39786f8cd5
aarch64/h26x: optimize sao_band_filter
...
int8_t[] is enough for offset_table of 8 bit streams.
On rpi5:
Before After
hevc_sao_band_8_8_c: 252.3 ( 1.00x) 252.3 ( 1.00x)
hevc_sao_band_8_8_neon: 95.8 ( 2.63x) 61.0 ( 4.57x)
hevc_sao_band_16_8_c: 875.2 ( 1.00x) 864.9 ( 1.00x)
hevc_sao_band_16_8_neon: 317.5 ( 2.76x) 150.0 ( 6.26x)
hevc_sao_band_32_8_c: 3853.5 ( 1.00x) 3871.6 ( 1.00x)
hevc_sao_band_32_8_neon: 1222.3 ( 3.15x) 550.6 ( 7.39)
hevc_sao_band_48_8_c: 8203.6 ( 1.00x) 8182.6 ( 1.00x)
hevc_sao_band_48_8_neon: 2685.7 ( 3.05x) 1185.8 ( 7.36x)
hevc_sao_band_64_8_c: 14023.0 ( 1.00x) 14038.9 ( 1.00x)
hevc_sao_band_64_8_neon: 4783.2 ( 2.93x) 2078.4 ( 7.15x)
Reviewed-by: Martin Storsjö <martin@martin.st>
Signed-off-by: Zhao Zhili <zhilizhao@tencent.com>
2025-04-29 15:11:45 +08:00
f9b8f30680
avcodec/aarch64/vvc: Optimize vvc_avg{8, 10, 12}
...
This patch replaces integer widening with halving addition, and
multi-step "emulated" rounding shift with a single asm instruction doing
exactly that.
Benchmarks before and after:
A78
avg_8_64x64_neon: 2686.2 ( 6.12x)
avg_8_128x128_neon: 10734.2 ( 5.88x)
avg_10_64x64_neon: 2536.8 ( 5.40x)
avg_10_128x128_neon: 10079.0 ( 5.22x)
avg_12_64x64_neon: 2548.2 ( 5.38x)
avg_12_128x128_neon: 10133.8 ( 5.19x)
avg_8_64x64_neon: 897.8 (18.26x)
avg_8_128x128_neon: 3608.5 (17.37x)
avg_10_32x32_neon: 444.2 ( 8.51x)
avg_10_64x64_neon: 1711.8 ( 8.00x)
avg_12_64x64_neon: 1706.2 ( 8.02x)
avg_12_128x128_neon: 7010.0 ( 7.46x)
A72
avg_8_64x64_neon: 5823.4 ( 3.88x)
avg_8_128x128_neon: 17430.5 ( 4.73x)
avg_10_64x64_neon: 5228.1 ( 3.71x)
avg_10_128x128_neon: 16722.2 ( 4.17x)
avg_12_64x64_neon: 5379.1 ( 3.51x)
avg_12_128x128_neon: 16715.7 ( 4.17x)
avg_8_64x64_neon: 2006.5 (10.61x)
avg_8_128x128_neon: 9158.7 ( 8.96x)
avg_10_64x64_neon: 3357.7 ( 5.60x)
avg_10_128x128_neon: 12411.7 ( 5.56x)
avg_12_64x64_neon: 3317.5 ( 5.67x)
avg_12_128x128_neon: 12358.5 ( 5.58x)
A53
avg_8_64x64_neon: 8327.8 ( 5.18x)
avg_8_128x128_neon: 31631.3 ( 5.34x)
avg_10_64x64_neon: 8783.5 ( 4.98x)
avg_10_128x128_neon: 32617.0 ( 5.25x)
avg_12_64x64_neon: 8686.0 ( 5.06x)
avg_12_128x128_neon: 32487.5 ( 5.25x)
avg_8_64x64_neon: 6032.3 ( 7.17x)
avg_8_128x128_neon: 22008.5 ( 7.69x)
avg_10_64x64_neon: 7738.0 ( 5.68x)
avg_10_128x128_neon: 27813.8 ( 6.14x)
avg_12_64x64_neon: 7844.5 ( 5.60x)
avg_12_128x128_neon: 26999.5 ( 6.34x)
Signed-off-by: Martin Storsjö <martin@martin.st>
2025-03-07 15:51:20 +02:00
71a91485fa
avcodec/aarch64/vvc: Optimize NEON version of vvc_dmvr
...
