-#!/usr/bin/env perl
+#! /usr/bin/env perl
+# Copyright 2005-2020 The OpenSSL Project Authors. All Rights Reserved.
+#
+# Licensed under the Apache License 2.0 (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/.
#
# 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.
+# $output is the last argument if it looks like a file (it has an extension)
+$output = $#ARGV >= 0 && $ARGV[$#ARGV] =~ m|\.\w+$| ? pop : undef;
+
+$output and 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
$ASI_FL16_P=0xD2; # magic ASI value to engage 16-bit FP load
$code=<<___;
+#include "sparc_arch.h"
+
.section ".text",#alloc,#execinstr
.global $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
print $code;
# flush
-close STDOUT;
+close STDOUT or die "error closing STDOUT: $!";