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
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
|
/* -*-arm64-*-
* vim: syntax=arm64asm
*
* Copyright (c) 2022 J. Dekker <jdek@itanimul.li>
*
* 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
*/
#include "libavutil/aarch64/asm.S"
#define MAX_PB_SIZE 64
const qpel_filters, align=4
.byte 0, 0, 0, 0, 0, 0, 0, 0
.byte -1, 4,-10, 58, 17, -5, 1, 0
.byte -1, 4,-11, 40, 40,-11, 4, -1
.byte 0, 1, -5, 17, 58,-10, 4, -1
endconst
.macro load_filter m
movrel x15, qpel_filters
add x15, x15, \m, lsl #3
ld1 {v0.8b}, [x15]
sxtl v0.8h, v0.8b
.endm
.macro put_hevc type
.ifc \type, qpel
// void put_hevc_qpel_h(int16_t *dst,
// uint8_t *_src, ptrdiff_t _srcstride,
// int height, intptr_t mx, intptr_t my, int width)
dst .req x0
dststride .req x7
src .req x1
srcstride .req x2
height .req x3
heightw .req w3
mx .req x4
width .req w6
.endif
.ifc \type, qpel_uni
// void put_hevc_qpel_uni_h(uint8_t *_dst, ptrdiff_t _dststride,
// uint8_t *_src, ptrdiff_t _srcstride,
// int height, intptr_t mx, intptr_t my, int width)
dst .req x0
dststride .req x1
src .req x2
srcstride .req x3
height .req x4
heightw .req w4
mx .req x5
width .req w7
.endif
.ifc \type, qpel_bi
// void put_hevc_qpel_bi_h(uint8_t *_dst, ptrdiff_t _dststride,
// uint8_t *_src, ptrdiff_t _srcstride,
// int16_t *src2, int height, intptr_t mx,
// intptr_t my, int width)
dst .req x0
dststride .req x1
src .req x2
srcstride .req x3
height .req x5
heightw .req w5
mx .req x6
width .req w8
.endif
.ifc \type, qpel
function ff_hevc_put_hevc_h4_8_neon, export=0
uxtl v16.8h, v16.8b
uxtl v17.8h, v17.8b
uxtl v18.8h, v18.8b
uxtl v19.8h, v19.8b
mul v23.4h, v16.4h, v0.h[0]
mul v24.4h, v18.4h, v0.h[0]
.irpc i, 1234567
ext v20.16b, v16.16b, v17.16b, #(2*\i)
ext v21.16b, v18.16b, v19.16b, #(2*\i)
mla v23.4h, v20.4h, v0.h[\i]
mla v24.4h, v21.4h, v0.h[\i]
.endr
ret
endfunc
.endif
function ff_hevc_put_hevc_\type\()_h4_8_neon, export=1
load_filter mx
.ifc \type, qpel_bi
mov x16, #(MAX_PB_SIZE << 2) // src2bstridel
add x15, x4, #(MAX_PB_SIZE << 1) // src2b
.endif
sub src, src, #3
mov mx, x30
.ifc \type, qpel
mov dststride, #(MAX_PB_SIZE << 1)
lsl x13, srcstride, #1 // srcstridel
mov x14, #(MAX_PB_SIZE << 2)
.else
lsl x14, dststride, #1 // dststridel
lsl x13, srcstride, #1 // srcstridel
.endif
add x10, dst, dststride // dstb
add x12, src, srcstride // srcb
0: ld1 {v16.8b, v17.8b}, [src], x13
ld1 {v18.8b, v19.8b}, [x12], x13
.ifc \type, qpel_bi
ld1 {v25.8h}, [ x4], x16
ld1 {v26.8h}, [x15], x16
.endif
