lineage-rockchip/android_external_ffmpeg
1
0
Fork 0
Code Activity Actions

aarch64/vvc: Add put_qpel_hx i8mm

Browse source 
Benchmark on Android pixel 8 with -fno-vectorize

put_luma_h_8_4x4_c:                                      0.2 ( 1.00x)
put_luma_h_8_4x4_neon:                                   0.2 ( 1.00x)
put_luma_h_8_4x4_i8mm:                                   0.0 ( 0.00x)
put_luma_h_8_8x8_c:                                      1.5 ( 1.00x)
put_luma_h_8_8x8_neon:                                   0.5 ( 3.00x)
put_luma_h_8_8x8_i8mm:                                   0.5 ( 3.00x)
put_luma_h_8_16x16_c:                                    6.2 ( 1.00x)
put_luma_h_8_16x16_neon:                                 2.0 ( 3.12x)
put_luma_h_8_16x16_i8mm:                                 1.5 ( 4.17x)
put_luma_h_8_32x32_c:                                   25.5 ( 1.00x)
put_luma_h_8_32x32_neon:                                 9.0 ( 2.83x)
put_luma_h_8_32x32_i8mm:                                 6.8 ( 3.78x)
put_luma_h_8_64x64_c:                                   99.8 ( 1.00x)
put_luma_h_8_64x64_neon:                                35.2 ( 2.83x)
put_luma_h_8_64x64_i8mm:                                27.2 ( 3.66x)
put_luma_h_8_128x128_c:                                422.0 ( 1.00x)
put_luma_h_8_128x128_neon:                             138.5 ( 3.05x)
put_luma_h_8_128x128_i8mm:                             109.2 ( 3.86x)
This commit is contained in:
Zhao Zhili 2024-09-07 16:28:34 +08:00 • committed by Nuo Mi
parent 25448d1716
commit 9f6c8eb412
3 changed files with 76 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

9
libavcodec/aarch64/vvc/dsp_init.c
View file

@ -88,6 +88,15 @@ void ff_vvc_dsp_init_aarch64(VVCDSPContext *const c, const int bd)
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;
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;
}
} else if (bd == 10) {
c->alf.filter[LUMA] = alf_filter_luma_10_neon;
c->alf.filter[CHROMA] = alf_filter_chroma_10_neon;