aboutsummaryrefslogtreecommitdiffstats
path: root/libavcodec/riscv/vc1dsp_rvv.S
blob: d8b62579aaf42508ebd32daea76844653f2a4f6b (plain) (blame)
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
485
486
487
488
489
490
491
492
493
494
495
496
497
498
/*
 * Copyright (c) 2023 Institue of Software Chinese Academy of Sciences (ISCAS).
 * Copyright (c) 2024 Rémi Denis-Courmont.
 *
 * 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/riscv/asm.S"

func ff_vc1_inv_trans_8x8_dc_rvv, zve64x
        lh            t2, (a2)
        vsetivli      zero, 8, e8, mf2, ta, ma
        vlse64.v      v0, (a0), a1
        sh1add        t2, t2, t2
        addi          t2, t2, 1
        srai          t2, t2, 1
        sh1add        t2, t2, t2
        addi          t2, t2, 16
        srai          t2, t2, 5
        li            t0, 8*8
        vsetvli       zero, t0, e16, m8, ta, ma
        vzext.vf2     v8, v0
        vadd.vx       v8, v8, t2
        vmax.vx       v8, v8, zero
        vsetvli       zero, zero, e8, m4, ta, ma
        vnclipu.wi    v0, v8, 0
        vsetivli      zero, 8, e8, mf2, ta, ma
        vsse64.v      v0, (a0), a1
        ret
endfunc

func ff_vc1_inv_trans_4x8_dc_rvv, zve32x
        lh            t2, (a2)
        vsetivli      zero, 8, e8, mf2, ta, ma
        vlse32.v      v0, (a0), a1
        slli          t1, t2, 4
        add           t2, t2, t1
        addi          t2, t2, 4
        srai          t2, t2, 3
        sh1add        t2, t2, t2
        slli          t2, t2, 2
        addi          t2, t2, 64
        srai          t2, t2, 7
        li            t0, 4*8
        vsetvli       zero, t0, e16, m4, ta, ma
        vzext.vf2     v4, v0
        vadd.vx       v4, v4, t2
        vmax.vx       v4, v4, zero
        vsetvli       zero, zero, e8, m2, ta, ma
        vnclipu.wi    v0, v4, 0
        vsetivli      zero, 8, e8, mf2, ta, ma
        vsse32.v      v0, (a0), a1
        ret
endfunc

func ff_vc1_inv_trans_8x4_dc_rvv, zve64x
        lh            t2, (a2)
        vsetivli      zero, 4, e8, mf4, ta, ma
        vlse64.v      v0, (a0), a1
        sh1add        t2, t2, t2
        addi          t2, t2, 1
        srai          t2, t2, 1
        slli          t1, t2, 4
        add           t2, t2, t1
        addi          t2, t2, 64
        srai          t2, t2, 7
        li            t0, 8*4
        vsetvli       zero, t0, e16, m4, ta, ma
        vzext.vf2     v4, v0
        vadd.vx       v4, v4, t2
        vmax.vx       v4, v4, zero
        vsetvli       zero, zero, e8, m2, ta, ma
        vnclipu.wi    v0, v4, 0
        vsetivli      zero, 4, e8, mf4, ta, ma
        vsse64.v      v0, (a0), a1
        ret
endfunc

func ff_vc1_inv_trans_4x4_dc_rvv, zve32x
        lh            t2, (a2)
        vsetivli      zero, 4, e8, mf4, ta, ma
        vlse32.v      v0, (a0), a1
        slli          t1, t2, 4
        add           t2, t2, t1
        addi          t2, t2, 4
        srai          t2, t2, 3
        slli          t1, t2, 4
        add           t2, t2, t1
        addi          t2, t2, 64
        srai          t2, t2, 7
        vsetivli      zero, 4*4, e16, m2, ta, ma
        vzext.vf2     v2, v0
        vadd.vx       v2, v2, t2
        vmax.vx       v2, v2, zero
        vsetvli       zero, zero, e8, m1, ta, ma
        vnclipu.wi    v0, v2, 0
        vsetivli      zero, 4, e8, mf4, ta, ma
        vsse32.v      v0, (a0), a1
        ret
endfunc

