2016-05-21 12:23:39 +00:00
|
|
|
|
#! /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
|
|
|
|
|
|
2005-10-09 09:53:58 +00:00
|
|
|
|
|
|
|
|
|
# ====================================================================
|
|
|
|
|
# Written by Andy Polyakov <appro@fy.chalmers.se> for the OpenSSL
|
2006-11-27 14:59:35 +00:00
|
|
|
|
# project. The module is, however, dual licensed under OpenSSL and
|
|
|
|
|
# CRYPTOGAMS licenses depending on where you obtain it. For further
|
|
|
|
|
# details see http://www.openssl.org/~appro/cryptogams/.
|
2005-10-09 09:53:58 +00:00
|
|
|
|
# ====================================================================
|
|
|
|
|
|
2005-10-09 10:26:56 +00:00
|
|
|
|
# October 2005
|
|
|
|
|
#
|
2005-10-09 09:53:58 +00:00
|
|
|
|
# This is a "teaser" code, as it can be improved in several ways...
|
|
|
|
|
# First of all non-SSE2 path should be implemented (yes, for now it
|
|
|
|
|
# performs Montgomery multiplication/convolution only on SSE2-capable
|
|
|
|
|
# CPUs such as P4, others fall down to original code). Then inner loop
|
|
|
|
|
# can be unrolled and modulo-scheduled to improve ILP and possibly
|
|
|
|
|
# moved to 128-bit XMM register bank (though it would require input
|
|
|
|
|
# rearrangement and/or increase bus bandwidth utilization). Dedicated
|
|
|
|
|
# squaring procedure should give further performance improvement...
|
|
|
|
|
# Yet, for being draft, the code improves rsa512 *sign* benchmark by
|
|
|
|
|
# 110%(!), rsa1024 one - by 70% and rsa4096 - by 20%:-)
|
|
|
|
|
|
2006-12-22 15:28:07 +00:00
|
|
|
|
# December 2006
|
|
|
|
|
#
|
|
|
|
|
# Modulo-scheduling SSE2 loops results in further 15-20% improvement.
|
|
|
|
|
# Integer-only code [being equipped with dedicated squaring procedure]
|
2006-12-28 12:43:16 +00:00
|
|
|
|
# gives ~40% on rsa512 sign benchmark...
|
2006-12-22 15:28:07 +00:00
|
|
|
|
|
|
|
|
|
$0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1;
|
|
|
|
|
push(@INC,"${dir}","${dir}../../perlasm");
|
2005-10-09 09:53:58 +00:00
|
|
|
|
require "x86asm.pl";
|
|
|
|
|
|
2016-03-07 14:41:33 +00:00
|
|
|
|
$output = pop;
|
|
|
|
|
open STDOUT,">$output";
|
2016-10-10 16:01:24 +00:00
|
|
|
|
|
2005-10-09 09:53:58 +00:00
|
|
|
|
&asm_init($ARGV[0],$0);
|
|
|
|
|
|
|
|
|
|
$sse2=0;
|
|
|
|
|
for (@ARGV) { $sse2=1 if (/-DOPENSSL_IA32_SSE2/); }
|
|
|
|
|
|
|
|
|
|
&external_label("OPENSSL_ia32cap_P") if ($sse2);
|
|
|
|
|
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&function_begin("bn_mul_mont");
|
2005-10-09 09:53:58 +00:00
|
|
|
|
|
2006-11-27 14:59:35 +00:00
|
|
|
|
$i="edx";
|
2005-10-09 09:53:58 +00:00
|
|
|
|
$j="ecx";
|
2007-06-17 17:10:03 +00:00
|
|
|
|
$ap="esi"; $tp="esi"; # overlapping variables!!!
|
2005-10-09 09:53:58 +00:00
|
|
|
|
$rp="edi"; $bp="edi"; # overlapping variables!!!
|
2006-11-27 14:59:35 +00:00
|
|
|
|
$np="ebp";
|
|
|
|
|
$num="ebx";
|
2005-10-09 09:53:58 +00:00
|
|
|
|
|
2006-12-28 12:43:16 +00:00
|
|
|
|
$_num=&DWP(4*0,"esp"); # stack top layout
|
|
|
|
|
$_rp=&DWP(4*1,"esp");
|
|
|
|
|
$_ap=&DWP(4*2,"esp");
|
|
|
|
|
$_bp=&DWP(4*3,"esp");
|
|
|
|
|
$_np=&DWP(4*4,"esp");
|
2007-03-20 08:55:58 +00:00
|
|
|
|
$_n0=&DWP(4*5,"esp"); $_n0q=&QWP(4*5,"esp");
|
2005-10-14 16:05:21 +00:00
|
|
|
|
$_sp=&DWP(4*6,"esp");
|
2006-11-27 14:59:35 +00:00
|
|
|
|
$_bpend=&DWP(4*7,"esp");
|
2005-10-14 16:05:21 +00:00
|
|
|
|
$frame=32; # size of above frame rounded up to 16n
|
2005-10-09 09:53:58 +00:00
|
|
|
|
|
2006-11-27 14:59:35 +00:00
|
|
|
|
&xor ("eax","eax");
|
|
|
|
|
&mov ("edi",&wparam(5)); # int num
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&cmp ("edi",4);
|
|
|
|
|
&jl (&label("just_leave"));
|
2005-10-09 09:53:58 +00:00
|
|
|
|
|
2006-12-28 12:43:16 +00:00
|
|
|
|
&lea ("esi",&wparam(0)); # put aside pointer to argument block
|
|
|
|
|
&lea ("edx",&wparam(1)); # load ap
|
2006-11-27 14:59:35 +00:00
|
|
|
|
&add ("edi",2); # extra two words on top of tp
|
|
|
|
|
&neg ("edi");
|
2016-03-16 22:33:53 +00:00
|
|
|
|
&lea ("ebp",&DWP(-$frame,"esp","edi",4)); # future alloca($frame+4*(num+2))
|
2006-11-27 14:59:35 +00:00
|
|
|
|
&neg ("edi");
