abc/GmSSL
1
0
Fork 0
mirror of https://github.com/guanzhi/GmSSL.git synced 2026-08-11 16:33:40 +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

27
crypto/bn/asm/x86_64-gf2m.pl
View File

@@ -1,4 +1,11 @@
#!/usr/bin/env perl
#! /usr/bin/env perl
# Copyright 2011-2016 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
@@ -13,7 +20,7 @@
# in bn_gf2m.c. It's kind of low-hanging mechanical port from C for
# the time being... Except that it has two code paths: code suitable
# for any x86_64 CPU and PCLMULQDQ one suitable for Westmere and
# later. Improvement varies from one benchmark and µ-arch to another.
# later. Improvement varies from one benchmark and µ-arch to another.
# Vanilla code path is at most 20% faster than compiler-generated code
# [not very impressive], while PCLMULQDQ - whole 85%-160% better on
# 163- and 571-bit ECDH benchmarks on Intel CPUs. Keep in mind that
@@ -31,7 +38,7 @@ $0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1;
( $xlate="${dir}../../perlasm/x86_64-xlate.pl" and -f $xlate) or
die "can't locate x86_64-xlate.pl";
open OUT,"| \"$^X\" $xlate $flavour $output";
open OUT,"| \"$^X\" \"$xlate\" $flavour \"$output\"";
*STDOUT=*OUT;
($lo,$hi)=("%rax","%rdx"); $a=$lo;
@@ -184,13 +191,13 @@ ___
$code.=<<___;
movdqa %xmm0,%xmm4
movdqa %xmm1,%xmm5
pclmulqdq \$0,%xmm1,%xmm0 # a1·b1
pclmulqdq \$0,%xmm1,%xmm0 # a1·b1
pxor %xmm2,%xmm4
pxor %xmm3,%xmm5
pclmulqdq \$0,%xmm3,%xmm2 # a0·b0
pclmulqdq \$0,%xmm5,%xmm4 # (a0+a1)·(b0+b1)
pclmulqdq \$0,%xmm3,%xmm2 # a0·b0
pclmulqdq \$0,%xmm5,%xmm4 # (a0+a1)·(b0+b1)
xorps %xmm0,%xmm4
xorps %xmm2,%xmm4 # (a0+a1)·(b0+b1)-a0·b0-a1·b1
xorps %xmm2,%xmm4 # (a0+a1)·(b0+b1)-a0·b0-a1·b1
movdqa %xmm4,%xmm5
pslldq \$8,%xmm4
psrldq \$8,%xmm5
@@ -225,13 +232,13 @@ $code.=<<___;
mov \$0xf,$mask
mov $a1,$a
mov $b1,$b
call _mul_1x1 # a1·b1
call _mul_1x1 # a1·b1
mov $lo,16(%rsp)
mov $hi,24(%rsp)
mov 48(%rsp),$a
mov 64(%rsp),$b
call _mul_1x1 # a0·b0
call _mul_1x1 # a0·b0
mov $lo,0(%rsp)
mov $hi,8(%rsp)
@@ -239,7 +246,7 @@ $code.=<<___;
mov 56(%rsp),$b
xor 48(%rsp),$a
xor 64(%rsp),$b
call _mul_1x1 # (a0+a1)·(b0+b1)
call _mul_1x1 # (a0+a1)·(b0+b1)
___
@r=("%rbx","%rcx","%rdi","%rsi");
$code.=<<___;