Skip to content

x86/itx: Add 8x16, 16x8 12bpc AVX2 transforms

Matthias Dressel requested to merge another/dav1d:itx-12-avx2-8x16 into master
inv_txfm_add_8x16_adst_adst_0_12bpc_c: 4440.4
inv_txfm_add_8x16_adst_adst_0_12bpc_avx2: 354.3
inv_txfm_add_8x16_adst_adst_1_12bpc_c: 4437.3
inv_txfm_add_8x16_adst_adst_1_12bpc_avx2: 354.3
inv_txfm_add_8x16_adst_adst_2_12bpc_c: 4438.8
inv_txfm_add_8x16_adst_adst_2_12bpc_avx2: 442.6
inv_txfm_add_8x16_adst_dct_0_12bpc_c: 4507.3
inv_txfm_add_8x16_adst_dct_0_12bpc_avx2: 310.0
inv_txfm_add_8x16_adst_dct_1_12bpc_c: 4500.3
inv_txfm_add_8x16_adst_dct_1_12bpc_avx2: 310.0
inv_txfm_add_8x16_adst_dct_2_12bpc_c: 4516.1
inv_txfm_add_8x16_adst_dct_2_12bpc_avx2: 399.5
inv_txfm_add_8x16_adst_flipadst_0_12bpc_c: 4457.3
inv_txfm_add_8x16_adst_flipadst_0_12bpc_avx2: 355.6
inv_txfm_add_8x16_adst_flipadst_1_12bpc_c: 4441.3
inv_txfm_add_8x16_adst_flipadst_1_12bpc_avx2: 355.6
inv_txfm_add_8x16_adst_flipadst_2_12bpc_c: 4448.9
inv_txfm_add_8x16_adst_flipadst_2_12bpc_avx2: 445.5
inv_txfm_add_8x16_adst_identity_0_12bpc_c: 3204.0
inv_txfm_add_8x16_adst_identity_0_12bpc_avx2: 173.1
inv_txfm_add_8x16_adst_identity_1_12bpc_c: 3207.1
inv_txfm_add_8x16_adst_identity_1_12bpc_avx2: 173.6
inv_txfm_add_8x16_adst_identity_2_12bpc_c: 3210.4
inv_txfm_add_8x16_adst_identity_2_12bpc_avx2: 261.2
inv_txfm_add_8x16_dct_adst_0_12bpc_c: 4484.2
inv_txfm_add_8x16_dct_adst_0_12bpc_avx2: 334.0
inv_txfm_add_8x16_dct_adst_1_12bpc_c: 4503.8
inv_txfm_add_8x16_dct_adst_1_12bpc_avx2: 334.6
inv_txfm_add_8x16_dct_adst_2_12bpc_c: 4490.7
inv_txfm_add_8x16_dct_adst_2_12bpc_avx2: 395.6
inv_txfm_add_8x16_dct_dct_0_12bpc_c: 419.9
inv_txfm_add_8x16_dct_dct_0_12bpc_avx2: 37.6
inv_txfm_add_8x16_dct_dct_1_12bpc_c: 4482.6
inv_txfm_add_8x16_dct_dct_1_12bpc_avx2: 284.6
inv_txfm_add_8x16_dct_dct_2_12bpc_c: 4468.7
inv_txfm_add_8x16_dct_dct_2_12bpc_avx2: 348.3
inv_txfm_add_8x16_dct_flipadst_0_12bpc_c: 4468.4
inv_txfm_add_8x16_dct_flipadst_0_12bpc_avx2: 333.6
inv_txfm_add_8x16_dct_flipadst_1_12bpc_c: 4463.5
inv_txfm_add_8x16_dct_flipadst_1_12bpc_avx2: 333.5
inv_txfm_add_8x16_dct_flipadst_2_12bpc_c: 4459.4
inv_txfm_add_8x16_dct_flipadst_2_12bpc_avx2: 397.4
inv_txfm_add_8x16_dct_identity_0_12bpc_c: 3237.1
inv_txfm_add_8x16_dct_identity_0_12bpc_avx2: 149.6
inv_txfm_add_8x16_dct_identity_1_12bpc_c: 3229.9
inv_txfm_add_8x16_dct_identity_1_12bpc_avx2: 148.6
inv_txfm_add_8x16_dct_identity_2_12bpc_c: 3225.6
inv_txfm_add_8x16_dct_identity_2_12bpc_avx2: 211.3