This patch replaces blocks of instructions performing rounding and
widening shifts with one-liners achieving the same result.
Before and after on A78
dmvr_8_12x20_neon: 86.2 ( 6.90x)
dmvr_8_20x12_neon: 94.8 ( 5.93x)
dmvr_8_20x20_neon: 141.5 ( 6.50x)
dmvr_12_12x20_neon: 158.0 ( 3.76x)
dmvr_12_20x12_neon: 151.2 ( 3.73x)
dmvr_12_20x20_neon: 247.2 ( 3.71x)
dmvr_hv_8_12x20_neon: 423.2 ( 3.75x)
dmvr_hv_8_20x12_neon: 434.0 ( 3.69x)
dmvr_hv_8_20x20_neon: 706.0 ( 3.69x)
dmvr_8_12x20_neon: 77.2 ( 7.70x)
dmvr_8_20x12_neon: 66.5 ( 8.49x)
dmvr_8_20x20_neon: 92.2 ( 9.90x)
dmvr_12_12x20_neon: 80.2 ( 7.38x)
dmvr_12_20x12_neon: 58.2 ( 9.59x)
dmvr_12_20x20_neon: 90.0 (10.15x)
dmvr_hv_8_12x20_neon: 369.0 ( 4.34x)
dmvr_hv_8_20x12_neon: 355.8 ( 4.49x)
dmvr_hv_8_20x20_neon: 574.2 ( 4.51x)
Signed-off-by: Martin Storsjö <martin@martin.st>
2025-03-04 10:35:31 +02:00
952508ae05
aarch64/vvc: Add apply_bdof
...
Test on rpi 5 with gcc 12:
apply_bdof_8_8x16_c: 7315.2 ( 1.00x)
apply_bdof_8_8x16_neon: 1876.8 ( 3.90x)
apply_bdof_8_16x8_c: 7170.5 ( 1.00x)
apply_bdof_8_16x8_neon: 1752.8 ( 4.09x)
apply_bdof_8_16x16_c: 14695.2 ( 1.00x)
apply_bdof_8_16x16_neon: 3490.5 ( 4.21x)
apply_bdof_10_8x16_c: 7371.5 ( 1.00x)
apply_bdof_10_8x16_neon: 1863.8 ( 3.96x)
apply_bdof_10_16x8_c: 7172.0 ( 1.00x)
apply_bdof_10_16x8_neon: 1766.0 ( 4.06x)
apply_bdof_10_16x16_c: 14551.5 ( 1.00x)
apply_bdof_10_16x16_neon: 3576.0 ( 4.07x)
apply_bdof_12_8x16_c: 7236.5 ( 1.00x)
apply_bdof_12_8x16_neon: 1863.8 ( 3.88x)
apply_bdof_12_16x8_c: 7316.5 ( 1.00x)
apply_bdof_12_16x8_neon: 1758.8 ( 4.16x)
apply_bdof_12_16x16_c: 14691.2 ( 1.00x)
apply_bdof_12_16x16_neon: 3480.5 ( 4.22x)
2024-12-21 11:54:44 +08:00
2bb00ef59c
aarch64: vvc: Fix building the dmvr_hv assembly with older MSVC versions
...
Explicitly use ldur for unaligned offsets; newer versions of
armasm64 implicitly convert ldr to ldur as necessary, but older
versions require it explicitly written out.
This fixes these build errors:
ffmpeg\libavcodec\aarch64\vvc\inter.o.asm(2039) :
error A2518: operand 2: Memory offset must be aligned
ldr s5, [x1, #1 ]
ffmpeg\libavcodec\aarch64\vvc\inter.o.asm(2250) :
error A2518: operand 2: Memory offset must be aligned
ldr d7, [x1, #2 ]
Signed-off-by: Martin Storsjö <martin@martin.st>
2024-12-18 13:45:09 +02:00
40feba5f77
aarch64/vvc: Fix clip in alf
...
Fix test failure:
./tests/checkasm/checkasm --test=vvc_alf 3607569773
2024-12-10 21:00:47 +08:00
91436638de
aarch64/vvc: Use faster clip operation
...
Replace sqxtn+smin+smax by sqxtun+umin.
