github-mirrors/FFmpeg
1
0
Fork 0
mirror of https://mirror.skon.top/https://github.com/FFmpeg/FFmpeg synced 2026-04-30 22:00:51 +08:00
Code Issues Packages Projects Releases Wiki Activity
Files
release/8.1
FFmpeg/libavcodec/aarch64/vvc/dsp_init.c
Georgii Zagoruiko 510999f6b0 aarch64/vvc: sme2 optimisation of alf_filter_luma() 8/10/12 bit 
Apple M4:
vvc_alf_filter_luma_8x8_8_c:                           347.3 ( 1.00x)
vvc_alf_filter_luma_8x8_8_neon:                        138.7 ( 2.50x)
vvc_alf_filter_luma_8x8_8_sme2:                        134.5 ( 2.58x)
vvc_alf_filter_luma_8x8_10_c:                          299.8 ( 1.00x)
vvc_alf_filter_luma_8x8_10_neon:                       129.8 ( 2.31x)
vvc_alf_filter_luma_8x8_10_sme2:                       128.6 ( 2.33x)
vvc_alf_filter_luma_8x8_12_c:                          293.0 ( 1.00x)
vvc_alf_filter_luma_8x8_12_neon:                       126.8 ( 2.31x)
vvc_alf_filter_luma_8x8_12_sme2:                       126.3 ( 2.32x)
vvc_alf_filter_luma_16x16_8_c:                        1386.1 ( 1.00x)
vvc_alf_filter_luma_16x16_8_neon:                      560.3 ( 2.47x)
vvc_alf_filter_luma_16x16_8_sme2:                      540.1 ( 2.57x)
vvc_alf_filter_luma_16x16_10_c:                       1200.3 ( 1.00x)
vvc_alf_filter_luma_16x16_10_neon:                     515.6 ( 2.33x)
vvc_alf_filter_luma_16x16_10_sme2:                     531.3 ( 2.26x)
vvc_alf_filter_luma_16x16_12_c:                       1223.8 ( 1.00x)
vvc_alf_filter_luma_16x16_12_neon:                     510.7 ( 2.40x)
vvc_alf_filter_luma_16x16_12_sme2:                     524.9 ( 2.33x)
vvc_alf_filter_luma_32x32_8_c:                        5488.8 ( 1.00x)
vvc_alf_filter_luma_32x32_8_neon:                     2233.4 ( 2.46x)
vvc_alf_filter_luma_32x32_8_sme2:                     1093.6 ( 5.02x)
vvc_alf_filter_luma_32x32_10_c:                       4738.0 ( 1.00x)
vvc_alf_filter_luma_32x32_10_neon:                    2057.5 ( 2.30x)
vvc_alf_filter_luma_32x32_10_sme2:                    1053.6 ( 4.50x)
vvc_alf_filter_luma_32x32_12_c:                       4808.3 ( 1.00x)
vvc_alf_filter_luma_32x32_12_neon:                    1981.2 ( 2.43x)
vvc_alf_filter_luma_32x32_12_sme2:                    1047.7 ( 4.59x)
vvc_alf_filter_luma_64x64_8_c:                       22116.8 ( 1.00x)
vvc_alf_filter_luma_64x64_8_neon:                     8951.0 ( 2.47x)
vvc_alf_filter_luma_64x64_8_sme2:                     4225.2 ( 5.23x)
vvc_alf_filter_luma_64x64_10_c:                      19072.8 ( 1.00x)
vvc_alf_filter_luma_64x64_10_neon:                    8448.1 ( 2.26x)
vvc_alf_filter_luma_64x64_10_sme2:                    4225.8 ( 4.51x)
vvc_alf_filter_luma_64x64_12_c:                      19312.6 ( 1.00x)
vvc_alf_filter_luma_64x64_12_neon:                    8270.9 ( 2.34x)
vvc_alf_filter_luma_64x64_12_sme2:                    4245.4 ( 4.55x)
vvc_alf_filter_luma_128x128_8_c:                     88530.5 ( 1.00x)
vvc_alf_filter_luma_128x128_8_neon:                  35686.3 ( 2.48x)
