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
|
dnl AMD64 mpn_gcd_22. Assumes useful bsf, useless shrd, no tzcnt, no shlx.
dnl Copyright 2019 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/bit
C AMD K8,K9 ?
C AMD K10 7.4
C AMD bd1 9.9
C AMD bd2 ?
C AMD bd3 ?
C AMD bd4 ?
C AMD bt1 ?
C AMD bt2 ?
C AMD zn1 ?
C AMD zn2 ?
C Intel P4 ?
C Intel CNR ?
C Intel PNR ?
C Intel NHM 9.2
C Intel WSM 9.0
C Intel SBR ?
C Intel IBR ?
C Intel HWL ?
C Intel BWL ?
C Intel SKL ?
C Intel atom ?
C Intel SLM ?
C Intel GLM ?
C Intel GLM+ ?
C VIA nano ?
define(`u1', `%rdi')
define(`u0', `%rsi')
define(`v1', `%rdx')
define(`v0_param', `%rcx')
define(`v0', `%rax')
define(`cnt', `%rcx')
define(`s0', `%r8')
define(`s1', `%r9')
define(`t0', `%r10')
define(`t1', `%r11')
dnl ABI_SUPPORT(DOS64) C returns mp_double_limb_t in memory
ABI_SUPPORT(STD64)
ASM_START()
TEXT
ALIGN(64)
PROLOGUE(mpn_gcd_22)
FUNC_ENTRY(4)
mov v0_param, v0
ALIGN(16)
L(top): mov v0, t0
sub u0, t0
jz L(lowz) C jump when low limb result = 0
mov v1, t1
sbb u1, t1
mov u0, s0
mov u1, s1
bsf t0, cnt
sub v0, u0
sbb v1, u1
L(bck): cmovc t0, u0 C u = |u - v|
cmovnc u1, t1 C u = |u - v|
cmovc s0, v0 C v = min(u,v)
cmovc s1, v1 C v = min(u,v)
shr R8(cnt), u0
mov t1, u1
shr R8(cnt), u1
neg cnt
shl R8(cnt), t1
or t1, u0
test u1, u1
jnz L(top)
test v1, v1
jnz L(top)
L(gcd_11):
mov v0, %rdi
C mov u0, %rsi
TCALL( mpn_gcd_11)
L(lowz):C We come here when v0 - u0 = 0
C 1. If v1 - u1 = 0, then gcd is u = v.
C 2. Else compute gcd_21({v1,v0}, |u1-v1|)
mov v1, t0
sub u1, t0
je L(end)
xor t1, t1
mov u0, s0
mov u1, s1
bsf t0, cnt
mov u1, u0
xor u1, u1
sub v1, u0
jmp L(bck)
L(end): C mov v0, %rax
C mov v1, %rdx
FUNC_EXIT()
ret
EPILOGUE()
|
