aboutsummaryrefslogtreecommitdiff
path: root/vendor/gmp-6.3.0/mpn/x86_64/aors_n.asm
blob: d5a314ac513669904b47850409e5335bb14bbaf4 (plain) (blame)
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
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
dnl  AMD64 mpn_add_n, mpn_sub_n

dnl  Copyright 2003-2005, 2007, 2008, 2010-2012 Free Software Foundation, Inc.

dnl  This file is part of the GNU MP Library.
dnl
dnl  The GNU MP Library is free software; you can redistribute it and/or modify
dnl  it under the terms of either:
dnl
dnl    * the GNU Lesser General Public License as published by the Free
dnl      Software Foundation; either version 3 of the License, or (at your
dnl      option) any later version.
dnl
dnl  or
dnl
dnl    * the GNU General Public License as published by the Free Software
dnl      Foundation; either version 2 of the License, or (at your option) any
dnl      later version.
dnl
dnl  or both in parallel, as here.
dnl
dnl  The GNU MP Library is distributed in the hope that it will be useful, but
dnl  WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
dnl  or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
dnl  for more details.
dnl
dnl  You should have received copies of the GNU General Public License and the
dnl  GNU Lesser General Public License along with the GNU MP Library.  If not,
dnl  see https://www.gnu.org/licenses/.

include(`../config.m4')

C	     cycles/limb
C AMD K8,K9	 1.5
C AMD K10	 1.5
C AMD bd1	 1.8
C AMD bd2	 1.74
C AMD bd3	 ?
C AMD bd4	 1.78
C AMD zen	 1.5
C AMD bt1	 2.54
C AMD bt2	 2.15
C Intel P4	11.5
C Intel core2	 4.9
C Intel NHM	 5.53
C Intel SBR	 1.59
C Intel IBR	 1.55
C Intel HWL	 1.44
C Intel BWL	 1.14
C Intel SKL	 1.21
C Intel atom	 4
C Intel SLM	 3
C VIA nano	 3.25

C The loop of this code is the result of running a code generation and
C optimization tool suite written by David Harvey and Torbjorn Granlund.

C INPUT PARAMETERS
define(`rp',	`%rdi')	C rcx
define(`up',	`%rsi')	C rdx
define(`vp',	`%rdx')	C r8
define(`n',	`%rcx')	C r9
define(`cy',	`%r8')	C rsp+40    (mpn_add_nc and mpn_sub_nc)

ifdef(`OPERATION_add_n', `
	define(ADCSBB,	      adc)
	define(func,	      mpn_add_n)
	define(func_nc,	      mpn_add_nc)')
ifdef(`OPERATION_sub_n', `
	define(ADCSBB,	      sbb)
	define(func,	      mpn_sub_n)
	define(func_nc,	      mpn_sub_nc)')

MULFUNC_PROLOGUE(mpn_add_n mpn_add_nc mpn_sub_n mpn_sub_nc)

ABI_SUPPORT(DOS64)
ABI_SUPPORT(STD64)

ASM_START()
	TEXT
	ALIGN(16)
PROLOGUE(func_nc)
	FUNC_ENTRY(4)
IFDOS(`	mov	56(%rsp), %r8	')
	mov	R32(n), R32(%rax)
	shr	$2, n
	and	$3, R32(%rax)
	bt	$0, %r8			C cy flag <- carry parameter
	jrcxz	L(lt4)

	mov	(up), %r8
	mov	8(up), %r9
	dec	n
	jmp	L(mid)

EPILOGUE()
	ALIGN(16)
PROLOGUE(func)
	FUNC_ENTRY(4)
	mov	R32(n), R32(%rax)
	shr	$2, n
	and	$3, R32(%rax)
	jrcxz	L(lt4)

	mov	(up), %r8
	mov	8(up), %r9
	dec	n
	jmp	L(mid)

L(lt4):	dec	R32(%rax)
	mov	(up), %r8
	jnz	L(2)
	ADCSBB	(vp), %r8
	mov	%r8, (rp)
	adc	R32(%rax), R32(%rax)
	FUNC_EXIT()
	ret

L(2):	dec	R32(%rax)
	mov	8(up), %r9
	jnz	L(3)
	ADCSBB	(vp), %r8
	ADCSBB	8(vp), %r9
	mov	%r8, (rp)
	mov	%r9, 8(rp)
	adc	R32(%rax), R32(%rax)
	FUNC_EXIT()
	ret

L(3):	mov	16(up), %r10
	ADCSBB	(vp), %r8
	ADCSBB	8(vp), %r9
	ADCSBB	16(vp), %r10
	mov	%r8, (rp)
	mov	%r9, 8(rp)
	mov	%r10, 16(rp)
	setc	R8(%rax)
	FUNC_EXIT()
	ret

	ALIGN(16)
L(top):	ADCSBB	(vp), %r8
	ADCSBB	8(vp), %r9
	ADCSBB	16(vp), %r10
	ADCSBB	24(vp), %r11
	mov	%r8, (rp)
	lea	32(up), up
	mov	%r9, 8(rp)
	mov	%r10, 16(rp)
	dec	n
	mov	%r11, 24(rp)
	lea	32(vp), vp
	mov	(up), %r8
	mov	8(up), %r9
	lea	32(rp), rp
L(mid):	mov	16(up), %r10
	mov	24(up), %r11
	jnz	L(top)

L(end):	lea	32(up), up
	ADCSBB	(vp), %r8
	ADCSBB	8(vp), %r9
	ADCSBB	16(vp), %r10
	ADCSBB	24(vp), %r11
	lea	32(vp), vp
	mov	%r8, (rp)
	mov	%r9, 8(rp)
	mov	%r10, 16(rp)
	mov	%r11, 24(rp)
	lea	32(rp), rp

	inc	R32(%rax)
	dec	R32(%rax)
	jnz	L(lt4)
	adc	R32(%rax), R32(%rax)
	FUNC_EXIT()
	ret
EPILOGUE()