1dnl  Alpha mpn_mul_1 -- Multiply a limb vector with a limb and store
2dnl  the result in a second limb vector.
3
4dnl  Copyright 1992, 1994, 1995, 2000, 2002 Free Software Foundation, Inc.
5
6dnl  This file is part of the GNU MP Library.
7dnl
8dnl  The GNU MP Library is free software; you can redistribute it and/or modify
9dnl  it under the terms of either:
10dnl
11dnl    * the GNU Lesser General Public License as published by the Free
12dnl      Software Foundation; either version 3 of the License, or (at your
13dnl      option) any later version.
14dnl
15dnl  or
16dnl
17dnl    * the GNU General Public License as published by the Free Software
18dnl      Foundation; either version 2 of the License, or (at your option) any
19dnl      later version.
20dnl
21dnl  or both in parallel, as here.
22dnl
23dnl  The GNU MP Library is distributed in the hope that it will be useful, but
24dnl  WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
25dnl  or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
26dnl  for more details.
27dnl
28dnl  You should have received copies of the GNU General Public License and the
29dnl  GNU Lesser General Public License along with the GNU MP Library.  If not,
30dnl  see https://www.gnu.org/licenses/.
31
32include(`../config.m4')
33
34C      cycles/limb
35C EV4:     42
36C EV5:     18
37C EV6:      7
38
39C  INPUT PARAMETERS
40C  rp	r16
41C  up	r17
42C  n	r18
43C  vl	r19
44C  cl	r20
45
46
47ASM_START()
48PROLOGUE(mpn_mul_1c)
49	ldq	r2,0(r17)	C r2 = s1_limb
50	lda	r18,-1(r18)	C size--
51	mulq	r2,r19,r3	C r3 = prod_low
52	umulh	r2,r19,r4	C r4 = prod_high
53	beq	r18,$Le1c	C jump if size was == 1
54	ldq	r2,8(r17)	C r2 = s1_limb
55	lda	r18,-1(r18)	C size--
56	addq	r3,r20,r3	C r3 = cy_limb + cl
57	stq	r3,0(r16)
58	cmpult	r3,r20,r0	C r0 = carry from (cy_limb + cl)
59	bne	r18,$Loop	C jump if size was == 2
60	br	r31,$Le2
61$Le1c:	addq	r3,r20,r3	C r3 = cy_limb + cl
62	cmpult	r3,r20,r0	C r0 = carry from (cy_limb + cl)
63$Le1:	stq	r3,0(r16)
64	addq	r4,r0,r0
65	ret	r31,(r26),1
66EPILOGUE(mpn_mul_1c)
67
68PROLOGUE(mpn_mul_1)
69	ldq	r2,0(r17)	C r2 = s1_limb
70	lda	r18,-1(r18)	C size--
71	mulq	r2,r19,r3	C r3 = prod_low
72	bic	r31,r31,r0	C clear cy_limb
73	umulh	r2,r19,r4	C r4 = prod_high
74	beq	r18,$Le1	C jump if size was == 1
75	ldq	r2,8(r17)	C r2 = s1_limb
76	lda	r18,-1(r18)	C size--
77	stq	r3,0(r16)
78	beq	r18,$Le2	C jump if size was == 2
79
80	ALIGN(8)
81$Loop:	mulq	r2,r19,r3	C r3 = prod_low
82	addq	r4,r0,r0	C cy_limb = cy_limb + 'cy'
83	lda	r18,-1(r18)	C size--
84	umulh	r2,r19,r4	C r4 = prod_high
85	ldq	r2,16(r17)	C r2 = s1_limb
86	lda	r17,8(r17)	C s1_ptr++
87	addq	r3,r0,r3	C r3 = cy_limb + prod_low
88	stq	r3,8(r16)
89	cmpult	r3,r0,r0	C r0 = carry from (cy_limb + prod_low)
90	lda	r16,8(r16)	C res_ptr++
91	bne	r18,$Loop
92
93$Le2:	mulq	r2,r19,r3	C r3 = prod_low
94	addq	r4,r0,r0	C cy_limb = cy_limb + 'cy'
95	umulh	r2,r19,r4	C r4 = prod_high
96	addq	r3,r0,r3	C r3 = cy_limb + prod_low
97	cmpult	r3,r0,r0	C r0 = carry from (cy_limb + prod_low)
98	stq	r3,8(r16)
99	addq	r4,r0,r0	C cy_limb = prod_high + cy
100	ret	r31,(r26),1
101EPILOGUE(mpn_mul_1)
102ASM_END()
103