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
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
|
/*
* Loongson SIMD utils
*
* Copyright (c) 2016 Loongson Technology Corporation Limited
* Copyright (c) 2016 Zhou Xiaoyong <zhouxiaoyong@loongson.cn>
*
* This file is part of FFmpeg.
*
* FFmpeg is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2.1 of the License, or (at your option) any later version.
*
* FFmpeg is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with FFmpeg; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
*/
#ifndef AVUTIL_MIPS_MMIUTILS_H
#define AVUTIL_MIPS_MMIUTILS_H
#include "config.h"
#include "libavutil/mips/asmdefs.h"
#if HAVE_LOONGSON2
#define DECLARE_VAR_LOW32 int32_t low32
#define RESTRICT_ASM_LOW32 [low32]"=&r"(low32),
#define DECLARE_VAR_ALL64 int64_t all64
#define RESTRICT_ASM_ALL64 [all64]"=&r"(all64),
#define DECLARE_VAR_ADDRT mips_reg addrt
#define RESTRICT_ASM_ADDRT [addrt]"=&r"(addrt),
#define MMI_LWX(reg, addr, stride, bias) \
PTR_ADDU "%[addrt], "#addr", "#stride" \n\t" \
"lw "#reg", "#bias"(%[addrt]) \n\t"
#define MMI_SWX(reg, addr, stride, bias) \
PTR_ADDU "%[addrt], "#addr", "#stride" \n\t" \
"sw "#reg", "#bias"(%[addrt]) \n\t"
#define MMI_LDX(reg, addr, stride, bias) \
PTR_ADDU "%[addrt], "#addr", "#stride" \n\t" \
"ld "#reg", "#bias"(%[addrt]) \n\t"
#define MMI_SDX(reg, addr, stride, bias) \
PTR_ADDU "%[addrt], "#addr", "#stride" \n\t" \
"sd "#reg", "#bias"(%[addrt]) \n\t"
#define MMI_LWC1(fp, addr, bias) \
"lwc1 "#fp", "#bias"("#addr") \n\t"
#define MMI_ULWC1(fp, addr, bias) \
"ulw %[low32], "#bias"("#addr") \n\t" \
"mtc1 %[low32], "#fp" \n\t"
#define MMI_LWXC1(fp, addr, stride, bias) \
PTR_ADDU "%[addrt], "#addr", "#stride" \n\t" \
MMI_LWC1(fp, %[addrt], bias)
#define MMI_SWC1(fp, addr, bias) \
"swc1 "#fp", "#bias"("#addr") \n\t"
#define MMI_USWC1(fp, addr, bias) \
"mfc1 %[low32], "#fp" \n\t" \
"usw %[low32], "#bias"("#addr") \n\t"
#define MMI_SWXC1(fp, addr, stride, bias) \
PTR_ADDU "%[addrt], "#addr", "#stride" \n\t" \
MMI_SWC1(fp, %[addrt], bias)
#define MMI_LDC1(fp, addr, bias) \
"ldc1 "#fp", "#bias"("#addr") \n\t"
#define MMI_ULDC1(fp, addr, bias) \
"uld %[all64], "#bias"("#addr") \n\t" \
"dmtc1 %[all64], "#fp" \n\t"
#define MMI_LDXC1(fp, addr, stride, bias) \
PTR_ADDU "%[addrt], "#addr", "#stride" \n\t" \
MMI_LDC1(fp, %[addrt], bias)
#define MMI_SDC1(fp, addr, bias) \
"sdc1 "#fp", "#bias"("#addr") \n\t"
#define MMI_USDC1(fp, addr, bias) \
"dmfc1 %[all64], "#fp" \n\t" \
