På lørdag 1. august 2026 kl. 07:46, skrev Brad Smith
<[email protected]>:

> Here is an update to x265 4.3.
>
> All depends build Ok.
>
> Tested on aarch64 and amd64.
>
>


$ cd /usr/ports/multimedia/x265/ && make build package test ; make 
port-lib-depends-check check-shlib-syms clean

===>  Regression tests for x265-4.3
/usr/ports/pobj/x265-4.3/build-amd64/test/TestBench
Using random seed 6A6FB69D 8bit
Testing primitives: SSE2
Testing primitives: SSE3
Testing primitives: SSSE3
Testing primitives: SSE4
Testing primitives: AVX

Test performance improvement with full optimizations
== pixel primitives ==
           satd[  4x4] |        3.84x |          162.40   |      623.50
         avg_pp[  4x4] |        1.74x |          238.51   |      415.03
 avg_pp_aligned[  4x4] |        1.80x |          226.73   |      407.04
            sad[  4x4] |        3.45x |          73.70    |      254.40
         sad_x3[  4x4] |        10.00x |         132.51   |      1324.85
         sad_x4[  4x4] |        11.81x |         178.02   |      2102.18
        copy_pp[  4x4] |        2.75x |          63.65    |      175.09
         addAvg[  4x4] |        5.69x |          137.71   |      783.51
 addAvg_aligned[  4x4] |        5.28x |          140.51   |      741.85
         sse_pp[  4x4] |        0.70x |          238.45   |      167.19
         sse_ss[  4x4] |        2.31x |          107.30   |      247.33
         sub_ps[  4x4] |        4.01x |          103.40   |      414.93
         add_ps[  4x4] |        5.28x |          109.93   |      580.73
 add_ps_aligned[  4x4] |        5.59x |          103.34   |      577.95
        copy_ss[  4x4] |        2.63x |          63.62    |      167.24
        copy_sp[  4x4] |        1.62x |          103.55   |      167.65
        copy_ps[  4x4] |        2.21x |          75.24    |      165.92
           satd[  8x8] |        3.81x |          341.70   |      1300.84
         avg_pp[  8x8] |        13.21x |         195.03   |      2575.90
 avg_pp_aligned[  8x8] |        13.22x |         194.44   |      2570.56
            sad[  8x8] |        2.43x |          123.16   |      299.86
         sad_x3[  8x8] |        18.80x |         250.34   |      4707.44
         sad_x4[  8x8] |        77.23x |         284.39   |      21964.18
        copy_pp[  8x8] |        7.08x |          80.33    |      568.69
         addAvg[  8x8] |        10.22x |         235.97   |      2412.31
 addAvg_aligned[  8x8] |        10.33x |         233.84   |      2414.43
         sse_pp[  8x8] |        3.58x |          203.14   |      728.16
         sse_ss[  8x8] |        6.52x |          174.41   |      1137.35
         sub_ps[  8x8] |        4.91x |          194.88   |      956.50
         add_ps[  8x8] |        11.38x |         193.22   |      2199.00
 add_ps_aligned[  8x8] |        10.06x |         215.33   |      2166.21
        copy_ss[  8x8] |        5.91x |          95.42    |      563.64
        copy_sp[  8x8] |        5.21x |          109.49   |      570.00
        copy_ps[  8x8] |        4.52x |          125.34   |      567.11
 [i420] copy_pp[  4x4] |        2.98x |          58.09    |      173.19
 [i420]  addAvg[  4x4] |        5.46x |          136.57   |      745.57
[i420]  addAvg_aligned[  4x4] |         5.44x |          136.76   |      743.45
    [i420] satd[  4x4] |        3.94x |          156.21   |      615.66
 [i420] copy_ss[  4x4] |        2.66x |          63.64    |      169.33
 [i420] copy_ps[  4x4] |        2.30x |          74.56    |      171.33
 [i420] copy_sp[  4x4] |        2.29x |          75.11    |      171.84
 [i420]  sub_ps[  4x4] |        2.95x |          107.31   |      316.47
 [i420]  add_ps[  4x4] |        5.47x |          104.73   |      572.59
[i420]  add_ps_aligned[  4x4] |         5.29x |          108.11   |      572.33
    [i420] sa8d[  4x4] |        3.97x |          155.15   |      616.11
 [i422] copy_pp[  4x8] |        3.42x |          91.32    |      312.58
 [i422]  addAvg[  4x8] |        5.88x |          232.35   |      1365.38
[i422]  addAvg_aligned[  4x8] |         5.83x |          233.74   |      1361.93
    [i422] satd[  4x8] |        5.22x |          254.67   |      1329.63
 [i422] copy_ss[  4x8] |        2.92x |          106.10   |      309.54
 [i422] copy_ps[  4x8] |        2.26x |          137.30   |      310.97
 [i422] copy_sp[  4x8] |        2.83x |          111.98   |      316.58
  [i422] sse_pp[  4x8] |        0.86x |          328.11   |      281.51
 [i422]  sub_ps[  4x8] |        2.84x |          194.85   |      552.67
 [i422]  add_ps[  4x8] |        6.11x |          196.77   |      1201.84
[i422]  add_ps_aligned[  4x8] |         6.36x |          186.94   |      1188.82
           satd[  8x4] |        2.59x |          233.95   |      606.36
         avg_pp[  8x4] |        10.42x |         128.77   |      1341.30
 avg_pp_aligned[  8x4] |        10.88x |         123.31   |      1342.08
            sad[  8x4] |        1.86x |          76.81    |      142.95
         sad_x3[  8x4] |        16.08x |         148.68   |      2391.49
         sad_x4[  8x4] |        59.37x |         182.07   |      10809.83
        copy_pp[  8x4] |        4.61x |          63.64    |      293.19
         addAvg[  8x4] |        9.12x |          140.55   |      1282.35
 addAvg_aligned[  8x4] |        9.09x |          139.09   |      1264.88
 [i420] copy_pp[  4x2] |        2.14x |          54.63    |      117.13
 [i420]  addAvg[  4x2] |        6.04x |          81.14    |      490.18
[i420]  addAvg_aligned[  4x2] |         6.07x |          85.24    |      517.09
 [i422] copy_pp[  4x4] |        3.02x |          60.95    |      183.81
 [i422]  addAvg[  4x4] |        5.42x |          136.87   |      741.94
[i422]  addAvg_aligned[  4x4] |         5.45x |          137.09   |      746.72
    [i422] satd[  4x4] |        3.98x |          154.97   |      616.52
           satd[  4x8] |        5.49x |          243.37   |      1335.27
         avg_pp[  4x8] |        5.47x |          266.84   |      1460.68
 avg_pp_aligned[  4x8] |        5.61x |          277.58   |      1557.41
            sad[  4x8] |        2.28x |          140.41   |      319.93
         sad_x3[  4x8] |        11.07x |         236.42   |      2617.12
         sad_x4[  4x8] |        12.73x |         297.70   |      3788.84
        copy_pp[  4x8] |        3.49x |          87.47    |      305.07
         addAvg[  4x8] |        6.00x |          226.61   |      1360.54
 addAvg_aligned[  4x8] |        5.85x |          231.07   |      1350.71
 [i420] copy_pp[  2x4] |        1.74x |          66.51    |      115.63
 [i420]  addAvg[  2x4] |        3.17x |          125.24   |      397.18
[i420]  addAvg_aligned[  2x4] |         3.26x |          122.29   |      398.16
 [i422] copy_pp[  2x8] |        1.81x |          105.37   |      191.21
 [i422]  addAvg[  2x8] |        3.83x |          220.02   |      842.58
[i422]  addAvg_aligned[  2x8] |         3.72x |          230.67   |      857.32
           satd[16x16] |        3.81x |          1385.74  |      5277.11
         avg_pp[16x16] |        27.45x |         327.26   |      8983.29
 avg_pp_aligned[16x16] |        27.28x |         331.10   |      9032.45
            sad[16x16] |        3.29x |          238.36   |      783.14
         sad_x3[16x16] |        7.66x |          495.47   |      3796.89
         sad_x4[16x16] |        146.62x |        597.65   |      87630.22
        copy_pp[16x16] |        14.42x |         158.79   |      2289.90
         addAvg[16x16] |        17.94x |         614.88   |      11030.91
 addAvg_aligned[16x16] |        17.85x |         622.56   |      11115.24
         sse_pp[16x16] |        3.74x |          547.51   |      2047.54
         sse_ss[16x16] |        7.41x |          482.94   |      3580.61
         sub_ps[16x16] |        6.15x |          550.73   |      3388.75
         add_ps[16x16] |        4.01x |          445.57   |      1786.44
 add_ps_aligned[16x16] |        4.13x |          434.01   |      1791.13
        copy_ss[16x16] |        6.99x |          328.30   |      2293.83
        copy_sp[16x16] |        9.61x |          238.66   |      2293.06
        copy_ps[16x16] |        6.58x |          349.58   |      2299.50
 [i420] copy_pp[  8x8] |        6.31x |          90.19    |      569.47
 [i420]  addAvg[  8x8] |        10.23x |         237.27   |      2426.98
[i420]  addAvg_aligned[  8x8] |         10.26x |         236.16   |      2423.54
    [i420] satd[  8x8] |        4.00x |          348.26   |      1392.81
 [i420] copy_ss[  8x8] |        5.42x |          111.36   |      604.03
 [i420] copy_ps[  8x8] |        4.54x |          132.55   |      602.18
 [i420] copy_sp[  8x8] |        5.52x |          110.00   |      607.12
  [i420] sse_pp[  8x8] |        3.37x |          214.29   |      721.74
 [i420]  sub_ps[  8x8] |        4.94x |          193.02   |      953.22
 [i420]  add_ps[  8x8] |        11.22x |         192.19   |      2156.27
[i420]  add_ps_aligned[  8x8] |         11.15x |         192.79   |      2150.34
    [i420] sa8d[  8x8] |        4.06x |          450.92   |      1830.30
 [i422] copy_pp[ 8x16] |        7.85x |          161.97   |      1272.11
 [i422]  addAvg[ 8x16] |        10.38x |         460.45   |      4779.45
[i422]  addAvg_aligned[ 8x16] |         10.66x |         466.47   |      4971.82
    [i422] satd[ 8x16] |        3.52x |          723.57   |      2549.59
 [i422] copy_ss[ 8x16] |        7.32x |          173.73   |      1271.98
 [i422] copy_ps[ 8x16] |        5.51x |          230.95   |      1273.29
 [i422] copy_sp[ 8x16] |        6.42x |          197.77   |      1269.23
  [i422] sse_pp[ 8x16] |        3.91x |          350.78   |      1372.38
 [i422]  sub_ps[ 8x16] |        5.21x |          339.71   |      1771.35
 [i422]  add_ps[ 8x16] |        12.67x |         340.84   |      4318.48
[i422]  add_ps_aligned[ 8x16] |         12.23x |         340.73   |      4167.34
    [i422] sa8d[ 8x16] |        3.92x |          862.42   |      3377.86
           satd[ 16x8] |        3.63x |          719.44   |      2609.08
         avg_pp[ 16x8] |        23.22x |         197.52   |      4587.16
 avg_pp_aligned[ 16x8] |        22.67x |         202.03   |      4580.89
            sad[ 16x8] |        3.45x |          119.76   |      413.52
         sad_x3[ 16x8] |        7.58x |          255.87   |      1938.61
         sad_x4[ 16x8] |        129.36x |        345.60   |      44706.25
        copy_pp[ 16x8] |        11.30x |         103.33   |      1167.51
         addAvg[ 16x8] |        17.14x |         314.23   |      5386.38
 addAvg_aligned[ 16x8] |        16.93x |         317.89   |      5383.15
 [i420] copy_pp[  8x4] |        4.56x |          64.73    |      295.36