|
2006-12-28 12:43:16 +00:00
|
|
|
|
|
|
|
|
|
# minimize cache contention by arraning 2K window between stack
|
|
|
|
|
# pointer and ap argument [np is also position sensitive vector,
|
|
|
|
|
# but it's assumed to be near ap, as it's allocated at ~same
|
|
|
|
|
# time].
|
2016-03-16 22:33:53 +00:00
|
|
|
|
&mov ("eax","ebp");
|
2006-12-28 12:43:16 +00:00
|
|
|
|
&sub ("eax","edx");
|
|
|
|
|
&and ("eax",2047);
|
2016-03-16 22:33:53 +00:00
|
|
|
|
&sub ("ebp","eax"); # this aligns sp and ap modulo 2048
|
2006-12-28 12:43:16 +00:00
|
|
|
|
|
2016-03-16 22:33:53 +00:00
|
|
|
|
&xor ("edx","ebp");
|
2006-12-28 12:43:16 +00:00
|
|
|
|
&and ("edx",2048);
|
|
|
|
|
&xor ("edx",2048);
|
2016-03-16 22:33:53 +00:00
|
|
|
|
&sub ("ebp","edx"); # this splits them apart modulo 4096
|
2006-12-28 12:43:16 +00:00
|
|
|
|
|
2016-03-16 22:33:53 +00:00
|
|
|
|
&and ("ebp",-64); # align to cache line
|
2006-12-28 12:43:16 +00:00
|
|
|
|
|
2016-03-15 22:04:14 +00:00
|
|
|
|
# An OS-agnostic version of __chkstk.
|
|
|
|
|
#
|
2016-03-15 20:52:31 +00:00
|
|
|
|
# Some OSes (Windows) insist on stack being "wired" to
|
2016-03-04 10:39:11 +00:00
|
|
|
|
# physical memory in strictly sequential manner, i.e. if stack
|
|
|
|
|
# allocation spans two pages, then reference to farmost one can
|
|
|
|
|
# be punishable by SEGV. But page walking can do good even on
|
|
|
|
|
# other OSes, because it guarantees that villain thread hits
|
|
|
|
|
# the guard page before it can make damage to innocent one...
|
2016-03-16 22:33:53 +00:00
|
|
|
|
&mov ("eax","esp");
|
|
|
|
|
&sub ("eax","ebp");
|
2016-03-04 10:39:11 +00:00
|
|
|
|
&and ("eax",-4096);
|
2016-03-16 22:33:53 +00:00
|
|
|
|
&mov ("edx","esp"); # saved stack pointer!
|
|
|
|
|
&lea ("esp",&DWP(0,"ebp","eax"));
|
|
|
|
|
&mov ("eax",&DWP(0,"esp"));
|
|
|
|
|
&cmp ("esp","ebp");
|
|
|
|
|
&ja (&label("page_walk"));
|
|
|
|
|
&jmp (&label("page_walk_done"));
|
|
|
|
|
|
|
|
|
|
&set_label("page_walk",16);
|
|
|
|
|
&lea ("esp",&DWP(-4096,"esp"));
|
|
|
|
|
&mov ("eax",&DWP(0,"esp"));
|
|
|
|
|
&cmp ("esp","ebp");
|
|
|
|
|
&ja (&label("page_walk"));
|
|
|
|
|
&set_label("page_walk_done");
|
2016-03-04 10:39:11 +00:00
|
|
|
|
|
2006-12-28 12:43:16 +00:00
|
|
|
|
################################# load argument block...
|
|
|
|
|
&mov ("eax",&DWP(0*4,"esi"));# BN_ULONG *rp
|
|
|
|
|
&mov ("ebx",&DWP(1*4,"esi"));# const BN_ULONG *ap
|
|
|
|
|
&mov ("ecx",&DWP(2*4,"esi"));# const BN_ULONG *bp
|
2016-03-16 22:33:53 +00:00
|
|
|
|
&mov ("ebp",&DWP(3*4,"esi"));# const BN_ULONG *np
|
2006-12-28 12:43:16 +00:00
|
|
|
|
&mov ("esi",&DWP(4*4,"esi"));# const BN_ULONG *n0
|
|
|
|
|
#&mov ("edi",&DWP(5*4,"esi"));# int num
|
2005-10-09 09:53:58 +00:00
|
|
|
|
|
2005-10-22 17:57:18 +00:00
|
|
|
|
&mov ("esi",&DWP(0,"esi")); # pull n0[0]
|
2005-10-09 09:53:58 +00:00
|
|
|
|
&mov ($_rp,"eax"); # ... save a copy of argument block
|
|
|
|
|
&mov ($_ap,"ebx");
|
|
|
|
|
&mov ($_bp,"ecx");
|
2016-03-16 22:33:53 +00:00
|
|
|
|
&mov ($_np,"ebp");
|
2005-10-09 09:53:58 +00:00
|
|
|
|
&mov ($_n0,"esi");
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&lea ($num,&DWP(-3,"edi")); # num=num-1 to assist modulo-scheduling
|
2006-11-27 14:59:35 +00:00
|
|
|
|
#&mov ($_num,$num); # redundant as $num is not reused
|
2016-03-16 22:33:53 +00:00
|
|
|
|
&mov ($_sp,"edx"); # saved stack pointer!
