Merge remote-tracking branch 'origin/master'

# 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

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
@@ -13,7 +20,7 @@
# for undertaken effort are multiple. First of all, UltraSPARC is not
# the whole SPARCv9 universe and other VIS-free implementations deserve
# optimized code as much. Secondly, newly introduced UltraSPARC T1,
# a.k.a. Niagara, has shared FPU and concurrent FPU-intensive pathes,
# a.k.a. Niagara, has shared FPU and concurrent FPU-intensive paths,
# such as sparcv9a-mont, will simply sink it. Yes, T1 is equipped with
# several integrated RSA/DSA accelerator circuits accessible through
# kernel driver [only(*)], but having decent user-land software
@@ -42,6 +49,9 @@
# module still have hidden potential [see TODO list there], which is
# estimated to be larger than 20%...
$output = pop;
open STDOUT,">$output";
# int bn_mul_mont(
$rp="%i0"; # BN_ULONG *rp,
$ap="%i1"; # const BN_ULONG *ap,
@@ -50,10 +60,8 @@ $np="%i3"; # const BN_ULONG *np,
$n0="%i4"; # const BN_ULONG *n0,
$num="%i5"; # int num);
$bits=32;
for (@ARGV) { $bits=64 if (/\-m64/ || /\-xarch\=v9/); }
if ($bits==64) { $bias=2047; $frame=192; }
else { $bias=0; $frame=128; }
$frame="STACK_FRAME";
$bias="STACK_BIAS";
$car0="%o0";
$car1="%o1";
@@ -76,6 +84,8 @@ $tpj="%l7";
$fname="bn_mul_mont_int";
$code=<<___;
#include "sparc_arch.h"
.section ".text",#alloc,#execinstr
.global $fname
@@ -105,7 +115,7 @@ $fname:
ld [$np],$car1 ! np[0]
sub %o7,$bias,%sp ! alloca
ld [$np+4],$npj ! np[1]
be,pt `$bits==32?"%icc":"%xcc"`,.Lbn_sqr_mont
be,pt SIZE_T_CC,.Lbn_sqr_mont
mov 12,$j
mulx $car0,$mul0,$car0 ! ap[0]*bp[0]