mirror of
https://git.ffmpeg.org/ffmpeg.git
synced 2024-12-12 02:04:58 +00:00
8f4b000c37
Provide optimized implementation for vsse_intra8 for arm64. Performance tests are shown below. - vsse_5_c: 87.7 - vsse_5_neon: 26.2 Benchmarks and tests are run with checkasm tool on AWS Graviton 3. Co-authored-by: Martin Storsjö <martin@martin.st> Signed-off-by: Martin Storsjö <martin@martin.st>
135 lines
5.5 KiB
C
135 lines
5.5 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 <stdint.h>
|
|
|
|
#include "config.h"
|
|
#include "libavutil/attributes.h"
|
|
#include "libavutil/aarch64/cpu.h"
|
|
#include "libavcodec/mpegvideo.h"
|
|
|
|
int ff_pix_abs16_neon(MpegEncContext *s, const uint8_t *blk1, const uint8_t *blk2,
|
|
ptrdiff_t stride, int h);
|
|
int ff_pix_abs16_xy2_neon(MpegEncContext *s, const uint8_t *blk1, const uint8_t *blk2,
|
|
ptrdiff_t stride, int h);
|
|
int ff_pix_abs16_x2_neon(MpegEncContext *v, const uint8_t *pix1, const uint8_t *pix2,
|
|
ptrdiff_t stride, int h);
|
|
int ff_pix_abs16_y2_neon(MpegEncContext *v, const uint8_t *pix1, const uint8_t *pix2,
|
|
ptrdiff_t stride, int h);
|
|
int ff_pix_abs8_neon(MpegEncContext *s, const uint8_t *blk1, const uint8_t *blk2,
|
|
ptrdiff_t stride, int h);
|
|
|
|
int sse16_neon(MpegEncContext *v, const uint8_t *pix1, const uint8_t *pix2,
|
|
ptrdiff_t stride, int h);
|
|
int sse8_neon(MpegEncContext *v, const uint8_t *pix1, const uint8_t *pix2,
|
|
ptrdiff_t stride, int h);
|
|
int sse4_neon(MpegEncContext *v, const uint8_t *pix1, const uint8_t *pix2,
|
|
ptrdiff_t stride, int h);
|
|
|
|
int vsad16_neon(MpegEncContext *c, const uint8_t *s1, const uint8_t *s2,
|
|
ptrdiff_t stride, int h);
|
|
int vsad_intra16_neon(MpegEncContext *c, const uint8_t *s, const uint8_t *dummy,
|
|
ptrdiff_t stride, int h) ;
|
|
int vsad_intra8_neon(MpegEncContext *c, const uint8_t *s, const uint8_t *dummy,
|
|
ptrdiff_t stride, int h) ;
|
|
int vsse16_neon(MpegEncContext *c, const uint8_t *s1, const uint8_t *s2,
|
|
ptrdiff_t stride, int h);
|
|
int vsse_intra16_neon(MpegEncContext *c, const uint8_t *s, const uint8_t *dummy,
|
|
ptrdiff_t stride, int h);
|
|
int nsse16_neon(int multiplier, const uint8_t *s, const uint8_t *s2,
|
|
ptrdiff_t stride, int h);
|
|
int nsse16_neon_wrapper(MpegEncContext *c, const uint8_t *s1, const uint8_t *s2,
|
|
ptrdiff_t stride, int h);
|
|
int pix_median_abs16_neon(MpegEncContext *v, const uint8_t *pix1, const uint8_t *pix2,
|
|
ptrdiff_t stride, int h);
|
|
