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
|
/*
* 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 "config.h"
#include "libavutil/attributes.h"
#include "libswscale/swscale.h"
#include "libswscale/swscale_internal.h"
#include "libavutil/aarch64/cpu.h"
void ff_hscale16to15_4_neon_asm(int shift, int16_t *_dst, int dstW,
const uint8_t *_src, const int16_t *filter,
const int32_t *filterPos, int filterSize);
void ff_hscale16to15_X8_neon_asm(int shift, int16_t *_dst, int dstW,
const uint8_t *_src, const int16_t *filter,
const int32_t *filterPos, int filterSize);
void ff_hscale16to15_X4_neon_asm(int shift, int16_t *_dst, int dstW,
const uint8_t *_src, const int16_t *filter,
const int32_t *filterPos, int filterSize);
void ff_hscale16to19_4_neon_asm(int shift, int16_t *_dst, int dstW,
const uint8_t *_src, const int16_t *filter,
const int32_t *filterPos, int filterSize);
void ff_hscale16to19_X8_neon_asm(int shift, int16_t *_dst, int dstW,
const uint8_t *_src, const int16_t *filter,
const int32_t *filterPos, int filterSize);
void ff_hscale16to19_X4_neon_asm(int shift, int16_t *_dst, int dstW,
const uint8_t *_src, const int16_t *filter,
const int32_t *filterPos, int filterSize);
static void ff_hscale16to15_4_neon(SwsInternal *c, int16_t *_dst, int dstW,
const uint8_t *_src, const int16_t *filter,
const int32_t *filterPos, int filterSize)
{
const AVPixFmtDescriptor *desc = av_pix_fmt_desc_get(c->opts.src_format);
int sh = desc->comp[0].depth - 1;
if (sh<15) {
sh = isAnyRGB(c->opts.src_format) || c->opts.src_format==AV_PIX_FMT_PAL8 ? 13 : (desc->comp[0].depth - 1);
} else if (desc->flags & AV_PIX_FMT_FLAG_FLOAT) { /* float input are process like uint 16bpc */
sh = 16 - 1;
}
ff_hscale16to15_4_neon_asm(sh, _dst, dstW, _src, filter, filterPos, filterSize);
}
static void ff_hscale16to15_X8_neon(SwsInternal *c, int16_t *_dst, int dstW,
const uint8_t *_src, const int16_t *filter,
const int32_t *filterPos, int filterSize)
{
const AVPixFmtDescriptor *desc = av_pix_fmt_desc_get(c->opts.src_format);
int sh = desc->comp[0].depth - 1;
if (sh<15) {
sh = isAnyRGB(c->opts.src_format) || c->opts.src_format==AV_PIX_FMT_PAL8 ? 13 : (desc->comp[0].depth - 1);
} else if (desc->flags & AV_PIX_FMT_FLAG_FLOAT) { /* float input are process like uint 16bpc */
sh = 16 - 1;
}
ff_hscale16to15_X8_neon_asm(sh, _dst, dstW, _src, filter, filterPos, filterSize);
}
static void ff_hscale16to15_X4_neon(SwsInternal *c, int16_t *_dst, int dstW,
const uint8_t *_src, const int16_t *filter,
const int32_t *filterPos, int filterSize)
{
const AVPixFmtDescriptor *desc = av_pix_fmt_desc_get(c->opts.src_format);
int sh = desc->comp[0].depth - 1;
if (sh<15) {
sh = isAnyRGB(c->opts.src_format) || c->opts.src_format==AV_PIX_FMT_PAL8 ? 13 : (desc->comp[0].depth - 1);
} else if (desc->flags & AV_PIX_FMT_FLAG_FLOAT) { /* float input are process like uint 16bpc */
sh = 16 - 1;
}
ff_hscale16to15_X4_neon_asm(sh, _dst, dstW, _src, filter, filterPos, filterSize);
}
