm5
+	pand	xmm2,XMMWORD[448+rsp]
+	pand	xmm3,XMMWORD[((448+16))+rsp]
+	por	xmm2,xmm0
+	por	xmm3,xmm1
+
+	movdqa	xmm0,xmm4
+	movdqa	xmm1,xmm4
+	pandn	xmm0,xmm2
+	movdqa	xmm2,xmm4
+	pandn	xmm1,xmm3
+	movdqa	xmm3,xmm4
+	pand	xmm2,XMMWORD[352+rsp]
+	pand	xmm3,XMMWORD[((352+16))+rsp]
+	por	xmm2,xmm0
+	por	xmm3,xmm1
+	movdqu	XMMWORD[32+rdi],xmm2
+	movdqu	XMMWORD[48+rdi],xmm3
+
+	add	rsp,32*15+8
+	pop	r15
+	pop	r14
+	pop	r13
+	pop	r12
+	pop	rbx
+	pop	rbp
+	mov	rdi,QWORD[8+rsp]	;WIN64 epilogue
+	mov	rsi,QWORD[16+rsp]
+	DB	0F3h,0C3h		;repret
+$L$SEH_end_ecp_nistz256_point_add_affine:
diff --git a/packager/third_party/boringssl/win-x86_64/crypto/sha/sha1-x86_64.asm b/packager/third_party/boringssl/win-x86_64/crypto/sha/sha1-x86_64.asm
index 0f5361a1b5..168f78db3f 100644
--- a/packager/third_party/boringssl/win-x86_64/crypto/sha/sha1-x86_64.asm
+++ b/packager/third_party/boringssl/win-x86_64/crypto/sha/sha1-x86_64.asm
@@ -24,6 +24,11 @@ $L$SEH_begin_sha1_block_data_order:
 	mov	r10d,DWORD[((OPENSSL_ia32cap_P+8))]
 	test	r8d,512
 	jz	NEAR $L$ialu
+	and	r8d,268435456
+	and	r9d,1073741824
+	or	r8d,r9d
+	cmp	r8d,1342177280
+	je	NEAR _avx_shortcut
 	jmp	NEAR _ssse3_shortcut
 
 ALIGN	16
@@ -2445,6 +2450,1146 @@ $L$epilogue_ssse3:
 	mov	rsi,QWORD[16+rsp]
 	DB	0F3h,0C3h		;repret
 $L$SEH_end_sha1_block_data_order_ssse3:
+
+ALIGN	16
+sha1_block_data_order_avx:
+	mov	QWORD[8+rsp],rdi	;WIN64 prologue
+	mov	QWORD[16+rsp],rsi
+	mov	rax,rsp
+$L$SEH_begin_sha1_block_data_order_avx:
+	mov	rdi,rcx
+	mov	rsi,rdx
+	mov	rdx,r8
+
+
+_avx_shortcut:
+	mov	rax,rsp
+	push	rbx
+	push	rbp
+	push	r12
+	push	r13
+	push	r14
+	lea	rsp,[((-160))+rsp]
+	vzeroupper
+	vmovaps	XMMWORD[(-40-96)+rax],xmm6
+	vmovaps	XMMWORD[(-40-80)+rax],xmm7
+	vmovaps	XMMWORD[(-40-64)+rax],xmm8
+	vmovaps	XMMWORD[(-40-48)+rax],xmm9
+	vmovaps	XMMWORD[(-40-32)+rax],xmm10
+	vmovaps	XMMWORD[(-40-16)+rax],xmm11
+$L$prologue_avx:
+	mov	r14,rax
+	and	rsp,-64
+	mov	r8,rdi
+	mov	r9,rsi
+	mov	r10,rdx
+
+	shl	r10,6
+	add	r10,r9
+	lea	r11,[((K_XX_XX+64))]
+
+	mov	eax,DWORD[r8]
+	mov	ebx,DWORD[4+r8]
+	mov	ecx,DWORD[8+r8]
+	mov	edx,DWORD[12+r8]
+	mov	esi,ebx
+	mov	ebp,DWORD[16+r8]
+	mov	edi,ecx
+	xor	edi,edx
+	and	esi,edi
+
+	vmovdqa	xmm6,XMMWORD[64+r11]
+	vmovdqa	xmm11,XMMWORD[((-64))+r11]
+	vmovdqu	xmm0,XMMWORD[r9]
+	vmovdqu	xmm1,XMMWORD[16+r9]
+	vmovdqu	xmm2,XMMWORD[32+r9]
+	vmovdqu	xmm3,XMMWORD[48+r9]
+	vpshufb	xmm0,xmm0,xmm6
+	add	r9,64
+	vpshufb	xmm1,xmm1,xmm6
+	vpshufb	xmm2,xmm2,xmm6
+	vpshufb	xmm3,xmm3,xmm6
+	vpaddd	xmm4,xmm0,xmm11
+	vpaddd	xmm5,xmm1,xmm11
+	vpaddd	xmm6,xmm2,xmm11
+	vmovdqa	XMMWORD[rsp],xmm4
+	vmovdqa	XMMWORD[16+rsp],xmm5
+	vmovdqa	XMMWORD[32+rsp],xmm6
+	jmp	NEAR $L$oop_avx
+ALIGN	16
+$L$oop_avx:
+	shrd	ebx,ebx,2
+	xor	esi,edx
+	vpalignr	xmm4,xmm1,xmm0,8
+	mov	edi,eax
+	add	ebp,DWORD[rsp]
+	vpaddd	xmm9,xmm11,xmm3
+	xor	ebx,ecx
+	shld	eax,eax,5
+	vpsrldq	xmm8,xmm3,4
+	add	ebp,esi
+	and	edi,ebx
+	vpxor	xmm4,xmm4,xmm0
+	xor	ebx,ecx
+	add	ebp,eax
+	vpxor	xmm8,xmm8,xmm2
+	shrd	eax,eax,7
+	xor	edi,ecx
+	mov	esi,ebp
+	add	edx,DWORD[4+rsp]
+	vpxor	xmm4,xmm4,xmm8
+	xor	eax,ebx
+	shld	ebp,ebp,5
+	vmovdqa	XMMWORD[48+rsp],xmm9
+	add	edx,edi
+	and	esi,eax
+	vpsrld	xmm8,xmm4,31
+	xor	eax,ebx
+	add	edx,ebp
+	shrd	ebp,ebp,7
+	xor	esi,ebx
+	vpslldq	xmm10,xmm4,12
+	vpaddd	xmm4,xmm4,xmm4
+	mov	edi,edx
+	add	ecx,DWORD[8+rsp]
+	xor	ebp,eax
+	shld	edx,edx,5
+	vpsrld	xmm9,xmm10,30
+	vpor	xmm4,xmm4,xmm8
+	add	ecx,esi
+	and	edi,ebp
+	xor	ebp,eax
+	add	ecx,edx
+	vpslld	xmm10,xmm10,2
+	vpxor	xmm4,xmm4,xmm9
+	shrd	edx,edx,7
+	xor	edi,eax
+	mov	esi,ecx
+	add	ebx,DWORD[12+rsp]
+	vpxor	xmm4,xmm4,xmm10
+	xor	edx,ebp
+	shld	ecx,ecx,5
+	add	ebx,edi
+	and	esi,edx
+	xor	edx,ebp
+	add	ebx,ecx
+	shrd	ecx,ecx,7
+	xor	esi,ebp
+	vpalignr	xmm5,xmm2,xmm1,8
+	mov	edi,ebx
+	add	eax,DWORD[16+rsp]
+	vpaddd	xmm9,xmm11,xmm4
+	xor	ecx,edx
+	shld	ebx,ebx,5
+	vpsrldq	xmm8,xmm4,4
+	add	eax,esi
+	and	edi,ecx
+	vpxor	xmm5,xmm5,xmm1
+	xor	ecx,edx
+	add	eax,ebx
+	vpxor	xmm8,xmm8,xmm3
+	shrd	ebx,ebx,7
+	xor	edi,edx
+	mov	esi,eax
+	add	ebp,DWORD[20+rsp]
+	vpxor	xmm5,xmm5,xmm8
+	xor	ebx,ecx
+	shld	eax,eax,5
+	vmovdqa	XMMWORD[rsp],xmm9
+	add	ebp,edi
+	and	esi,ebx
+	vpsrld	xmm8,xmm5,31
+	xor	ebx,ecx
+	add	ebp,eax
+	shrd	eax,eax,7
+	xor	esi,ecx
+	vpslldq	xmm10,xmm5,12
+	vpaddd	xmm5,xmm5,xmm5
+	mov	edi,ebp
+	add	edx,DWORD[24+rsp]
+	xor	eax,ebx
+	shld	ebp,ebp,5
+	vpsrld	xmm9,xmm10,30
+	vpor	xmm5,xmm5,xmm8
+	add	edx,esi
+	and	edi,eax
+	xor	eax,ebx
+	add	edx,ebp
+	vpslld	xmm10,xmm10,2
+	vpxor	xmm5,xmm5,xmm9
+	shrd	ebp,ebp,7
+	xor	edi,ebx
+	mov	esi,edx
+	add	ecx,DWORD[28+rsp]
+	vpxor	xmm5,xmm5,xmm10
+	xor	ebp,eax
+	shld	edx,edx,5
+	vmovdqa	xmm11,XMMWORD[((-32))+r11]
+	add	ecx,edi
+	and	esi,ebp
+	xor	ebp,eax
+	add	ecx,edx
+	shrd	edx,edx,7
+	xor	esi,eax
+	vpalignr	xmm6,xmm3,xmm2,8
+	mov	edi,ecx
+	add	ebx,DWORD[32+rsp]
+	vpaddd	xmm9,xmm11,xmm5
+	xor	edx,ebp
+	shld	ecx,ecx,5
+	vpsrldq	xmm8,xmm5,4
+	add	ebx,esi
+	and	edi,edx
+	vpxor	xmm6,xmm6,xmm2
+	xor	edx,ebp
+	add	ebx,ecx
+	vpxor	xmm8,xmm8,xmm4
+	shrd	ecx,ecx,7
+	xor	edi,ebp
+	mov	esi,ebx
+	add	eax,DWORD[36+rsp]
+	vpxor	xmm6,xmm6,xmm8
+	xor	ecx,edx
+	shld	ebx,ebx,5
+	vmovdqa	XMMWORD[16+rsp],xmm9
+	add	eax,edi
+	and	esi,ecx
+	vpsrld	xmm8,xmm6,31
+	xor	ecx,edx
+	add	eax,ebx
+	shrd	ebx,ebx,7
+	xor	esi,edx
+	vpslldq	xmm10,xmm6,12
+	vpaddd	xmm6,xmm6,xmm6
+	mov	edi,eax
+	add	ebp,DWORD[40+rsp]
+	xor	ebx,ecx
+	shld	eax,eax,5
+	vpsrld	xmm9,xmm10,30
+	vpor	xmm6,xmm6,xmm8
+	add	ebp,esi
+	and	edi,ebx
+	xor	ebx,ecx
+	add	ebp,eax
+	vpslld	xmm10,xmm10,2
+	vpxor	xmm6,xmm6,xmm9
+	shrd	eax,eax,7
+	xor	edi,ecx
+	mov	esi,ebp
+	add	edx,DWORD[44+rsp]
+	vpxor	xmm6,xmm6,xmm10
+	xor	eax,ebx
+	shld	ebp,ebp,5
+	add	edx,edi
+	and	esi,eax
+	xor	eax,ebx
+	add	edx,ebp
+	shrd	ebp,ebp,7
+	xor	esi,ebx
+	vpalignr	xmm7,xmm4,xmm3,8
+	mov	edi,edx
+	add	ecx,DWORD[48+rsp]
+	vpaddd	xmm9,xmm11,xmm6
+	xor	ebp,eax
+	shld	edx,edx,5
+	vpsrldq	xmm8,xmm6,4
+	add	ecx,esi
+	and	edi,ebp
+	vpxor	xmm7,xmm7,xmm3
+	xor	ebp,eax
+	add	ecx,edx
+	vpxor	xmm8,xmm8,xmm5
+	shrd	edx,edx,7
+	xor	edi,eax
+	mov	esi,ecx
+	add	ebx,DWORD[52+rsp]
+	vpxor	xmm7,xmm7,xmm8
+	xor	edx,ebp
+	shld	ecx,ecx,5
+	vmovdqa	XMMWORD[32+rsp],xmm9
+	add	ebx,edi
+	and	esi,edx
+	vpsrld	xmm8,xmm7,31
+	xor	edx,ebp
+	add	ebx,ecx
+	shrd	ecx,ecx,7
+	xor	esi,ebp
+	vpslldq	xmm10,xmm7,12
+	vpaddd	xmm7,xmm7,xmm7
+	mov	edi,ebx
+	add	eax,DWORD[56+rsp]
+	xor	ecx,edx
+	shld	ebx,ebx,5
+	vpsrld	xmm9,xmm10,30
+	vpor	xmm7,xmm7,xmm8
+	add	eax,esi
+	and	edi,ecx
+	xor	ecx,edx
+	add	eax,ebx
+	vpslld	xmm10,xmm10,2
+	vpxor	xmm7,xmm7,xmm9
+	shrd	ebx,ebx,7
+	xor	edi,edx
+	mov	esi,eax
+	add	ebp,DWORD[60+rsp]
+	vpxor	xmm7,xmm7,xmm10
+	xor	ebx,ecx
+	shld	eax,eax,5
+	add	ebp,edi
+	and	esi,ebx
+	xor	ebx,ecx
+	add	ebp,eax
+	vpalignr	xmm8,xmm7,xmm6,8
+	vpxor	xmm0,xmm0,xmm4
+	shrd	eax,eax,7
+	xor	esi,ecx
+	mov	edi,ebp
+	add	edx,DWORD[rsp]
+	vpxor	xmm0,xmm0,xmm1
+	xor	eax,ebx
+	shld	ebp,ebp,5
+	vpaddd	xmm9,xmm11,xmm7
+	add	edx,esi
+	and	edi,eax
+	vpxor	xmm0,xmm0,xmm8
+	xor	eax,ebx
+	add	edx,ebp
+	shrd	ebp,ebp,7
+	xor	edi,ebx
+	vpsrld	xmm8,xmm0,30
+	vmovdqa	XMMWORD[48+rsp],xmm9
+	mov	esi,edx
+	add	ecx,DWORD[4+rsp]
+	xor	ebp,eax
+	shld	edx,edx,5
+	vpslld	xmm0,xmm0,2
+	add	ecx,edi
+	and	esi,ebp
+	xor	ebp,eax
+	add	ecx,edx
+	shrd	edx,edx,7
+	xor	esi,eax
+	mov	edi,ecx
+	add	ebx,DWORD[8+rsp]
+	vpor	xmm0,xmm0,xmm8
+	xor	edx,ebp
+	shld	ecx,ecx,5
+	add	ebx,esi
+	and	edi,edx
+	xor	edx,ebp
+	add	ebx,ecx
+	add	eax,DWORD[12+rsp]
+	xor	edi,ebp
+	mov	esi,ebx
+	shld	ebx,ebx,5
+	add	eax,edi
+	xor	esi,edx
+	shrd	ecx,ecx,7
+	add	eax,ebx
+	vpalignr	xmm8,xmm0,xmm7,8
+	vpxor	xmm1,xmm1,xmm5
+	add	ebp,DWORD[16+rsp]
+	xor	esi,ecx
+	mov	edi,eax
+	shld	eax,eax,5
+	vpxor	xmm1,xmm1,xmm2
+	add	ebp,esi
+	xor	edi,ecx
+	vpaddd	xmm9,xmm11,xmm0
+	shrd	ebx,ebx,7
+	add	ebp,eax
+	vpxor	xmm1,xmm1,xmm8
+	add	edx,DWORD[20+rsp]
+	xor	edi,ebx
+	mov	esi,ebp
+	shld	ebp,ebp,5
+	vpsrld	xmm8,xmm1,30
+	vmovdqa	XMMWORD[rsp],xmm9
+	add	edx,edi
+	xor	esi,ebx
+	shrd	eax,eax,7
+	add	edx,ebp
+	vpslld	xmm1,xmm1,2
+	add	ecx,DWORD[24+rsp]
+	xor	esi,eax
+	mov	edi,edx
+	shld	edx,edx,5
+	add	ecx,esi
+	xor	edi,eax
+	shrd	ebp,ebp,7
+	add	ecx,edx
+	vpor	xmm1,xmm1,xmm8
+	add	ebx,DWORD[28+rsp]
+	xor	edi,ebp
+	mov	esi,ecx
+	shld	ecx,ecx,5
+	add	ebx,edi
+	xor	esi,ebp
+	shrd	edx,edx,7
+	add	ebx,ecx
+	vpalignr	xmm8,xmm1,xmm0,8
+	vpxor	xmm2,xmm2,xmm6
+	add	eax,DWORD[32+rsp]
+	xor	esi,edx
+	mov	edi,ebx
+	shld	ebx,ebx,5
+	vpxor	xmm2,xmm2,xmm3
+	add	eax,esi
+	xor	edi,edx
+	vpaddd	xmm9,xmm11,xmm1
+	vmovdqa	xmm11,XMMWORD[r11]
+	shrd	ecx,ecx,7
+	add	eax,ebx
+	vpxor	xmm2,xmm2,xmm8
+	add	ebp,DWORD[36+rsp]
+	xor	edi,ecx
+	mov	esi,eax
+	shld	eax,eax,5
+	vpsrld	xmm8,xmm2,30
+	vmovdqa	XMMWORD[16+rsp],xmm9
+	add	ebp,edi
+	xor	esi,ecx
+	shrd	ebx,ebx,7
+	add	ebp,eax
+	vpslld	xmm2,xmm2,2
+	add	edx,DWORD[40+rsp]
+	xor	esi,ebx
+	mov	edi,ebp
+	shld	ebp,ebp,5
+	add	edx,esi
+	xor	edi,ebx
+	shrd	eax,eax,7
+	add	edx,ebp
+	vpor	xmm2,xmm2,xmm8
+	add	ecx,DWORD[44+rsp]
+	xor	edi,eax
+	mov	esi,edx
+	shld	edx,edx,5
+	add	ecx,edi
+	xor	esi,eax
+	shrd	ebp,ebp,7
+	add	ecx,edx
+	vpalignr	xmm8,xmm2,xmm1,8
+	vpxor	xmm3,xmm3,xmm7
+	add	ebx,DWORD[48+rsp]
+	xor	esi,ebp
+	mov	edi,ecx
+	shld	ecx,ecx,5
+	vpxor	xmm3,xmm3,xmm4
+	add	ebx,esi
+	xor	edi,ebp
+	vpaddd	xmm9,xmm11,xmm2
+	shrd	edx,edx,7
+	add	ebx,ecx
+	vpxor	xmm3,xmm3,xmm8
+	add	eax,DWORD[52+rsp]
+	xor	edi,edx
+	mov	esi,ebx
+	shld	ebx,ebx,5
+	vpsrld	xmm8,xmm3,30
+	vmovdqa	XMMWORD[32+rsp],xmm9
+	add	eax,edi
+	xor	esi,edx
+	shrd	ecx,ecx,7
+	add	eax,ebx
+	vpslld	xmm3,xmm3,2
+	add	ebp,DWORD[56+rsp]
+	xor	esi,ecx
+	mov	edi,eax
+	shld	eax,eax,5
+	add	ebp,esi
+	xor	edi,ecx
+	shrd	ebx,ebx,7
+	add	ebp,eax
+	vpor	xmm3,xmm3,xmm8
+	add	edx,DWORD[60+rsp]
+	xor	edi,ebx
+	mov	esi,ebp
+	shld	ebp,ebp,5
+	add	edx,edi
+	xor	esi,ebx
+	shrd	eax,eax,7
+	add	edx,ebp
+	vpalignr	xmm8,xmm3,xmm2,8
+	vpxor	xmm4,xmm4,xmm0
+	add	ecx,DWORD[rsp]
+	xor	esi,eax
+	mov	edi,edx
+	shld	edx,edx,5
+	vpxor	xmm4,xmm4,xmm5
+	add	ecx,esi
+	xor	edi,eax
+	vpaddd	xmm9,xmm11,xmm3
+	shrd	ebp,ebp,7
+	add	ecx,edx
+	vpxor	xmm4,xmm4,xmm8
+	add	ebx,DWORD[4+rsp]
+	xor	edi,ebp
+	mov	esi,ecx
+	shld	ecx,ecx,5
+	vpsrld	xmm8,xmm4,30
+	vmovdqa	XMMWORD[48+rsp],xmm9
+	add	ebx,edi
+	xor	esi,ebp
+	shrd	edx,edx,7
+	add	ebx,ecx
+	vpslld	xmm4,xmm4,2
+	add	eax,DWORD[8+rsp]
+	xor	esi,edx
+	mov	edi,ebx
+	shld	ebx,ebx,5
+	add	eax,esi
+	xor	edi,edx
+	shrd	ecx,ecx,7
+	add	eax,ebx
+	vpor	xmm4,xmm4,xmm8
+	add	ebp,DWORD[12+rsp]
+	xor	edi,ecx
+	mov	esi,eax
+	shld	eax,eax,5
+	add	ebp,edi
+	xor	esi,ecx
+	shrd	ebx,ebx,7
+	add	ebp,eax
+	vpalignr	xmm8,xmm4,xmm3,8
+	vpxor	xmm5,xmm5,xmm1
+	add	edx,DWORD[16+rsp]
+	xor	esi,ebx
+	mov	edi,ebp
+	shld	ebp,ebp,5
+	vpxor	xmm5,xmm5,xmm6
+	add	edx,esi
+	xor	edi,ebx
+	vpaddd	xmm9,xmm11,xmm4
+	shrd	eax,eax,7
+	add	edx,ebp
+	vpxor	xmm5,xmm5,xmm8
+	add	ecx,DWORD[20+rsp]
+	xor	edi,eax
+	mov	esi,edx
+	shld	edx,edx,5
+	vpsrld	xmm8,xmm5,30
+	vmovdqa	XMMWORD[rsp],xmm9
+	add	ecx,edi
+	xor	esi,eax
+	shrd	ebp,ebp,7
+	add	ecx,edx
+	vpslld	xmm5,xmm5,2
+	add	ebx,DWORD[24+rsp]
+	xor	esi,ebp
+	mov	edi,ecx
+	shld	ecx,ecx,5
+	add	ebx,esi
+	xor	edi,ebp
+	shrd	edx,edx,7
+	add	ebx,ecx
+	vpor	xmm5,xmm5,xmm8
