-#!/usr/bin/env perl
+#! /usr/bin/env perl
+# Copyright 2012-2018 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
# October 2012.
#
-# SPARCv9 VIS3 Montgomery multiplicaion procedure suitable for T3 and
+# SPARCv9 VIS3 Montgomery multiplication procedure suitable for T3 and
# onward. There are three new instructions used here: umulxhi,
# addxc[cc] and initializing store. On T3 RSA private key operations
# are 1.54/1.87/2.11/2.26 times faster for 512/1024/2048/4096-bit key
sub $anp, $num, $anp
sub $rp, $num, $rp
- subc $ovf, %g0, $ovf ! handle upmost overflow bit
- and $tp, $ovf, $ap
- andn $rp, $ovf, $np
- or $np, $ap, $ap ! ap=borrow?tp:rp
+ subccc $ovf, %g0, $ovf ! handle upmost overflow bit
ba .Lcopy
sub $num, 8, $cnt
.align 16
-.Lcopy: ! copy or in-place refresh
- ld [$ap+0], $t2
- ld [$ap+4], $t3
- add $ap, 8, $ap
+.Lcopy: ! conditional copy
+ ld [$tp+0], $t0
+ ld [$tp+4], $t1
+ ld [$rp+0], $t2
+ ld [$rp+4], $t3
stx %g0, [$tp] ! zap
add $tp, 8, $tp
stx %g0, [$anp] ! zap
stx %g0, [$anp+8]
add $anp, 16, $anp
+ movcs %icc, $t0, $t2
+ movcs %icc, $t1, $t3
st $t3, [$rp+0] ! flip order
st $t2, [$rp+4]
add $rp, 8, $rp