 [i420]  addAvg[  8x4] |        8.64x |          157.17   |      1357.23
[i420]  addAvg_aligned[  8x4] |         8.62x |          148.13   |      1276.25
    [i420] satd[  8x4] |        2.50x |          241.29   |      603.26
 [i422] copy_pp[  8x8] |        6.32x |          90.28    |      570.81
 [i422]  addAvg[  8x8] |        10.22x |         237.80   |      2430.08
[i422]  addAvg_aligned[  8x8] |         9.86x |          250.47   |      2469.43
    [i422] satd[  8x8] |        3.81x |          343.95   |      1310.64
           satd[ 8x16] |        3.58x |          712.18   |      2548.68
         avg_pp[ 8x16] |        15.54x |         325.71   |      5060.19
 avg_pp_aligned[ 8x16] |        15.39x |         325.72   |      5013.10
            sad[ 8x16] |        3.01x |          239.77   |      722.66
         sad_x3[ 8x16] |        23.44x |         404.19   |      9474.19
         sad_x4[ 8x16] |        83.74x |         530.75   |      44443.92
        copy_pp[ 8x16] |        8.59x |          154.30   |      1325.80
         addAvg[ 8x16] |        10.68x |         441.98   |      4718.99
 addAvg_aligned[ 8x16] |        10.64x |         443.34   |      4718.06
 [i420] copy_pp[  4x8] |        3.46x |          90.95    |      314.71
 [i420]  addAvg[  4x8] |        5.85x |          233.40   |      1365.03
[i420]  addAvg_aligned[  4x8] |         5.87x |          233.60   |      1372.27
    [i420] satd[  4x8] |        5.29x |          252.18   |      1333.89
 [i422] copy_pp[ 4x16] |        3.69x |          170.44   |      628.74
 [i422]  addAvg[ 4x16] |        6.31x |          427.36   |      2696.78
[i422]  addAvg_aligned[ 4x16] |         6.41x |          430.55   |      2759.77
    [i422] satd[ 4x16] |        5.61x |          464.69   |      2606.06
           satd[ 16x4] |        3.21x |          410.21   |      1315.12
         avg_pp[ 16x4] |        17.93x |         130.12   |      2333.18
 avg_pp_aligned[ 16x4] |        17.79x |         131.08   |      2331.39
            sad[ 16x4] |        2.11x |          78.34    |      165.02
         sad_x3[ 16x4] |        9.46x |          147.19   |      1392.43
         sad_x4[ 16x4] |        107.14x |        203.71   |      21825.15
        copy_pp[ 16x4] |        6.88x |          79.53    |      547.24
         addAvg[ 16x4] |        15.20x |         177.81   |      2702.81
 addAvg_aligned[ 16x4] |        14.81x |         181.73   |      2691.91
 [i420] copy_pp[  8x2] |        3.18x |          53.74    |      170.64
 [i420]  addAvg[  8x2] |        7.18x |          100.31   |      720.21
[i420]  addAvg_aligned[  8x2] |         7.63x |          93.95    |      717.08
 [i422] copy_pp[  8x4] |        5.14x |          57.38    |      294.99
 [i422]  addAvg[  8x4] |        8.67x |          147.01   |      1275.03
[i422]  addAvg_aligned[  8x4] |         8.83x |          145.03   |      1281.22
    [i422] satd[  8x4] |        2.53x |          238.92   |      603.79
           satd[16x12] |        3.78x |          1061.19  |      4010.74
         avg_pp[16x12] |        26.64x |         255.20   |      6798.21
 avg_pp_aligned[16x12] |        26.65x |         254.99   |      6795.44
            sad[16x12] |        3.08x |          194.68   |      598.68
         sad_x3[16x12] |        8.07x |          360.11   |      2907.76
         sad_x4[16x12] |        151.82x |        457.21   |      69414.52
        copy_pp[16x12] |        11.75x |         147.13   |      1728.95
         addAvg[16x12] |        18.28x |         459.96   |      8406.37
 addAvg_aligned[16x12] |        18.34x |         458.67   |      8413.08
 [i420] copy_pp[  8x6] |        5.80x |          74.19    |      430.42
 [i420]  addAvg[  8x6] |        11.02x |         168.26   |      1854.51
[i420]  addAvg_aligned[  8x6] |         11.10x |         166.79   |      1851.88
 [i422] copy_pp[ 8x12] |        7.63x |          125.95   |      961.10
 [i422]  addAvg[ 8x12] |        11.02x |         325.74   |      3588.58
[i422]  addAvg_aligned[ 8x12] |         10.98x |         326.16   |      3582.38
    [i422] satd[ 8x12] |        6.91x |          563.75   |      3896.12
           satd[ 4x16] |        6.12x |          426.97   |      2611.98
         avg_pp[ 4x16] |        7.92x |          369.60   |      2927.03
 avg_pp_aligned[ 4x16] |        7.87x |          381.32   |      3001.85
            sad[ 4x16] |        2.97x |          260.67   |      773.12
         sad_x3[ 4x16] |        11.85x |         412.27   |      4886.14
         sad_x4[ 4x16] |        13.49x |         548.01   |      7390.67
        copy_pp[ 4x16] |        4.03x |          151.25   |      610.06
         addAvg[ 4x16] |        6.09x |          425.10   |      2587.91
 addAvg_aligned[ 4x16] |        6.08x |          426.23   |      2592.30
 [i420] copy_pp[  2x8] |        1.94x |          104.34   |      202.73
 [i420]  addAvg[  2x8] |        3.81x |          215.74   |      821.00
[i420]  addAvg_aligned[  2x8] |         3.78x |          216.58   |      819.12
 [i422] copy_pp[ 2x16] |        1.77x |          207.87   |      367.98
 [i422]  addAvg[ 2x16] |        3.73x |          408.73   |      1525.94
[i422]  addAvg_aligned[ 2x16] |         3.75x |          407.67   |      1528.75
           satd[12x16] |        6.50x |          1202.93  |      7816.25
         avg_pp[12x16] |        13.49x |         520.67   |      7024.59
 avg_pp_aligned[12x16] |        13.39x |         529.35   |      7088.41
            sad[12x16] |        5.18x |          367.17   |      1901.11
         sad_x3[12x16] |        19.02x |         725.27   |      13793.73
         sad_x4[12x16] |        76.01x |         917.33   |      69730.76
        copy_pp[12x16] |        6.46x |          293.63   |      1896.66
         addAvg[12x16] |        9.32x |          748.12   |      6975.39
 addAvg_aligned[12x16] |        9.77x |          698.13   |      6820.57
 [i420] copy_pp[  6x8] |        2.71x |          162.92   |      441.30
 [i420]  addAvg[  6x8] |        7.16x |          269.16   |      1927.24
[i420]  addAvg_aligned[  6x8] |         7.19x |          280.57   |      2016.46
 [i422] copy_pp[ 6x16] |        3.12x |          331.07   |      1031.43
 [i422]  addAvg[ 6x16] |        6.39x |          573.90   |      3669.05
[i422]  addAvg_aligned[ 6x16] |         6.35x |          576.15   |      3659.98
           satd[32x32] |        3.72x |          5471.52  |      20351.52
         avg_pp[32x32] |        4.81x |          810.20   |      3900.14
 avg_pp_aligned[32x32] |        4.86x |          840.91   |      4084.16
            sad[32x32] |        5.53x |          770.31   |      4262.78
         sad_x3[32x32] |        7.59x |          1971.58  |      14972.28
         sad_x4[32x32] |        133.14x |        2663.93  |      354669.03
        copy_pp[32x32] |        15.45x |         557.17   |      8606.12
         addAvg[32x32] |        3.62x |          2225.32  |      8058.43
 addAvg_aligned[32x32] |        3.54x |          2216.47  |      7845.03
         sse_pp[32x32] |        4.85x |          2219.00  |      10752.97
         sse_ss[32x32] |        7.28x |          1734.53  |      12622.09
         sub_ps[32x32] |        10.04x |         1887.34  |      18948.21
         add_ps[32x32] |        4.10x |          1458.54  |      5985.56
 add_ps_aligned[32x32] |        4.24x |          1462.37  |      6199.50
        copy_ss[32x32] |        7.96x |          1078.41  |      8580.66
        copy_sp[32x32] |        10.68x |         817.35   |      8731.54
        copy_ps[32x32] |        8.07x |          1066.69  |      8612.63
 [i420] copy_pp[16x16] |        12.61x |         186.75   |      2354.47
 [i420]  addAvg[16x16] |        17.68x |         615.09   |      10875.63
[i420]  addAvg_aligned[16x16] |         17.79x |         616.41   |      
10968.13
    [i420] satd[16x16] |        3.81x |          1400.62  |      5333.00
 [i420] copy_ss[16x16] |        7.50x |          324.81   |      2437.53
 [i420] copy_ps[16x16] |        6.68x |          358.34   |      2393.78
 [i420] copy_sp[16x16] |        9.31x |          246.51   |      2293.90
 [i420]  sub_ps[16x16] |        6.70x |          505.98   |      3389.76
 [i420]  add_ps[16x16] |        4.12x |          436.28   |      1799.37
[i420]  add_ps_aligned[16x16] |         4.11x |          436.99   |      1798.06
    [i420] sa8d[16x16] |        4.13x |          1651.11  |      6812.85
 [i422] copy_pp[16x32] |        14.01x |         332.79   |      4661.24
 [i422]  addAvg[16x32] |        18.78x |         1225.39  |      23012.96
[i422]  addAvg_aligned[16x32] |         17.76x |         1253.66  |      
22264.78
    [i422] satd[16x32] |        3.98x |          2777.82  |      11052.54
 [i422] copy_ss[16x32] |        7.60x |          614.59   |      4673.49
 [i422] copy_ps[16x32] |        7.05x |          662.74   |      4670.40
 [i422] copy_sp[16x32] |        10.00x |         452.86   |      4529.70
  [i422] sse_pp[16x32] |        3.59x |          1065.68  |      3822.47
 [i422]  sub_ps[16x32] |        6.71x |          986.30   |      6619.48
 [i422]  add_ps[16x32] |        4.50x |          818.49   |      3687.08
[i422]  add_ps_aligned[16x32] |         4.48x |          818.14   |      3663.97
    [i422] sa8d[16x32] |        4.09x |          3278.75  |      13406.49
           satd[32x16] |        3.75x |          2760.72  |      10357.71
         avg_pp[32x16] |        5.00x |          425.51   |      2125.67
 avg_pp_aligned[32x16] |        4.79x |          431.86   |      2068.64
            sad[32x16] |        5.80x |          407.43   |      2363.84
         sad_x3[32x16] |        7.36x |          1026.73  |      7554.78
         sad_x4[32x16] |        128.02x |        1402.80  |      179581.48
        copy_pp[32x16] |        15.79x |         273.82   |      4324.18
         addAvg[32x16] |        3.72x |          1115.71  |      4145.12
 addAvg_aligned[32x16] |        3.70x |          1113.77  |      4124.47
 [i420] copy_pp[ 16x8] |        11.44x |         104.82   |      1199.26
 [i420]  addAvg[ 16x8] |        15.99x |         340.00   |      5436.16
[i420]  addAvg_aligned[ 16x8] |         16.77x |         320.81   |      5380.01
    [i420] satd[ 16x8] |        3.54x |          759.22   |      2690.88
 [i422] copy_pp[16x16] |        12.64x |         186.09   |      2352.13
 [i422]  addAvg[16x16] |        18.03x |         614.88   |      11084.68
[i422]  addAvg_aligned[16x16] |         18.16x |         621.18   |      
11279.38
    [i422] satd[16x16] |        3.85x |          1390.59  |      5352.04
           satd[16x32] |        3.73x |          2795.28  |      10425.06
         avg_pp[16x32] |        31.19x |         610.65   |      19043.99
