2016-02-08 16:14:17 +02:00
|
|
|
/*
|
|
|
|
|
* 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 "libswscale/swscale.h"
|
|
|
|
|
#include "libswscale/swscale_internal.h"
|
|
|
|
|
#include "libavutil/aarch64/cpu.h"
|
|
|
|
|
|
|
|
|
|
#define YUV_TO_RGB_TABLE \
|
|
|
|
|
c->yuv2rgb_v2r_coeff, \
|
|
|
|
|
c->yuv2rgb_u2g_coeff, \
|
|
|
|
|
c->yuv2rgb_v2g_coeff, \
|
|
|
|
|
c->yuv2rgb_u2b_coeff, \
|
|
|
|
|
|
|
|
|
|
#define DECLARE_FF_YUVX_TO_RGBX_FUNCS(ifmt, ofmt) \
|
|
|
|
|
int ff_##ifmt##_to_##ofmt##_neon(int w, int h, \
|
|
|
|
|
uint8_t *dst, int linesize, \
|
|
|
|
|
const uint8_t *srcY, int linesizeY, \
|
|
|
|
|
const uint8_t *srcU, int linesizeU, \
|
|
|
|
|
const uint8_t *srcV, int linesizeV, \
|
|
|
|
|
const int16_t *table, \
|
|
|
|
|
int y_offset, \
|
|
|
|
|
int y_coeff); \
|
|
|
|
|
\
|
2024-10-02 15:37:10 +02:00
|
|
|
static int ifmt##_to_##ofmt##_neon_wrapper(SwsContext *c, const uint8_t *const src[], \
|
|
|
|
|
const int srcStride[], int srcSliceY, \
|
|
|
|
|
int srcSliceH, uint8_t *const dst[], \
|
|
|
|
|
const int dstStride[]) { \
|
2016-02-08 16:14:17 +02:00
|
|
|
const int16_t yuv2rgb_table[] = { YUV_TO_RGB_TABLE }; \
|
|
|
|
|
\
|
2020-07-07 17:01:58 +02:00
|
|
|
return ff_##ifmt##_to_##ofmt##_neon(c->srcW, srcSliceH, \
|
|
|
|
|
dst[0] + srcSliceY * dstStride[0], dstStride[0], \
|
|
|
|
|
src[0], srcStride[0], \
|
|
|
|
|
src[1], srcStride[1], \
|
|
|
|
|
src[2], srcStride[2], \
|
|
|
|
|
yuv2rgb_table, \
|
|
|
|
|
c->yuv2rgb_y_offset >> 6, \
|
|
|
|
|
c->yuv2rgb_y_coeff); \
|
2016-02-08 16:14:17 +02:00
|
|
|
} \
|
|
|
|
|
|
2024-08-06 12:51:06 +02:00
|
|
|
#define DECLARE_FF_YUVX_TO_GBRP_FUNCS(ifmt, ofmt) \
|
|
|
|
|
int ff_##ifmt##_to_##ofmt##_neon(int w, int h, \
|
|
|
|
|
uint8_t *dst, int linesize, \
|
|
|
|
|
const uint8_t *srcY, int linesizeY, \
|
|
|
|
|
const uint8_t *srcU, int linesizeU, \
|
|
|
|
|
const uint8_t *srcV, int linesizeV, \
|
|
|
|
|
const int16_t *table, \
|
|
|
|
|
int y_offset, \
|
|
|
|
|
int y_coeff, \
|
|
|
|
|
uint8_t *dst1, int linesize1, \
|
|
|
|
|
uint8_t *dst2, int linesize2); \
|
|
|
|
|
\
|
2024-10-02 15:37:10 +02:00
|
|
|
static int ifmt##_to_##ofmt##_neon_wrapper(SwsContext *c, const uint8_t *const src[], \
|
|
|
|
|
const int srcStride[], int srcSliceY, \
|
|
|
|
|
int srcSliceH, uint8_t *const dst[], \
|
|
|
|
|
const int dstStride[]) { \
|
2024-08-06 12:51:06 +02:00
|
|
|
const int16_t yuv2rgb_table[] = { YUV_TO_RGB_TABLE }; \
|
|
|
|
|
\
|
|
|
|
|
return ff_##ifmt##_to_##ofmt##_neon(c->srcW, srcSliceH, \
|
|
|
|
|
dst[0] + srcSliceY * dstStride[0], dstStride[0], \
|
|
|
|
|
src[0], srcStride[0], \
|
|
|
|
|
src[1], srcStride[1], \
|
|
|
|
|
src[2], srcStride[2], \
|
|
|
|
|
yuv2rgb_table, \
|
|
|
|
|
c->yuv2rgb_y_offset >> 6, \
|
|
|
|
|
c->yuv2rgb_y_coeff, \
|
|
|
|
|
