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

aarch64/vvc: Add put_qpel_hv

Browse source 
With Apple M1 (no i8mm):

put_luma_hv_8_4x4_c:                                     2.2 ( 1.00x)
put_luma_hv_8_4x4_neon:                                  0.8 ( 3.00x)
put_luma_hv_8_8x8_c:                                     7.0 ( 1.00x)
put_luma_hv_8_8x8_neon:                                  0.8 ( 9.33x)
put_luma_hv_8_16x16_c:                                  22.8 ( 1.00x)
put_luma_hv_8_16x16_neon:                                2.5 ( 9.10x)
put_luma_hv_8_32x32_c:                                  84.8 ( 1.00x)
put_luma_hv_8_32x32_neon:                                9.5 ( 8.92x)
put_luma_hv_8_64x64_c:                                 333.0 ( 1.00x)
put_luma_hv_8_64x64_neon:                               35.5 ( 9.38x)
put_luma_hv_8_128x128_c:                              1294.5 ( 1.00x)
put_luma_hv_8_128x128_neon:                            137.8 ( 9.40x)

With Pixel 8 Pro:

put_luma_hv_8_4x4_c:                                     5.0 ( 1.00x)
put_luma_hv_8_4x4_neon:                                  0.8 ( 6.67x)
put_luma_hv_8_4x4_i8mm:                                  0.2 (20.00x)
put_luma_hv_8_8x8_c:                                    13.2 ( 1.00x)
put_luma_hv_8_8x8_neon:                                  1.2 (10.60x)
put_luma_hv_8_8x8_i8mm:                                  1.2 (10.60x)
put_luma_hv_8_16x16_c:                                  44.2 ( 1.00x)
put_luma_hv_8_16x16_neon:                                4.5 ( 9.83x)
put_luma_hv_8_16x16_i8mm:                                4.2 (10.41x)
put_luma_hv_8_32x32_c:                                 160.8 ( 1.00x)
put_luma_hv_8_32x32_neon:                               17.5 ( 9.19x)
put_luma_hv_8_32x32_i8mm:                               16.0 (10.05x)
put_luma_hv_8_64x64_c:                                 611.2 ( 1.00x)
put_luma_hv_8_64x64_neon:                               68.0 ( 8.99x)
put_luma_hv_8_64x64_i8mm:                               62.2 ( 9.82x)
put_luma_hv_8_128x128_c:                              2384.8 ( 1.00x)
put_luma_hv_8_128x128_neon:                            268.8 ( 8.87x)
put_luma_hv_8_128x128_i8mm:                            245.8 ( 9.70x)
This commit is contained in:
Zhao Zhili 2024-09-11 00:59:27 +08:00 • committed by Nuo Mi
parent a0b52afd32
commit 5ac6925803
3 changed files with 162 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

14
libavcodec/aarch64/vvc/dsp_init.c
View file

@ -67,6 +67,13 @@ void ff_vvc_dsp_init_aarch64(VVCDSPContext *const c, const int bd)
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_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;
@ -103,6 +110,13 @@ void ff_vvc_dsp_init_aarch64(VVCDSPContext *const c, const int bd)
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;
}
} else if (bd == 10) {
c->alf.filter[LUMA] = alf_filter_luma_10_neon;