        .variant_cc ff_vc1_inv_trans_8_rvv
func ff_vc1_inv_trans_8_rvv, zve32x
        li      t4, 12
        vsll.vi v14, v6, 4
        li      t2, 6
        vsll.vi v12, v2, 4
        li      t5, 15
        vmul.vx v8, v0, t4
        li      t3, 9
        # t[2..5] = [6 9 12 15]
        vmul.vx v10, v4, t4
        vmul.vx v16, v2, t2
        vmacc.vx  v12, t2, v6  # t3
        vnmsac.vx v14, t2, v2 # -t4
        vadd.vv v24, v8, v10  # t1
        vsub.vv v25, v8, v10  # t2
        vadd.vv v28, v24, v12 # t5
        vsub.vv v31, v24, v12 # t8
        vsub.vv v29, v25, v14 # t6
        vadd.vv v30, v25, v14 # t7
        vsll.vi v20, v1, 4
        vsll.vi v22, v7, 2
        vmacc.vx  v20, t5, v3
        vmacc.vx  v22, t3, v5
        vsll.vi v21, v3, 2
        vsll.vi v23, v5, 4
        vadd.vv v24, v20, v22 # t1
        vnmsac.vx v21, t5, v1
        vmacc.vx  v23, t3, v7
        vsll.vi v20, v3, 4
        vsll.vi v22, v5, 2
        vadd.vv v25, v21, v23 # -t2
        vnmsac.vx v20, t3, v1
        vmacc.vx v22, t5, v7
        vsll.vi v21, v1, 2
        vsll.vi v23, v7, 4
        vsub.vv v26, v22, v20 # t3
        vnmsac.vx v21, t3, v3
        vnmsac.vx v23, t5, v5
        srli    t2, t1, 2
        vwadd.vv  v8, v28, v24
        vwsub.vv  v10, v29, v25
        vsub.vv v27, v21, v23 # t4
        vwadd.vv  v12, v30, v26
        vwadd.vv  v14, v31, v27
        beqz    t2, 1f # faster than 4x add t2=zero
        .irp    n,31,30,29,28
        vadd.vi v\n, v\n, 1
        .endr
1:
        vwsub.vv  v16, v31, v27
        vwsub.vv  v18, v30, v26
        vwadd.vv  v20, v29, v25
        vwsub.vv  v22, v28, v24
        vnclip.wx v0, v8, t1
        vnclip.wx v1, v10, t1
        vnclip.wx v2, v12, t1
        vnclip.wx v3, v14, t1
        vnclip.wx v4, v16, t1
        vnclip.wx v5, v18, t1
        vnclip.wx v6, v20, t1
        vnclip.wx v7, v22, t1
        jr      t0
endfunc

        .variant_cc ff_vc1_inv_trans_4_rvv
func ff_vc1_inv_trans_4_rvv, zve32x
        li      t3, 17
        vmul.vx v8, v0, t3
        li      t4, 22
        vmul.vx v10, v2, t3
        li      t2, 10
        vmul.vx v26, v1, t4
        vmul.vx v27, v3, t4
        vadd.vv v24, v8, v10  # t1
        vsub.vv v25, v8, v10  # t2
        vmacc.vx v26, t2, v3  # t3
        vnmsac.vx v27, t2, v1 # t4
        vwadd.vv  v8, v24, v26
        vwsub.vv  v10, v25, v27
        vwadd.vv  v12, v25, v27
        vwsub.vv  v14, v24, v26
        vnclip.wx v0, v8, t1
        vnclip.wx v1, v10, t1
        vnclip.wx v2, v12, t1
        vnclip.wx v3, v14, t1
        jr      t0
endfunc