|
2006-12-22 15:28:07 +00:00
|
|
|
|
|
2006-11-27 14:59:35 +00:00
|
|
|
|
if($sse2) {
|
|
|
|
|
$acc0="mm0"; # mmx register bank layout
|
|
|
|
|
$acc1="mm1";
|
|
|
|
|
$car0="mm2";
|
|
|
|
|
$car1="mm3";
|
|
|
|
|
$mul0="mm4";
|
|
|
|
|
$mul1="mm5";
|
|
|
|
|
$temp="mm6";
|
|
|
|
|
$mask="mm7";
|
|
|
|
|
|
|
|
|
|
&picmeup("eax","OPENSSL_ia32cap_P");
|
|
|
|
|
&bt (&DWP(0,"eax"),26);
|
|
|
|
|
&jnc (&label("non_sse2"));
|
2005-10-09 09:53:58 +00:00
|
|
|
|
|
|
|
|
|
&mov ("eax",-1);
|
|
|
|
|
&movd ($mask,"eax"); # mask 32 lower bits
|
|
|
|
|
|
|
|
|
|
&mov ($ap,$_ap); # load input pointers
|
|
|
|
|
&mov ($bp,$_bp);
|
|
|
|
|
&mov ($np,$_np);
|
|
|
|
|
|
|
|
|
|
&xor ($i,$i); # i=0
|
|
|
|
|
&xor ($j,$j); # j=0
|
|
|
|
|
|
|
|
|
|
&movd ($mul0,&DWP(0,$bp)); # bp[0]
|
|
|
|
|
&movd ($mul1,&DWP(0,$ap)); # ap[0]
|
|
|
|
|
&movd ($car1,&DWP(0,$np)); # np[0]
|
|
|
|
|
|
|
|
|
|
&pmuludq($mul1,$mul0); # ap[0]*bp[0]
|
|
|
|
|
&movq ($car0,$mul1);
|
|
|
|
|
&movq ($acc0,$mul1); # I wish movd worked for
|
|
|
|
|
&pand ($acc0,$mask); # inter-register transfers
|
|
|
|
|
|
2007-03-20 08:55:58 +00:00
|
|
|
|
&pmuludq($mul1,$_n0q); # *=n0
|
2005-10-09 09:53:58 +00:00
|
|
|
|
|
|
|
|
|
&pmuludq($car1,$mul1); # "t[0]"*np[0]*n0
|
|
|
|
|
&paddq ($car1,$acc0);
|
|
|
|
|
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&movd ($acc1,&DWP(4,$np)); # np[1]
|
|
|
|
|
&movd ($acc0,&DWP(4,$ap)); # ap[1]
|
|
|
|
|
|
2005-10-09 09:53:58 +00:00
|
|
|
|
&psrlq ($car0,32);
|
|
|
|
|
&psrlq ($car1,32);
|
|
|
|
|
|
|
|
|
|
&inc ($j); # j++
|
2006-12-28 12:43:16 +00:00
|
|
|
|
&set_label("1st",16);
|
2005-10-09 09:53:58 +00:00
|
|
|
|
&pmuludq($acc0,$mul0); # ap[j]*bp[0]
|
|
|
|
|
&pmuludq($acc1,$mul1); # np[j]*m1
|
|
|
|
|
&paddq ($car0,$acc0); # +=c0
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&paddq ($car1,$acc1); # +=c1
|
|
|
|
|
|
2005-10-09 09:53:58 +00:00
|
|
|
|
&movq ($acc0,$car0);
|
|
|
|
|
&pand ($acc0,$mask);
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&movd ($acc1,&DWP(4,$np,$j,4)); # np[j+1]
|
2005-10-09 09:53:58 +00:00
|
|
|
|
&paddq ($car1,$acc0); # +=ap[j]*bp[0];
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&movd ($acc0,&DWP(4,$ap,$j,4)); # ap[j+1]
|
2005-10-09 09:53:58 +00:00
|
|
|
|
&psrlq ($car0,32);
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&movd (&DWP($frame-4,"esp",$j,4),$car1); # tp[j-1]=
|
2005-10-09 09:53:58 +00:00
|
|
|
|
&psrlq ($car1,32);
|
|
|
|
|
|
|
|
|
|
&lea ($j,&DWP(1,$j));
|
|
|
|
|
&cmp ($j,$num);
|
|
|
|
|
&jl (&label("1st"));
|
|
|
|
|
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&pmuludq($acc0,$mul0); # ap[num-1]*bp[0]
|
|
|
|
|
&pmuludq($acc1,$mul1); # np[num-1]*m1
|
|
|
|
|
&paddq ($car0,$acc0); # +=c0
|
|
|
|
|
&paddq ($car1,$acc1); # +=c1
|
2005-10-09 09:53:58 +00:00
|
|
|
|
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&movq ($acc0,$car0);
|
|
|
|
|
&pand ($acc0,$mask);
|
|
|
|
|
&paddq ($car1,$acc0); # +=ap[num-1]*bp[0];
|
|
|
|
|
&movd (&DWP($frame-4,"esp",$j,4),$car1); # tp[num-2]=
|
|
|
|
|
|
|
|
|
|
&psrlq ($car0,32);
|
|
|
|
|
&psrlq ($car1,32);
|
|
|
|
|
|
|
|
|
|
&paddq ($car1,$car0);
|
2007-03-20 08:55:58 +00:00
|
|
|
|
&movq (&QWP($frame,"esp",$num,4),$car1); # tp[num].tp[num-1]
|
2006-12-22 15:28:07 +00:00
|
|
|
|
|
2005-10-09 09:53:58 +00:00
|
|
|
|
&inc ($i); # i++
|
|
|
|
|
&set_label("outer");
|
|
|
|
|
&xor ($j,$j); # j=0
|
|
|
|
|
|
|
|
|
|
&movd ($mul0,&DWP(0,$bp,$i,4)); # bp[i]
|
|
|
|
|
&movd ($mul1,&DWP(0,$ap)); # ap[0]
|
2005-10-14 16:05:21 +00:00
|
|
|
|
&movd ($temp,&DWP($frame,"esp")); # tp[0]
|
|
|
|
|
&movd ($car1,&DWP(0,$np)); # np[0]
|