bl ff_hevc_put_hevc_h4_8_neon
subs heightw, heightw, #2
.ifc \type, qpel
st1 {v23.4h}, [dst], x14
st1 {v24.4h}, [x10], x14
.else
.ifc \type, qpel_bi
sqadd v23.4h, v23.4h, v25.4h
sqadd v24.4h, v24.4h, v26.4h
sqrshrun v23.8b, v23.8h, #7
sqrshrun v24.8b, v24.8h, #7
.else
sqrshrun v23.8b, v23.8h, #6
sqrshrun v24.8b, v24.8h, #6
.endif
st1 {v23.s}[0], [dst], x14
st1 {v24.s}[0], [x10], x14
.endif
b.gt 0b // double line
ret mx
endfunc
.ifc \type, qpel
function ff_hevc_put_hevc_h8_8_neon, export=0
uxtl v16.8h, v16.8b
uxtl v17.8h, v17.8b
uxtl v18.8h, v18.8b
uxtl v19.8h, v19.8b
mul v23.8h, v16.8h, v0.h[0]
mul v24.8h, v18.8h, v0.h[0]
.irpc i, 1234567
ext v20.16b, v16.16b, v17.16b, #(2*\i)
ext v21.16b, v18.16b, v19.16b, #(2*\i)
mla v23.8h, v20.8h, v0.h[\i]
mla v24.8h, v21.8h, v0.h[\i]
.endr
ret
endfunc
.endif
function ff_hevc_put_hevc_\type\()_h6_8_neon, export=1
load_filter mx
.ifc \type, qpel_bi
mov x16, #(MAX_PB_SIZE << 2) // src2bstridel
add x15, x4, #(MAX_PB_SIZE << 1) // src2b
.endif
sub src, src, #3
mov mx, x30
.ifc \type, qpel
mov dststride, #(MAX_PB_SIZE << 1)
lsl x13, srcstride, #1 // srcstridel
mov x14, #((MAX_PB_SIZE << 2) - 8)
.else
lsl x14, dststride, #1 // dststridel
lsl x13, srcstride, #1 // srcstridel
sub x14, x14, #4
.endif
add x10, dst, dststride // dstb
add x12, src, srcstride // srcb
0: ld1 {v16.8b, v17.8b}, [src], x13
ld1 {v18.8b, v19.8b}, [x12], x13
.ifc \type, qpel_bi
ld1 {v25.8h}, [ x4], x16
ld1 {v26.8h}, [x15], x16
.endif
bl ff_hevc_put_hevc_h8_8_neon
subs heightw, heightw, #2
.ifc \type, qpel
st1 {v23.4h}, [dst], #8
st1 {v24.4h}, [x10], #8
st1 {v23.s}[2], [dst], x14
st1 {v24.s}[2], [x10], x14
.else
.ifc \type, qpel_bi
sqadd v23.8h, v23.8h, v25.8h
sqadd v24.8h, v24.8h, v26.8h
sqrshrun v23.8b, v23.8h, #7
sqrshrun v24.8b, v24.8h, #7
.else
sqrshrun v23.8b, v23.8h, #6
sqrshrun v24.8b, v24.8h, #6
.endif
st1 {v23.s}[0], [dst], #4
st1 {v24.s}[0], [x10], #4
st1 {v23.h}[2], [dst], x14
st1 {v24.h}[2], [x10], x14
.endif
b.gt 0b // double line
ret mx
endfunc
function ff_hevc_put_hevc_\type\()_h8_8_neon, export=1
load_filter mx
.ifc \type, qpel_bi
mov x16, #(MAX_PB_SIZE << 2) // src2bstridel
add x15, x4, #(MAX_PB_SIZE << 1) // src2b
.endif
sub src, src, #3
mov mx, x30
.ifc \type, qpel
mov dststride, #(MAX_PB_SIZE << 1)
lsl x13, srcstride, #1 // srcstridel
mov x14, #(MAX_PB_SIZE << 2)
.else
lsl x14, dststride, #1 // dststridel
lsl x13, srcstride, #1 // srcstridel
.endif
add x10, dst, dststride // dstb
add x12, src, srcstride // srcb
0: ld1 {v16.8b, v17.8b}, [src], x13
