Shaun Loo 45bea45c7b checkasm: add vvc_sao ...

This is a part of Google Summer of Code 2023

AVX2:
 - vvc_sao.sao_band [OK]
 - vvc_sao.sao_edge [OK]
checkasm: all 54 tests passed
vvc_sao_band_8_8_c:                                    157.4 ( 1.00x)
vvc_sao_band_8_8_avx2:                                  30.7 ( 5.12x)
vvc_sao_band_8_10_c:                                   119.4 ( 1.00x)
vvc_sao_band_8_10_avx2:                                 29.2 ( 4.09x)
vvc_sao_band_8_12_c:                                   144.6 ( 1.00x)
vvc_sao_band_8_12_avx2:                                 30.0 ( 4.82x)
vvc_sao_band_16_8_c:                                   446.5 ( 1.00x)
vvc_sao_band_16_8_avx2:                                103.3 ( 4.32x)
vvc_sao_band_16_10_c:                                  399.2 ( 1.00x)
vvc_sao_band_16_10_avx2:                                64.3 ( 6.21x)
vvc_sao_band_16_12_c:                                  472.9 ( 1.00x)
vvc_sao_band_16_12_avx2:                                56.5 ( 8.37x)
vvc_sao_band_32_8_c:                                  2430.9 ( 1.00x)
vvc_sao_band_32_8_avx2:                                203.3 (11.96x)
vvc_sao_band_32_10_c:                                 1405.7 ( 1.00x)
vvc_sao_band_32_10_avx2:                               208.5 ( 6.74x)
vvc_sao_band_32_12_c:                                 2054.3 ( 1.00x)
vvc_sao_band_32_12_avx2:                               213.0 ( 9.64x)
vvc_sao_band_48_8_c:                                  3835.4 ( 1.00x)
vvc_sao_band_48_8_avx2:                                604.2 ( 6.35x)
vvc_sao_band_48_10_c:                                 3624.6 ( 1.00x)
vvc_sao_band_48_10_avx2:                               468.8 ( 7.73x)
vvc_sao_band_48_12_c:                                 3752.4 ( 1.00x)
vvc_sao_band_48_12_avx2:                               477.5 ( 7.86x)
vvc_sao_band_64_8_c:                                  6061.1 ( 1.00x)
vvc_sao_band_64_8_avx2:                                803.9 ( 7.54x)
vvc_sao_band_64_10_c:                                 6142.5 ( 1.00x)
vvc_sao_band_64_10_avx2:                               827.3 ( 7.43x)
vvc_sao_band_64_12_c:                                 6106.6 ( 1.00x)
vvc_sao_band_64_12_avx2:                               839.9 ( 7.27x)
vvc_sao_band_80_8_c:                                  9478.0 ( 1.00x)
vvc_sao_band_80_8_avx2:                               1516.7 ( 6.25x)
vvc_sao_band_80_10_c:                                10300.5 ( 1.00x)
vvc_sao_band_80_10_avx2:                              1298.7 ( 7.93x)
vvc_sao_band_80_12_c:                                 8941.1 ( 1.00x)
vvc_sao_band_80_12_avx2:                              1315.3 ( 6.80x)
vvc_sao_band_96_8_c:                                 13351.5 ( 1.00x)
vvc_sao_band_96_8_avx2:                               1815.4 ( 7.35x)
vvc_sao_band_96_10_c:                                13197.5 ( 1.00x)
vvc_sao_band_96_10_avx2:                              1872.4 ( 7.05x)
vvc_sao_band_96_12_c:                                11969.0 ( 1.00x)
vvc_sao_band_96_12_avx2:                              1895.8 ( 6.31x)
vvc_sao_band_112_8_c:                                19936.9 ( 1.00x)
vvc_sao_band_112_8_avx2:                              2802.3 ( 7.11x)
vvc_sao_band_112_10_c:                               19534.9 ( 1.00x)
vvc_sao_band_112_10_avx2:                             2635.0 ( 7.41x)
vvc_sao_band_112_12_c:                               16520.6 ( 1.00x)
vvc_sao_band_112_12_avx2:                             2591.8 ( 6.37x)
vvc_sao_band_128_8_c:                                25967.5 ( 1.00x)
vvc_sao_band_128_8_avx2:                              3155.3 ( 8.23x)
vvc_sao_band_128_10_c:                               24002.6 ( 1.00x)
vvc_sao_band_128_10_avx2:                             3374.6 ( 7.11x)
vvc_sao_band_128_12_c:                               20829.4 ( 1.00x)