dst[1] + srcSliceY * dstStride[1], dstStride[1], \
|
|
|
|
|
dst[2] + srcSliceY * dstStride[2], dstStride[2]); \
|
|
|
|
|
} \
|
|
|
|
|
|
2016-02-08 16:14:17 +02:00
|
|
|
#define DECLARE_FF_YUVX_TO_ALL_RGBX_FUNCS(yuvx) \
|
|
|
|
|
DECLARE_FF_YUVX_TO_RGBX_FUNCS(yuvx, argb) \
|
|
|
|
|
DECLARE_FF_YUVX_TO_RGBX_FUNCS(yuvx, rgba) \
|
|
|
|
|
DECLARE_FF_YUVX_TO_RGBX_FUNCS(yuvx, abgr) \
|
|
|
|
|
DECLARE_FF_YUVX_TO_RGBX_FUNCS(yuvx, bgra) \
|
2024-08-06 12:51:06 +02:00
|
|
|
DECLARE_FF_YUVX_TO_GBRP_FUNCS(yuvx, gbrp) \
|
2016-02-08 16:14:17 +02:00
|
|
|
|
|
|
|
|
DECLARE_FF_YUVX_TO_ALL_RGBX_FUNCS(yuv420p)
|
|
|
|
|
DECLARE_FF_YUVX_TO_ALL_RGBX_FUNCS(yuv422p)
|
|
|
|
|
|
|
|
|
|
#define DECLARE_FF_NVX_TO_RGBX_FUNCS(ifmt, ofmt) \
|
|
|
|
|
int ff_##ifmt##_to_##ofmt##_neon(int w, int h, \
|
|
|
|
|
uint8_t *dst, int linesize, \
|
|
|
|
|
const uint8_t *srcY, int linesizeY, \
|
|
|
|
|
const uint8_t *srcC, int linesizeC, \
|
|
|
|
|
const int16_t *table, \
|
|
|
|
|
int y_offset, \
|
|
|
|
|
int y_coeff); \
|
|
|
|
|
\
|
2024-10-02 15:37:10 +02:00
|
|
|
static int ifmt##_to_##ofmt##_neon_wrapper(SwsContext *c, const uint8_t *const src[], \
|
|
|
|
|
const int srcStride[], int srcSliceY, \
|
|
|
|
|
int srcSliceH, uint8_t *const dst[], \
|
|
|
|
|
const int dstStride[]) { \
|
2016-02-08 16:14:17 +02:00
|
|
|
const int16_t yuv2rgb_table[] = { YUV_TO_RGB_TABLE }; \
|
|
|
|
|
\
|
2020-07-07 17:01:58 +02:00
|
|
|
return ff_##ifmt##_to_##ofmt##_neon(c->srcW, srcSliceH, \
|
|
|
|
|
dst[0] + srcSliceY * dstStride[0], dstStride[0], \
|
|
|
|
|
src[0], srcStride[0], src[1], srcStride[1], \
|
|
|
|
|
yuv2rgb_table, \
|
|
|
|
|
c->yuv2rgb_y_offset >> 6, \
|
|
|
|
|
c->yuv2rgb_y_coeff); \
|
2016-02-08 16:14:17 +02:00
|
|
|
} \
|
|
|
|
|
|
2024-08-06 12:51:06 +02:00
|
|
|
#define DECLARE_FF_NVX_TO_GBRP_FUNCS(ifmt, ofmt) \
|
|
|
|
|
int ff_##ifmt##_to_##ofmt##_neon(int w, int h, \
|
|
|
|
|
uint8_t *dst, int linesize, \
|
|
|
|
|
const uint8_t *srcY, int linesizeY, \
|
|
|
|
|
const uint8_t *srcC, int linesizeC, \
|
|
|
|
|
const int16_t *table, \
|
|
|
|
|
int y_offset, \
|
|
|
|
|
int y_coeff, \
|
|
|
|
|
uint8_t *dst1, int linesize1, \
|
|
|
|
|
uint8_t *dst2, int linesize2); \
|
|
|
|
|
\
|
2024-10-02 15:37:10 +02:00
|
|
|
static int ifmt##_to_##ofmt##_neon_wrapper(SwsContext *c, const uint8_t *const src[], \
|
|
|
|
|
const int srcStride[], int srcSliceY, \
|
|
|
|
|
int srcSliceH, uint8_t *const dst[], \
|
|
|
|
|
const int dstStride[]) { \
|
2024-08-06 12:51:06 +02:00
|
|
|
const int16_t yuv2rgb_table[] = { YUV_TO_RGB_TABLE }; \
|
|
|
|
|
\
|
|
|
|
|
return ff_##ifmt##_to_##ofmt##_neon(c->srcW, srcSliceH, \
|
|
|
|
|
dst[0] + srcSliceY * dstStride[0], dstStride[0], \
|
|
|
|
|
src[0], srcStride[0], src[1], srcStride[1], \
|
|
|
|
|
yuv2rgb_table, \
|
|
|
|
|
c->yuv2rgb_y_offset >> 6, \
