summaryrefslogtreecommitdiff
path: root/mpi/mips3/mpih-mul3.S
blob: 960c5c2744b0a06759edb205bc31b4cbc34ae38d (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
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
/* MIPS3 submul_1 -- Multiply a limb vector with a single limb and
 *		     subtract the product from a second limb vector.
 *
 *      Copyright (C) 1992, 1994, 1995, 1998, 2000
 *                    2001 Free Software Foundation, Inc.
 *
 * This file is part of GnuPG.
 *
 * GnuPG is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 * GnuPG 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 General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301,
 * USA.
 */


/*******************
 * mpi_limb_t
 * mpihelp_submul_1( mpi_ptr_t res_ptr,      (r4)
 *		     mpi_ptr_t s1_ptr,	     (r5)
 *		     mpi_size_t s1_size,     (r6)
 *		     mpi_limb_t s2_limb)     (r7)
 */

	.text
	.align	4
	.globl	mpihelp_submul_1
	.ent	mpihelp_submul_1
mpihelp_submul_1:
	.set	noreorder
	.set	nomacro

/* # warm up phase 0 */
	ld	$8,0($5)

/* # warm up phase 1 */
	daddiu	$5,$5,8
	dmultu	$8,$7

	daddiu	$6,$6,-1
	beq	$6,$0,$LC0
	 move	$2,$0		# zero cy2

	daddiu	$6,$6,-1
	beq	$6,$0,$LC1
	ld	$8,0($5)	# load new s1 limb as early as possible

Loop:	ld	$10,0($4)
	mflo	$3
	mfhi	$9
	daddiu	$5,$5,8
	daddu	$3,$3,$2	# add old carry limb to low product limb
	dmultu	$8,$7
	ld	$8,0($5)	# load new s1 limb as early as possible
	daddiu	$6,$6,-1	# decrement loop counter
	sltu	$2,$3,$2	# carry from previous addition -> $2
	dsubu	$3,$10,$3
	sgtu	$10,$3,$10
	daddu	$2,$2,$10
	sd	$3,0($4)
	daddiu	$4,$4,8
	bne	$6,$0,Loop
	 daddu	$2,$9,$2	# add high product limb and carry from addition

/* # cool down phase 1 */
$LC1:	ld	$10,0($4)
	mflo	$3
	mfhi	$9
	daddu	$3,$3,$2
	sltu	$2,$3,$2
	dmultu	$8,$7
	dsubu	$3,$10,$3
	sgtu	$10,$3,$10
	daddu	$2,$2,$10
	sd	$3,0($4)
	daddiu	$4,$4,8
	daddu	$2,$9,$2	# add high product limb and carry from addition

/* # cool down phase 0 */
$LC0:	ld	$10,0($4)
	mflo	$3
	mfhi	$9
	daddu	$3,$3,$2
	sltu	$2,$3,$2
	dsubu	$3,$10,$3
	sgtu	$10,$3,$10
	daddu	$2,$2,$10
	sd	$3,0($4)
	j	$31
	daddu	$2,$9,$2	# add high product limb and carry from addition

	.end	mpihelp_submul_1