vvc_sao_band_128_12_avx2:                             3377.0 ( 6.17x)
vvc_sao_edge_8_8_c:                                    174.6 ( 1.00x)
vvc_sao_edge_8_8_avx2:                                  37.0 ( 4.72x)
vvc_sao_edge_8_10_c:                                   174.4 ( 1.00x)
vvc_sao_edge_8_10_avx2:                                 58.5 ( 2.98x)
vvc_sao_edge_8_12_c:                                   171.1 ( 1.00x)
vvc_sao_edge_8_12_avx2:                                 58.5 ( 2.93x)
vvc_sao_edge_16_8_c:                                   677.7 ( 1.00x)
vvc_sao_edge_16_8_avx2:                                 72.2 ( 9.39x)
vvc_sao_edge_16_10_c:                                  724.8 ( 1.00x)
vvc_sao_edge_16_10_avx2:                               106.4 ( 6.81x)
vvc_sao_edge_16_12_c:                                  647.0 ( 1.00x)
vvc_sao_edge_16_12_avx2:                               106.6 ( 6.07x)
vvc_sao_edge_32_8_c:                                  3001.8 ( 1.00x)
vvc_sao_edge_32_8_avx2:                                157.6 (19.04x)
vvc_sao_edge_32_10_c:                                 3071.1 ( 1.00x)
vvc_sao_edge_32_10_avx2:                               404.2 ( 7.60x)
vvc_sao_edge_32_12_c:                                 2698.6 ( 1.00x)
vvc_sao_edge_32_12_avx2:                               398.8 ( 6.77x)
vvc_sao_edge_48_8_c:                                  6557.7 ( 1.00x)
vvc_sao_edge_48_8_avx2:                                380.1 (17.25x)
vvc_sao_edge_48_10_c:                                 6319.9 ( 1.00x)
vvc_sao_edge_48_10_avx2:                               896.3 ( 7.05x)
vvc_sao_edge_48_12_c:                                 6306.4 ( 1.00x)
vvc_sao_edge_48_12_avx2:                               885.5 ( 7.12x)
vvc_sao_edge_64_8_c:                                 11510.7 ( 1.00x)
vvc_sao_edge_64_8_avx2:                                504.1 (22.84x)
vvc_sao_edge_64_10_c:                                10917.4 ( 1.00x)
vvc_sao_edge_64_10_avx2:                              1608.3 ( 6.79x)
vvc_sao_edge_64_12_c:                                11499.8 ( 1.00x)
vvc_sao_edge_64_12_avx2:                              1586.4 ( 7.25x)
vvc_sao_edge_80_8_c:                                 18193.2 ( 1.00x)
vvc_sao_edge_80_8_avx2:                                930.2 (19.56x)
vvc_sao_edge_80_10_c:                                17984.3 ( 1.00x)
vvc_sao_edge_80_10_avx2:                              2420.9 ( 7.43x)
vvc_sao_edge_80_12_c:                                18289.4 ( 1.00x)
vvc_sao_edge_80_12_avx2:                              2412.1 ( 7.58x)
vvc_sao_edge_96_8_c:                                 26361.8 ( 1.00x)
vvc_sao_edge_96_8_avx2:                               1118.4 (23.57x)
vvc_sao_edge_96_10_c:                                26162.2 ( 1.00x)
vvc_sao_edge_96_10_avx2:                              3666.9 ( 7.13x)
vvc_sao_edge_96_12_c:                                25926.6 ( 1.00x)
vvc_sao_edge_96_12_avx2:                              3433.9 ( 7.55x)
vvc_sao_edge_112_8_c:                                36562.9 ( 1.00x)
vvc_sao_edge_112_8_avx2:                              1741.0 (21.00x)
vvc_sao_edge_112_10_c:                               38126.4 ( 1.00x)
vvc_sao_edge_112_10_avx2:                             5153.3 ( 7.40x)
vvc_sao_edge_112_12_c:                               36345.7 ( 1.00x)
vvc_sao_edge_112_12_avx2:                             4684.9 ( 7.76x)
vvc_sao_edge_128_8_c:                                46379.8 ( 1.00x)
vvc_sao_edge_128_8_avx2:                              2012.4 (23.05x)
vvc_sao_edge_128_10_c:                               47029.5 ( 1.00x)
vvc_sao_edge_128_10_avx2:                             6162.2 ( 7.63x)
vvc_sao_edge_128_12_c:                               49647.3 ( 1.00x)
vvc_sao_edge_128_12_avx2:                             6127.1 ( 8.10x)

Co-authored-by: Nuo Mi <nuomi2021@gmail.com>

2025-05-14 20:55:39 +08:00

37 KiB

Raw Blame History

View Raw