summaryrefslogtreecommitdiff
path: root/plugins/MirOTR/libgcrypt-1.4.6/mpi/amd64/mpih-lshift.S
blob: e87dd1a99bfe1d922899d6469afeee1b79473a27 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
/* AMD64 (x86_64) lshift -- Left shift a limb vector and store
 *		  result in a second limb vector.
 *
 *      Copyright (C) 1992, 1994, 1995, 1998, 
 *                    2001, 2002, 2006 Free Software Foundation, Inc.
 *
 * This file is part of Libgcrypt.
 *
 * Libgcrypt is free software; you can redistribute it and/or modify
 * it under the terms of the GNU Lesser General Public License as
 * published by the Free Software Foundation; either version 2.1 of
 * the License, or (at your option) any later version.
 *
 * Libgcrypt is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU Lesser General Public License for more details.
 *
 * You should have received a copy of the GNU Lesser General Public
 * License along with this program; if not, write to the Free Software
 * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA
 *
 * Note: This code is heavily based on the GNU MP Library.
 *	 Actually it's the same code with only minor changes in the
 *	 way the data is stored; this is to support the abstraction
 *	 of an optional secure memory allocation which may be used
 *	 to avoid revealing of sensitive data due to paging etc.
 */


#include "sysdep.h"
#include "asm-syntax.h"

/*******************
 * mpi_limb_t
 * _gcry_mpih_lshift( mpi_ptr_t wp,	rdi
 *		   mpi_ptr_t up,	rsi
 *		   mpi_size_t usize,	rdx
 *		   unsigned cnt)	rcx
 */

.text
	.globl C_SYMBOL_NAME(_gcry_mpih_lshift)
C_SYMBOL_NAME(_gcry_mpih_lshift:)
	movq	-8(%rsi,%rdx,8), %mm7
	movd	%ecx, %mm1
	movl	$64, %eax
	subl	%ecx, %eax
	movd	%eax, %mm0
	movq	%mm7, %mm3
	psrlq	%mm0, %mm7
	movd	%mm7, %rax
	subq	$2, %rdx
	jl	.Lendo

	ALIGN(4)			/* minimal alignment for claimed speed */
.Loop:	movq	(%rsi,%rdx,8), %mm6
	movq	%mm6, %mm2
	psrlq	%mm0, %mm6
	psllq	%mm1, %mm3
	por	%mm6, %mm3
	movq	%mm3, 8(%rdi,%rdx,8)
	je	.Lende
	movq	-8(%rsi,%rdx,8), %mm7
	movq	%mm7, %mm3
	psrlq	%mm0, %mm7
	psllq	%mm1, %mm2
	por	%mm7, %mm2
	movq	%mm2, (%rdi,%rdx,8)
	subq	$2, %rdx
	jge	.Loop

.Lendo:	movq	%mm3, %mm2
.Lende:	psllq	%mm1, %mm2
	movq	%mm2, (%rdi)
	emms
	ret