abc/GmSSL
1
0
Fork 0
mirror of https://github.com/guanzhi/GmSSL.git synced 2026-08-14 01:53:41 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'origin/master'

Browse Source 
# Conflicts:
#	README.md
This commit is contained in:
Zhi Guan
2017-02-14 16:12:29 +08:00
parent d2254170b8
commit 43fed1108d
3503 changed files with 320546 additions and 408546 deletions
Download Patch File Download Diff File Expand all files Collapse all files

29
crypto/modes/asm/ghash-x86_64.pl
View File

@@ -1,4 +1,11 @@
#!/usr/bin/env perl
#! /usr/bin/env perl
# Copyright 2010-2016 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
@@ -64,8 +71,10 @@
# Ivy Bridge 1.80(+7%)
# Haswell 0.55(+93%) (if system doesn't support AVX)
# Broadwell 0.45(+110%)(if system doesn't support AVX)
# Skylake 0.44(+110%)(if system doesn't support AVX)
# Bulldozer 1.49(+27%)
# Silvermont 2.88(+13%)
# Goldmont 1.08(+24%)
# March 2013
#
@@ -74,8 +83,8 @@
# CPUs such as Sandy and Ivy Bridge can execute it, the code performs
# sub-optimally in comparison to above mentioned version. But thanks
# to Ilya Albrekht and Max Locktyukhin of Intel Corp. we knew that
# it performs in 0.41 cycles per byte on Haswell processor, and in
# 0.29 on Broadwell.
# it performs in 0.41 cycles per byte on Haswell processor, in
# 0.29 on Broadwell, and in 0.36 on Skylake.
#
# [1] http://rt.openssl.org/Ticket/Display.html?id=2900&user=guest&pass=guest
@@ -92,7 +101,7 @@ die "can't locate x86_64-xlate.pl";
if (`$ENV{CC} -Wa,-v -c -o /dev/null -x assembler /dev/null 2>&1`
=~ /GNU assembler version ([2-9]\.[0-9]+)/) {
$avx = ($1>=2.19) + ($1>=2.22);
$avx = ($1>=2.20) + ($1>=2.22);
}
if (!$avx && $win64 && ($flavour =~ /nasm/ || $ENV{ASM} =~ /nasm/) &&
@@ -105,11 +114,11 @@ if (!$avx && $win64 && ($flavour =~ /masm/ || $ENV{ASM} =~ /ml64/) &&
$avx = ($1>=10) + ($1>=11);
}
if (!$avx && `$ENV{CC} -v 2>&1` =~ /(^clang version|based on LLVM) ([3-9]\.[0-9]+)/) {
if (!$avx && `$ENV{CC} -v 2>&1` =~ /((?:^clang|LLVM) version|.*based on LLVM) ([3-9]\.[0-9]+)/) {
$avx = ($2>=3.0) + ($2>3.0);
}
open OUT,"| \"$^X\" $xlate $flavour $output";
open OUT,"| \"$^X\" \"$xlate\" $flavour \"$output\"";
*STDOUT=*OUT;
$do4xaggr=1;
@@ -576,15 +585,15 @@ $code.=<<___ if (0 || (&reduction_alg9($Xhi,$Xi)&&0));
# experimental alternative. special thing about is that there
# no dependency between the two multiplications...
mov \$`0xE1<<1`,%eax
mov \$0xA040608020C0E000,%r10 # ((7..0)·0xE0)&0xff
mov \$0xA040608020C0E000,%r10 # ((7..0)·0xE0)&0xff
mov \$0x07,%r11d
movq %rax,$T1
movq %r10,$T2
movq %r11,$T3 # borrow $T3
pand $Xi,$T3
pshufb $T3,$T2 # ($Xi&7)·0xE0
pshufb $T3,$T2 # ($Xi&7)·0xE0
movq %rax,$T3
pclmulqdq \$0x00,$Xi,$T1 # ·(0xE1<<1)
pclmulqdq \$0x00,$Xi,$T1 # ·(0xE1<<1)
pxor $Xi,$T2
pslldq \$15,$T2
paddd $T2,$T2 # <<(64+56+1)
@@ -657,7 +666,7 @@ $code.=<<___;
je .Lskip4x
sub \$0x30,$len
mov \$0xA040608020C0E000,%rax # ((7..0)·0xE0)&0xff
mov \$0xA040608020C0E000,%rax # ((7..0)·0xE0)&0xff
movdqu 0x30($Htbl),$Hkey3
movdqu 0x40($Htbl),$Hkey4