+	add	eax,DWORD[28+rsp]
+	shrd	ecx,ecx,7
+	mov	esi,ebx
+	xor	edi,edx
+	shld	ebx,ebx,5
+	add	eax,edi
+	xor	esi,ecx
+	xor	ecx,edx
+	add	eax,ebx
+	vpalignr	xmm8,xmm5,xmm4,8
+	vpxor	xmm6,xmm6,xmm2
+	add	ebp,DWORD[32+rsp]
+	and	esi,ecx
+	xor	ecx,edx
+	shrd	ebx,ebx,7
+	vpxor	xmm6,xmm6,xmm7
+	mov	edi,eax
+	xor	esi,ecx
+	vpaddd	xmm9,xmm11,xmm5
+	shld	eax,eax,5
+	add	ebp,esi
+	vpxor	xmm6,xmm6,xmm8
+	xor	edi,ebx
+	xor	ebx,ecx
+	add	ebp,eax
+	add	edx,DWORD[36+rsp]
+	vpsrld	xmm8,xmm6,30
+	vmovdqa	XMMWORD[16+rsp],xmm9
+	and	edi,ebx
+	xor	ebx,ecx
+	shrd	eax,eax,7
+	mov	esi,ebp
+	vpslld	xmm6,xmm6,2
+	xor	edi,ebx
+	shld	ebp,ebp,5
+	add	edx,edi
+	xor	esi,eax
+	xor	eax,ebx
+	add	edx,ebp
+	add	ecx,DWORD[40+rsp]
+	and	esi,eax
+	vpor	xmm6,xmm6,xmm8
+	xor	eax,ebx
+	shrd	ebp,ebp,7
+	mov	edi,edx
+	xor	esi,eax
+	shld	edx,edx,5
+	add	ecx,esi
+	xor	edi,ebp
+	xor	ebp,eax
+	add	ecx,edx
+	add	ebx,DWORD[44+rsp]
+	and	edi,ebp
+	xor	ebp,eax
+	shrd	edx,edx,7
+	mov	esi,ecx
+	xor	edi,ebp
+	shld	ecx,ecx,5
+	add	ebx,edi
+	xor	esi,edx
+	xor	edx,ebp
+	add	ebx,ecx
+	vpalignr	xmm8,xmm6,xmm5,8
+	vpxor	xmm7,xmm7,xmm3
+	add	eax,DWORD[48+rsp]
+	and	esi,edx
+	xor	edx,ebp
+	shrd	ecx,ecx,7
+	vpxor	xmm7,xmm7,xmm0
+	mov	edi,ebx
+	xor	esi,edx
+	vpaddd	xmm9,xmm11,xmm6
+	vmovdqa	xmm11,XMMWORD[32+r11]
+	shld	ebx,ebx,5
+	add	eax,esi
+	vpxor	xmm7,xmm7,xmm8
+	xor	edi,ecx
+	xor	ecx,edx
+	add	eax,ebx
+	add	ebp,DWORD[52+rsp]
+	vpsrld	xmm8,xmm7,30
+	vmovdqa	XMMWORD[32+rsp],xmm9
+	and	edi,ecx
+	xor	ecx,edx
+	shrd	ebx,ebx,7
+	mov	esi,eax
+	vpslld	xmm7,xmm7,2
+	xor	edi,ecx
+	shld	eax,eax,5
+	add	ebp,edi
+	xor	esi,ebx
+	xor	ebx,ecx
+	add	ebp,eax
+	add	edx,DWORD[56+rsp]
+	and	esi,ebx
+	vpor	xmm7,xmm7,xmm8
+	xor	ebx,ecx
+	shrd	eax,eax,7
+	mov	edi,ebp
+	xor	esi,ebx
+	shld	ebp,ebp,5
+	add	edx,esi
+	xor	edi,eax
+	xor	eax,ebx
+	add	edx,ebp
+	add	ecx,DWORD[60+rsp]
+	and	edi,eax
+	xor	eax,ebx
+	shrd	ebp,ebp,7
+	mov	esi,edx
+	xor	edi,eax
+	shld	edx,edx,5
+	add	ecx,edi
+	xor	esi,ebp
+	xor	ebp,eax
+	add	ecx,edx
+	vpalignr	xmm8,xmm7,xmm6,8
+	vpxor	xmm0,xmm0,xmm4
+	add	ebx,DWORD[rsp]
+	and	esi,ebp
+	xor	ebp,eax
+	shrd	edx,edx,7
+	vpxor	xmm0,xmm0,xmm1
+	mov	edi,ecx
+	xor	esi,ebp
+	vpaddd	xmm9,xmm11,xmm7
+	shld	ecx,ecx,5
+	add	ebx,esi
+	vpxor	xmm0,xmm0,xmm8
+	xor	edi,edx
+	xor	edx,ebp
+	add	ebx,ecx
+	add	eax,DWORD[4+rsp]
+	vpsrld	xmm8,xmm0,30
+	vmovdqa	XMMWORD[48+rsp],xmm9
+	and	edi,edx
+	xor	edx,ebp
+	shrd	ecx,ecx,7
+	mov	esi,ebx
+	vpslld	xmm0,xmm0,2
+	xor	edi,edx
+	shld	ebx,ebx,5
+	add	eax,edi
+	xor	esi,ecx
+	xor	ecx,edx
+	add	eax,ebx
+	add	ebp,DWORD[8+rsp]
+	and	esi,ecx
+	vpor	xmm0,xmm0,xmm8
+	xor	ecx,edx
+	shrd	ebx,ebx,7
+	mov	edi,eax
+	xor	esi,ecx
+	shld	eax,eax,5
+	add	ebp,esi
+	xor	edi,ebx
+	xor	ebx,ecx
+	add	ebp,eax
+	add	edx,DWORD[12+rsp]
+	and	edi,ebx
+	xor	ebx,ecx
+	shrd	eax,eax,7
+	mov	esi,ebp
+	xor	edi,ebx
+	shld	ebp,ebp,5
+	add	edx,edi
+	xor	esi,eax
+	xor	eax,ebx
+	add	edx,ebp
+	vpalignr	xmm8,xmm0,xmm7,8
+	vpxor	xmm1,xmm1,xmm5
+	add	ecx,DWORD[16+rsp]
+	and	esi,eax
+	xor	eax,ebx
+	shrd	ebp,ebp,7
+	vpxor	xmm1,xmm1,xmm2
+	mov	edi,edx
+	xor	esi,eax
+	vpaddd	xmm9,xmm11,xmm0
+	shld	edx,edx,5
+	add	ecx,esi
+	vpxor	xmm1,xmm1,xmm8
+	xor	edi,ebp
+	xor	ebp,eax
+	add	ecx,edx
+	add	ebx,DWORD[20+rsp]
+	vpsrld	xmm8,xmm1,30
+	vmovdqa	XMMWORD[rsp],xmm9
+	and	edi,ebp
+	xor	ebp,eax
+	shrd	edx,edx,7
+	mov	esi,ecx
+	vpslld	xmm1,xmm1,2
+	xor	edi,ebp
+	shld	ecx,ecx,5
+	add	ebx,edi
+	xor	esi,edx
+	xor	edx,ebp
+	add	ebx,ecx
+	add	eax,DWORD[24+rsp]
+	and	esi,edx
+	vpor	xmm1,xmm1,xmm8
+	xor	edx,ebp
+	shrd	ecx,ecx,7
+	mov	edi,ebx
+	xor	esi,edx
+	shld	ebx,ebx,5
+	add	eax,esi
+	xor	edi,ecx
+	xor	ecx,edx
+	add	eax,ebx
+	add	ebp,DWORD[28+rsp]
+	and	edi,ecx
+	xor	ecx,edx
+	shrd	ebx,ebx,7
+	mov	esi,eax
+	xor	edi,ecx
+	shld	eax,eax,5
+	add	ebp,edi
+	xor	esi,ebx
+	xor	ebx,ecx
+	add	ebp,eax
+	vpalignr	xmm8,xmm1,xmm0,8
+	vpxor	xmm2,xmm2,xmm6
+	add	edx,DWORD[32+rsp]
+	and	esi,ebx
+	xor	ebx,ecx
+	shrd	eax,eax,7
+	vpxor	xmm2,xmm2,xmm3
+	mov	edi,ebp
+	xor	esi,ebx
+	vpaddd	xmm9,xmm11,xmm1
+	shld	ebp,ebp,5
+	add	edx,esi
+	vpxor	xmm2,xmm2,xmm8
+	xor	edi,eax
+	xor	eax,ebx
+	add	edx,ebp
+	add	ecx,DWORD[36+rsp]
+	vpsrld	xmm8,xmm2,30
+	vmovdqa	XMMWORD[16+rsp],xmm9
+	and	edi,eax
+	xor	eax,ebx
+	shrd	ebp,ebp,7
+	mov	esi,edx
+	vpslld	xmm2,xmm2,2
+	xor	edi,eax
+	shld	edx,edx,5
+	add	ecx,edi
+	xor	esi,ebp
+	xor	ebp,eax
+	add	ecx,edx
+	add	ebx,DWORD[40+rsp]
+	and	esi,ebp
+	vpor	xmm2,xmm2,xmm8
+	xor	ebp,eax
+	shrd	edx,edx,7
+	mov	edi,ecx
+	xor	esi,ebp
+	shld	ecx,ecx,5
+	add	ebx,esi
+	xor	edi,edx
+	xor	edx,ebp
+	add	ebx,ecx
+	add	eax,DWORD[44+rsp]
+	and	edi,edx
+	xor	edx,ebp
+	shrd	ecx,ecx,7
+	mov	esi,ebx
+	xor	edi,edx
+	shld	ebx,ebx,5
+	add	eax,edi
+	xor	esi,edx
+	add	eax,ebx
+	vpalignr	xmm8,xmm2,xmm1,8
+	vpxor	xmm3,xmm3,xmm7
+	add	ebp,DWORD[48+rsp]
+	xor	esi,ecx
+	mov	edi,eax
+	shld	eax,eax,5
+	vpxor	xmm3,xmm3,xmm4
+	add	ebp,esi
+	xor	edi,ecx
+	vpaddd	xmm9,xmm11,xmm2
+	shrd	ebx,ebx,7
+	add	ebp,eax
+	vpxor	xmm3,xmm3,xmm8
+	add	edx,DWORD[52+rsp]
+	xor	edi,ebx
+	mov	esi,ebp
+	shld	ebp,ebp,5
+	vpsrld	xmm8,xmm3,30
+	vmovdqa	XMMWORD[32+rsp],xmm9
+	add	edx,edi
+	xor	esi,ebx
+	shrd	eax,eax,7
+	add	edx,ebp
+	vpslld	xmm3,xmm3,2
+	add	ecx,DWORD[56+rsp]
+	xor	esi,eax
+	mov	edi,edx
+	shld	edx,edx,5
+	add	ecx,esi
+	xor	edi,eax
+	shrd	ebp,ebp,7
+	add	ecx,edx
+	vpor	xmm3,xmm3,xmm8
+	add	ebx,DWORD[60+rsp]
+	xor	edi,ebp
+	mov	esi,ecx
+	shld	ecx,ecx,5
+	add	ebx,edi
+	xor	esi,ebp
+	shrd	edx,edx,7
+	add	ebx,ecx
+	add	eax,DWORD[rsp]
+	vpaddd	xmm9,xmm11,xmm3
+	xor	esi,edx
+	mov	edi,ebx
+	shld	ebx,ebx,5
+	add	eax,esi
+	vmovdqa	XMMWORD[48+rsp],xmm9
+	xor	edi,edx
+	shrd	ecx,ecx,7
+	add	eax,ebx
+	add	ebp,DWORD[4+rsp]
+	xor	edi,ecx
+	mov	esi,eax
+	shld	eax,eax,5
+	add	ebp,edi
+	xor	esi,ecx
+	shrd	ebx,ebx,7
+	add	ebp,eax
+	add	edx,DWORD[8+rsp]
+	xor	esi,ebx
+	mov	edi,ebp
+	shld	ebp,ebp,5
+	add	edx,esi
+	xor	edi,ebx
+	shrd	eax,eax,7
+	add	edx,ebp
+	add	ecx,DWORD[12+rsp]
+	xor	edi,eax
+	mov	esi,edx
+	shld	edx,edx,5
+	add	ecx,edi
+	xor	esi,eax
+	shrd	ebp,ebp,7
+	add	ecx,edx
+	cmp	r9,r10
+	je	NEAR $L$done_avx
+	vmovdqa	xmm6,XMMWORD[64+r11]
+	vmovdqa	xmm11,XMMWORD[((-64))+r11]
+	vmovdqu	xmm0,XMMWORD[r9]
+	vmovdqu	xmm1,XMMWORD[16+r9]
+	vmovdqu	xmm2,XMMWORD[32+r9]
+	vmovdqu	xmm3,XMMWORD[48+r9]
+	vpshufb	xmm0,xmm0,xmm6
+	add	r9,64
+	add	ebx,DWORD[16+rsp]
+	xor	esi,ebp
+	vpshufb	xmm1,xmm1,xmm6
+	mov	edi,ecx
+	shld	ecx,ecx,5
+	vpaddd	xmm4,xmm0,xmm11
+	add	ebx,esi
+	xor	edi,ebp
+	shrd	edx,edx,7
+	add	ebx,ecx
+	vmovdqa	XMMWORD[rsp],xmm4
+	add	eax,DWORD[20+rsp]
+	xor	edi,edx
+	mov	esi,ebx
+	shld	ebx,ebx,5
+	add	eax,edi
+	xor	esi,edx
+	shrd	ecx,ecx,7
+	add	eax,ebx
+	add	ebp,DWORD[24+rsp]
+	xor	esi,ecx
+	mov	edi,eax
+	shld	eax,eax,5
+	add	ebp,esi
+	xor	edi,ecx
+	shrd	ebx,ebx,7
+	add	ebp,eax
+	add	edx,DWORD[28+rsp]
+	xor	edi,ebx
+	mov	esi,ebp
+	shld	ebp,ebp,5
+	add	edx,edi
+	xor	esi,ebx
+	shrd	eax,eax,7
+	add	edx,ebp
+	add	ecx,DWORD[32+rsp]
+	xor	esi,eax
+	vpshufb	xmm2,xmm2,xmm6
+	mov	edi,edx
+	shld	edx,edx,5
+	vpaddd	xmm5,xmm1,xmm11
+	add	ecx,esi
+	xor	edi,eax
+	shrd	ebp,ebp,7
+	add	ecx,edx
+	vmovdqa	XMMWORD[16+rsp],xmm5
+	add	ebx,DWORD[36+rsp]
+	xor	edi,ebp
+	mov	esi,ecx
+	shld	ecx,ecx,5
+	add	ebx,edi
+	xor	esi,ebp
+	shrd	edx,edx,7
+	add	ebx,ecx
+	add	eax,DWORD[40+rsp]
+	xor	esi,edx
+	mov	edi,ebx
+	shld	ebx,ebx,5
+	add	eax,esi
+	xor	edi,edx
+	shrd	ecx,ecx,7
+	add	eax,ebx
+	add	ebp,DWORD[44+rsp]
+	xor	edi,ecx
+	mov	esi,eax
+	shld	eax,eax,5
+	add	ebp,edi
+	xor	esi,ecx
+	shrd	ebx,ebx,7
+	add	ebp,eax
+	add	edx,DWORD[48+rsp]
+	xor	esi,ebx
+	vpshufb	xmm3,xmm3,xmm6
+	mov	edi,ebp
+	shld	ebp,ebp,5
+	vpaddd	xmm6,xmm2,xmm11
+	add	edx,esi
+	xor	edi,ebx
+	shrd	eax,eax,7
+	add	edx,ebp
+	vmovdqa	XMMWORD[32+rsp],xmm6
+	add	ecx,DWORD[52+rsp]
+	xor	edi,eax
+	mov	esi,edx
+	shld	edx,edx,5
+	add	ecx,edi
+	xor	esi,eax
+	shrd	ebp,ebp,7
+	add	ecx,edx
+	add	ebx,DWORD[56+rsp]
+	xor	esi,ebp
+	mov	edi,ecx
+	shld	ecx,ecx,5
+	add	ebx,esi
+	xor	edi,ebp
+	shrd	edx,edx,7
+	add	ebx,ecx
+	add	eax,DWORD[60+rsp]
+	xor	edi,edx
+	mov	esi,ebx
+	shld	ebx,ebx,5
+	add	eax,edi
+	shrd	ecx,ecx,7
+	add	eax,ebx
+	add	eax,DWORD[r8]
+	add	esi,DWORD[4+r8]
+	add	ecx,DWORD[8+r8]
+	add	edx,DWORD[12+r8]
+	mov	DWORD[r8],eax
+	add	ebp,DWORD[16+r8]
+	mov	DWORD[4+r8],esi
+	mov	ebx,esi
+	mov	DWORD[8+r8],ecx
+	mov	edi,ecx
+	mov	DWORD[12+r8],edx
+	xor	edi,edx
+	mov	DWORD[16+r8],ebp
+	and	esi,edi
+	jmp	NEAR $L$oop_avx
+
+ALIGN	16
+$L$done_avx:
+	add	ebx,DWORD[16+rsp]
+	xor	esi,ebp
+	mov	edi,ecx
+	shld	ecx,ecx,5
+	add	ebx,esi
+	xor	edi,ebp
+	shrd	edx,edx,7
+	add	ebx,ecx
+	add	eax,DWORD[20+rsp]
+	xor	edi,edx
+	mov	esi,ebx
+	shld	ebx,ebx,5
+	add	eax,edi
+	xor	esi,edx
+	shrd	ecx,ecx,7
+	add	eax,ebx
+	add	ebp,DWORD[24+rsp]
+	xor	esi,ecx
+	mov	edi,eax
+	shld	eax,eax,5
+	add	ebp,esi
+	xor	edi,ecx
+	shrd	ebx,ebx,7
+	add	ebp,eax
+	add	edx,DWORD[28+rsp]
+	xor	edi,ebx
+	mov	esi,ebp
+	shld	ebp,ebp,5
+	add	edx,edi
+	xor	esi,ebx
+	shrd	eax,eax,7
+	add	edx,ebp
+	add	ecx,DWORD[32+rsp]
+	xor	esi,eax
+	mov	edi,edx
+	shld	edx,edx,5
+	add	ecx,esi
+	xor	edi,eax
+	shrd	ebp,ebp,7
+	add	ecx,edx
+	add	ebx,DWORD[36+rsp]
+	xor	edi,ebp
+	mov	esi,ecx
+	shld	ecx,ecx,5
+	add	ebx,edi
+	xor	esi,ebp
+	shrd	edx,edx,7
+	add	ebx,ecx
+	add	eax,DWORD[40+rsp]
+	xor	esi,edx
+	mov	edi,ebx
+	shld	ebx,ebx,5
+	add	eax,esi
+	xor	edi,edx
+	shrd	ecx,ecx,7
+	add	eax,ebx
+	add	ebp,DWORD[44+rsp]
+	xor	edi,ecx
+	mov	esi,eax
+	shld	eax,eax,5
+	add	ebp,edi
+	xor	esi,ecx
+	shrd	ebx,ebx,7
+	add	ebp,eax
+	add	edx,DWORD[48+rsp]
+	xor	esi,ebx
+	mov	edi,ebp
+	shld	ebp,ebp,5
+	add	edx,esi
+	xor	edi,ebx
+	shrd	eax,eax,7
+	add	edx,ebp
+	add	ecx,DWORD[52+rsp]
+	xor	edi,eax
+	mov	esi,edx
+	shld	edx,edx,5
+	add	ecx,edi
+	xor	esi,eax
+	shrd	ebp,ebp,7
+	add	ecx,edx
+	add	ebx,DWORD[56+rsp]
+	xor	esi,ebp
+	mov	edi,ecx
+	shld	ecx,ecx,5
+	add	ebx,esi
+	xor	edi,ebp
+	shrd	edx,edx,7
+	add	ebx,ecx
+	add	eax,DWORD[60+rsp]
+	xor	edi,edx
+	mov	esi,ebx
+	shld	ebx,ebx,5
+	add	eax,edi
+	shrd	ecx,ecx,7
+	add	eax,ebx
+	vzeroupper
+
+	add	eax,DWORD[r8]
+	add	esi,DWORD[4+r8]
+	add	ecx,DWORD[8+r8]
+	mov	DWORD[r8],eax
+	add	edx,DWORD[12+r8]
+	mov	DWORD[4+r8],esi
+	add	ebp,DWORD[16+r8]
+	mov	DWORD[8+r8],ecx
+	mov	DWORD[12+r8],edx
+	mov	DWORD[16+r8],ebp
+	movaps	xmm6,XMMWORD[((-40-96))+r14]
+	movaps	xmm7,XMMWORD[((-40-80))+r14]
+	movaps	xmm8,XMMWORD[((-40-64))+r14]
+	movaps	xmm9,XMMWORD[((-40-48))+r14]
+	movaps	xmm10,XMMWORD[((-40-32))+r14]
+	movaps	xmm11,XMMWORD[((-40-16))+r14]
+	lea	rsi,[r14]
+	mov	r14,QWORD[((-40))+rsi]
+	mov	r13,QWORD[((-32))+rsi]
+	mov	r12,QWORD[((-24))+rsi]
+	mov	rbp,QWORD[((-16))+rsi]
+	mov	rbx,QWORD[((-8))+rsi]
+	lea	rsp,[rsi]
+$L$epilogue_avx:
+	mov	rdi,QWORD[8+rsp]	;WIN64 epilogue
+	mov	rsi,QWORD[16+rsp]
+	DB	0F3h,0C3h		;repret
+$L$SEH_end_sha1_block_data_order_avx:
 ALIGN	64
 K_XX_XX:
 	DD	0x5a827999,0x5a827999,0x5a827999,0x5a827999
@@ -2605,6 +3750,9 @@ ALIGN	4
 	DD	$L$SEH_begin_sha1_block_data_order_ssse3 wrt ..imagebase
 	DD	$L$SEH_end_sha1_block_data_order_ssse3 wrt ..imagebase
 	DD	$L$SEH_info_sha1_block_data_order_ssse3 wrt ..imagebase
+	DD	$L$SEH_begin_sha1_block_data_order_avx wrt ..imagebase
+	DD	$L$SEH_end_sha1_block_data_order_avx wrt ..imagebase