inv_txfm_add_8x16_flipadst_adst_0_12bpc_c: 4532.1
inv_txfm_add_8x16_flipadst_adst_0_12bpc_avx2: 356.2
inv_txfm_add_8x16_flipadst_adst_1_12bpc_c: 4527.6
inv_txfm_add_8x16_flipadst_adst_1_12bpc_avx2: 356.1
inv_txfm_add_8x16_flipadst_adst_2_12bpc_c: 4532.5
inv_txfm_add_8x16_flipadst_adst_2_12bpc_avx2: 440.0
inv_txfm_add_8x16_flipadst_dct_0_12bpc_c: 4571.6
inv_txfm_add_8x16_flipadst_dct_0_12bpc_avx2: 310.3
inv_txfm_add_8x16_flipadst_dct_1_12bpc_c: 4554.5
inv_txfm_add_8x16_flipadst_dct_1_12bpc_avx2: 309.7
inv_txfm_add_8x16_flipadst_dct_2_12bpc_c: 4554.3
inv_txfm_add_8x16_flipadst_dct_2_12bpc_avx2: 399.9
inv_txfm_add_8x16_flipadst_flipadst_0_12bpc_c: 4497.2
inv_txfm_add_8x16_flipadst_flipadst_0_12bpc_avx2: 355.9
inv_txfm_add_8x16_flipadst_flipadst_1_12bpc_c: 4486.2
inv_txfm_add_8x16_flipadst_flipadst_1_12bpc_avx2: 355.6
inv_txfm_add_8x16_flipadst_flipadst_2_12bpc_c: 4493.4
inv_txfm_add_8x16_flipadst_flipadst_2_12bpc_avx2: 446.0
inv_txfm_add_8x16_flipadst_identity_0_12bpc_c: 3265.7
inv_txfm_add_8x16_flipadst_identity_0_12bpc_avx2: 173.8
inv_txfm_add_8x16_flipadst_identity_1_12bpc_c: 3270.8
inv_txfm_add_8x16_flipadst_identity_1_12bpc_avx2: 173.5
inv_txfm_add_8x16_flipadst_identity_2_12bpc_c: 3271.8
inv_txfm_add_8x16_flipadst_identity_2_12bpc_avx2: 261.6
inv_txfm_add_8x16_identity_adst_0_12bpc_c: 3295.3
inv_txfm_add_8x16_identity_adst_0_12bpc_avx2: 302.5
inv_txfm_add_8x16_identity_adst_1_12bpc_c: 3303.1
inv_txfm_add_8x16_identity_adst_1_12bpc_avx2: 303.0
inv_txfm_add_8x16_identity_adst_2_12bpc_c: 3304.6
inv_txfm_add_8x16_identity_adst_2_12bpc_avx2: 303.1
inv_txfm_add_8x16_identity_dct_0_12bpc_c: 3298.9
inv_txfm_add_8x16_identity_dct_0_12bpc_avx2: 257.8
inv_txfm_add_8x16_identity_dct_1_12bpc_c: 3308.1
inv_txfm_add_8x16_identity_dct_1_12bpc_avx2: 259.2
inv_txfm_add_8x16_identity_dct_2_12bpc_c: 3306.6
inv_txfm_add_8x16_identity_dct_2_12bpc_avx2: 259.2
inv_txfm_add_8x16_identity_flipadst_0_12bpc_c: 3294.7
inv_txfm_add_8x16_identity_flipadst_0_12bpc_avx2: 302.2
inv_txfm_add_8x16_identity_flipadst_1_12bpc_c: 3292.5
inv_txfm_add_8x16_identity_flipadst_1_12bpc_avx2: 302.2
inv_txfm_add_8x16_identity_flipadst_2_12bpc_c: 3275.4
inv_txfm_add_8x16_identity_flipadst_2_12bpc_avx2: 303.3
inv_txfm_add_8x16_identity_identity_0_12bpc_c: 2044.6
inv_txfm_add_8x16_identity_identity_0_12bpc_avx2: 116.2
inv_txfm_add_8x16_identity_identity_1_12bpc_c: 2059.9
inv_txfm_add_8x16_identity_identity_1_12bpc_avx2: 117.0
inv_txfm_add_8x16_identity_identity_2_12bpc_c: 2048.4
