[FFmpeg-devel] [PATCH v3 7/8] avcodec/x86/vvc: add avg and avg_w AVX2 optimizations

Tue Jan 23 00:46:39 EET 2024

On Tue, Jan 23, 2024 at 01:46:27AM +0800, toqsxw at outlook.com wrote:
> From: Wu Jianhua <toqsxw at outlook.com>
> 
> The avg/avg_w is based on dav1d.
> See https://code.videolan.org/videolan/dav1d/-/blob/master/src/x86/mc_avx2.asm
> 
> vvc_avg_8_2x2_c: 71.6
> vvc_avg_8_2x2_avx2: 26.8
> vvc_avg_8_2x4_c: 140.8
> vvc_avg_8_2x4_avx2: 34.6
> vvc_avg_8_2x8_c: 410.3
> vvc_avg_8_2x8_avx2: 41.3
> vvc_avg_8_2x16_c: 769.3
> vvc_avg_8_2x16_avx2: 60.3
> vvc_avg_8_2x32_c: 1669.6
> vvc_avg_8_2x32_avx2: 105.1
> vvc_avg_8_2x64_c: 1978.3
> vvc_avg_8_2x64_avx2: 425.8
> vvc_avg_8_2x128_c: 6536.8
> vvc_avg_8_2x128_avx2: 1315.1
> vvc_avg_8_4x2_c: 155.6
> vvc_avg_8_4x2_avx2: 26.1
> vvc_avg_8_4x4_c: 250.3
> vvc_avg_8_4x4_avx2: 31.3
> vvc_avg_8_4x8_c: 831.8
> vvc_avg_8_4x8_avx2: 41.3
> vvc_avg_8_4x16_c: 1461.1
> vvc_avg_8_4x16_avx2: 57.1
> vvc_avg_8_4x32_c: 2821.6
> vvc_avg_8_4x32_avx2: 105.1
> vvc_avg_8_4x64_c: 3615.8
> vvc_avg_8_4x64_avx2: 412.6
> vvc_avg_8_4x128_c: 11962.6
> vvc_avg_8_4x128_avx2: 1274.3
> vvc_avg_8_8x2_c: 215.8
> vvc_avg_8_8x2_avx2: 29.1
> vvc_avg_8_8x4_c: 430.6
> vvc_avg_8_8x4_avx2: 37.6
> vvc_avg_8_8x8_c: 1463.3
> vvc_avg_8_8x8_avx2: 51.8
> vvc_avg_8_8x16_c: 2630.1
> vvc_avg_8_8x16_avx2: 97.6
> vvc_avg_8_8x32_c: 5813.8
> vvc_avg_8_8x32_avx2: 196.6
> vvc_avg_8_8x64_c: 6687.3
> vvc_avg_8_8x64_avx2: 487.8
> vvc_avg_8_8x128_c: 13178.6
> vvc_avg_8_8x128_avx2: 1290.6
> vvc_avg_8_16x2_c: 443.8
> vvc_avg_8_16x2_avx2: 28.3
> vvc_avg_8_16x4_c: 1253.3
> vvc_avg_8_16x4_avx2: 32.1
> vvc_avg_8_16x8_c: 2236.3
> vvc_avg_8_16x8_avx2: 44.3
> vvc_avg_8_16x16_c: 5127.8
> vvc_avg_8_16x16_avx2: 63.3
> vvc_avg_8_16x32_c: 6573.3
> vvc_avg_8_16x32_avx2: 223.6
> vvc_avg_8_16x64_c: 30311.8
> vvc_avg_8_16x64_avx2: 437.8
> vvc_avg_8_16x128_c: 25693.3
> vvc_avg_8_16x128_avx2: 1266.8
> vvc_avg_8_32x2_c: 954.6
> vvc_avg_8_32x2_avx2: 32.1
> vvc_avg_8_32x4_c: 2359.6
> vvc_avg_8_32x4_avx2: 39.6
> vvc_avg_8_32x8_c: 5703.6
> vvc_avg_8_32x8_avx2: 57.1
> vvc_avg_8_32x16_c: 9967.6
> vvc_avg_8_32x16_avx2: 107.1
> vvc_avg_8_32x32_c: 21327.6
> vvc_avg_8_32x32_avx2: 272.6
> vvc_avg_8_32x64_c: 39240.8
> vvc_avg_8_32x64_avx2: 529.6
> vvc_avg_8_32x128_c: 52580.8
> vvc_avg_8_32x128_avx2: 1338.8
> vvc_avg_8_64x2_c: 1647.3
> vvc_avg_8_64x2_avx2: 38.8
> vvc_avg_8_64x4_c: 5130.1
> vvc_avg_8_64x4_avx2: 58.8
> vvc_avg_8_64x8_c: 6529.3
> vvc_avg_8_64x8_avx2: 88.3
> vvc_avg_8_64x16_c: 19913.6
> vvc_avg_8_64x16_avx2: 162.3
> vvc_avg_8_64x32_c: 39360.8
> vvc_avg_8_64x32_avx2: 295.8
> vvc_avg_8_64x64_c: 49658.3
> vvc_avg_8_64x64_avx2: 784.1
> vvc_avg_8_64x128_c: 108513.1
> vvc_avg_8_64x128_avx2: 1977.1
> vvc_avg_8_128x2_c: 3226.1
> vvc_avg_8_128x2_avx2: 61.1
> vvc_avg_8_128x4_c: 10280.3
> vvc_avg_8_128x4_avx2: 94.6
> vvc_avg_8_128x8_c: 18079.3
> vvc_avg_8_128x8_avx2: 155.3
> vvc_avg_8_128x16_c: 45121.8
> vvc_avg_8_128x16_avx2: 285.3
> vvc_avg_8_128x32_c: 48651.8
> vvc_avg_8_128x32_avx2: 581.6