2005-10-09 09:53:58 +00:00
|
|
|
|
&pmuludq($mul1,$mul0); # ap[0]*bp[i]
|
|
|
|
|
|
|
|
|
|
&paddq ($mul1,$temp); # +=tp[0]
|
|
|
|
|
&movq ($acc0,$mul1);
|
|
|
|
|
&movq ($car0,$mul1);
|
|
|
|
|
&pand ($acc0,$mask);
|
|
|
|
|
|
2007-03-20 08:55:58 +00:00
|
|
|
|
&pmuludq($mul1,$_n0q); # *=n0
|
2005-10-09 09:53:58 +00:00
|
|
|
|
|
|
|
|
|
&pmuludq($car1,$mul1);
|
|
|
|
|
&paddq ($car1,$acc0);
|
|
|
|
|
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&movd ($temp,&DWP($frame+4,"esp")); # tp[1]
|
|
|
|
|
&movd ($acc1,&DWP(4,$np)); # np[1]
|
|
|
|
|
&movd ($acc0,&DWP(4,$ap)); # ap[1]
|
|
|
|
|
|
2005-10-09 09:53:58 +00:00
|
|
|
|
&psrlq ($car0,32);
|
|
|
|
|
&psrlq ($car1,32);
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&paddq ($car0,$temp); # +=tp[1]
|
2005-10-09 09:53:58 +00:00
|
|
|
|
|
|
|
|
|
&inc ($j); # j++
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&dec ($num);
|
2005-10-09 09:53:58 +00:00
|
|
|
|
&set_label("inner");
|
|
|
|
|
&pmuludq($acc0,$mul0); # ap[j]*bp[i]
|
|
|
|
|
&pmuludq($acc1,$mul1); # np[j]*m1
|
|
|
|
|
&paddq ($car0,$acc0); # +=c0
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&paddq ($car1,$acc1); # +=c1
|
|
|
|
|
|
2005-10-09 09:53:58 +00:00
|
|
|
|
&movq ($acc0,$car0);
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&movd ($temp,&DWP($frame+4,"esp",$j,4));# tp[j+1]
|
2005-10-09 09:53:58 +00:00
|
|
|
|
&pand ($acc0,$mask);
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&movd ($acc1,&DWP(4,$np,$j,4)); # np[j+1]
|
2005-10-09 09:53:58 +00:00
|
|
|
|
&paddq ($car1,$acc0); # +=ap[j]*bp[i]+tp[j]
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&movd ($acc0,&DWP(4,$ap,$j,4)); # ap[j+1]
|
2005-10-09 09:53:58 +00:00
|
|
|
|
&psrlq ($car0,32);
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&movd (&DWP($frame-4,"esp",$j,4),$car1);# tp[j-1]=
|
2005-10-09 09:53:58 +00:00
|
|
|
|
&psrlq ($car1,32);
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&paddq ($car0,$temp); # +=tp[j+1]
|
2005-10-09 09:53:58 +00:00
|
|
|
|
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&dec ($num);
|
2005-10-09 09:53:58 +00:00
|
|
|
|
&lea ($j,&DWP(1,$j)); # j++
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&jnz (&label("inner"));
|
|
|
|
|
|
|
|
|
|
&mov ($num,$j);
|
|
|
|
|
&pmuludq($acc0,$mul0); # ap[num-1]*bp[i]
|
|
|
|
|
&pmuludq($acc1,$mul1); # np[num-1]*m1
|
|
|
|
|
&paddq ($car0,$acc0); # +=c0
|
|
|
|
|
&paddq ($car1,$acc1); # +=c1
|
|
|
|
|
|
|
|
|
|
&movq ($acc0,$car0);
|
|
|
|
|
&pand ($acc0,$mask);
|
|
|
|
|
&paddq ($car1,$acc0); # +=ap[num-1]*bp[i]+tp[num-1]
|
|
|
|
|
&movd (&DWP($frame-4,"esp",$j,4),$car1); # tp[num-2]=
|
|
|
|
|
&psrlq ($car0,32);
|
|
|
|
|
&psrlq ($car1,32);
|
2005-10-09 09:53:58 +00:00
|
|
|
|
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&movd ($temp,&DWP($frame+4,"esp",$num,4)); # += tp[num]
|
2005-10-09 09:53:58 +00:00
|
|
|
|
&paddq ($car1,$car0);
|
|
|
|
|
&paddq ($car1,$temp);
|
2007-03-20 08:55:58 +00:00
|
|
|
|
&movq (&QWP($frame,"esp",$num,4),$car1); # tp[num].tp[num-1]
|
2005-10-09 09:53:58 +00:00
|
|
|
|
|
|
|
|
|
&lea ($i,&DWP(1,$i)); # i++
|
|
|
|
|
&cmp ($i,$num);
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&jle (&label("outer"));
|
2005-10-09 09:53:58 +00:00
|
|
|
|
|
|
|
|
|
&emms (); # done with mmx bank
|
2006-11-27 14:59:35 +00:00
|
|
|
|
&jmp (&label("common_tail"));
|
|
|
|
|
|
|
|
|
|
&set_label("non_sse2",16);
|
|
|
|
|
}
|
2006-12-22 15:28:07 +00:00
|
|
|
|
|
|
|
|
|
if (0) {
|
2006-11-27 14:59:35 +00:00
|
|
|
|
&mov ("esp",$_sp);
|
|
|
|
|
&xor ("eax","eax"); # signal "not fast enough [yet]"
|
|
|
|
|
&jmp (&label("just_leave"));