+	DD	$L$SEH_info_sha1_block_data_order_avx wrt ..imagebase
 section	.xdata rdata align=8
 ALIGN	8
 $L$SEH_info_sha1_block_data_order:
@@ -2614,3 +3762,7 @@ $L$SEH_info_sha1_block_data_order_ssse3:
 DB	9,0,0,0
 	DD	ssse3_handler wrt ..imagebase
 	DD	$L$prologue_ssse3 wrt ..imagebase,$L$epilogue_ssse3 wrt ..imagebase
+$L$SEH_info_sha1_block_data_order_avx:
+DB	9,0,0,0
+	DD	ssse3_handler wrt ..imagebase
+	DD	$L$prologue_avx wrt ..imagebase,$L$epilogue_avx wrt ..imagebase
diff --git a/packager/third_party/boringssl/win-x86_64/crypto/sha/sha256-x86_64.asm b/packager/third_party/boringssl/win-x86_64/crypto/sha/sha256-x86_64.asm
index e6193c5b9d..efaf9b55fc 100644
--- a/packager/third_party/boringssl/win-x86_64/crypto/sha/sha256-x86_64.asm
+++ b/packager/third_party/boringssl/win-x86_64/crypto/sha/sha256-x86_64.asm
@@ -23,6 +23,11 @@ $L$SEH_begin_sha256_block_data_order:
 	mov	r9d,DWORD[r11]
 	mov	r10d,DWORD[4+r11]
 	mov	r11d,DWORD[8+r11]
+	and	r9d,1073741824
+	and	r10d,268435968
+	or	r10d,r9d
+	cmp	r10d,1342177792
+	je	NEAR $L$avx_shortcut
 	test	r10d,512
 	jnz	NEAR $L$ssse3_shortcut
 	push	rbx
@@ -2877,6 +2882,1082 @@ $L$epilogue_ssse3:
 	mov	rsi,QWORD[16+rsp]
 	DB	0F3h,0C3h		;repret
 $L$SEH_end_sha256_block_data_order_ssse3:
+
+ALIGN	64
+sha256_block_data_order_avx:
+	mov	QWORD[8+rsp],rdi	;WIN64 prologue
+	mov	QWORD[16+rsp],rsi
+	mov	rax,rsp
+$L$SEH_begin_sha256_block_data_order_avx:
+	mov	rdi,rcx
+	mov	rsi,rdx
+	mov	rdx,r8
+
+
+$L$avx_shortcut:
+	push	rbx
+	push	rbp
+	push	r12
+	push	r13
+	push	r14
+	push	r15
+	mov	r11,rsp
+	shl	rdx,4
+	sub	rsp,160
+	lea	rdx,[rdx*4+rsi]
+	and	rsp,-64
+	mov	QWORD[((64+0))+rsp],rdi
+	mov	QWORD[((64+8))+rsp],rsi
+	mov	QWORD[((64+16))+rsp],rdx
+	mov	QWORD[((64+24))+rsp],r11
+	movaps	XMMWORD[(64+32)+rsp],xmm6
+	movaps	XMMWORD[(64+48)+rsp],xmm7
+	movaps	XMMWORD[(64+64)+rsp],xmm8
+	movaps	XMMWORD[(64+80)+rsp],xmm9
+$L$prologue_avx:
+
+	vzeroupper
+	mov	eax,DWORD[rdi]
+	mov	ebx,DWORD[4+rdi]
+	mov	ecx,DWORD[8+rdi]
+	mov	edx,DWORD[12+rdi]
+	mov	r8d,DWORD[16+rdi]
+	mov	r9d,DWORD[20+rdi]
+	mov	r10d,DWORD[24+rdi]
+	mov	r11d,DWORD[28+rdi]
+	vmovdqa	xmm8,XMMWORD[((K256+512+32))]
+	vmovdqa	xmm9,XMMWORD[((K256+512+64))]
+	jmp	NEAR $L$loop_avx
+ALIGN	16
+$L$loop_avx:
+	vmovdqa	xmm7,XMMWORD[((K256+512))]
+	vmovdqu	xmm0,XMMWORD[rsi]
+	vmovdqu	xmm1,XMMWORD[16+rsi]
+	vmovdqu	xmm2,XMMWORD[32+rsi]
+	vmovdqu	xmm3,XMMWORD[48+rsi]
+	vpshufb	xmm0,xmm0,xmm7
+	lea	rbp,[K256]
+	vpshufb	xmm1,xmm1,xmm7
+	vpshufb	xmm2,xmm2,xmm7
+	vpaddd	xmm4,xmm0,XMMWORD[rbp]
+	vpshufb	xmm3,xmm3,xmm7
+	vpaddd	xmm5,xmm1,XMMWORD[32+rbp]
+	vpaddd	xmm6,xmm2,XMMWORD[64+rbp]
+	vpaddd	xmm7,xmm3,XMMWORD[96+rbp]
+	vmovdqa	XMMWORD[rsp],xmm4
+	mov	r14d,eax
+	vmovdqa	XMMWORD[16+rsp],xmm5
+	mov	edi,ebx
+	vmovdqa	XMMWORD[32+rsp],xmm6
+	xor	edi,ecx
+	vmovdqa	XMMWORD[48+rsp],xmm7
+	mov	r13d,r8d
+	jmp	NEAR $L$avx_00_47
+
+ALIGN	16
+$L$avx_00_47:
+	sub	rbp,-128
+	vpalignr	xmm4,xmm1,xmm0,4
+	shrd	r13d,r13d,14
+	mov	eax,r14d
+	mov	r12d,r9d
+	vpalignr	xmm7,xmm3,xmm2,4
+	shrd	r14d,r14d,9
+	xor	r13d,r8d
+	xor	r12d,r10d
+	vpsrld	xmm6,xmm4,7
+	shrd	r13d,r13d,5
+	xor	r14d,eax
+	and	r12d,r8d
+	vpaddd	xmm0,xmm0,xmm7
+	xor	r13d,r8d
+	add	r11d,DWORD[rsp]
+	mov	r15d,eax
+	vpsrld	xmm7,xmm4,3
+	xor	r12d,r10d
+	shrd	r14d,r14d,11
+	xor	r15d,ebx
+	vpslld	xmm5,xmm4,14
+	add	r11d,r12d
+	shrd	r13d,r13d,6
+	and	edi,r15d
+	vpxor	xmm4,xmm7,xmm6
+	xor	r14d,eax
+	add	r11d,r13d
+	xor	edi,ebx
+	vpshufd	xmm7,xmm3,250
+	shrd	r14d,r14d,2
+	add	edx,r11d
+	add	r11d,edi
+	vpsrld	xmm6,xmm6,11
+	mov	r13d,edx
+	add	r14d,r11d
+	shrd	r13d,r13d,14
+	vpxor	xmm4,xmm4,xmm5
+	mov	r11d,r14d
+	mov	r12d,r8d
+	shrd	r14d,r14d,9
+	vpslld	xmm5,xmm5,11
+	xor	r13d,edx
+	xor	r12d,r9d
+	shrd	r13d,r13d,5
+	vpxor	xmm4,xmm4,xmm6
+	xor	r14d,r11d
+	and	r12d,edx
+	xor	r13d,edx
+	vpsrld	xmm6,xmm7,10
+	add	r10d,DWORD[4+rsp]
+	mov	edi,r11d
+	xor	r12d,r9d
+	vpxor	xmm4,xmm4,xmm5
+	shrd	r14d,r14d,11
+	xor	edi,eax
+	add	r10d,r12d
+	vpsrlq	xmm7,xmm7,17
+	shrd	r13d,r13d,6
+	and	r15d,edi
+	xor	r14d,r11d
+	vpaddd	xmm0,xmm0,xmm4
+	add	r10d,r13d
+	xor	r15d,eax
+	shrd	r14d,r14d,2
+	vpxor	xmm6,xmm6,xmm7
+	add	ecx,r10d
+	add	r10d,r15d
+	mov	r13d,ecx
+	vpsrlq	xmm7,xmm7,2
+	add	r14d,r10d
+	shrd	r13d,r13d,14
+	mov	r10d,r14d
+	vpxor	xmm6,xmm6,xmm7
+	mov	r12d,edx
+	shrd	r14d,r14d,9
+	xor	r13d,ecx
+	vpshufb	xmm6,xmm6,xmm8
+	xor	r12d,r8d
+	shrd	r13d,r13d,5
+	xor	r14d,r10d
+	vpaddd	xmm0,xmm0,xmm6
+	and	r12d,ecx
+	xor	r13d,ecx
+	add	r9d,DWORD[8+rsp]
+	vpshufd	xmm7,xmm0,80
+	mov	r15d,r10d
+	xor	r12d,r8d
+	shrd	r14d,r14d,11
+	vpsrld	xmm6,xmm7,10
+	xor	r15d,r11d
+	add	r9d,r12d
+	shrd	r13d,r13d,6
+	vpsrlq	xmm7,xmm7,17
+	and	edi,r15d
+	xor	r14d,r10d
+	add	r9d,r13d
+	vpxor	xmm6,xmm6,xmm7
+	xor	edi,r11d
+	shrd	r14d,r14d,2
+	add	ebx,r9d
+	vpsrlq	xmm7,xmm7,2
+	add	r9d,edi
+	mov	r13d,ebx
+	add	r14d,r9d
+	vpxor	xmm6,xmm6,xmm7
+	shrd	r13d,r13d,14
+	mov	r9d,r14d
+	mov	r12d,ecx
+	vpshufb	xmm6,xmm6,xmm9
+	shrd	r14d,r14d,9
+	xor	r13d,ebx
+	xor	r12d,edx
+	vpaddd	xmm0,xmm0,xmm6
+	shrd	r13d,r13d,5
+	xor	r14d,r9d
+	and	r12d,ebx
+	vpaddd	xmm6,xmm0,XMMWORD[rbp]
+	xor	r13d,ebx
+	add	r8d,DWORD[12+rsp]
+	mov	edi,r9d
+	xor	r12d,edx
+	shrd	r14d,r14d,11
+	xor	edi,r10d
+	add	r8d,r12d
+	shrd	r13d,r13d,6
+	and	r15d,edi
+	xor	r14d,r9d
+	add	r8d,r13d
+	xor	r15d,r10d
+	shrd	r14d,r14d,2
+	add	eax,r8d
+	add	r8d,r15d
+	mov	r13d,eax
+	add	r14d,r8d
+	vmovdqa	XMMWORD[rsp],xmm6
+	vpalignr	xmm4,xmm2,xmm1,4
+	shrd	r13d,r13d,14
+	mov	r8d,r14d
+	mov	r12d,ebx
+	vpalignr	xmm7,xmm0,xmm3,4
+	shrd	r14d,r14d,9
+	xor	r13d,eax
+	xor	r12d,ecx
+	vpsrld	xmm6,xmm4,7
+	shrd	r13d,r13d,5
+	xor	r14d,r8d
+	and	r12d,eax
+	vpaddd	xmm1,xmm1,xmm7
+	xor	r13d,eax
+	add	edx,DWORD[16+rsp]
+	mov	r15d,r8d
+	vpsrld	xmm7,xmm4,3
+	xor	r12d,ecx
+	shrd	r14d,r14d,11
+	xor	r15d,r9d
+	vpslld	xmm5,xmm4,14
+	add	edx,r12d
+	shrd	r13d,r13d,6
+	and	edi,r15d
+	vpxor	xmm4,xmm7,xmm6
+	xor	r14d,r8d
+	add	edx,r13d
+	xor	edi,r9d
+	vpshufd	xmm7,xmm0,250
+	shrd	r14d,r14d,2
+	add	r11d,edx
+	add	edx,edi
+	vpsrld	xmm6,xmm6,11
+	mov	r13d,r11d
+	add	r14d,edx
+	shrd	r13d,r13d,14
+	vpxor	xmm4,xmm4,xmm5
+	mov	edx,r14d
+	mov	r12d,eax
+	shrd	r14d,r14d,9
+	vpslld	xmm5,xmm5,11
+	xor	r13d,r11d
+	xor	r12d,ebx
+	shrd	r13d,r13d,5
+	vpxor	xmm4,xmm4,xmm6
+	xor	r14d,edx
+	and	r12d,r11d
+	xor	r13d,r11d
+	vpsrld	xmm6,xmm7,10
+	add	ecx,DWORD[20+rsp]
+	mov	edi,edx
+	xor	r12d,ebx
+	vpxor	xmm4,xmm4,xmm5
+	shrd	r14d,r14d,11
+	xor	edi,r8d
+	add	ecx,r12d
+	vpsrlq	xmm7,xmm7,17
+	shrd	r13d,r13d,6
+	and	r15d,edi
+	xor	r14d,edx
+	vpaddd	xmm1,xmm1,xmm4
+	add	ecx,r13d
+	xor	r15d,r8d
+	shrd	r14d,r14d,2
+	vpxor	xmm6,xmm6,xmm7
+	add	r10d,ecx
+	add	ecx,r15d
+	mov	r13d,r10d
+	vpsrlq	xmm7,xmm7,2
+	add	r14d,ecx
+	shrd	r13d,r13d,14
+	mov	ecx,r14d
+	vpxor	xmm6,xmm6,xmm7
+	mov	r12d,r11d
+	shrd	r14d,r14d,9
+	xor	r13d,r10d
+	vpshufb	xmm6,xmm6,xmm8
+	xor	r12d,eax
+	shrd	r13d,r13d,5
+	xor	r14d,ecx
+	vpaddd	xmm1,xmm1,xmm6
+	and	r12d,r10d
+	xor	r13d,r10d
+	add	ebx,DWORD[24+rsp]
+	vpshufd	xmm7,xmm1,80
+	mov	r15d,ecx
+	xor	r12d,eax
+	shrd	r14d,r14d,11
+	vpsrld	xmm6,xmm7,10
+	xor	r15d,edx
+	add	ebx,r12d
+	shrd	r13d,r13d,6
+	vpsrlq	xmm7,xmm7,17
+	and	edi,r15d
+	xor	r14d,ecx
+	add	ebx,r13d
+	vpxor	xmm6,xmm6,xmm7
+	xor	edi,edx
+	shrd	r14d,r14d,2
+	add	r9d,ebx
+	vpsrlq	xmm7,xmm7,2
+	add	ebx,edi
+	mov	r13d,r9d
+	add	r14d,ebx
+	vpxor	xmm6,xmm6,xmm7
+	shrd	r13d,r13d,14
+	mov	ebx,r14d
+	mov	r12d,r10d
+	vpshufb	xmm6,xmm6,xmm9
+	shrd	r14d,r14d,9
+	xor	r13d,r9d
+	xor	r12d,r11d
+	vpaddd	xmm1,xmm1,xmm6
+	shrd	r13d,r13d,5
+	xor	r14d,ebx
+	and	r12d,r9d
+	vpaddd	xmm6,xmm1,XMMWORD[32+rbp]
+	xor	r13d,r9d
+	add	eax,DWORD[28+rsp]
+	mov	edi,ebx
+	xor	r12d,r11d
+	shrd	r14d,r14d,11
+	xor	edi,ecx
+	add	eax,r12d
+	shrd	r13d,r13d,6
+	and	r15d,edi
+	xor	r14d,ebx
+	add	eax,r13d
+	xor	r15d,ecx
+	shrd	r14d,r14d,2
+	add	r8d,eax
+	add	eax,r15d
+	mov	r13d,r8d
+	add	r14d,eax
+	vmovdqa	XMMWORD[16+rsp],xmm6
+	vpalignr	xmm4,xmm3,xmm2,4
+	shrd	r13d,r13d,14
+	mov	eax,r14d
+	mov	r12d,r9d
+	vpalignr	xmm7,xmm1,xmm0,4
+	shrd	r14d,r14d,9
+	xor	r13d,r8d
+	xor	r12d,r10d
+	vpsrld	xmm6,xmm4,7
+	shrd	r13d,r13d,5
+	xor	r14d,eax
+	and	r12d,r8d
+	vpaddd	xmm2,xmm2,xmm7
+	xor	r13d,r8d
+	add	r11d,DWORD[32+rsp]
+	mov	r15d,eax
+	vpsrld	xmm7,xmm4,3
+	xor	r12d,r10d
+	shrd	r14d,r14d,11
+	xor	r15d,ebx
+	vpslld	xmm5,xmm4,14
+	add	r11d,r12d
+	shrd	r13d,r13d,6
+	and	edi,r15d
+	vpxor	xmm4,xmm7,xmm6
+	xor	r14d,eax
+	add	r11d,r13d
+	xor	edi,ebx
+	vpshufd	xmm7,xmm1,250
+	shrd	r14d,r14d,2
+	add	edx,r11d
+	add	r11d,edi
+	vpsrld	xmm6,xmm6,11
+	mov	r13d,edx
+	add	r14d,r11d
+	shrd	r13d,r13d,14
+	vpxor	xmm4,xmm4,xmm5
+	mov	r11d,r14d
+	mov	r12d,r8d
+	shrd	r14d,r14d,9
+	vpslld	xmm5,xmm5,11
+	xor	r13d,edx
+	xor	r12d,r9d
+	shrd	r13d,r13d,5
+	vpxor	xmm4,xmm4,xmm6
+	xor	r14d,r11d
+	and	r12d,edx
+	xor	r13d,edx
+	vpsrld	xmm6,xmm7,10
+	add	r10d,DWORD[36+rsp]
+	mov	edi,r11d
+	xor	r12d,r9d
+	vpxor	xmm4,xmm4,xmm5
+	shrd	r14d,r14d,11
+	xor	edi,eax
+	add	r10d,r12d
+	vpsrlq	xmm7,xmm7,17
+	shrd	r13d,r13d,6
+	and	r15d,edi
+	xor	r14d,r11d
+	vpaddd	xmm2,xmm2,xmm4
+	add	r10d,r13d
+	xor	r15d,eax
+	shrd	r14d,r14d,2
+	vpxor	xmm6,xmm6,xmm7
+	add	ecx,r10d
+	add	r10d,r15d
+	mov	r13d,ecx
+	vpsrlq	xmm7,xmm7,2
+	add	r14d,r10d
+	shrd	r13d,r13d,14
+	mov	r10d,r14d
+	vpxor	xmm6,xmm6,xmm7
+	mov	r12d,edx
+	shrd	r14d,r14d,9
+	xor	r13d,ecx
+	vpshufb	xmm6,xmm6,xmm8
+	xor	r12d,r8d
+	shrd	r13d,r13d,5
+	xor	r14d,r10d
+	vpaddd	xmm2,xmm2,xmm6
+	and	r12d,ecx
+	xor	r13d,ecx
+	add	r9d,DWORD[40+rsp]
+	vpshufd	xmm7,xmm2,80
+	mov	r15d,r10d
+	xor	r12d,r8d
+	shrd	r14d,r14d,11
+	vpsrld	xmm6,xmm7,10
+	xor	r15d,r11d
+	add	r9d,r12d
+	shrd	r13d,r13d,6
+	vpsrlq	xmm7,xmm7,17
+	and	edi,r15d
+	xor	r14d,r10d
+	add	r9d,r13d
+	vpxor	xmm6,xmm6,xmm7
+	xor	edi,r11d
+	shrd	r14d,r14d,2
+	add	ebx,r9d
+	vpsrlq	xmm7,xmm7,2
+	add	r9d,edi
+	mov	r13d,ebx
+	add	r14d,r9d
+	vpxor	xmm6,xmm6,xmm7
+	shrd	r13d,r13d,14
+	mov	r9d,r14d
+	mov	r12d,ecx
+	vpshufb	xmm6,xmm6,xmm9
+	shrd	r14d,r14d,9
+	xor	r13d,ebx
+	xor	r12d,edx
+	vpaddd	xmm2,xmm2,xmm6
+	shrd	r13d,r13d,5
+	xor	r14d,r9d
+	and	r12d,ebx
+	vpaddd	xmm6,xmm2,XMMWORD[64+rbp]
+	xor	r13d,ebx
+	add	r8d,DWORD[44+rsp]
+	mov	edi,r9d
+	xor	r12d,edx
+	shrd	r14d,r14d,11
+	xor	edi,r10d
+	add	r8d,r12d
+	shrd	r13d,r13d,6
+	and	r15d,edi
+	xor	r14d,r9d
+	add	r8d,r13d
+	xor	r15d,r10d
+	shrd	r14d,r14d,2
+	add	eax,r8d
+	add	r8d,r15d
+	mov	r13d,eax
+	add	r14d,r8d
+	vmovdqa	XMMWORD[32+rsp],xmm6
+	vpalignr	xmm4,xmm0,xmm3,4
+	shrd	r13d,r13d,14
+	mov	r8d,r14d
+	mov	r12d,ebx
+	vpalignr	xmm7,xmm2,xmm1,4
+	shrd	r14d,r14d,9
+	xor	r13d,eax
+	xor	r12d,ecx
+	vpsrld	xmm6,xmm4,7
+	shrd	r13d,r13d,5
+	xor	r14d,r8d
+	and	r12d,eax
+	vpaddd	xmm3,xmm3,xmm7
+	xor	r13d,eax
+	add	edx,DWORD[48+rsp]
+	mov	r15d,r8d
+	vpsrld	xmm7,xmm4,3
+	xor	r12d,ecx
+	shrd	r14d,r14d,11
+	xor	r15d,r9d
+	vpslld	xmm5,xmm4,14
+	add	edx,r12d
+	shrd	r13d,r13d,6
+	and	edi,r15d
+	vpxor	xmm4,xmm7,xmm6
+	xor	r14d,r8d
+	add	edx,r13d
+	xor	edi,r9d
+	vpshufd	xmm7,xmm2,250
+	shrd	r14d,r14d,2
+	add	r11d,edx
+	add	edx,edi
+	vpsrld	xmm6,xmm6,11
+	mov	r13d,r11d
+	add	r14d,edx
+	shrd	r13d,r13d,14
+	vpxor	xmm4,xmm4,xmm5
+	mov	edx,r14d
+	mov	r12d,eax
+	shrd	r14d,r14d,9
+	vpslld	xmm5,xmm5,11
+	xor	r13d,r11d
+	xor	r12d,ebx
+	shrd	r13d,r13d,5
+	vpxor	xmm4,xmm4,xmm6