> vvc_avg_8_128x64_c: 165078.6
> vvc_avg_8_128x64_avx2: 1942.8
> vvc_avg_8_128x128_c: 339103.1
> vvc_avg_8_128x128_avx2: 4332.6
> vvc_avg_10_2x2_c: 144.3
> vvc_avg_10_2x2_avx2: 26.8
> vvc_avg_10_2x4_c: 142.6
> vvc_avg_10_2x4_avx2: 45.3
> vvc_avg_10_2x8_c: 478.1
> vvc_avg_10_2x8_avx2: 38.1
> vvc_avg_10_2x16_c: 518.3
> vvc_avg_10_2x16_avx2: 58.1
> vvc_avg_10_2x32_c: 2059.8
> vvc_avg_10_2x32_avx2: 93.1
> vvc_avg_10_2x64_c: 2383.8
> vvc_avg_10_2x64_avx2: 714.8
> vvc_avg_10_2x128_c: 4498.3
> vvc_avg_10_2x128_avx2: 1466.3
> vvc_avg_10_4x2_c: 228.6
> vvc_avg_10_4x2_avx2: 26.8
> vvc_avg_10_4x4_c: 378.3
> vvc_avg_10_4x4_avx2: 30.6
> vvc_avg_10_4x8_c: 866.8
> vvc_avg_10_4x8_avx2: 44.6
> vvc_avg_10_4x16_c: 1018.1
> vvc_avg_10_4x16_avx2: 58.1
> vvc_avg_10_4x32_c: 3590.8
> vvc_avg_10_4x32_avx2: 128.8
> vvc_avg_10_4x64_c: 4200.8
> vvc_avg_10_4x64_avx2: 663.6
> vvc_avg_10_4x128_c: 8450.8
> vvc_avg_10_4x128_avx2: 1531.8
> vvc_avg_10_8x2_c: 369.3
> vvc_avg_10_8x2_avx2: 28.3
> vvc_avg_10_8x4_c: 513.8
> vvc_avg_10_8x4_avx2: 32.1
> vvc_avg_10_8x8_c: 1720.3
> vvc_avg_10_8x8_avx2: 49.1
> vvc_avg_10_8x16_c: 1894.8
> vvc_avg_10_8x16_avx2: 71.6
> vvc_avg_10_8x32_c: 3931.3
> vvc_avg_10_8x32_avx2: 148.1
> vvc_avg_10_8x64_c: 7964.3
> vvc_avg_10_8x64_avx2: 613.1
> vvc_avg_10_8x128_c: 15540.1
> vvc_avg_10_8x128_avx2: 1585.1
> vvc_avg_10_16x2_c: 877.3
> vvc_avg_10_16x2_avx2: 27.6
> vvc_avg_10_16x4_c: 955.8
> vvc_avg_10_16x4_avx2: 29.8
> vvc_avg_10_16x8_c: 3419.6
> vvc_avg_10_16x8_avx2: 62.6
> vvc_avg_10_16x16_c: 3826.8
> vvc_avg_10_16x16_avx2: 54.3
> vvc_avg_10_16x32_c: 7655.3
> vvc_avg_10_16x32_avx2: 86.3
> vvc_avg_10_16x64_c: 30011.1
> vvc_avg_10_16x64_avx2: 692.6
> vvc_avg_10_16x128_c: 47894.8
> vvc_avg_10_16x128_avx2: 1580.3
> vvc_avg_10_32x2_c: 944.3
> vvc_avg_10_32x2_avx2: 29.8
> vvc_avg_10_32x4_c: 2022.6
> vvc_avg_10_32x4_avx2: 35.1
> vvc_avg_10_32x8_c: 6148.8
> vvc_avg_10_32x8_avx2: 51.3
> vvc_avg_10_32x16_c: 12601.6
> vvc_avg_10_32x16_avx2: 70.8
> vvc_avg_10_32x32_c: 15958.6
> vvc_avg_10_32x32_avx2: 124.3
> vvc_avg_10_32x64_c: 31784.6
> vvc_avg_10_32x64_avx2: 757.3
> vvc_avg_10_32x128_c: 63892.8
> vvc_avg_10_32x128_avx2: 1711.3
> vvc_avg_10_64x2_c: 1890.8
> vvc_avg_10_64x2_avx2: 34.3
> vvc_avg_10_64x4_c: 6267.3
> vvc_avg_10_64x4_avx2: 42.6
> vvc_avg_10_64x8_c: 12778.1
> vvc_avg_10_64x8_avx2: 67.8
> vvc_avg_10_64x16_c: 22304.3
> vvc_avg_10_64x16_avx2: 116.8
> vvc_avg_10_64x32_c: 30777.1
> vvc_avg_10_64x32_avx2: 201.1
> vvc_avg_10_64x64_c: 60169.1
> vvc_avg_10_64x64_avx2: 1454.3
> vvc_avg_10_64x128_c: 124392.8
> vvc_avg_10_64x128_avx2: 3648.6
> vvc_avg_10_128x2_c: 3650.1
> vvc_avg_10_128x2_avx2: 41.1
> vvc_avg_10_128x4_c: 22887.8
> vvc_avg_10_128x4_avx2: 64.1
> vvc_avg_10_128x8_c: 14622.6
> vvc_avg_10_128x8_avx2: 111.6
> vvc_avg_10_128x16_c: 62207.6
> vvc_avg_10_128x16_avx2: 186.3
> vvc_avg_10_128x32_c: 59761.3
> vvc_avg_10_128x32_avx2: 374.6
> vvc_avg_10_128x64_c: 117504.3
> vvc_avg_10_128x64_avx2: 2684.6
> vvc_avg_10_128x128_c: 236767.6