|
2006-12-22 15:28:07 +00:00
|
|
|
|
# While the below code provides competitive performance for
|
2016-08-05 17:56:58 +00:00
|
|
|
|
# all key lengths on modern Intel cores, it's still more
|
2006-12-28 12:43:16 +00:00
|
|
|
|
# than 10% slower for 4096-bit key elsewhere:-( "Competitive"
|
|
|
|
|
# means compared to the original integer-only assembler.
|
|
|
|
|
# 512-bit RSA sign is better by ~40%, but that's about all
|
|
|
|
|
# one can say about all CPUs...
|
2006-11-27 14:59:35 +00:00
|
|
|
|
} else {
|
|
|
|
|
$inp="esi"; # integer path uses these registers differently
|
|
|
|
|
$word="edi";
|
|
|
|
|
$carry="ebp";
|
|
|
|
|
|
|
|
|
|
&mov ($inp,$_ap);
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&lea ($carry,&DWP(1,$num));
|
2006-11-27 14:59:35 +00:00
|
|
|
|
&mov ($word,$_bp);
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&xor ($j,$j); # j=0
|
|
|
|
|
&mov ("edx",$inp);
|
|
|
|
|
&and ($carry,1); # see if num is even
|
|
|
|
|
&sub ("edx",$word); # see if ap==bp
|
2006-11-27 14:59:35 +00:00
|
|
|
|
&lea ("eax",&DWP(4,$word,$num,4)); # &bp[num]
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&or ($carry,"edx");
|
2006-11-27 14:59:35 +00:00
|
|
|
|
&mov ($word,&DWP(0,$word)); # bp[0]
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&jz (&label("bn_sqr_mont"));
|
2006-11-27 14:59:35 +00:00
|
|
|
|
&mov ($_bpend,"eax");
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&mov ("eax",&DWP(0,$inp));
|
2006-11-27 14:59:35 +00:00
|
|
|
|
&xor ("edx","edx");
|
|
|
|
|
|
|
|
|
|
&set_label("mull",16);
|
|
|
|
|
&mov ($carry,"edx");
|
|
|
|
|
&mul ($word); # ap[j]*bp[0]
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&add ($carry,"eax");
|
2006-11-27 14:59:35 +00:00
|
|
|
|
&lea ($j,&DWP(1,$j));
|
|
|
|
|
&adc ("edx",0);
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&mov ("eax",&DWP(0,$inp,$j,4)); # ap[j+1]
|
2006-11-27 14:59:35 +00:00
|
|
|
|
&cmp ($j,$num);
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&mov (&DWP($frame-4,"esp",$j,4),$carry); # tp[j]=
|
|
|
|
|
&jl (&label("mull"));
|
2006-11-27 14:59:35 +00:00
|
|
|
|
|
|
|
|
|
&mov ($carry,"edx");
|
|
|
|
|
&mul ($word); # ap[num-1]*bp[0]
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&mov ($word,$_n0);
|
2006-11-27 14:59:35 +00:00
|
|
|
|
&add ("eax",$carry);
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&mov ($inp,$_np);
|
2006-11-27 14:59:35 +00:00
|
|
|
|
&adc ("edx",0);
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&imul ($word,&DWP($frame,"esp")); # n0*tp[0]
|
2006-11-27 14:59:35 +00:00
|
|
|
|
|
|
|
|
|
&mov (&DWP($frame,"esp",$num,4),"eax"); # tp[num-1]=
|
|
|
|
|
&xor ($j,$j);
|
|
|
|
|
&mov (&DWP($frame+4,"esp",$num,4),"edx"); # tp[num]=
|
|
|
|
|
&mov (&DWP($frame+8,"esp",$num,4),$j); # tp[num+1]=
|
|
|
|
|
|
|
|
|
|
&mov ("eax",&DWP(0,$inp)); # np[0]
|
|
|
|
|
&mul ($word); # np[0]*m
|
|
|
|
|
&add ("eax",&DWP($frame,"esp")); # +=tp[0]
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&mov ("eax",&DWP(4,$inp)); # np[1]
|
2006-11-27 14:59:35 +00:00
|
|
|
|
&adc ("edx",0);
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&inc ($j);
|
2006-11-27 14:59:35 +00:00
|
|
|
|
|
|
|
|
|
&jmp (&label("2ndmadd"));
|
2006-12-22 15:28:07 +00:00
|
|
|
|
|
2006-11-27 14:59:35 +00:00
|
|
|
|
&set_label("1stmadd",16);
|
|
|
|
|
&mov ($carry,"edx");
|
|
|
|
|
&mul ($word); # ap[j]*bp[i]
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&add ($carry,&DWP($frame,"esp",$j,4)); # +=tp[j]
|
2006-11-27 14:59:35 +00:00
|
|
|
|
&lea ($j,&DWP(1,$j));
|
|
|
|
|
&adc ("edx",0);
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&add ($carry,"eax");
|
|
|
|
|
&mov ("eax",&DWP(0,$inp,$j,4)); # ap[j+1]
|
2006-11-27 14:59:35 +00:00
|
|
|
|
&adc ("edx",0);
|
|
|
|
|
&cmp ($j,$num);
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&mov (&DWP($frame-4,"esp",$j,4),$carry); # tp[j]=
|
|
