1dnl Alpha mpn_addmul_1 -- Multiply a limb vector with a limb and add the
2dnl result to 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.
7
8dnl  The GNU MP Library is free software; you can redistribute it and/or modify
9dnl  it under the terms of the GNU Lesser General Public License as published
10dnl  by the Free Software Foundation; either version 3 of the License, or (at
11dnl  your option) any later version.
12
13dnl  The GNU MP Library is distributed in the hope that it will be useful, but
14dnl  WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
15dnl  or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU Lesser General Public
16dnl  License for more details.
17
18dnl  You should have received a copy of the GNU Lesser General Public License
19dnl  along with the GNU MP Library.  If not, see http://www.gnu.org/licenses/.
20
21include(`../config.m4')
22
23C      cycles/limb
24C EV4:     42
25C EV5:     18
26C EV6:      7
27
28C  INPUT PARAMETERS
29C  rp	r16
30C  up	r17
31C  n	r18
32C  vl	r19
33
34
35ASM_START()
36PROLOGUE(mpn_addmul_1)
37	ldq	r2,0(r17)	C r2 = s1_limb
38	addq	r17,8,r17	C s1_ptr++
39	subq	r18,1,r18	C size--
40	mulq	r2,r19,r3	C r3 = prod_low
41	ldq	r5,0(r16)	C r5 = *res_ptr
42	umulh	r2,r19,r0	C r0 = prod_high
43	beq	r18,$Lend1	C jump if size was == 1
44	ldq	r2,0(r17)	C r2 = s1_limb
45	addq	r17,8,r17	C s1_ptr++
46	subq	r18,1,r18	C size--
47	addq	r5,r3,r3
48	cmpult	r3,r5,r4
49	stq	r3,0(r16)
50	addq	r16,8,r16	C res_ptr++
51	beq	r18,$Lend2	C jump if size was == 2
52
53	ALIGN(8)
54$Loop:	mulq	r2,r19,r3	C r3 = prod_low
55	ldq	r5,0(r16)	C r5 = *res_ptr
56	addq	r4,r0,r0	C cy_limb = cy_limb + 'cy'
57	subq	r18,1,r18	C size--
58	umulh	r2,r19,r4	C r4 = cy_limb
59	ldq	r2,0(r17)	C r2 = s1_limb
60	addq	r17,8,r17	C s1_ptr++
61	addq	r3,r0,r3	C r3 = cy_limb + prod_low
62	cmpult	r3,r0,r0	C r0 = carry from (cy_limb + prod_low)
63	addq	r5,r3,r3
64	cmpult	r3,r5,r5
65	stq	r3,0(r16)
66	addq	r16,8,r16	C res_ptr++
67	addq	r5,r0,r0	C combine carries
68	bne	r18,$Loop
69
70$Lend2:	mulq	r2,r19,r3	C r3 = prod_low
71	ldq	r5,0(r16)	C r5 = *res_ptr
72	addq	r4,r0,r0	C cy_limb = cy_limb + 'cy'
73	umulh	r2,r19,r4	C r4 = cy_limb
74	addq	r3,r0,r3	C r3 = cy_limb + prod_low
75	cmpult	r3,r0,r0	C r0 = carry from (cy_limb + prod_low)
76	addq	r5,r3,r3
77	cmpult	r3,r5,r5
78	stq	r3,0(r16)
79	addq	r5,r0,r0	C combine carries
80	addq	r4,r0,r0	C cy_limb = prod_high + cy
81	ret	r31,(r26),1
82$Lend1:	addq	r5,r3,r3
83	cmpult	r3,r5,r5
84	stq	r3,0(r16)
85	addq	r0,r5,r0
86	ret	r31,(r26),1
87EPILOGUE(mpn_addmul_1)
88ASM_END()
89