inv_txfm_add_8x16_identity_identity_2_12bpc_avx2: 116.2
inv_txfm_add_16x8_adst_adst_0_12bpc_c: 4517.9
inv_txfm_add_16x8_adst_adst_0_12bpc_avx2: 432.4
inv_txfm_add_16x8_adst_adst_1_12bpc_c: 4510.9
inv_txfm_add_16x8_adst_adst_1_12bpc_avx2: 432.4
inv_txfm_add_16x8_adst_adst_2_12bpc_c: 4498.6
inv_txfm_add_16x8_adst_adst_2_12bpc_avx2: 432.4
inv_txfm_add_16x8_adst_dct_0_12bpc_c: 4553.8
inv_txfm_add_16x8_adst_dct_0_12bpc_avx2: 389.1
inv_txfm_add_16x8_adst_dct_1_12bpc_c: 4543.3
inv_txfm_add_16x8_adst_dct_1_12bpc_avx2: 389.1
inv_txfm_add_16x8_adst_dct_2_12bpc_c: 4538.4
inv_txfm_add_16x8_adst_dct_2_12bpc_avx2: 389.1
inv_txfm_add_16x8_adst_flipadst_0_12bpc_c: 4532.6
inv_txfm_add_16x8_adst_flipadst_0_12bpc_avx2: 435.4
inv_txfm_add_16x8_adst_flipadst_1_12bpc_c: 4520.4
inv_txfm_add_16x8_adst_flipadst_1_12bpc_avx2: 435.4
inv_txfm_add_16x8_adst_flipadst_2_12bpc_c: 4516.2
inv_txfm_add_16x8_adst_flipadst_2_12bpc_avx2: 435.4
inv_txfm_add_16x8_adst_identity_0_12bpc_c: 3502.3
inv_txfm_add_16x8_adst_identity_0_12bpc_avx2: 255.9
inv_txfm_add_16x8_adst_identity_1_12bpc_c: 3492.9
inv_txfm_add_16x8_adst_identity_1_12bpc_avx2: 256.3
inv_txfm_add_16x8_adst_identity_2_12bpc_c: 3471.4
inv_txfm_add_16x8_adst_identity_2_12bpc_avx2: 256.7
inv_txfm_add_16x8_dct_adst_0_12bpc_c: 4563.2
inv_txfm_add_16x8_dct_adst_0_12bpc_avx2: 383.6
inv_txfm_add_16x8_dct_adst_1_12bpc_c: 4573.1
inv_txfm_add_16x8_dct_adst_1_12bpc_avx2: 383.9
inv_txfm_add_16x8_dct_adst_2_12bpc_c: 4562.2
inv_txfm_add_16x8_dct_adst_2_12bpc_avx2: 383.7
inv_txfm_add_16x8_dct_dct_0_12bpc_c: 514.0
inv_txfm_add_16x8_dct_dct_0_12bpc_avx2: 25.0
inv_txfm_add_16x8_dct_dct_1_12bpc_c: 4540.5
inv_txfm_add_16x8_dct_dct_1_12bpc_avx2: 340.4
inv_txfm_add_16x8_dct_dct_2_12bpc_c: 4563.0
inv_txfm_add_16x8_dct_dct_2_12bpc_avx2: 339.3
inv_txfm_add_16x8_dct_flipadst_0_12bpc_c: 4568.0
inv_txfm_add_16x8_dct_flipadst_0_12bpc_avx2: 385.9
inv_txfm_add_16x8_dct_flipadst_1_12bpc_c: 4577.5
inv_txfm_add_16x8_dct_flipadst_1_12bpc_avx2: 385.8
inv_txfm_add_16x8_dct_flipadst_2_12bpc_c: 4573.8
inv_txfm_add_16x8_dct_flipadst_2_12bpc_avx2: 385.8
inv_txfm_add_16x8_dct_identity_0_12bpc_c: 3549.9
inv_txfm_add_16x8_dct_identity_0_12bpc_avx2: 212.1
inv_txfm_add_16x8_dct_identity_1_12bpc_c: 3538.7
inv_txfm_add_16x8_dct_identity_1_12bpc_avx2: 212.1
inv_txfm_add_16x8_dct_identity_2_12bpc_c: 3539.7
inv_txfm_add_16x8_dct_identity_2_12bpc_avx2: 212.1
inv_txfm_add_16x8_flipadst_adst_0_12bpc_c: 4495.3
inv_txfm_add_16x8_flipadst_adst_0_12bpc_avx2: 431.4