"usd %[all64], "#bias"("#addr") \n\t"
#define MMI_SDXC1(fp, addr, stride, bias) \
PTR_ADDU "%[addrt], "#addr", "#stride" \n\t" \
MMI_SDC1(fp, %[addrt], bias)
#define MMI_LQ(reg1, reg2, addr, bias) \
"ld "#reg1", "#bias"("#addr") \n\t" \
"ld "#reg2", 8+"#bias"("#addr") \n\t"
#define MMI_SQ(reg1, reg2, addr, bias) \
"sd "#reg1", "#bias"("#addr") \n\t" \
"sd "#reg2", 8+"#bias"("#addr") \n\t"
#define MMI_LQC1(fp1, fp2, addr, bias) \
"ldc1 "#fp1", "#bias"("#addr") \n\t" \
"ldc1 "#fp2", 8+"#bias"("#addr") \n\t"
#define MMI_SQC1(fp1, fp2, addr, bias) \
"sdc1 "#fp1", "#bias"("#addr") \n\t" \
"sdc1 "#fp2", 8+"#bias"("#addr") \n\t"
#elif HAVE_LOONGSON3 /* !HAVE_LOONGSON2 */
#define DECLARE_VAR_ALL64
#define RESTRICT_ASM_ALL64
#define DECLARE_VAR_ADDRT
#define RESTRICT_ASM_ADDRT
#define MMI_LWX(reg, addr, stride, bias) \
"gslwx "#reg", "#bias"("#addr", "#stride") \n\t"
#define MMI_SWX(reg, addr, stride, bias) \
"gsswx "#reg", "#bias"("#addr", "#stride") \n\t"
#define MMI_LDX(reg, addr, stride, bias) \
"gsldx "#reg", "#bias"("#addr", "#stride") \n\t"
#define MMI_SDX(reg, addr, stride, bias) \
"gssdx "#reg", "#bias"("#addr", "#stride") \n\t"
#define MMI_LWC1(fp, addr, bias) \
"lwc1 "#fp", "#bias"("#addr") \n\t"
#if _MIPS_SIM == _ABIO32 /* workaround for 3A2000 gslwlc1 bug */
#define DECLARE_VAR_LOW32 int32_t low32
#define RESTRICT_ASM_LOW32 [low32]"=&r"(low32),
#define MMI_ULWC1(fp, addr, bias) \
"ulw %[low32], "#bias"("#addr") \n\t" \
"mtc1 %[low32], "#fp" \n\t"
#else /* _MIPS_SIM != _ABIO32 */
#define DECLARE_VAR_LOW32
#define RESTRICT_ASM_LOW32
#define MMI_ULWC1(fp, addr, bias) \
"gslwlc1 "#fp", 3+"#bias"("#addr") \n\t" \
"gslwrc1 "#fp", "#bias"("#addr") \n\t"
#endif /* _MIPS_SIM != _ABIO32 */
#define MMI_LWXC1(fp, addr, stride, bias) \
"gslwxc1 "#fp", "#bias"("#addr", "#stride") \n\t"
#define MMI_SWC1(fp, addr, bias) \
"swc1 "#fp", "#bias"("#addr") \n\t"
#define MMI_USWC1(fp, addr, bias) \
"gsswlc1 "#fp", 3+"#bias"("#addr") \n\t" \
"gsswrc1 "#fp", "#bias"("#addr") \n\t"
#define MMI_SWXC1(fp, addr, stride, bias) \
"gsswxc1 "#fp", "#bias"("#addr", "#stride") \n\t"
#define MMI_LDC1(fp, addr, bias) \
"ldc1 "#fp", "#bias"("#addr") \n\t"
#define MMI_ULDC1(fp, addr, bias) \
"gsldlc1 "#fp", 7+"#bias"("#addr") \n\t" \
"gsldrc1 "#fp", "#bias"("#addr") \n\t"
#define MMI_LDXC1(fp, addr, stride, bias) \
"gsldxc1 "#fp", "#bias"("#addr", "#stride") \n\t"
#define MMI_SDC1(fp, addr, bias) \
"sdc1 "#fp", "#bias"("#addr") \n\t"
#define MMI_USDC1(fp, addr, bias) \
"gssdlc1 "#fp", 7+"#bias"("#addr") \n\t" \
