Unify all assembler file generators

[openssl.git] / crypto / poly1305 / asm / poly1305-x86.pl

diff --git a/crypto/poly1305/asm/poly1305-x86.pl b/crypto/poly1305/asm/poly1305-x86.pl
index cf521c26868da5ec386a3f17b4bbaaa157d8df2b..9aa1bc1600e176f0a1a13d2f22aee2cad90bc034 100755 (executable)
--- a/crypto/poly1305/asm/poly1305-x86.pl
+++ b/crypto/poly1305/asm/poly1305-x86.pl
@@ -1,4 +1,11 @@
-#!/usr/bin/env perl
+#! /usr/bin/env perl
+# Copyright 2016-2018 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@openssl.org> for the OpenSSL
@@ -22,7 +29,9 @@
 # Westmere     4.58/+100%      1.43
 # Sandy Bridge 3.90/+100%      1.36
 # Haswell      3.88/+70%       1.18            0.72
+# Skylake      3.10/+60%       1.14            0.62
 # Silvermont   11.0/+40%       4.80
+# Goldmont     4.10/+200%      2.10
 # VIA Nano     6.71/+90%       2.47
 # Sledgehammer 3.51/+180%      4.27
 # Bulldozer    4.53/+140%      1.31
@@ -38,10 +47,9 @@ $0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1;
 push(@INC,"${dir}","${dir}../../perlasm");
 require "x86asm.pl";
 
-$output=pop;
-open STDOUT,">$output";
+$output=pop and open STDOUT,">$output";
 
-&asm_init($ARGV[0],"poly1305-x86.pl",$ARGV[$#ARGV] eq "386");
+&asm_init($ARGV[0],$ARGV[$#ARGV] eq "386");
 
 $sse2=$avx=0;
 for (@ARGV) { $sse2=1 if (/-DOPENSSL_IA32_SSE2/); }
@@ -62,7 +70,7 @@ if ($sse2) {
        $avx = ($1>=2.09) + ($1>=2.10);
        }
 
-       if (!$avx && `$ENV{CC} -v 2>&1` =~ /(^clang version|based on LLVM) ([3-9]\.[0-9]+)/) {
+       if (!$avx && `$ENV{CC} -v 2>&1` =~ /((?:^clang|LLVM) version|based on LLVM) ([3-9]\.[0-9]+)/) {
                $avx = ($2>=3.0) + ($2>3.0);
        }
 }
@@ -721,7 +729,7 @@ my $extra = shift;
 
        &movdqa         ($T0,$T1);                      # -> base 2^26 ...
        &pand           ($T1,$MASK);
-       &paddd          ($D0,$T1);                      # ... and accumuate
+       &paddd          ($D0,$T1);                      # ... and accumulate
 
        &movdqa         ($T1,$T0);
        &psrlq          ($T0,26);