ld1 {v18.8b, v19.8b}, [x12], x13
.ifc \type, qpel_bi
ld1 {v25.8h}, [ x4], x16
ld1 {v26.8h}, [x15], x16
.endif
bl ff_hevc_put_hevc_h8_8_neon
subs heightw, heightw, #2
.ifc \type, qpel
st1 {v23.8h}, [dst], x14
st1 {v24.8h}, [x10], x14
.else
.ifc \type, qpel_bi
sqadd v23.8h, v23.8h, v25.8h
sqadd v24.8h, v24.8h, v26.8h
sqrshrun v23.8b, v23.8h, #7
sqrshrun v24.8b, v24.8h, #7
.else
sqrshrun v23.8b, v23.8h, #6
sqrshrun v24.8b, v24.8h, #6
.endif
st1 {v23.8b}, [dst], x14
st1 {v24.8b}, [x10], x14
.endif
b.gt 0b // double line
ret mx
endfunc
.ifc \type, qpel
function ff_hevc_put_hevc_h16_8_neon, export=0
uxtl v16.8h, v16.8b
uxtl v17.8h, v17.8b
uxtl v18.8h, v18.8b
uxtl v19.8h, v19.8b
uxtl v20.8h, v20.8b
uxtl v21.8h, v21.8b
mul v26.8h, v16.8h, v0.h[0]
mul v27.8h, v17.8h, v0.h[0]
mul v28.8h, v19.8h, v0.h[0]
mul v29.8h, v20.8h, v0.h[0]
.irpc i, 1234567
ext v22.16b, v16.16b, v17.16b, #(2*\i)
ext v23.16b, v17.16b, v18.16b, #(2*\i)
ext v24.16b, v19.16b, v20.16b, #(2*\i)
ext v25.16b, v20.16b, v21.16b, #(2*\i)
mla v26.8h, v22.8h, v0.h[\i]
mla v27.8h, v23.8h, v0.h[\i]
mla v28.8h, v24.8h, v0.h[\i]
mla v29.8h, v25.8h, v0.h[\i]
.endr
subs x9, x9, #2
ret
endfunc
.endif
function ff_hevc_put_hevc_\type\()_h12_8_neon, export=1
load_filter mx
sxtw height, heightw
.ifc \type, qpel_bi
ldrh w8, [sp] // width
mov x16, #(MAX_PB_SIZE << 2) // src2bstridel
lsl x17, height, #7 // src2b reset (height * (MAX_PB_SIZE << 1))
add x15, x4, #(MAX_PB_SIZE << 1) // src2b
.endif
sub src, src, #3
mov mx, x30
.ifc \type, qpel
mov dststride, #(MAX_PB_SIZE << 1)
lsl x13, srcstride, #1 // srcstridel
mov x14, #((MAX_PB_SIZE << 2) - 16)
.else
lsl x14, dststride, #1 // dststridel
lsl x13, srcstride, #1 // srcstridel
sub x14, x14, #8
.endif
add x10, dst, dststride // dstb
add x12, src, srcstride // srcb
0: mov x9, height
1: ld1 {v16.8b-v18.8b}, [src], x13
ld1 {v19.8b-v21.8b}, [x12], x13
bl ff_hevc_put_hevc_h16_8_neon
.ifc \type, qpel
st1 {v26.8h}, [dst], #16
st1 {v28.8h}, [x10], #16
st1 {v27.4h}, [dst], x14
st1 {v29.4h}, [x10], x14
.else
.ifc \type, qpel_bi
ld1 {v16.8h, v17.8h}, [ x4], x16
ld1 {v18.8h, v19.8h}, [x15], x16
sqadd v26.8h, v26.8h, v16.8h
sqadd v27.8h, v27.8h, v17.8h
sqadd v28.8h, v28.8h, v18.8h
sqadd v29.8h, v29.8h, v19.8h
sqrshrun v26.8b, v26.8h, #7
sqrshrun v27.8b, v27.8h, #7
sqrshrun v28.8b, v28.8h, #7
sqrshrun v29.8b, v29.8h, #7
.else
sqrshrun v26.8b, v26.8h, #6
sqrshrun v27.8b, v27.8h, #6
sqrshrun v28.8b, v28.8h, #6
sqrshrun v29.8b, v29.8h, #6
.endif
st1 {v26.8b}, [dst], #8
st1 {v28.8b}, [x10], #8
st1 {v27.s}[0], [dst], x14