> vvc_avg_10_128x128_avx2: 15278.1
> vvc_avg_12_2x2_c: 78.6
> vvc_avg_12_2x2_avx2: 26.1
> vvc_avg_12_2x4_c: 254.1
> vvc_avg_12_2x4_avx2: 30.6
> vvc_avg_12_2x8_c: 261.8
> vvc_avg_12_2x8_avx2: 39.1
> vvc_avg_12_2x16_c: 527.6
> vvc_avg_12_2x16_avx2: 57.3
> vvc_avg_12_2x32_c: 1089.1
> vvc_avg_12_2x32_avx2: 93.8
> vvc_avg_12_2x64_c: 2337.6
> vvc_avg_12_2x64_avx2: 707.1
> vvc_avg_12_2x128_c: 4582.1
> vvc_avg_12_2x128_avx2: 1414.6
> vvc_avg_12_4x2_c: 129.6
> vvc_avg_12_4x2_avx2: 26.8
> vvc_avg_12_4x4_c: 427.3
> vvc_avg_12_4x4_avx2: 30.6
> vvc_avg_12_4x8_c: 529.6
> vvc_avg_12_4x8_avx2: 36.6
> vvc_avg_12_4x16_c: 1022.1
> vvc_avg_12_4x16_avx2: 57.3
> vvc_avg_12_4x32_c: 1987.6
> vvc_avg_12_4x32_avx2: 84.3
> vvc_avg_12_4x64_c: 4147.6
> vvc_avg_12_4x64_avx2: 706.3
> vvc_avg_12_4x128_c: 8469.3
> vvc_avg_12_4x128_avx2: 1448.3
> vvc_avg_12_8x2_c: 253.6
> vvc_avg_12_8x2_avx2: 27.6
> vvc_avg_12_8x4_c: 836.3
> vvc_avg_12_8x4_avx2: 32.1
> vvc_avg_12_8x8_c: 1074.6
> vvc_avg_12_8x8_avx2: 45.1
> vvc_avg_12_8x16_c: 3616.8
> vvc_avg_12_8x16_avx2: 71.6
> vvc_avg_12_8x32_c: 3823.6
> vvc_avg_12_8x32_avx2: 140.1
> vvc_avg_12_8x64_c: 7764.8
> vvc_avg_12_8x64_avx2: 656.1
> vvc_avg_12_8x128_c: 15896.1
> vvc_avg_12_8x128_avx2: 1232.8
> vvc_avg_12_16x2_c: 462.1
> vvc_avg_12_16x2_avx2: 26.8
> vvc_avg_12_16x4_c: 1732.1
> vvc_avg_12_16x4_avx2: 29.1
> vvc_avg_12_16x8_c: 2097.6
> vvc_avg_12_16x8_avx2: 62.6
> vvc_avg_12_16x16_c: 6753.1
> vvc_avg_12_16x16_avx2: 47.8
> vvc_avg_12_16x32_c: 7373.1
> vvc_avg_12_16x32_avx2: 80.8
> vvc_avg_12_16x64_c: 15046.3
> vvc_avg_12_16x64_avx2: 621.1
> vvc_avg_12_16x128_c: 52574.6
> vvc_avg_12_16x128_avx2: 1417.1
> vvc_avg_12_32x2_c: 1712.1
> vvc_avg_12_32x2_avx2: 29.8
> vvc_avg_12_32x4_c: 2036.8
> vvc_avg_12_32x4_avx2: 37.6
> vvc_avg_12_32x8_c: 4017.6
> vvc_avg_12_32x8_avx2: 44.1
> vvc_avg_12_32x16_c: 8018.6
> vvc_avg_12_32x16_avx2: 70.8
> vvc_avg_12_32x32_c: 15637.6
> vvc_avg_12_32x32_avx2: 124.3
> vvc_avg_12_32x64_c: 31143.3
> vvc_avg_12_32x64_avx2: 830.3
> vvc_avg_12_32x128_c: 75706.8
> vvc_avg_12_32x128_avx2: 1604.8
> vvc_avg_12_64x2_c: 3230.3
> vvc_avg_12_64x2_avx2: 33.6
> vvc_avg_12_64x4_c: 4139.6
> vvc_avg_12_64x4_avx2: 45.1
> vvc_avg_12_64x8_c: 8201.6
> vvc_avg_12_64x8_avx2: 67.1
> vvc_avg_12_64x16_c: 25632.3
> vvc_avg_12_64x16_avx2: 110.3
> vvc_avg_12_64x32_c: 30744.3
> vvc_avg_12_64x32_avx2: 200.3
> vvc_avg_12_64x64_c: 105554.8
> vvc_avg_12_64x64_avx2: 1325.6
> vvc_avg_12_64x128_c: 235254.3
> vvc_avg_12_64x128_avx2: 3132.6
> vvc_avg_12_128x2_c: 6194.3
> vvc_avg_12_128x2_avx2: 55.1
> vvc_avg_12_128x4_c: 7583.8
> vvc_avg_12_128x4_avx2: 79.3
> vvc_avg_12_128x8_c: 14635.6
> vvc_avg_12_128x8_avx2: 104.3
> vvc_avg_12_128x16_c: 29270.8
> vvc_avg_12_128x16_avx2: 194.3
> vvc_avg_12_128x32_c: 60113.6
> vvc_avg_12_128x32_avx2: 346.3
> vvc_avg_12_128x64_c: 197030.3
> vvc_avg_12_128x64_avx2: 2779.6
> vvc_avg_12_128x128_c: 432809.6
> vvc_avg_12_128x128_avx2: 5513.3
> vvc_w_avg_8_2x2_c: 84.3
> vvc_w_avg_8_2x2_avx2: 42.6
> vvc_w_avg_8_2x4_c: 156.3
