diff options
Diffstat (limited to 'deps/openssl/openssl/crypto/sha/asm/sha512-x86_64.pl')
-rwxr-xr-x | deps/openssl/openssl/crypto/sha/asm/sha512-x86_64.pl | 17 |
1 files changed, 13 insertions, 4 deletions
diff --git a/deps/openssl/openssl/crypto/sha/asm/sha512-x86_64.pl b/deps/openssl/openssl/crypto/sha/asm/sha512-x86_64.pl index 78e445f3fe..c9b7b28123 100755 --- a/deps/openssl/openssl/crypto/sha/asm/sha512-x86_64.pl +++ b/deps/openssl/openssl/crypto/sha/asm/sha512-x86_64.pl @@ -1,4 +1,11 @@ -#!/usr/bin/env perl +#! /usr/bin/env perl +# Copyright 2005-2016 The OpenSSL Project Authors. All Rights Reserved. +# +# Licensed under the OpenSSL license (the "License"). You may not use +# this file except in compliance with the License. You can obtain a copy +# in the file LICENSE in the source distribution or at +# https://www.openssl.org/source/license.html + # # ==================================================================== # Written by Andy Polyakov <appro@openssl.org> for the OpenSSL @@ -34,7 +41,7 @@ # level parallelism, on a given CPU implementation in this case. # # Special note on Intel EM64T. While Opteron CPU exhibits perfect -# perfromance ratio of 1.5 between 64- and 32-bit flavors [see above], +# performance ratio of 1.5 between 64- and 32-bit flavors [see above], # [currently available] EM64T CPUs apparently are far from it. On the # contrary, 64-bit version, sha512_block, is ~30% *slower* than 32-bit # sha256_block:-( This is presumably because 64-bit shifts/rotates @@ -86,12 +93,14 @@ # Sandy Bridge 17.4 14.2(+23%) 11.6(+50%(**)) 11.2 8.10(+38%(**)) # Ivy Bridge 12.6 10.5(+20%) 10.3(+22%) 8.17 7.22(+13%) # Haswell 12.2 9.28(+31%) 7.80(+56%) 7.66 5.40(+42%) +# Skylake 11.4 9.03(+26%) 7.70(+48%) 7.25 5.20(+40%) # Bulldozer 21.1 13.6(+54%) 13.6(+54%(***)) 13.5 8.58(+57%) # VIA Nano 23.0 16.5(+39%) - 14.7 - # Atom 23.0 18.9(+22%) - 14.7 - # Silvermont 27.4 20.6(+33%) - 17.5 - +# Goldmont 18.9 14.3(+32%) 4.16(+350%) 12.0 - # -# (*) whichever best applicable; +# (*) whichever best applicable, including SHAEXT; # (**) switch from ror to shrd stands for fair share of improvement; # (***) execution time is fully determined by remaining integer-only # part, body_00_15; reducing the amount of SIMD instructions @@ -131,7 +140,7 @@ if (!$avx && `$ENV{CC} -v 2>&1` =~ /((?:^clang|LLVM) version|.*based on LLVM) ([ $shaext=1; ### set to zero if compiling for 1.0.1 $avx=1 if (!$shaext && $avx); -open OUT,"| \"$^X\" $xlate $flavour $output"; +open OUT,"| \"$^X\" \"$xlate\" $flavour \"$output\""; *STDOUT=*OUT; if ($output =~ /512/) { |