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
|
dnl AMD64 mpn_sub_n -- Subtract two limb vectors of the same length > 0 and
dnl store difference in a third limb vector.
dnl Copyright 2003, 2004, 2005, 2007 Free Software Foundation, Inc.
dnl This file is part of the GNU MP Library.
dnl The GNU MP Library is free software; you can redistribute it and/or modify
dnl it under the terms of the GNU Lesser General Public License as published
dnl by the Free Software Foundation; either version 2.1 of the License, or (at
dnl your option) any later version.
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 Lesser General Public
dnl License for more details.
dnl You should have received a copy of the GNU Lesser General Public License
dnl along with the GNU MP Library; see the file COPYING.LIB. If not, write
dnl to the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
dnl Boston, MA 02110-1301, USA.
include(`../config.m4')
C cycles/limb
C K8: 1.69
C P4: 11
C P6-15: 5.0
MULFUNC_PROLOGUE(mpn_sub_n mpn_sub_nc)
C INPUT PARAMETERS
C rp rdi
C up rsi
C vp rdx
C n rcx
C cy r8 (only for mpn_sub_nc)
TEXT
ALIGN(16)
ASM_START()
PROLOGUE(mpn_sub_nc)
movq %rcx, %r10 C 3
andl $3, %r10d C 4
shrq $2, %rcx C 4
bt $0, %r8 C cy flag <- carry parameter 5
je .L0 C 2
jmp .Loop C 2
EPILOGUE()
PROLOGUE(mpn_sub_n)
movq %rcx, %r10 C 3
shrq $2, %rcx C 4
je .Lend C 2
andl $3, %r10d C 4
C Main loop. 1 mod 16 aligned. Blocks between blank lines take one cycle.
.Loop: movq (%rsi), %rax C 3
movq 8(%rsi), %r9 C 4
leaq 32(%rsi), %rsi C 4
sbbq (%rdx), %rax C 3
movq %rax, (%rdi) C 3
sbbq 8(%rdx), %r9 C 4
movq %r9, 8(%rdi) C 4
movq -16(%rsi), %rax C 4
movq -8(%rsi), %r9 C 4
sbbq 16(%rdx), %rax C 4
movq %rax, 16(%rdi) C 4
sbbq 24(%rdx), %r9 C 4
movq %r9, 24(%rdi) C 4
decq %rcx C 3
leaq 32(%rdx), %rdx C 4
leaq 32(%rdi), %rdi C 4
jne .Loop C 2
incl %r10d C 3
decl %r10d C 3
jne .L0 C 2
sbbl %eax,%eax C 2
negl %eax C 2
ret C 1
.Lend: testl %eax, %eax C clear cy 2
.L0: decl %r10d C 3
jne .L1 C 2
movq (%rsi), %rax C 3
sbbq (%rdx), %rax C 3
movq %rax, (%rdi) C 3
sbbl %eax,%eax C 2
negl %eax C 2
ret C 1
.L1: decl %r10d C 3
jne .L2 C 2
movq (%rsi), %rax C 3
movq 8(%rsi), %r9 C 4
sbbq (%rdx), %rax C 3
movq %rax, (%rdi) C 3
sbbq 8(%rdx), %r9 C 4
movq %r9, 8(%rdi) C 4
sbbl %eax,%eax C 2
negl %eax C 2
ret C 1
.L2:
movq (%rsi), %rax C 3
movq 8(%rsi), %r9 C 4
sbbq (%rdx), %rax C 3
movq %rax, (%rdi) C 3
sbbq 8(%rdx), %r9 C 4
movq %r9, 8(%rdi) C 4
movq 16(%rsi), %rax C 4
sbbq 16(%rdx), %rax C 4
movq %rax, 16(%rdi) C 4
sbbl %eax,%eax C 2
negl %eax C 2
ret C 1
EPILOGUE()
|