+	xor	r14d,edx
+	and	r12d,r11d
+	xor	r13d,r11d
+	vpsrld	xmm6,xmm7,10
+	add	ecx,DWORD[52+rsp]
+	mov	edi,edx
+	xor	r12d,ebx
+	vpxor	xmm4,xmm4,xmm5
+	shrd	r14d,r14d,11
+	xor	edi,r8d
+	add	ecx,r12d
+	vpsrlq	xmm7,xmm7,17
+	shrd	r13d,r13d,6
+	and	r15d,edi
+	xor	r14d,edx
+	vpaddd	xmm3,xmm3,xmm4
+	add	ecx,r13d
+	xor	r15d,r8d
+	shrd	r14d,r14d,2
+	vpxor	xmm6,xmm6,xmm7
+	add	r10d,ecx
+	add	ecx,r15d
+	mov	r13d,r10d
+	vpsrlq	xmm7,xmm7,2
+	add	r14d,ecx
+	shrd	r13d,r13d,14
+	mov	ecx,r14d
+	vpxor	xmm6,xmm6,xmm7
+	mov	r12d,r11d
+	shrd	r14d,r14d,9
+	xor	r13d,r10d
+	vpshufb	xmm6,xmm6,xmm8
+	xor	r12d,eax
+	shrd	r13d,r13d,5
+	xor	r14d,ecx
+	vpaddd	xmm3,xmm3,xmm6
+	and	r12d,r10d
+	xor	r13d,r10d
+	add	ebx,DWORD[56+rsp]
+	vpshufd	xmm7,xmm3,80
+	mov	r15d,ecx
+	xor	r12d,eax
+	shrd	r14d,r14d,11
+	vpsrld	xmm6,xmm7,10
+	xor	r15d,edx
+	add	ebx,r12d
+	shrd	r13d,r13d,6
+	vpsrlq	xmm7,xmm7,17
+	and	edi,r15d
+	xor	r14d,ecx
+	add	ebx,r13d
+	vpxor	xmm6,xmm6,xmm7
+	xor	edi,edx
+	shrd	r14d,r14d,2
+	add	r9d,ebx
+	vpsrlq	xmm7,xmm7,2
+	add	ebx,edi
+	mov	r13d,r9d
+	add	r14d,ebx
+	vpxor	xmm6,xmm6,xmm7
+	shrd	r13d,r13d,14
+	mov	ebx,r14d
+	mov	r12d,r10d
+	vpshufb	xmm6,xmm6,xmm9
+	shrd	r14d,r14d,9
+	xor	r13d,r9d
+	xor	r12d,r11d
+	vpaddd	xmm3,xmm3,xmm6
+	shrd	r13d,r13d,5
+	xor	r14d,ebx
+	and	r12d,r9d
+	vpaddd	xmm6,xmm3,XMMWORD[96+rbp]
+	xor	r13d,r9d
+	add	eax,DWORD[60+rsp]
+	mov	edi,ebx
+	xor	r12d,r11d
+	shrd	r14d,r14d,11
+	xor	edi,ecx
+	add	eax,r12d
+	shrd	r13d,r13d,6
+	and	r15d,edi
+	xor	r14d,ebx
+	add	eax,r13d
+	xor	r15d,ecx
+	shrd	r14d,r14d,2
+	add	r8d,eax
+	add	eax,r15d
+	mov	r13d,r8d
+	add	r14d,eax
+	vmovdqa	XMMWORD[48+rsp],xmm6
+	cmp	BYTE[131+rbp],0
+	jne	NEAR $L$avx_00_47
+	shrd	r13d,r13d,14
+	mov	eax,r14d
+	mov	r12d,r9d
+	shrd	r14d,r14d,9
+	xor	r13d,r8d
+	xor	r12d,r10d
+	shrd	r13d,r13d,5
+	xor	r14d,eax
+	and	r12d,r8d
+	xor	r13d,r8d
+	add	r11d,DWORD[rsp]
+	mov	r15d,eax
+	xor	r12d,r10d
+	shrd	r14d,r14d,11
+	xor	r15d,ebx
+	add	r11d,r12d
+	shrd	r13d,r13d,6
+	and	edi,r15d
+	xor	r14d,eax
+	add	r11d,r13d
+	xor	edi,ebx
+	shrd	r14d,r14d,2
+	add	edx,r11d
+	add	r11d,edi
+	mov	r13d,edx
+	add	r14d,r11d
+	shrd	r13d,r13d,14
+	mov	r11d,r14d
+	mov	r12d,r8d
+	shrd	r14d,r14d,9
+	xor	r13d,edx
+	xor	r12d,r9d
+	shrd	r13d,r13d,5
+	xor	r14d,r11d
+	and	r12d,edx
+	xor	r13d,edx
+	add	r10d,DWORD[4+rsp]
+	mov	edi,r11d
+	xor	r12d,r9d
+	shrd	r14d,r14d,11
+	xor	edi,eax
+	add	r10d,r12d
+	shrd	r13d,r13d,6
+	and	r15d,edi
+	xor	r14d,r11d
+	add	r10d,r13d
+	xor	r15d,eax
+	shrd	r14d,r14d,2
+	add	ecx,r10d
+	add	r10d,r15d
+	mov	r13d,ecx
+	add	r14d,r10d
+	shrd	r13d,r13d,14
+	mov	r10d,r14d
+	mov	r12d,edx
+	shrd	r14d,r14d,9
+	xor	r13d,ecx
+	xor	r12d,r8d
+	shrd	r13d,r13d,5
+	xor	r14d,r10d
+	and	r12d,ecx
+	xor	r13d,ecx
+	add	r9d,DWORD[8+rsp]
+	mov	r15d,r10d
+	xor	r12d,r8d
+	shrd	r14d,r14d,11
+	xor	r15d,r11d
+	add	r9d,r12d
+	shrd	r13d,r13d,6
+	and	edi,r15d
+	xor	r14d,r10d
+	add	r9d,r13d
+	xor	edi,r11d
+	shrd	r14d,r14d,2
+	add	ebx,r9d
+	add	r9d,edi
+	mov	r13d,ebx
+	add	r14d,r9d
+	shrd	r13d,r13d,14
+	mov	r9d,r14d
+	mov	r12d,ecx
+	shrd	r14d,r14d,9
+	xor	r13d,ebx
+	xor	r12d,edx
+	shrd	r13d,r13d,5
+	xor	r14d,r9d
+	and	r12d,ebx
+	xor	r13d,ebx
+	add	r8d,DWORD[12+rsp]
+	mov	edi,r9d
+	xor	r12d,edx
+	shrd	r14d,r14d,11
+	xor	edi,r10d
+	add	r8d,r12d
+	shrd	r13d,r13d,6
+	and	r15d,edi
+	xor	r14d,r9d
+	add	r8d,r13d
+	xor	r15d,r10d
+	shrd	r14d,r14d,2
+	add	eax,r8d
+	add	r8d,r15d
+	mov	r13d,eax
+	add	r14d,r8d
+	shrd	r13d,r13d,14
+	mov	r8d,r14d
+	mov	r12d,ebx
+	shrd	r14d,r14d,9
+	xor	r13d,eax
+	xor	r12d,ecx
+	shrd	r13d,r13d,5
+	xor	r14d,r8d
+	and	r12d,eax
+	xor	r13d,eax
+	add	edx,DWORD[16+rsp]
+	mov	r15d,r8d
+	xor	r12d,ecx
+	shrd	r14d,r14d,11
+	xor	r15d,r9d
+	add	edx,r12d
+	shrd	r13d,r13d,6
+	and	edi,r15d
+	xor	r14d,r8d
+	add	edx,r13d
+	xor	edi,r9d
+	shrd	r14d,r14d,2
+	add	r11d,edx
+	add	edx,edi
+	mov	r13d,r11d
+	add	r14d,edx
+	shrd	r13d,r13d,14
+	mov	edx,r14d
+	mov	r12d,eax
+	shrd	r14d,r14d,9
+	xor	r13d,r11d
+	xor	r12d,ebx
+	shrd	r13d,r13d,5
+	xor	r14d,edx
+	and	r12d,r11d
+	xor	r13d,r11d
+	add	ecx,DWORD[20+rsp]
+	mov	edi,edx
+	xor	r12d,ebx
+	shrd	r14d,r14d,11
+	xor	edi,r8d
+	add	ecx,r12d
+	shrd	r13d,r13d,6
+	and	r15d,edi
+	xor	r14d,edx
+	add	ecx,r13d
+	xor	r15d,r8d
+	shrd	r14d,r14d,2
+	add	r10d,ecx
+	add	ecx,r15d
+	mov	r13d,r10d
+	add	r14d,ecx
+	shrd	r13d,r13d,14
+	mov	ecx,r14d
+	mov	r12d,r11d
+	shrd	r14d,r14d,9
+	xor	r13d,r10d
+	xor	r12d,eax
+	shrd	r13d,r13d,5
+	xor	r14d,ecx
+	and	r12d,r10d
+	xor	r13d,r10d
+	add	ebx,DWORD[24+rsp]
+	mov	r15d,ecx
+	xor	r12d,eax
+	shrd	r14d,r14d,11
+	xor	r15d,edx
+	add	ebx,r12d
+	shrd	r13d,r13d,6
+	and	edi,r15d
+	xor	r14d,ecx
+	add	ebx,r13d
+	xor	edi,edx
+	shrd	r14d,r14d,2
+	add	r9d,ebx
+	add	ebx,edi
+	mov	r13d,r9d
+	add	r14d,ebx
+	shrd	r13d,r13d,14
+	mov	ebx,r14d
+	mov	r12d,r10d
+	shrd	r14d,r14d,9
+	xor	r13d,r9d
+	xor	r12d,r11d
+	shrd	r13d,r13d,5
+	xor	r14d,ebx
+	and	r12d,r9d
+	xor	r13d,r9d
+	add	eax,DWORD[28+rsp]
+	mov	edi,ebx
+	xor	r12d,r11d
+	shrd	r14d,r14d,11
+	xor	edi,ecx
+	add	eax,r12d
+	shrd	r13d,r13d,6
+	and	r15d,edi
+	xor	r14d,ebx
+	add	eax,r13d
+	xor	r15d,ecx
+	shrd	r14d,r14d,2
+	add	r8d,eax
+	add	eax,r15d
+	mov	r13d,r8d
+	add	r14d,eax
+	shrd	r13d,r13d,14
+	mov	eax,r14d
+	mov	r12d,r9d
+	shrd	r14d,r14d,9
+	xor	r13d,r8d
+	xor	r12d,r10d
+	shrd	r13d,r13d,5
+	xor	r14d,eax
+	and	r12d,r8d
+	xor	r13d,r8d
+	add	r11d,DWORD[32+rsp]
+	mov	r15d,eax
+	xor	r12d,r10d
+	shrd	r14d,r14d,11
+	xor	r15d,ebx
+	add	r11d,r12d
+	shrd	r13d,r13d,6
+	and	edi,r15d
+	xor	r14d,eax
+	add	r11d,r13d
+	xor	edi,ebx
+	shrd	r14d,r14d,2
+	add	edx,r11d
+	add	r11d,edi
+	mov	r13d,edx
+	add	r14d,r11d
+	shrd	r13d,r13d,14
+	mov	r11d,r14d
+	mov	r12d,r8d
+	shrd	r14d,r14d,9
+	xor	r13d,edx
+	xor	r12d,r9d
+	shrd	r13d,r13d,5
+	xor	r14d,r11d
+	and	r12d,edx
+	xor	r13d,edx
+	add	r10d,DWORD[36+rsp]
+	mov	edi,r11d
+	xor	r12d,r9d
+	shrd	r14d,r14d,11
+	xor	edi,eax
+	add	r10d,r12d
+	shrd	r13d,r13d,6
+	and	r15d,edi
+	xor	r14d,r11d
+	add	r10d,r13d
+	xor	r15d,eax
+	shrd	r14d,r14d,2
+	add	ecx,r10d
+	add	r10d,r15d
+	mov	r13d,ecx
+	add	r14d,r10d
+	shrd	r13d,r13d,14
+	mov	r10d,r14d
+	mov	r12d,edx
+	shrd	r14d,r14d,9
+	xor	r13d,ecx
+	xor	r12d,r8d
+	shrd	r13d,r13d,5
+	xor	r14d,r10d
+	and	r12d,ecx
+	xor	r13d,ecx
+	add	r9d,DWORD[40+rsp]
+	mov	r15d,r10d
+	xor	r12d,r8d
+	shrd	r14d,r14d,11
+	xor	r15d,r11d
+	add	r9d,r12d
+	shrd	r13d,r13d,6
+	and	edi,r15d
+	xor	r14d,r10d
+	add	r9d,r13d
+	xor	edi,r11d
+	shrd	r14d,r14d,2
+	add	ebx,r9d
+	add	r9d,edi
+	mov	r13d,ebx
+	add	r14d,r9d
+	shrd	r13d,r13d,14
+	mov	r9d,r14d
+	mov	r12d,ecx
+	shrd	r14d,r14d,9
+	xor	r13d,ebx
+	xor	r12d,edx
+	shrd	r13d,r13d,5
+	xor	r14d,r9d
+	and	r12d,ebx
+	xor	r13d,ebx
+	add	r8d,DWORD[44+rsp]
+	mov	edi,r9d
+	xor	r12d,edx
+	shrd	r14d,r14d,11
+	xor	edi,r10d
+	add	r8d,r12d
+	shrd	r13d,r13d,6
+	and	r15d,edi
+	xor	r14d,r9d
+	add	r8d,r13d
+	xor	r15d,r10d
+	shrd	r14d,r14d,2
+	add	eax,r8d
+	add	r8d,r15d
+	mov	r13d,eax
+	add	r14d,r8d
+	shrd	r13d,r13d,14
+	mov	r8d,r14d
+	mov	r12d,ebx
+	shrd	r14d,r14d,9
+	xor	r13d,eax
+	xor	r12d,ecx
+	shrd	r13d,r13d,5
+	xor	r14d,r8d
+	and	r12d,eax
+	xor	r13d,eax
+	add	edx,DWORD[48+rsp]
+	mov	r15d,r8d
+	xor	r12d,ecx
+	shrd	r14d,r14d,11
+	xor	r15d,r9d
+	add	edx,r12d
+	shrd	r13d,r13d,6
+	and	edi,r15d
+	xor	r14d,r8d
+	add	edx,r13d
+	xor	edi,r9d
+	shrd	r14d,r14d,2
+	add	r11d,edx
+	add	edx,edi
+	mov	r13d,r11d
+	add	r14d,edx
+	shrd	r13d,r13d,14
+	mov	edx,r14d
+	mov	r12d,eax
+	shrd	r14d,r14d,9
+	xor	r13d,r11d
+	xor	r12d,ebx
+	shrd	r13d,r13d,5
+	xor	r14d,edx
+	and	r12d,r11d
+	xor	r13d,r11d
+	add	ecx,DWORD[52+rsp]
+	mov	edi,edx
+	xor	r12d,ebx
+	shrd	r14d,r14d,11
+	xor	edi,r8d
+	add	ecx,r12d
+	shrd	r13d,r13d,6
+	and	r15d,edi
+	xor	r14d,edx
+	add	ecx,r13d
+	xor	r15d,r8d
+	shrd	r14d,r14d,2
+	add	r10d,ecx
+	add	ecx,r15d
+	mov	r13d,r10d
+	add	r14d,ecx
+	shrd	r13d,r13d,14
+	mov	ecx,r14d
+	mov	r12d,r11d
+	shrd	r14d,r14d,9
+	xor	r13d,r10d
+	xor	r12d,eax
+	shrd	r13d,r13d,5
+	xor	r14d,ecx
+	and	r12d,r10d
+	xor	r13d,r10d
+	add	ebx,DWORD[56+rsp]
+	mov	r15d,ecx
+	xor	r12d,eax
+	shrd	r14d,r14d,11
+	xor	r15d,edx
+	add	ebx,r12d
+	shrd	r13d,r13d,6
+	and	edi,r15d
+	xor	r14d,ecx
+	add	ebx,r13d
+	xor	edi,edx
+	shrd	r14d,r14d,2
+	add	r9d,ebx
+	add	ebx,edi
+	mov	r13d,r9d
+	add	r14d,ebx
+	shrd	r13d,r13d,14
+	mov	ebx,r14d
+	mov	r12d,r10d
+	shrd	r14d,r14d,9
+	xor	r13d,r9d
+	xor	r12d,r11d
+	shrd	r13d,r13d,5
+	xor	r14d,ebx
+	and	r12d,r9d
+	xor	r13d,r9d
+	add	eax,DWORD[60+rsp]
+	mov	edi,ebx
+	xor	r12d,r11d
+	shrd	r14d,r14d,11
+	xor	edi,ecx
+	add	eax,r12d
+	shrd	r13d,r13d,6
+	and	r15d,edi
+	xor	r14d,ebx
+	add	eax,r13d
+	xor	r15d,ecx
+	shrd	r14d,r14d,2
+	add	r8d,eax
+	add	eax,r15d
+	mov	r13d,r8d
+	add	r14d,eax
+	mov	rdi,QWORD[((64+0))+rsp]
+	mov	eax,r14d
+
+	add	eax,DWORD[rdi]
+	lea	rsi,[64+rsi]
+	add	ebx,DWORD[4+rdi]
+	add	ecx,DWORD[8+rdi]
+	add	edx,DWORD[12+rdi]
+	add	r8d,DWORD[16+rdi]
+	add	r9d,DWORD[20+rdi]
+	add	r10d,DWORD[24+rdi]
+	add	r11d,DWORD[28+rdi]
+
+	cmp	rsi,QWORD[((64+16))+rsp]
+
+	mov	DWORD[rdi],eax
+	mov	DWORD[4+rdi],ebx
+	mov	DWORD[8+rdi],ecx
+	mov	DWORD[12+rdi],edx
+	mov	DWORD[16+rdi],r8d
+	mov	DWORD[20+rdi],r9d
+	mov	DWORD[24+rdi],r10d
+	mov	DWORD[28+rdi],r11d
+	jb	NEAR $L$loop_avx
+
+	mov	rsi,QWORD[((64+24))+rsp]
+	vzeroupper
+	movaps	xmm6,XMMWORD[((64+32))+rsp]
+	movaps	xmm7,XMMWORD[((64+48))+rsp]
+	movaps	xmm8,XMMWORD[((64+64))+rsp]
+	movaps	xmm9,XMMWORD[((64+80))+rsp]
+	mov	r15,QWORD[rsi]
+	mov	r14,QWORD[8+rsi]
+	mov	r13,QWORD[16+rsi]
+	mov	r12,QWORD[24+rsi]
+	mov	rbp,QWORD[32+rsi]
+	mov	rbx,QWORD[40+rsi]
+	lea	rsp,[48+rsi]
+$L$epilogue_avx:
+	mov	rdi,QWORD[8+rsp]	;WIN64 epilogue
+	mov	rsi,QWORD[16+rsp]
+	DB	0F3h,0C3h		;repret
+$L$SEH_end_sha256_block_data_order_avx:
 EXTERN	__imp_RtlVirtualUnwind
 
 ALIGN	16
@@ -2982,6 +4063,9 @@ ALIGN	4
 	DD	$L$SEH_begin_sha256_block_data_order_ssse3 wrt ..imagebase
 	DD	$L$SEH_end_sha256_block_data_order_ssse3 wrt ..imagebase
 	DD	$L$SEH_info_sha256_block_data_order_ssse3 wrt ..imagebase
+	DD	$L$SEH_begin_sha256_block_data_order_avx wrt ..imagebase
+	DD	$L$SEH_end_sha256_block_data_order_avx wrt ..imagebase
+	DD	$L$SEH_info_sha256_block_data_order_avx wrt ..imagebase
 section	.xdata rdata align=8
 ALIGN	8
 $L$SEH_info_sha256_block_data_order:
@@ -2992,3 +4076,7 @@ $L$SEH_info_sha256_block_data_order_ssse3:
 DB	9,0,0,0
 	DD	se_handler wrt ..imagebase
 	DD	$L$prologue_ssse3 wrt ..imagebase,$L$epilogue_ssse3 wrt ..imagebase
+$L$SEH_info_sha256_block_data_order_avx:
+DB	9,0,0,0
+	DD	se_handler wrt ..imagebase
+	DD	$L$prologue_avx wrt ..imagebase,$L$epilogue_avx wrt ..imagebase
diff --git a/packager/third_party/boringssl/win-x86_64/crypto/sha/sha512-x86_64.asm b/packager/third_party/boringssl/win-x86_64/crypto/sha/sha512-x86_64.asm
index b76cc0edb9..71449cd24f 100644
--- a/packager/third_party/boringssl/win-x86_64/crypto/sha/sha512-x86_64.asm
+++ b/packager/third_party/boringssl/win-x86_64/crypto/sha/sha512-x86_64.asm
@@ -19,6 +19,17 @@ $L$SEH_begin_sha512_block_data_order:
 	mov	rdx,r8
 
 
+	lea	r11,[OPENSSL_ia32cap_P]
+	mov	r9d,DWORD[r11]
+	mov	r10d,DWORD[4+r11]
+	mov	r11d,DWORD[8+r11]
+	test	r10d,2048
+	jnz	NEAR $L$xop_shortcut
+	and	r9d,1073741824
+	and	r10d,268435968
+	or	r10d,r9d
+	cmp	r10d,1342177792
+	je	NEAR $L$avx_shortcut