 avg_pp_aligned[16x32] |        31.04x |         616.53   |      19136.33
            sad[16x32] |        2.91x |          535.76   |      1557.77
         sad_x3[16x32] |        8.36x |          935.86   |      7826.39
         sad_x4[16x32] |        157.22x |        1141.67  |      179489.80
        copy_pp[16x32] |        14.28x |         318.51   |      4549.31
         addAvg[16x32] |        18.00x |         1230.17  |      22142.70
 addAvg_aligned[16x32] |        18.41x |         1175.32  |      21641.53
 [i420] copy_pp[ 8x16] |        7.49x |          170.81   |      1278.89
 [i420]  addAvg[ 8x16] |        10.37x |         457.46   |      4744.18
[i420]  addAvg_aligned[ 8x16] |         10.70x |         442.97   |      4739.26
    [i420] satd[ 8x16] |        3.53x |          726.51   |      2561.91
 [i422] copy_pp[ 8x32] |        8.34x |          314.16   |      2620.53
 [i422]  addAvg[ 8x32] |        11.45x |         819.81   |      9385.12
[i422]  addAvg_aligned[ 8x32] |         11.93x |         822.97   |      9813.92
    [i422] satd[ 8x32] |        3.74x |          1388.02  |      5197.44
           satd[ 32x8] |        3.59x |          1450.07  |      5210.18
         avg_pp[ 32x8] |        2.43x |          248.24   |      603.74
 avg_pp_aligned[ 32x8] |        2.45x |          247.39   |      606.40
            sad[ 32x8] |        4.99x |          216.40   |      1078.97
         sad_x3[ 32x8] |        7.90x |          493.37   |      3899.77
         sad_x4[ 32x8] |        134.00x |        647.31   |      86741.77
        copy_pp[ 32x8] |        14.86x |         147.01   |      2183.99
         addAvg[ 32x8] |        3.63x |          585.20   |      2125.70
 addAvg_aligned[ 32x8] |        3.70x |          574.04   |      2126.36
 [i420] copy_pp[ 16x4] |        6.74x |          81.81    |      551.00
 [i420]  addAvg[ 16x4] |        14.64x |         184.37   |      2698.45
[i420]  addAvg_aligned[ 16x4] |         15.08x |         183.20   |      2763.34
    [i420] satd[ 16x4] |        3.43x |          405.43   |      1389.31
 [i422] copy_pp[ 16x8] |        11.44x |         103.85   |      1188.48
 [i422]  addAvg[ 16x8] |        17.17x |         328.49   |      5641.17
[i422]  addAvg_aligned[ 16x8] |         16.64x |         324.22   |      5396.23
    [i422] satd[ 16x8] |        3.57x |          731.35   |      2612.75
           satd[32x24] |        3.72x |          4074.13  |      15163.38
         avg_pp[32x24] |        2.68x |          619.64   |      1660.61
 avg_pp_aligned[32x24] |        2.69x |          618.03   |      1660.61
            sad[32x24] |        5.67x |          581.39   |      3294.30
         sad_x3[32x24] |        7.82x |          1476.25  |      11537.22
         sad_x4[32x24] |        123.69x |        2171.73  |      268624.41
        copy_pp[32x24] |        15.25x |         424.15   |      6466.22
         addAvg[32x24] |        3.58x |          1702.20  |      6100.41
 addAvg_aligned[32x24] |        3.58x |          1683.15  |      6020.77
 [i420] copy_pp[16x12] |        11.11x |         155.56   |      1728.69
 [i420]  addAvg[16x12] |        18.01x |         466.35   |      8396.84
[i420]  addAvg_aligned[16x12] |         17.83x |         474.25   |      8454.91
    [i420] satd[16x12] |        3.68x |          1060.47  |      3904.75
 [i422] copy_pp[16x24] |        14.17x |         241.23   |      3419.26
 [i422]  addAvg[16x24] |        18.15x |         906.87   |      16462.27
[i422]  addAvg_aligned[16x24] |         17.94x |         901.97   |      
16182.90
    [i422] satd[16x24] |        3.67x |          2158.35  |      7928.15
           satd[ 8x32] |        3.67x |          1377.02  |      5055.98
         avg_pp[ 8x32] |        17.25x |         587.31   |      10128.99
 avg_pp_aligned[ 8x32] |        17.75x |         584.34   |      10370.35
            sad[ 8x32] |        2.80x |          530.81   |      1485.77
         sad_x3[ 8x32] |        24.44x |         758.42   |      18535.79
         sad_x4[ 8x32] |        95.10x |         969.67   |      92214.36
        copy_pp[ 8x32] |        8.35x |          318.62   |      2660.49
         addAvg[ 8x32] |        11.31x |         876.56   |      9910.75
 addAvg_aligned[ 8x32] |        10.78x |         867.50   |      9351.44
 [i420] copy_pp[ 4x16] |        3.80x |          175.97   |      668.44
 [i420]  addAvg[ 4x16] |        5.98x |          439.11   |      2626.30
[i420]  addAvg_aligned[ 4x16] |         6.07x |          428.12   |      2599.27
    [i420] satd[ 4x16] |        5.95x |          438.80   |      2609.08
 [i422] copy_pp[ 4x32] |        4.65x |          305.40   |      1420.75
 [i422]  addAvg[ 4x32] |        6.76x |          782.25   |      5291.22
[i422]  addAvg_aligned[ 4x32] |         6.13x |          833.45   |      5105.73
    [i422] satd[ 4x32] |        6.13x |          844.27   |      5173.49
           satd[24x32] |        3.76x |          4117.26  |      15462.04
         avg_pp[24x32] |        2.02x |          1266.73  |      2559.63
 avg_pp_aligned[24x32] |        1.98x |          1265.59  |      2509.96
            sad[24x32] |        4.70x |          791.78   |      3722.46
         sad_x3[24x32] |        5.65x |          2215.74  |      12521.47
         sad_x4[24x32] |        88.44x |         3017.43  |      266872.75
        copy_pp[24x32] |        12.27x |         535.96   |      6574.40
         addAvg[24x32] |        18.58x |         1721.51  |      31982.00
 addAvg_aligned[24x32] |        18.23x |         1753.70  |      31966.61
 [i420] copy_pp[12x16] |        5.98x |          298.01   |      1782.93
 [i420]  addAvg[12x16] |        9.56x |          723.11   |      6916.01
[i420]  addAvg_aligned[12x16] |         9.80x |          702.71   |      6883.89
    [i420] satd[12x16] |        6.45x |          1212.61  |      7824.82
 [i422] copy_pp[12x32] |        6.32x |          558.68   |      3531.87
 [i422]  addAvg[12x32] |        10.06x |         1387.66  |      13963.64
[i422]  addAvg_aligned[12x32] |         9.92x |          1387.35  |      
13759.62
    [i422] satd[12x32] |        6.80x |          2363.69  |      16061.79
           satd[64x64] |        4.08x |          22421.97 |      91370.84
         avg_pp[64x64] |        1.60x |          3181.07  |      5097.75
 avg_pp_aligned[64x64] |        1.67x |          3112.85  |      5188.20
            sad[64x64] |        5.31x |          2404.23  |      12759.11
         sad_x3[64x64] |        7.85x |          6934.15  |      54444.16
         sad_x4[64x64] |        146.11x |        9733.99  |      1422244.75
        copy_pp[64x64] |        1.42x |          2063.38  |      2935.40
         addAvg[64x64] |        4.04x |          8989.90  |      36343.35
 addAvg_aligned[64x64] |        4.07x |          9079.29  |      36934.67
         sse_pp[64x64] |        5.02x |          8805.67  |      44166.03
         sse_ss[64x64] |        8.24x |          6577.86  |      54225.88
         sub_ps[64x64] |        11.57x |         6425.31  |      74362.36
         add_ps[64x64] |        4.61x |          5356.79  |      24680.54
 add_ps_aligned[64x64] |        4.66x |          5343.55  |      24910.88
        copy_ss[64x64] |        0.97x |          5404.74  |      5218.28
        copy_sp[64x64] |        1.92x |          3182.84  |      6113.40
        copy_ps[64x64] |        1.31x |          4419.19  |      5811.03
 [i420] copy_pp[32x32] |        13.80x |         623.39   |      8600.53
 [i420]  addAvg[32x32] |        3.58x |          2226.17  |      7976.33
[i420]  addAvg_aligned[32x32] |         3.52x |          2228.31  |      7842.11
    [i420] satd[32x32] |        3.69x |          5436.26  |      20054.07
 [i420] copy_ss[32x32] |        7.91x |          1107.16  |      8754.08
 [i420] copy_ps[32x32] |        8.26x |          1066.58  |      8808.11
 [i420] copy_sp[32x32] |        10.41x |         821.47   |      8554.76
 [i420]  sub_ps[32x32] |        9.37x |          1979.95  |      18547.86
 [i420]  add_ps[32x32] |        4.17x |          1455.32  |      6063.38
[i420]  add_ps_aligned[32x32] |         4.25x |          1451.28  |      6169.88
    [i420] sa8d[32x32] |        4.12x |          6594.10  |      27163.56
 [i422] copy_pp[32x64] |        15.26x |         1149.02  |      17532.69
 [i422]  addAvg[32x64] |        3.37x |          4642.86  |      15656.39
[i422]  addAvg_aligned[32x64] |         3.40x |          4563.91  |      
15524.98
    [i422] satd[32x64] |        3.83x |          10871.89 |      41654.08
 [i422] copy_ss[32x64] |        7.91x |          2192.04  |      17334.00
 [i422] copy_ps[32x64] |        8.17x |          2114.98  |      17271.42
 [i422] copy_sp[32x64] |        10.94x |         1600.51  |      17511.99
  [i422] sse_pp[32x64] |        5.11x |          4292.34  |      21921.68
 [i422]  sub_ps[32x64] |        9.61x |          3956.48  |      38018.57
 [i422]  add_ps[32x64] |        3.84x |          3124.82  |      11986.28
[i422]  add_ps_aligned[32x64] |         3.99x |          3055.21  |      
12188.06
    [i422] sa8d[32x64] |        4.48x |          13286.38 |      59457.29
           satd[64x32] |        3.81x |          10854.72 |      41323.57
         avg_pp[64x32] |        1.82x |          1560.60  |      2834.43
 avg_pp_aligned[64x32] |        1.83x |          1563.56  |      2867.75
            sad[64x32] |        5.29x |          1217.75  |      6439.34
         sad_x3[64x32] |        7.12x |          3753.81  |      26731.02
         sad_x4[64x32] |        132.19x |        5372.64  |      710225.62
        copy_pp[64x32] |        1.60x |          1040.54  |      1666.71
         addAvg[64x32] |        4.10x |          4505.52  |      18483.64
 addAvg_aligned[64x32] |        4.10x |          4636.37  |      19029.55
 [i420] copy_pp[32x16] |        13.88x |         311.77   |      4328.81
 [i420]  addAvg[32x16] |        3.68x |          1148.85  |      4227.52
[i420]  addAvg_aligned[32x16] |         3.87x |          1118.50  |      4333.56
    [i420] satd[32x16] |        3.74x |          2771.84  |      10353.46
 [i422] copy_pp[32x32] |        14.15x |         607.75   |      8598.80
 [i422]  addAvg[32x32] |        3.48x |          2261.47  |      7865.09
[i422]  addAvg_aligned[32x32] |         3.70x |          2262.76  |      8370.03
    [i422] satd[32x32] |        3.74x |          5445.79  |      20342.58
           satd[32x64] |        3.82x |          10860.62 |      41486.09
         avg_pp[32x64] |        2.46x |          1692.06  |      4155.75
 avg_pp_aligned[32x64] |        2.64x |          1576.02  |      4164.78
            sad[32x64] |        5.36x |          1558.28  |      8348.68