func ff_vc1_inv_trans_8x8_rvv, zve32x
        csrwi    vxrm, 0
        vsetivli zero, 8, e16, m1, ta, ma
        addi     a1, a0, 1 * 8 * 2
        vle16.v  v0, (a0)
        addi     a2, a0, 2 * 8 * 2
        vle16.v  v1, (a1)
        addi     a3, a0, 3 * 8 * 2
        vle16.v  v2, (a2)
        addi     a4, a0, 4 * 8 * 2
        vle16.v  v3, (a3)
        addi     a5, a0, 5 * 8 * 2
        vle16.v  v4, (a4)
        addi     a6, a0, 6 * 8 * 2
        vle16.v  v5, (a5)
        addi     a7, a0, 7 * 8 * 2
        vle16.v  v6, (a6)
        vle16.v  v7, (a7)
        li       t1, 3
        jal      t0, ff_vc1_inv_trans_8_rvv
        vsseg8e16.v v0, (a0)
        .irp n,0,1,2,3,4,5,6,7
        vle16.v  v\n, (a\n)
        .endr
        li       t1, 7
        jal      t0, ff_vc1_inv_trans_8_rvv
        vse16.v  v0, (a0)
        vse16.v  v1, (a1)
        vse16.v  v2, (a2)
        vse16.v  v3, (a3)
        vse16.v  v4, (a4)
        vse16.v  v5, (a5)
        vse16.v  v6, (a6)
        vse16.v  v7, (a7)
        ret
endfunc

func ff_vc1_inv_trans_8x4_rvv, zve32x
        csrwi       vxrm, 0
        vsetivli    zero, 4, e16, mf2, ta, ma
        vlseg8e16.v v0, (a2)
        li          t1, 3
        jal         t0, ff_vc1_inv_trans_8_rvv
        vsseg8e16.v v0, (a2)
        addi        a3, a2, 1 * 8 * 2
        vsetivli    zero, 8, e16, m1, ta, ma
        vle16.v     v0, (a2)
        addi        a4, a2, 2 * 8 * 2
        vle16.v     v1, (a3)
        addi        a5, a2, 3 * 8 * 2
        vle16.v     v2, (a4)
        vle16.v     v3, (a5)
        li          t1, 7
        jal         t0, ff_vc1_inv_trans_4_rvv
        add         a3, a1, a0
        vle8.v      v8, (a0)
        add         a4, a1, a3
        vle8.v      v9, (a3)
        add         a5, a1, a4
        vle8.v      v10, (a4)
        vle8.v      v11, (a5)
        vsetvli     zero, zero, e8, mf2, ta, ma
        vwaddu.wv   v0, v0, v8
        vwaddu.wv   v1, v1, v9
        vwaddu.wv   v2, v2, v10
        vwaddu.wv   v3, v3, v11
        vsetvli     zero, zero, e16, m1, ta, ma
        .irp    n,0,1,2,3
        vmax.vx     v\n, v\n, zero
        .endr
        vsetvli     zero, zero, e8, mf2, ta, ma
        vnclipu.wi  v8, v0, 0
        vnclipu.wi  v9, v1, 0
        vse8.v      v8, (a0)
        vnclipu.wi  v10, v2, 0
        vse8.v      v9, (a3)
        vnclipu.wi  v11, v3, 0
        vse8.v      v10, (a4)
        vse8.v      v11, (a5)
        ret
endfunc

