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 ARM64 mpn_mul_1
dnl Contributed to the GNU project by Torbjörn Granlund.
dnl Copyright 2013, 2015, 2017 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 Cortex-A53 7.5-8
C Cortex-A57 7
C Cortex-A72
C X-Gene 4
C Apple M1 1
C TODO
C * Start first multiply earlier.
changecom(blah)
define(`rp', `x0')
define(`up', `x1')
define(`n', `x2')
define(`v0', `x3')
PROLOGUE(mpn_mul_1c)
adds xzr, xzr, xzr C clear cy flag
b L(com)
EPILOGUE()
PROLOGUE(mpn_mul_1)
adds x4, xzr, xzr C clear register and cy flag
L(com): lsr x17, n, #2
tbnz n, #0, L(bx1)
L(bx0): mov x11, x4
tbz n, #1, L(b00)
L(b10): ldp x4, x5, [up]
mul x8, x4, v0
umulh x10, x4, v0
cbz x17, L(2)
ldp x6, x7, [up,#16]!
mul x9, x5, v0
b L(mid)-8
L(2): mul x9, x5, v0
b L(2e)
L(bx1): ldr x7, [up],#8
mul x9, x7, v0
umulh x11, x7, v0
adds x9, x9, x4
str x9, [rp],#8
tbnz n, #1, L(b10)
L(b01): cbz x17, L(1)
L(b00): ldp x6, x7, [up]
mul x8, x6, v0
umulh x10, x6, v0
ldp x4, x5, [up,#16]
mul x9, x7, v0
adcs x12, x8, x11
umulh x11, x7, v0
add rp, rp, #16
sub x17, x17, #1
cbz x17, L(end)
ALIGN(16)
L(top): mul x8, x4, v0
ldp x6, x7, [up,#32]!
adcs x13, x9, x10
umulh x10, x4, v0
mul x9, x5, v0
stp x12, x13, [rp,#-16]
adcs x12, x8, x11
umulh x11, x5, v0
L(mid): mul x8, x6, v0
ldp x4, x5, [up,#16]
adcs x13, x9, x10
umulh x10, x6, v0
mul x9, x7, v0
stp x12, x13, [rp],#32
adcs x12, x8, x11
umulh x11, x7, v0
sub x17, x17, #1
cbnz x17, L(top)
L(end): mul x8, x4, v0
adcs x13, x9, x10
umulh x10, x4, v0
mul x9, x5, v0
stp x12, x13, [rp,#-16]
L(2e): adcs x12, x8, x11
umulh x11, x5, v0
adcs x13, x9, x10
stp x12, x13, [rp]
L(1): adc x0, x11, xzr
ret
EPILOGUE()
|
