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
|
dnl PowerPC-32 mpn_sec_tabselect.
dnl Contributed to the GNU project by Torbjörn Granlund.
dnl Copyright 2011-2013 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 603e: ?
C 604e: ?
C 75x (G3): ?
C 7400,7410 (G4): 2.5
C 744x,745x (G4+): 2.0
C power4/ppc970: 2.0
C power5: ?
define(`rp', `r3')
define(`tp', `r4')
define(`n', `r5')
define(`nents', `r6')
define(`which', `r7')
define(`i', `r8')
define(`j', `r9')
define(`stride', `r12')
define(`mask', `r11')
ASM_START()
PROLOGUE(mpn_sec_tabselect)
stwu r1, -32(r1)
addic. j, n, -4 C outer loop induction variable
stmw r27, 8(r1)
slwi stride, n, 2
blt cr0, L(outer_end)
L(outer_top):
mtctr nents
mr r10, tp
li r28, 0
li r29, 0
li r30, 0
li r31, 0
addic. j, j, -4 C outer loop induction variable
mr i, which
ALIGN(16)
L(top): addic i, i, -1 C set carry iff i != 0
subfe mask, mask, mask
lwz r0, 0(tp)
lwz r27, 4(tp)
and r0, r0, mask
and r27, r27, mask
or r28, r28, r0
or r29, r29, r27
lwz r0, 8(tp)
lwz r27, 12(tp)
and r0, r0, mask
and r27, r27, mask
or r30, r30, r0
or r31, r31, r27
add tp, tp, stride
bdnz L(top)
stw r28, 0(rp)
stw r29, 4(rp)
stw r30, 8(rp)
stw r31, 12(rp)
addi tp, r10, 16
addi rp, rp, 16
bge cr0, L(outer_top)
L(outer_end):
andi. r0, n, 2
beq cr0, L(b0x)
L(b1x): mtctr nents
mr r10, tp
li r28, 0
li r29, 0
mr i, which
ALIGN(16)
L(tp2): addic i, i, -1
subfe mask, mask, mask
lwz r0, 0(tp)
lwz r27, 4(tp)
and r0, r0, mask
and r27, r27, mask
or r28, r28, r0
or r29, r29, r27
add tp, tp, stride
bdnz L(tp2)
stw r28, 0(rp)
stw r29, 4(rp)
addi tp, r10, 8
addi rp, rp, 8
L(b0x): andi. r0, n, 1
beq cr0, L(b00)
L(b01): mtctr nents
mr r10, tp
li r28, 0
mr i, which
ALIGN(16)
L(tp1): addic i, i, -1
subfe mask, mask, mask
lwz r0, 0(tp)
and r0, r0, mask
or r28, r28, r0
add tp, tp, stride
bdnz L(tp1)
stw r28, 0(rp)
L(b00): lmw r27, 8(r1)
addi r1, r1, 32
blr
EPILOGUE()
|