vvc_alf_filter_luma_128x128_8_sme2:                  16961.2 ( 5.22x)
vvc_alf_filter_luma_128x128_10_c:                    76904.9 ( 1.00x)
vvc_alf_filter_luma_128x128_10_neon:                 32439.5 ( 2.37x)
vvc_alf_filter_luma_128x128_10_sme2:                 16845.6 ( 4.57x)
vvc_alf_filter_luma_128x128_12_c:                    77363.3 ( 1.00x)
vvc_alf_filter_luma_128x128_12_neon:                 32907.5 ( 2.35x)
vvc_alf_filter_luma_128x128_12_sme2:                 17018.1 ( 4.55x)
2026-03-04 23:52:58 +02:00

354 lines
18 KiB
C
Raw Permalink Blame History

/*
* VVC filters DSP
*
* Copyright (C) 2024 Zhao Zhili
*
* 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 "libavutil/cpu.h"
#include "libavutil/aarch64/cpu.h"
#include "libavcodec/aarch64/h26x/dsp.h"
#include "libavcodec/vvc/dsp.h"
#include "libavcodec/vvc/dec.h"
#include "libavcodec/vvc/ctu.h"
#define BDOF_BLOCK_SIZE 16
#define BDOF_MIN_BLOCK_SIZE 4
void ff_vvc_put_luma_h8_10_neon(int16_t *dst, const uint8_t *_src, const ptrdiff_t _src_stride,
const int height, const int8_t *hf, const int8_t *vf, const int width);
void ff_vvc_put_luma_h16_10_neon(int16_t *dst, const uint8_t *_src, const ptrdiff_t _src_stride,
const int height, const int8_t *hf, const int8_t *vf, const int width);
void ff_vvc_put_luma_h_x16_10_neon(int16_t *dst, const uint8_t *_src, const ptrdiff_t _src_stride,
const int height, const int8_t *hf, const int8_t *vf, const int width);
void ff_vvc_put_luma_h8_12_neon(int16_t *dst, const uint8_t *_src, const ptrdiff_t _src_stride,
const int height, const int8_t *hf, const int8_t *vf, const int width);
void ff_vvc_put_luma_h16_12_neon(int16_t *dst, const uint8_t *_src, const ptrdiff_t _src_stride,
const int height, const int8_t *hf, const int8_t *vf, const int width);
void ff_vvc_put_luma_h_x16_12_neon(int16_t *dst, const uint8_t *_src, const ptrdiff_t _src_stride,
const int height, const int8_t *hf, const int8_t *vf, const int width);
void ff_vvc_put_luma_v4_10_neon(int16_t *dst, const uint8_t *_src, const ptrdiff_t _src_stride,
const int height, const int8_t *hf, const int8_t *vf, const int width);
void ff_vvc_put_luma_v8_10_neon(int16_t *dst, const uint8_t *_src, const ptrdiff_t _src_stride,
const int height, const int8_t *hf, const int8_t *vf, const int width);
void ff_vvc_put_luma_v16_10_neon(int16_t *dst, const uint8_t *_src, const ptrdiff_t _src_stride,
const int height, const int8_t *hf, const int8_t *vf, const int width);
void ff_vvc_put_luma_v_x16_10_neon(int16_t *dst, const uint8_t *_src, const ptrdiff_t _src_stride,
const int height, const int8_t *hf, const int8_t *vf, const int width);
void ff_vvc_put_luma_v4_12_neon(int16_t *dst, const uint8_t *_src, const ptrdiff_t _src_stride,
const int height, const int8_t *hf, const int8_t *vf, const int width);
void ff_vvc_put_luma_v8_12_neon(int16_t *dst, const uint8_t *_src, const ptrdiff_t _src_stride,
const int height, const int8_t *hf, const int8_t *vf, const int width);