         sad_x3[32x64] |        8.06x |          3929.12  |      31671.88
         sad_x4[32x64] |        136.17x |        5251.57  |      715083.69
        copy_pp[32x64] |        15.08x |         1146.49  |      17285.02
         addAvg[32x64] |        3.39x |          4544.25  |      15383.46
 addAvg_aligned[32x64] |        3.37x |          4562.59  |      15370.40
 [i420] copy_pp[16x32] |        14.80x |         307.38   |      4548.52
 [i420]  addAvg[16x32] |        17.98x |         1217.24  |      21886.27
[i420]  addAvg_aligned[16x32] |         18.34x |         1178.97  |      
21618.69
    [i420] satd[16x32] |        3.87x |          2722.97  |      10548.83
 [i422] copy_pp[16x64] |        14.78x |         627.17   |      9266.67
 [i422]  addAvg[16x64] |        18.97x |         2317.64  |      43971.58
[i422]  addAvg_aligned[16x64] |         19.11x |         2352.94  |      
44960.16
    [i422] satd[16x64] |        3.79x |          5416.59  |      20553.94
           satd[64x16] |        3.74x |          5561.60  |      20809.16
         avg_pp[64x16] |        1.77x |          802.10   |      1416.63
 avg_pp_aligned[64x16] |        1.78x |          794.38   |      1410.62
            sad[64x16] |        5.42x |          625.51   |      3388.36
         sad_x3[64x16] |        6.68x |          2032.70  |      13579.82
         sad_x4[64x16] |        119.33x |        2993.22  |      357167.56
        copy_pp[64x16] |        1.24x |          534.26   |      662.63
         addAvg[64x16] |        4.33x |          2148.32  |      9311.71
 addAvg_aligned[64x16] |        4.39x |          2142.49  |      9398.79
 [i420] copy_pp[ 32x8] |        14.67x |         148.99   |      2185.91
 [i420]  addAvg[ 32x8] |        3.70x |          578.59   |      2141.86
[i420]  addAvg_aligned[ 32x8] |         3.69x |          586.52   |      2164.42
    [i420] satd[ 32x8] |        3.45x |          1478.27  |      5100.24
 [i422] copy_pp[32x16] |        13.88x |         317.00   |      4399.82
 [i422]  addAvg[32x16] |        3.62x |          1147.84  |      4155.15
[i422]  addAvg_aligned[32x16] |         3.60x |          1180.65  |      4248.76
    [i422] satd[32x16] |        3.81x |          2767.46  |      10553.88
           satd[64x48] |        3.79x |          16393.19 |      62156.74
         avg_pp[64x48] |        1.62x |          2449.73  |      3961.85
 avg_pp_aligned[64x48] |        1.70x |          2318.60  |      3937.42
            sad[64x48] |        5.29x |          1806.23  |      9546.46
         sad_x3[64x48] |        7.62x |          5371.85  |      40951.99
         sad_x4[64x48] |        156.17x |        7601.26  |      1187121.25
        copy_pp[64x48] |        1.42x |          1671.48  |      2371.65
         addAvg[64x48] |        4.02x |          6957.03  |      27943.84
 addAvg_aligned[64x48] |        4.16x |          6718.38  |      27921.21
 [i420] copy_pp[32x24] |        14.03x |         462.75   |      6492.49
 [i420]  addAvg[32x24] |        3.70x |          1705.58  |      6307.33
[i420]  addAvg_aligned[32x24] |         3.58x |          1682.11  |      6019.07
    [i420] satd[32x24] |        3.64x |          4159.31  |      15145.68
 [i422] copy_pp[32x48] |        15.61x |         862.71   |      13467.25
 [i422]  addAvg[32x48] |        3.48x |          3431.92  |      11958.51
[i422]  addAvg_aligned[32x48] |         3.62x |          3316.03  |      
11997.87
    [i422] satd[32x48] |        3.82x |          8141.35  |      31137.22
           satd[16x64] |        3.81x |          5424.73  |      20656.60
         avg_pp[16x64] |        30.23x |         1238.44  |      37441.53
 avg_pp_aligned[16x64] |        30.52x |         1237.53  |      37775.50
            sad[16x64] |        3.22x |          1036.91  |      3333.75
         sad_x3[16x64] |        7.33x |          1938.42  |      14210.21
         sad_x4[16x64] |        163.54x |        2255.22  |      368814.94
        copy_pp[16x64] |        14.19x |         651.08   |      9236.27
         addAvg[16x64] |        18.74x |         2357.28  |      44166.82
 addAvg_aligned[16x64] |        18.09x |         2415.37  |      43699.52
 [i420] copy_pp[ 8x32] |        8.11x |          306.26   |      2484.32
 [i420]  addAvg[ 8x32] |        11.41x |         822.97   |      9386.08
[i420]  addAvg_aligned[ 8x32] |         11.50x |         820.19   |      9432.01
    [i420] satd[ 8x32] |        3.84x |          1388.03  |      5333.81
 [i422] copy_pp[ 8x64] |        8.59x |          632.71   |      5437.61
 [i422]  addAvg[ 8x64] |        11.79x |         1649.54  |      19448.68
[i422]  addAvg_aligned[ 8x64] |         11.75x |         1597.33  |      
18772.71
    [i422] satd[ 8x64] |        3.68x |          2754.57  |      10136.62
           satd[48x64] |        3.89x |          16242.04 |      63106.50
         avg_pp[48x64] |        1.85x |          2651.85  |      4912.36
 avg_pp_aligned[48x64] |        1.84x |          2521.15  |      4642.08
            sad[48x64] |        5.38x |          2140.16  |      11518.94
         sad_x3[48x64] |        8.54x |          5094.55  |      43494.28
         sad_x4[48x64] |        163.06x |        7042.83  |      1148368.12
        copy_pp[48x64] |        1.85x |          1646.51  |      3046.28
         addAvg[48x64] |        4.69x |          6132.14  |      28754.97
 addAvg_aligned[48x64] |        4.51x |          6469.15  |      29196.08
 [i420] copy_pp[24x32] |        11.69x |         600.41   |      7016.30
 [i420]  addAvg[24x32] |        18.30x |         1858.64  |      34007.53
[i420]  addAvg_aligned[24x32] |         17.98x |         1843.20  |      
33136.05
    [i420] satd[24x32] |        3.58x |          4270.17  |      15271.44
 [i422] copy_pp[24x64] |        12.10x |         1083.30  |      13107.83
 [i422]  addAvg[24x64] |        18.12x |         3577.91  |      64820.08
[i422]  addAvg_aligned[24x64] |         17.41x |         3690.49  |      
64241.30
    [i422] satd[24x64] |        3.73x |          8378.28  |      31254.23
            ssd_s[4x4] |        3.00x |          83.40    |      250.18
             sa8d[4x4] |        3.99x |          155.06   |      618.83
         residual[4x4] |        2.78x |          100.40   |      279.02
 residual_aligned[4x4] |        2.77x |          102.58   |      284.43
          blkfill[4x4] |        1.90x |          55.76    |      105.98
  blkfill_aligned[4x4] |        1.78x |          56.68    |      100.66
        transpose[4x4] |        2.84x |          59.67    |      169.43
    cpy2Dto1D_shl[4x4] |        2.98x |          76.49    |      228.26
    cpy2Dto1D_shr[4x4] |        3.29x |          87.25    |      286.65
    cpy1Dto2D_shl[4x4] |        2.97x |          75.28    |      223.69
cpy1Dto2D_shl_aligned[4x4] |    2.99x |          74.53    |      223.21
    cpy1Dto2D_shr[4x4] |        3.21x |          84.95    |      272.84
         copy_cnt[4x4] |        5.36x |          82.50    |      441.82
      psy_cost_pp[4x4] |        5.24x |          297.60   |      1559.49
            ssd_s[8x8] |        2.89x |          107.42   |      310.36
             sa8d[8x8] |        4.07x |          448.77   |      1825.45
         residual[8x8] |        4.93x |          178.35   |      879.00
 residual_aligned[8x8] |        4.92x |          178.16   |      877.36
          blkfill[8x8] |        1.48x |          78.70    |      116.68
  blkfill_aligned[8x8] |        1.36x |          79.31    |      107.62
        transpose[8x8] |        5.07x |          109.29   |      554.34
              var[8x8] |        8.20x |          201.51   |      1652.01
    cpy2Dto1D_shl[8x8] |        5.83x |          135.33   |      788.58
    cpy2Dto1D_shr[8x8] |        13.91x |         161.05   |      2239.96
    cpy1Dto2D_shl[8x8] |        6.15x |          113.79   |      700.40
cpy1Dto2D_shl_aligned[8x8] |    6.56x |          111.90   |      733.48
    cpy1Dto2D_shr[8x8] |        15.64x |         140.09   |      2191.40
         copy_cnt[8x8] |        8.92x |          129.21   |      1152.82
      psy_cost_pp[8x8] |        4.66x |          772.59   |      3603.86
          ssd_s[16x16] |        2.56x |          307.33   |      786.15
           sa8d[16x16] |        4.02x |          1673.28  |      6719.79
       residual[16x16] |        6.73x |          493.76   |      3321.33
residual_aligned[16x16] |       6.56x |          506.52   |      3321.61
        blkfill[16x16] |        1.03x |          270.03   |      278.88
blkfill_aligned[16x16] |        1.06x |          270.03   |      286.13
      transpose[16x16] |        5.88x |          414.19   |      2434.85
            var[16x16] |        14.86x |         547.44   |      8135.48
  cpy2Dto1D_shl[16x16] |        8.10x |          375.98   |      3047.12
  cpy2Dto1D_shr[16x16] |        18.76x |         474.72   |      8905.63
  cpy1Dto2D_shl[16x16] |        7.94x |          388.65   |      3084.21
cpy1Dto2D_shl_aligned[16x16] |  7.98x |          386.95   |      3085.99
  cpy1Dto2D_shr[16x16] |        19.06x |         472.37   |      9004.94
       copy_cnt[16x16] |        11.19x |         380.02   |      4251.58
    psy_cost_pp[16x16] |        5.53x |          3220.74  |      17816.96
          ssd_s[32x32] |        2.07x |          1069.77  |      2213.55
           sa8d[32x32] |        4.10x |          6577.27  |      26991.19
       residual[32x32] |        1.79x |          1678.39  |      3006.34
residual_aligned[32x32] |       1.80x |          1672.24  |      3004.84
        blkfill[32x32] |        1.07x |          1046.51  |      1118.51
blkfill_aligned[32x32] |        1.02x |          1100.04  |      1118.00
      transpose[32x32] |        5.68x |          1948.83  |      11078.95
            var[32x32] |        4.01x |          2000.43  |      8016.67
  cpy2Dto1D_shl[32x32] |        4.71x |          1430.59  |      6736.23
  cpy2Dto1D_shr[32x32] |        5.18x |          1688.51  |      8739.90
  cpy1Dto2D_shl[32x32] |        5.16x |          1302.71  |      6716.02
cpy1Dto2D_shl_aligned[32x32] |  4.78x |          1385.59  |      6624.78
  cpy1Dto2D_shr[32x32] |        5.36x |          1569.45  |      8415.84
       copy_cnt[32x32] |        8.36x |          1221.26  |      10206.91
    psy_cost_pp[32x32] |        6.50x |          12233.78 |      79517.37
           sa8d[64x64] |        3.96x |          27521.11 |      109104.11
      transpose[64x64] |        5.59x |          7362.50  |      41186.68
            var[64x64] |        3.36x |          7536.13  |      25345.79
    psy_cost_pp[64x64] |        6.56x |          50179.54 |      329384.62
      weight_pp[w0=64] |        2.12x |          6396.51  |      13548.53