inv_txfm_add_16x8_flipadst_adst_1_12bpc_c: 4496.3
inv_txfm_add_16x8_flipadst_adst_1_12bpc_avx2: 431.4
inv_txfm_add_16x8_flipadst_adst_2_12bpc_c: 4499.2
inv_txfm_add_16x8_flipadst_adst_2_12bpc_avx2: 431.3
inv_txfm_add_16x8_flipadst_dct_0_12bpc_c: 4506.9
inv_txfm_add_16x8_flipadst_dct_0_12bpc_avx2: 386.3
inv_txfm_add_16x8_flipadst_dct_1_12bpc_c: 4512.9
inv_txfm_add_16x8_flipadst_dct_1_12bpc_avx2: 386.0
inv_txfm_add_16x8_flipadst_dct_2_12bpc_c: 4503.2
inv_txfm_add_16x8_flipadst_dct_2_12bpc_avx2: 386.0
inv_txfm_add_16x8_flipadst_flipadst_0_12bpc_c: 4509.1
inv_txfm_add_16x8_flipadst_flipadst_0_12bpc_avx2: 432.2
inv_txfm_add_16x8_flipadst_flipadst_1_12bpc_c: 4519.0
inv_txfm_add_16x8_flipadst_flipadst_1_12bpc_avx2: 432.1
inv_txfm_add_16x8_flipadst_flipadst_2_12bpc_c: 4518.3
inv_txfm_add_16x8_flipadst_flipadst_2_12bpc_avx2: 432.1
inv_txfm_add_16x8_flipadst_identity_0_12bpc_c: 3511.0
inv_txfm_add_16x8_flipadst_identity_0_12bpc_avx2: 257.1
inv_txfm_add_16x8_flipadst_identity_1_12bpc_c: 3518.5
inv_txfm_add_16x8_flipadst_identity_1_12bpc_avx2: 257.2
inv_txfm_add_16x8_flipadst_identity_2_12bpc_c: 3521.7
inv_txfm_add_16x8_flipadst_identity_2_12bpc_avx2: 257.1
inv_txfm_add_16x8_identity_adst_0_12bpc_c: 3166.8
inv_txfm_add_16x8_identity_adst_0_12bpc_avx2: 268.6
inv_txfm_add_16x8_identity_adst_1_12bpc_c: 3157.9
inv_txfm_add_16x8_identity_adst_1_12bpc_avx2: 268.6
inv_txfm_add_16x8_identity_adst_2_12bpc_c: 3156.5
inv_txfm_add_16x8_identity_adst_2_12bpc_avx2: 268.6
inv_txfm_add_16x8_identity_dct_0_12bpc_c: 3187.4
inv_txfm_add_16x8_identity_dct_0_12bpc_avx2: 224.4
inv_txfm_add_16x8_identity_dct_1_12bpc_c: 3185.8
inv_txfm_add_16x8_identity_dct_1_12bpc_avx2: 224.4
inv_txfm_add_16x8_identity_dct_2_12bpc_c: 3190.8
inv_txfm_add_16x8_identity_dct_2_12bpc_avx2: 224.4
inv_txfm_add_16x8_identity_flipadst_0_12bpc_c: 3167.7
inv_txfm_add_16x8_identity_flipadst_0_12bpc_avx2: 269.7
inv_txfm_add_16x8_identity_flipadst_1_12bpc_c: 3174.1
inv_txfm_add_16x8_identity_flipadst_1_12bpc_avx2: 269.8
inv_txfm_add_16x8_identity_flipadst_2_12bpc_c: 3174.7
inv_txfm_add_16x8_identity_flipadst_2_12bpc_avx2: 269.7
inv_txfm_add_16x8_identity_identity_0_12bpc_c: 2153.3
inv_txfm_add_16x8_identity_identity_0_12bpc_avx2: 99.1
inv_txfm_add_16x8_identity_identity_1_12bpc_c: 2143.6
inv_txfm_add_16x8_identity_identity_1_12bpc_avx2: 99.3
inv_txfm_add_16x8_identity_identity_2_12bpc_c: 2145.9
inv_txfm_add_16x8_identity_identity_2_12bpc_avx2: 98.6

Merge request reports