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
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
|
/*********************************************************************/
/* Copyright 2009, 2010 The University of Texas at Austin. */
/* All rights reserved. */
/* */
/* Redistribution and use in source and binary forms, with or */
/* without modification, are permitted provided that the following */
/* conditions are met: */
/* */
/* 1. Redistributions of source code must retain the above */
/* copyright notice, this list of conditions and the following */
/* disclaimer. */
/* */
/* 2. Redistributions in binary form must reproduce the above */
/* copyright notice, this list of conditions and the following */
/* disclaimer in the documentation and/or other materials */
/* provided with the distribution. */
/* */
/* THIS SOFTWARE IS PROVIDED BY THE UNIVERSITY OF TEXAS AT */
/* AUSTIN ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES, */
/* INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF */
/* MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE */
/* DISCLAIMED. IN NO EVENT SHALL THE UNIVERSITY OF TEXAS AT */
/* AUSTIN OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, */
/* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES */
/* (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE */
/* GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR */
/* BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF */
/* LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT */
/* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT */
/* OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE */
/* POSSIBILITY OF SUCH DAMAGE. */
/* */
/* The views and conclusions contained in the software and */
/* documentation are those of the authors and should not be */
/* interpreted as representing official policies, either expressed */
/* or implied, of The University of Texas at Austin. */
/*********************************************************************/
#define ASSEMBLER
#include "common.h"
#define STACK 8
#define ARGS 0
#define STACK_M 4 + STACK + ARGS(%esp)
#define STACK_X 8 + STACK + ARGS(%esp)
#define STACK_INCX 12 + STACK + ARGS(%esp)
#define I %eax
#define M %ecx
#define X %esi
#define INCX %ebx
#define xmm8 xmm4
#define xmm9 xmm5
#define xmm10 xmm6
#define xmm11 xmm7
#include "l1param.h"
PROLOGUE
PROFCODE
pushl %esi
pushl %ebx
movl STACK_M, M
movl STACK_X, X
movl STACK_INCX, INCX
xorps %xmm0, %xmm0
xorps %xmm1, %xmm1
testl M, M
jle .L999
testl INCX, INCX
jle .L999
pcmpeqb %xmm3, %xmm3
psrlq $1, %xmm3
sall $ZBASE_SHIFT, INCX
cmpl $2 * SIZE, INCX
jne .L40
subl $-16 * SIZE, X
addl M, M
testl $SIZE, X
je .L05
movsd -16 * SIZE(X), %xmm0
addl $SIZE, X
andps %xmm3, %xmm0
subl $1, M
jle .L999
ALIGN_3
.L05:
movl M, I
sarl $4, I
jle .L20
movaps -16 * SIZE(X), %xmm4
movaps -14 * SIZE(X), %xmm5