     weight_pp[w0=127] |        2.15x |          6294.20  |      13556.42
             weight_sp |        2.56x |          6999.11  |      17884.08
             downscale |        33.51x |         32385.01 |      1085168.75
       scale1D_128to64 |        12.85x |         283.94   |      3648.40
scale1D_128to64_aligned |       13.16x |         274.64   |      3613.90
        scale2D_64to32 |        4.70x |          6932.50  |      32559.99
       ssim_4x4x2_core |        9.89x |          210.65   |      2084.14
            ssim_end_4 |        3.71x |          207.51   |      769.64
               calSign |        2.54x |          236.50   |      600.81
              SAO_EO_0 |        10.16x |         914.07   |      9283.05
              SAO_EO_1 |        15.18x |         370.32   |      5619.87
        SAO_EO_1_2Rows |        22.11x |         600.46   |      13278.42
           SAO_EO_2[0] |        9.14x |          139.74   |      1276.94
           SAO_EO_2[1] |        7.98x |          626.34   |      4995.53
           SAO_EO_3[0] |        10.57x |         173.55   |      1835.21
           SAO_EO_3[1] |        9.73x |          695.77   |      6769.34
              SAO_BO_0 |        10.08x |         14240.17 |      143522.67
          saoCuStatsE0 |        1.78x |          129675.38 |     230915.30
          saoCuStatsE1 |        2.85x |          129834.23 |     370069.44
          saoCuStatsE2 |        3.14x |          136667.72 |     428596.47
          saoCuStatsE3 |        4.01x |          128496.16 |     515875.53
          planecopy_sp |        2.87x |          6844.81  |      19651.95
         propagateCost |        1.20x |          4407.33  |      5306.66
        cuTreeFix8Pack |        1.64x |          3755.72  |      6153.20
      cuTreeFix8Unpack |        1.69x |          3768.97  |      6368.94
           scanPosLast |        2.44x |          29771.41 |      72788.71
findPosFirstLast[SCAN_DIAG] |   5.38x |          123.99   |      666.85
findPosFirstLast[SCAN_HOR] |    6.11x |          120.72   |      737.00
findPosFirstLast[SCAN_VER] |    4.98x |          122.90   |      611.96
          costCoeffNxN |        3.28x |          1228.14  |      4025.92
       costCoeffRemain |        1.74x |          455.64   |      792.31
          costC1C2Flag |        1.20x |          750.53   |      902.33
pelFilterLumaStrong_Vertical |  4.34x |          492.41   |      2136.55
pelFilterLumaStrong_Horizontal |        6.18x |          363.86   |      2249.25
pelFilterChroma_Vertical[MaskP: -1, MaskQ: -1] |        2.19x |          246.27 
  |      538.96
pelFilterChroma_Vertical[MaskP: -1, MaskQ: 0] |         2.17x |          246.19 
  |      535.12
pelFilterChroma_Vertical[MaskP: 0, MaskQ: -1] |         2.27x |          246.18 
  |      559.98
pelFilterChroma_Horizontal[MaskP: -1, MaskQ: -1] |      4.33x |          160.36 
  |      693.76
pelFilterChroma_Horizontal[MaskP: -1, MaskQ: 0] |       4.58x |          151.19 
  |      692.43
pelFilterChroma_Horizontal[MaskP: 0, MaskQ: -1] |       4.58x |          151.22 
  |      692.66
== transforms primitives ==
dst4x4   |      4.61x |          368.09   |      1696.73
dct4x4           |      4.18x |          383.81   |      1603.59
dct8x8           |      4.74x |          1677.61  |      7955.31
dct16x16         |      4.72x |          13931.26 |      65748.16
dct32x32         |      2.63x |          109166.12 |     287413.25
idst4x4  |      3.01x |          426.34   |      1284.95
idct4x4          |      7.12x |          237.32   |      1689.36
idct8x8          |      5.61x |          1359.34  |      7629.15
idct16x16        |      4.38x |          8582.83  |      37603.48
idct32x32        |      4.07x |          60405.33 |      245649.88
dequant_normal   |      2.94x |          4691.93  |      13773.52
dequant_scaling  |      3.95x |          6800.87  |      26855.33
quant            |      1.69x |          15425.11 |      26064.02
nquant           |      5.01x |          8763.86  |      43923.98
count_nonzero[4x4] |    2.13x |          57.71    |      123.08
count_nonzero[8x8] |    3.09x |          103.32   |      319.46
count_nonzero[16x16] |  5.11x |          248.05   |      1266.49
count_nonzero[32x32] |  5.66x |          819.10   |      4639.96
denoiseDct       |      3.38x |          6441.36  |      21785.86
== interp primitives ==
luma_hpp[  4x4]  |      8.94x |          282.84   |      2527.35
luma_hps[  4x4]  |      5.41x |          685.81   |      3711.20
luma_vpp[  4x4]  |      10.70x |         257.34   |      2753.99
luma_vps[  4x4]  |      9.28x |          259.00   |      2404.42
luma_vsp[  4x4]  |      7.92x |          340.60   |      2697.29
luma_vss[  4x4]  |      5.81x |          319.95   |      1858.77
luma_hv [  4x4]  |      4.66x |          1086.79  |      5069.26
convert_p2s[  4x4]       |      2.60x |          87.47    |      227.65
convert_p2s_aligned[  4x4]       |      3.53x |          91.68    |      323.88
luma_hpp[  8x8]  |      7.41x |          572.74   |      4243.61
luma_hps[  8x8]  |      4.18x |          1354.20  |      5654.31
luma_vpp[  8x8]  |      27.83x |         485.31   |      13507.87
luma_vps[  8x8]  |      22.24x |         517.67   |      11510.71
luma_vsp[  8x8]  |      13.11x |         1160.32  |      15207.73
luma_vss[  8x8]  |      14.75x |         1037.27  |      15296.75
luma_hv [  8x8]  |      3.36x |          2103.57  |      7067.86
convert_p2s[  8x8]       |      5.34x |          153.11   |      817.65
convert_p2s_aligned[  8x8]       |      5.33x |          155.17   |      826.44
luma_hpp[16x16]  |      3.94x |          1997.31  |      7878.18
luma_hps[16x16]  |      1.29x |          3701.13  |      4781.26
luma_vpp[16x16]  |      3.96x |          1877.85  |      7431.22
luma_vps[16x16]  |      1.99x |          1882.20  |      3748.72
luma_vsp[16x16]  |      2.98x |          4089.06  |      12199.17
luma_vss[16x16]  |      3.29x |          3558.67  |      11722.71
luma_hv [16x16]  |      3.31x |          8012.86  |      26528.43
convert_p2s[16x16]       |      6.64x |          467.87   |      3104.32
convert_p2s_aligned[16x16]       |      6.77x |          458.72   |      3106.17
luma_hpp[32x32]  |      4.00x |          8038.13  |      32127.11
luma_hps[32x32]  |      1.22x |          11802.65 |      14442.64
luma_vpp[32x32]  |      4.25x |          7187.02  |      30523.57
luma_vps[32x32]  |      1.63x |          7286.59  |      11858.39
luma_vsp[32x32]  |      3.01x |          16184.98 |      48743.82
luma_vss[32x32]  |      3.42x |          13831.33 |      47243.70
luma_hv [32x32]  |      3.38x |          28616.25 |      96692.09
convert_p2s[32x32]       |      1.65x |          1523.53  |      2506.47
convert_p2s_aligned[32x32]       |      1.67x |          1531.22  |      2552.78
luma_hpp[64x64]  |      4.32x |          29516.29 |      127532.86
luma_hps[64x64]  |      1.73x |          43778.96 |      75952.23
luma_vpp[64x64]  |      3.94x |          29820.82 |      117462.16
luma_vps[64x64]  |      2.17x |          29538.25 |      64193.76
luma_vsp[64x64]  |      2.72x |          69038.90 |      187513.80
luma_vss[64x64]  |      3.20x |          58295.77 |      186473.12
luma_hv [64x64]  |      3.46x |          113679.78 |     393416.03
convert_p2s[64x64]       |      1.29x |          6103.85  |      7882.35
convert_p2s_aligned[64x64]       |      1.29x |          6098.03  |      7844.04
luma_hpp[  8x4]  |      6.99x |          325.15   |      2272.64
luma_hps[  8x4]  |      4.10x |          1046.72  |      4287.22
luma_vpp[  8x4]  |      23.89x |         301.84   |      7211.42
luma_vps[  8x4]  |      16.87x |         296.78   |      5005.38
luma_vsp[  8x4]  |      12.49x |         615.56   |      7686.18
luma_vss[  8x4]  |      9.23x |          565.91   |      5223.32
luma_hv [  8x4]  |      2.46x |          1744.10  |      4289.47
convert_p2s[  8x4]       |      3.76x |          109.81   |      412.44
convert_p2s_aligned[  8x4]       |      3.70x |          112.62   |      416.42
luma_hpp[  4x8]  |      8.86x |          547.68   |      4853.78
luma_hps[  4x8]  |      5.38x |          961.25   |      5167.03
luma_vpp[  4x8]  |      11.74x |         451.34   |      5296.43
luma_vps[  4x8]  |      10.97x |         431.66   |      4735.33
luma_vsp[  4x8]  |      8.13x |          648.56   |      5272.56
luma_vss[  4x8]  |      6.18x |          607.16   |      3753.10
luma_hv [  4x8]  |      4.77x |          1668.12  |      7963.69
convert_p2s[  4x8]       |      3.45x |          128.95   |      444.38
convert_p2s_aligned[  4x8]       |      3.15x |          140.39   |      442.58
luma_hpp[ 16x8]  |      3.92x |          1085.16  |      4257.07
luma_hps[ 16x8]  |      1.33x |          2533.44  |      3364.75
luma_vpp[ 16x8]  |      4.09x |          1038.86  |      4245.04
luma_vps[ 16x8]  |      2.21x |          1022.15  |      2259.51
luma_vsp[ 16x8]  |      3.03x |          2205.76  |      6688.89
luma_vss[ 16x8]  |      3.38x |          1932.85  |      6524.65
luma_hv [ 16x8]  |      2.87x |          4842.30  |      13879.48
convert_p2s[ 16x8]       |      6.07x |          256.90   |      1558.54
convert_p2s_aligned[ 16x8]       |      6.11x |          253.56   |      1549.96
luma_hpp[ 8x16]  |      7.52x |          1163.60  |      8746.71
luma_hps[ 8x16]  |      4.26x |          2123.80  |      9043.80
luma_vpp[ 8x16]  |      30.09x |         964.86   |      29029.11
luma_vps[ 8x16]  |      23.39x |         966.55   |      22612.36
luma_vsp[ 8x16]  |      13.46x |         2244.59  |      30211.93
luma_vss[ 8x16]  |      15.33x |         1984.11  |      30424.25
luma_hv [ 8x16]  |      3.09x |          4420.99  |      13655.97
convert_p2s[ 8x16]       |      6.18x |          271.02   |      1674.65
convert_p2s_aligned[ 8x16]       |      6.12x |          270.79   |      1656.49
luma_hpp[32x16]  |      4.22x |          3907.06  |      16480.89
luma_hps[32x16]  |      1.19x |          7221.19  |      8591.75
luma_vpp[32x16]  |      4.06x |          3830.68  |      15539.20
luma_vps[32x16]  |      1.73x |          3802.89  |      6593.98
luma_vsp[32x16]  |      2.80x |          8299.99  |      23266.83
luma_vss[32x16]  |      3.29x |          6934.04  |      22815.95
luma_hv [32x16]  |      3.14x |          15190.08 |      47689.76
convert_p2s[32x16]       |      1.54x |          788.29   |      1210.12
convert_p2s_aligned[32x16]       |      1.55x |          778.75   |      1209.80
luma_hpp[16x32]  |      3.68x |          4365.38  |      16045.29
luma_hps[16x32]  |      1.36x |          6378.32  |      8683.26
luma_vpp[16x32]  |      3.82x |          3688.63  |      14080.64
luma_vps[16x32]  |      1.90x |          3692.79  |      7029.41