> vvc_w_avg_8_2x4_avx2: 58.8
> vvc_w_avg_8_2x8_c: 310.6
> vvc_w_avg_8_2x8_avx2: 73.1
> vvc_w_avg_8_2x16_c: 942.1
> vvc_w_avg_8_2x16_avx2: 113.3
> vvc_w_avg_8_2x32_c: 1098.8
> vvc_w_avg_8_2x32_avx2: 202.6
> vvc_w_avg_8_2x64_c: 2414.3
> vvc_w_avg_8_2x64_avx2: 467.6
> vvc_w_avg_8_2x128_c: 4763.8
> vvc_w_avg_8_2x128_avx2: 1333.1
> vvc_w_avg_8_4x2_c: 140.1
> vvc_w_avg_8_4x2_avx2: 49.8
> vvc_w_avg_8_4x4_c: 276.3
> vvc_w_avg_8_4x4_avx2: 58.1
> vvc_w_avg_8_4x8_c: 524.3
> vvc_w_avg_8_4x8_avx2: 72.3
> vvc_w_avg_8_4x16_c: 1108.1
> vvc_w_avg_8_4x16_avx2: 111.8
> vvc_w_avg_8_4x32_c: 2149.8
> vvc_w_avg_8_4x32_avx2: 199.6
> vvc_w_avg_8_4x64_c: 12288.1
> vvc_w_avg_8_4x64_avx2: 509.3
> vvc_w_avg_8_4x128_c: 8398.6
> vvc_w_avg_8_4x128_avx2: 1319.6
> vvc_w_avg_8_8x2_c: 271.1
> vvc_w_avg_8_8x2_avx2: 44.1
> vvc_w_avg_8_8x4_c: 503.3
> vvc_w_avg_8_8x4_avx2: 61.8
> vvc_w_avg_8_8x8_c: 1031.1
> vvc_w_avg_8_8x8_avx2: 93.8
> vvc_w_avg_8_8x16_c: 2009.8
> vvc_w_avg_8_8x16_avx2: 163.1
> vvc_w_avg_8_8x32_c: 4161.3
> vvc_w_avg_8_8x32_avx2: 292.1
> vvc_w_avg_8_8x64_c: 7940.6
> vvc_w_avg_8_8x64_avx2: 592.1
> vvc_w_avg_8_8x128_c: 16802.3
> vvc_w_avg_8_8x128_avx2: 1287.6
> vvc_w_avg_8_16x2_c: 762.6
> vvc_w_avg_8_16x2_avx2: 53.6
> vvc_w_avg_8_16x4_c: 1486.3
> vvc_w_avg_8_16x4_avx2: 67.1
> vvc_w_avg_8_16x8_c: 1907.8
> vvc_w_avg_8_16x8_avx2: 96.8
> vvc_w_avg_8_16x16_c: 3883.6
> vvc_w_avg_8_16x16_avx2: 151.3
> vvc_w_avg_8_16x32_c: 7974.8
> vvc_w_avg_8_16x32_avx2: 285.8
> vvc_w_avg_8_16x64_c: 25160.6
> vvc_w_avg_8_16x64_avx2: 589.8
> vvc_w_avg_8_16x128_c: 58328.1
> vvc_w_avg_8_16x128_avx2: 1169.8
> vvc_w_avg_8_32x2_c: 1009.1
> vvc_w_avg_8_32x2_avx2: 65.6
> vvc_w_avg_8_32x4_c: 2091.1
> vvc_w_avg_8_32x4_avx2: 96.8
> vvc_w_avg_8_32x8_c: 3997.8
> vvc_w_avg_8_32x8_avx2: 156.3
> vvc_w_avg_8_32x16_c: 8216.8
> vvc_w_avg_8_32x16_avx2: 269.6
> vvc_w_avg_8_32x32_c: 21746.1
> vvc_w_avg_8_32x32_avx2: 635.3
> vvc_w_avg_8_32x64_c: 31564.8
> vvc_w_avg_8_32x64_avx2: 1010.6
> vvc_w_avg_8_32x128_c: 114373.3
> vvc_w_avg_8_32x128_avx2: 2013.6
> vvc_w_avg_8_64x2_c: 2067.3
> vvc_w_avg_8_64x2_avx2: 97.6
> vvc_w_avg_8_64x4_c: 3901.1
> vvc_w_avg_8_64x4_avx2: 154.8
> vvc_w_avg_8_64x8_c: 7911.6
> vvc_w_avg_8_64x8_avx2: 268.8
> vvc_w_avg_8_64x16_c: 16508.8
> vvc_w_avg_8_64x16_avx2: 501.8
> vvc_w_avg_8_64x32_c: 38770.3
> vvc_w_avg_8_64x32_avx2: 1287.6
> vvc_w_avg_8_64x64_c: 110350.6
> vvc_w_avg_8_64x64_avx2: 1890.8
> vvc_w_avg_8_64x128_c: 141354.6
> vvc_w_avg_8_64x128_avx2: 3839.6
> vvc_w_avg_8_128x2_c: 7012.1
> vvc_w_avg_8_128x2_avx2: 159.3
> vvc_w_avg_8_128x4_c: 8146.8
> vvc_w_avg_8_128x4_avx2: 272.6
> vvc_w_avg_8_128x8_c: 24596.8
> vvc_w_avg_8_128x8_avx2: 501.1
> vvc_w_avg_8_128x16_c: 35918.1
> vvc_w_avg_8_128x16_avx2: 948.8
> vvc_w_avg_8_128x32_c: 68799.6
> vvc_w_avg_8_128x32_avx2: 1963.1
> vvc_w_avg_8_128x64_c: 133862.1
> vvc_w_avg_8_128x64_avx2: 3833.6
> vvc_w_avg_8_128x128_c: 348427.8
> vvc_w_avg_8_128x128_avx2: 7682.8
> vvc_w_avg_10_2x2_c: 118.6
> vvc_w_avg_10_2x2_avx2: 73.1
> vvc_w_avg_10_2x4_c: 189.1