movaps -12 * SIZE(X), %xmm6
movaps -10 * SIZE(X), %xmm7
decl I
jle .L11
ALIGN_4
.L10:
#ifdef PREFETCH
PREFETCH (PREFETCHSIZE + 0) - PREOFFSET(X)
#endif
andps %xmm3, %xmm4
addpd %xmm4, %xmm0
movaps -8 * SIZE(X), %xmm4
andps %xmm3, %xmm5
addpd %xmm5, %xmm1
movaps -6 * SIZE(X), %xmm5
andps %xmm3, %xmm6
addpd %xmm6, %xmm0
movaps -4 * SIZE(X), %xmm6
andps %xmm3, %xmm7
addpd %xmm7, %xmm1
movaps -2 * SIZE(X), %xmm7
#if defined(PREFETCH) && !defined(FETCH128)
PREFETCH (PREFETCHSIZE + 64) - PREOFFSET(X)
#endif
andps %xmm3, %xmm4
addpd %xmm4, %xmm0
movaps 0 * SIZE(X), %xmm4
andps %xmm3, %xmm5
addpd %xmm5, %xmm1
movaps 2 * SIZE(X), %xmm5
andps %xmm3, %xmm6
addpd %xmm6, %xmm0
movaps 4 * SIZE(X), %xmm6
andps %xmm3, %xmm7
addpd %xmm7, %xmm1
movaps 6 * SIZE(X), %xmm7
subl $-16 * SIZE, X
decl I
jg .L10
ALIGN_4
.L11:
andps %xmm3, %xmm4
addpd %xmm4, %xmm0
movaps -8 * SIZE(X), %xmm4
andps %xmm3, %xmm5
addpd %xmm5, %xmm1
movaps -6 * SIZE(X), %xmm5
andps %xmm3, %xmm6
addpd %xmm6, %xmm0
movaps -4 * SIZE(X), %xmm6
andps %xmm3, %xmm7
addpd %xmm7, %xmm1
movaps -2 * SIZE(X), %xmm7
andps %xmm3, %xmm4
addpd %xmm4, %xmm0
andps %xmm3, %xmm5
addpd %xmm5, %xmm1
andps %xmm3, %xmm6
addpd %xmm6, %xmm0
andps %xmm3, %xmm7
addpd %xmm7, %xmm1
subl $-16 * SIZE, X
ALIGN_3
.L20:
andl $15, M
jle .L999
testl $8, M
je .L21
movaps -16 * SIZE(X), %xmm4
movaps -14 * SIZE(X), %xmm5
movaps -12 * SIZE(X), %xmm6
movaps -10 * SIZE(X), %xmm7
andps %xmm3, %xmm4
addpd %xmm4, %xmm0
andps %xmm3, %xmm5
addpd %xmm5, %xmm1
andps %xmm3, %xmm6
addpd %xmm6, %xmm0
andps %xmm3, %xmm7
addpd %xmm7, %xmm1
addl $8 * SIZE, X
ALIGN_3
.L21:
testl $4, M
je .L22
movaps -16 * SIZE(X), %xmm4
movaps -14 * SIZE(X), %xmm5
andps %xmm3, %xmm4
addpd %xmm4, %xmm0
andps %xmm3, %xmm5
addpd %xmm5, %xmm1
addl $4 * SIZE, X
ALIGN_3
.L22:
testl $2, M
je .L23
movaps -16 * SIZE(X), %xmm4
andps %xmm3, %xmm4
addpd %xmm4, %xmm0
addl $2 * SIZE, X
.L23:
testl $1, M
je .L999
#ifdef movsd
xorps %xmm4, %xmm4
#endif
movsd -16 * SIZE(X), %xmm4
andps %xmm3, %xmm4
addsd %xmm4, %xmm0
jmp .L999
ALIGN_3
.L40:
movl M, I
sarl $2, I
jle .L60
ALIGN_4
.L50:
movsd 0 * SIZE(X), %xmm4
movhps 1 * SIZE(X), %xmm4
addl INCX, X
andps %xmm3, %xmm4
addpd %xmm4, %xmm0
movsd 0 * SIZE(X), %xmm5
movhps 1 * SIZE(X), %xmm5
addl INCX, X
andps %xmm3, %xmm5
addpd %xmm5, %xmm1
movsd 0 * SIZE(X), %xmm6
movhps 1 * SIZE(X), %xmm6
addl INCX, X
andps %xmm3, %xmm6
addpd %xmm6, %xmm0
movsd 0 * SIZE(X), %xmm7
movhps 1 * SIZE(X), %xmm7
addl INCX, X
andps %xmm3, %xmm7
addpd %xmm7, %xmm1
decl I
jg .L50
ALIGN_4
.L60:
andl $3, M
jle .L999
ALIGN_4
.L61:
movsd 0 * SIZE(X), %xmm4
movhps 1 * SIZE(X), %xmm4
andps %xmm3, %xmm4
addpd %xmm4, %xmm0
addl INCX, X
decl M
jg .L61
ALIGN_4
.L999:
addpd %xmm1, %xmm0
#ifndef HAVE_SSE3
movaps %xmm0, %xmm1
unpckhpd %xmm0, %xmm0
addsd %xmm1, %xmm0
#else
haddpd %xmm0, %xmm0
#endif
movsd %xmm0, STACK_M
fldl STACK_M
popl %ebx
popl %esi
ret
EPILOGUE
|