|
|
|
&jl (&label("1stmadd"));
|
2006-11-27 14:59:35 +00:00
|
|
|
|
|
|
|
|
|
&mov ($carry,"edx");
|
|
|
|
|
&mul ($word); # ap[num-1]*bp[i]
|
|
|
|
|
&add ("eax",&DWP($frame,"esp",$num,4)); # +=tp[num-1]
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&mov ($word,$_n0);
|
2006-11-27 14:59:35 +00:00
|
|
|
|
&adc ("edx",0);
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&mov ($inp,$_np);
|
|
|
|
|
&add ($carry,"eax");
|
2006-11-27 14:59:35 +00:00
|
|
|
|
&adc ("edx",0);
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&imul ($word,&DWP($frame,"esp")); # n0*tp[0]
|
2006-11-27 14:59:35 +00:00
|
|
|
|
|
|
|
|
|
&xor ($j,$j);
|
|
|
|
|
&add ("edx",&DWP($frame+4,"esp",$num,4)); # carry+=tp[num]
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&mov (&DWP($frame,"esp",$num,4),$carry); # tp[num-1]=
|
2006-11-27 14:59:35 +00:00
|
|
|
|
&adc ($j,0);
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&mov ("eax",&DWP(0,$inp)); # np[0]
|
2006-11-27 14:59:35 +00:00
|
|
|
|
&mov (&DWP($frame+4,"esp",$num,4),"edx"); # tp[num]=
|
|
|
|
|
&mov (&DWP($frame+8,"esp",$num,4),$j); # tp[num+1]=
|
|
|
|
|
|
|
|
|
|
&mul ($word); # np[0]*m
|
|
|
|
|
&add ("eax",&DWP($frame,"esp")); # +=tp[0]
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&mov ("eax",&DWP(4,$inp)); # np[1]
|
2006-11-27 14:59:35 +00:00
|
|
|
|
&adc ("edx",0);
|
|
|
|
|
&mov ($j,1);
|
2006-12-22 15:28:07 +00:00
|
|
|
|
|
2006-11-27 14:59:35 +00:00
|
|
|
|
&set_label("2ndmadd",16);
|
|
|
|
|
&mov ($carry,"edx");
|
|
|
|
|
&mul ($word); # np[j]*m
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&add ($carry,&DWP($frame,"esp",$j,4)); # +=tp[j]
|
2006-11-27 14:59:35 +00:00
|
|
|
|
&lea ($j,&DWP(1,$j));
|
|
|
|
|
&adc ("edx",0);
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&add ($carry,"eax");
|
|
|
|
|
&mov ("eax",&DWP(0,$inp,$j,4)); # np[j+1]
|
2006-11-27 14:59:35 +00:00
|
|
|
|
&adc ("edx",0);
|
|
|
|
|
&cmp ($j,$num);
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&mov (&DWP($frame-8,"esp",$j,4),$carry); # tp[j-1]=
|
|
|
|
|
&jl (&label("2ndmadd"));
|
2006-11-27 14:59:35 +00:00
|
|
|
|
|
|
|
|
|
&mov ($carry,"edx");
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&mul ($word); # np[j]*m
|
2006-12-27 10:59:51 +00:00
|
|
|
|
&add ($carry,&DWP($frame,"esp",$num,4)); # +=tp[num-1]
|
2006-11-27 14:59:35 +00:00
|
|
|
|
&adc ("edx",0);
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&add ($carry,"eax");
|
2006-11-27 14:59:35 +00:00
|
|
|
|
&adc ("edx",0);
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&mov (&DWP($frame-4,"esp",$num,4),$carry); # tp[num-2]=
|
2006-11-27 14:59:35 +00:00
|
|
|
|
|
|
|
|
|
&xor ("eax","eax");
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&mov ($j,$_bp); # &bp[i]
|
2006-11-27 14:59:35 +00:00
|
|
|
|
&add ("edx",&DWP($frame+4,"esp",$num,4)); # carry+=tp[num]
|
|
|
|
|
&adc ("eax",&DWP($frame+8,"esp",$num,4)); # +=tp[num+1]
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&lea ($j,&DWP(4,$j));
|
2006-11-27 14:59:35 +00:00
|
|
|
|
&mov (&DWP($frame,"esp",$num,4),"edx"); # tp[num-1]=
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&cmp ($j,$_bpend);
|
2006-11-27 14:59:35 +00:00
|
|
|
|
&mov (&DWP($frame+4,"esp",$num,4),"eax"); # tp[num]=
|
2006-12-27 10:59:51 +00:00
|
|
|
|
&je (&label("common_tail"));
|
2006-12-22 15:28:07 +00:00
|
|
|
|
|
2006-12-27 10:59:51 +00:00
|
|
|
|
&mov ($word,&DWP(0,$j)); # bp[i+1]
|
2006-11-27 14:59:35 +00:00
|
|
|
|
&mov ($inp,$_ap);
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&mov ($_bp,$j); # &bp[++i]
|
2006-11-27 14:59:35 +00:00
|
|
|
|
&xor ($j,$j);
|
|
|
|
|
&xor ("edx","edx");
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&mov ("eax",&DWP(0,$inp));
|
2006-11-27 14:59:35 +00:00
|
|
|
|
&jmp (&label("1stmadd"));
|
2006-12-22 15:28:07 +00:00
|
|
|
|
|
|
|
|
|
&set_label("bn_sqr_mont",16);
|
|
|
|
|
$sbit=$num;