> vvc_w_avg_10_2x4_avx2: 89.3
> vvc_w_avg_10_2x8_c: 382.8
> vvc_w_avg_10_2x8_avx2: 179.8
> vvc_w_avg_10_2x16_c: 658.3
> vvc_w_avg_10_2x16_avx2: 185.1
> vvc_w_avg_10_2x32_c: 1409.3
> vvc_w_avg_10_2x32_avx2: 290.8
> vvc_w_avg_10_2x64_c: 2906.8
> vvc_w_avg_10_2x64_avx2: 793.1
> vvc_w_avg_10_2x128_c: 6292.6
> vvc_w_avg_10_2x128_avx2: 1696.8
> vvc_w_avg_10_4x2_c: 178.8
> vvc_w_avg_10_4x2_avx2: 80.1
> vvc_w_avg_10_4x4_c: 581.6
> vvc_w_avg_10_4x4_avx2: 97.6
> vvc_w_avg_10_4x8_c: 693.3
> vvc_w_avg_10_4x8_avx2: 128.1
> vvc_w_avg_10_4x16_c: 1436.6
> vvc_w_avg_10_4x16_avx2: 179.8
> vvc_w_avg_10_4x32_c: 2409.1
> vvc_w_avg_10_4x32_avx2: 292.3
> vvc_w_avg_10_4x64_c: 4925.3
> vvc_w_avg_10_4x64_avx2: 746.1
> vvc_w_avg_10_4x128_c: 10664.6
> vvc_w_avg_10_4x128_avx2: 1647.6
> vvc_w_avg_10_8x2_c: 359.3
> vvc_w_avg_10_8x2_avx2: 80.1
> vvc_w_avg_10_8x4_c: 925.6
> vvc_w_avg_10_8x4_avx2: 97.6
> vvc_w_avg_10_8x8_c: 1360.6
> vvc_w_avg_10_8x8_avx2: 121.8
> vvc_w_avg_10_8x16_c: 3490.3
> vvc_w_avg_10_8x16_avx2: 203.3
> vvc_w_avg_10_8x32_c: 5266.1
> vvc_w_avg_10_8x32_avx2: 325.8
> vvc_w_avg_10_8x64_c: 11127.1
> vvc_w_avg_10_8x64_avx2: 747.8
> vvc_w_avg_10_8x128_c: 31058.3
> vvc_w_avg_10_8x128_avx2: 1424.6
> vvc_w_avg_10_16x2_c: 624.8
> vvc_w_avg_10_16x2_avx2: 84.6
> vvc_w_avg_10_16x4_c: 1389.6
> vvc_w_avg_10_16x4_avx2: 109.1
> vvc_w_avg_10_16x8_c: 2688.3
> vvc_w_avg_10_16x8_avx2: 137.1
> vvc_w_avg_10_16x16_c: 5387.1
> vvc_w_avg_10_16x16_avx2: 224.6
> vvc_w_avg_10_16x32_c: 10776.3
> vvc_w_avg_10_16x32_avx2: 312.1
> vvc_w_avg_10_16x64_c: 18069.1
> vvc_w_avg_10_16x64_avx2: 858.6
> vvc_w_avg_10_16x128_c: 43460.3
> vvc_w_avg_10_16x128_avx2: 1411.6
> vvc_w_avg_10_32x2_c: 1232.8
> vvc_w_avg_10_32x2_avx2: 99.1
> vvc_w_avg_10_32x4_c: 4017.6
> vvc_w_avg_10_32x4_avx2: 134.1
> vvc_w_avg_10_32x8_c: 9306.3
> vvc_w_avg_10_32x8_avx2: 208.1
> vvc_w_avg_10_32x16_c: 8424.6
> vvc_w_avg_10_32x16_avx2: 349.3
> vvc_w_avg_10_32x32_c: 20787.8
> vvc_w_avg_10_32x32_avx2: 655.3
> vvc_w_avg_10_32x64_c: 40972.1
> vvc_w_avg_10_32x64_avx2: 904.8
> vvc_w_avg_10_32x128_c: 85670.3
> vvc_w_avg_10_32x128_avx2: 1751.6
> vvc_w_avg_10_64x2_c: 2454.1
> vvc_w_avg_10_64x2_avx2: 132.6
> vvc_w_avg_10_64x4_c: 5012.6
> vvc_w_avg_10_64x4_avx2: 215.6
> vvc_w_avg_10_64x8_c: 10811.3
> vvc_w_avg_10_64x8_avx2: 361.1
> vvc_w_avg_10_64x16_c: 33349.1
> vvc_w_avg_10_64x16_avx2: 904.1
> vvc_w_avg_10_64x32_c: 41892.3
> vvc_w_avg_10_64x32_avx2: 1220.6
> vvc_w_avg_10_64x64_c: 66983.3
> vvc_w_avg_10_64x64_avx2: 2622.1
> vvc_w_avg_10_64x128_c: 246508.8
> vvc_w_avg_10_64x128_avx2: 3316.8
> vvc_w_avg_10_128x2_c: 7791.6
> vvc_w_avg_10_128x2_avx2: 198.8
> vvc_w_avg_10_128x4_c: 10534.3
> vvc_w_avg_10_128x4_avx2: 337.3
> vvc_w_avg_10_128x8_c: 21142.3
> vvc_w_avg_10_128x8_avx2: 614.8
> vvc_w_avg_10_128x16_c: 40968.6
> vvc_w_avg_10_128x16_avx2: 1160.6
> vvc_w_avg_10_128x32_c: 113043.3
> vvc_w_avg_10_128x32_avx2: 1644.6
> vvc_w_avg_10_128x64_c: 230658.3
> vvc_w_avg_10_128x64_avx2: 5065.3
> vvc_w_avg_10_128x128_c: 335236.3
> vvc_w_avg_10_128x128_avx2: 6450.3
