1/* MIPS3 __mpn_addmul_1 -- Multiply a limb vector with a single limb and
2 * add the product to a second limb vector.
3 *
4 * Copyright (C) 1992-2022 Free Software Foundation, Inc.
5 *
6 * This file is part of the GNU MP Library.
7 *
8 * The GNU MP Library is free software; you can redistribute it and/or modify
9 * it under the terms of the GNU Lesser General Public License as published by
10 * the Free Software Foundation; either version 2.1 of the License, or (at your
11 * option) any later version.
12 *
13 * The GNU MP Library is distributed in the hope that it will be useful, but
14 * WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
15 * or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU Lesser General Public
16 * License for more details.
17 *
18 * You should have received a copy of the GNU Lesser General Public License
19 * along with the GNU MP Library.  If not, see <https://www.gnu.org/licenses/>.
20 */
21
22#include <sysdep.h>
23#include <sys/asm.h>
24
25/* INPUT PARAMETERS
26 * res_ptr	$4
27 * s1_ptr	$5
28 * size		$6
29 * s2_limb	$7
30 */
31
32#ifdef PIC
33	.option pic2
34#endif
35ENTRY (__mpn_addmul_1)
36#ifdef PIC
37	SETUP_GP /* ??? unused */
38#endif
39	.set    noreorder
40	.set    nomacro
41
42 # warm up phase 0
43	ld	$8,0($5)
44
45 # warm up phase 1
46	daddiu	$5,$5,8
47#if __mips_isa_rev < 6
48	dmultu	$8,$7
49#else
50	dmulu	$11,$8,$7
51	dmuhu	$12,$8,$7
52#endif
53
54	daddiu	$6,$6,-1
55	beq	$6,$0,L(LC0)
56	move	$2,$0		# zero cy2
57
58	daddiu	$6,$6,-1
59	beq	$6,$0,L(LC1)
60	ld	$8,0($5)	# load new s1 limb as early as possible
61
62L(Loop):	ld	$10,0($4)
63#if __mips_isa_rev < 6
64	mflo	$3
65	mfhi	$9
66#else
67	move	$3,$11
68	move	$9,$12
69#endif
70	daddiu	$5,$5,8
71	daddu	$3,$3,$2	# add old carry limb to low product limb
72#if __mips_isa_rev < 6
73	dmultu	$8,$7
74#else
75	dmulu	$11,$8,$7
76	dmuhu	$12,$8,$7
77#endif
78	ld	$8,0($5)	# load new s1 limb as early as possible
79	daddiu	$6,$6,-1	# decrement loop counter
80	sltu	$2,$3,$2	# carry from previous addition -> $2
81	daddu	$3,$10,$3
82	sltu	$10,$3,$10
83	daddu	$2,$2,$10
84	sd	$3,0($4)
85	daddiu	$4,$4,8
86	bne	$6,$0,L(Loop)
87	daddu	$2,$9,$2	# add high product limb and carry from addition
88
89 # cool down phase 1
90L(LC1):	ld	$10,0($4)
91#if __mips_isa_rev < 6
92	mflo	$3
93	mfhi	$9
94#else
95	move	$3,$11
96	move	$9,$12
97#endif
98	daddu	$3,$3,$2
99	sltu	$2,$3,$2
100#if __mips_isa_rev < 6
101	dmultu	$8,$7
102#else
103	dmulu	$11,$8,$7
104	dmuhu	$12,$8,$7
105#endif
106	daddu	$3,$10,$3
107	sltu	$10,$3,$10
108	daddu	$2,$2,$10
109	sd	$3,0($4)
110	daddiu	$4,$4,8
111	daddu	$2,$9,$2	# add high product limb and carry from addition
112
113 # cool down phase 0
114L(LC0):	ld	$10,0($4)
115#if __mips_isa_rev < 6
116	mflo	$3
117	mfhi	$9
118#else
119	move	$3,$11
120	move	$9,$12
121#endif
122	daddu	$3,$3,$2
123	sltu	$2,$3,$2
124	daddu	$3,$10,$3
125	sltu	$10,$3,$10
126	daddu	$2,$2,$10
127	sd	$3,0($4)
128	j	$31
129	daddu	$2,$9,$2	# add high product limb and carry from addition
130
131END (__mpn_addmul_1)
132