st1 {v29.s}[0], [x10], x14
.endif
b.gt 1b // double line
subs width, width, #12
// reset src
msub src, srcstride, height, src
msub x12, srcstride, height, x12
// reset dst
msub dst, dststride, height, dst
msub x10, dststride, height, x10
.ifc \type, qpel_bi
// reset xsrc
sub x4, x4, x17
sub x15, x15, x17
add x4, x4, #24
add x15, x15, #24
.endif
add src, src, #12
add x12, x12, #12
.ifc \type, qpel
add dst, dst, #24
add x10, x10, #24
.else
add dst, dst, #12
add x10, x10, #12
.endif
b.gt 0b
ret mx
endfunc
function ff_hevc_put_hevc_\type\()_h16_8_neon, export=1
load_filter mx
sxtw height, heightw
mov mx, x30
.ifc \type, qpel_bi
ldrh w8, [sp] // width
mov x16, #(MAX_PB_SIZE << 2) // src2bstridel
lsl x17, x5, #7 // src2b reset
add x15, x4, #(MAX_PB_SIZE << 1) // src2b
.endif
sub src, src, #3
mov mx, x30
.ifc \type, qpel
mov dststride, #(MAX_PB_SIZE << 1)
lsl x13, srcstride, #1 // srcstridel
mov x14, #((MAX_PB_SIZE << 2) - 16)
.else
lsl x14, dststride, #1 // dststridel
lsl x13, srcstride, #1 // srcstridel
sub x14, x14, #8
.endif
add x10, dst, dststride // dstb
add x12, src, srcstride // srcb
0: mov x9, height
1: ld1 {v16.8b-v18.8b}, [src], x13
ld1 {v19.8b-v21.8b}, [x12], x13
bl ff_hevc_put_hevc_h16_8_neon
.ifc \type, qpel
st1 {v26.8h}, [dst], #16
st1 {v28.8h}, [x10], #16
st1 {v27.8h}, [dst], x14
st1 {v29.8h}, [x10], x14
.else
.ifc \type, qpel_bi
ld1 {v16.8h, v17.8h}, [ x4], x16
ld1 {v18.8h, v19.8h}, [x15], x16
sqadd v26.8h, v26.8h, v16.8h
sqadd v27.8h, v27.8h, v17.8h
sqadd v28.8h, v28.8h, v18.8h
sqadd v29.8h, v29.8h, v19.8h
sqrshrun v26.8b, v26.8h, #7
sqrshrun v27.8b, v27.8h, #7
sqrshrun v28.8b, v28.8h, #7
sqrshrun v29.8b, v29.8h, #7
.else
sqrshrun v26.8b, v26.8h, #6
sqrshrun v27.8b, v27.8h, #6
sqrshrun v28.8b, v28.8h, #6
sqrshrun v29.8b, v29.8h, #6
.endif
st1 {v26.8b}, [dst], #8
st1 {v28.8b}, [x10], #8
st1 {v27.8b}, [dst], x14
st1 {v29.8b}, [x10], x14
.endif
b.gt 1b // double line
subs width, width, #16
// reset src
msub src, srcstride, height, src
msub x12, srcstride, height, x12
// reset dst
msub dst, dststride, height, dst
msub x10, dststride, height, x10
.ifc \type, qpel_bi
// reset xsrc
sub x4, x4, x17
sub x15, x15, x17
add x4, x4, #32
add x15, x15, #32
.endif
add src, src, #16
add x12, x12, #16
.ifc \type, qpel
add dst, dst, #32
add x10, x10, #32
.else
add dst, dst, #16
add x10, x10, #16
.endif
b.gt 0b
ret mx
endfunc
.unreq height
.unreq heightw
.unreq width
.unreq src
.unreq dst
.unreq srcstride
.unreq dststride
.unreq mx
.endm
put_hevc qpel
put_hevc qpel_uni
put_hevc qpel_bi
|