func ff_vc1_inv_trans_4x8_rvv, zve32x
        li           a3, 8 * 2
        csrwi        vxrm, 0
        vsetivli     zero, 8, e16, m1, ta, ma
        vlsseg4e16.v v0, (a2), a3
        li           t1, 3
        jal          t0, ff_vc1_inv_trans_4_rvv
        vssseg4e16.v v0, (a2), a3
        vsetivli     zero, 4, e16, mf2, ta, ma
        addi         t1, a2, 1 * 8 * 2
        vle16.v      v0, (a2)
        addi         t2, a2, 2 * 8 * 2
        vle16.v      v1, (t1)
        addi         t3, a2, 3 * 8 * 2
        vle16.v      v2, (t2)
        addi         t4, a2, 4 * 8 * 2
        vle16.v      v3, (t3)
        addi         t5, a2, 5 * 8 * 2
        vle16.v      v4, (t4)
        addi         t6, a2, 6 * 8 * 2
        vle16.v      v5, (t5)
        addi         t1, a2, 7 * 8 * 2
        vle16.v      v6, (t6)
        vle16.v      v7, (t1)
        li           t1, 7
        jal          t0, ff_vc1_inv_trans_8_rvv
        add          t0, a1, a0
        vle8.v       v8, (a0)
        add          t1, a1, t0
        vle8.v       v9, (t0)
        add          t2, a1, t1
        vle8.v       v10, (t1)
        add          t3, a1, t2
        vle8.v       v11, (t2)
        add          t4, a1, t3
        vle8.v       v12, (t3)
        add          t5, a1, t4
        vle8.v       v13, (t4)
        add          t6, a1, t5
        vle8.v       v14, (t5)
        vle8.v       v15, (t6)
        vsetvli      zero, zero, e8, mf4, ta, ma
        vwaddu.wv    v0, v0, v8
        vwaddu.wv    v1, v1, v9
        vwaddu.wv    v2, v2, v10
        vwaddu.wv    v3, v3, v11
        vwaddu.wv    v4, v4, v12
        vwaddu.wv    v5, v5, v13
        vwaddu.wv    v6, v6, v14
        vwaddu.wv    v7, v7, v15
        vsetvli      zero, zero, e16, mf2, ta, ma
        .irp    n,0,1,2,3,4,5,6,7
        vmax.vx      v\n, v\n, zero
        .endr
        vsetvli      zero, zero, e8, mf4, ta, ma
        vnclipu.wi   v8, v0, 0
        vnclipu.wi   v9, v1, 0
        vse8.v       v8, (a0)
        vnclipu.wi   v10, v2, 0
        vse8.v       v9, (t0)
        vnclipu.wi   v11, v3, 0
        vse8.v       v10, (t1)
        vnclipu.wi   v12, v4, 0
        vse8.v       v11, (t2)
        vnclipu.wi   v13, v5, 0
        vse8.v       v12, (t3)
        vnclipu.wi   v14, v6, 0
        vse8.v       v13, (t4)
        vnclipu.wi   v15, v7, 0
        vse8.v       v14, (t5)
        vse8.v       v15, (t6)
        ret
endfunc

func ff_vc1_inv_trans_4x4_rvv, zve32x
        li           a3, 8 * 2
        csrwi        vxrm, 0
        vsetivli     zero, 4, e16, mf2, ta, ma
        vlsseg4e16.v v0, (a2), a3
        li           t1, 3
        jal          t0, ff_vc1_inv_trans_4_rvv
        vssseg4e16.v v0, (a2), a3
        addi         t1, a2, 2 * 4 * 2
        vle16.v      v0, (a2)
        addi         t2, a2, 4 * 4 * 2
        vle16.v      v1, (t1)
        addi         t3, a2, 6 * 4 * 2
        vle16.v      v2, (t2)
        vle16.v      v3, (t3)
        li           t1, 7
        jal          t0, ff_vc1_inv_trans_4_rvv
        add          t1, a1, a0
        vle8.v       v8, (a0)
        add          t2, a1, t1
        vle8.v       v9, (t1)
        add          t3, a1, t2
        vle8.v       v10, (t2)
        vle8.v       v11, (t3)
        vsetvli      zero, zero, e8, mf4, ta, ma
        vwaddu.wv    v0, v0, v8
        vwaddu.wv    v1, v1, v9
        vwaddu.wv    v2, v2, v10
        vwaddu.wv    v3, v3, v11
        vsetvli      zero, zero, e16, mf2, ta, ma
        .irp    n,0,1,2,3
        vmax.vx      v\n, v\n, zero
        .endr
        vsetvli      zero, zero, e8, mf4, ta, ma
        vnclipu.wi   v8, v0, 0
        vnclipu.wi   v9, v1, 0
        vse8.v       v8, (a0)
        vnclipu.wi   v10, v2, 0
        vse8.v       v9, (t1)
        vnclipu.wi   v11, v3, 0
        vse8.v       v10, (t2)
        vse8.v       v11, (t3)
        ret
endfunc