"gssdrc1 "#fp", "#bias"("#addr") \n\t"
#define MMI_SDXC1(fp, addr, stride, bias) \
"gssdxc1 "#fp", "#bias"("#addr", "#stride") \n\t"
#define MMI_LQ(reg1, reg2, addr, bias) \
"gslq "#reg1", "#reg2", "#bias"("#addr") \n\t"
#define MMI_SQ(reg1, reg2, addr, bias) \
"gssq "#reg1", "#reg2", "#bias"("#addr") \n\t"
#define MMI_LQC1(fp1, fp2, addr, bias) \
"gslqc1 "#fp1", "#fp2", "#bias"("#addr") \n\t"
#define MMI_SQC1(fp1, fp2, addr, bias) \
"gssqc1 "#fp1", "#fp2", "#bias"("#addr") \n\t"
#endif /* HAVE_LOONGSON2 */
/**
* backup register
*/
#define BACKUP_REG \
LOCAL_ALIGNED_16(double, temp_backup_reg, [8]); \
if (_MIPS_SIM == _ABI64) \
__asm__ volatile ( \
"gssqc1 $f25, $f24, 0x00(%[temp]) \n\t" \
"gssqc1 $f27, $f26, 0x10(%[temp]) \n\t" \
"gssqc1 $f29, $f28, 0x20(%[temp]) \n\t" \
"gssqc1 $f31, $f30, 0x30(%[temp]) \n\t" \
: \
: [temp]"r"(temp_backup_reg) \
: "memory" \
); \
else \
__asm__ volatile ( \
"gssqc1 $f22, $f20, 0x00(%[temp]) \n\t" \
"gssqc1 $f26, $f24, 0x10(%[temp]) \n\t" \
"gssqc1 $f30, $f28, 0x20(%[temp]) \n\t" \
: \
: [temp]"r"(temp_backup_reg) \
: "memory" \
);
/**
* recover register
*/
#define RECOVER_REG \
if (_MIPS_SIM == _ABI64) \
__asm__ volatile ( \
"gslqc1 $f25, $f24, 0x00(%[temp]) \n\t" \
"gslqc1 $f27, $f26, 0x10(%[temp]) \n\t" \
"gslqc1 $f29, $f28, 0x20(%[temp]) \n\t" \
"gslqc1 $f31, $f30, 0x30(%[temp]) \n\t" \
: \
: [temp]"r"(temp_backup_reg) \
: "memory" \
); \
else \
__asm__ volatile ( \
"gslqc1 $f22, $f20, 0x00(%[temp]) \n\t" \
"gslqc1 $f26, $f24, 0x10(%[temp]) \n\t" \
"gslqc1 $f30, $f28, 0x20(%[temp]) \n\t" \
: \
: [temp]"r"(temp_backup_reg) \
: "memory" \
);
/**
* brief: Transpose 2X2 word packaged data.
* fr_i0, fr_i1: src
* fr_o0, fr_o1: dst
*/
#define TRANSPOSE_2W(fr_i0, fr_i1, fr_o0, fr_o1) \
"punpcklwd "#fr_o0", "#fr_i0", "#fr_i1" \n\t" \
"punpckhwd "#fr_o1", "#fr_i0", "#fr_i1" \n\t"
/**
* brief: Transpose 4X4 half word packaged data.
* fr_i0, fr_i1, fr_i2, fr_i3: src & dst
* fr_t0, fr_t1, fr_t2, fr_t3: temporary register
*/
#define TRANSPOSE_4H(fr_i0, fr_i1, fr_i2, fr_i3, \
fr_t0, fr_t1, fr_t2, fr_t3) \
"punpcklhw "#fr_t0", "#fr_i0", "#fr_i1" \n\t" \
"punpckhhw "#fr_t1", "#fr_i0", "#fr_i1" \n\t" \
"punpcklhw "#fr_t2", "#fr_i2", "#fr_i3" \n\t" \
"punpckhhw "#fr_t3", "#fr_i2", "#fr_i3" \n\t" \
"punpcklwd "#fr_i0", "#fr_t0", "#fr_t2" \n\t" \
"punpckhwd "#fr_i1", "#fr_t0", "#fr_t2" \n\t" \
"punpcklwd "#fr_i2", "#fr_t1", "#fr_t3" \n\t" \
"punpckhwd "#fr_i3", "#fr_t1", "#fr_t3" \n\t"
/**
* brief: Transpose 8x8 byte packaged data.
