Skip to content

x86: add AVX2/SSSE3 SIMD for generate_grain_uv_{422,444}

gen_grain_uv_ar0_8bpc_420_c: 72275.4
gen_grain_uv_ar0_8bpc_420_ssse3: 7274.8
gen_grain_uv_ar0_8bpc_420_avx2: 7253.4
gen_grain_uv_ar0_8bpc_422_c: 111742.9
gen_grain_uv_ar0_8bpc_422_ssse3: 13724.8
gen_grain_uv_ar0_8bpc_422_avx2: 13704.1
gen_grain_uv_ar0_8bpc_444_c: 205688.5
gen_grain_uv_ar0_8bpc_444_ssse3: 26218.3
gen_grain_uv_ar0_8bpc_444_avx2: 25007.5
gen_grain_uv_ar1_8bpc_420_c: 100682.5
gen_grain_uv_ar1_8bpc_420_ssse3: 20168.4
gen_grain_uv_ar1_8bpc_420_avx2: 18434.4
gen_grain_uv_ar1_8bpc_422_c: 167931.4
gen_grain_uv_ar1_8bpc_422_ssse3: 39524.7
gen_grain_uv_ar1_8bpc_422_avx2: 37817.9
gen_grain_uv_ar1_8bpc_444_c: 323812.2
gen_grain_uv_ar1_8bpc_444_ssse3: 77930.3
gen_grain_uv_ar1_8bpc_444_avx2: 74049.6
gen_grain_uv_ar2_8bpc_420_c: 159545.7
gen_grain_uv_ar2_8bpc_420_ssse3: 25849.7
gen_grain_uv_ar2_8bpc_420_avx2: 23994.0
gen_grain_uv_ar2_8bpc_422_c: 295959.9
gen_grain_uv_ar2_8bpc_422_ssse3: 49286.6
gen_grain_uv_ar2_8bpc_422_avx2: 48103.5
gen_grain_uv_ar2_8bpc_444_c: 571862.2
gen_grain_uv_ar2_8bpc_444_ssse3: 98814.2
gen_grain_uv_ar2_8bpc_444_avx2: 93044.6
gen_grain_uv_ar3_8bpc_420_c: 243445.9
gen_grain_uv_ar3_8bpc_420_ssse3: 28806.2
gen_grain_uv_ar3_8bpc_420_avx2: 27698.3
gen_grain_uv_ar3_8bpc_422_c: 458189.9
gen_grain_uv_ar3_8bpc_422_ssse3: 56629.9
gen_grain_uv_ar3_8bpc_422_avx2: 54183.1
gen_grain_uv_ar3_8bpc_444_c: 883627.3
gen_grain_uv_ar3_8bpc_444_ssse3: 114761.2
gen_grain_uv_ar3_8bpc_444_avx2: 103296.7
Edited by Jean-Baptiste Kempf

Merge request reports