void ff_vvc_put_luma_v16_12_neon(int16_t *dst, const uint8_t *_src, const ptrdiff_t _src_stride,
const int height, const int8_t *hf, const int8_t *vf, const int width);
void ff_vvc_put_luma_v_x16_12_neon(int16_t *dst, const uint8_t *_src, const ptrdiff_t _src_stride,
const int height, const int8_t *hf, const int8_t *vf, const int width);
void ff_vvc_put_luma_hv8_10_neon(int16_t *dst, const uint8_t *_src, const ptrdiff_t _src_stride,
const int height, const int8_t *hf, const int8_t *vf, const int width);
void ff_vvc_put_luma_hv16_10_neon(int16_t *dst, const uint8_t *_src, const ptrdiff_t _src_stride,
const int height, const int8_t *hf, const int8_t *vf, const int width);
void ff_vvc_put_luma_hv_x16_10_neon(int16_t *dst, const uint8_t *_src, const ptrdiff_t _src_stride,
const int height, const int8_t *hf, const int8_t *vf, const int width);
void ff_vvc_put_luma_hv8_12_neon(int16_t *dst, const uint8_t *_src, const ptrdiff_t _src_stride,
const int height, const int8_t *hf, const int8_t *vf, const int width);
void ff_vvc_put_luma_hv16_12_neon(int16_t *dst, const uint8_t *_src, const ptrdiff_t _src_stride,
const int height, const int8_t *hf, const int8_t *vf, const int width);
void ff_vvc_put_luma_hv_x16_12_neon(int16_t *dst, const uint8_t *_src, const ptrdiff_t _src_stride,
const int height, const int8_t *hf, const int8_t *vf, const int width);
void ff_alf_classify_sum_neon(int *sum0, int *sum1, int16_t *grad, uint32_t gshift, uint32_t steps);
#define BIT_DEPTH 8
#include "alf_template.c"
#undef BIT_DEPTH
#define BIT_DEPTH 10
#include "alf_template.c"
#undef BIT_DEPTH
#define BIT_DEPTH 12
#include "alf_template.c"
#undef BIT_DEPTH
int ff_vvc_sad_neon(const int16_t *src0, const int16_t *src1, int dx, int dy,
const int block_w, const int block_h);
void ff_vvc_avg_8_neon(uint8_t *dst, ptrdiff_t dst_stride,
const int16_t *src0, const int16_t *src1, int width,
int height);
void ff_vvc_avg_10_neon(uint8_t *dst, ptrdiff_t dst_stride,
const int16_t *src0, const int16_t *src1, int width,
int height);
void ff_vvc_avg_12_neon(uint8_t *dst, ptrdiff_t dst_stride,
const int16_t *src0, const int16_t *src1, int width,
int height);
void ff_vvc_w_avg_8_neon(uint8_t *_dst, ptrdiff_t _dst_stride,
const int16_t *src0, const int16_t *src1,
int width, int height,
uintptr_t w0_w1, uintptr_t offset_shift);
void ff_vvc_w_avg_10_neon(uint8_t *_dst, ptrdiff_t _dst_stride,
const int16_t *src0, const int16_t *src1,
int width, int height,
uintptr_t w0_w1, uintptr_t offset_shift);
void ff_vvc_w_avg_12_neon(uint8_t *_dst, ptrdiff_t _dst_stride,
const int16_t *src0, const int16_t *src1,
int width, int height,
uintptr_t w0_w1, uintptr_t offset_shift);
/* When passing arguments to functions, Apple platforms diverge from the ARM64
* standard ABI for functions that require passing arguments on the stack. To
* simplify portability in the assembly function interface, use a different
* function signature that doesn't require passing arguments on the stack.