|
|
|
|
|
c->yuv2rgb_y_coeff, \
|
|
|
|
|
dst[1] + srcSliceY * dstStride[1], dstStride[1], \
|
|
|
|
|
dst[2] + srcSliceY * dstStride[2], dstStride[2]); \
|
|
|
|
|
} \
|
|
|
|
|
|
2024-08-07 18:53:12 +02:00
|
|
|
void ff_nv24_to_yuv420p_chroma_neon(uint8_t *dst1, int dstStride1,
|
|
|
|
|
uint8_t *dst2, int dstStride2,
|
|
|
|
|
const uint8_t *src, int srcStride,
|
|
|
|
|
int w, int h);
|
|
|
|
|
|
2024-10-02 15:37:10 +02:00
|
|
|
static int nv24_to_yuv420p_neon_wrapper(SwsContext *c, const uint8_t *const src[],
|
|
|
|
|
const int srcStride[], int srcSliceY, int srcSliceH,
|
swscale: Fix aarch64 and i386 compilation failures
This unbreaks builds after c1a0e657638f7007dcc807a2d985c22631fcd6d3,
which broke with errors like
src/libswscale/aarch64/rgb2rgb.c:66:25: error: incompatible function pointer types assigning to 'void (*)(const uint8_t *, uint8_t *, uint8_t *, uint8_t *, int, int, int, int, int, const int32_t *)' (aka 'void (*)(const unsigned char *, unsigned char *, unsigned char *, unsigned char *, int, int, int, int, int, const int *)') from 'void (const uint8_t *, uint8_t *, uint8_t *, uint8_t *, int, int, int, int, int, int32_t *)' (aka 'void (const unsigned char *, unsigned char *, unsigned char *, unsigned char *, int, int, int, int, int, int *)') [-Wincompatible-function-pointer-types]
66 | ff_rgb24toyv12 = rgb24toyv12;
| ^ ~~~~~~~~~~~
and
src/libswscale/aarch64/swscale_unscaled.c:213:29: error: incompatible function pointer types assigning to 'SwsFunc' (aka 'int (*)(struct SwsContext *, const unsigned char *const *, const int *, int, int, unsigned char *const *, const int *)') from 'int (SwsContext *, const uint8_t *const *, const int *, int, int, const uint8_t **, const int *)' (aka 'int (struct SwsContext *, const unsigned char *const *, const int *, int, int, const unsigned char **, const int *)') [-Wincompatible-function-pointer-types]
213 | c->convert_unscaled = nv24_to_yuv420p_neon_wrapper;
| ^ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Signed-off-by: Martin Storsjö <martin@martin.st>
2024-10-08 08:27:17 +02:00
|
|
|
uint8_t *const dst[], const int dstStride[])
|
2024-08-07 18:53:12 +02:00
|
|
|
{
|
|
|
|
|
uint8_t *dst1 = dst[1] + dstStride[1] * srcSliceY / 2;
|
|
|
|
|
uint8_t *dst2 = dst[2] + dstStride[2] * srcSliceY / 2;
|
|
|
|
|
|
|
|
|
|
ff_copyPlane(src[0], srcStride[0], srcSliceY, srcSliceH, c->srcW,
|
|
|
|
|
dst[0], dstStride[0]);
|
|
|
|
|
|
|
|
|
|
if (c->srcFormat == AV_PIX_FMT_NV24)
|
|
|
|
|
ff_nv24_to_yuv420p_chroma_neon(dst1, dstStride[1], dst2, dstStride[2],
|
|
|
|
|
src[1], srcStride[1], c->srcW / 2, srcSliceH);
|
|
|
|
|
else
|
|
|
|
|
ff_nv24_to_yuv420p_chroma_neon(dst2, dstStride[2], dst1, dstStride[1],
|
|
|
|
|
src[1], srcStride[1], c->srcW / 2, srcSliceH);
|
|
|
|
|
|
|
|
|
|
