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
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
|
dnl SPARC v9 32-bit mpn_submul_1 -- Multiply a limb vector with a limb and
dnl subtract the result from a second limb vector.
dnl Copyright (C) 1998, 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 Library General Public License as published
dnl by the Free Software Foundation; either version 2 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 Library General Public
dnl License for more details.
dnl You should have received a copy of the GNU Library 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')
C INPUT PARAMETERS
C res_ptr i0
C s1_ptr i1
C size i2
C s2_limb i3
ASM_START()
TEXT
ALIGN(4)
L(noll):
.word 0
PROLOGUE(mpn_submul_1)
save %sp,-256,%sp
ifdef(`PIC',
`L(pc): rd %pc,%o7
ld [%o7+L(noll)-L(pc)],%f10',
` sethi %hi(L(noll)),%g1
ld [%g1+%lo(L(noll))],%f10')
sethi %hi(0xffff0000),%o0
andn %i3,%o0,%o0
st %o0,[%fp-16]
ld [%fp-16],%f11
fxtod %f10,%f6
srl %i3,16,%o0
st %o0,[%fp-16]
ld [%fp-16],%f11
fxtod %f10,%f8
mov 0,%g3 C cy = 0
ld [%i1],%f11
subcc %i2,1,%i2
be,pn %icc,L(end1)
add %i1,4,%i1 C s1_ptr++
fxtod %f10,%f2
ld [%i1],%f11
add %i1,4,%i1 C s1_ptr++
fmuld %f2,%f8,%f16
fmuld %f2,%f6,%f4
fdtox %f16,%f14
std %f14,[%fp-24]
fdtox %f4,%f12
subcc %i2,1,%i2
be,pn %icc,L(end2)
std %f12,[%fp-16]
fxtod %f10,%f2
ld [%i1],%f11
add %i1,4,%i1 C s1_ptr++
fmuld %f2,%f8,%f16
fmuld %f2,%f6,%f4
fdtox %f16,%f14
std %f14,[%fp-40]
fdtox %f4,%f12
subcc %i2,1,%i2
be,pn %icc,L(end3)
std %f12,[%fp-32]
fxtod %f10,%f2
ld [%i1],%f11
add %i1,4,%i1 C s1_ptr++
ld [%i0],%g5
ldx [%fp-24],%g2 C p16
fmuld %f2,%f8,%f16
ldx [%fp-16],%g1 C p0
fmuld %f2,%f6,%f4
sllx %g2,16,%g2 C align p16
fdtox %f16,%f14
add %g2,%g1,%g1 C add p16 to p0 (ADD1)
std %f14,[%fp-24]
fdtox %f4,%f12
add %i0,4,%i0 C res_ptr++
subcc %i2,1,%i2
be,pn %icc,L(end4)
std %f12,[%fp-16]
b,a L(loopm)
.align 16
C BEGIN LOOP
L(loop):
fxtod %f10,%f2
ld [%i1],%f11
add %i1,4,%i1 C s1_ptr++
add %g3,%g1,%g4 C p += cy
subcc %g5,%g4,%l2 C add *res_ptr to p0 (ADD2)
ld [%i0],%g5
srlx %g4,32,%g3
ldx [%fp-24],%g2 C p16
fmuld %f2,%f8,%f16
ldx [%fp-16],%g1 C p0
fmuld %f2,%f6,%f4
sllx %g2,16,%g2 C align p16
st %l2,[%i0-4]
addx %g3,0,%g3
fdtox %f16,%f14
add %g2,%g1,%g1 C add p16 to p0 (ADD1)
std %f14,[%fp-24]
fdtox %f4,%f12
std %f12,[%fp-16]
subcc %i2,1,%i2
be,pn %icc,L(loope)
add %i0,4,%i0 C res_ptr++
L(loopm):
fxtod %f10,%f2
ld [%i1],%f11
add %i1,4,%i1 C s1_ptr++
add %g3,%g1,%g4 C p += cy
subcc %g5,%g4,%l2 C add *res_ptr to p0 (ADD2)
ld [%i0],%g5
srlx %g4,32,%g3
ldx [%fp-40],%g2 C p16
fmuld %f2,%f8,%f16
ldx [%fp-32],%g1 C p0
fmuld %f2,%f6,%f4
sllx %g2,16,%g2 C align p16
st %l2,[%i0-4]
addx %g3,0,%g3
fdtox %f16,%f14
add %g2,%g1,%g1 C add p16 to p0 (ADD1)
std %f14,[%fp-40]
fdtox %f4,%f12