*/
#define W_AVG_FUN(bit_depth) \
static void vvc_w_avg_ ## bit_depth(uint8_t *dst, ptrdiff_t dst_stride, \
const int16_t *src0, const int16_t *src1, int width, int height, \
int denom, int w0, int w1, int o) \
{ \
int shift = denom + FFMAX(3, 15 - bit_depth); \
int offset = (o * (1 << (bit_depth - 8)) + 1) * (1 << (shift - 1)); \
uintptr_t w0_w1 = ((uintptr_t)w0 << 32) | (uint32_t)w1; \
uintptr_t offset_shift = ((uintptr_t)offset << 32) | (uint32_t)shift; \
ff_vvc_w_avg_ ## bit_depth ## _neon(dst, dst_stride, src0, src1, width, height, w0_w1, offset_shift); \
}
W_AVG_FUN(8)
W_AVG_FUN(10)
W_AVG_FUN(12)
#define DMVR_FUN(fn, bd) \
void ff_vvc_dmvr_ ## fn ## bd ## _neon(int16_t *dst, \
const uint8_t *_src, ptrdiff_t _src_stride, int height, \
intptr_t mx, intptr_t my, int width);
DMVR_FUN(, 8)
DMVR_FUN(, 12)
DMVR_FUN(h_, 8)
DMVR_FUN(h_, 10)
DMVR_FUN(h_, 12)
DMVR_FUN(v_, 8)
DMVR_FUN(hv_, 8)
DMVR_FUN(hv_, 10)
DMVR_FUN(hv_, 12)
#define APPLY_BDOF_FUNC(bd) \
void ff_vvc_apply_bdof_ ## bd ## _neon(uint8_t *_dst, ptrdiff_t _dst_stride, \
const int16_t *_src0, const int16_t *_src1, \
int block_w, int block_h);
APPLY_BDOF_FUNC(8)
APPLY_BDOF_FUNC(10)
APPLY_BDOF_FUNC(12)
void ff_vvc_dsp_init_aarch64(VVCDSPContext *const c, const int bd)
{
int cpu_flags = av_get_cpu_flags();
if (!have_neon(cpu_flags))
return;
if (bd == 8) {
c->inter.put[0][1][0][0] = ff_vvc_put_pel_pixels4_8_neon;
c->inter.put[0][2][0][0] = ff_vvc_put_pel_pixels8_8_neon;
c->inter.put[0][3][0][0] = ff_vvc_put_pel_pixels16_8_neon;
c->inter.put[0][4][0][0] = ff_vvc_put_pel_pixels32_8_neon;
c->inter.put[0][5][0][0] = ff_vvc_put_pel_pixels64_8_neon;
c->inter.put[0][6][0][0] = ff_vvc_put_pel_pixels128_8_neon;
c->inter.put[0][1][0][1] = ff_vvc_put_qpel_h4_8_neon;
c->inter.put[0][2][0][1] = ff_vvc_put_qpel_h8_8_neon;
c->inter.put[0][3][0][1] = ff_vvc_put_qpel_h16_8_neon;
c->inter.put[0][4][0][1] =
c->inter.put[0][5][0][1] =
c->inter.put[0][6][0][1] = ff_vvc_put_qpel_h32_8_neon;
c->inter.put[0][1][1][0] = ff_vvc_put_qpel_v4_8_neon;
c->inter.put[0][2][1][0] =
c->inter.put[0][3][1][0] =
c->inter.put[0][4][1][0] =
c->inter.put[0][5][1][0] =
c->inter.put[0][6][1][0] = ff_vvc_put_qpel_v8_8_neon;
c->inter.put[0][1][1][1] = ff_vvc_put_qpel_hv4_8_neon;
c->inter.put[0][2][1][1] = ff_vvc_put_qpel_hv8_8_neon;
c->inter.put[0][3][1][1] = ff_vvc_put_qpel_hv16_8_neon;
c->inter.put[0][4][1][1] = ff_vvc_put_qpel_hv32_8_neon;
