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

43
crypto/modes/asm/ghashv8-armx.pl
View File

@@ -1,4 +1,11 @@
#!/usr/bin/env perl
#! /usr/bin/env perl
# Copyright 2014-2016 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
@@ -27,11 +34,21 @@
# Apple A7 0.92 5.62
# Cortex-A53 1.01 8.39
# Cortex-A57 1.17 7.61
# Denver 0.71 6.02
# Mongoose 1.10 8.06
#
# (*) presented for reference/comparison purposes;
$flavour = shift;
open STDOUT,">".shift;
$output = shift;
$0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1;
( $xlate="${dir}arm-xlate.pl" and -f $xlate ) or
( $xlate="${dir}../../perlasm/arm-xlate.pl" and -f $xlate) or
die "can't locate arm-xlate.pl";
open OUT,"| \"$^X\" $xlate $flavour $output";
*STDOUT=*OUT;
$Xi="x0"; # argument block
$Htbl="x1";
@@ -135,10 +152,10 @@ gcm_gmult_v8:
#endif
vext.8 $IN,$t1,$t1,#8
vpmull.p64 $Xl,$H,$IN @ H.lo·Xi.lo
vpmull.p64 $Xl,$H,$IN @ H.lo·Xi.lo
veor $t1,$t1,$IN @ Karatsuba pre-processing
vpmull2.p64 $Xh,$H,$IN @ H.hi·Xi.hi
vpmull.p64 $Xm,$Hhl,$t1 @ (H.lo+H.hi)·(Xi.lo+Xi.hi)
vpmull2.p64 $Xh,$H,$IN @ H.hi·Xi.hi
vpmull.p64 $Xm,$Hhl,$t1 @ (H.lo+H.hi)·(Xi.lo+Xi.hi)
vext.8 $t1,$Xl,$Xh,#8 @ Karatsuba post-processing
veor $t2,$Xl,$Xh
@@ -226,7 +243,7 @@ $code.=<<___;
#endif
vext.8 $In,$t1,$t1,#8
veor $IN,$IN,$Xl @ I[i]^=Xi
vpmull.p64 $Xln,$H,$In @ H·Ii+1
vpmull.p64 $Xln,$H,$In @ H·Ii+1
veor $t1,$t1,$In @ Karatsuba pre-processing
vpmull2.p64 $Xhn,$H,$In
b .Loop_mod2x_v8
@@ -235,14 +252,14 @@ $code.=<<___;
.Loop_mod2x_v8:
vext.8 $t2,$IN,$IN,#8
subs $len,$len,#32 @ is there more data?
vpmull.p64 $Xl,$H2,$IN @ H^2.lo·Xi.lo
vpmull.p64 $Xl,$H2,$IN @ H^2.lo·Xi.lo
cclr $inc,lo @ is it time to zero $inc?
vpmull.p64 $Xmn,$Hhl,$t1
veor $t2,$t2,$IN @ Karatsuba pre-processing
vpmull2.p64 $Xh,$H2,$IN @ H^2.hi·Xi.hi
vpmull2.p64 $Xh,$H2,$IN @ H^2.hi·Xi.hi
veor $Xl,$Xl,$Xln @ accumulate
vpmull2.p64 $Xm,$Hhl,$t2 @ (H^2.lo+H^2.hi)·(Xi.lo+Xi.hi)
vpmull2.p64 $Xm,$Hhl,$t2 @ (H^2.lo+H^2.hi)·(Xi.lo+Xi.hi)
vld1.64 {$t0},[$inp],$inc @ load [rotated] I[i+2]
veor $Xh,$Xh,$Xhn
@@ -267,7 +284,7 @@ $code.=<<___;
vext.8 $In,$t1,$t1,#8
vext.8 $IN,$t0,$t0,#8
veor $Xl,$Xm,$t2
vpmull.p64 $Xln,$H,$In @ H·Ii+1
vpmull.p64 $Xln,$H,$In @ H·Ii+1
veor $IN,$IN,$Xh @ accumulate $IN early
vext.8 $t2,$Xl,$Xl,#8 @ 2nd phase of reduction
@@ -291,10 +308,10 @@ $code.=<<___;
veor $IN,$IN,$Xl @ inp^=Xi
veor $t1,$t0,$t2 @ $t1 is rotated inp^Xi
vpmull.p64 $Xl,$H,$IN @ H.lo·Xi.lo
vpmull.p64 $Xl,$H,$IN @ H.lo·Xi.lo
veor $t1,$t1,$IN @ Karatsuba pre-processing
vpmull2.p64 $Xh,$H,$IN @ H.hi·Xi.hi
vpmull.p64 $Xm,$Hhl,$t1 @ (H.lo+H.hi)·(Xi.lo+Xi.hi)
vpmull2.p64 $Xh,$H,$IN @ H.hi·Xi.hi
vpmull.p64 $Xm,$Hhl,$t1 @ (H.lo+H.hi)·(Xi.lo+Xi.hi)
vext.8 $t1,$Xl,$Xh,#8 @ Karatsuba post-processing
veor $t2,$Xl,$Xh