2024-12-10 21:00:47 +08:00
bfed5f6b7d
aarch64/vvc: Reuse ff_vvc_put_pel_pixels for chroma
2024-12-10 21:00:47 +08:00
5988a2729b
aarch64/vvc: Add dmvr
...
dmvr_8_12x20_c: 1.5 ( 1.00x)
dmvr_8_12x20_neon: 0.2 ( 6.56x)
dmvr_8_20x12_c: 1.0 ( 1.00x)
dmvr_8_20x12_neon: 0.2 ( 4.33x)
dmvr_8_20x20_c: 1.7 ( 1.00x)
dmvr_8_20x20_neon: 0.5 ( 3.63x)
dmvr_12_12x20_c: 2.2 ( 1.00x)
dmvr_12_12x20_neon: 0.5 ( 4.68x)
dmvr_12_20x12_c: 2.0 ( 1.00x)
dmvr_12_20x12_neon: 0.5 ( 4.16x)
dmvr_12_20x20_c: 3.7 ( 1.00x)
dmvr_12_20x20_neon: 0.7 ( 5.14x)
Signed-off-by: Zhao Zhili <zhilizhao@tencent.com>
2024-10-01 10:28:54 +08:00
bcd65ebd8f
aarch64/vvc: Add dmvr_hv
...
dmvr_hv_8_12x20_c: 8.0 ( 1.00x)
dmvr_hv_8_12x20_neon: 1.2 ( 6.62x)
dmvr_hv_8_20x12_c: 8.0 ( 1.00x)
dmvr_hv_8_20x12_neon: 0.9 ( 8.37x)
dmvr_hv_8_20x20_c: 12.9 ( 1.00x)
dmvr_hv_8_20x20_neon: 1.7 ( 7.62x)
dmvr_hv_10_12x20_c: 7.0 ( 1.00x)
dmvr_hv_10_12x20_neon: 1.7 ( 4.09x)
dmvr_hv_10_20x12_c: 7.0 ( 1.00x)
dmvr_hv_10_20x12_neon: 1.7 ( 4.09x)
dmvr_hv_10_20x20_c: 11.2 ( 1.00x)
dmvr_hv_10_20x20_neon: 2.7 ( 4.15x)
dmvr_hv_12_12x20_c: 6.5 ( 1.00x)
dmvr_hv_12_12x20_neon: 1.7 ( 3.79x)
dmvr_hv_12_20x12_c: 6.5 ( 1.00x)
dmvr_hv_12_20x12_neon: 1.7 ( 3.79x)
dmvr_hv_12_20x20_c: 10.2 ( 1.00x)
dmvr_hv_12_20x20_neon: 2.2 ( 4.64x)
Signed-off-by: Zhao Zhili <zhilizhao@tencent.com>
2024-10-01 10:28:54 +08:00
0ba9e8d0d4
aarch64/vvc: Add w_avg
...
w_avg_8_2x2_c: 0.0 ( 0.00x)
w_avg_8_2x2_neon: 0.0 ( 0.00x)
w_avg_8_4x4_c: 0.2 ( 1.00x)
w_avg_8_4x4_neon: 0.0 ( 0.00x)
w_avg_8_8x8_c: 1.2 ( 1.00x)
w_avg_8_8x8_neon: 0.2 ( 5.00x)
w_avg_8_16x16_c: 4.2 ( 1.00x)
w_avg_8_16x16_neon: 0.8 ( 5.67x)
w_avg_8_32x32_c: 16.2 ( 1.00x)
w_avg_8_32x32_neon: 2.5 ( 6.50x)
w_avg_8_64x64_c: 64.5 ( 1.00x)
w_avg_8_64x64_neon: 9.0 ( 7.17x)
w_avg_8_128x128_c: 269.5 ( 1.00x)
w_avg_8_128x128_neon: 35.5 ( 7.59x)
w_avg_10_2x2_c: 0.2 ( 1.00x)
w_avg_10_2x2_neon: 0.2 ( 1.00x)
w_avg_10_4x4_c: 0.2 ( 1.00x)
w_avg_10_4x4_neon: 0.2 ( 1.00x)
w_avg_10_8x8_c: 1.0 ( 1.00x)
w_avg_10_8x8_neon: 0.2 ( 4.00x)
w_avg_10_16x16_c: 4.2 ( 1.00x)
w_avg_10_16x16_neon: 0.8 ( 5.67x)
w_avg_10_32x32_c: 16.2 ( 1.00x)
