chacha/asm/chacha-ppc.pl: optimize AltiVec/VMX code path.

[openssl.git] / crypto / chacha / asm / chacha-s390x.pl

diff --git a/crypto/chacha/asm/chacha-s390x.pl b/crypto/chacha/asm/chacha-s390x.pl
index e637dc2f4fbd2ddde844ac91a9550703a0b9ea92..c31526473dba4d59059088733fe16cb5fa7756c4 100755 (executable)
--- a/crypto/chacha/asm/chacha-s390x.pl
+++ b/crypto/chacha/asm/chacha-s390x.pl
@@ -1,4 +1,11 @@
-#!/usr/bin/env perl
+#! /usr/bin/env perl
+# Copyright 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
@@ -23,7 +30,7 @@ if ($flavour =~ /3[12]/) {
        $g="g";
 }
 
-while (($output=shift) && ($output!~/^\w[\w\-]*\.\w+$/)) {}
+while (($output=shift) && ($output!~/\w[\w\-]*\.\w+$/)) {}
 open STDOUT,">$output";
 
 sub AUTOLOAD()         # thunk [simplified] x86-style perlasm
@@ -140,7 +147,8 @@ $code.=<<___;
 .type  ChaCha20_ctr32,\@function
 .align 32
 ChaCha20_ctr32:
-       cl${g}ije       $len,0,.Lno_data        # $len==0?
+       lt${g}r $len,$len                       # $len==0?
+       bzr     %r14
        a${g}hi $len,-64
        l${g}hi %r1,-$frame
        stm${g} %r6,%r15,`6*$SIZE_T`($sp)
@@ -257,11 +265,11 @@ $code.=<<___;
         st     @x[1],4*9(@t[0])
         x      @x[3],4*11(%r14)
         st     @x[2],4*10(@t[0])
-       la      %r14,64(%r14)
         st     @x[3],4*11(@t[0])
 
        cl${g}r %r14,@t[1]                      # done yet?
-       jle     .Loop_outer
+       la      %r14,64(%r14)
+       jl      .Loop_outer
 
 .Ldone:
        xgr     %r0,%r0
@@ -272,7 +280,6 @@ $code.=<<___;
        stmg    %r0,%r3,$stdframe+4*12($sp)
 
        lm${g}  %r6,%r15,`$frame+6*$SIZE_T`($sp)
-.Lno_data:
        br      %r14
 
 .align 16
@@ -291,7 +298,7 @@ $code.=<<___;
        lrvr    @x[1],@x[1]
        lrvr    @x[2],@x[2]
        lrvr    @x[3],@x[3]
-       stm     @x[0],@x[3],$stdframe+4*8+4*8($sp)
+       stm     @x[0],@x[3],$stdframe+4*8($sp)
 
 .Loop_tail:
        llgc    @x[4],0(@x[6],%r14)