luma_vsp[16x32]  |      2.90x |          8185.89  |      23732.82
luma_vss[16x32]  |      3.29x |          7045.60  |      23182.95
luma_hv [16x32]  |      3.26x |          14627.79 |      47659.75
convert_p2s[16x32]       |      6.63x |          854.76   |      5666.93
convert_p2s_aligned[16x32]       |      6.66x |          855.89   |      5704.42
luma_hpp[64x32]  |      4.40x |          14129.91 |      62226.44
luma_hps[64x32]  |      1.75x |          22529.53 |      39363.57
luma_vpp[64x32]  |      4.05x |          14069.45 |      57034.71
luma_vps[64x32]  |      2.21x |          14120.00 |      31227.11
luma_vsp[64x32]  |      2.75x |          33397.93 |      92004.63
luma_vss[64x32]  |      3.25x |          27767.74 |      90290.77
luma_hv [64x32]  |      3.43x |          58691.05 |      201324.58
convert_p2s[64x32]       |      1.34x |          2958.45  |      3966.42
convert_p2s_aligned[64x32]       |      1.34x |          2929.46  |      3937.06
luma_hpp[32x64]  |      4.32x |          15018.57 |      64864.78
luma_hps[32x64]  |      1.22x |          20949.30 |      25651.62
luma_vpp[32x64]  |      4.15x |          14424.02 |      59813.49
luma_vps[32x64]  |      1.63x |          14192.96 |      23137.44
luma_vsp[32x64]  |      2.69x |          33919.93 |      91309.66
luma_vss[32x64]  |      3.24x |          28242.01 |      91537.22
luma_hv [32x64]  |      3.37x |          56239.20 |      189361.70
convert_p2s[32x64]       |      1.62x |          2977.67  |      4816.51
convert_p2s_aligned[32x64]       |      1.52x |          2983.77  |      4538.58
luma_hpp[16x12]  |      4.00x |          1503.56  |      6019.81
luma_hps[16x12]  |      1.35x |          3167.15  |      4260.66
luma_vpp[16x12]  |      3.94x |          1516.85  |      5976.93
luma_vps[16x12]  |      2.10x |          1484.40  |      3113.15
luma_vsp[16x12]  |      2.97x |          3280.02  |      9744.56
luma_vss[16x12]  |      3.39x |          2693.80  |      9133.75
luma_hv [16x12]  |      2.97x |          6313.85  |      18740.97
convert_p2s[16x12]       |      6.38x |          335.65   |      2139.93
convert_p2s_aligned[16x12]       |      6.38x |          336.51   |      2147.78
luma_hpp[12x16]  |      10.17x |         2178.54  |      22150.00
luma_hps[12x16]  |      3.94x |          3104.83  |      12226.08
luma_vpp[12x16]  |      25.57x |         1651.71  |      42231.89
luma_vps[12x16]  |      19.63x |         1633.01  |      32063.43
luma_vsp[12x16]  |      14.44x |         3091.58  |      44633.90
luma_vss[12x16]  |      16.73x |         2707.27  |      45286.30
luma_hv [12x16]  |      13.17x |         6233.21  |      82100.25
convert_p2s[12x16]       |      6.10x |          383.43   |      2337.96
convert_p2s_aligned[12x16]       |      5.93x |          394.94   |      2341.47
luma_hpp[ 16x4]  |      3.94x |          534.87   |      2109.82
luma_hps[ 16x4]  |      1.32x |          1795.29  |      2377.06
luma_vpp[ 16x4]  |      4.19x |          523.78   |      2196.09
luma_vps[ 16x4]  |      3.95x |          520.06   |      2054.73
luma_vsp[ 16x4]  |      3.12x |          1075.74  |      3354.44
luma_vss[ 16x4]  |      3.01x |          948.46   |      2853.73
luma_hv [ 16x4]  |      2.54x |          2966.84  |      7545.43
convert_p2s[ 16x4]       |      5.70x |          135.16   |      770.58
convert_p2s_aligned[ 16x4]       |      5.41x |          146.91   |      795.27
luma_hpp[ 4x16]  |      9.35x |          979.60   |      9155.87
luma_hps[ 4x16]  |      5.57x |          1366.40  |      7613.96
luma_vpp[ 4x16]  |      12.48x |         781.93   |      9756.55
luma_vps[ 4x16]  |      12.32x |         729.29   |      8981.91
luma_vsp[ 4x16]  |      8.40x |          1152.84  |      9685.43
luma_vss[ 4x16]  |      6.75x |          1025.61  |      6927.61
luma_hv [ 4x16]  |      4.99x |          2647.30  |      13218.18
convert_p2s[ 4x16]       |      4.15x |          256.52   |      1063.35
convert_p2s_aligned[ 4x16]       |      4.08x |          244.80   |      999.98
luma_hpp[32x24]  |      4.19x |          5532.64  |      23167.06
luma_hps[32x24]  |      1.25x |          9262.76  |      11589.32
luma_vpp[32x24]  |      4.06x |          5417.86  |      21996.99
luma_vps[32x24]  |      1.64x |          5540.25  |      9088.42
luma_vsp[32x24]  |      2.93x |          12282.36 |      35990.47
luma_vss[32x24]  |      3.31x |          10426.79 |      34480.43
luma_hv [32x24]  |      3.37x |          21980.45 |      74047.79
convert_p2s[32x24]       |      1.57x |          1204.00  |      1885.82
convert_p2s_aligned[32x24]       |      1.56x |          1195.50  |      1860.48
luma_hpp[24x32]  |      4.69x |          5825.03  |      27324.77
luma_hps[24x32]  |      1.30x |          9063.26  |      11772.40
luma_vpp[24x32]  |      3.92x |          5403.27  |      21192.22
luma_vps[24x32]  |      1.75x |          5511.71  |      9621.50
luma_vsp[24x32]  |      2.91x |          12306.06 |      35823.25
luma_vss[24x32]  |      3.31x |          10673.59 |      35301.80
luma_hv [24x32]  |      3.43x |          21314.36 |      73018.46
convert_p2s[24x32]       |      6.96x |          1157.98  |      8059.17
convert_p2s_aligned[24x32]       |      7.46x |          1084.08  |      8087.28
luma_hpp[ 32x8]  |      4.19x |          1881.04  |      7884.27
luma_hps[ 32x8]  |      1.25x |          4452.71  |      5566.61
luma_vpp[ 32x8]  |      4.25x |          1836.55  |      7797.08
luma_vps[ 32x8]  |      1.84x |          1818.20  |      3339.44
luma_vsp[ 32x8]  |      2.80x |          4211.07  |      11795.68
luma_vss[ 32x8]  |      3.28x |          3530.58  |      11563.69
luma_hv [ 32x8]  |      3.11x |          8587.64  |      26674.25
convert_p2s[ 32x8]       |      3.65x |          428.08   |      1561.08
convert_p2s_aligned[ 32x8]       |      3.63x |          429.30   |      1559.89
luma_hpp[ 8x32]  |      7.06x |          2470.91  |      17447.44
luma_hps[ 8x32]  |      4.08x |          3709.01  |      15121.15
luma_vpp[ 8x32]  |      33.15x |         1727.19  |      57261.53
luma_vps[ 8x32]  |      23.35x |         1866.01  |      43569.57
luma_vsp[ 8x32]  |      14.17x |         4295.83  |      60875.44
luma_vss[ 8x32]  |      15.79x |         3679.13  |      58075.52
luma_hv [ 8x32]  |      3.22x |          8022.94  |      25871.75
convert_p2s[ 8x32]       |      6.72x |          459.73   |      3087.79
convert_p2s_aligned[ 8x32]       |      6.79x |          452.88   |      3073.56
luma_hpp[64x48]  |      4.36x |          21430.12 |      93490.22
luma_hps[64x48]  |      1.72x |          33212.25 |      57249.29
luma_vpp[64x48]  |      4.08x |          21340.95 |      86988.70
luma_vps[64x48]  |      2.26x |          21268.24 |      48120.36
luma_vsp[64x48]  |      2.93x |          51033.72 |      149741.03
luma_vss[64x48]  |      3.27x |          43596.46 |      142548.77
luma_hv [64x48]  |      3.42x |          83413.36 |      285672.00
convert_p2s[64x48]       |      1.32x |          4328.30  |      5700.14
convert_p2s_aligned[64x48]       |      1.30x |          4396.74  |      5711.18
luma_hpp[48x64]  |      4.48x |          21250.46 |      95122.71
luma_hps[48x64]  |      1.74x |          31059.16 |      54168.04
luma_vpp[48x64]  |      3.92x |          21385.30 |      83931.90
luma_vps[48x64]  |      2.20x |          21231.09 |      46690.36
luma_vsp[48x64]  |      2.78x |          49682.95 |      138182.19
luma_vss[48x64]  |      3.18x |          42452.43 |      135132.58
luma_hv [48x64]  |      3.51x |          83129.43 |      291552.41
convert_p2s[48x64]       |      1.57x |          3907.33  |      6119.09
convert_p2s_aligned[48x64]       |      1.62x |          3924.19  |      6374.46
luma_hpp[64x16]  |      4.63x |          6952.68  |      32225.42
luma_hps[64x16]  |      1.73x |          13240.00 |      22923.05
luma_vpp[64x16]  |      4.11x |          7089.76  |      29173.38
luma_vps[64x16]  |      2.20x |          7039.99  |      15466.75
luma_vsp[64x16]  |      2.86x |          16189.87 |      46269.36
luma_vss[64x16]  |      3.33x |          13798.35 |      45902.35
luma_hv [64x16]  |      3.22x |          30608.42 |      98460.23
convert_p2s[64x16]       |      1.26x |          1546.03  |      1945.30
convert_p2s_aligned[64x16]       |      1.44x |          1497.75  |      2154.38
luma_hpp[16x64]  |      3.82x |          8322.17  |      31785.29
luma_hps[16x64]  |      1.29x |          11486.48 |      14847.82
luma_vpp[16x64]  |      3.83x |          7385.62  |      28257.29
luma_vps[16x64]  |      1.87x |          7292.69  |      13656.62
luma_vsp[16x64]  |      3.06x |          16177.80 |      49520.88
luma_vss[16x64]  |      3.39x |          14109.53 |      47819.61
luma_hv [16x64]  |      3.39x |          28667.29 |      97146.01
convert_p2s[16x64]       |      7.09x |          1578.04  |      11180.61
convert_p2s_aligned[16x64]       |      7.02x |          1600.54  |      
11234.29
= Color Space i420 =
chroma_hpp[  4x4] |     7.85x |          147.58   |      1158.04
chroma_hps[  4x4] |     4.33x |          313.44   |      1357.98
chroma_vpp[  4x4] |     5.58x |          175.41   |      979.24
chroma_vps[  4x4] |     4.80x |          159.05   |      762.88
chroma_vsp[  4x4] |     3.99x |          235.37   |      938.24
chroma_vss[  4x4] |     3.77x |          212.98   |      803.62
chroma_p2s[  4x4]        |      2.71x |          89.92    |      243.44
chroma_p2s_aligned[  4x4]        |      2.68x |          90.74    |      243.05
chroma_hpp[  8x8] |     10.22x |         445.45   |      4552.71
chroma_hps[  8x8] |     6.54x |          544.90   |      3564.60
chroma_vpp[  8x8] |     12.67x |         276.69   |      3506.21
chroma_vps[  8x8] |     9.32x |          272.50   |      2539.48
chroma_vsp[  8x8] |     5.60x |          577.22   |      3234.69
chroma_vss[  8x8] |     4.94x |          516.45   |      2552.83
chroma_p2s[  8x8]        |      5.50x |          149.12   |      820.31
chroma_p2s_aligned[  8x8]        |      5.48x |          149.79   |      820.27
chroma_hpp[16x16] |     3.56x |          1267.89  |      4513.88
chroma_hps[16x16] |     1.73x |          1507.27  |      2612.00
chroma_vpp[16x16] |     10.05x |         987.37   |      9920.50
chroma_vps[16x16] |     2.42x |          1000.90  |      2422.12
chroma_vsp[16x16] |     4.47x |          2896.68  |      12946.05
chroma_vss[16x16] |     1.91x |          2274.08  |      4350.35
chroma_p2s[16x16]        |      6.57x |          443.57   |      2915.97
chroma_p2s_aligned[16x16]        |      6.58x |          443.57   |      2916.84
chroma_hpp[32x32] |     4.32x |          4733.25  |      20436.93
chroma_hps[32x32] |     1.42x |          5269.97  |      7475.04
