mirror of
https://git.ffmpeg.org/ffmpeg.git
synced 2024-12-20 22:41:11 +00:00
2d1358a84d
For bit depths <= 14, the result is saturated to 15 bits.
For bit depths > 14, the result is saturated to 19 bits.
x86_64:
chrRangeFromJpeg8_1920_c: 2126.5 2127.4 (1.00x)
chrRangeFromJpeg16_1920_c: 2331.4 2325.2 (1.00x)
chrRangeToJpeg8_1920_c: 3163.0 3166.9 (1.00x)
chrRangeToJpeg16_1920_c: 3163.7 2152.4 (1.47x)
lumRangeFromJpeg8_1920_c: 1262.2 1263.0 (1.00x)
lumRangeFromJpeg16_1920_c: 1079.5 1080.5 (1.00x)
lumRangeToJpeg8_1920_c: 1860.5 1886.8 (0.99x)
lumRangeToJpeg16_1920_c: 1910.2 1077.0 (1.77x)
aarch64 A55:
chrRangeFromJpeg8_1920_c: 28836.2 28835.2 (1.00x)
chrRangeFromJpeg16_1920_c: 28840.1 28839.8 (1.00x)
chrRangeToJpeg8_1920_c: 44196.2 23074.7 (1.92x)
chrRangeToJpeg16_1920_c: 36527.3 17318.9 (2.11x)
lumRangeFromJpeg8_1920_c: 15388.5 15389.7 (1.00x)
lumRangeFromJpeg16_1920_c: 15389.3 15388.2 (1.00x)
lumRangeToJpeg8_1920_c: 23069.7 19227.8 (1.20x)
lumRangeToJpeg16_1920_c: 19227.8 15387.0 (1.25x)
aarch64 A76:
chrRangeFromJpeg8_1920_c: 6334.7 6324.4 (1.00x)
chrRangeFromJpeg16_1920_c: 6336.0 6339.9 (1.00x)
chrRangeToJpeg8_1920_c: 11474.5 9656.0 (1.19x)
chrRangeToJpeg16_1920_c: 9640.5 6340.4 (1.52x)
lumRangeFromJpeg8_1920_c: 4453.2 4422.0 (1.01x)
lumRangeFromJpeg16_1920_c: 4414.2 4420.9 (1.00x)
lumRangeToJpeg8_1920_c: 6645.0 5949.1 (1.12x)
lumRangeToJpeg16_1920_c: 6005.2 4446.8 (1.35x)
NOTE: all simd optimizations for range_convert have been disabled
except for x86, which already had the same behaviour.
they will be re-enabled when they are fixed for each architecture.
132 lines
4.5 KiB
C
132 lines
4.5 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 "libavutil/riscv/cpu.h"
|
|
#include "libswscale/swscale_internal.h"
|
|
|
|
void ff_range_lum_to_jpeg_16_rvv(int16_t *, int);
|
|
void ff_range_chr_to_jpeg_16_rvv(int16_t *, int16_t *, int);
|
|
void ff_range_lum_from_jpeg_16_rvv(int16_t *, int);
|
|
void ff_range_chr_from_jpeg_16_rvv(int16_t *, int16_t *, int);
|
|
|
|
av_cold void ff_sws_init_range_convert_riscv(SwsInternal *c)
|
|
{
|
|
/* This code is currently disabled because of changes in the base
|
|
* implementation of these functions. This code should be enabled
|
|
* again once those changes are ported to this architecture. */
|
|
#if 0
|
|
#if HAVE_RVV
|
|
int flags = av_get_cpu_flags();
|
|
|
|
static const struct {
|
|
void (*lum)(int16_t *, int);
|
|
void (*chr)(int16_t *, int16_t *, int);
|
|
} convs[2] = {