static void ff_hscale16to19_4_neon(SwsInternal *c, int16_t *_dst, int dstW,
const uint8_t *_src, const int16_t *filter,
const int32_t *filterPos, int filterSize)
{
const AVPixFmtDescriptor *desc = av_pix_fmt_desc_get(c->opts.src_format);
int bits = desc->comp[0].depth - 1;
int sh = bits - 4;
if ((isAnyRGB(c->opts.src_format) || c->opts.src_format==AV_PIX_FMT_PAL8) && desc->comp[0].depth<16) {
sh = 9;
} else if (desc->flags & AV_PIX_FMT_FLAG_FLOAT) { /* float input are process like uint 16bpc */
sh = 16 - 1 - 4;
}
ff_hscale16to19_4_neon_asm(sh, _dst, dstW, _src, filter, filterPos, filterSize);
}
static void ff_hscale16to19_X8_neon(SwsInternal *c, int16_t *_dst, int dstW,
const uint8_t *_src, const int16_t *filter,
const int32_t *filterPos, int filterSize)
{
const AVPixFmtDescriptor *desc = av_pix_fmt_desc_get(c->opts.src_format);
int bits = desc->comp[0].depth - 1;
int sh = bits - 4;
if ((isAnyRGB(c->opts.src_format) || c->opts.src_format==AV_PIX_FMT_PAL8) && desc->comp[0].depth<16) {
sh = 9;
} else if (desc->flags & AV_PIX_FMT_FLAG_FLOAT) { /* float input are process like uint 16bpc */
sh = 16 - 1 - 4;
}
ff_hscale16to19_X8_neon_asm(sh, _dst, dstW, _src, filter, filterPos, filterSize);
}
static void ff_hscale16to19_X4_neon(SwsInternal *c, int16_t *_dst, int dstW,
const uint8_t *_src, const int16_t *filter,
const int32_t *filterPos, int filterSize)
{
const AVPixFmtDescriptor *desc = av_pix_fmt_desc_get(c->opts.src_format);
int bits = desc->comp[0].depth - 1;
int sh = bits - 4;
if ((isAnyRGB(c->opts.src_format) || c->opts.src_format==AV_PIX_FMT_PAL8) && desc->comp[0].depth<16) {
sh = 9;
} else if (desc->flags & AV_PIX_FMT_FLAG_FLOAT) { /* float input are process like uint 16bpc */
sh = 16 - 1 - 4;
}
ff_hscale16to19_X4_neon_asm(sh, _dst, dstW, _src, filter, filterPos, filterSize);
}
#define SCALE_FUNC(filter_n, from_bpc, to_bpc, opt) \
void ff_hscale ## from_bpc ## to ## to_bpc ## _ ## filter_n ## _ ## opt( \
SwsInternal *c, int16_t *data, \
int dstW, const uint8_t *src, \
const int16_t *filter, \
const int32_t *filterPos, int filterSize)
#define SCALE_FUNCS(filter_n, opt) \
SCALE_FUNC(filter_n, 8, 15, opt); \
SCALE_FUNC(filter_n, 8, 19, opt);
#define ALL_SCALE_FUNCS(opt) \
SCALE_FUNCS(4, opt); \
SCALE_FUNCS(X8, opt); \
SCALE_FUNCS(X4, opt)
ALL_SCALE_FUNCS(neon);
void ff_yuv2planeX_8_neon(const int16_t *filter, int filterSize,
const int16_t **src, uint8_t *dest, int dstW,
const uint8_t *dither, int offset);
void ff_yuv2plane1_8_neon(
const int16_t *src,
uint8_t *dest,
int dstW,
const uint8_t *dither,
int offset);
#define ASSIGN_SCALE_FUNC2(hscalefn, filtersize, opt) do { \
if (c->srcBpc == 8) { \
if(c->dstBpc <= 14) { \
hscalefn = \
ff_hscale8to15_ ## filtersize ## _ ## opt; \
} else \
hscalefn = \
ff_hscale8to19_ ## filtersize ## _ ## opt; \
} else { \
if (c->dstBpc <= 14) \
hscalefn = \
ff_hscale16to15_ ## filtersize ## _ ## opt; \
else \
hscalefn = \
ff_hscale16to19_ ## filtersize ## _ ## opt; \
} \
} while (0)
#define ASSIGN_SCALE_FUNC(hscalefn, filtersize, opt) do { \
