summaryrefslogtreecommitdiff
path: root/mpi/arm/mpih-mul1.S
blob: ea196e8bfc37ca1c77a8345db423ba216e9e6784 (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
78
79
80
/* ARM mul_1 -- Multiply a limb vector with a limb and store the result in
 *              a second limb vector.
 *
 *      Copyright (C) 2013 Jussi Kivilinna <jussi.kivilinna@iki.fi>
 *
 * 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, see <http://www.gnu.org/licenses/>.
 *
 * Note: This code is heavily based on the GNU MP Library (version 4.2.1).
 */

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

.syntax unified
.arm

/*******************
 * mpi_limb_t
 * _gcry_mpih_mul_1( mpi_ptr_t res_ptr,		r0
 *		  mpi_ptr_t s1_ptr,		r1
 *		  mpi_size_t s1_size,		r2
 *		  mpi_limb_t s2_limb)		r3
 */

.text

.globl _gcry_mpih_mul_1
.type  _gcry_mpih_mul_1,%function
_gcry_mpih_mul_1:
	push	{r4, r5, r6, r7, r8, r9, r10, r11, lr};
	mov	r4, #0;

	tst	r2, #3;
	beq	.Large_loop;

.Loop:
	ldr	r5, [r1], #4;
	mov	lr, #0;
	umlal	r4, lr, r5, r3;
	sub	r2, #1;
	str	r4, [r0], #4;
	tst	r2, #3;
	mov	r4, lr;
	bne	.Loop;

	teq	r2, #0;
	beq	.Lend;

.Large_loop:
	ldm	r1!, {r5, r6, r7, r8};
	mov	r9, #0;
	mov	r10, #0;
	umlal	r4, r9, r5, r3;
	mov	r11, #0;
	umlal	r9, r10, r6, r3;
	str	r4, [r0], #4;
	mov	r4, #0;
	umlal	r10, r11, r7, r3;
	subs	r2, #4;
	umlal	r11, r4, r8, r3;
	stm	r0!, {r9, r10, r11};
	bne	.Large_loop;

.Lend:
	mov	r0, r4;
	pop	{r4, r5, r6, r7, r8, r9, r10, r11, pc};
.size _gcry_mpih_mul_1,.-_gcry_mpih_mul_1;