 	push	rbx
 	push	rbp
 	push	r12
@@ -1801,6 +1812,2282 @@ DB	110,115,102,111,114,109,32,102,111,114,32,120,56,54,95,54
 DB	52,44,32,67,82,89,80,84,79,71,65,77,83,32,98,121
 DB	32,60,97,112,112,114,111,64,111,112,101,110,115,115,108,46
 DB	111,114,103,62,0
+
+ALIGN	64
+sha512_block_data_order_xop:
+	mov	QWORD[8+rsp],rdi	;WIN64 prologue
+	mov	QWORD[16+rsp],rsi
+	mov	rax,rsp
+$L$SEH_begin_sha512_block_data_order_xop:
+	mov	rdi,rcx
+	mov	rsi,rdx
+	mov	rdx,r8
+
+
+$L$xop_shortcut:
+	push	rbx
+	push	rbp
+	push	r12
+	push	r13
+	push	r14
+	push	r15
+	mov	r11,rsp
+	shl	rdx,4
+	sub	rsp,256
+	lea	rdx,[rdx*8+rsi]
+	and	rsp,-64
+	mov	QWORD[((128+0))+rsp],rdi
+	mov	QWORD[((128+8))+rsp],rsi
+	mov	QWORD[((128+16))+rsp],rdx
+	mov	QWORD[((128+24))+rsp],r11
+	movaps	XMMWORD[(128+32)+rsp],xmm6
+	movaps	XMMWORD[(128+48)+rsp],xmm7
+	movaps	XMMWORD[(128+64)+rsp],xmm8
+	movaps	XMMWORD[(128+80)+rsp],xmm9
+	movaps	XMMWORD[(128+96)+rsp],xmm10
+	movaps	XMMWORD[(128+112)+rsp],xmm11
+$L$prologue_xop:
+
+	vzeroupper
+	mov	rax,QWORD[rdi]
+	mov	rbx,QWORD[8+rdi]
+	mov	rcx,QWORD[16+rdi]
+	mov	rdx,QWORD[24+rdi]
+	mov	r8,QWORD[32+rdi]
+	mov	r9,QWORD[40+rdi]
+	mov	r10,QWORD[48+rdi]
+	mov	r11,QWORD[56+rdi]
+	jmp	NEAR $L$loop_xop
+ALIGN	16
+$L$loop_xop:
+	vmovdqa	xmm11,XMMWORD[((K512+1280))]
+	vmovdqu	xmm0,XMMWORD[rsi]
+	lea	rbp,[((K512+128))]
+	vmovdqu	xmm1,XMMWORD[16+rsi]
+	vmovdqu	xmm2,XMMWORD[32+rsi]
+	vpshufb	xmm0,xmm0,xmm11
+	vmovdqu	xmm3,XMMWORD[48+rsi]
+	vpshufb	xmm1,xmm1,xmm11
+	vmovdqu	xmm4,XMMWORD[64+rsi]
+	vpshufb	xmm2,xmm2,xmm11
+	vmovdqu	xmm5,XMMWORD[80+rsi]
+	vpshufb	xmm3,xmm3,xmm11
+	vmovdqu	xmm6,XMMWORD[96+rsi]
+	vpshufb	xmm4,xmm4,xmm11
+	vmovdqu	xmm7,XMMWORD[112+rsi]
+	vpshufb	xmm5,xmm5,xmm11
+	vpaddq	xmm8,xmm0,XMMWORD[((-128))+rbp]
+	vpshufb	xmm6,xmm6,xmm11
+	vpaddq	xmm9,xmm1,XMMWORD[((-96))+rbp]
+	vpshufb	xmm7,xmm7,xmm11
+	vpaddq	xmm10,xmm2,XMMWORD[((-64))+rbp]
+	vpaddq	xmm11,xmm3,XMMWORD[((-32))+rbp]
+	vmovdqa	XMMWORD[rsp],xmm8
+	vpaddq	xmm8,xmm4,XMMWORD[rbp]
+	vmovdqa	XMMWORD[16+rsp],xmm9
+	vpaddq	xmm9,xmm5,XMMWORD[32+rbp]
+	vmovdqa	XMMWORD[32+rsp],xmm10
+	vpaddq	xmm10,xmm6,XMMWORD[64+rbp]
+	vmovdqa	XMMWORD[48+rsp],xmm11
+	vpaddq	xmm11,xmm7,XMMWORD[96+rbp]
+	vmovdqa	XMMWORD[64+rsp],xmm8
+	mov	r14,rax
+	vmovdqa	XMMWORD[80+rsp],xmm9
+	mov	rdi,rbx
+	vmovdqa	XMMWORD[96+rsp],xmm10
+	xor	rdi,rcx
+	vmovdqa	XMMWORD[112+rsp],xmm11
+	mov	r13,r8
+	jmp	NEAR $L$xop_00_47
+
+ALIGN	16
+$L$xop_00_47:
+	add	rbp,256
+	vpalignr	xmm8,xmm1,xmm0,8
+	ror	r13,23
+	mov	rax,r14
+	vpalignr	xmm11,xmm5,xmm4,8
+	mov	r12,r9
+	ror	r14,5
+DB	143,72,120,195,200,56
+	xor	r13,r8
+	xor	r12,r10
+	vpsrlq	xmm8,xmm8,7
+	ror	r13,4
+	xor	r14,rax
+	vpaddq	xmm0,xmm0,xmm11
+	and	r12,r8
+	xor	r13,r8
+	add	r11,QWORD[rsp]
+	mov	r15,rax
+DB	143,72,120,195,209,7
+	xor	r12,r10
+	ror	r14,6
+	vpxor	xmm8,xmm8,xmm9
+	xor	r15,rbx
+	add	r11,r12
+	ror	r13,14
+	and	rdi,r15
+DB	143,104,120,195,223,3
+	xor	r14,rax
+	add	r11,r13
+	vpxor	xmm8,xmm8,xmm10
+	xor	rdi,rbx
+	ror	r14,28
+	vpsrlq	xmm10,xmm7,6
+	add	rdx,r11
+	add	r11,rdi
+	vpaddq	xmm0,xmm0,xmm8
+	mov	r13,rdx
+	add	r14,r11
+DB	143,72,120,195,203,42
+	ror	r13,23
+	mov	r11,r14
+	vpxor	xmm11,xmm11,xmm10
+	mov	r12,r8
+	ror	r14,5
+	xor	r13,rdx
+	xor	r12,r9
+	vpxor	xmm11,xmm11,xmm9
+	ror	r13,4
+	xor	r14,r11
+	and	r12,rdx
+	xor	r13,rdx
+	vpaddq	xmm0,xmm0,xmm11
+	add	r10,QWORD[8+rsp]
+	mov	rdi,r11
+	xor	r12,r9
+	ror	r14,6
+	vpaddq	xmm10,xmm0,XMMWORD[((-128))+rbp]
+	xor	rdi,rax
+	add	r10,r12
+	ror	r13,14
+	and	r15,rdi
+	xor	r14,r11
+	add	r10,r13
+	xor	r15,rax
+	ror	r14,28
+	add	rcx,r10
+	add	r10,r15
+	mov	r13,rcx
+	add	r14,r10
+	vmovdqa	XMMWORD[rsp],xmm10
+	vpalignr	xmm8,xmm2,xmm1,8
+	ror	r13,23
+	mov	r10,r14
+	vpalignr	xmm11,xmm6,xmm5,8
+	mov	r12,rdx
+	ror	r14,5
+DB	143,72,120,195,200,56
+	xor	r13,rcx
+	xor	r12,r8
+	vpsrlq	xmm8,xmm8,7
+	ror	r13,4
+	xor	r14,r10
+	vpaddq	xmm1,xmm1,xmm11
+	and	r12,rcx
+	xor	r13,rcx
+	add	r9,QWORD[16+rsp]
+	mov	r15,r10
+DB	143,72,120,195,209,7
+	xor	r12,r8
+	ror	r14,6
+	vpxor	xmm8,xmm8,xmm9
+	xor	r15,r11
+	add	r9,r12
+	ror	r13,14
+	and	rdi,r15
+DB	143,104,120,195,216,3
+	xor	r14,r10
+	add	r9,r13
+	vpxor	xmm8,xmm8,xmm10
+	xor	rdi,r11
+	ror	r14,28
+	vpsrlq	xmm10,xmm0,6
+	add	rbx,r9
+	add	r9,rdi
+	vpaddq	xmm1,xmm1,xmm8
+	mov	r13,rbx
+	add	r14,r9
+DB	143,72,120,195,203,42
+	ror	r13,23
+	mov	r9,r14
+	vpxor	xmm11,xmm11,xmm10
+	mov	r12,rcx
+	ror	r14,5
+	xor	r13,rbx
+	xor	r12,rdx
+	vpxor	xmm11,xmm11,xmm9
+	ror	r13,4
+	xor	r14,r9
+	and	r12,rbx
+	xor	r13,rbx
+	vpaddq	xmm1,xmm1,xmm11
+	add	r8,QWORD[24+rsp]
+	mov	rdi,r9
+	xor	r12,rdx
+	ror	r14,6
+	vpaddq	xmm10,xmm1,XMMWORD[((-96))+rbp]
+	xor	rdi,r10
+	add	r8,r12
+	ror	r13,14
+	and	r15,rdi
+	xor	r14,r9
+	add	r8,r13
+	xor	r15,r10
+	ror	r14,28
+	add	rax,r8
+	add	r8,r15
+	mov	r13,rax
+	add	r14,r8
+	vmovdqa	XMMWORD[16+rsp],xmm10
+	vpalignr	xmm8,xmm3,xmm2,8
+	ror	r13,23
+	mov	r8,r14
+	vpalignr	xmm11,xmm7,xmm6,8
+	mov	r12,rbx
+	ror	r14,5
+DB	143,72,120,195,200,56
+	xor	r13,rax
+	xor	r12,rcx
+	vpsrlq	xmm8,xmm8,7
+	ror	r13,4
+	xor	r14,r8
+	vpaddq	xmm2,xmm2,xmm11
+	and	r12,rax
+	xor	r13,rax
+	add	rdx,QWORD[32+rsp]
+	mov	r15,r8
+DB	143,72,120,195,209,7
+	xor	r12,rcx
+	ror	r14,6
+	vpxor	xmm8,xmm8,xmm9
+	xor	r15,r9
+	add	rdx,r12
+	ror	r13,14
+	and	rdi,r15
+DB	143,104,120,195,217,3
+	xor	r14,r8
+	add	rdx,r13
+	vpxor	xmm8,xmm8,xmm10
+	xor	rdi,r9
+	ror	r14,28
+	vpsrlq	xmm10,xmm1,6
+	add	r11,rdx
+	add	rdx,rdi
+	vpaddq	xmm2,xmm2,xmm8
+	mov	r13,r11
+	add	r14,rdx
+DB	143,72,120,195,203,42
+	ror	r13,23
+	mov	rdx,r14
+	vpxor	xmm11,xmm11,xmm10
+	mov	r12,rax
+	ror	r14,5
+	xor	r13,r11
+	xor	r12,rbx
+	vpxor	xmm11,xmm11,xmm9
+	ror	r13,4
+	xor	r14,rdx
+	and	r12,r11
+	xor	r13,r11
+	vpaddq	xmm2,xmm2,xmm11
+	add	rcx,QWORD[40+rsp]
+	mov	rdi,rdx
+	xor	r12,rbx
+	ror	r14,6
+	vpaddq	xmm10,xmm2,XMMWORD[((-64))+rbp]
+	xor	rdi,r8
+	add	rcx,r12
+	ror	r13,14
+	and	r15,rdi
+	xor	r14,rdx
+	add	rcx,r13
+	xor	r15,r8
+	ror	r14,28
+	add	r10,rcx
+	add	rcx,r15
+	mov	r13,r10
+	add	r14,rcx
+	vmovdqa	XMMWORD[32+rsp],xmm10
+	vpalignr	xmm8,xmm4,xmm3,8
+	ror	r13,23
+	mov	rcx,r14
+	vpalignr	xmm11,xmm0,xmm7,8
+	mov	r12,r11
+	ror	r14,5
+DB	143,72,120,195,200,56
+	xor	r13,r10
+	xor	r12,rax
+	vpsrlq	xmm8,xmm8,7
+	ror	r13,4
+	xor	r14,rcx
+	vpaddq	xmm3,xmm3,xmm11
+	and	r12,r10
+	xor	r13,r10
+	add	rbx,QWORD[48+rsp]
+	mov	r15,rcx
+DB	143,72,120,195,209,7
+	xor	r12,rax
+	ror	r14,6
+	vpxor	xmm8,xmm8,xmm9
+	xor	r15,rdx
+	add	rbx,r12
+	ror	r13,14
+	and	rdi,r15
+DB	143,104,120,195,218,3
+	xor	r14,rcx
+	add	rbx,r13
+	vpxor	xmm8,xmm8,xmm10
+	xor	rdi,rdx
+	ror	r14,28
+	vpsrlq	xmm10,xmm2,6
+	add	r9,rbx
+	add	rbx,rdi
+	vpaddq	xmm3,xmm3,xmm8
+	mov	r13,r9
+	add	r14,rbx
+DB	143,72,120,195,203,42
+	ror	r13,23
+	mov	rbx,r14
+	vpxor	xmm11,xmm11,xmm10
+	mov	r12,r10
+	ror	r14,5
+	xor	r13,r9
+	xor	r12,r11
+	vpxor	xmm11,xmm11,xmm9
+	ror	r13,4
+	xor	r14,rbx
+	and	r12,r9
+	xor	r13,r9
+	vpaddq	xmm3,xmm3,xmm11
+	add	rax,QWORD[56+rsp]
+	mov	rdi,rbx
+	xor	r12,r11
+	ror	r14,6
+	vpaddq	xmm10,xmm3,XMMWORD[((-32))+rbp]
+	xor	rdi,rcx
+	add	rax,r12
+	ror	r13,14
+	and	r15,rdi
+	xor	r14,rbx
+	add	rax,r13
+	xor	r15,rcx
+	ror	r14,28
+	add	r8,rax
+	add	rax,r15
+	mov	r13,r8
+	add	r14,rax
+	vmovdqa	XMMWORD[48+rsp],xmm10
+	vpalignr	xmm8,xmm5,xmm4,8
+	ror	r13,23
+	mov	rax,r14
+	vpalignr	xmm11,xmm1,xmm0,8
+	mov	r12,r9
+	ror	r14,5
+DB	143,72,120,195,200,56
+	xor	r13,r8
+	xor	r12,r10
+	vpsrlq	xmm8,xmm8,7
+	ror	r13,4
+	xor	r14,rax
+	vpaddq	xmm4,xmm4,xmm11
+	and	r12,r8
+	xor	r13,r8
+	add	r11,QWORD[64+rsp]
+	mov	r15,rax
+DB	143,72,120,195,209,7
+	xor	r12,r10
+	ror	r14,6
+	vpxor	xmm8,xmm8,xmm9
+	xor	r15,rbx
+	add	r11,r12
+	ror	r13,14
+	and	rdi,r15
+DB	143,104,120,195,219,3
+	xor	r14,rax
+	add	r11,r13
+	vpxor	xmm8,xmm8,xmm10
+	xor	rdi,rbx
+	ror	r14,28
+	vpsrlq	xmm10,xmm3,6
+	add	rdx,r11
+	add	r11,rdi
+	vpaddq	xmm4,xmm4,xmm8
+	mov	r13,rdx
+	add	r14,r11
+DB	143,72,120,195,203,42
+	ror	r13,23
+	mov	r11,r14
+	vpxor	xmm11,xmm11,xmm10
+	mov	r12,r8
+	ror	r14,5
+	xor	r13,rdx
+	xor	r12,r9
+	vpxor	xmm11,xmm11,xmm9
+	ror	r13,4
+	xor	r14,r11
+	and	r12,rdx
+	xor	r13,rdx
+	vpaddq	xmm4,xmm4,xmm11
+	add	r10,QWORD[72+rsp]
+	mov	rdi,r11
+	xor	r12,r9
+	ror	r14,6
+	vpaddq	xmm10,xmm4,XMMWORD[rbp]
+	xor	rdi,rax
+	add	r10,r12
+	ror	r13,14
+	and	r15,rdi
+	xor	r14,r11
+	add	r10,r13
+	xor	r15,rax
+	ror	r14,28
+	add	rcx,r10
+	add	r10,r15
+	mov	r13,rcx
+	add	r14,r10
+	vmovdqa	XMMWORD[64+rsp],xmm10
+	vpalignr	xmm8,xmm6,xmm5,8
+	ror	r13,23
+	mov	r10,r14
+	vpalignr	xmm11,xmm2,xmm1,8
+	mov	r12,rdx
+	ror	r14,5
+DB	143,72,120,195,200,56
+	xor	r13,rcx
+	xor	r12,r8
+	vpsrlq	xmm8,xmm8,7
+	ror	r13,4
+	xor	r14,r10
+	vpaddq	xmm5,xmm5,xmm11
+	and	r12,rcx
+	xor	r13,rcx
+	add	r9,QWORD[80+rsp]
+	mov	r15,r10
+DB	143,72,120,195,209,7
+	xor	r12,r8
+	ror	r14,6
+	vpxor	xmm8,xmm8,xmm9
+	xor	r15,r11
+	add	r9,r12
+	ror	r13,14
+	and	rdi,r15
+DB	143,104,120,195,220,3
+	xor	r14,r10
+	add	r9,r13
+	vpxor	xmm8,xmm8,xmm10
+	xor	rdi,r11
+	ror	r14,28
+	vpsrlq	xmm10,xmm4,6
+	add	rbx,r9
+	add	r9,rdi
+	vpaddq	xmm5,xmm5,xmm8
+	mov	r13,rbx
+	add	r14,r9
+DB	143,72,120,195,203,42
+	ror	r13,23
+	mov	r9,r14
+	vpxor	xmm11,xmm11,xmm10
+	mov	r12,rcx
+	ror	r14,5
+	xor	r13,rbx
+	xor	r12,rdx
+	vpxor	xmm11,xmm11,xmm9
+	ror	r13,4
+	xor	r14,r9
+	and	r12,rbx
+	xor	r13,rbx
+	vpaddq	xmm5,xmm5,xmm11
+	add	r8,QWORD[88+rsp]
+	mov	rdi,r9
+	xor	r12,rdx
+	ror	r14,6
+	vpaddq	xmm10,xmm5,XMMWORD[32+rbp]
+	xor	rdi,r10
+	add	r8,r12
+	ror	r13,14
+	and	r15,rdi
+	xor	r14,r9
+	add	r8,r13
+	xor	r15,r10
+	ror	r14,28
+	add	rax,r8
+	add	r8,r15
+	mov	r13,rax
+	add	r14,r8
+	vmovdqa	XMMWORD[80+rsp],xmm10
+	vpalignr	xmm8,xmm7,xmm6,8
+	ror	r13,23
+	mov	r8,r14
+	vpalignr	xmm11,xmm3,xmm2,8
+	mov	r12,rbx
+	ror	r14,5
+DB	143,72,120,195,200,56
+	xor	r13,rax
+	xor	r12,rcx
+	vpsrlq	xmm8,xmm8,7
+	ror	r13,4
+	xor	r14,r8
+	vpaddq	xmm6,xmm6,xmm11
+	and	r12,rax
+	xor	r13,rax
+	add	rdx,QWORD[96+rsp]
+	mov	r15,r8
+DB	143,72,120,195,209,7
+	xor	r12,rcx
+	ror	r14,6
+	vpxor	xmm8,xmm8,xmm9
+	xor	r15,r9
+	add	rdx,r12
+	ror	r13,14
+	and	rdi,r15
+DB	143,104,120,195,221,3
+	xor	r14,r8
+	add	rdx,r13
+	vpxor	xmm8,xmm8,xmm10
+	xor	rdi,r9
+	ror	r14,28
+	vpsrlq	xmm10,xmm5,6
+	add	r11,rdx
+	add	rdx,rdi
+	vpaddq	xmm6,xmm6,xmm8
+	mov	r13,r11
+	add	r14,rdx
+DB	143,72,120,195,203,42
+	ror	r13,23
+	mov	rdx,r14
+	vpxor	xmm11,xmm11,xmm10
+	mov	r12,rax
+	ror	r14,5
+	xor	r13,r11
+	xor	r12,rbx
+	vpxor	xmm11,xmm11,xmm9
+	ror	r13,4
+	xor	r14,rdx
+	and	r12,r11
+	xor	r13,r11
+	vpaddq	xmm6,xmm6,xmm11
+	add	rcx,QWORD[104+rsp]
+	mov	rdi,rdx
+	xor	r12,rbx
+	ror	r14,6
+	vpaddq	xmm10,xmm6,XMMWORD[64+rbp]
+	xor	rdi,r8
+	add	rcx,r12
+	ror	r13,14
+	and	r15,rdi
+	xor	r14,rdx
+	add	rcx,r13
+	xor	r15,r8
+	ror	r14,28
+	add	r10,rcx
+	add	rcx,r15
+	mov	r13,r10
+	add	r14,rcx
+	vmovdqa	XMMWORD[96+rsp],xmm10
+	vpalignr	xmm8,xmm0,xmm7,8
+	ror	r13,23
+	mov	rcx,r14
+	vpalignr	xmm11,xmm4,xmm3,8
+	mov	r12,r11
+	ror	r14,5
+DB	143,72,120,195,200,56
+	xor	r13,r10
+	xor	r12,rax
+	vpsrlq	xmm8,xmm8,7
+	ror	r13,4
+	xor	r14,rcx
+	vpaddq	xmm7,xmm7,xmm11
+	and	r12,r10
+	xor	r13,r10
+	add	rbx,QWORD[112+rsp]
+	mov	r15,rcx
+DB	143,72,120,195,209,7
+	xor	r12,rax
+	ror	r14,6
+	vpxor	xmm8,xmm8,xmm9
+	xor	r15,rdx
+	add	rbx,r12
+	ror	r13,14
+	and	rdi,r15
