abc/GmSSL
1
0
Fork 0
mirror of https://github.com/guanzhi/GmSSL.git synced 2026-08-08 06:03:47 +08:00
Code Issues Packages Projects Releases Wiki Activity

quantum init

Browse Source
This commit is contained in:
zhaoxiaomeng
2018-01-04 13:38:57 +08:00
committed by Simon
parent d11f845fde
commit 53af3b51ae
2361 changed files with 387455 additions and 144458 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
crypto/rc4/asm/rc4-586.pl
View File

@@ -1,11 +1,4 @@
#! /usr/bin/env perl
# Copyright 1998-2016 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
#!/usr/bin/env perl
# ====================================================================
# [Re]written by Andy Polyakov <appro@fy.chalmers.se> for the OpenSSL
@@ -50,9 +43,6 @@
# Westmere 5.1/+94%(**)
# Sandy Bridge 5.0/+8%
# Atom 12.6/+6%
# VIA Nano 6.4/+9%
# Ivy Bridge 4.9/±0%
# Bulldozer 4.9/+15%
#
# (*) PIII can actually deliver 6.6 cycles per byte with MMX code,
# but this specific code performs poorly on Core2. And vice
@@ -70,9 +60,6 @@ $0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1;
push(@INC,"${dir}","${dir}../../perlasm");
require "x86asm.pl";
$output=pop;
open STDOUT,">$output";
&asm_init($ARGV[0],"rc4-586.pl",$x86only = $ARGV[$#ARGV] eq "386");
$xx="eax";
@@ -157,7 +144,7 @@ if ($alt=0) {
&movd ($i>0?"mm1":"mm2",&DWP(0,$dat,$ty,4));
# (*) This is the key to Core2 and Westmere performance.
# Without movz out-of-order execution logic confuses
# Whithout movz out-of-order execution logic confuses
# itself and fails to reorder loads and stores. Problem
# appears to be fixed in Sandy Bridge...
}
@@ -317,7 +304,7 @@ $ido="ecx";
$idx="edx";
# void RC4_set_key(RC4_KEY *key,int len,const unsigned char *data);
&function_begin("RC4_set_key");
&function_begin("private_RC4_set_key");
&mov ($out,&wparam(0)); # load key
&mov ($idi,&wparam(1)); # load len
&mov ($inp,&wparam(2)); # load data
@@ -395,7 +382,7 @@ $idx="edx";
&xor ("eax","eax");
&mov (&DWP(-8,$out),"eax"); # key->x=0;
&mov (&DWP(-4,$out),"eax"); # key->y=0;
&function_end("RC4_set_key");
&function_end("private_RC4_set_key");
# const char *RC4_options(void);
&function_begin_B("RC4_options");
@@ -425,4 +412,3 @@ $idx="edx";
&asm_finish();
close STDOUT;

14
crypto/rc4/asm/rc4-ia64.pl
View File

@@ -1,11 +1,4 @@
#! /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
#!/usr/bin/env perl
#
# ====================================================================
# Written by David Mosberger <David.Mosberger@acm.org> based on the
@@ -171,9 +164,6 @@
# random input data).
#
$output = pop;
open STDOUT,">$output";
$phases = 4; # number of stages/phases in the pipelined-loop
$unroll_count = 6; # number of times we unrolled it
$pComI = (1 << 0);
@@ -763,5 +753,3 @@ $code.=<<___;
___
print $code;
close STDOUT;

17
crypto/rc4/asm/rc4-md5-x86_64.pl
View File

@@ -1,11 +1,4 @@
#! /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
#!/usr/bin/env perl
#
# ====================================================================
# Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
@@ -36,16 +29,10 @@
# Core2 6.5 5.8 12.3 7.7 +60%
# Westmere 4.3 5.2 9.5 7.0 +36%
# Sandy Bridge 4.2 5.5 9.7 6.8 +43%
# Ivy Bridge 4.1 5.2 9.3 6.0 +54%
# Haswell 4.0 5.0 9.0 5.7 +60%
# Skylake 6.3(**) 5.0 11.3 5.3 +110%
# Atom 9.3 6.5 15.8 11.1 +42%
# VIA Nano 6.3 5.4 11.7 8.6 +37%
# Bulldozer 4.5 5.4 9.9 7.7 +29%
#
# (*) rc4-x86_64.pl delivers 5.3 on Opteron, so real improvement
# is +53%...
# (**) unidentified anomaly;
my ($rc4,$md5)=(1,1); # what to generate?
my $D="#" if (!$md5); # if set to "#", MD5 is stitched into RC4(),
@@ -64,7 +51,7 @@ $0 =~ m/(.*[\/\\])[^\/\\]+$/; my $dir=$1; my $xlate;
( $xlate="${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 $output";
*STDOUT=*OUT;
my ($dat,$in0,$out,$ctx,$inp,$len, $func,$nargs);