w_avg_10_32x32_neon: 2.5 ( 6.50x)
w_avg_10_64x64_c: 66.2 ( 1.00x)
w_avg_10_64x64_neon: 10.0 ( 6.62x)
w_avg_10_128x128_c: 277.8 ( 1.00x)
w_avg_10_128x128_neon: 39.8 ( 6.99x)
w_avg_12_2x2_c: 0.0 ( 0.00x)
w_avg_12_2x2_neon: 0.2 ( 0.00x)
w_avg_12_4x4_c: 0.2 ( 1.00x)
w_avg_12_4x4_neon: 0.0 ( 0.00x)
w_avg_12_8x8_c: 1.2 ( 1.00x)
w_avg_12_8x8_neon: 0.5 ( 2.50x)
w_avg_12_16x16_c: 4.8 ( 1.00x)
w_avg_12_16x16_neon: 0.8 ( 6.33x)
w_avg_12_32x32_c: 17.0 ( 1.00x)
w_avg_12_32x32_neon: 2.8 ( 6.18x)
w_avg_12_64x64_c: 64.0 ( 1.00x)
w_avg_12_64x64_neon: 10.0 ( 6.40x)
w_avg_12_128x128_c: 269.2 ( 1.00x)
w_avg_12_128x128_neon: 42.0 ( 6.41x)
Signed-off-by: Zhao Zhili <zhilizhao@tencent.com>
2024-10-01 10:28:54 +08:00
3f84d1d1fb
aarch64/vvc: Add avg
...
avg_8_2x2_c: 0.2 ( 1.00x)
avg_8_2x2_neon: 0.2 ( 1.00x)
avg_8_4x4_c: 0.2 ( 1.00x)
avg_8_4x4_neon: 0.2 ( 1.00x)
avg_8_8x8_c: 0.9 ( 1.00x)
avg_8_8x8_neon: 0.2 ( 5.29x)
avg_8_16x16_c: 3.7 ( 1.00x)
avg_8_16x16_neon: 0.7 ( 5.44x)
avg_8_32x32_c: 14.9 ( 1.00x)
avg_8_32x32_neon: 1.7 ( 8.91x)
avg_8_64x64_c: 59.7 ( 1.00x)
avg_8_64x64_neon: 6.9 ( 8.62x)
avg_8_128x128_c: 254.7 ( 1.00x)
avg_8_128x128_neon: 26.9 ( 9.46x)
avg_10_2x2_c: 0.2 ( 1.00x)
avg_10_2x2_neon: 0.2 ( 1.00x)
avg_10_4x4_c: 0.2 ( 1.00x)
avg_10_4x4_neon: 0.2 ( 1.00x)
avg_10_8x8_c: 0.9 ( 1.00x)
avg_10_8x8_neon: 0.2 ( 5.29x)
avg_10_16x16_c: 3.4 ( 1.00x)
avg_10_16x16_neon: 0.4 ( 8.06x)
avg_10_32x32_c: 13.9 ( 1.00x)
avg_10_32x32_neon: 1.9 ( 7.23x)
avg_10_64x64_c: 54.2 ( 1.00x)
avg_10_64x64_neon: 8.4 ( 6.43x)
avg_10_128x128_c: 232.4 ( 1.00x)
avg_10_128x128_neon: 30.9 ( 7.52x)
avg_12_2x2_c: 0.0 ( 0.00x)
avg_12_2x2_neon: 0.2 ( 0.00x)
avg_12_4x4_c: 0.4 ( 1.00x)
avg_12_4x4_neon: 0.2 ( 2.43x)
avg_12_8x8_c: 0.7 ( 1.00x)
avg_12_8x8_neon: 0.2 ( 3.86x)
avg_12_16x16_c: 3.7 ( 1.00x)
avg_12_16x16_neon: 0.4 ( 8.65x)
avg_12_32x32_c: 13.7 ( 1.00x)
avg_12_32x32_neon: 2.2 ( 6.29x)
avg_12_64x64_c: 53.9 ( 1.00x)
avg_12_64x64_neon: 7.7 ( 7.03x)
avg_12_128x128_c: 270.9 ( 1.00x)
avg_12_128x128_neon: 30.4 ( 8.90x)
2024-09-14 16:36:34 +08:00
1be5a2374f
aarch64/vvc: Add put_epel_hv
...
