spelling fixes, just comments and readme.

[openssl.git] / crypto / sha / asm / sha512-x86_64.pl

diff --git a/crypto/sha/asm/sha512-x86_64.pl b/crypto/sha/asm/sha512-x86_64.pl
index 476e99fee8f4d6508a9e9f059d11cb7c1c258c4d..63a62656f6508deaf7ab55799d28cdf412a399ad 100755 (executable)
--- a/crypto/sha/asm/sha512-x86_64.pl
+++ b/crypto/sha/asm/sha512-x86_64.pl
@@ -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@openssl.org> for the OpenSSL
@@ -34,7 +41,7 @@
 # level parallelism, on a given CPU implementation in this case.
 #
 # Special note on Intel EM64T. While Opteron CPU exhibits perfect
-# perfromance ratio of 1.5 between 64- and 32-bit flavors [see above],
+# performance ratio of 1.5 between 64- and 32-bit flavors [see above],
 # [currently available] EM64T CPUs apparently are far from it. On the
 # contrary, 64-bit version, sha512_block, is ~30% *slower* than 32-bit
 # sha256_block:-( This is presumably because 64-bit shifts/rotates
@@ -86,9 +93,11 @@
 # Sandy Bridge 17.4    14.2(+23%)  11.6(+50%(**))  11.2    8.10(+38%(**))
 # Ivy Bridge   12.6    10.5(+20%)  10.3(+22%)      8.17    7.22(+13%)
 # Haswell      12.2    9.28(+31%)  7.80(+56%)      7.66    5.40(+42%)
+# Skylake      11.4    9.03(+26%)  7.70(+48%)      7.25    5.20(+40%)
 # Bulldozer    21.1    13.6(+54%)  13.6(+54%(***)) 13.5    8.58(+57%)
 # VIA Nano     23.0    16.5(+39%)  -               14.7    -
 # Atom         23.0    18.9(+22%)  -               14.7    -
+# Silvermont   27.4    20.6(+33%)  -               17.5    -
 #
 # (*)  whichever best applicable;
 # (**) switch from ror to shrd stands for fair share of improvement;
@@ -123,14 +132,14 @@ if (!$avx && $win64 && ($flavour =~ /masm/ || $ENV{ASM} =~ /ml64/) &&
        $avx = ($1>=10) + ($1>=11);
 }
 
-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);
 }
 
 $shaext=1;     ### set to zero if compiling for 1.0.1
 $avx=1         if (!$shaext && $avx);
 
-open OUT,"| \"$^X\" $xlate $flavour $output";
+open OUT,"| \"$^X\" \"$xlate\" $flavour \"$output\"";
 *STDOUT=*OUT;
 
 if ($output =~ /512/) {