chroma_vpp[32x32] |     9.08x |          4041.48  |      36698.39
chroma_vps[32x32] |     1.62x |          4252.14  |      6901.55
chroma_vsp[32x32] |     4.21x |          10654.50 |      44820.09
chroma_vss[32x32] |     2.21x |          8696.43  |      19236.06
chroma_p2s[32x32]        |      1.49x |          1550.98  |      2312.40
chroma_p2s_aligned[32x32]        |      1.63x |          1527.21  |      2482.59
chroma_hpp[  4x2] |     7.23x |          91.41    |      660.75
chroma_hps[  4x2] |     4.42x |          226.72   |      1001.32
chroma_vpp[  4x2] |     5.81x |          119.87   |      695.94
chroma_vps[  4x2] |     3.65x |          108.99   |      397.35
chroma_vsp[  4x2] |     5.41x |          128.13   |      693.59
chroma_vss[  4x2] |     3.53x |          111.54   |      393.31
chroma_p2s[  4x2]        |      2.27x |          62.31    |      141.33
chroma_p2s_aligned[  4x2]        |      2.34x |          60.32    |      141.28
chroma_hpp[  2x4] |     4.79x |          165.85   |      794.95
chroma_hps[  2x4] |     2.65x |          326.20   |      866.02
chroma_vpp[  2x4] |     3.16x |          187.35   |      592.95
chroma_vps[  2x4] |     2.46x |          164.85   |      404.77
chroma_vsp[  2x4] |     3.26x |          182.68   |      594.93
chroma_vss[  2x4] |     2.50x |          162.09   |      405.83
chroma_p2s[  2x4]        |      1.74x |          88.45    |      154.18
chroma_p2s_aligned[  2x4]        |      1.62x |          91.43    |      148.38
chroma_hpp[  8x4] |     9.57x |          228.95   |      2192.22
chroma_hps[  8x4] |     6.14x |          370.06   |      2271.60
chroma_vpp[  8x4] |     9.37x |          184.39   |      1728.10
chroma_vps[  8x4] |     7.71x |          177.37   |      1368.11
chroma_vsp[  8x4] |     5.24x |          324.03   |      1698.52
chroma_vss[  8x4] |     4.63x |          292.18   |      1352.98
chroma_p2s[  8x4]        |      3.97x |          99.00    |      393.49
chroma_p2s_aligned[  8x4]        |      4.12x |          95.39    |      393.35
chroma_hpp[  4x8] |     7.86x |          273.77   |      2151.64
chroma_hps[  4x8] |     4.61x |          444.51   |      2050.43
chroma_vpp[  4x8] |     5.26x |          333.64   |      1753.48
chroma_vps[  4x8] |     5.07x |          276.97   |      1404.15
chroma_vsp[  4x8] |     4.27x |          416.53   |      1776.75
chroma_vss[  4x8] |     3.76x |          373.93   |      1404.81
chroma_p2s[  4x8]        |      3.21x |          130.18   |      417.28
chroma_p2s_aligned[  4x8]        |      3.07x |          135.40   |      415.60
chroma_hpp[ 16x8] |     3.87x |          618.33   |      2394.85
chroma_hps[ 16x8] |     1.77x |          873.21   |      1546.16
chroma_vpp[ 16x8] |     9.56x |          535.07   |      5115.47
chroma_vps[ 16x8] |     2.48x |          500.85   |      1242.81
chroma_vsp[ 16x8] |     4.42x |          1408.30  |      6224.40
chroma_vss[ 16x8] |     2.02x |          1153.37  |      2332.74
chroma_p2s[ 16x8]        |      6.60x |          228.68   |      1509.21
chroma_p2s_aligned[ 16x8]        |      6.20x |          249.89   |      1549.26
chroma_hpp[ 8x16] |     11.14x |         787.51   |      8775.33
chroma_hps[ 8x16] |     6.79x |          891.13   |      6050.65
chroma_vpp[ 8x16] |     13.23x |         510.33   |      6752.78
chroma_vps[ 8x16] |     10.28x |         474.02   |      4874.92
chroma_vsp[ 8x16] |     5.91x |          1068.13  |      6308.43
chroma_vss[ 8x16] |     5.02x |          985.12   |      4944.81
chroma_p2s[ 8x16]        |      6.17x |          256.88   |      1585.30
chroma_p2s_aligned[ 8x16]        |      6.03x |          258.64   |      1559.76
chroma_hpp[32x16] |     4.67x |          2152.89  |      10061.48
chroma_hps[32x16] |     1.53x |          2786.42  |      4250.00
chroma_vpp[32x16] |     9.18x |          2008.82  |      18448.67
chroma_vps[32x16] |     1.71x |          2139.75  |      3653.31
chroma_vsp[32x16] |     3.97x |          5705.86  |      22624.62
chroma_vss[32x16] |     2.21x |          4369.46  |      9636.25
chroma_p2s[32x16]        |      1.54x |          779.97   |      1200.48
chroma_p2s_aligned[32x16]        |      1.64x |          786.49   |      1287.49
chroma_hpp[16x32] |     3.46x |          2583.27  |      8928.21
chroma_hps[16x32] |     1.55x |          2933.20  |      4540.59
chroma_vpp[16x32] |     10.25x |         1886.42  |      19332.28
chroma_vps[16x32] |     2.37x |          1927.62  |      4569.14
chroma_vsp[16x32] |     4.21x |          5759.02  |      24237.62
chroma_vss[16x32] |     1.77x |          4575.06  |      8093.69
chroma_p2s[16x32]        |      6.61x |          854.88   |      5649.51
chroma_p2s_aligned[16x32]        |      6.89x |          855.51   |      5893.33
chroma_hpp[  8x6] |     9.76x |          332.90   |      3247.47
chroma_hps[  8x6] |     6.13x |          475.84   |      2914.99
chroma_vpp[  8x6] |     10.85x |         236.91   |      2569.58
chroma_vps[  8x6] |     7.68x |          250.49   |      1924.12
chroma_vsp[  8x6] |     5.65x |          445.21   |      2516.92
chroma_vss[  8x6] |     4.87x |          396.47   |      1930.67
chroma_p2s[  8x6]        |      5.79x |          109.66   |      634.70
chroma_p2s_aligned[  8x6]        |      5.78x |          110.73   |      639.72
chroma_hpp[  6x8] |     6.25x |          468.68   |      2929.58
chroma_hps[  6x8] |     4.66x |          633.23   |      2951.24
chroma_vpp[  6x8] |     7.48x |          341.70   |      2554.81
chroma_vps[  6x8] |     6.15x |          313.60   |      1929.54
chroma_vsp[  6x8] |     3.84x |          644.27   |      2476.05
chroma_vss[  6x8] |     3.53x |          558.45   |      1971.57
chroma_p2s[  6x8]        |      3.50x |          205.34   |      718.21
chroma_p2s_aligned[  6x8]        |      3.38x |          210.45   |      711.78
chroma_hpp[  8x2] |     8.49x |          141.79   |      1203.86
chroma_hps[  8x2] |     6.06x |          286.09   |      1733.06
chroma_vpp[  8x2] |     7.95x |          117.26   |      932.26
chroma_vps[  8x2] |     7.16x |          115.23   |      824.79
chroma_vsp[  8x2] |     4.80x |          203.38   |      977.03
chroma_vss[  8x2] |     4.04x |          191.31   |      772.33
chroma_p2s[  8x2]        |      3.45x |          65.64    |      226.45
chroma_p2s_aligned[  8x2]        |      3.09x |          69.73    |      215.63
chroma_hpp[  2x8] |     4.70x |          300.56   |      1412.57
chroma_hps[  2x8] |     2.61x |          444.40   |      1160.65
chroma_vpp[  2x8] |     3.22x |          322.57   |      1040.19
chroma_vps[  2x8] |     2.95x |          295.77   |      871.07
chroma_vsp[  2x8] |     3.50x |          314.78   |      1102.30
chroma_vss[  2x8] |     3.17x |          288.69   |      914.17
chroma_p2s[  2x8]        |      1.69x |          153.83   |      260.69
chroma_p2s_aligned[  2x8]        |      1.52x |          159.71   |      243.22
chroma_hpp[16x12] |     3.70x |          910.30   |      3365.91
chroma_hps[16x12] |     1.84x |          1205.25  |      2217.29
chroma_vpp[16x12] |     10.81x |         708.62   |      7658.12
chroma_vps[16x12] |     2.26x |          774.63   |      1747.11
chroma_vsp[16x12] |     4.50x |          2218.80  |      9973.59
chroma_vss[16x12] |     2.00x |          1814.93  |      3621.33
chroma_p2s[16x12]        |      6.39x |          356.76   |      2278.65
chroma_p2s_aligned[16x12]        |      6.13x |          360.23   |      2208.31
chroma_hpp[12x16] |     10.64x |         1218.37  |      12961.72
chroma_hps[12x16] |     5.60x |          1393.42  |      7809.55
chroma_vpp[12x16] |     25.77x |         1036.49  |      26709.71
chroma_vps[12x16] |     14.88x |         940.99   |      14003.90
chroma_vsp[12x16] |     13.39x |         2092.18  |      28015.96
chroma_vss[12x16] |     7.89x |          1729.86  |      13648.85
chroma_p2s[12x16]        |      5.26x |          444.23   |      2336.87
chroma_p2s_aligned[12x16]        |      5.47x |          454.55   |      2485.66
chroma_hpp[ 16x4] |     4.07x |          349.22   |      1421.11
chroma_hps[ 16x4] |     1.81x |          564.33   |      1023.52
chroma_vpp[ 16x4] |     8.99x |          281.84   |      2533.68
chroma_vps[ 16x4] |     3.79x |          289.86   |      1098.46
chroma_vsp[ 16x4] |     4.53x |          727.08   |      3295.86
chroma_vss[ 16x4] |     2.20x |          618.97   |      1362.52
chroma_p2s[ 16x4]        |      5.68x |          137.16   |      779.17
chroma_p2s_aligned[ 16x4]        |      5.75x |          135.11   |      777.16
chroma_hpp[ 4x16] |     8.60x |          511.36   |      4398.53
chroma_hps[ 4x16] |     4.57x |          734.14   |      3358.42
chroma_vpp[ 4x16] |     6.25x |          560.88   |      3507.97
chroma_vps[ 4x16] |     5.54x |          480.85   |      2664.59
chroma_vsp[ 4x16] |     4.29x |          796.90   |      3416.68
chroma_vss[ 4x16] |     4.05x |          668.63   |      2708.60
chroma_p2s[ 4x16]        |      4.07x |          244.16   |      993.64
chroma_p2s_aligned[ 4x16]        |      4.09x |          244.15   |      997.68
chroma_hpp[32x24] |     4.74x |          3204.74  |      15176.55
chroma_hps[32x24] |     1.50x |          3794.34  |      5684.55
chroma_vpp[32x24] |     9.29x |          2962.09  |      27520.74
chroma_vps[32x24] |     1.70x |          3086.67  |      5234.74
chroma_vsp[32x24] |     4.24x |          8045.38  |      34144.79
chroma_vss[32x24] |     2.19x |          6556.66  |      14385.00
chroma_p2s[32x24]        |      1.60x |          1157.87  |      1853.67
chroma_p2s_aligned[32x24]        |      1.66x |          1182.31  |      1967.23
chroma_hpp[24x32] |     4.49x |          3830.59  |      17206.82
chroma_hps[24x32] |     1.70x |          3835.28  |      6511.63
chroma_vpp[24x32] |     12.10x |         2675.66  |      32365.63
chroma_vps[24x32] |     2.57x |          2737.14  |      7023.44
chroma_vsp[24x32] |     4.28x |          8226.36  |      35236.96
chroma_vss[24x32] |     2.27x |          6484.10  |      14707.44
chroma_p2s[24x32]        |      5.71x |          1385.87  |      7909.82
chroma_p2s_aligned[24x32]        |      5.62x |          1406.42  |      7900.16
chroma_hpp[ 32x8] |     4.51x |          1103.64  |      4981.44
chroma_hps[ 32x8] |     1.53x |          1532.51  |      2346.70
chroma_vpp[ 32x8] |     8.78x |          1027.71  |      9021.82
chroma_vps[ 32x8] |     1.66x |          1034.51  |      1713.08
chroma_vsp[ 32x8] |     4.19x |          2699.44  |      11314.52
chroma_vss[ 32x8] |     2.17x |          2232.70  |      4836.26
chroma_p2s[ 32x8]        |      3.66x |          401.31   |      1469.50
chroma_p2s_aligned[ 32x8]        |      3.59x |          405.43   |      1453.77