On Apple M1:
put_chroma_hv_8_4x4_c: 1.7 ( 1.00x)
put_chroma_hv_8_4x4_neon: 0.2 ( 7.67x)
put_chroma_hv_8_8x8_c: 5.5 ( 1.00x)
put_chroma_hv_8_8x8_neon: 0.5 (11.53x)
put_chroma_hv_8_16x16_c: 18.5 ( 1.00x)
put_chroma_hv_8_16x16_neon: 1.5 (12.53x)
put_chroma_hv_8_32x32_c: 72.5 ( 1.00x)
put_chroma_hv_8_32x32_neon: 4.7 (15.34x)
put_chroma_hv_8_64x64_c: 274.0 ( 1.00x)
put_chroma_hv_8_64x64_neon: 18.5 (14.83x)
put_chroma_hv_8_128x128_c: 1058.7 ( 1.00x)
put_chroma_hv_8_128x128_neon: 75.2 (14.07x)
On Android Pixel 8 Pro:
put_chroma_hv_8_4x4_c: 1.2 ( 1.00x)
put_chroma_hv_8_4x4_neon: 0.0 ( 0.00x)
put_chroma_hv_8_4x4_i8mm: 0.2 ( 5.00x)
put_chroma_hv_8_8x8_c: 4.0 ( 1.00x)
put_chroma_hv_8_8x8_neon: 0.5 ( 8.00x)
put_chroma_hv_8_8x8_i8mm: 0.5 ( 8.00x)
put_chroma_hv_8_16x16_c: 15.2 ( 1.00x)
put_chroma_hv_8_16x16_neon: 2.5 ( 6.10x)
put_chroma_hv_8_16x16_i8mm: 2.2 ( 6.78x)
put_chroma_hv_8_32x32_c: 61.0 ( 1.00x)
put_chroma_hv_8_32x32_neon: 9.8 ( 6.26x)
put_chroma_hv_8_32x32_i8mm: 8.5 ( 7.18x)
put_chroma_hv_8_64x64_c: 229.5 ( 1.00x)
put_chroma_hv_8_64x64_neon: 38.5 ( 5.96x)
put_chroma_hv_8_64x64_i8mm: 34.0 ( 6.75x)
put_chroma_hv_8_128x128_c: 919.8 ( 1.00x)
put_chroma_hv_8_128x128_neon: 154.5 ( 5.95x)
put_chroma_hv_8_128x128_i8mm: 140.0 ( 6.57x)
2024-09-14 16:36:34 +08:00
0dcf204e5d
aarch64/vvc: Add put_epel_h i8mm
...
put_chroma_h_8_4x4_c: 0.4 ( 1.00x)
put_chroma_h_8_4x4_neon: 0.0 ( 0.00x)
put_chroma_h_8_4x4_i8mm: 0.1 ( 2.67x)
put_chroma_h_8_8x8_c: 1.6 ( 1.00x)
put_chroma_h_8_8x8_neon: 0.1 (11.00x)
put_chroma_h_8_8x8_i8mm: 0.1 (11.00x)
put_chroma_h_8_16x16_c: 6.9 ( 1.00x)
put_chroma_h_8_16x16_neon: 1.1 ( 6.00x)
put_chroma_h_8_16x16_i8mm: 0.7 (10.62x)
put_chroma_h_8_32x32_c: 27.6 ( 1.00x)
put_chroma_h_8_32x32_neon: 4.7 ( 5.95x)
put_chroma_h_8_32x32_i8mm: 4.4 ( 6.28x)
put_chroma_h_8_64x64_c: 116.2 ( 1.00x)
put_chroma_h_8_64x64_neon: 19.1 ( 6.07x)
put_chroma_h_8_64x64_i8mm: 17.1 ( 6.77x)
put_chroma_h_8_128x128_c: 466.6 ( 1.00x)
put_chroma_h_8_128x128_neon: 81.4 ( 5.73x)
put_chroma_h_8_128x128_i8mm: 71.7 ( 6.51x)
2024-09-14 16:36:34 +08:00
41a1885f7a
aarch64/vvc: Add put_epel_h
...