+DB	143,104,120,195,222,3
+	xor	r14,rcx
+	add	rbx,r13
+	vpxor	xmm8,xmm8,xmm10
+	xor	rdi,rdx
+	ror	r14,28
+	vpsrlq	xmm10,xmm6,6
+	add	r9,rbx
+	add	rbx,rdi
+	vpaddq	xmm7,xmm7,xmm8
+	mov	r13,r9
+	add	r14,rbx
+DB	143,72,120,195,203,42
+	ror	r13,23
+	mov	rbx,r14
+	vpxor	xmm11,xmm11,xmm10
+	mov	r12,r10
+	ror	r14,5
+	xor	r13,r9
+	xor	r12,r11
+	vpxor	xmm11,xmm11,xmm9
+	ror	r13,4
+	xor	r14,rbx
+	and	r12,r9
+	xor	r13,r9
+	vpaddq	xmm7,xmm7,xmm11
+	add	rax,QWORD[120+rsp]
+	mov	rdi,rbx
+	xor	r12,r11
+	ror	r14,6
+	vpaddq	xmm10,xmm7,XMMWORD[96+rbp]
+	xor	rdi,rcx
+	add	rax,r12
+	ror	r13,14
+	and	r15,rdi
+	xor	r14,rbx
+	add	rax,r13
+	xor	r15,rcx
+	ror	r14,28
+	add	r8,rax
+	add	rax,r15
+	mov	r13,r8
+	add	r14,rax
+	vmovdqa	XMMWORD[112+rsp],xmm10
+	cmp	BYTE[135+rbp],0
+	jne	NEAR $L$xop_00_47
+	ror	r13,23
+	mov	rax,r14
+	mov	r12,r9
+	ror	r14,5
+	xor	r13,r8
+	xor	r12,r10
+	ror	r13,4
+	xor	r14,rax
+	and	r12,r8
+	xor	r13,r8
+	add	r11,QWORD[rsp]
+	mov	r15,rax
+	xor	r12,r10
+	ror	r14,6
+	xor	r15,rbx
+	add	r11,r12
+	ror	r13,14
+	and	rdi,r15
+	xor	r14,rax
+	add	r11,r13
+	xor	rdi,rbx
+	ror	r14,28
+	add	rdx,r11
+	add	r11,rdi
+	mov	r13,rdx
+	add	r14,r11
+	ror	r13,23
+	mov	r11,r14
+	mov	r12,r8
+	ror	r14,5
+	xor	r13,rdx
+	xor	r12,r9
+	ror	r13,4
+	xor	r14,r11
+	and	r12,rdx
+	xor	r13,rdx
+	add	r10,QWORD[8+rsp]
+	mov	rdi,r11
+	xor	r12,r9
+	ror	r14,6
+	xor	rdi,rax
+	add	r10,r12
+	ror	r13,14
+	and	r15,rdi
+	xor	r14,r11
+	add	r10,r13
+	xor	r15,rax
+	ror	r14,28
+	add	rcx,r10
+	add	r10,r15
+	mov	r13,rcx
+	add	r14,r10
+	ror	r13,23
+	mov	r10,r14
+	mov	r12,rdx
+	ror	r14,5
+	xor	r13,rcx
+	xor	r12,r8
+	ror	r13,4
+	xor	r14,r10
+	and	r12,rcx
+	xor	r13,rcx
+	add	r9,QWORD[16+rsp]
+	mov	r15,r10
+	xor	r12,r8
+	ror	r14,6
+	xor	r15,r11
+	add	r9,r12
+	ror	r13,14
+	and	rdi,r15
+	xor	r14,r10
+	add	r9,r13
+	xor	rdi,r11
+	ror	r14,28
+	add	rbx,r9
+	add	r9,rdi
+	mov	r13,rbx
+	add	r14,r9
+	ror	r13,23
+	mov	r9,r14
+	mov	r12,rcx
+	ror	r14,5
+	xor	r13,rbx
+	xor	r12,rdx
+	ror	r13,4
+	xor	r14,r9
+	and	r12,rbx
+	xor	r13,rbx
+	add	r8,QWORD[24+rsp]
+	mov	rdi,r9
+	xor	r12,rdx
+	ror	r14,6
+	xor	rdi,r10
+	add	r8,r12
+	ror	r13,14
+	and	r15,rdi
+	xor	r14,r9
+	add	r8,r13
+	xor	r15,r10
+	ror	r14,28
+	add	rax,r8
+	add	r8,r15
+	mov	r13,rax
+	add	r14,r8
+	ror	r13,23
+	mov	r8,r14
+	mov	r12,rbx
+	ror	r14,5
+	xor	r13,rax
+	xor	r12,rcx
+	ror	r13,4
+	xor	r14,r8
+	and	r12,rax
+	xor	r13,rax
+	add	rdx,QWORD[32+rsp]
+	mov	r15,r8
+	xor	r12,rcx
+	ror	r14,6
+	xor	r15,r9
+	add	rdx,r12
+	ror	r13,14
+	and	rdi,r15
+	xor	r14,r8
+	add	rdx,r13
+	xor	rdi,r9
+	ror	r14,28
+	add	r11,rdx
+	add	rdx,rdi
+	mov	r13,r11
+	add	r14,rdx
+	ror	r13,23
+	mov	rdx,r14
+	mov	r12,rax
+	ror	r14,5
+	xor	r13,r11
+	xor	r12,rbx
+	ror	r13,4
+	xor	r14,rdx
+	and	r12,r11
+	xor	r13,r11
+	add	rcx,QWORD[40+rsp]
+	mov	rdi,rdx
+	xor	r12,rbx
+	ror	r14,6
+	xor	rdi,r8
+	add	rcx,r12
+	ror	r13,14
+	and	r15,rdi
+	xor	r14,rdx
+	add	rcx,r13
+	xor	r15,r8
+	ror	r14,28
+	add	r10,rcx
+	add	rcx,r15
+	mov	r13,r10
+	add	r14,rcx
+	ror	r13,23
+	mov	rcx,r14
+	mov	r12,r11
+	ror	r14,5
+	xor	r13,r10
+	xor	r12,rax
+	ror	r13,4
+	xor	r14,rcx
+	and	r12,r10
+	xor	r13,r10
+	add	rbx,QWORD[48+rsp]
+	mov	r15,rcx
+	xor	r12,rax
+	ror	r14,6
+	xor	r15,rdx
+	add	rbx,r12
+	ror	r13,14
+	and	rdi,r15
+	xor	r14,rcx
+	add	rbx,r13
+	xor	rdi,rdx
+	ror	r14,28
+	add	r9,rbx
+	add	rbx,rdi
+	mov	r13,r9
+	add	r14,rbx
+	ror	r13,23
+	mov	rbx,r14
+	mov	r12,r10
+	ror	r14,5
+	xor	r13,r9
+	xor	r12,r11
+	ror	r13,4
+	xor	r14,rbx
+	and	r12,r9
+	xor	r13,r9
+	add	rax,QWORD[56+rsp]
+	mov	rdi,rbx
+	xor	r12,r11
+	ror	r14,6
+	xor	rdi,rcx
+	add	rax,r12
+	ror	r13,14
+	and	r15,rdi
+	xor	r14,rbx
+	add	rax,r13
+	xor	r15,rcx
+	ror	r14,28
+	add	r8,rax
+	add	rax,r15
+	mov	r13,r8
+	add	r14,rax
+	ror	r13,23
+	mov	rax,r14
+	mov	r12,r9
+	ror	r14,5
+	xor	r13,r8
+	xor	r12,r10
+	ror	r13,4
+	xor	r14,rax
+	and	r12,r8
+	xor	r13,r8
+	add	r11,QWORD[64+rsp]
+	mov	r15,rax
+	xor	r12,r10
+	ror	r14,6
+	xor	r15,rbx
+	add	r11,r12
+	ror	r13,14
+	and	rdi,r15
+	xor	r14,rax
+	add	r11,r13
+	xor	rdi,rbx
+	ror	r14,28
+	add	rdx,r11
+	add	r11,rdi
+	mov	r13,rdx
+	add	r14,r11
+	ror	r13,23
+	mov	r11,r14
+	mov	r12,r8
+	ror	r14,5
+	xor	r13,rdx
+	xor	r12,r9
+	ror	r13,4
+	xor	r14,r11
+	and	r12,rdx
+	xor	r13,rdx
+	add	r10,QWORD[72+rsp]
+	mov	rdi,r11
+	xor	r12,r9
+	ror	r14,6
+	xor	rdi,rax
+	add	r10,r12
+	ror	r13,14
+	and	r15,rdi
+	xor	r14,r11
+	add	r10,r13
+	xor	r15,rax
+	ror	r14,28
+	add	rcx,r10
+	add	r10,r15
+	mov	r13,rcx
+	add	r14,r10
+	ror	r13,23
+	mov	r10,r14
+	mov	r12,rdx
+	ror	r14,5
+	xor	r13,rcx
+	xor	r12,r8
+	ror	r13,4
+	xor	r14,r10
+	and	r12,rcx
+	xor	r13,rcx
+	add	r9,QWORD[80+rsp]
+	mov	r15,r10
+	xor	r12,r8
+	ror	r14,6
+	xor	r15,r11
+	add	r9,r12
+	ror	r13,14
+	and	rdi,r15
+	xor	r14,r10
+	add	r9,r13
+	xor	rdi,r11
+	ror	r14,28
+	add	rbx,r9
+	add	r9,rdi
+	mov	r13,rbx
+	add	r14,r9
+	ror	r13,23
+	mov	r9,r14
+	mov	r12,rcx
+	ror	r14,5
+	xor	r13,rbx
+	xor	r12,rdx
+	ror	r13,4
+	xor	r14,r9
+	and	r12,rbx
+	xor	r13,rbx
+	add	r8,QWORD[88+rsp]
+	mov	rdi,r9
+	xor	r12,rdx
+	ror	r14,6
+	xor	rdi,r10
+	add	r8,r12
+	ror	r13,14
+	and	r15,rdi
+	xor	r14,r9
+	add	r8,r13
+	xor	r15,r10
+	ror	r14,28
+	add	rax,r8
+	add	r8,r15
+	mov	r13,rax
+	add	r14,r8
+	ror	r13,23
+	mov	r8,r14
+	mov	r12,rbx
+	ror	r14,5
+	xor	r13,rax
+	xor	r12,rcx
+	ror	r13,4
+	xor	r14,r8
+	and	r12,rax
+	xor	r13,rax
+	add	rdx,QWORD[96+rsp]
+	mov	r15,r8
+	xor	r12,rcx
+	ror	r14,6
+	xor	r15,r9
+	add	rdx,r12
+	ror	r13,14
+	and	rdi,r15
+	xor	r14,r8
+	add	rdx,r13
+	xor	rdi,r9
+	ror	r14,28
+	add	r11,rdx
+	add	rdx,rdi
+	mov	r13,r11
+	add	r14,rdx
+	ror	r13,23
+	mov	rdx,r14
+	mov	r12,rax
+	ror	r14,5
+	xor	r13,r11
+	xor	r12,rbx
+	ror	r13,4
+	xor	r14,rdx
+	and	r12,r11
+	xor	r13,r11
+	add	rcx,QWORD[104+rsp]
+	mov	rdi,rdx
+	xor	r12,rbx
+	ror	r14,6
+	xor	rdi,r8
+	add	rcx,r12
+	ror	r13,14
+	and	r15,rdi
+	xor	r14,rdx
+	add	rcx,r13
+	xor	r15,r8
+	ror	r14,28
+	add	r10,rcx
+	add	rcx,r15
+	mov	r13,r10
+	add	r14,rcx
+	ror	r13,23
+	mov	rcx,r14
+	mov	r12,r11
+	ror	r14,5
+	xor	r13,r10
+	xor	r12,rax
+	ror	r13,4
+	xor	r14,rcx
+	and	r12,r10
+	xor	r13,r10
+	add	rbx,QWORD[112+rsp]
+	mov	r15,rcx
+	xor	r12,rax
+	ror	r14,6
+	xor	r15,rdx
+	add	rbx,r12
+	ror	r13,14
+	and	rdi,r15
+	xor	r14,rcx
+	add	rbx,r13
+	xor	rdi,rdx
+	ror	r14,28
+	add	r9,rbx
+	add	rbx,rdi
+	mov	r13,r9
+	add	r14,rbx
+	ror	r13,23
+	mov	rbx,r14
+	mov	r12,r10
+	ror	r14,5
+	xor	r13,r9
+	xor	r12,r11
+	ror	r13,4
+	xor	r14,rbx
+	and	r12,r9
+	xor	r13,r9
+	add	rax,QWORD[120+rsp]
+	mov	rdi,rbx
+	xor	r12,r11
+	ror	r14,6
+	xor	rdi,rcx
+	add	rax,r12
+	ror	r13,14
+	and	r15,rdi
+	xor	r14,rbx
+	add	rax,r13
+	xor	r15,rcx
+	ror	r14,28
+	add	r8,rax
+	add	rax,r15
+	mov	r13,r8
+	add	r14,rax
+	mov	rdi,QWORD[((128+0))+rsp]
+	mov	rax,r14
+
+	add	rax,QWORD[rdi]
+	lea	rsi,[128+rsi]
+	add	rbx,QWORD[8+rdi]
+	add	rcx,QWORD[16+rdi]
+	add	rdx,QWORD[24+rdi]
+	add	r8,QWORD[32+rdi]
+	add	r9,QWORD[40+rdi]
+	add	r10,QWORD[48+rdi]
+	add	r11,QWORD[56+rdi]
+
+	cmp	rsi,QWORD[((128+16))+rsp]
+
+	mov	QWORD[rdi],rax
+	mov	QWORD[8+rdi],rbx
+	mov	QWORD[16+rdi],rcx
+	mov	QWORD[24+rdi],rdx
+	mov	QWORD[32+rdi],r8
+	mov	QWORD[40+rdi],r9
+	mov	QWORD[48+rdi],r10
+	mov	QWORD[56+rdi],r11
+	jb	NEAR $L$loop_xop
+
+	mov	rsi,QWORD[((128+24))+rsp]
+	vzeroupper
+	movaps	xmm6,XMMWORD[((128+32))+rsp]
+	movaps	xmm7,XMMWORD[((128+48))+rsp]
+	movaps	xmm8,XMMWORD[((128+64))+rsp]
+	movaps	xmm9,XMMWORD[((128+80))+rsp]
+	movaps	xmm10,XMMWORD[((128+96))+rsp]
+	movaps	xmm11,XMMWORD[((128+112))+rsp]
+	mov	r15,QWORD[rsi]
+	mov	r14,QWORD[8+rsi]
+	mov	r13,QWORD[16+rsi]
+	mov	r12,QWORD[24+rsi]
+	mov	rbp,QWORD[32+rsi]
+	mov	rbx,QWORD[40+rsi]
+	lea	rsp,[48+rsi]
+$L$epilogue_xop:
+	mov	rdi,QWORD[8+rsp]	;WIN64 epilogue
+	mov	rsi,QWORD[16+rsp]
+	DB	0F3h,0C3h		;repret
+$L$SEH_end_sha512_block_data_order_xop:
+
+ALIGN	64
+sha512_block_data_order_avx:
+	mov	QWORD[8+rsp],rdi	;WIN64 prologue
+	mov	QWORD[16+rsp],rsi
+	mov	rax,rsp
+$L$SEH_begin_sha512_block_data_order_avx:
+	mov	rdi,rcx
+	mov	rsi,rdx
+	mov	rdx,r8
+
+
+$L$avx_shortcut:
+	push	rbx
+	push	rbp
+	push	r12
+	push	r13
+	push	r14
+	push	r15
+	mov	r11,rsp
+	shl	rdx,4
+	sub	rsp,256
+	lea	rdx,[rdx*8+rsi]
+	and	rsp,-64
+	mov	QWORD[((128+0))+rsp],rdi
+	mov	QWORD[((128+8))+rsp],rsi
+	mov	QWORD[((128+16))+rsp],rdx
+	mov	QWORD[((128+24))+rsp],r11
+	movaps	XMMWORD[(128+32)+rsp],xmm6
+	movaps	XMMWORD[(128+48)+rsp],xmm7
+	movaps	XMMWORD[(128+64)+rsp],xmm8
+	movaps	XMMWORD[(128+80)+rsp],xmm9
+	movaps	XMMWORD[(128+96)+rsp],xmm10
+	movaps	XMMWORD[(128+112)+rsp],xmm11
+$L$prologue_avx:
+
+	vzeroupper
+	mov	rax,QWORD[rdi]
+	mov	rbx,QWORD[8+rdi]
+	mov	rcx,QWORD[16+rdi]
+	mov	rdx,QWORD[24+rdi]
+	mov	r8,QWORD[32+rdi]
+	mov	r9,QWORD[40+rdi]
+	mov	r10,QWORD[48+rdi]
+	mov	r11,QWORD[56+rdi]
+	jmp	NEAR $L$loop_avx
+ALIGN	16
+$L$loop_avx:
+	vmovdqa	xmm11,XMMWORD[((K512+1280))]
+	vmovdqu	xmm0,XMMWORD[rsi]
+	lea	rbp,[((K512+128))]
+	vmovdqu	xmm1,XMMWORD[16+rsi]
+	vmovdqu	xmm2,XMMWORD[32+rsi]
+	vpshufb	xmm0,xmm0,xmm11
+	vmovdqu	xmm3,XMMWORD[48+rsi]
+	vpshufb	xmm1,xmm1,xmm11
+	vmovdqu	xmm4,XMMWORD[64+rsi]
+	vpshufb	xmm2,xmm2,xmm11
+	vmovdqu	xmm5,XMMWORD[80+rsi]
+	vpshufb	xmm3,xmm3,xmm11
+	vmovdqu	xmm6,XMMWORD[96+rsi]
+	vpshufb	xmm4,xmm4,xmm11
+	vmovdqu	xmm7,XMMWORD[112+rsi]
+	vpshufb	xmm5,xmm5,xmm11
+	vpaddq	xmm8,xmm0,XMMWORD[((-128))+rbp]
+	vpshufb	xmm6,xmm6,xmm11
+	vpaddq	xmm9,xmm1,XMMWORD[((-96))+rbp]
+	vpshufb	xmm7,xmm7,xmm11
+	vpaddq	xmm10,xmm2,XMMWORD[((-64))+rbp]
+	vpaddq	xmm11,xmm3,XMMWORD[((-32))+rbp]
+	vmovdqa	XMMWORD[rsp],xmm8
+	vpaddq	xmm8,xmm4,XMMWORD[rbp]
+	vmovdqa	XMMWORD[16+rsp],xmm9
+	vpaddq	xmm9,xmm5,XMMWORD[32+rbp]
+	vmovdqa	XMMWORD[32+rsp],xmm10
+	vpaddq	xmm10,xmm6,XMMWORD[64+rbp]
+	vmovdqa	XMMWORD[48+rsp],xmm11
+	vpaddq	xmm11,xmm7,XMMWORD[96+rbp]
+	vmovdqa	XMMWORD[64+rsp],xmm8
+	mov	r14,rax
+	vmovdqa	XMMWORD[80+rsp],xmm9
+	mov	rdi,rbx
+	vmovdqa	XMMWORD[96+rsp],xmm10
+	xor	rdi,rcx
+	vmovdqa	XMMWORD[112+rsp],xmm11
+	mov	r13,r8
+	jmp	NEAR $L$avx_00_47
+
+ALIGN	16
+$L$avx_00_47:
+	add	rbp,256
+	vpalignr	xmm8,xmm1,xmm0,8
+	shrd	r13,r13,23
+	mov	rax,r14
+	vpalignr	xmm11,xmm5,xmm4,8
+	mov	r12,r9
+	shrd	r14,r14,5
+	vpsrlq	xmm10,xmm8,1
+	xor	r13,r8
+	xor	r12,r10
+	vpaddq	xmm0,xmm0,xmm11
+	shrd	r13,r13,4
+	xor	r14,rax
+	vpsrlq	xmm11,xmm8,7
+	and	r12,r8
+	xor	r13,r8
+	vpsllq	xmm9,xmm8,56
+	add	r11,QWORD[rsp]
+	mov	r15,rax
+	vpxor	xmm8,xmm11,xmm10
+	xor	r12,r10
+	shrd	r14,r14,6
+	vpsrlq	xmm10,xmm10,7
+	xor	r15,rbx
+	add	r11,r12
+	vpxor	xmm8,xmm8,xmm9
+	shrd	r13,r13,14
+	and	rdi,r15
+	vpsllq	xmm9,xmm9,7
+	xor	r14,rax
+	add	r11,r13
+	vpxor	xmm8,xmm8,xmm10
+	xor	rdi,rbx
+	shrd	r14,r14,28
+	vpsrlq	xmm11,xmm7,6
+	add	rdx,r11
+	add	r11,rdi
+	vpxor	xmm8,xmm8,xmm9
+	mov	r13,rdx
+	add	r14,r11
+	vpsllq	xmm10,xmm7,3
+	shrd	r13,r13,23
+	mov	r11,r14
+	vpaddq	xmm0,xmm0,xmm8
+	mov	r12,r8
+	shrd	r14,r14,5
+	vpsrlq	xmm9,xmm7,19
+	xor	r13,rdx
+	xor	r12,r9
+	vpxor	xmm11,xmm11,xmm10
+	shrd	r13,r13,4
+	xor	r14,r11
+	vpsllq	xmm10,xmm10,42
+	and	r12,rdx
+	xor	r13,rdx
+	vpxor	xmm11,xmm11,xmm9
+	add	r10,QWORD[8+rsp]
+	mov	rdi,r11
+	vpsrlq	xmm9,xmm9,42
+	xor	r12,r9
+	shrd	r14,r14,6
+	vpxor	xmm11,xmm11,xmm10
+	xor	rdi,rax
+	add	r10,r12
+	vpxor	xmm11,xmm11,xmm9
+	shrd	r13,r13,14
+	and	r15,rdi
+	vpaddq	xmm0,xmm0,xmm11