> vvc_w_avg_12_2x2_c: 185.3
> vvc_w_avg_12_2x2_avx2: 43.6
> vvc_w_avg_12_2x4_c: 340.3
> vvc_w_avg_12_2x4_avx2: 55.8
> vvc_w_avg_12_2x8_c: 632.3
> vvc_w_avg_12_2x8_avx2: 70.1
> vvc_w_avg_12_2x16_c: 728.3
> vvc_w_avg_12_2x16_avx2: 108.1
> vvc_w_avg_12_2x32_c: 1392.6
> vvc_w_avg_12_2x32_avx2: 176.8
> vvc_w_avg_12_2x64_c: 2618.3
> vvc_w_avg_12_2x64_avx2: 757.3
> vvc_w_avg_12_2x128_c: 6408.8
> vvc_w_avg_12_2x128_avx2: 1435.1
> vvc_w_avg_12_4x2_c: 349.3
> vvc_w_avg_12_4x2_avx2: 44.3
> vvc_w_avg_12_4x4_c: 607.1
> vvc_w_avg_12_4x4_avx2: 52.6
> vvc_w_avg_12_4x8_c: 1134.8
> vvc_w_avg_12_4x8_avx2: 70.1
> vvc_w_avg_12_4x16_c: 1378.1
> vvc_w_avg_12_4x16_avx2: 115.3
> vvc_w_avg_12_4x32_c: 2599.3
> vvc_w_avg_12_4x32_avx2: 174.3
> vvc_w_avg_12_4x64_c: 4474.8
> vvc_w_avg_12_4x64_avx2: 656.1
> vvc_w_avg_12_4x128_c: 11319.6
> vvc_w_avg_12_4x128_avx2: 1373.1
> vvc_w_avg_12_8x2_c: 595.8
> vvc_w_avg_12_8x2_avx2: 44.3
> vvc_w_avg_12_8x4_c: 1164.3
> vvc_w_avg_12_8x4_avx2: 56.6
> vvc_w_avg_12_8x8_c: 2019.6
> vvc_w_avg_12_8x8_avx2: 80.1
> vvc_w_avg_12_8x16_c: 4071.6
> vvc_w_avg_12_8x16_avx2: 139.3
> vvc_w_avg_12_8x32_c: 4485.1
> vvc_w_avg_12_8x32_avx2: 250.6
> vvc_w_avg_12_8x64_c: 8404.8
> vvc_w_avg_12_8x64_avx2: 735.8
> vvc_w_avg_12_8x128_c: 35679.8
> vvc_w_avg_12_8x128_avx2: 1252.6
> vvc_w_avg_12_16x2_c: 1114.8
> vvc_w_avg_12_16x2_avx2: 46.6
> vvc_w_avg_12_16x4_c: 2240.1
> vvc_w_avg_12_16x4_avx2: 62.6
> vvc_w_avg_12_16x8_c: 13174.6
> vvc_w_avg_12_16x8_avx2: 88.6
> vvc_w_avg_12_16x16_c: 5334.6
> vvc_w_avg_12_16x16_avx2: 144.3
> vvc_w_avg_12_16x32_c: 8378.1
> vvc_w_avg_12_16x32_avx2: 234.6
> vvc_w_avg_12_16x64_c: 21300.8
> vvc_w_avg_12_16x64_avx2: 761.8
> vvc_w_avg_12_16x128_c: 32786.8
> vvc_w_avg_12_16x128_avx2: 1432.8
> vvc_w_avg_12_32x2_c: 2154.3
> vvc_w_avg_12_32x2_avx2: 61.1
> vvc_w_avg_12_32x4_c: 4299.8
> vvc_w_avg_12_32x4_avx2: 83.1
> vvc_w_avg_12_32x8_c: 7964.8
> vvc_w_avg_12_32x8_avx2: 132.6
> vvc_w_avg_12_32x16_c: 13321.6
> vvc_w_avg_12_32x16_avx2: 234.6
> vvc_w_avg_12_32x32_c: 21149.3
> vvc_w_avg_12_32x32_avx2: 433.3
> vvc_w_avg_12_32x64_c: 43666.6
> vvc_w_avg_12_32x64_avx2: 876.6
> vvc_w_avg_12_32x128_c: 83189.8
> vvc_w_avg_12_32x128_avx2: 1756.6
> vvc_w_avg_12_64x2_c: 3829.8
> vvc_w_avg_12_64x2_avx2: 83.1
> vvc_w_avg_12_64x4_c: 8588.1
> vvc_w_avg_12_64x4_avx2: 127.1
> vvc_w_avg_12_64x8_c: 17027.6
> vvc_w_avg_12_64x8_avx2: 310.6
> vvc_w_avg_12_64x16_c: 29797.8
> vvc_w_avg_12_64x16_avx2: 415.6
> vvc_w_avg_12_64x32_c: 43854.3
> vvc_w_avg_12_64x32_avx2: 773.3
> vvc_w_avg_12_64x64_c: 137767.3
> vvc_w_avg_12_64x64_avx2: 1608.6
> vvc_w_avg_12_64x128_c: 316428.3
> vvc_w_avg_12_64x128_avx2: 3249.8
> vvc_w_avg_12_128x2_c: 8824.6
> vvc_w_avg_12_128x2_avx2: 130.3
> vvc_w_avg_12_128x4_c: 17173.6
> vvc_w_avg_12_128x4_avx2: 219.3
> vvc_w_avg_12_128x8_c: 21997.8
> vvc_w_avg_12_128x8_avx2: 397.3
> vvc_w_avg_12_128x16_c: 43553.8
> vvc_w_avg_12_128x16_avx2: 790.1
> vvc_w_avg_12_128x32_c: 89792.1
> vvc_w_avg_12_128x32_avx2: 1497.6
> vvc_w_avg_12_128x64_c: 226573.3
