mirror of
https://github.com/FFmpeg/FFmpeg.git
synced 2024-12-23 12:43:46 +02:00
c62bbd4d20
checkasm benchmarks on 1.5 GHz Cortex-A72 are as follows. Note that the C version can still outperform the NEON version in specific cases. The balance between different code paths is stream-dependent, but in practice the best case happens about 5% of the time, the worst case happens about 40% of the time, and the complexity of the remaining cases fall somewhere in between. Therefore, taking the average of the best and worst case timings is probably a conservative estimate of the degree by which the NEON code improves performance. vc1dsp.vc1_h_loop_filter4_bestcase_c: 10.7 vc1dsp.vc1_h_loop_filter4_bestcase_neon: 43.5 vc1dsp.vc1_h_loop_filter4_worstcase_c: 184.5 vc1dsp.vc1_h_loop_filter4_worstcase_neon: 73.7 vc1dsp.vc1_h_loop_filter8_bestcase_c: 31.2 vc1dsp.vc1_h_loop_filter8_bestcase_neon: 62.2 vc1dsp.vc1_h_loop_filter8_worstcase_c: 358.2 vc1dsp.vc1_h_loop_filter8_worstcase_neon: 88.2 vc1dsp.vc1_h_loop_filter16_bestcase_c: 51.0 vc1dsp.vc1_h_loop_filter16_bestcase_neon: 107.7 vc1dsp.vc1_h_loop_filter16_worstcase_c: 722.7 vc1dsp.vc1_h_loop_filter16_worstcase_neon: 140.5 vc1dsp.vc1_v_loop_filter4_bestcase_c: 9.7 vc1dsp.vc1_v_loop_filter4_bestcase_neon: 43.0 vc1dsp.vc1_v_loop_filter4_worstcase_c: 178.7 vc1dsp.vc1_v_loop_filter4_worstcase_neon: 69.0 vc1dsp.vc1_v_loop_filter8_bestcase_c: 30.2 vc1dsp.vc1_v_loop_filter8_bestcase_neon: 50.7 vc1dsp.vc1_v_loop_filter8_worstcase_c: 353.0 vc1dsp.vc1_v_loop_filter8_worstcase_neon: 69.2 vc1dsp.vc1_v_loop_filter16_bestcase_c: 60.0 vc1dsp.vc1_v_loop_filter16_bestcase_neon: 90.0 vc1dsp.vc1_v_loop_filter16_worstcase_c: 714.2 vc1dsp.vc1_v_loop_filter16_worstcase_neon: 97.2 Signed-off-by: Ben Avison <bavison@riscosopen.org> Signed-off-by: Martin Storsjö <martin@martin.st>
62 lines
2.7 KiB
C
62 lines
2.7 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 <stdint.h>
|
|
|
|
#include "libavutil/attributes.h"
|
|
#include "libavutil/cpu.h"
|
|
#include "libavutil/aarch64/cpu.h"
|
|
#include "libavcodec/vc1dsp.h"
|
|
|
|
#include "config.h"
|
|
|
|
void ff_vc1_v_loop_filter4_neon(uint8_t *src, ptrdiff_t stride, int pq);
|
|
void ff_vc1_h_loop_filter4_neon(uint8_t *src, ptrdiff_t stride, int pq);
|
|
void ff_vc1_v_loop_filter8_neon(uint8_t *src, ptrdiff_t stride, int pq);
|
|
void ff_vc1_h_loop_filter8_neon(uint8_t *src, ptrdiff_t stride, int pq);
|
|
void ff_vc1_v_loop_filter16_neon(uint8_t *src, ptrdiff_t stride, int pq);
|
|
void ff_vc1_h_loop_filter16_neon(uint8_t *src, ptrdiff_t stride, int pq);
|
|
|
|
void ff_put_vc1_chroma_mc8_neon(uint8_t *dst, uint8_t *src, ptrdiff_t stride,
|
|
int h, int x, int y);
|
|
void ff_avg_vc1_chroma_mc8_neon(uint8_t *dst, uint8_t *src, ptrdiff_t stride,
|
|
int h, int x, int y);
|
|
void ff_put_vc1_chroma_mc4_neon(uint8_t *dst, uint8_t *src, ptrdiff_t stride,
|
|
int h, int x, int y);
|
|
void ff_avg_vc1_chroma_mc4_neon(uint8_t *dst, uint8_t *src, ptrdiff_t stride,
|
|
int h, int x, int y);
|
|
|
|
av_cold void ff_vc1dsp_init_aarch64(VC1DSPContext *dsp)
|
|
{
|
|
int cpu_flags = av_get_cpu_flags();
|
|
|
|
if (have_neon(cpu_flags)) {
|
|
dsp->vc1_v_loop_filter4 = ff_vc1_v_loop_filter4_neon;
|
|
dsp->vc1_h_loop_filter4 = ff_vc1_h_loop_filter4_neon;
|
|
dsp->vc1_v_loop_filter8 = ff_vc1_v_loop_filter8_neon;
|
|
dsp->vc1_h_loop_filter8 = ff_vc1_h_loop_filter8_neon;
|
|
dsp->vc1_v_loop_filter16 = ff_vc1_v_loop_filter16_neon;
|
|
dsp->vc1_h_loop_filter16 = ff_vc1_h_loop_filter16_neon;
|
|
|
|
dsp->put_no_rnd_vc1_chroma_pixels_tab[0] = ff_put_vc1_chroma_mc8_neon;
|
|
dsp->avg_no_rnd_vc1_chroma_pixels_tab[0] = ff_avg_vc1_chroma_mc8_neon;
|
|
dsp->put_no_rnd_vc1_chroma_pixels_tab[1] = ff_put_vc1_chroma_mc4_neon;
|
|
dsp->avg_no_rnd_vc1_chroma_pixels_tab[1] = ff_avg_vc1_chroma_mc4_neon;
|
|
}
|
|
}
|