• J. Dekker's avatar
    lavc/aarch64: add hevc horizontal qpel/uni/bi · 9bed814e
    J. Dekker authored
    checkasm --benchmark on Ampere Altra (Neoverse N1):
    
    put_hevc_qpel_bi_h4_8_c: 170.7
    put_hevc_qpel_bi_h4_8_neon: 64.5
    put_hevc_qpel_bi_h6_8_c: 373.7
    put_hevc_qpel_bi_h6_8_neon: 130.2
    put_hevc_qpel_bi_h8_8_c: 662.0
    put_hevc_qpel_bi_h8_8_neon: 138.5
    put_hevc_qpel_bi_h12_8_c: 1529.5
    put_hevc_qpel_bi_h12_8_neon: 422.0
    put_hevc_qpel_bi_h16_8_c: 2735.5
    put_hevc_qpel_bi_h16_8_neon: 560.5
    put_hevc_qpel_bi_h24_8_c: 6015.7
    put_hevc_qpel_bi_h24_8_neon: 1636.0
    put_hevc_qpel_bi_h32_8_c: 10779.0
    put_hevc_qpel_bi_h32_8_neon: 2204.5
    put_hevc_qpel_bi_h48_8_c: 24375.0
    put_hevc_qpel_bi_h48_8_neon: 4984.0
    put_hevc_qpel_bi_h64_8_c: 42768.0
    put_hevc_qpel_bi_h64_8_neon: 8795.7
    put_hevc_qpel_h4_8_c: 149.0
    put_hevc_qpel_h4_8_neon: 55.7
    put_hevc_qpel_h6_8_c: 321.2
    put_hevc_qpel_h6_8_neon: 106.0
    put_hevc_qpel_h8_8_c: 578.7
    put_hevc_qpel_h8_8_neon: 133.2
    put_hevc_qpel_h12_8_c: 1279.0
    put_hevc_qpel_h12_8_neon: 391.7
    put_hevc_qpel_h16_8_c: 2286.2
    put_hevc_qpel_h16_8_neon: 519.7
    put_hevc_qpel_h24_8_c: 5100.7
    put_hevc_qpel_h24_8_neon: 1546.2
    put_hevc_qpel_h32_8_c: 9022.0
    put_hevc_qpel_h32_8_neon: 2060.2
    put_hevc_qpel_h48_8_c: 20293.5
    put_hevc_qpel_h48_8_neon: 4656.7
    put_hevc_qpel_h64_8_c: 36037.0
    put_hevc_qpel_h64_8_neon: 8262.7
    put_hevc_qpel_uni_h4_8_c: 162.2
    put_hevc_qpel_uni_h4_8_neon: 61.7
    put_hevc_qpel_uni_h6_8_c: 355.2
    put_hevc_qpel_uni_h6_8_neon: 114.2
    put_hevc_qpel_uni_h8_8_c: 651.0
    put_hevc_qpel_uni_h8_8_neon: 135.7
    put_hevc_qpel_uni_h12_8_c: 1412.5
    put_hevc_qpel_uni_h12_8_neon: 402.7
    put_hevc_qpel_uni_h16_8_c: 2551.0
    put_hevc_qpel_uni_h16_8_neon: 533.5
    put_hevc_qpel_uni_h24_8_c: 5782.2
    put_hevc_qpel_uni_h24_8_neon: 1578.7
    put_hevc_qpel_uni_h32_8_c: 10586.5
    put_hevc_qpel_uni_h32_8_neon: 2102.2
    put_hevc_qpel_uni_h48_8_c: 23812.0
    put_hevc_qpel_uni_h48_8_neon: 4739.5
    put_hevc_qpel_uni_h64_8_c: 42958.7
    put_hevc_qpel_uni_h64_8_neon: 8366.5
    Signed-off-by: 's avatarJ. Dekker <jdek@itanimul.li>
    9bed814e
hevcdsp_qpel_neon.S 16 KB