put_chroma_h_8_4x4_c: 0.2 ( 1.00x)
put_chroma_h_8_4x4_neon: 0.2 ( 1.00x)
put_chroma_h_8_8x8_c: 0.8 ( 1.00x)
put_chroma_h_8_8x8_neon: 0.2 ( 3.00x)
put_chroma_h_8_16x16_c: 3.8 ( 1.00x)
put_chroma_h_8_16x16_neon: 0.8 ( 5.00x)
put_chroma_h_8_32x32_c: 12.5 ( 1.00x)
put_chroma_h_8_32x32_neon: 2.2 ( 5.56x)
put_chroma_h_8_64x64_c: 47.0 ( 1.00x)
put_chroma_h_8_64x64_neon: 8.8 ( 5.37x)
put_chroma_h_8_128x128_c: 200.2 ( 1.00x)
put_chroma_h_8_128x128_neon: 31.8 ( 6.31x)
2024-09-14 16:36:34 +08:00
260e1b4b62
aarch64/vvc: Add sad
...
sad_8x16_c: 0.8 ( 1.00x)
sad_8x16_neon: 0.2 ( 3.00x)
sad_16x8_c: 0.5 ( 1.00x)
sad_16x8_neon: 0.2 ( 2.00x)
sad_16x16_c: 1.5 ( 1.00x)
sad_16x16_neon: 0.2 ( 6.00x)
2024-09-14 16:36:34 +08:00
5ac6925803
aarch64/vvc: Add put_qpel_hv
...
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)
2024-09-14 16:36:34 +08:00
a0b52afd32
aarch64/vvc: Add put_qpel_vx
...
put_luma_v_8_4x4_c: 1.0 ( 1.00x)
put_luma_v_8_4x4_neon: 0.0 ( 0.00x)
put_luma_v_8_8x8_c: 3.5 ( 1.00x)
put_luma_v_8_8x8_neon: 0.5 ( 7.00x)
put_luma_v_8_16x16_c: 13.8 ( 1.00x)
put_luma_v_8_16x16_neon: 1.2 (11.00x)
put_luma_v_8_32x32_c: 54.2 ( 1.00x)
put_luma_v_8_32x32_neon: 5.0 (10.85x)
put_luma_v_8_64x64_c: 217.5 ( 1.00x)
put_luma_v_8_64x64_neon: 18.8 (11.60x)
put_luma_v_8_128x128_c: 886.2 ( 1.00x)
put_luma_v_8_128x128_neon: 74.0 (11.98x)
2024-09-14 16:36:34 +08:00
9f6c8eb412
aarch64/vvc: Add put_qpel_hx i8mm
...
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)
2024-09-14 16:36:34 +08:00
25448d1716
aarch64/vvc: Add put_pel/put_pel_uni/put_pel_uni_w
...
put_luma_pixels_8_4x4_c: 0.2 ( 1.00x)
put_luma_pixels_8_4x4_neon: 0.2 ( 1.00x)
put_luma_pixels_8_8x8_c: 0.7 ( 1.00x)
put_luma_pixels_8_8x8_neon: 0.2 ( 3.22x)
put_luma_pixels_8_16x16_c: 2.2 ( 1.00x)
put_luma_pixels_8_16x16_neon: 0.2 ( 9.89x)
put_luma_pixels_8_32x32_c: 8.2 ( 1.00x)
put_luma_pixels_8_32x32_neon: 1.2 ( 6.71x)
put_luma_pixels_8_64x64_c: 33.7 ( 1.00x)
put_luma_pixels_8_64x64_neon: 2.5 (13.63x)
put_luma_pixels_8_128x128_c: 145.5 ( 1.00x)
put_luma_pixels_8_128x128_neon: 10.2 (14.23x)
put_uni_pixels_luma_8_4x4_c: 0.5 ( 1.00x)
put_uni_pixels_luma_8_4x4_neon: 0.0 ( 0.00x)
put_uni_pixels_luma_8_8x8_c: 0.5 ( 1.00x)
put_uni_pixels_luma_8_8x8_neon: 0.2 ( 2.11x)
put_uni_pixels_luma_8_16x16_c: 1.2 ( 1.00x)
put_uni_pixels_luma_8_16x16_neon: 0.2 ( 5.44x)
put_uni_pixels_luma_8_32x32_c: 3.0 ( 1.00x)
put_uni_pixels_luma_8_32x32_neon: 0.5 ( 6.26x)
put_uni_pixels_luma_8_64x64_c: 3.0 ( 1.00x)
put_uni_pixels_luma_8_64x64_neon: 1.7 ( 1.72x)
put_uni_pixels_luma_8_128x128_c: 6.5 ( 1.00x)
put_uni_pixels_luma_8_128x128_neon: 6.5 ( 1.00x)
2024-09-14 16:36:34 +08:00
20f2bf5530
aarch64/vvc: Add put_qpel_h_* and put_qpel_uni_h_*
...
