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
|
dnl Alpha EV5 __gmpn_lshift -- Shift a number left.
dnl Copyright (C) 1994, 1995, 2000 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 by
dnl the Free Software Foundation; either version 2.1 of the License, or (at your
dnl 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 to
dnl the Free Software Foundation, Inc., 59 Temple Place - Suite 330, Boston,
dnl MA 02111-1307, USA.
include(`../config.m4')
dnl INPUT PARAMETERS
dnl res_ptr r16
dnl s1_ptr r17
dnl size r18
dnl cnt r19
dnl This code runs at 3.25 cycles/limb on the EV5.
ASM_START()
PROLOGUE(mpn_lshift)
s8addq r18,r17,r17 C make r17 point at end of s1
ldq r4,-8(r17) C load first limb
subq r31,r19,r20
s8addq r18,r16,r16 C make r16 point at end of RES
subq r18,1,r18
and r18,4-1,r28 C number of limbs in first loop
srl r4,r20,r0 C compute function result
beq r28,$L0
subq r18,r28,r18
ALIGN(8)
$Loop0: ldq r3,-16(r17)
subq r16,8,r16
sll r4,r19,r5
subq r17,8,r17
subq r28,1,r28
srl r3,r20,r6
bis r3,r3,r4
bis r5,r6,r8
stq r8,0(r16)
bne r28,$Loop0
$L0: sll r4,r19,r24
beq r18,$Lend
C warm up phase 1
ldq r1,-16(r17)
subq r18,4,r18
ldq r2,-24(r17)
ldq r3,-32(r17)
ldq r4,-40(r17)
beq r18,$Lend1
C warm up phase 2
srl r1,r20,r7
sll r1,r19,r21
srl r2,r20,r8
ldq r1,-48(r17)
sll r2,r19,r22
ldq r2,-56(r17)
srl r3,r20,r5
bis r7,r24,r7
sll r3,r19,r23
bis r8,r21,r8
srl r4,r20,r6
ldq r3,-64(r17)
sll r4,r19,r24
ldq r4,-72(r17)
subq r18,4,r18
beq r18,$Lend2
ALIGN(16)
C main loop
$Loop: stq r7,-8(r16)
bis r5,r22,r5
stq r8,-16(r16)
bis r6,r23,r6
srl r1,r20,r7
subq r18,4,r18
sll r1,r19,r21
unop C ldq r31,-96(r17)
srl r2,r20,r8
ldq r1,-80(r17)
sll r2,r19,r22
ldq r2,-88(r17)
stq r5,-24(r16)
bis r7,r24,r7
stq r6,-32(r16)
bis r8,r21,r8
srl r3,r20,r5
unop C ldq r31,-96(r17)
sll r3,r19,r23
subq r16,32,r16
srl r4,r20,r6
ldq r3,-96(r17)
sll r4,r19,r24
ldq r4,-104(r17)
subq r17,32,r17
bne r18,$Loop
C cool down phase 2/1
$Lend2: stq r7,-8(r16)
bis r5,r22,r5
stq r8,-16(r16)
bis r6,r23,r6
srl r1,r20,r7
sll r1,r19,r21
srl r2,r20,r8
sll r2,r19,r22
stq r5,-24(r16)
bis r7,r24,r7
stq r6,-32(r16)
bis r8,r21,r8
srl r3,r20,r5
sll r3,r19,r23
srl r4,r20,r6
sll r4,r19,r24
C cool down phase 2/2
stq r7,-40(r16)
bis r5,r22,r5
stq r8,-48(r16)
bis r6,r23,r6
stq r5,-56(r16)
stq r6,-64(r16)
C cool down phase 2/3
stq r24,-72(r16)
ret r31,(r26),1
C cool down phase 1/1
$Lend1: srl r1,r20,r7
sll r1,r19,r21
srl r2,r20,r8
sll r2,r19,r22
srl r3,r20,r5
bis r7,r24,r7
sll r3,r19,r23
bis r8,r21,r8
srl r4,r20,r6
sll r4,r19,r24
C cool down phase 1/2
stq r7,-8(r16)
bis r5,r22,r5
stq r8,-16(r16)
bis r6,r23,r6
stq r5,-24(r16)
stq r6,-32(r16)
stq r24,-40(r16)
ret r31,(r26),1
$Lend: stq r24,-8(r16)
ret r31,(r26),1
EPILOGUE(mpn_lshift)
ASM_END()
|
