abc/GmSSL
1
0
Fork 0
mirror of https://github.com/guanzhi/GmSSL.git synced 2026-06-13 08:23:50 +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

31
crypto/bn/asm/sparcv9a-mont.pl
View File

@@ -1,4 +1,11 @@
#!/usr/bin/env perl
#! /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
# ====================================================================
# Written by Andy Polyakov <appro@fy.chalmers.se> for the OpenSSL
@@ -51,21 +58,17 @@
#
# Modulo-scheduled inner loops allow to interleave floating point and
# integer instructions and minimize Read-After-Write penalties. This
# results in *further* 20-50% perfromance improvement [depending on
# results in *further* 20-50% performance improvement [depending on
# key length, more for longer keys] on USI&II cores and 30-80% - on
# USIII&IV.
$fname="bn_mul_mont_fpu";
$bits=32;
for (@ARGV) { $bits=64 if (/\-m64/ || /\-xarch\=v9/); }
$output = pop;
open STDOUT,">$output";
if ($bits==64) {
$bias=2047;
$frame=192;
} else {
$bias=0;
$frame=128; # 96 rounded up to largest known cache-line
}
$fname="bn_mul_mont_fpu";
$frame="STACK_FRAME";
$bias="STACK_BIAS";
$locals=64;
# In order to provide for 32-/64-bit ABI duality, I keep integers wider
@@ -121,6 +124,8 @@ $nhia="%f56"; $nhib="%f58"; $nhic="%f60"; $nhid="%f62";
$ASI_FL16_P=0xD2; # magic ASI value to engage 16-bit FP load
$code=<<___;
#include "sparc_arch.h"
.section ".text",#alloc,#execinstr
.global $fname
@@ -867,7 +872,7 @@ ___
$code =~ s/\`([^\`]*)\`/eval($1)/gem;
# Below substitution makes it possible to compile without demanding
# VIS extentions on command line, e.g. -xarch=v9 vs. -xarch=v9a. I
# VIS extensions on command line, e.g. -xarch=v9 vs. -xarch=v9a. I
# dare to do this, because VIS capability is detected at run-time now
# and this routine is not called on CPU not capable to execute it. Do
# note that fzeros is not the only VIS dependency! Another dependency