Just share hevc implementation.
checkasm --test=vvc_mc --benchmark:
put_luma_h_8_4x4_c: 0.2 ( 1.00x)
put_luma_h_8_4x4_neon: 0.2 ( 1.00x)
put_luma_h_8_8x8_c: 1.0 ( 1.00x)
put_luma_h_8_8x8_neon: 0.2 ( 4.33x)
put_luma_h_8_16x16_c: 3.2 ( 1.00x)
put_luma_h_8_16x16_neon: 1.2 ( 2.63x)
put_luma_h_8_32x32_c: 13.7 ( 1.00x)
put_luma_h_8_32x32_neon: 4.0 ( 3.45x)
put_luma_h_8_64x64_c: 48.2 ( 1.00x)
put_luma_h_8_64x64_neon: 15.7 ( 3.07x)
put_luma_h_8_128x128_c: 203.5 ( 1.00x)
put_luma_h_8_128x128_neon: 62.0 ( 3.28x)
put_uni_h_luma_8_4x4_c: 0.2 ( 1.00x)
put_uni_h_luma_8_4x4_neon: 0.2 ( 1.00x)
put_uni_h_luma_8_8x8_c: 1.5 ( 1.00x)
put_uni_h_luma_8_8x8_neon: 0.2 ( 6.56x)
put_uni_h_luma_8_16x16_c: 5.7 ( 1.00x)
put_uni_h_luma_8_16x16_neon: 1.2 ( 4.67x)
put_uni_h_luma_8_32x32_c: 24.0 ( 1.00x)
put_uni_h_luma_8_32x32_neon: 4.7 ( 5.07x)
put_uni_h_luma_8_64x64_c: 90.0 ( 1.00x)
put_uni_h_luma_8_64x64_neon: 17.0 ( 5.30x)
put_uni_h_luma_8_128x128_c: 357.7 ( 1.00x)
put_uni_h_luma_8_128x128_neon: 67.5 ( 5.30x)
2024-09-14 16:36:34 +08:00
4c0372281b
aarch64/vvc: Bind h26x/sao filter implementation to vvc
...
Reviewed-by: Martin Storsjö <martin@martin.st>
2024-08-31 16:07:50 +08:00
4acb9b7d10
aarch64: vvc: Fix unnecessary extra spaces
...
Signed-off-by: Martin Storsjö <martin@martin.st>
2024-07-23 16:04:28 +03:00
99598629e8
aarch64: vvc: Consistently use # for immediate constants
...
Signed-off-by: Martin Storsjö <martin@martin.st>
2024-07-23 15:24:37 +03:00
400843151d
aarch64: vvc: Fix compilation of alf.S with MSVC 2022 17.7 and older
...
Use the "ldur" instruction explicitly, instead of having the
assembler implicitly convert "ldr" instructions to "ldur".
This fixes build errors like these:
libavcodec\aarch64\vvc\alf.o.asm(1023) : error A2518: operand 2: Memory offset must be aligned
ldr q22, [x3, #24 ]
libavcodec\aarch64\vvc\alf.o.asm(1024) : error A2518: operand 2: Memory offset must be aligned
ldr q24, [x2, #24 ]
libavcodec\aarch64\vvc\alf.o.asm(1393) : error A2518: operand 2: Memory offset must be aligned
ldr q22, [x3, #24 ]
libavcodec\aarch64\vvc\alf.o.asm(1394) : error A2518: operand 2: Memory offset must be aligned
ldr q24, [x2, #24 ]
Signed-off-by: Martin Storsjö <martin@martin.st>
2024-07-23 15:24:33 +03:00
2d4ef304c9
avcodec/vvc: Add aarch64 neon optimization for ALF
...