c->inter.put[0][5][1][1] = ff_vvc_put_qpel_hv64_8_neon;
c->inter.put[0][6][1][1] = ff_vvc_put_qpel_hv128_8_neon;
c->inter.put[1][1][0][0] = ff_vvc_put_pel_pixels4_8_neon;
c->inter.put[1][2][0][0] = ff_vvc_put_pel_pixels8_8_neon;
c->inter.put[1][3][0][0] = ff_vvc_put_pel_pixels16_8_neon;
c->inter.put[1][4][0][0] = ff_vvc_put_pel_pixels32_8_neon;
c->inter.put[1][5][0][0] = ff_vvc_put_pel_pixels64_8_neon;
c->inter.put[1][6][0][0] = ff_vvc_put_pel_pixels128_8_neon;
c->inter.put[1][1][0][1] = ff_vvc_put_epel_h4_8_neon;
c->inter.put[1][2][0][1] = ff_vvc_put_epel_h8_8_neon;
c->inter.put[1][3][0][1] = ff_vvc_put_epel_h16_8_neon;
c->inter.put[1][4][0][1] =
c->inter.put[1][5][0][1] =
c->inter.put[1][6][0][1] = ff_vvc_put_epel_h32_8_neon;
c->inter.put[1][1][1][1] = ff_vvc_put_epel_hv4_8_neon;
c->inter.put[1][2][1][1] = ff_vvc_put_epel_hv8_8_neon;
c->inter.put[1][3][1][1] = ff_vvc_put_epel_hv16_8_neon;
c->inter.put[1][4][1][1] = ff_vvc_put_epel_hv32_8_neon;
c->inter.put[1][5][1][1] = ff_vvc_put_epel_hv64_8_neon;
c->inter.put[1][6][1][1] = ff_vvc_put_epel_hv128_8_neon;
c->inter.put_uni[0][1][0][0] = ff_vvc_put_pel_uni_pixels4_8_neon;
c->inter.put_uni[0][2][0][0] = ff_vvc_put_pel_uni_pixels8_8_neon;
c->inter.put_uni[0][3][0][0] = ff_vvc_put_pel_uni_pixels16_8_neon;
c->inter.put_uni[0][4][0][0] = ff_vvc_put_pel_uni_pixels32_8_neon;
c->inter.put_uni[0][5][0][0] = ff_vvc_put_pel_uni_pixels64_8_neon;
c->inter.put_uni[0][6][0][0] = ff_vvc_put_pel_uni_pixels128_8_neon;
c->inter.put_uni[0][1][0][1] = ff_vvc_put_qpel_uni_h4_8_neon;
c->inter.put_uni[0][2][0][1] = ff_vvc_put_qpel_uni_h8_8_neon;
c->inter.put_uni[0][3][0][1] = ff_vvc_put_qpel_uni_h16_8_neon;
c->inter.put_uni[0][4][0][1] =
c->inter.put_uni[0][5][0][1] =
c->inter.put_uni[0][6][0][1] = ff_vvc_put_qpel_uni_h32_8_neon;
c->inter.put_uni_w[0][1][0][0] = ff_vvc_put_pel_uni_w_pixels4_8_neon;
c->inter.put_uni_w[0][2][0][0] = ff_vvc_put_pel_uni_w_pixels8_8_neon;
c->inter.put_uni_w[0][3][0][0] = ff_vvc_put_pel_uni_w_pixels16_8_neon;
c->inter.put_uni_w[0][4][0][0] = ff_vvc_put_pel_uni_w_pixels32_8_neon;
c->inter.put_uni_w[0][5][0][0] = ff_vvc_put_pel_uni_w_pixels64_8_neon;
c->inter.put_uni_w[0][6][0][0] = ff_vvc_put_pel_uni_w_pixels128_8_neon;
c->inter.avg = ff_vvc_avg_8_neon;
c->inter.w_avg = vvc_w_avg_8;
c->inter.dmvr[0][0] = ff_vvc_dmvr_8_neon;
c->inter.dmvr[0][1] = ff_vvc_dmvr_h_8_neon;
