1/* AMD64 (x86_64) lshift -- Left shift a limb vector and store
2 *		  result in a second limb vector.
3 *
4 *      Copyright (C) 1992, 1994, 1995, 1998,
5 *                    2001, 2002, 2006 Free Software Foundation, Inc.
6 *
7 * This file is part of Libgcrypt.
8 *
9 * Libgcrypt is free software; you can redistribute it and/or modify
10 * it under the terms of the GNU Lesser General Public License as
11 * published by the Free Software Foundation; either version 2.1 of
12 * the License, or (at your option) any later version.
13 *
14 * Libgcrypt is distributed in the hope that it will be useful,
15 * but WITHOUT ANY WARRANTY; without even the implied warranty of
16 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
17 * GNU Lesser General Public License for more details.
18 *
19 * You should have received a copy of the GNU Lesser General Public
20 * License along with this program; if not, write to the Free Software
21 * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA
22 *
23 * Note: This code is heavily based on the GNU MP Library.
24 *	 Actually it's the same code with only minor changes in the
25 *	 way the data is stored; this is to support the abstraction
26 *	 of an optional secure memory allocation which may be used
27 *	 to avoid revealing of sensitive data due to paging etc.
28 */
29
30
31#include "sysdep.h"
32#include "asm-syntax.h"
33
34/*******************
35 * mpi_limb_t
36 * _gcry_mpih_lshift( mpi_ptr_t wp,	rdi
37 *		   mpi_ptr_t up,	rsi
38 *		   mpi_size_t usize,	rdx
39 *		   unsigned cnt)	rcx
40 */
41
42.text
43	.globl C_SYMBOL_NAME(_gcry_mpih_lshift)
44C_SYMBOL_NAME(_gcry_mpih_lshift:)
45	movq	-8(%rsi,%rdx,8), %mm7
46	movd	%ecx, %mm1
47	movl	$64, %eax
48	subl	%ecx, %eax
49	movd	%eax, %mm0
50	movq	%mm7, %mm3
51	psrlq	%mm0, %mm7
52	movd	%mm7, %rax
53	subq	$2, %rdx
54	jl	.Lendo
55
56	ALIGN(4)			/* minimal alignment for claimed speed */
57.Loop:	movq	(%rsi,%rdx,8), %mm6
58	movq	%mm6, %mm2
59	psrlq	%mm0, %mm6
60	psllq	%mm1, %mm3
61	por	%mm6, %mm3
62	movq	%mm3, 8(%rdi,%rdx,8)
63	je	.Lende
64	movq	-8(%rsi,%rdx,8), %mm7
65	movq	%mm7, %mm3
66	psrlq	%mm0, %mm7
67	psllq	%mm1, %mm2
68	por	%mm7, %mm2
69	movq	%mm2, (%rdi,%rdx,8)
70	subq	$2, %rdx
71	jge	.Loop
72
73.Lendo:	movq	%mm3, %mm2
74.Lende:	psllq	%mm1, %mm2
75	movq	%mm2, (%rdi)
76	emms
77	ret
78