summaryrefslogtreecommitdiff
path: root/mpn/arm/addmul_1.S
blob: f4316df3352cd4bbb385d4815a44fb2554e2c131 (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
@ ARM mpn_mul_1 -- Multiply a limb vector with a limb and add the result to a
@ second limb vector.
@ Contributed by Robert Harley.

@ Copyright (C) 1998, 2000 Free Software Foundation, Inc.

@ This file is part of the GNU MP Library.

@ The GNU MP Library is free software; you can redistribute it and/or modify
@ it under the terms of the GNU Library General Public License as published by
@ the Free Software Foundation; either version 2 of the License, or (at your
@ option) any later version.

@ The GNU MP Library 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 Library General Public
@ License for more details.

@ You should have received a copy of the GNU Library General Public License
@ along with the GNU MP Library; see the file COPYING.LIB.  If not, write to
@ the Free Software Foundation, Inc., 59 Temple Place - Suite 330, Boston,
@ MA 02111-1307, USA.

#define p r0
#define a r1
#define n r2
#define w r3

#define z r11

#define ip r12
#define sp r13
#define lr r14
#define pc r15

.text
	.align	0
	.global	__gmpn_addmul_1
	.type	__gmpn_addmul_1,%function
__gmpn_addmul_1:
	stmfd	sp!, { r8-r11, lr }
	mov	z, #0
	mov	ip, #0
	movs	n, n, lsr #1
	bcc	skip1
	ldr	lr, [a], #4
	ldr	r9, [p]
	umlal	r9, ip, w, lr
	str	r9, [p], #4
skip1:
	movs	n, n, lsr #1
	bcc	skip2
	ldmia	p, { r9, r10 }
	adds	r8, ip, r9
	adc	r9, z, #0
	ldmia	a!, { ip, lr }
	umlal	r8, r9, w, ip
	adds	r9, r9, r10
	adc	ip, z, #0
	umlal	r9, ip, w, lr
	stmia	p!, { r8, r9 }
skip2:
	teq	n, #0
	beq	return
	stmfd	sp!, { r4-r7 }
addmul_loop:
	ldmia	p, { r5, r6, r7, r8 }
	adds	r4, ip, r5
	adc	r5, z, #0
	ldmia	a!, { r9, r10, ip, lr }
	umlal	r4, r5, w, r9
	adds	r5, r5, r6
	adc	r6, z, #0
	umlal	r5, r6, w, r10
	adds	r6, r6, r7
	adc	r7, z, #0
	umlal	r6, r7, w, ip
	adds	r7, r7, r8
	adc	ip, z, #0
	umlal	r7, ip, w, lr
	subs	n, n, #1
	stmia	p!, { r4, r5, r6, r7 }
	bne	addmul_loop
	ldmfd	sp!, { r4-r7 }
return:
	mov	r0, ip
	ldmfd	sp!, { r8-r11, pc }
end:
	.size	__gmpn_addmul_1, end - __gmpn_addmul_1