c->inter.dmvr[1][0] = ff_vvc_dmvr_v_8_neon;
c->inter.dmvr[1][1] = ff_vvc_dmvr_hv_8_neon;
c->inter.apply_bdof = ff_vvc_apply_bdof_8_neon;
c->sao.band_filter[0] = ff_h26x_sao_band_filter_8x8_8_neon;
for (int i = 1; i < FF_ARRAY_ELEMS(c->sao.band_filter); i++)
c->sao.band_filter[i] = ff_h26x_sao_band_filter_16x16_8_neon;
c->sao.edge_filter[0] = ff_vvc_sao_edge_filter_8x8_8_neon;
for (int i = 1; i < FF_ARRAY_ELEMS(c->sao.edge_filter); i++)
c->sao.edge_filter[i] = ff_vvc_sao_edge_filter_16x16_8_neon;
c->alf.filter[LUMA] = alf_filter_luma_8_neon;
c->alf.filter[CHROMA] = alf_filter_chroma_8_neon;
c->alf.classify = alf_classify_8_neon;
if (have_i8mm(cpu_flags)) {
c->inter.put[0][1][0][1] = ff_vvc_put_qpel_h4_8_neon_i8mm;
c->inter.put[0][2][0][1] = ff_vvc_put_qpel_h8_8_neon_i8mm;
c->inter.put[0][3][0][1] = ff_vvc_put_qpel_h16_8_neon_i8mm;
c->inter.put[0][4][0][1] = ff_vvc_put_qpel_h32_8_neon_i8mm;
c->inter.put[0][5][0][1] = ff_vvc_put_qpel_h64_8_neon_i8mm;
c->inter.put[0][6][0][1] = ff_vvc_put_qpel_h128_8_neon_i8mm;
c->inter.put[0][1][1][1] = ff_vvc_put_qpel_hv4_8_neon_i8mm;
c->inter.put[0][2][1][1] = ff_vvc_put_qpel_hv8_8_neon_i8mm;
c->inter.put[0][3][1][1] = ff_vvc_put_qpel_hv16_8_neon_i8mm;
c->inter.put[0][4][1][1] = ff_vvc_put_qpel_hv32_8_neon_i8mm;
c->inter.put[0][5][1][1] = ff_vvc_put_qpel_hv64_8_neon_i8mm;
c->inter.put[0][6][1][1] = ff_vvc_put_qpel_hv128_8_neon_i8mm;
c->inter.put[1][1][0][1] = ff_vvc_put_epel_h4_8_neon_i8mm;
c->inter.put[1][2][0][1] = ff_vvc_put_epel_h8_8_neon_i8mm;
c->inter.put[1][3][0][1] = ff_vvc_put_epel_h16_8_neon_i8mm;
c->inter.put[1][4][0][1] = ff_vvc_put_epel_h32_8_neon_i8mm;
c->inter.put[1][5][0][1] = ff_vvc_put_epel_h64_8_neon_i8mm;
c->inter.put[1][6][0][1] = ff_vvc_put_epel_h128_8_neon_i8mm;
c->inter.put[1][1][1][1] = ff_vvc_put_epel_hv4_8_neon_i8mm;
c->inter.put[1][2][1][1] = ff_vvc_put_epel_hv8_8_neon_i8mm;
c->inter.put[1][3][1][1] = ff_vvc_put_epel_hv16_8_neon_i8mm;
c->inter.put[1][4][1][1] = ff_vvc_put_epel_hv32_8_neon_i8mm;
c->inter.put[1][5][1][1] = ff_vvc_put_epel_hv64_8_neon_i8mm;
c->inter.put[1][6][1][1] = ff_vvc_put_epel_hv128_8_neon_i8mm;
}
if (have_sme2(cpu_flags) && have_sme_i16i64(cpu_flags)) {
c->alf.filter[LUMA] = alf_filter_luma_8_sme2;
}
} else if (bd == 10) {
c->inter.avg = ff_vvc_avg_10_neon;
c->inter.w_avg = vvc_w_avg_10;
c->inter.dmvr[0][1] = ff_vvc_dmvr_h_10_neon;
