mirror of
https://git.ffmpeg.org/ffmpeg.git
synced 2025-01-04 06:02:12 +00:00
9dac8495b0
Test on Apple M1: rgb24_to_uv_8_c: 0.0 rgb24_to_uv_8_neon: 0.2 rgb24_to_uv_128_c: 1.0 rgb24_to_uv_128_neon: 0.5 rgb24_to_uv_1080_c: 7.0 rgb24_to_uv_1080_neon: 5.7 rgb24_to_uv_1920_c: 12.5 rgb24_to_uv_1920_neon: 9.5 rgb24_to_uv_half_8_c: 0.2 rgb24_to_uv_half_8_neon: 0.2 rgb24_to_uv_half_128_c: 1.0 rgb24_to_uv_half_128_neon: 0.5 rgb24_to_uv_half_1080_c: 6.2 rgb24_to_uv_half_1080_neon: 3.0 rgb24_to_uv_half_1920_c: 11.2 rgb24_to_uv_half_1920_neon: 5.2 rgb24_to_y_8_c: 0.2 rgb24_to_y_8_neon: 0.0 rgb24_to_y_128_c: 0.5 rgb24_to_y_128_neon: 0.5 rgb24_to_y_1080_c: 4.7 rgb24_to_y_1080_neon: 3.2 rgb24_to_y_1920_c: 8.0 rgb24_to_y_1920_neon: 5.7 On Pixel 6: rgb24_to_uv_8_c: 30.7 rgb24_to_uv_8_neon: 56.9 rgb24_to_uv_128_c: 213.9 rgb24_to_uv_128_neon: 173.2 rgb24_to_uv_1080_c: 1649.9 rgb24_to_uv_1080_neon: 1424.4 rgb24_to_uv_1920_c: 2907.9 rgb24_to_uv_1920_neon: 2480.7 rgb24_to_uv_half_8_c: 36.2 rgb24_to_uv_half_8_neon: 33.4 rgb24_to_uv_half_128_c: 167.9 rgb24_to_uv_half_128_neon: 99.4 rgb24_to_uv_half_1080_c: 1293.9 rgb24_to_uv_half_1080_neon: 778.7 rgb24_to_uv_half_1920_c: 2292.7 rgb24_to_uv_half_1920_neon: 1328.7 rgb24_to_y_8_c: 19.7 rgb24_to_y_8_neon: 27.7 rgb24_to_y_128_c: 129.9 rgb24_to_y_128_neon: 96.7 rgb24_to_y_1080_c: 995.4 rgb24_to_y_1080_neon: 767.7 rgb24_to_y_1920_c: 1747.4 rgb24_to_y_1920_neon: 1337.2 Note both tests use clang as compiler, which has vectorization enabled by default with -O3. Reviewed-by: Rémi Denis-Courmont <remi@remlab.net> Reviewed-by: Martin Storsjö <martin@martin.st> Signed-off-by: Zhao Zhili <zhilizhao@tencent.com>
242 lines
10 KiB
C
242 lines
10 KiB
C
/*
|
|
* 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(SwsContext *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->srcFormat);
|
|
int sh = desc->comp[0].depth - 1;
|
|
|
|
if (sh<15) {
|
|
sh = isAnyRGB(c->srcFormat) || c->srcFormat==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(SwsContext *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->srcFormat);
|
|
int sh = desc->comp[0].depth - 1;
|
|
|
|
if (sh<15) {
|
|
sh = isAnyRGB(c->srcFormat) || c->srcFormat==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(SwsContext *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->srcFormat);
|
|
int sh = desc->comp[0].depth - 1;
|
|
|
|
if (sh<15) {
|
|
sh = isAnyRGB(c->srcFormat) || c->srcFormat==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(SwsContext *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->srcFormat);
|
|
int bits = desc->comp[0].depth - 1;
|
|
int sh = bits - 4;
|
|
|
|
if ((isAnyRGB(c->srcFormat) || c->srcFormat==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(SwsContext *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->srcFormat);
|
|
int bits = desc->comp[0].depth - 1;
|
|
int sh = bits - 4;
|
|
|
|
if ((isAnyRGB(c->srcFormat) || c->srcFormat==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(SwsContext *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->srcFormat);
|
|
int bits = desc->comp[0].depth - 1;
|
|
int sh = bits - 4;
|
|
|
|
if ((isAnyRGB(c->srcFormat) || c->srcFormat==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( \
|
|
SwsContext *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; \
|
|
}
|
|
|
|
void ff_rgb24ToY_neon(uint8_t *_dst, const uint8_t *src, const uint8_t *unused1,
|
|
const uint8_t *unused2, int width,
|
|
uint32_t *rgb2yuv, void *opq);
|
|
|
|
void ff_rgb24ToUV_neon(uint8_t *_dstU, uint8_t *_dstV, const uint8_t *unused0,
|
|
const uint8_t *src1,
|
|
const uint8_t *src2, int width, uint32_t *rgb2yuv,
|
|
void *opq);
|
|
|
|
void ff_rgb24ToUV_half_neon(uint8_t *_dstU, uint8_t *_dstV, const uint8_t *unused0,
|
|
const uint8_t *src1,
|
|
const uint8_t *src2, int width, uint32_t *rgb2yuv,
|
|
void *opq);
|
|
|
|
av_cold void ff_sws_init_swscale_aarch64(SwsContext *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->srcFormat) {
|
|
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;
|
|
default:
|
|
break;
|
|
}
|
|
}
|
|
}
|