|
|
{ ff_range_lum_to_jpeg_16_rvv, ff_range_chr_to_jpeg_16_rvv },
|
|
{ ff_range_lum_from_jpeg_16_rvv, ff_range_chr_from_jpeg_16_rvv },
|
|
};
|
|
|
|
if (c->dstBpc <= 14 &&
|
|
(flags & AV_CPU_FLAG_RVV_I32) && (flags & AV_CPU_FLAG_RVB)) {
|
|
bool from = c->opts.src_range != 0;
|
|
|
|
c->lumConvertRange = convs[from].lum;
|
|
c->chrConvertRange = convs[from].chr;
|
|
}
|
|
#endif
|
|
#endif
|
|
}
|
|
|
|
#define RVV_INPUT(name) \
|
|
void ff_##name##ToY_rvv(uint8_t *dst, const uint8_t *src, const uint8_t *, \
|
|
const uint8_t *, int w, uint32_t *coeffs, void *); \
|
|
void ff_##name##ToUV_rvv(uint8_t *, uint8_t *, const uint8_t *, \
|
|
const uint8_t *, const uint8_t *, int w, \
|
|
uint32_t *coeffs, void *); \
|
|
void ff_##name##ToUV_half_rvv(uint8_t *, uint8_t *, const uint8_t *, \
|
|
const uint8_t *, const uint8_t *, int w, \
|
|
uint32_t *coeffs, void *)
|
|
|
|
RVV_INPUT(abgr32);
|
|
RVV_INPUT(argb32);
|
|
RVV_INPUT(bgr24);
|
|
RVV_INPUT(bgra32);
|
|
RVV_INPUT(rgb24);
|
|
RVV_INPUT(rgba32);
|
|
|
|
av_cold void ff_sws_init_swscale_riscv(SwsInternal *c)
|
|
{
|
|
#if HAVE_RVV
|
|
int flags = av_get_cpu_flags();
|
|
|
|
if ((flags & AV_CPU_FLAG_RVV_I32) && (flags & AV_CPU_FLAG_RVB)) {
|
|
switch (c->opts.src_format) {
|
|
case AV_PIX_FMT_ABGR:
|
|
c->lumToYV12 = ff_abgr32ToY_rvv;
|
|
if (c->chrSrcHSubSample)
|
|
c->chrToYV12 = ff_abgr32ToUV_half_rvv;
|
|
else
|
|
c->chrToYV12 = ff_abgr32ToUV_rvv;
|
|
break;
|
|
|
|
case AV_PIX_FMT_ARGB:
|
|
c->lumToYV12 = ff_argb32ToY_rvv;
|
|
if (c->chrSrcHSubSample)
|
|
c->chrToYV12 = ff_argb32ToUV_half_rvv;
|
|
else
|
|
c->chrToYV12 = ff_argb32ToUV_rvv;
|
|
break;
|
|
|
|
case AV_PIX_FMT_BGR24:
|
|
c->lumToYV12 = ff_bgr24ToY_rvv;
|
|
if (c->chrSrcHSubSample)
|
|
c->chrToYV12 = ff_bgr24ToUV_half_rvv;
|
|
else
|
|
c->chrToYV12 = ff_bgr24ToUV_rvv;
|
|
break;
|
|
|
|
case AV_PIX_FMT_BGRA:
|
|
c->lumToYV12 = ff_bgra32ToY_rvv;
|
|
if (c->chrSrcHSubSample)
|
|
c->chrToYV12 = ff_bgra32ToUV_half_rvv;
|
|
else
|
|
c->chrToYV12 = ff_bgra32ToUV_rvv;
|
|
break;
|
|
|
|
case AV_PIX_FMT_RGB24:
|
|
c->lumToYV12 = ff_rgb24ToY_rvv;
|
|
if (c->chrSrcHSubSample)
|
|
c->chrToYV12 = ff_rgb24ToUV_half_rvv;
|
|
else
|
|
c->chrToYV12 = ff_rgb24ToUV_rvv;
|
|
break;
|
|
|
|
case AV_PIX_FMT_RGBA:
|
|
c->lumToYV12 = ff_rgba32ToY_rvv;
|
|
if (c->chrSrcHSubSample)
|
|
c->chrToYV12 = ff_rgba32ToUV_half_rvv;
|
|
else
|
|
c->chrToYV12 = ff_rgba32ToUV_rvv;
|
|
break;
|
|
}
|
|
}
|
|
#endif
|
|
}
|