> vvc_w_avg_12_128x64_avx2: 3153.1
> vvc_w_avg_12_128x128_c: 332090.1
> vvc_w_avg_12_128x128_avx2: 6499.6
> 
> Signed-off-by: Wu Jianhua <toqsxw at outlook.com>
> ---
>  libavcodec/x86/vvc/Makefile      |   3 +-
>  libavcodec/x86/vvc/vvc_mc.asm    | 301 +++++++++++++++++++++++++++++++
>  libavcodec/x86/vvc/vvcdsp_init.c |  52 ++++++
>  3 files changed, 355 insertions(+), 1 deletion(-)
>  create mode 100644 libavcodec/x86/vvc/vvc_mc.asm

this seems to break x86-32

src/libavcodec/x86/vvc/vvc_mc.asm:51: error: symbol `ff_vvc_avg_8bpc_avx2.w2' undefined
src/libavcodec/x86/vvc/vvc_mc.asm:48: ... from macro `AVG_JMP_TABLE' defined here
src/libavcodec/x86/vvc/vvc_mc.asm:51: error: symbol `ff_vvc_avg_8bpc_avx2.w4' undefined
src/libavcodec/x86/vvc/vvc_mc.asm:48: ... from macro `AVG_JMP_TABLE' defined here
src/libavcodec/x86/vvc/vvc_mc.asm:51: error: symbol `ff_vvc_avg_8bpc_avx2.w8' undefined
src/libavcodec/x86/vvc/vvc_mc.asm:48: ... from macro `AVG_JMP_TABLE' defined here
src/libavcodec/x86/vvc/vvc_mc.asm:51: error: symbol `ff_vvc_avg_8bpc_avx2.w16' undefined
src/libavcodec/x86/vvc/vvc_mc.asm:48: ... from macro `AVG_JMP_TABLE' defined here
src/libavcodec/x86/vvc/vvc_mc.asm:51: error: symbol `ff_vvc_avg_8bpc_avx2.w32' undefined
src/libavcodec/x86/vvc/vvc_mc.asm:48: ... from macro `AVG_JMP_TABLE' defined here
src/libavcodec/x86/vvc/vvc_mc.asm:51: error: symbol `ff_vvc_avg_8bpc_avx2.w64' undefined
src/libavcodec/x86/vvc/vvc_mc.asm:48: ... from macro `AVG_JMP_TABLE' defined here
src/libavcodec/x86/vvc/vvc_mc.asm:51: error: symbol `ff_vvc_avg_8bpc_avx2.w128' undefined
src/libavcodec/x86/vvc/vvc_mc.asm:48: ... from macro `AVG_JMP_TABLE' defined here
src/libavcodec/x86/vvc/vvc_mc.asm:52: error: symbol `ff_vvc_avg_16bpc_avx2.w2' undefined
src/libavcodec/x86/vvc/vvc_mc.asm:48: ... from macro `AVG_JMP_TABLE' defined here
src/libavcodec/x86/vvc/vvc_mc.asm:52: error: symbol `ff_vvc_avg_16bpc_avx2.w4' undefined
src/libavcodec/x86/vvc/vvc_mc.asm:48: ... from macro `AVG_JMP_TABLE' defined here
src/libavcodec/x86/vvc/vvc_mc.asm:52: error: symbol `ff_vvc_avg_16bpc_avx2.w8' undefined
src/libavcodec/x86/vvc/vvc_mc.asm:48: ... from macro `AVG_JMP_TABLE' defined here
src/libavcodec/x86/vvc/vvc_mc.asm:52: error: symbol `ff_vvc_avg_16bpc_avx2.w16' undefined
src/libavcodec/x86/vvc/vvc_mc.asm:48: ... from macro `AVG_JMP_TABLE' defined here
src/libavcodec/x86/vvc/vvc_mc.asm:52: error: symbol `ff_vvc_avg_16bpc_avx2.w32' undefined
src/libavcodec/x86/vvc/vvc_mc.asm:48: ... from macro `AVG_JMP_TABLE' defined here
src/libavcodec/x86/vvc/vvc_mc.asm:52: error: symbol `ff_vvc_avg_16bpc_avx2.w64' undefined
src/libavcodec/x86/vvc/vvc_mc.asm:48: ... from macro `AVG_JMP_TABLE' defined here
src/libavcodec/x86/vvc/vvc_mc.asm:52: error: symbol `ff_vvc_avg_16bpc_avx2.w128' undefined
src/libavcodec/x86/vvc/vvc_mc.asm:48: ... from macro `AVG_JMP_TABLE' defined here
src/libavcodec/x86/vvc/vvc_mc.asm:53: error: symbol `ff_vvc_w_avg_8bpc_avx2.w2' undefined