std %f12,[%fp-32]
subcc %i2,1,%i2
bne,pt %icc,L(loop)
add %i0,4,%i0 C res_ptr++
C END LOOP
fxtod %f10,%f2
add %g3,%g1,%g4 C p += cy
subcc %g5,%g4,%l2 C add *res_ptr to p0 (ADD2)
ld [%i0],%g5
srlx %g4,32,%g3
ldx [%fp-24],%g2 C p16
fmuld %f2,%f8,%f16
ldx [%fp-16],%g1 C p0
fmuld %f2,%f6,%f4
sllx %g2,16,%g2 C align p16
st %l2,[%i0-4]
b,a L(xxx)
L(loope):
L(end4):
fxtod %f10,%f2
add %g3,%g1,%g4 C p += cy
subcc %g5,%g4,%l2 C add *res_ptr to p0 (ADD2)
ld [%i0],%g5
srlx %g4,32,%g3
ldx [%fp-40],%g2 C p16
fmuld %f2,%f8,%f16
ldx [%fp-32],%g1 C p0
fmuld %f2,%f6,%f4
sllx %g2,16,%g2 C align p16
st %l2,[%i0-4]
fdtox %f16,%f14
add %g2,%g1,%g1 C add p16 to p0 (ADD1)
std %f14,[%fp-40]
fdtox %f4,%f12
std %f12,[%fp-32]
add %i0,4,%i0 C res_ptr++
add %g3,%g1,%g4 C p += cy
subxcc %g5,%g4,%l2 C add *res_ptr to p0 (ADD2)
ld [%i0],%g5
srlx %g4,32,%g3
ldx [%fp-24],%g2 C p16
ldx [%fp-16],%g1 C p0
sllx %g2,16,%g2 C align p16
st %l2,[%i0-4]
b,a L(yyy)
L(end3):
fxtod %f10,%f2
ld [%i0],%g5
ldx [%fp-24],%g2 C p16
fmuld %f2,%f8,%f16
ldx [%fp-16],%g1 C p0
fmuld %f2,%f6,%f4
sllx %g2,16,%g2 C align p16
L(xxx): fdtox %f16,%f14
add %g2,%g1,%g1 C add p16 to p0 (ADD1)
std %f14,[%fp-24]
fdtox %f4,%f12
std %f12,[%fp-16]
add %i0,4,%i0 C res_ptr++
add %g3,%g1,%g4 C p += cy
subxcc %g5,%g4,%l2 C add *res_ptr to p0 (ADD2)
ld [%i0],%g5
srlx %g4,32,%g3
ldx [%fp-40],%g2 C p16
ldx [%fp-32],%g1 C p0
sllx %g2,16,%g2 C align p16
st %l2,[%i0-4]
add %g2,%g1,%g1 C add p16 to p0 (ADD1)
add %i0,4,%i0 C res_ptr++
add %g3,%g1,%g4 C p += cy
subxcc %g5,%g4,%l2 C add *res_ptr to p0 (ADD2)
ld [%i0],%g5
srlx %g4,32,%g3
ldx [%fp-24],%g2 C p16
ldx [%fp-16],%g1 C p0
sllx %g2,16,%g2 C align p16
st %l2,[%i0-4]
add %g2,%g1,%g1 C add p16 to p0 (ADD1)
add %i0,4,%i0 C res_ptr++
b,a L(ret)
L(end2):
fxtod %f10,%f2
fmuld %f2,%f8,%f16
fmuld %f2,%f6,%f4
fdtox %f16,%f14
std %f14,[%fp-40]
fdtox %f4,%f12
std %f12,[%fp-32]
ld [%i0],%g5
ldx [%fp-24],%g2 C p16
ldx [%fp-16],%g1 C p0
sllx %g2,16,%g2 C align p16
L(yyy): add %g2,%g1,%g1 C add p16 to p0 (ADD1)
add %i0,4,%i0 C res_ptr++
add %g3,%g1,%g4 C p += cy
subxcc %g5,%g4,%l2 C add *res_ptr to p0 (ADD2)
ld [%i0],%g5
srlx %g4,32,%g3
ldx [%fp-40],%g2 C p16
ldx [%fp-32],%g1 C p0
sllx %g2,16,%g2 C align p16
st %l2,[%i0-4]
add %g2,%g1,%g1 C add p16 to p0 (ADD1)
add %i0,4,%i0 C res_ptr++
b,a L(ret)
L(end1):
fxtod %f10,%f2
fmuld %f2,%f8,%f16
fmuld %f2,%f6,%f4
fdtox %f16,%f14
std %f14,[%fp-24]
fdtox %f4,%f12
std %f12,[%fp-16]
ld [%i0],%g5
ldx [%fp-24],%g2 C p16
ldx [%fp-16],%g1 C p0
sllx %g2,16,%g2 C align p16
add %g2,%g1,%g1 C add p16 to p0 (ADD1)
add %i0,4,%i0 C res_ptr++
L(ret): add %g3,%g1,%g4 C p += cy
subxcc %g5,%g4,%l2 C add *res_ptr to p0 (ADD2)
srlx %g4,32,%g3
st %l2,[%i0-4]
addx %g3,%g0,%g3
ret
restore %g0,%g3,%o0 C sideeffect: put cy in retreg
EPILOGUE(mpn_submul_1)
|