if (filtersize == 4) \
ASSIGN_SCALE_FUNC2(hscalefn, 4, opt); \
else if (filtersize % 8 == 0) \
ASSIGN_SCALE_FUNC2(hscalefn, X8, opt); \
else if (filtersize % 4 == 0 && filtersize % 8 != 0) \
ASSIGN_SCALE_FUNC2(hscalefn, X4, opt); \
} while (0)
#define ASSIGN_VSCALE_FUNC(vscalefn, opt) \
switch (c->dstBpc) { \
case 8: vscalefn = ff_yuv2plane1_8_ ## opt; break; \
default: break; \
}
#define NEON_INPUT(name) \
void ff_##name##ToY_neon(uint8_t *dst, const uint8_t *src, const uint8_t *, \
const uint8_t *, int w, uint32_t *coeffs, void *); \
void ff_##name##ToUV_neon(uint8_t *, uint8_t *, const uint8_t *, \
const uint8_t *, const uint8_t *, int w, \
uint32_t *coeffs, void *); \
void ff_##name##ToUV_half_neon(uint8_t *, uint8_t *, const uint8_t *, \
const uint8_t *, const uint8_t *, int w, \
uint32_t *coeffs, void *)
NEON_INPUT(abgr32);
NEON_INPUT(argb32);
NEON_INPUT(bgr24);
NEON_INPUT(bgra32);
NEON_INPUT(rgb24);
NEON_INPUT(rgba32);
void ff_lumRangeFromJpeg_neon(int16_t *dst, int width);
void ff_chrRangeFromJpeg_neon(int16_t *dstU, int16_t *dstV, int width);
void ff_lumRangeToJpeg_neon(int16_t *dst, int width);
void ff_chrRangeToJpeg_neon(int16_t *dstU, int16_t *dstV, int width);
av_cold void ff_sws_init_range_convert_aarch64(SwsInternal *c)
{
int cpu_flags = av_get_cpu_flags();
if (have_neon(cpu_flags)) {
if (c->dstBpc <= 14) {
if (c->opts.src_range) {
c->lumConvertRange = ff_lumRangeFromJpeg_neon;
c->chrConvertRange = ff_chrRangeFromJpeg_neon;
} else {
c->lumConvertRange = ff_lumRangeToJpeg_neon;
c->chrConvertRange = ff_chrRangeToJpeg_neon;
}
}
}
}
av_cold void ff_sws_init_swscale_aarch64(SwsInternal *c)
{
int cpu_flags = av_get_cpu_flags();
if (have_neon(cpu_flags)) {
ASSIGN_SCALE_FUNC(c->hyScale, c->hLumFilterSize, neon);
ASSIGN_SCALE_FUNC(c->hcScale, c->hChrFilterSize, neon);
ASSIGN_VSCALE_FUNC(c->yuv2plane1, neon);
if (c->dstBpc == 8) {
c->yuv2planeX = ff_yuv2planeX_8_neon;
}
switch (c->opts.src_format) {
case AV_PIX_FMT_ABGR:
c->lumToYV12 = ff_abgr32ToY_neon;
if (c->chrSrcHSubSample)
c->chrToYV12 = ff_abgr32ToUV_half_neon;
else
c->chrToYV12 = ff_abgr32ToUV_neon;
break;
case AV_PIX_FMT_ARGB:
c->lumToYV12 = ff_argb32ToY_neon;
if (c->chrSrcHSubSample)
c->chrToYV12 = ff_argb32ToUV_half_neon;
else
c->chrToYV12 = ff_argb32ToUV_neon;
break;
case AV_PIX_FMT_BGR24:
c->lumToYV12 = ff_bgr24ToY_neon;
if (c->chrSrcHSubSample)
c->chrToYV12 = ff_bgr24ToUV_half_neon;
else
c->chrToYV12 = ff_bgr24ToUV_neon;
break;
case AV_PIX_FMT_BGRA:
c->lumToYV12 = ff_bgra32ToY_neon;
if (c->chrSrcHSubSample)
c->chrToYV12 = ff_bgra32ToUV_half_neon;
else
c->chrToYV12 = ff_bgra32ToUV_neon;
break;
case AV_PIX_FMT_RGB24:
c->lumToYV12 = ff_rgb24ToY_neon;
if (c->chrSrcHSubSample)
c->chrToYV12 = ff_rgb24ToUV_half_neon;
else
c->chrToYV12 = ff_rgb24ToUV_neon;
break;
case AV_PIX_FMT_RGBA:
c->lumToYV12 = ff_rgba32ToY_neon;
if (c->chrSrcHSubSample)
c->chrToYV12 = ff_rgba32ToUV_half_neon;
else
c->chrToYV12 = ff_rgba32ToUV_neon;
break;
default:
break;
}
}
}
|