int pix_median_abs8_neon(MpegEncContext *v, const uint8_t *pix1, const uint8_t *pix2,
|
|
ptrdiff_t stride, int h);
|
|
int ff_pix_abs8_x2_neon(MpegEncContext *v, const uint8_t *pix1, const uint8_t *pix2,
|
|
ptrdiff_t stride, int h);
|
|
int ff_pix_abs8_y2_neon(MpegEncContext *v, const uint8_t *pix1, const uint8_t *pix2,
|
|
ptrdiff_t stride, int h);
|
|
int ff_pix_abs8_xy2_neon(MpegEncContext *v, const uint8_t *pix1, const uint8_t *pix2,
|
|
ptrdiff_t stride, int h);
|
|
|
|
int nsse8_neon(int multiplier, const uint8_t *s, const uint8_t *s2,
|
|
ptrdiff_t stride, int h);
|
|
int nsse8_neon_wrapper(MpegEncContext *c, const uint8_t *s1, const uint8_t *s2,
|
|
ptrdiff_t stride, int h);
|
|
|
|
int vsse8_neon(MpegEncContext *c, const uint8_t *s1, const uint8_t *s2,
|
|
ptrdiff_t stride, int h);
|
|
|
|
int vsse_intra8_neon(MpegEncContext *c, const uint8_t *s, const uint8_t *dummy,
|
|
ptrdiff_t stride, int h);
|
|
|
|
av_cold void ff_me_cmp_init_aarch64(MECmpContext *c, AVCodecContext *avctx)
|
|
{
|
|
int cpu_flags = av_get_cpu_flags();
|
|
|
|
if (have_neon(cpu_flags)) {
|
|
c->pix_abs[0][0] = ff_pix_abs16_neon;
|
|
c->pix_abs[0][1] = ff_pix_abs16_x2_neon;
|
|
c->pix_abs[0][2] = ff_pix_abs16_y2_neon;
|
|
c->pix_abs[0][3] = ff_pix_abs16_xy2_neon;
|
|
c->pix_abs[1][0] = ff_pix_abs8_neon;
|
|
c->pix_abs[1][1] = ff_pix_abs8_x2_neon;
|
|
c->pix_abs[1][2] = ff_pix_abs8_y2_neon;
|
|
c->pix_abs[1][3] = ff_pix_abs8_xy2_neon;
|
|
|
|
c->sad[0] = ff_pix_abs16_neon;
|
|
c->sad[1] = ff_pix_abs8_neon;
|
|
c->sse[0] = sse16_neon;
|
|
c->sse[1] = sse8_neon;
|
|
c->sse[2] = sse4_neon;
|
|
|
|
c->vsad[0] = vsad16_neon;
|
|
c->vsad[4] = vsad_intra16_neon;
|
|
c->vsad[5] = vsad_intra8_neon;
|
|
|
|
c->vsse[0] = vsse16_neon;
|
|
c->vsse[1] = vsse8_neon;
|
|
|
|
c->vsse[4] = vsse_intra16_neon;
|
|
c->vsse[5] = vsse_intra8_neon;
|
|
|
|
c->nsse[0] = nsse16_neon_wrapper;
|
|
c->nsse[1] = nsse8_neon_wrapper;
|
|
|
|
c->median_sad[0] = pix_median_abs16_neon;
|
|
c->median_sad[1] = pix_median_abs8_neon;
|
|
}
|
|
}
|
|
|
|
int nsse16_neon_wrapper(MpegEncContext *c, const uint8_t *s1, const uint8_t *s2,
|
|
ptrdiff_t stride, int h)
|
|
{
|
|
if (c)
|
|
return nsse16_neon(c->avctx->nsse_weight, s1, s2, stride, h);
|
|
else
|
|
return nsse16_neon(8, s1, s2, stride, h);
|
|
}
|
|
|
|
int nsse8_neon_wrapper(MpegEncContext *c, const uint8_t *s1, const uint8_t *s2,
|
|
ptrdiff_t stride, int h)
|
|
{
|
|
if (c)
|
|
return nsse8_neon(c->avctx->nsse_weight, s1, s2, stride, h);
|
|
else
|
|
return nsse8_neon(8, s1, s2, stride, h);
|
|
}
|