+	xor	r14,r11
+	add	r10,r13
+	vpaddq	xmm10,xmm0,XMMWORD[((-128))+rbp]
+	xor	r15,rax
+	shrd	r14,r14,28
+	add	rcx,r10
+	add	r10,r15
+	mov	r13,rcx
+	add	r14,r10
+	vmovdqa	XMMWORD[rsp],xmm10
+	vpalignr	xmm8,xmm2,xmm1,8
+	shrd	r13,r13,23
+	mov	r10,r14
+	vpalignr	xmm11,xmm6,xmm5,8
+	mov	r12,rdx
+	shrd	r14,r14,5
+	vpsrlq	xmm10,xmm8,1
+	xor	r13,rcx
+	xor	r12,r8
+	vpaddq	xmm1,xmm1,xmm11
+	shrd	r13,r13,4
+	xor	r14,r10
+	vpsrlq	xmm11,xmm8,7
+	and	r12,rcx
+	xor	r13,rcx
+	vpsllq	xmm9,xmm8,56
+	add	r9,QWORD[16+rsp]
+	mov	r15,r10
+	vpxor	xmm8,xmm11,xmm10
+	xor	r12,r8
+	shrd	r14,r14,6
+	vpsrlq	xmm10,xmm10,7
+	xor	r15,r11
+	add	r9,r12
+	vpxor	xmm8,xmm8,xmm9
+	shrd	r13,r13,14
+	and	rdi,r15
+	vpsllq	xmm9,xmm9,7
+	xor	r14,r10
+	add	r9,r13
+	vpxor	xmm8,xmm8,xmm10
+	xor	rdi,r11
+	shrd	r14,r14,28
+	vpsrlq	xmm11,xmm0,6
+	add	rbx,r9
+	add	r9,rdi
+	vpxor	xmm8,xmm8,xmm9
+	mov	r13,rbx
+	add	r14,r9
+	vpsllq	xmm10,xmm0,3
+	shrd	r13,r13,23
+	mov	r9,r14
+	vpaddq	xmm1,xmm1,xmm8
+	mov	r12,rcx
+	shrd	r14,r14,5
+	vpsrlq	xmm9,xmm0,19
+	xor	r13,rbx
+	xor	r12,rdx
+	vpxor	xmm11,xmm11,xmm10
+	shrd	r13,r13,4
+	xor	r14,r9
+	vpsllq	xmm10,xmm10,42
+	and	r12,rbx
+	xor	r13,rbx
+	vpxor	xmm11,xmm11,xmm9
+	add	r8,QWORD[24+rsp]
+	mov	rdi,r9
+	vpsrlq	xmm9,xmm9,42
+	xor	r12,rdx
+	shrd	r14,r14,6
+	vpxor	xmm11,xmm11,xmm10
+	xor	rdi,r10
+	add	r8,r12
+	vpxor	xmm11,xmm11,xmm9
+	shrd	r13,r13,14
+	and	r15,rdi
+	vpaddq	xmm1,xmm1,xmm11
+	xor	r14,r9
+	add	r8,r13
+	vpaddq	xmm10,xmm1,XMMWORD[((-96))+rbp]
+	xor	r15,r10
+	shrd	r14,r14,28
+	add	rax,r8
+	add	r8,r15
+	mov	r13,rax
+	add	r14,r8
+	vmovdqa	XMMWORD[16+rsp],xmm10
+	vpalignr	xmm8,xmm3,xmm2,8
+	shrd	r13,r13,23
+	mov	r8,r14
+	vpalignr	xmm11,xmm7,xmm6,8
+	mov	r12,rbx
+	shrd	r14,r14,5
+	vpsrlq	xmm10,xmm8,1
+	xor	r13,rax
+	xor	r12,rcx
+	vpaddq	xmm2,xmm2,xmm11
+	shrd	r13,r13,4
+	xor	r14,r8
+	vpsrlq	xmm11,xmm8,7
+	and	r12,rax
+	xor	r13,rax
+	vpsllq	xmm9,xmm8,56
+	add	rdx,QWORD[32+rsp]
+	mov	r15,r8
+	vpxor	xmm8,xmm11,xmm10
+	xor	r12,rcx
+	shrd	r14,r14,6
+	vpsrlq	xmm10,xmm10,7
+	xor	r15,r9
+	add	rdx,r12
+	vpxor	xmm8,xmm8,xmm9
+	shrd	r13,r13,14
+	and	rdi,r15
+	vpsllq	xmm9,xmm9,7
+	xor	r14,r8
+	add	rdx,r13
+	vpxor	xmm8,xmm8,xmm10
+	xor	rdi,r9
+	shrd	r14,r14,28
+	vpsrlq	xmm11,xmm1,6
+	add	r11,rdx
+	add	rdx,rdi
+	vpxor	xmm8,xmm8,xmm9
+	mov	r13,r11
+	add	r14,rdx
+	vpsllq	xmm10,xmm1,3
+	shrd	r13,r13,23
+	mov	rdx,r14
+	vpaddq	xmm2,xmm2,xmm8
+	mov	r12,rax
+	shrd	r14,r14,5
+	vpsrlq	xmm9,xmm1,19
+	xor	r13,r11
+	xor	r12,rbx
+	vpxor	xmm11,xmm11,xmm10
+	shrd	r13,r13,4
+	xor	r14,rdx
+	vpsllq	xmm10,xmm10,42
+	and	r12,r11
+	xor	r13,r11
+	vpxor	xmm11,xmm11,xmm9
+	add	rcx,QWORD[40+rsp]
+	mov	rdi,rdx
+	vpsrlq	xmm9,xmm9,42
+	xor	r12,rbx
+	shrd	r14,r14,6
+	vpxor	xmm11,xmm11,xmm10
+	xor	rdi,r8
+	add	rcx,r12
+	vpxor	xmm11,xmm11,xmm9
+	shrd	r13,r13,14
+	and	r15,rdi
+	vpaddq	xmm2,xmm2,xmm11
+	xor	r14,rdx
+	add	rcx,r13
+	vpaddq	xmm10,xmm2,XMMWORD[((-64))+rbp]
+	xor	r15,r8
+	shrd	r14,r14,28
+	add	r10,rcx
+	add	rcx,r15
+	mov	r13,r10
+	add	r14,rcx
+	vmovdqa	XMMWORD[32+rsp],xmm10
+	vpalignr	xmm8,xmm4,xmm3,8
+	shrd	r13,r13,23
+	mov	rcx,r14
+	vpalignr	xmm11,xmm0,xmm7,8
+	mov	r12,r11
+	shrd	r14,r14,5
+	vpsrlq	xmm10,xmm8,1
+	xor	r13,r10
+	xor	r12,rax
+	vpaddq	xmm3,xmm3,xmm11
+	shrd	r13,r13,4
+	xor	r14,rcx
+	vpsrlq	xmm11,xmm8,7
+	and	r12,r10
+	xor	r13,r10
+	vpsllq	xmm9,xmm8,56
+	add	rbx,QWORD[48+rsp]
+	mov	r15,rcx
+	vpxor	xmm8,xmm11,xmm10
+	xor	r12,rax
+	shrd	r14,r14,6
+	vpsrlq	xmm10,xmm10,7
+	xor	r15,rdx
+	add	rbx,r12
+	vpxor	xmm8,xmm8,xmm9
+	shrd	r13,r13,14
+	and	rdi,r15
+	vpsllq	xmm9,xmm9,7
+	xor	r14,rcx
+	add	rbx,r13
+	vpxor	xmm8,xmm8,xmm10
+	xor	rdi,rdx
+	shrd	r14,r14,28
+	vpsrlq	xmm11,xmm2,6
+	add	r9,rbx
+	add	rbx,rdi
+	vpxor	xmm8,xmm8,xmm9
+	mov	r13,r9
+	add	r14,rbx
+	vpsllq	xmm10,xmm2,3
+	shrd	r13,r13,23
+	mov	rbx,r14
+	vpaddq	xmm3,xmm3,xmm8
+	mov	r12,r10
+	shrd	r14,r14,5
+	vpsrlq	xmm9,xmm2,19
+	xor	r13,r9
+	xor	r12,r11
+	vpxor	xmm11,xmm11,xmm10
+	shrd	r13,r13,4
+	xor	r14,rbx
+	vpsllq	xmm10,xmm10,42
+	and	r12,r9
+	xor	r13,r9
+	vpxor	xmm11,xmm11,xmm9
+	add	rax,QWORD[56+rsp]
+	mov	rdi,rbx
+	vpsrlq	xmm9,xmm9,42
+	xor	r12,r11
+	shrd	r14,r14,6
+	vpxor	xmm11,xmm11,xmm10
+	xor	rdi,rcx
+	add	rax,r12
+	vpxor	xmm11,xmm11,xmm9
+	shrd	r13,r13,14
+	and	r15,rdi
+	vpaddq	xmm3,xmm3,xmm11
+	xor	r14,rbx
+	add	rax,r13
+	vpaddq	xmm10,xmm3,XMMWORD[((-32))+rbp]
+	xor	r15,rcx
+	shrd	r14,r14,28
+	add	r8,rax
+	add	rax,r15
+	mov	r13,r8
+	add	r14,rax
+	vmovdqa	XMMWORD[48+rsp],xmm10
+	vpalignr	xmm8,xmm5,xmm4,8
+	shrd	r13,r13,23
+	mov	rax,r14
+	vpalignr	xmm11,xmm1,xmm0,8
+	mov	r12,r9
+	shrd	r14,r14,5
+	vpsrlq	xmm10,xmm8,1
+	xor	r13,r8
+	xor	r12,r10
+	vpaddq	xmm4,xmm4,xmm11
+	shrd	r13,r13,4
+	xor	r14,rax
+	vpsrlq	xmm11,xmm8,7
+	and	r12,r8
+	xor	r13,r8
+	vpsllq	xmm9,xmm8,56
+	add	r11,QWORD[64+rsp]
+	mov	r15,rax
+	vpxor	xmm8,xmm11,xmm10
+	xor	r12,r10
+	shrd	r14,r14,6
+	vpsrlq	xmm10,xmm10,7
+	xor	r15,rbx
+	add	r11,r12
+	vpxor	xmm8,xmm8,xmm9
+	shrd	r13,r13,14
+	and	rdi,r15
+	vpsllq	xmm9,xmm9,7
+	xor	r14,rax
+	add	r11,r13
+	vpxor	xmm8,xmm8,xmm10
+	xor	rdi,rbx
+	shrd	r14,r14,28
+	vpsrlq	xmm11,xmm3,6
+	add	rdx,r11
+	add	r11,rdi
+	vpxor	xmm8,xmm8,xmm9
+	mov	r13,rdx
+	add	r14,r11
+	vpsllq	xmm10,xmm3,3
+	shrd	r13,r13,23
+	mov	r11,r14
+	vpaddq	xmm4,xmm4,xmm8
+	mov	r12,r8
+	shrd	r14,r14,5
+	vpsrlq	xmm9,xmm3,19
+	xor	r13,rdx
+	xor	r12,r9
+	vpxor	xmm11,xmm11,xmm10
+	shrd	r13,r13,4
+	xor	r14,r11
+	vpsllq	xmm10,xmm10,42
+	and	r12,rdx
+	xor	r13,rdx
+	vpxor	xmm11,xmm11,xmm9
+	add	r10,QWORD[72+rsp]
+	mov	rdi,r11
+	vpsrlq	xmm9,xmm9,42
+	xor	r12,r9
+	shrd	r14,r14,6
+	vpxor	xmm11,xmm11,xmm10
+	xor	rdi,rax
+	add	r10,r12
+	vpxor	xmm11,xmm11,xmm9
+	shrd	r13,r13,14
+	and	r15,rdi
+	vpaddq	xmm4,xmm4,xmm11
+	xor	r14,r11
+	add	r10,r13
+	vpaddq	xmm10,xmm4,XMMWORD[rbp]
+	xor	r15,rax
+	shrd	r14,r14,28
+	add	rcx,r10
+	add	r10,r15
+	mov	r13,rcx
+	add	r14,r10
+	vmovdqa	XMMWORD[64+rsp],xmm10
+	vpalignr	xmm8,xmm6,xmm5,8
+	shrd	r13,r13,23
+	mov	r10,r14
+	vpalignr	xmm11,xmm2,xmm1,8
+	mov	r12,rdx
+	shrd	r14,r14,5
+	vpsrlq	xmm10,xmm8,1
+	xor	r13,rcx
+	xor	r12,r8
+	vpaddq	xmm5,xmm5,xmm11
+	shrd	r13,r13,4
+	xor	r14,r10
+	vpsrlq	xmm11,xmm8,7
+	and	r12,rcx
+	xor	r13,rcx
+	vpsllq	xmm9,xmm8,56
+	add	r9,QWORD[80+rsp]
+	mov	r15,r10
+	vpxor	xmm8,xmm11,xmm10
+	xor	r12,r8
+	shrd	r14,r14,6
+	vpsrlq	xmm10,xmm10,7
+	xor	r15,r11
+	add	r9,r12
+	vpxor	xmm8,xmm8,xmm9
+	shrd	r13,r13,14
+	and	rdi,r15
+	vpsllq	xmm9,xmm9,7
+	xor	r14,r10
+	add	r9,r13
+	vpxor	xmm8,xmm8,xmm10
+	xor	rdi,r11
+	shrd	r14,r14,28
+	vpsrlq	xmm11,xmm4,6
+	add	rbx,r9
+	add	r9,rdi
+	vpxor	xmm8,xmm8,xmm9
+	mov	r13,rbx
+	add	r14,r9
+	vpsllq	xmm10,xmm4,3
+	shrd	r13,r13,23
+	mov	r9,r14
+	vpaddq	xmm5,xmm5,xmm8
+	mov	r12,rcx
+	shrd	r14,r14,5
+	vpsrlq	xmm9,xmm4,19
+	xor	r13,rbx
+	xor	r12,rdx
+	vpxor	xmm11,xmm11,xmm10
+	shrd	r13,r13,4
+	xor	r14,r9
+	vpsllq	xmm10,xmm10,42
+	and	r12,rbx
+	xor	r13,rbx
+	vpxor	xmm11,xmm11,xmm9
+	add	r8,QWORD[88+rsp]
+	mov	rdi,r9
+	vpsrlq	xmm9,xmm9,42
+	xor	r12,rdx
+	shrd	r14,r14,6
+	vpxor	xmm11,xmm11,xmm10
+	xor	rdi,r10
+	add	r8,r12
+	vpxor	xmm11,xmm11,xmm9
+	shrd	r13,r13,14
+	and	r15,rdi
+	vpaddq	xmm5,xmm5,xmm11
+	xor	r14,r9
+	add	r8,r13
+	vpaddq	xmm10,xmm5,XMMWORD[32+rbp]
+	xor	r15,r10
+	shrd	r14,r14,28
+	add	rax,r8
+	add	r8,r15
+	mov	r13,rax
+	add	r14,r8
+	vmovdqa	XMMWORD[80+rsp],xmm10
+	vpalignr	xmm8,xmm7,xmm6,8
+	shrd	r13,r13,23
+	mov	r8,r14
+	vpalignr	xmm11,xmm3,xmm2,8
+	mov	r12,rbx
+	shrd	r14,r14,5
+	vpsrlq	xmm10,xmm8,1
+	xor	r13,rax
+	xor	r12,rcx
+	vpaddq	xmm6,xmm6,xmm11
+	shrd	r13,r13,4
+	xor	r14,r8
+	vpsrlq	xmm11,xmm8,7
+	and	r12,rax
+	xor	r13,rax
+	vpsllq	xmm9,xmm8,56
+	add	rdx,QWORD[96+rsp]
+	mov	r15,r8
+	vpxor	xmm8,xmm11,xmm10
+	xor	r12,rcx
+	shrd	r14,r14,6
+	vpsrlq	xmm10,xmm10,7
+	xor	r15,r9
+	add	rdx,r12
+	vpxor	xmm8,xmm8,xmm9
+	shrd	r13,r13,14
+	and	rdi,r15
+	vpsllq	xmm9,xmm9,7
+	xor	r14,r8
+	add	rdx,r13
+	vpxor	xmm8,xmm8,xmm10
+	xor	rdi,r9
+	shrd	r14,r14,28
+	vpsrlq	xmm11,xmm5,6
+	add	r11,rdx
+	add	rdx,rdi
+	vpxor	xmm8,xmm8,xmm9
+	mov	r13,r11
+	add	r14,rdx
+	vpsllq	xmm10,xmm5,3
+	shrd	r13,r13,23
+	mov	rdx,r14
+	vpaddq	xmm6,xmm6,xmm8
+	mov	r12,rax
+	shrd	r14,r14,5
+	vpsrlq	xmm9,xmm5,19
+	xor	r13,r11
+	xor	r12,rbx
+	vpxor	xmm11,xmm11,xmm10
+	shrd	r13,r13,4
+	xor	r14,rdx
+	vpsllq	xmm10,xmm10,42
+	and	r12,r11
+	xor	r13,r11
+	vpxor	xmm11,xmm11,xmm9
+	add	rcx,QWORD[104+rsp]
+	mov	rdi,rdx
+	vpsrlq	xmm9,xmm9,42
+	xor	r12,rbx
+	shrd	r14,r14,6
+	vpxor	xmm11,xmm11,xmm10
+	xor	rdi,r8
+	add	rcx,r12
+	vpxor	xmm11,xmm11,xmm9
+	shrd	r13,r13,14
+	and	r15,rdi
+	vpaddq	xmm6,xmm6,xmm11
+	xor	r14,rdx
+	add	rcx,r13
+	vpaddq	xmm10,xmm6,XMMWORD[64+rbp]
+	xor	r15,r8
+	shrd	r14,r14,28
+	add	r10,rcx
+	add	rcx,r15
+	mov	r13,r10
+	add	r14,rcx
+	vmovdqa	XMMWORD[96+rsp],xmm10
+	vpalignr	xmm8,xmm0,xmm7,8
+	shrd	r13,r13,23
+	mov	rcx,r14
+	vpalignr	xmm11,xmm4,xmm3,8
+	mov	r12,r11
+	shrd	r14,r14,5
+	vpsrlq	xmm10,xmm8,1
+	xor	r13,r10
+	xor	r12,rax
+	vpaddq	xmm7,xmm7,xmm11
+	shrd	r13,r13,4
+	xor	r14,rcx
+	vpsrlq	xmm11,xmm8,7
+	and	r12,r10
+	xor	r13,r10
+	vpsllq	xmm9,xmm8,56
+	add	rbx,QWORD[112+rsp]
+	mov	r15,rcx
+	vpxor	xmm8,xmm11,xmm10
+	xor	r12,rax
+	shrd	r14,r14,6
+	vpsrlq	xmm10,xmm10,7
+	xor	r15,rdx
+	add	rbx,r12
+	vpxor	xmm8,xmm8,xmm9
+	shrd	r13,r13,14
+	and	rdi,r15
+	vpsllq	xmm9,xmm9,7
+	xor	r14,rcx
+	add	rbx,r13
+	vpxor	xmm8,xmm8,xmm10
+	xor	rdi,rdx
+	shrd	r14,r14,28
+	vpsrlq	xmm11,xmm6,6
+	add	r9,rbx
+	add	rbx,rdi
+	vpxor	xmm8,xmm8,xmm9
+	mov	r13,r9
+	add	r14,rbx
+	vpsllq	xmm10,xmm6,3
+	shrd	r13,r13,23
+	mov	rbx,r14
+	vpaddq	xmm7,xmm7,xmm8
+	mov	r12,r10
+	shrd	r14,r14,5
+	vpsrlq	xmm9,xmm6,19
+	xor	r13,r9
+	xor	r12,r11
+	vpxor	xmm11,xmm11,xmm10
+	shrd	r13,r13,4
+	xor	r14,rbx
+	vpsllq	xmm10,xmm10,42
+	and	r12,r9
+	xor	r13,r9
+	vpxor	xmm11,xmm11,xmm9
+	add	rax,QWORD[120+rsp]
+	mov	rdi,rbx
+	vpsrlq	xmm9,xmm9,42
+	xor	r12,r11
+	shrd	r14,r14,6
+	vpxor	xmm11,xmm11,xmm10
+	xor	rdi,rcx
+	add	rax,r12
+	vpxor	xmm11,xmm11,xmm9
+	shrd	r13,r13,14
+	and	r15,rdi
+	vpaddq	xmm7,xmm7,xmm11
+	xor	r14,rbx
+	add	rax,r13
+	vpaddq	xmm10,xmm7,XMMWORD[96+rbp]
+	xor	r15,rcx
+	shrd	r14,r14,28
+	add	r8,rax
+	add	rax,r15
+	mov	r13,r8
+	add	r14,rax
+	vmovdqa	XMMWORD[112+rsp],xmm10
+	cmp	BYTE[135+rbp],0
+	jne	NEAR $L$avx_00_47
+	shrd	r13,r13,23
+	mov	rax,r14
+	mov	r12,r9
+	shrd	r14,r14,5
+	xor	r13,r8
+	xor	r12,r10
+	shrd	r13,r13,4
+	xor	r14,rax
+	and	r12,r8
+	xor	r13,r8
+	add	r11,QWORD[rsp]
+	mov	r15,rax
+	xor	r12,r10
+	shrd	r14,r14,6
+	xor	r15,rbx
+	add	r11,r12
+	shrd	r13,r13,14
+	and	rdi,r15
+	xor	r14,rax
+	add	r11,r13
+	xor	rdi,rbx
+	shrd	r14,r14,28
+	add	rdx,r11
+	add	r11,rdi
+	mov	r13,rdx
+	add	r14,r11
+	shrd	r13,r13,23
+	mov	r11,r14
+	mov	r12,r8
+	shrd	r14,r14,5
+	xor	r13,rdx
+	xor	r12,r9
+	shrd	r13,r13,4
+	xor	r14,r11
+	and	r12,rdx
+	xor	r13,rdx
+	add	r10,QWORD[8+rsp]
+	mov	rdi,r11
+	xor	r12,r9
+	shrd	r14,r14,6
+	xor	rdi,rax
+	add	r10,r12
+	shrd	r13,r13,14
+	and	r15,rdi
+	xor	r14,r11
+	add	r10,r13
+	xor	r15,rax
+	shrd	r14,r14,28
+	add	rcx,r10
+	add	r10,r15
+	mov	r13,rcx
+	add	r14,r10
+	shrd	r13,r13,23
+	mov	r10,r14
+	mov	r12,rdx
+	shrd	r14,r14,5
+	xor	r13,rcx
+	xor	r12,r8
+	shrd	r13,r13,4
+	xor	r14,r10
+	and	r12,rcx
+	xor	r13,rcx
+	add	r9,QWORD[16+rsp]
+	mov	r15,r10
+	xor	r12,r8