* fr_i0~i7: src & dst
* fr_t0~t3: temporary register
*/
#define TRANSPOSE_8B(fr_i0, fr_i1, fr_i2, fr_i3, fr_i4, fr_i5, \
fr_i6, fr_i7, fr_t0, fr_t1, fr_t2, fr_t3) \
"punpcklbh "#fr_t0", "#fr_i0", "#fr_i1" \n\t" \
"punpckhbh "#fr_t1", "#fr_i0", "#fr_i1" \n\t" \
"punpcklbh "#fr_t2", "#fr_i2", "#fr_i3" \n\t" \
"punpckhbh "#fr_t3", "#fr_i2", "#fr_i3" \n\t" \
"punpcklbh "#fr_i0", "#fr_i4", "#fr_i5" \n\t" \
"punpckhbh "#fr_i1", "#fr_i4", "#fr_i5" \n\t" \
"punpcklbh "#fr_i2", "#fr_i6", "#fr_i7" \n\t" \
"punpckhbh "#fr_i3", "#fr_i6", "#fr_i7" \n\t" \
"punpcklhw "#fr_i4", "#fr_t0", "#fr_t2" \n\t" \
"punpckhhw "#fr_i5", "#fr_t0", "#fr_t2" \n\t" \
"punpcklhw "#fr_i6", "#fr_t1", "#fr_t3" \n\t" \
"punpckhhw "#fr_i7", "#fr_t1", "#fr_t3" \n\t" \
"punpcklhw "#fr_t0", "#fr_i0", "#fr_i2" \n\t" \
"punpckhhw "#fr_t1", "#fr_i0", "#fr_i2" \n\t" \
"punpcklhw "#fr_t2", "#fr_i1", "#fr_i3" \n\t" \
"punpckhhw "#fr_t3", "#fr_i1", "#fr_i3" \n\t" \
"punpcklwd "#fr_i0", "#fr_i4", "#fr_t0" \n\t" \
"punpckhwd "#fr_i1", "#fr_i4", "#fr_t0" \n\t" \
"punpcklwd "#fr_i2", "#fr_i5", "#fr_t1" \n\t" \
"punpckhwd "#fr_i3", "#fr_i5", "#fr_t1" \n\t" \
"punpcklwd "#fr_i4", "#fr_i6", "#fr_t2" \n\t" \
"punpckhwd "#fr_i5", "#fr_i6", "#fr_t2" \n\t" \
"punpcklwd "#fr_i6", "#fr_i7", "#fr_t3" \n\t" \
"punpckhwd "#fr_i7", "#fr_i7", "#fr_t3" \n\t"
/**
* brief: Parallel SRA for 8 byte packaged data.
* fr_i0: src
* fr_i1: SRA number(SRAB number + 8)
* fr_t0, fr_t1: temporary register
* fr_d0: dst
*/
#define PSRAB_MMI(fr_i0, fr_i1, fr_t0, fr_t1, fr_d0) \
"punpcklbh "#fr_t0", "#fr_t0", "#fr_i0" \n\t" \
"punpckhbh "#fr_t1", "#fr_t1", "#fr_i0" \n\t" \
"psrah "#fr_t0", "#fr_t0", "#fr_i1" \n\t" \
"psrah "#fr_t1", "#fr_t1", "#fr_i1" \n\t" \
"packsshb "#fr_d0", "#fr_t0", "#fr_t1" \n\t"
/**
* brief: Parallel SRL for 8 byte packaged data.
* fr_i0: src
* fr_i1: SRL number(SRLB number + 8)
* fr_t0, fr_t1: temporary register
* fr_d0: dst
*/
#define PSRLB_MMI(fr_i0, fr_i1, fr_t0, fr_t1, fr_d0) \
"punpcklbh "#fr_t0", "#fr_t0", "#fr_i0" \n\t" \
"punpckhbh "#fr_t1", "#fr_t1", "#fr_i0" \n\t" \
"psrlh "#fr_t0", "#fr_t0", "#fr_i1" \n\t" \
"psrlh "#fr_t1", "#fr_t1", "#fr_i1" \n\t" \
"packsshb "#fr_d0", "#fr_t0", "#fr_t1" \n\t"
#define PSRAH_4_MMI(fp1, fp2, fp3, fp4, shift) \
"psrah "#fp1", "#fp1", "#shift" \n\t" \
"psrah "#fp2", "#fp2", "#shift" \n\t" \
"psrah "#fp3", "#fp3", "#shift" \n\t" \
"psrah "#fp4", "#fp4", "#shift" \n\t"
#define PSRAH_8_MMI(fp1, fp2, fp3, fp4, fp5, fp6, fp7, fp8, shift) \
PSRAH_4_MMI(fp1, fp2, fp3, fp4, shift) \
PSRAH_4_MMI(fp5, fp6, fp7, fp8, shift)
/**
* brief: (((value) + (1 << ((n) - 1))) >> (n))
* fr_i0: src & dst
* fr_i1: Operand number
* fr_t0, fr_t1: temporary FPR
* gr_t0: temporary GPR
*/
#define ROUND_POWER_OF_TWO_MMI(fr_i0, fr_i1, fr_t0, fr_t1, gr_t0) \
"li "#gr_t0", 0x01 \n\t" \
"dmtc1 "#gr_t0", "#fr_t0" \n\t" \
"punpcklwd "#fr_t0", "#fr_t0", "#fr_t0" \n\t" \
"psubw "#fr_t1", "#fr_i1", "#fr_t0" \n\t" \
"psllw "#fr_t1", "#fr_t0", "#fr_t1" \n\t" \
"paddw "#fr_i0", "#fr_i0", "#fr_t1" \n\t" \
"psraw "#fr_i0", "#fr_i0", "#fr_i1" \n\t"
#endif /* AVUTILS_MIPS_MMIUTILS_H */
|