|
|
|
|
|
&mov ($_num,$num);
|
|
|
|
|
&mov ($_bp,$j); # i=0
|
|
|
|
|
|
|
|
|
|
&mov ("eax",$word); # ap[0]
|
|
|
|
|
&mul ($word); # ap[0]*ap[0]
|
|
|
|
|
&mov (&DWP($frame,"esp"),"eax"); # tp[0]=
|
|
|
|
|
&mov ($sbit,"edx");
|
|
|
|
|
&shr ("edx",1);
|
|
|
|
|
&and ($sbit,1);
|
|
|
|
|
&inc ($j);
|
|
|
|
|
&set_label("sqr",16);
|
|
|
|
|
&mov ("eax",&DWP(0,$inp,$j,4)); # ap[j]
|
|
|
|
|
&mov ($carry,"edx");
|
|
|
|
|
&mul ($word); # ap[j]*ap[0]
|
|
|
|
|
&add ("eax",$carry);
|
|
|
|
|
&lea ($j,&DWP(1,$j));
|
|
|
|
|
&adc ("edx",0);
|
|
|
|
|
&lea ($carry,&DWP(0,$sbit,"eax",2));
|
|
|
|
|
&shr ("eax",31);
|
|
|
|
|
&cmp ($j,$_num);
|
|
|
|
|
&mov ($sbit,"eax");
|
|
|
|
|
&mov (&DWP($frame-4,"esp",$j,4),$carry); # tp[j]=
|
|
|
|
|
&jl (&label("sqr"));
|
|
|
|
|
|
|
|
|
|
&mov ("eax",&DWP(0,$inp,$j,4)); # ap[num-1]
|
|
|
|
|
&mov ($carry,"edx");
|
|
|
|
|
&mul ($word); # ap[num-1]*ap[0]
|
|
|
|
|
&add ("eax",$carry);
|
|
|
|
|
&mov ($word,$_n0);
|
|
|
|
|
&adc ("edx",0);
|
|
|
|
|
&mov ($inp,$_np);
|
|
|
|
|
&lea ($carry,&DWP(0,$sbit,"eax",2));
|
|
|
|
|
&imul ($word,&DWP($frame,"esp")); # n0*tp[0]
|
|
|
|
|
&shr ("eax",31);
|
|
|
|
|
&mov (&DWP($frame,"esp",$j,4),$carry); # tp[num-1]=
|
|
|
|
|
|
|
|
|
|
&lea ($carry,&DWP(0,"eax","edx",2));
|
|
|
|
|
&mov ("eax",&DWP(0,$inp)); # np[0]
|
|
|
|
|
&shr ("edx",31);
|
|
|
|
|
&mov (&DWP($frame+4,"esp",$j,4),$carry); # tp[num]=
|
|
|
|
|
&mov (&DWP($frame+8,"esp",$j,4),"edx"); # tp[num+1]=
|
|
|
|
|
|
|
|
|
|
&mul ($word); # np[0]*m
|
|
|
|
|
&add ("eax",&DWP($frame,"esp")); # +=tp[0]
|
|
|
|
|
&mov ($num,$j);
|
|
|
|
|
&adc ("edx",0);
|
|
|
|
|
&mov ("eax",&DWP(4,$inp)); # np[1]
|
|
|
|
|
&mov ($j,1);
|
|
|
|
|
|
|
|
|
|
&set_label("3rdmadd",16);
|
|
|
|
|
&mov ($carry,"edx");
|
|
|
|
|
&mul ($word); # np[j]*m
|
|
|
|
|
&add ($carry,&DWP($frame,"esp",$j,4)); # +=tp[j]
|
|
|
|
|
&adc ("edx",0);
|
|
|
|
|
&add ($carry,"eax");
|
|
|
|
|
&mov ("eax",&DWP(4,$inp,$j,4)); # np[j+1]
|
|
|
|
|
&adc ("edx",0);
|
|
|
|
|
&mov (&DWP($frame-4,"esp",$j,4),$carry); # tp[j-1]=
|
|
|
|
|
|
|
|
|
|
&mov ($carry,"edx");
|
|
|
|
|
&mul ($word); # np[j+1]*m
|
|
|
|
|
&add ($carry,&DWP($frame+4,"esp",$j,4)); # +=tp[j+1]
|
|
|
|
|
&lea ($j,&DWP(2,$j));
|
|
|
|
|
&adc ("edx",0);
|
|
|
|
|
&add ($carry,"eax");
|
|
|
|
|
&mov ("eax",&DWP(0,$inp,$j,4)); # np[j+2]
|
|
|
|
|
&adc ("edx",0);
|
|
|
|
|
&cmp ($j,$num);
|
|
|
|
|
&mov (&DWP($frame-8,"esp",$j,4),$carry); # tp[j]=
|
|
|
|
|
&jl (&label("3rdmadd"));
|
|
|
|
|
|
|
|
|
|
&mov ($carry,"edx");
|
|
|
|
|
&mul ($word); # np[j]*m
|
|
|
|
|
&add ($carry,&DWP($frame,"esp",$num,4)); # +=tp[num-1]
|
|
|
|
|
&adc ("edx",0);
|
|
|
|
|
&add ($carry,"eax");
|
|
|
|
|
&adc ("edx",0);
|
|
|
|
|
&mov (&DWP($frame-4,"esp",$num,4),$carry); # tp[num-2]=
|
|
|
|
|
|
|
|
|
|
&mov ($j,$_bp); # i
|
|
|
|
|
&xor ("eax","eax");
|
|
|
|
|
&mov ($inp,$_ap);
|
|
|
|
|
&add ("edx",&DWP($frame+4,"esp",$num,4)); # carry+=tp[num]
|
|
|
|
|
&adc ("eax",&DWP($frame+8,"esp",$num,4)); # +=tp[num+1]
|
|
|
|
|
&mov (&DWP($frame,"esp",$num,4),"edx"); # tp[num-1]=
|
|
|
|
|
&cmp ($j,$num);
|
|
|
|
|
&mov (&DWP($frame+4,"esp",$num,4),"eax"); # tp[num]=
|
2006-12-27 10:59:51 +00:00
|
|
|
|
&je (&label("common_tail"));
|
2006-12-22 15:28:07 +00:00
|
|
|
|
|
|
|
|
|
&mov ($word,&DWP(4,$inp,$j,4)); # ap[i]
|
|
|
|
|
&lea ($j,&DWP(1,$j));
|
|
|
|
|
&mov ("eax",$word);
|
|
|
|
|
&mov ($_bp,$j); # ++i
|
|
|
|
|
&mul ($word); # ap[i]*ap[i]
|
|
|
|
|
&add ("eax",&DWP($frame,"esp",$j,4)); # +=tp[i]
|
|
|
|
|
&adc ("edx",0);
|
|
|
|
|
&mov (&DWP($frame,"esp",$j,4),"eax"); # tp[i]=
|
|
|
|
|
&xor ($carry,$carry);
|
|
|
|
|
&cmp ($j,$num);
|
|
|
|
|
&lea ($j,&DWP(1,$j));
|
|
|
|
|
&je (&label("sqrlast"));
|
2006-11-27 14:59:35 +00:00
|
|
|
|
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&mov ($sbit,"edx"); # zaps $num
|
|
|
|
|
&shr ("edx",1);
|
|
|
|
|