+	shrd	r14,r14,6
+	xor	r15,r11
+	add	r9,r12
+	shrd	r13,r13,14
+	and	rdi,r15
+	xor	r14,r10
+	add	r9,r13
+	xor	rdi,r11
+	shrd	r14,r14,28
+	add	rbx,r9
+	add	r9,rdi
+	mov	r13,rbx
+	add	r14,r9
+	shrd	r13,r13,23
+	mov	r9,r14
+	mov	r12,rcx
+	shrd	r14,r14,5
+	xor	r13,rbx
+	xor	r12,rdx
+	shrd	r13,r13,4
+	xor	r14,r9
+	and	r12,rbx
+	xor	r13,rbx
+	add	r8,QWORD[24+rsp]
+	mov	rdi,r9
+	xor	r12,rdx
+	shrd	r14,r14,6
+	xor	rdi,r10
+	add	r8,r12
+	shrd	r13,r13,14
+	and	r15,rdi
+	xor	r14,r9
+	add	r8,r13
+	xor	r15,r10
+	shrd	r14,r14,28
+	add	rax,r8
+	add	r8,r15
+	mov	r13,rax
+	add	r14,r8
+	shrd	r13,r13,23
+	mov	r8,r14
+	mov	r12,rbx
+	shrd	r14,r14,5
+	xor	r13,rax
+	xor	r12,rcx
+	shrd	r13,r13,4
+	xor	r14,r8
+	and	r12,rax
+	xor	r13,rax
+	add	rdx,QWORD[32+rsp]
+	mov	r15,r8
+	xor	r12,rcx
+	shrd	r14,r14,6
+	xor	r15,r9
+	add	rdx,r12
+	shrd	r13,r13,14
+	and	rdi,r15
+	xor	r14,r8
+	add	rdx,r13
+	xor	rdi,r9
+	shrd	r14,r14,28
+	add	r11,rdx
+	add	rdx,rdi
+	mov	r13,r11
+	add	r14,rdx
+	shrd	r13,r13,23
+	mov	rdx,r14
+	mov	r12,rax
+	shrd	r14,r14,5
+	xor	r13,r11
+	xor	r12,rbx
+	shrd	r13,r13,4
+	xor	r14,rdx
+	and	r12,r11
+	xor	r13,r11
+	add	rcx,QWORD[40+rsp]
+	mov	rdi,rdx
+	xor	r12,rbx
+	shrd	r14,r14,6
+	xor	rdi,r8
+	add	rcx,r12
+	shrd	r13,r13,14
+	and	r15,rdi
+	xor	r14,rdx
+	add	rcx,r13
+	xor	r15,r8
+	shrd	r14,r14,28
+	add	r10,rcx
+	add	rcx,r15
+	mov	r13,r10
+	add	r14,rcx
+	shrd	r13,r13,23
+	mov	rcx,r14
+	mov	r12,r11
+	shrd	r14,r14,5
+	xor	r13,r10
+	xor	r12,rax
+	shrd	r13,r13,4
+	xor	r14,rcx
+	and	r12,r10
+	xor	r13,r10
+	add	rbx,QWORD[48+rsp]
+	mov	r15,rcx
+	xor	r12,rax
+	shrd	r14,r14,6
+	xor	r15,rdx
+	add	rbx,r12
+	shrd	r13,r13,14
+	and	rdi,r15
+	xor	r14,rcx
+	add	rbx,r13
+	xor	rdi,rdx
+	shrd	r14,r14,28
+	add	r9,rbx
+	add	rbx,rdi
+	mov	r13,r9
+	add	r14,rbx
+	shrd	r13,r13,23
+	mov	rbx,r14
+	mov	r12,r10
+	shrd	r14,r14,5
+	xor	r13,r9
+	xor	r12,r11
+	shrd	r13,r13,4
+	xor	r14,rbx
+	and	r12,r9
+	xor	r13,r9
+	add	rax,QWORD[56+rsp]
+	mov	rdi,rbx
+	xor	r12,r11
+	shrd	r14,r14,6
+	xor	rdi,rcx
+	add	rax,r12
+	shrd	r13,r13,14
+	and	r15,rdi
+	xor	r14,rbx
+	add	rax,r13
+	xor	r15,rcx
+	shrd	r14,r14,28
+	add	r8,rax
+	add	rax,r15
+	mov	r13,r8
+	add	r14,rax
+	shrd	r13,r13,23
+	mov	rax,r14
+	mov	r12,r9
+	shrd	r14,r14,5
+	xor	r13,r8
+	xor	r12,r10
+	shrd	r13,r13,4
+	xor	r14,rax
+	and	r12,r8
+	xor	r13,r8
+	add	r11,QWORD[64+rsp]
+	mov	r15,rax
+	xor	r12,r10
+	shrd	r14,r14,6
+	xor	r15,rbx
+	add	r11,r12
+	shrd	r13,r13,14
+	and	rdi,r15
+	xor	r14,rax
+	add	r11,r13
+	xor	rdi,rbx
+	shrd	r14,r14,28
+	add	rdx,r11
+	add	r11,rdi
+	mov	r13,rdx
+	add	r14,r11
+	shrd	r13,r13,23
+	mov	r11,r14
+	mov	r12,r8
+	shrd	r14,r14,5
+	xor	r13,rdx
+	xor	r12,r9
+	shrd	r13,r13,4
+	xor	r14,r11
+	and	r12,rdx
+	xor	r13,rdx
+	add	r10,QWORD[72+rsp]
+	mov	rdi,r11
+	xor	r12,r9
+	shrd	r14,r14,6
+	xor	rdi,rax
+	add	r10,r12
+	shrd	r13,r13,14
+	and	r15,rdi
+	xor	r14,r11
+	add	r10,r13
+	xor	r15,rax
+	shrd	r14,r14,28
+	add	rcx,r10
+	add	r10,r15
+	mov	r13,rcx
+	add	r14,r10
+	shrd	r13,r13,23
+	mov	r10,r14
+	mov	r12,rdx
+	shrd	r14,r14,5
+	xor	r13,rcx
+	xor	r12,r8
+	shrd	r13,r13,4
+	xor	r14,r10
+	and	r12,rcx
+	xor	r13,rcx
+	add	r9,QWORD[80+rsp]
+	mov	r15,r10
+	xor	r12,r8
+	shrd	r14,r14,6
+	xor	r15,r11
+	add	r9,r12
+	shrd	r13,r13,14
+	and	rdi,r15
+	xor	r14,r10
+	add	r9,r13
+	xor	rdi,r11
+	shrd	r14,r14,28
+	add	rbx,r9
+	add	r9,rdi
+	mov	r13,rbx
+	add	r14,r9
+	shrd	r13,r13,23
+	mov	r9,r14
+	mov	r12,rcx
+	shrd	r14,r14,5
+	xor	r13,rbx
+	xor	r12,rdx
+	shrd	r13,r13,4
+	xor	r14,r9
+	and	r12,rbx
+	xor	r13,rbx
+	add	r8,QWORD[88+rsp]
+	mov	rdi,r9
+	xor	r12,rdx
+	shrd	r14,r14,6
+	xor	rdi,r10
+	add	r8,r12
+	shrd	r13,r13,14
+	and	r15,rdi
+	xor	r14,r9
+	add	r8,r13
+	xor	r15,r10
+	shrd	r14,r14,28
+	add	rax,r8
+	add	r8,r15
+	mov	r13,rax
+	add	r14,r8
+	shrd	r13,r13,23
+	mov	r8,r14
+	mov	r12,rbx
+	shrd	r14,r14,5
+	xor	r13,rax
+	xor	r12,rcx
+	shrd	r13,r13,4
+	xor	r14,r8
+	and	r12,rax
+	xor	r13,rax
+	add	rdx,QWORD[96+rsp]
+	mov	r15,r8
+	xor	r12,rcx
+	shrd	r14,r14,6
+	xor	r15,r9
+	add	rdx,r12
+	shrd	r13,r13,14
+	and	rdi,r15
+	xor	r14,r8
+	add	rdx,r13
+	xor	rdi,r9
+	shrd	r14,r14,28
+	add	r11,rdx
+	add	rdx,rdi
+	mov	r13,r11
+	add	r14,rdx
+	shrd	r13,r13,23
+	mov	rdx,r14
+	mov	r12,rax
+	shrd	r14,r14,5
+	xor	r13,r11
+	xor	r12,rbx
+	shrd	r13,r13,4
+	xor	r14,rdx
+	and	r12,r11
+	xor	r13,r11
+	add	rcx,QWORD[104+rsp]
+	mov	rdi,rdx
+	xor	r12,rbx
+	shrd	r14,r14,6
+	xor	rdi,r8
+	add	rcx,r12
+	shrd	r13,r13,14
+	and	r15,rdi
+	xor	r14,rdx
+	add	rcx,r13
+	xor	r15,r8
+	shrd	r14,r14,28
+	add	r10,rcx
+	add	rcx,r15
+	mov	r13,r10
+	add	r14,rcx
+	shrd	r13,r13,23
+	mov	rcx,r14
+	mov	r12,r11
+	shrd	r14,r14,5
+	xor	r13,r10
+	xor	r12,rax
+	shrd	r13,r13,4
+	xor	r14,rcx
+	and	r12,r10
+	xor	r13,r10
+	add	rbx,QWORD[112+rsp]
+	mov	r15,rcx
+	xor	r12,rax
+	shrd	r14,r14,6
+	xor	r15,rdx
+	add	rbx,r12
+	shrd	r13,r13,14
+	and	rdi,r15
+	xor	r14,rcx
+	add	rbx,r13
+	xor	rdi,rdx
+	shrd	r14,r14,28
+	add	r9,rbx
+	add	rbx,rdi
+	mov	r13,r9
+	add	r14,rbx
+	shrd	r13,r13,23
+	mov	rbx,r14
+	mov	r12,r10
+	shrd	r14,r14,5
+	xor	r13,r9
+	xor	r12,r11
+	shrd	r13,r13,4
+	xor	r14,rbx
+	and	r12,r9
+	xor	r13,r9
+	add	rax,QWORD[120+rsp]
+	mov	rdi,rbx
+	xor	r12,r11
+	shrd	r14,r14,6
+	xor	rdi,rcx
+	add	rax,r12
+	shrd	r13,r13,14
+	and	r15,rdi
+	xor	r14,rbx
+	add	rax,r13
+	xor	r15,rcx
+	shrd	r14,r14,28
+	add	r8,rax
+	add	rax,r15
+	mov	r13,r8
+	add	r14,rax
+	mov	rdi,QWORD[((128+0))+rsp]
+	mov	rax,r14
+
+	add	rax,QWORD[rdi]
+	lea	rsi,[128+rsi]
+	add	rbx,QWORD[8+rdi]
+	add	rcx,QWORD[16+rdi]
+	add	rdx,QWORD[24+rdi]
+	add	r8,QWORD[32+rdi]
+	add	r9,QWORD[40+rdi]
+	add	r10,QWORD[48+rdi]
+	add	r11,QWORD[56+rdi]
+
+	cmp	rsi,QWORD[((128+16))+rsp]
+
+	mov	QWORD[rdi],rax
+	mov	QWORD[8+rdi],rbx
+	mov	QWORD[16+rdi],rcx
+	mov	QWORD[24+rdi],rdx
+	mov	QWORD[32+rdi],r8
+	mov	QWORD[40+rdi],r9
+	mov	QWORD[48+rdi],r10
+	mov	QWORD[56+rdi],r11
+	jb	NEAR $L$loop_avx
+
+	mov	rsi,QWORD[((128+24))+rsp]
+	vzeroupper
+	movaps	xmm6,XMMWORD[((128+32))+rsp]
+	movaps	xmm7,XMMWORD[((128+48))+rsp]
+	movaps	xmm8,XMMWORD[((128+64))+rsp]
+	movaps	xmm9,XMMWORD[((128+80))+rsp]
+	movaps	xmm10,XMMWORD[((128+96))+rsp]
+	movaps	xmm11,XMMWORD[((128+112))+rsp]
+	mov	r15,QWORD[rsi]
+	mov	r14,QWORD[8+rsi]
+	mov	r13,QWORD[16+rsi]
+	mov	r12,QWORD[24+rsi]
+	mov	rbp,QWORD[32+rsi]
+	mov	rbx,QWORD[40+rsi]
+	lea	rsp,[48+rsi]
+$L$epilogue_avx:
+	mov	rdi,QWORD[8+rsp]	;WIN64 epilogue
+	mov	rsi,QWORD[16+rsp]
+	DB	0F3h,0C3h		;repret
+$L$SEH_end_sha512_block_data_order_avx:
 EXTERN	__imp_RtlVirtualUnwind
 
 ALIGN	16
@@ -1903,9 +4190,23 @@ ALIGN	4
 	DD	$L$SEH_begin_sha512_block_data_order wrt ..imagebase
 	DD	$L$SEH_end_sha512_block_data_order wrt ..imagebase
 	DD	$L$SEH_info_sha512_block_data_order wrt ..imagebase
+	DD	$L$SEH_begin_sha512_block_data_order_xop wrt ..imagebase
+	DD	$L$SEH_end_sha512_block_data_order_xop wrt ..imagebase
+	DD	$L$SEH_info_sha512_block_data_order_xop wrt ..imagebase
+	DD	$L$SEH_begin_sha512_block_data_order_avx wrt ..imagebase
+	DD	$L$SEH_end_sha512_block_data_order_avx wrt ..imagebase
+	DD	$L$SEH_info_sha512_block_data_order_avx wrt ..imagebase
 section	.xdata rdata align=8
 ALIGN	8
 $L$SEH_info_sha512_block_data_order:
 DB	9,0,0,0
 	DD	se_handler wrt ..imagebase
 	DD	$L$prologue wrt ..imagebase,$L$epilogue wrt ..imagebase
+$L$SEH_info_sha512_block_data_order_xop:
+DB	9,0,0,0
+	DD	se_handler wrt ..imagebase
+	DD	$L$prologue_xop wrt ..imagebase,$L$epilogue_xop wrt ..imagebase
+$L$SEH_info_sha512_block_data_order_avx:
+DB	9,0,0,0
+	DD	se_handler wrt ..imagebase
+	DD	$L$prologue_avx wrt ..imagebase,$L$epilogue_avx wrt ..imagebase
diff --git a/packager/third_party/curl/curl.gyp b/packager/third_party/curl/curl.gyp
index eec6da48d8..c82a98514b 100644
--- a/packager/third_party/curl/curl.gyp
+++ b/packager/third_party/curl/curl.gyp
@@ -108,14 +108,14 @@
         'source/lib/content_encoding.c',
         'source/lib/cookie.c',
         'source/lib/curl_addrinfo.c',
+        'source/lib/curl_des.c',
+        'source/lib/curl_endian.c',
         'source/lib/curl_fnmatch.c',
         'source/lib/curl_gethostname.c',
         'source/lib/curl_gssapi.c',
         'source/lib/curl_memrchr.c',
         'source/lib/curl_multibyte.c',
-        'source/lib/curl_ntlm.c',
         'source/lib/curl_ntlm_core.c',
-        'source/lib/curl_ntlm_msgs.c',
         'source/lib/curl_ntlm_wb.c',
         'source/lib/curl_rtmp.c',
         'source/lib/curl_sasl.c',
@@ -137,21 +137,23 @@
         'source/lib/hmac.c',
         'source/lib/hostasyn.c',
         'source/lib/hostcheck.c',
-        'source/lib/hostip.c',
         'source/lib/hostip4.c',
         'source/lib/hostip6.c',
+        'source/lib/hostip.c',
         'source/lib/hostsyn.c',
+        'source/lib/http2.c',
         'source/lib/http.c',
         'source/lib/http_chunks.c',
         'source/lib/http_digest.c',
         'source/lib/http_negotiate.c',
-        'source/lib/http_negotiate_sspi.c',
+        'source/lib/http_ntlm.c',
         'source/lib/http_proxy.c',
         'source/lib/idn_win32.c',
         'source/lib/if2ip.c',
         'source/lib/imap.c',
         'source/lib/inet_ntop.c',
         'source/lib/inet_pton.c',
+        'source/lib/krb5.c',
         'source/lib/ldap.c',
         'source/lib/llist.c',
         'source/lib/md4.c',
@@ -162,6 +164,8 @@
         'source/lib/netrc.c',
         'source/lib/non-ascii.c',
         'source/lib/nonblock.c',
+        'source/lib/nwlib.c',
+        'source/lib/nwos.c',
         'source/lib/openldap.c',
         'source/lib/parsedate.c',
         'source/lib/pingpong.c',
@@ -175,6 +179,7 @@
         'source/lib/sendf.c',
         'source/lib/share.c',
         'source/lib/slist.c',
+        'source/lib/smb.c',
         'source/lib/smtp.c',
         'source/lib/socks.c',
         'source/lib/socks_gssapi.c',
@@ -187,17 +192,31 @@
         'source/lib/strerror.c',
         'source/lib/strtok.c',
         'source/lib/strtoofft.c',
+        'source/lib/system_win32.c',
         'source/lib/telnet.c',
         'source/lib/tftp.c',
         'source/lib/timeval.c',
         'source/lib/transfer.c',
         'source/lib/url.c',
+        'source/lib/vauth/cleartext.c',
+        'source/lib/vauth/cram.c',
+        'source/lib/vauth/digest.c',
+        'source/lib/vauth/digest_sspi.c',
+        'source/lib/vauth/krb5_gssapi.c',
+        'source/lib/vauth/krb5_sspi.c',
+        'source/lib/vauth/ntlm.c',
+        'source/lib/vauth/ntlm_sspi.c',
+        'source/lib/vauth/oauth2.c',
+        'source/lib/vauth/spnego_gssapi.c',
+        'source/lib/vauth/spnego_sspi.c',
+        'source/lib/vauth/vauth.c',
         'source/lib/version.c',
         'source/lib/vtls/axtls.c',
         'source/lib/vtls/cyassl.c',
         'source/lib/vtls/darwinssl.c',
         'source/lib/vtls/gskit.c',
         'source/lib/vtls/gtls.c',
+        'source/lib/vtls/mbedtls.c',
         'source/lib/vtls/nss.c',
         'source/lib/vtls/openssl.c',
         'source/lib/vtls/polarssl.c',
@@ -206,6 +225,7 @@
         'source/lib/vtls/vtls.c',
         'source/lib/warnless.c',
         'source/lib/wildcard.c',
+        'source/lib/x509asn1.c',
       ],
     },
     {