1
0
mirror of https://github.com/FFmpeg/FFmpeg.git synced 2024-12-12 19:18:44 +02:00
FFmpeg/libswscale/aarch64/swscale.c
Ramiro Polla 75f1a8e071 swscale/aarch64: add neon {lum,chr}ConvertRange
chrRangeFromJpeg_8_c: 29.2
chrRangeFromJpeg_8_neon: 19.5
chrRangeFromJpeg_24_c: 80.5
chrRangeFromJpeg_24_neon: 34.0
chrRangeFromJpeg_128_c: 413.7
chrRangeFromJpeg_128_neon: 156.0
chrRangeFromJpeg_144_c: 471.0
chrRangeFromJpeg_144_neon: 174.2
chrRangeFromJpeg_256_c: 842.0
chrRangeFromJpeg_256_neon: 305.5
chrRangeFromJpeg_512_c: 1699.0
chrRangeFromJpeg_512_neon: 608.0
chrRangeToJpeg_8_c: 51.7
chrRangeToJpeg_8_neon: 22.7
chrRangeToJpeg_24_c: 149.7
chrRangeToJpeg_24_neon: 38.0
chrRangeToJpeg_128_c: 761.7
chrRangeToJpeg_128_neon: 176.7
chrRangeToJpeg_144_c: 866.2
chrRangeToJpeg_144_neon: 198.7
chrRangeToJpeg_256_c: 1516.5
chrRangeToJpeg_256_neon: 348.7
chrRangeToJpeg_512_c: 3067.2
chrRangeToJpeg_512_neon: 692.7
lumRangeFromJpeg_8_c: 24.0
lumRangeFromJpeg_8_neon: 17.0
lumRangeFromJpeg_24_c: 56.7
lumRangeFromJpeg_24_neon: 21.0
lumRangeFromJpeg_128_c: 294.5
lumRangeFromJpeg_128_neon: 76.7
lumRangeFromJpeg_144_c: 332.5
lumRangeFromJpeg_144_neon: 86.7
lumRangeFromJpeg_256_c: 586.0
lumRangeFromJpeg_256_neon: 152.2
lumRangeFromJpeg_512_c: 1190.0
lumRangeFromJpeg_512_neon: 298.0
lumRangeToJpeg_8_c: 31.7
lumRangeToJpeg_8_neon: 19.5
lumRangeToJpeg_24_c: 83.5
lumRangeToJpeg_24_neon: 24.2
lumRangeToJpeg_128_c: 440.5
lumRangeToJpeg_128_neon: 91.0
lumRangeToJpeg_144_c: 504.2
lumRangeToJpeg_144_neon: 101.0
lumRangeToJpeg_256_c: 879.7
lumRangeToJpeg_256_neon: 177.2
lumRangeToJpeg_512_c: 1794.2
lumRangeToJpeg_512_neon: 354.0
2024-06-18 23:12:41 +02:00

263 lines
11 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);
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(SwsContext *c)
{
if (c->srcRange != c->dstRange && !isAnyRGB(c->dstFormat)) {
if (c->dstBpc <= 14) {
if (c->srcRange) {
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(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;
}
ff_sws_init_range_convert_aarch64(c);
}
}