&and ($sbit,1);
|
|
|
|
|
&set_label("sqradd",16);
|
|
|
|
|
&mov ("eax",&DWP(0,$inp,$j,4)); # ap[j]
|
|
|
|
|
&mov ($carry,"edx");
|
|
|
|
|
&mul ($word); # ap[j]*ap[i]
|
|
|
|
|
&add ("eax",$carry);
|
2006-12-28 12:43:16 +00:00
|
|
|
|
&lea ($carry,&DWP(0,"eax","eax"));
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&adc ("edx",0);
|
|
|
|
|
&shr ("eax",31);
|
2006-12-28 12:43:16 +00:00
|
|
|
|
&add ($carry,&DWP($frame,"esp",$j,4)); # +=tp[j]
|
|
|
|
|
&lea ($j,&DWP(1,$j));
|
2006-12-27 10:59:51 +00:00
|
|
|
|
&adc ("eax",0);
|
2006-12-28 12:43:16 +00:00
|
|
|
|
&add ($carry,$sbit);
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&adc ("eax",0);
|
|
|
|
|
&cmp ($j,$_num);
|
|
|
|
|
&mov (&DWP($frame-4,"esp",$j,4),$carry); # tp[j]=
|
|
|
|
|
&mov ($sbit,"eax");
|
|
|
|
|
&jle (&label("sqradd"));
|
|
|
|
|
|
|
|
|
|
&mov ($carry,"edx");
|
2011-12-09 14:21:25 +00:00
|
|
|
|
&add ("edx","edx");
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&shr ($carry,31);
|
2011-12-09 14:21:25 +00:00
|
|
|
|
&add ("edx",$sbit);
|
|
|
|
|
&adc ($carry,0);
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&set_label("sqrlast");
|
|
|
|
|
&mov ($word,$_n0);
|
|
|
|
|
&mov ($inp,$_np);
|
|
|
|
|
&imul ($word,&DWP($frame,"esp")); # n0*tp[0]
|
|
|
|
|
|
|
|
|
|
&add ("edx",&DWP($frame,"esp",$j,4)); # +=tp[num]
|
|
|
|
|
&mov ("eax",&DWP(0,$inp)); # np[0]
|
|
|
|
|
&adc ($carry,0);
|
|
|
|
|
&mov (&DWP($frame,"esp",$j,4),"edx"); # tp[num]=
|
|
|
|
|
&mov (&DWP($frame+4,"esp",$j,4),$carry); # tp[num+1]=
|
|
|
|
|
|
|
|
|
|
&mul ($word); # np[0]*m
|
|
|
|
|
&add ("eax",&DWP($frame,"esp")); # +=tp[0]
|
|
|
|
|
&lea ($num,&DWP(-1,$j));
|
|
|
|
|
&adc ("edx",0);
|
|
|
|
|
&mov ($j,1);
|
|
|
|
|
&mov ("eax",&DWP(4,$inp)); # np[1]
|
|
|
|
|
|
|
|
|
|
&jmp (&label("3rdmadd"));
|
2006-11-27 14:59:35 +00:00
|
|
|
|
}
|
2006-12-27 10:59:51 +00:00
|
|
|
|
|
2006-11-27 14:59:35 +00:00
|
|
|
|
&set_label("common_tail",16);
|
2007-06-17 17:10:03 +00:00
|
|
|
|
&mov ($np,$_np); # load modulus pointer
|
2005-10-09 09:53:58 +00:00
|
|
|
|
&mov ($rp,$_rp); # load result pointer
|
2007-06-17 17:10:03 +00:00
|
|
|
|
&lea ($tp,&DWP($frame,"esp")); # [$ap and $bp are zapped]
|
|
|
|
|
|
|
|
|
|
&mov ("eax",&DWP(0,$tp)); # tp[0]
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&mov ($j,$num); # j=num-1
|
2007-06-17 17:10:03 +00:00
|
|
|
|
&xor ($i,$i); # i=0 and clear CF!
|
2005-10-09 09:53:58 +00:00
|
|
|
|
|
2006-11-27 14:59:35 +00:00
|
|
|
|
&set_label("sub",16);
|
2005-10-09 09:53:58 +00:00
|
|
|
|
&sbb ("eax",&DWP(0,$np,$i,4));
|
|
|
|
|
&mov (&DWP(0,$rp,$i,4),"eax"); # rp[i]=tp[i]-np[i]
|
|
|
|
|
&dec ($j); # doesn't affect CF!
|
2007-06-17 17:10:03 +00:00
|
|
|
|
&mov ("eax",&DWP(4,$tp,$i,4)); # tp[i+1]
|
|
|
|
|
&lea ($i,&DWP(1,$i)); # i++
|
2005-10-09 09:53:58 +00:00
|
|
|
|
&jge (&label("sub"));
|
2007-06-17 17:10:03 +00:00
|
|
|
|
|
|
|
|
|
&sbb ("eax",0); # handle upmost overflow bit
|
|
|
|
|
&and ($tp,"eax");
|
|
|
|
|
¬ ("eax");
|
|
|
|
|
&mov ($np,$rp);
|
|
|
|
|
&and ($np,"eax");
|
|
|
|
|
&or ($tp,$np); # tp=carry?tp:rp
|
|
|
|
|
|
|
|
|
|
&set_label("copy",16); # copy or in-place refresh
|
|
|
|
|
&mov ("eax",&DWP(0,$tp,$num,4));
|
|
|
|
|
&mov (&DWP(0,$rp,$num,4),"eax"); # rp[i]=tp[i]
|
|
|
|
|
&mov (&DWP($frame,"esp",$num,4),$j); # zap temporary vector
|
|
|
|
|
&dec ($num);
|
|
|
|
|
&jge (&label("copy"));
|
|
|
|
|
|
2005-10-09 09:53:58 +00:00
|
|
|
|
&mov ("esp",$_sp); # pull saved stack pointer
|
|
|
|
|
&mov ("eax",1);
|
2006-11-27 14:59:35 +00:00
|
|
|
|
&set_label("just_leave");
|
2005-10-09 09:53:58 +00:00
|
|
|
|
&function_end("bn_mul_mont");
|
|
|
|
|
|
2006-12-22 15:28:07 +00:00
|
|
|
|
&asciz("Montgomery Multiplication for x86, CRYPTOGAMS by <appro\@openssl.org>");
|
|
|
|
|
|
2005-10-09 09:53:58 +00:00
|
|
|
|
&asm_finish();
|
2016-03-07 14:41:33 +00:00
|
|
|
|
|
|
|
|
|
close STDOUT;
|