c->inter.dmvr[1][1] = ff_vvc_dmvr_hv_10_neon;
c->inter.apply_bdof = ff_vvc_apply_bdof_10_neon;
c->inter.put[0][2][0][1] = ff_vvc_put_luma_h8_10_neon;
c->inter.put[0][3][0][1] = ff_vvc_put_luma_h16_10_neon;
c->inter.put[0][4][0][1] =
c->inter.put[0][5][0][1] =
c->inter.put[0][6][0][1] = ff_vvc_put_luma_h_x16_10_neon;
c->inter.put[0][1][1][0] = ff_vvc_put_luma_v4_10_neon;
c->inter.put[0][2][1][0] = ff_vvc_put_luma_v8_10_neon;
c->inter.put[0][3][1][0] = ff_vvc_put_luma_v16_10_neon;
c->inter.put[0][4][1][0] =
c->inter.put[0][5][1][0] =
c->inter.put[0][6][1][0] = ff_vvc_put_luma_v_x16_10_neon;
c->inter.put[0][2][1][1] = ff_vvc_put_luma_hv8_10_neon;
c->inter.put[0][3][1][1] = ff_vvc_put_luma_hv16_10_neon;
c->inter.put[0][4][1][1] =
c->inter.put[0][5][1][1] =
c->inter.put[0][6][1][1] = ff_vvc_put_luma_hv_x16_10_neon;
c->alf.filter[LUMA] = alf_filter_luma_10_neon;
c->alf.filter[CHROMA] = alf_filter_chroma_10_neon;
c->alf.classify = alf_classify_10_neon;
if (have_sme2(cpu_flags) && have_sme_i16i64(cpu_flags)) {
c->alf.filter[LUMA] = alf_filter_luma_10_sme2;
}
} else if (bd == 12) {
c->inter.avg = ff_vvc_avg_12_neon;
c->inter.w_avg = vvc_w_avg_12;
c->inter.dmvr[0][0] = ff_vvc_dmvr_12_neon;
c->inter.dmvr[0][1] = ff_vvc_dmvr_h_12_neon;
c->inter.dmvr[1][1] = ff_vvc_dmvr_hv_12_neon;
c->inter.apply_bdof = ff_vvc_apply_bdof_12_neon;
c->inter.put[0][2][0][1] = ff_vvc_put_luma_h8_12_neon;
c->inter.put[0][3][0][1] = ff_vvc_put_luma_h16_12_neon;
c->inter.put[0][4][0][1] =
c->inter.put[0][5][0][1] =
c->inter.put[0][6][0][1] = ff_vvc_put_luma_h_x16_12_neon;
c->inter.put[0][2][1][1] = ff_vvc_put_luma_hv8_12_neon;
c->inter.put[0][3][1][1] = ff_vvc_put_luma_hv16_12_neon;
c->inter.put[0][4][1][1] =
c->inter.put[0][5][1][1] =
c->inter.put[0][6][1][1] = ff_vvc_put_luma_hv_x16_12_neon;
c->inter.put[0][1][1][0] = ff_vvc_put_luma_v4_12_neon;
c->inter.put[0][2][1][0] = ff_vvc_put_luma_v8_12_neon;
c->inter.put[0][3][1][0] = ff_vvc_put_luma_v16_12_neon;
c->inter.put[0][4][1][0] =
c->inter.put[0][5][1][0] =
c->inter.put[0][6][1][0] = ff_vvc_put_luma_v_x16_12_neon;
c->alf.filter[LUMA] = alf_filter_luma_12_neon;
c->alf.filter[CHROMA] = alf_filter_chroma_12_neon;
c->alf.classify = alf_classify_12_neon;
if (have_sme2(cpu_flags) && have_sme_i16i64(cpu_flags)) {
c->alf.filter[LUMA] = alf_filter_luma_12_sme2;
}
}
c->inter.sad = ff_vvc_sad_neon;
}
Reference in New Issue View Git Blame Copy Permalink