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
|
/***************************************************************************
Copyright (c) 2013, The OpenBLAS Project
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.
3. Neither the name of the OpenBLAS project nor the names of
its contributors may be used to endorse or promote products
derived from this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "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 OPENBLAS PROJECT 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.
*****************************************************************************/
/**************************************************************************************
* 2013/11/11 Saar
* BLASTEST : OK
* CTEST : OK
* TEST : OK
*
**************************************************************************************/
#define ASSEMBLER
#include "common.h"
#define STACKSIZE 256
#define N r0
#define X r1
#define INC_X r2
#define OLD_Y r3
/******************************************************
* [fp, #-128] - [fp, #-64] is reserved
* for store and restore of floating point
* registers
*******************************************************/
#define OLD_INC_Y [fp, #4 ]
#define I r5
#define Y r6
#define INC_Y r7
#define X_PRE 512
/**************************************************************************************
* Macro definitions
**************************************************************************************/
.macro KERNEL_F4
pld [ X, #X_PRE ]
pld [ Y, #X_PRE ]
fldmias X!, { s4 - s5 }
fldmias Y!, { s8 - s9 }
fmacs s0 , s4, s8
fmacs s1 , s4, s9
fldmias X!, { s6 - s7 }
fmacs s2 , s5, s9
fmacs s3 , s5, s8
fldmias Y!, { s10 - s11 }
fmacs s0 , s6, s10
fmacs s1 , s6, s11
fmacs s2 , s7, s11
fmacs s3 , s7, s10
fldmias X!, { s4 - s5 }
fldmias Y!, { s8 - s9 }
fmacs s0 , s4, s8
fmacs s1 , s4, s9
fldmias X!, { s6 - s7 }
fmacs s2 , s5, s9
fmacs s3 , s5, s8
fldmias Y!, { s10 - s11 }
fmacs s0 , s6, s10
fmacs s1 , s6, s11
fmacs s2 , s7, s11
fmacs s3 , s7, s10
.endm
.macro KERNEL_F1
fldmias X!, { s4 - s5 }
fldmias Y!, { s8 - s9 }
fmacs s0 , s4, s8
fmacs s1 , s4, s9
fmacs s2 , s5, s9
fmacs s3 , s5, s8
.endm
/*************************************************************************************************************************/
.macro KERNEL_S4
nop
fldmias X, { s4 - s5 }
fldmias Y, { s8 - s9 }
fmacs s0 , s4, s8
fmacs s1 , s4, s9
fmacs s2 , s5, s9
fmacs s3 , s5, s8
add X, X, INC_X
add Y, Y, INC_Y
fldmias X, { s4 - s5 }
fldmias Y, { s8 - s9 }
fmacs s0 , s4, s8
fmacs s1 , s4, s9
fmacs s2 , s5, s9
fmacs s3 , s5, s8
add X, X, INC_X
add Y, Y, INC_Y
fldmias X, { s4 - s5 }
fldmias Y, { s8 - s9 }
fmacs s0 , s4, s8
fmacs s1 , s4, s9
fmacs s2 , s5, s9
fmacs s3 , s5, s8
add X, X, INC_X
add Y, Y, INC_Y
fldmias X, { s4 - s5 }
fldmias Y, { s8 - s9 }
fmacs s0 , s4, s8
fmacs s1 , s4, s9
fmacs s2 , s5, s9
fmacs s3 , s5, s8
add X, X, INC_X
add Y, Y, INC_Y
.endm
.macro KERNEL_S1
fldmias X, { s4 - s5 }
fldmias Y, { s8 - s9 }
fmacs s0 , s4, s8
fmacs s1 , s4, s9
fmacs s2 , s5, s9
fmacs s3 , s5, s8
add X, X, INC_X
add Y, Y, INC_Y
.endm
/**************************************************************************************
* End of macro definitions
**************************************************************************************/
PROLOGUE
.align 5
push {r4 - r9, fp}
add fp, sp, #24
sub sp, sp, #STACKSIZE // reserve stack
sub r4, fp, #128
vstm r4, { s8 - s15} // store floating point registers
mov Y, OLD_Y
ldr INC_Y, OLD_INC_Y
vsub.f32 s0 , s0 , s0
vsub.f32 s1 , s1 , s1
vsub.f32 s2 , s2 , s2
vsub.f32 s3 , s3 , s3
cmp N, #0
ble cdot_kernel_L999
cmp INC_X, #0
beq cdot_kernel_L999
cmp INC_Y, #0
beq cdot_kernel_L999
cmp INC_X, #1
bne cdot_kernel_S_BEGIN
cmp INC_Y, #1
bne cdot_kernel_S_BEGIN
cdot_kernel_F_BEGIN:
asrs I, N, #2 // I = N / 4
ble cdot_kernel_F1
cdot_kernel_F4:
KERNEL_F4
subs I, I, #1
bne cdot_kernel_F4
cdot_kernel_F1:
ands I, N, #3
ble cdot_kernel_L999
cdot_kernel_F10:
KERNEL_F1
subs I, I, #1
bne cdot_kernel_F10
b cdot_kernel_L999
cdot_kernel_S_BEGIN:
lsl INC_X, INC_X, #3 // INC_X * SIZE * 2
lsl INC_Y, INC_Y, #3 // INC_Y * SIZE * 2
asrs I, N, #2 // I = N / 4
ble cdot_kernel_S1
cdot_kernel_S4:
KERNEL_S4
subs I, I, #1
bne cdot_kernel_S4
cdot_kernel_S1:
ands I, N, #3
ble cdot_kernel_L999
cdot_kernel_S10:
KERNEL_S1
subs I, I, #1
bne cdot_kernel_S10
cdot_kernel_L999:
sub r3, fp, #128
vldm r3, { s8 - s15} // restore floating point registers
#if !defined(CONJ)
vsub.f32 s0 , s0, s2
vadd.f32 s1 , s1, s3
#else
vadd.f32 s0 , s0, s2
vsub.f32 s1 , s1, s3
#endif
sub sp, fp, #24
pop {r4 - r9, fp}
bx lr
EPILOGUE
|