vvc_alf_filter_chroma_4x4_8_c: 3.0
vvc_alf_filter_chroma_4x4_8_neon: 1.0
vvc_alf_filter_chroma_4x4_10_c: 2.7
vvc_alf_filter_chroma_4x4_10_neon: 1.0
vvc_alf_filter_chroma_4x4_12_c: 2.7
vvc_alf_filter_chroma_4x4_12_neon: 1.0
vvc_alf_filter_chroma_8x8_8_c: 10.2
vvc_alf_filter_chroma_8x8_8_neon: 3.0
vvc_alf_filter_chroma_8x8_10_c: 10.0
vvc_alf_filter_chroma_8x8_10_neon: 2.5
vvc_alf_filter_chroma_8x8_12_c: 10.0
vvc_alf_filter_chroma_8x8_12_neon: 2.5
vvc_alf_filter_chroma_16x16_8_c: 41.7
vvc_alf_filter_chroma_16x16_8_neon: 11.2
vvc_alf_filter_chroma_16x16_10_c: 39.0
vvc_alf_filter_chroma_16x16_10_neon: 10.0
vvc_alf_filter_chroma_16x16_12_c: 40.2
vvc_alf_filter_chroma_16x16_12_neon: 10.2
vvc_alf_filter_chroma_32x32_8_c: 162.0
vvc_alf_filter_chroma_32x32_8_neon: 45.0
vvc_alf_filter_chroma_32x32_10_c: 155.5
vvc_alf_filter_chroma_32x32_10_neon: 39.5
vvc_alf_filter_chroma_32x32_12_c: 155.5
vvc_alf_filter_chroma_32x32_12_neon: 40.0
vvc_alf_filter_chroma_64x64_8_c: 646.0
vvc_alf_filter_chroma_64x64_8_neon: 175.5
vvc_alf_filter_chroma_64x64_10_c: 708.2
vvc_alf_filter_chroma_64x64_10_neon: 166.7
vvc_alf_filter_chroma_64x64_12_c: 619.2
vvc_alf_filter_chroma_64x64_12_neon: 157.2
vvc_alf_filter_chroma_128x128_8_c: 2611.5
vvc_alf_filter_chroma_128x128_8_neon: 698.2
vvc_alf_filter_chroma_128x128_10_c: 2470.0
vvc_alf_filter_chroma_128x128_10_neon: 616.0
vvc_alf_filter_chroma_128x128_12_c: 2531.5
vvc_alf_filter_chroma_128x128_12_neon: 620.2
vvc_alf_filter_luma_8x8_8_c: 25.2
vvc_alf_filter_luma_8x8_8_neon: 4.2
vvc_alf_filter_luma_8x8_10_c: 18.5
vvc_alf_filter_luma_8x8_10_neon: 4.0
vvc_alf_filter_luma_8x8_12_c: 19.0
vvc_alf_filter_luma_8x8_12_neon: 4.0
vvc_alf_filter_luma_16x16_8_c: 106.5
vvc_alf_filter_luma_16x16_8_neon: 16.2
vvc_alf_filter_luma_16x16_10_c: 75.2
vvc_alf_filter_luma_16x16_10_neon: 14.7
vvc_alf_filter_luma_16x16_12_c: 79.7
vvc_alf_filter_luma_16x16_12_neon: 14.7
vvc_alf_filter_luma_32x32_8_c: 400.5
vvc_alf_filter_luma_32x32_8_neon: 63.2
vvc_alf_filter_luma_32x32_10_c: 299.2
vvc_alf_filter_luma_32x32_10_neon: 57.7
vvc_alf_filter_luma_32x32_12_c: 299.2
vvc_alf_filter_luma_32x32_12_neon: 57.7
vvc_alf_filter_luma_64x64_8_c: 1602.5
vvc_alf_filter_luma_64x64_8_neon: 251.7
vvc_alf_filter_luma_64x64_10_c: 1197.0
vvc_alf_filter_luma_64x64_10_neon: 235.5
vvc_alf_filter_luma_64x64_12_c: 1220.2
vvc_alf_filter_luma_64x64_12_neon: 235.7
vvc_alf_filter_luma_128x128_8_c: 6570.2
vvc_alf_filter_luma_128x128_8_neon: 1007.7
vvc_alf_filter_luma_128x128_10_c: 4822.7
vvc_alf_filter_luma_128x128_10_neon: 936.2
vvc_alf_filter_luma_128x128_12_c: 4791.2
vvc_alf_filter_luma_128x128_12_neon: 938.5
Signed-off-by: Zhao Zhili <zhilizhao@tencent.com>
2024-07-22 21:09:56 +08:00
Zhao Zhili
Krzysztof Pyrkosz
Martin Storsjö