return srcSliceH;
|
|
|
|
|
}
|
|
|
|
|
|
2016-02-08 16:14:17 +02:00
|
|
|
#define DECLARE_FF_NVX_TO_ALL_RGBX_FUNCS(nvx) \
|
|
|
|
|
DECLARE_FF_NVX_TO_RGBX_FUNCS(nvx, argb) \
|
|
|
|
|
DECLARE_FF_NVX_TO_RGBX_FUNCS(nvx, rgba) \
|
|
|
|
|
DECLARE_FF_NVX_TO_RGBX_FUNCS(nvx, abgr) \
|
|
|
|
|
DECLARE_FF_NVX_TO_RGBX_FUNCS(nvx, bgra) \
|
2024-08-06 12:51:06 +02:00
|
|
|
DECLARE_FF_NVX_TO_GBRP_FUNCS(nvx, gbrp) \
|
2016-02-08 16:14:17 +02:00
|
|
|
|
|
|
|
|
DECLARE_FF_NVX_TO_ALL_RGBX_FUNCS(nv12)
|
|
|
|
|
DECLARE_FF_NVX_TO_ALL_RGBX_FUNCS(nv21)
|
|
|
|
|
|
|
|
|
|
/* We need a 16 pixel width alignment. This constraint can easily be removed
|
|
|
|
|
* for input reading but for the output which is 4-bytes per pixel (RGBA) the
|
|
|
|
|
* assembly might be writing as much as 4*15=60 extra bytes at the end of the
|
|
|
|
|
* line, which won't fit the 32-bytes buffer alignment. */
|
|
|
|
|
#define SET_FF_NVX_TO_RGBX_FUNC(ifmt, IFMT, ofmt, OFMT, accurate_rnd) do { \
|
|
|
|
|
if (c->srcFormat == AV_PIX_FMT_##IFMT \
|
|
|
|
|
&& c->dstFormat == AV_PIX_FMT_##OFMT \
|
|
|
|
|
&& !(c->srcH & 1) \
|
|
|
|
|
&& !(c->srcW & 15) \
|
|
|
|
|
&& !accurate_rnd) \
|
2021-06-10 17:10:35 +02:00
|
|
|
c->convert_unscaled = ifmt##_to_##ofmt##_neon_wrapper; \
|
2016-02-08 16:14:17 +02:00
|
|
|
} while (0)
|
|
|
|
|
|
|
|
|
|
#define SET_FF_NVX_TO_ALL_RGBX_FUNC(nvx, NVX, accurate_rnd) do { \
|
|
|
|
|
SET_FF_NVX_TO_RGBX_FUNC(nvx, NVX, argb, ARGB, accurate_rnd); \
|
|
|
|
|
SET_FF_NVX_TO_RGBX_FUNC(nvx, NVX, rgba, RGBA, accurate_rnd); \
|
|
|
|
|
SET_FF_NVX_TO_RGBX_FUNC(nvx, NVX, abgr, ABGR, accurate_rnd); \
|
|
|
|
|
SET_FF_NVX_TO_RGBX_FUNC(nvx, NVX, bgra, BGRA, accurate_rnd); \
|
2024-08-06 12:51:06 +02:00
|
|
|
SET_FF_NVX_TO_RGBX_FUNC(nvx, NVX, gbrp, GBRP, accurate_rnd); \
|
2016-02-08 16:14:17 +02:00
|
|
|
} while (0)
|
|
|
|
|
|
|
|
|
|
static void get_unscaled_swscale_neon(SwsContext *c) {
|
|
|
|
|
int accurate_rnd = c->flags & SWS_ACCURATE_RND;
|
|
|
|
|
|
|
|
|
|
SET_FF_NVX_TO_ALL_RGBX_FUNC(nv12, NV12, accurate_rnd);
|
|
|
|
|
SET_FF_NVX_TO_ALL_RGBX_FUNC(nv21, NV21, accurate_rnd);
|
|
|
|
|
SET_FF_NVX_TO_ALL_RGBX_FUNC(yuv420p, YUV420P, accurate_rnd);
|
|
|
|
|
SET_FF_NVX_TO_ALL_RGBX_FUNC(yuv422p, YUV422P, accurate_rnd);
|
2024-08-07 18:53:12 +02:00
|
|
|
|
|
|
|
|
if (c->dstFormat == AV_PIX_FMT_YUV420P &&
|
|
|
|
|
(c->srcFormat == AV_PIX_FMT_NV24 || c->srcFormat == AV_PIX_FMT_NV42) &&
|
|
|
|
|
!(c->srcH & 1) && !(c->srcW & 15) && !accurate_rnd)
|
|
|
|
|
c->convert_unscaled = nv24_to_yuv420p_neon_wrapper;
|
2016-02-08 16:14:17 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
void ff_get_unscaled_swscale_aarch64(SwsContext *c)
|
|
|
|
|
{
|
|
|
|
|
int cpu_flags = av_get_cpu_flags();
|
|
|
|
|
if (have_neon(cpu_flags))
|
|
|
|
|
get_unscaled_swscale_neon(c);
|
|
|
|
|
}
|
