diff options
Diffstat (limited to 'crypto/bn/asm/sparcv9a-mont.pl')
| -rwxr-xr-x | crypto/bn/asm/sparcv9a-mont.pl | 35 |
1 files changed, 20 insertions, 15 deletions
diff --git a/crypto/bn/asm/sparcv9a-mont.pl b/crypto/bn/asm/sparcv9a-mont.pl index a14205f2f006..c8f759df9fbd 100755 --- a/crypto/bn/asm/sparcv9a-mont.pl +++ b/crypto/bn/asm/sparcv9a-mont.pl @@ -1,7 +1,14 @@ -#!/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 +# Written by Andy Polyakov <appro@openssl.org> for the OpenSSL # 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/. @@ -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. +$output = pop; +open STDOUT,">$output"; + $fname="bn_mul_mont_fpu"; -$bits=32; -for (@ARGV) { $bits=64 if (/\-m64/ || /\-xarch\=v9/); } - -if ($bits==64) { - $bias=2047; - $frame=192; -} else { - $bias=0; - $frame=128; # 96 rounded up to largest known cache-line -} + +$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 @@ -860,14 +865,14 @@ $fname: restore .type $fname,#function .size $fname,(.-$fname) -.asciz "Montgomery Multipltication for UltraSPARC, CRYPTOGAMS by <appro\@openssl.org>" +.asciz "Montgomery Multiplication for UltraSPARC, CRYPTOGAMS by <appro\@openssl.org>" .align 32 ___ $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 |