.macro mspel_op op pos n1 n2
        add           t1, \pos, a2
        v\op\()e8.v   v\n1, (\pos)
        sh1add        \pos, a2, \pos
        v\op\()e8.v   v\n2, (t1)
.endm

.macro mspel_op_all op pos a1 a2 a3 a4 a5 a6 a7 a8 a9 a10 a11 a12 a13 a14 a15 a16
        mspel_op      \op \pos \a1 \a2
        mspel_op      \op \pos \a3 \a4
        mspel_op      \op \pos \a5 \a6
        mspel_op      \op \pos \a7 \a8
        mspel_op      \op \pos \a9 \a10
        mspel_op      \op \pos \a11 \a12
        mspel_op      \op \pos \a13 \a14
        mspel_op      \op \pos \a15 \a16
.endm

func ff_avg_pixels16x16_rvv, zve32x
        li       t0, 16
        vsetivli zero, 16, e8, m1, ta, ma
        j        1f
endfunc

func ff_avg_pixels8x8_rvv, zve32x
        li        t0, 8
        vsetivli  zero, 8, e8, mf2, ta, ma
1:
        csrwi     vxrm, 0
2:
        vle8.v    v16, (a1)
        addi      t0, t0, -1
        vle8.v    v8, (a0)
        add       a1, a1, a2
        vaaddu.vv v16, v16, v8
        vse8.v    v16, (a0)
        add       a0, a0, a2
        bnez      t0, 2b

        ret
endfunc

func ff_vc1_unescape_buffer_rvv, zve32x
        vsetivli       zero, 2, e8, m1, ta, ma
        vmv.v.i        v8, -1
        li             t4, 1
        vmv.v.i        v12, -1
        li             t3, -1
        mv             t5, a2
        blez           a1, 3f
1:
        vsetvli        t0, a1, e8, m4, ta, ma
        vle8.v         v16, (a0)
        vslideup.vi    v8, v16, 2
        addi           t0, t0, -1 # we cannot fully process the last element
        vslideup.vi    v12, v16, 1
        vslide1down.vx v20, v16, t3
        vsetvli        zero, t0, e8, m4, ta, ma
        vmseq.vi       v0, v8, 0
        vmseq.vi       v1, v12, 0
        vmseq.vi       v2, v16, 3
        vmand.mm       v0, v0, v1
        vmsltu.vi      v3, v20, 4
        vmand.mm       v0, v0, v2
        vmand.mm       v0, v0, v3
        vfirst.m       t2, v0
        bgez           t2, 4f # found an escape byte?

        vse8.v         v16, (a2)
        addi           t2, t0, -2
        add            a2, a2, t0
2:
        vslidedown.vx  v8, v16, t2
        sub            a1, a1, t0
        vslidedown.vi  v12, v8, 1
        add            a0, a0, t0
        bgtu           a1, t4, 1b // size > 1

        lb             t0, (a0)
        sb             t0, (a2) # copy last byte (cannot be escaped)
        addi           a2, a2, 1
3:
        sub            a0, a2, t5
        ret
4:
        vsetvli        zero, t2, e8, m4, ta, ma
        vse8.v         v16, (a2)
        addi           t0, t2, 1
        add            a2, a2, t2
        addi           t2, t2, -1
        vsetvli        zero, t0, e8, m4, ta, ma
        j              2b
endfunc