src/libavcodec/x86/vvc/vvc_mc.asm:48: ... from macro `AVG_JMP_TABLE' defined here
src/libavcodec/x86/vvc/vvc_mc.asm:53: error: symbol `ff_vvc_w_avg_8bpc_avx2.w4' undefined
src/libavcodec/x86/vvc/vvc_mc.asm:48: ... from macro `AVG_JMP_TABLE' defined here
src/libavcodec/x86/vvc/vvc_mc.asm:53: error: symbol `ff_vvc_w_avg_8bpc_avx2.w8' undefined
src/libavcodec/x86/vvc/vvc_mc.asm:48: ... from macro `AVG_JMP_TABLE' defined here
src/libavcodec/x86/vvc/vvc_mc.asm:53: error: symbol `ff_vvc_w_avg_8bpc_avx2.w16' undefined
src/libavcodec/x86/vvc/vvc_mc.asm:48: ... from macro `AVG_JMP_TABLE' defined here
src/libavcodec/x86/vvc/vvc_mc.asm:53: error: symbol `ff_vvc_w_avg_8bpc_avx2.w32' undefined
src/libavcodec/x86/vvc/vvc_mc.asm:48: ... from macro `AVG_JMP_TABLE' defined here
src/libavcodec/x86/vvc/vvc_mc.asm:53: error: symbol `ff_vvc_w_avg_8bpc_avx2.w64' undefined
src/libavcodec/x86/vvc/vvc_mc.asm:48: ... from macro `AVG_JMP_TABLE' defined here
src/libavcodec/x86/vvc/vvc_mc.asm:53: error: symbol `ff_vvc_w_avg_8bpc_avx2.w128' undefined
src/libavcodec/x86/vvc/vvc_mc.asm:48: ... from macro `AVG_JMP_TABLE' defined here
src/libavcodec/x86/vvc/vvc_mc.asm:54: error: symbol `ff_vvc_w_avg_16bpc_avx2.w2' undefined
src/libavcodec/x86/vvc/vvc_mc.asm:48: ... from macro `AVG_JMP_TABLE' defined here
src/libavcodec/x86/vvc/vvc_mc.asm:54: error: symbol `ff_vvc_w_avg_16bpc_avx2.w4' undefined
src/libavcodec/x86/vvc/vvc_mc.asm:48: ... from macro `AVG_JMP_TABLE' defined here
src/libavcodec/x86/vvc/vvc_mc.asm:54: error: symbol `ff_vvc_w_avg_16bpc_avx2.w8' undefined
src/libavcodec/x86/vvc/vvc_mc.asm:48: ... from macro `AVG_JMP_TABLE' defined here
src/libavcodec/x86/vvc/vvc_mc.asm:54: error: symbol `ff_vvc_w_avg_16bpc_avx2.w16' undefined
src/libavcodec/x86/vvc/vvc_mc.asm:48: ... from macro `AVG_JMP_TABLE' defined here
src/libavcodec/x86/vvc/vvc_mc.asm:54: error: symbol `ff_vvc_w_avg_16bpc_avx2.w32' undefined
src/libavcodec/x86/vvc/vvc_mc.asm:48: ... from macro `AVG_JMP_TABLE' defined here
src/libavcodec/x86/vvc/vvc_mc.asm:54: error: symbol `ff_vvc_w_avg_16bpc_avx2.w64' undefined
src/libavcodec/x86/vvc/vvc_mc.asm:48: ... from macro `AVG_JMP_TABLE' defined here
src/libavcodec/x86/vvc/vvc_mc.asm:54: error: symbol `ff_vvc_w_avg_16bpc_avx2.w128' undefined
src/libavcodec/x86/vvc/vvc_mc.asm:48: ... from macro `AVG_JMP_TABLE' defined here
src/ffbuild/common.mak:103: recipe for target 'libavcodec/x86/vvc/vvc_mc.o' failed
make: *** [libavcodec/x86/vvc/vvc_mc.o] Error 1
make: *** Waiting for unfinished jobs....

[...]
-- 
Michael     GnuPG fingerprint: 9FF2128B147EF6730BADF133611EC787040B0FAB

Dictatorship: All citizens are under surveillance, all their steps and
actions recorded, for the politicians to enforce control.
Democracy: All politicians are under surveillance, all their steps and
actions recorded, for the citizens to enforce control.
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 195 bytes
Desc: not available
URL: <https://ffmpeg.org/pipermail/ffmpeg-devel/attachments/20240122/9e71b0fe/attachment.sig>