13
crypto/rc4/asm/rc4-parisc.pl
View File

@@ -1,11 +1,4 @@
#! /usr/bin/env perl
# Copyright 2009-2016 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
#!/usr/bin/env perl
# ====================================================================
# Written by Andy Polyakov <appro@fy.chalmers.se> for the OpenSSL
@@ -250,9 +243,9 @@ ___
$code.=<<___;
.EXPORT RC4_set_key,ENTRY,ARGW0=GR,ARGW1=GR,ARGW2=GR
.EXPORT private_RC4_set_key,ENTRY,ARGW0=GR,ARGW1=GR,ARGW2=GR
.ALIGN 8
RC4_set_key
private_RC4_set_key
.PROC
.CALLINFO NO_CALLS
.ENTRY

19
crypto/rc4/asm/rc4-s390x.pl
View File

@@ -1,11 +1,4 @@
#! /usr/bin/env perl
# Copyright 2009-2016 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
#!/usr/bin/env perl
#
# ====================================================================
# Written by Andy Polyakov <appro@fy.chalmers.se> for the OpenSSL
@@ -40,7 +33,7 @@ if ($flavour =~ /3[12]/) {
$g="g";
}
while (($output=shift) && ($output!~/\w[\w\-]*\.\w+$/)) {}
while (($output=shift) && ($output!~/^\w[\w\-]*\.\w+$/)) {}
open STDOUT,">$output";
$rp="%r14";
@@ -178,10 +171,10 @@ $ikey="%r7";
$iinp="%r8";
$code.=<<___;
.globl RC4_set_key
.type RC4_set_key,\@function
.globl private_RC4_set_key
.type private_RC4_set_key,\@function
.align 64
RC4_set_key:
private_RC4_set_key:
stm${g} %r6,%r8,6*$SIZE_T($sp)
lhi $cnt,256
la $idx,0(%r0)
@@ -217,7 +210,7 @@ RC4_set_key:
.Ldone:
lm${g} %r6,%r8,6*$SIZE_T($sp)
br $rp
.size RC4_set_key,.-RC4_set_key
.size private_RC4_set_key,.-private_RC4_set_key
___
}

32
crypto/rc4/asm/rc4-x86_64.pl
View File

@@ -1,11 +1,4 @@
#! /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
#!/usr/bin/env perl
#
# ====================================================================
# Written by Andy Polyakov <appro@fy.chalmers.se> for the OpenSSL
@@ -57,7 +50,7 @@
# As was shown by Zou Nanhai loop unrolling can improve Intel EM64T
# performance by >30% [unlike P4 32-bit case that is]. But this is
# provided that loads are reordered even more aggressively! Both code
# paths, AMD64 and EM64T, reorder loads in essentially same manner
# pathes, AMD64 and EM64T, reorder loads in essentially same manner
# as my IA-64 implementation. On Opteron this resulted in modest 5%
# improvement [I had to test it], while final Intel P4 performance
# achieves respectful 432MBps on 2.8GHz processor now. For reference.
@@ -99,9 +92,6 @@
# Westmere 4.2/+60%
# Sandy Bridge 4.2/+120%
# Atom 9.3/+80%
# VIA Nano 6.4/+4%
# Ivy Bridge 4.1/+30%
# Bulldozer 4.5/+30%(*)
#
# (*) But corresponding loop has less instructions, which should have
# positive effect on upcoming Bulldozer, which has one less ALU.
@@ -122,7 +112,7 @@ $0 =~ m/(.*[\/\\])[^\/\\]+$/; $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;
$dat="%rdi"; # arg1
@@ -440,10 +430,10 @@ $idx="%r8";
$ido="%r9";
$code.=<<___;
.globl RC4_set_key
.type RC4_set_key,\@function,3
.globl private_RC4_set_key
.type private_RC4_set_key,\@function,3
.align 16
RC4_set_key:
private_RC4_set_key:
lea 8($dat),$dat
lea ($inp,$len),$inp
neg $len
@@ -510,7 +500,7 @@ RC4_set_key:
mov %eax,-8($dat)
mov %eax,-4($dat)
ret
.size RC4_set_key,.-RC4_set_key
.size private_RC4_set_key,.-private_RC4_set_key
.globl RC4_options
.type RC4_options,\@abi-omnipotent
@@ -655,16 +645,16 @@ key_se_handler:
.rva .LSEH_end_RC4
.rva .LSEH_info_RC4
.rva .LSEH_begin_RC4_set_key
.rva .LSEH_end_RC4_set_key
.rva .LSEH_info_RC4_set_key
.rva .LSEH_begin_private_RC4_set_key
.rva .LSEH_end_private_RC4_set_key
.rva .LSEH_info_private_RC4_set_key
.section .xdata
.align 8
.LSEH_info_RC4:
.byte 9,0,0,0
.rva stream_se_handler
.LSEH_info_RC4_set_key:
.LSEH_info_private_RC4_set_key:
.byte 9,0,0,0
.rva key_se_handler
___