chroma_hpp[ 8x32] |     10.65x |         1655.79  |      17626.04
chroma_hps[ 8x32] |     6.01x |          1863.67  |      11198.01
chroma_vpp[ 8x32] |     14.17x |         949.17   |      13452.72
chroma_vps[ 8x32] |     10.29x |         949.06   |      9763.92
chroma_vsp[ 8x32] |     5.48x |          2240.29  |      12275.14
chroma_vss[ 8x32] |     5.19x |          1872.23  |      9713.61
chroma_p2s[ 8x32]        |      6.64x |          463.98   |      3078.97
chroma_p2s_aligned[ 8x32]        |      6.73x |          456.25   |      3071.09
= Color Space i422 =
chroma_hpp[  4x8] |     7.87x |          273.53   |      2153.01
chroma_hps[  4x8] |     4.57x |          446.04   |      2036.79
chroma_vpp[  4x8] |     5.79x |          313.90   |      1817.51
chroma_vps[  4x8] |     4.84x |          289.83   |      1402.15
chroma_vsp[  4x8] |     4.57x |          412.39   |      1885.67
chroma_vss[  4x8] |     3.79x |          397.15   |      1504.79
chroma_p2s[  4x8]        |      3.14x |          135.22   |      424.22
chroma_p2s_aligned[  4x8]        |      3.27x |          127.28   |      415.87
chroma_hpp[ 8x16] |     11.03x |         786.07   |      8668.14
chroma_hps[ 8x16] |     7.04x |          894.14   |      6291.08
chroma_vpp[ 8x16] |     13.51x |         509.43   |      6883.50
chroma_vps[ 8x16] |     10.11x |         486.44   |      4915.82
chroma_vsp[ 8x16] |     5.70x |          1081.40  |      6162.88
chroma_vss[ 8x16] |     5.02x |          980.78   |      4921.85
chroma_p2s[ 8x16]        |      6.13x |          254.36   |      1560.24
chroma_p2s_aligned[ 8x16]        |      6.14x |          257.00   |      1577.99
chroma_hpp[16x32] |     3.47x |          2521.09  |      8740.67
chroma_hps[16x32] |     1.52x |          2939.94  |      4470.60
chroma_vpp[16x32] |     10.76x |         1821.73  |      19610.14
chroma_vps[16x32] |     2.37x |          1924.06  |      4569.51
chroma_vsp[16x32] |     4.30x |          5759.73  |      24783.87
chroma_vss[16x32] |     1.83x |          4417.24  |      8094.57
chroma_p2s[16x32]        |      5.89x |          964.67   |      5686.29
chroma_p2s_aligned[16x32]        |      6.15x |          954.73   |      5868.70
chroma_hpp[32x64] |     4.62x |          9151.61  |      42283.11
chroma_hps[32x64] |     1.36x |          10115.93 |      13768.67
chroma_vpp[32x64] |     8.69x |          8184.42  |      71086.17
chroma_vps[32x64] |     1.64x |          8028.01  |      13195.67
chroma_vsp[32x64] |     4.10x |          21537.56 |      88228.79
chroma_vss[32x64] |     2.25x |          17359.80 |      39039.53
chroma_p2s[32x64]        |      1.54x |          2941.90  |      4535.44
chroma_p2s_aligned[32x64]        |      1.53x |          2966.22  |      4528.93
chroma_hpp[  4x4] |     7.84x |          147.71   |      1158.13
chroma_hps[  4x4] |     4.25x |          315.42   |      1340.04
chroma_vpp[  4x4] |     5.49x |          178.88   |      981.19
chroma_vps[  4x4] |     4.66x |          166.86   |      777.75
chroma_vsp[  4x4] |     3.98x |          238.18   |      948.40
chroma_vss[  4x4] |     3.63x |          215.67   |      783.38
chroma_p2s[  4x4]        |      2.62x |          87.41    |      228.86
chroma_p2s_aligned[  4x4]        |      2.59x |          87.45    |      226.76
chroma_hpp[  2x8] |     4.70x |          301.26   |      1415.43
chroma_hps[  2x8] |     2.61x |          444.21   |      1160.40
chroma_vpp[  2x8] |     3.22x |          324.18   |      1042.50
chroma_vps[  2x8] |     2.88x |          305.85   |      881.44
chroma_vsp[  2x8] |     3.44x |          304.63   |      1047.72
chroma_vss[  2x8] |     3.13x |          292.07   |      914.11
chroma_p2s[  2x8]        |      1.63x |          150.03   |      244.72
chroma_p2s_aligned[  2x8]        |      1.64x |          151.30   |      247.65
chroma_hpp[  8x8] |     10.27x |         419.20   |      4303.14
chroma_hps[  8x8] |     6.51x |          545.65   |      3551.68
chroma_vpp[  8x8] |     12.80x |         278.31   |      3563.18
chroma_vps[  8x8] |     9.43x |          282.95   |      2668.14
chroma_vsp[  8x8] |     5.59x |          580.39   |      3244.22
chroma_vss[  8x8] |     4.88x |          519.99   |      2537.52
chroma_p2s[  8x8]        |      5.57x |          149.11   |      830.16
chroma_p2s_aligned[  8x8]        |      5.54x |          149.86   |      830.11
chroma_hpp[ 4x16] |     8.31x |          503.01   |      4181.99
chroma_hps[ 4x16] |     4.71x |          714.95   |      3366.96
chroma_vpp[ 4x16] |     6.18x |          594.77   |      3674.30
chroma_vps[ 4x16] |     5.51x |          484.10   |      2667.70
chroma_vsp[ 4x16] |     4.32x |          782.91   |      3381.10
chroma_vss[ 4x16] |     4.05x |          667.35   |      2699.44
chroma_p2s[ 4x16]        |      4.03x |          244.95   |      987.82
chroma_p2s_aligned[ 4x16]        |      3.99x |          254.57   |      1015.36
chroma_hpp[16x16] |     3.70x |          1189.39  |      4395.39
chroma_hps[16x16] |     1.71x |          1470.83  |      2509.45
chroma_vpp[16x16] |     10.11x |         923.99   |      9339.38
chroma_vps[16x16] |     2.43x |          944.81   |      2292.85
chroma_vsp[16x16] |     4.49x |          2743.93  |      12328.69
chroma_vss[16x16] |     1.91x |          2311.00  |      4420.21
chroma_p2s[16x16]        |      6.17x |          486.51   |      3000.74
chroma_p2s_aligned[16x16]        |      5.86x |          497.73   |      2917.47
chroma_hpp[ 8x32] |     10.60x |         1665.24  |      17643.34
chroma_hps[ 8x32] |     6.00x |          1861.67  |      11179.09
chroma_vpp[ 8x32] |     13.66x |         952.13   |      13003.03
chroma_vps[ 8x32] |     10.52x |         928.46   |      9769.07
chroma_vsp[ 8x32] |     5.66x |          2162.36  |      12234.77
chroma_vss[ 8x32] |     5.33x |          1894.18  |      10099.06
chroma_p2s[ 8x32]        |      6.90x |          448.12   |      3090.51
chroma_p2s_aligned[ 8x32]        |      6.77x |          452.85   |      3067.68
chroma_hpp[32x32] |     4.41x |          4626.60  |      20387.60
chroma_hps[32x32] |     1.41x |          5266.65  |      7421.08
chroma_vpp[32x32] |     9.11x |          4034.01  |      36758.82
chroma_vps[32x32] |     1.64x |          4209.38  |      6901.43
chroma_vsp[32x32] |     4.10x |          10657.25 |      43721.98
chroma_vss[32x32] |     2.23x |          8635.76  |      19270.60
chroma_p2s[32x32]        |      1.63x |          1522.84  |      2482.76
chroma_p2s_aligned[32x32]        |      1.64x |          1522.24  |      2488.89
chroma_hpp[16x64] |     3.38x |          5052.91  |      17063.12
chroma_hps[16x64] |     1.50x |          5325.87  |      8014.57
chroma_vpp[16x64] |     10.09x |         3749.44  |      37849.96
chroma_vps[16x64] |     2.16x |          3700.95  |      7976.83
chroma_vsp[16x64] |     4.56x |          10834.96 |      49385.56
chroma_vss[16x64] |     1.78x |          8831.96  |      15736.37
chroma_p2s[16x64]        |      6.05x |          1873.75  |      11329.91
chroma_p2s_aligned[16x64]        |      6.16x |          1883.91  |      
11601.43
chroma_hpp[ 8x12] |     10.92x |         637.11   |      6954.89
chroma_hps[ 8x12] |     6.83x |          761.90   |      5203.11
chroma_vpp[ 8x12] |     12.71x |         420.36   |      5342.80
chroma_vps[ 8x12] |     8.33x |          471.76   |      3930.44
chroma_vsp[ 8x12] |     5.74x |          881.60   |      5060.58
chroma_vss[ 8x12] |     4.69x |          830.55   |      3892.62
chroma_p2s[ 8x12]        |      5.90x |          213.25   |      1258.30
chroma_p2s_aligned[ 8x12]        |      5.91x |          212.84   |      1257.61
chroma_hpp[ 6x16] |     6.30x |          960.38   |      6053.88
chroma_hps[ 6x16] |     4.83x |          1096.67  |      5292.81
chroma_vpp[ 6x16] |     8.19x |          664.97   |      5448.02
chroma_vps[ 6x16] |     6.60x |          605.61   |      3999.53
chroma_vsp[ 6x16] |     3.83x |          1264.51  |      4842.01
chroma_vss[ 6x16] |     3.69x |          1062.01  |      3922.09
chroma_p2s[ 6x16]        |      3.40x |          396.86   |      1347.47
chroma_p2s_aligned[ 6x16]        |      3.38x |          373.93   |      1265.11
chroma_hpp[  8x4] |     9.70x |          226.58   |      2198.49
chroma_hps[  8x4] |     6.29x |          370.85   |      2332.89
chroma_vpp[  8x4] |     9.28x |          186.40   |      1729.66
chroma_vps[  8x4] |     7.43x |          180.05   |      1337.24
chroma_vsp[  8x4] |     5.25x |          324.11   |      1700.11
chroma_vss[  8x4] |     4.63x |          292.22   |      1353.46
chroma_p2s[  8x4]        |      3.94x |          100.16   |      394.73
chroma_p2s_aligned[  8x4]        |      4.12x |          95.40    |      393.32
chroma_hpp[ 2x16] |     4.34x |          584.77   |      2535.39
chroma_hps[ 2x16] |     2.64x |          717.85   |      1896.79
chroma_vpp[ 2x16] |     3.65x |          611.50   |      2229.03
chroma_vps[ 2x16] |     3.08x |          528.01   |      1628.09
chroma_vsp[ 2x16] |     3.57x |          553.20   |      1972.44
chroma_vss[ 2x16] |     3.23x |          519.38   |      1675.30
chroma_p2s[ 2x16]        |      1.57x |          281.03   |      440.08
chroma_p2s_aligned[ 2x16]        |      1.54x |          280.97   |      432.47
chroma_hpp[16x24] |     3.68x |          1759.27  |      6465.48
chroma_hps[16x24] |     1.61x |          2141.83  |      3441.57
chroma_vpp[16x24] |     10.41x |         1362.75  |      14191.70
chroma_vps[16x24] |     2.38x |          1363.23  |      3245.74
chroma_vsp[16x24] |     4.59x |          4076.12  |      18702.90
chroma_vss[16x24] |     1.83x |          3335.56  |      6109.71
chroma_p2s[16x24]        |      5.87x |          731.63   |      4296.58
chroma_p2s_aligned[16x24]        |      5.90x |          727.38   |      4289.58
chroma_hpp[12x32] |     9.97x |          2553.56  |      25458.28
chroma_hps[12x32] |     5.41x |          2612.32  |      14126.38
chroma_vpp[12x32] |     26.93x |         1994.23  |      53704.47
chroma_vps[12x32] |     14.97x |         1821.90  |      27277.32
chroma_vsp[12x32] |     13.65x |         4124.16  |      56310.33
chroma_vss[12x32] |     8.00x |          3367.74  |      26937.04
chroma_p2s[12x32]        |      5.16x |          882.64   |      4558.72
chroma_p2s_aligned[12x32]        |      5.13x |          886.10   |      4549.69
chroma_hpp[ 16x8] |     3.71x |          634.65   |      2357.05
chroma_hps[ 16x8] |     1.71x |          850.92   |      1455.83
chroma_vpp[ 16x8] |     10.11x |         497.20   |      5027.69
chroma_vps[ 16x8] |     2.40x |          504.45   |      1210.22
chroma_vsp[ 16x8] |     4.48x |          1387.57  |      6217.42
chroma_vss[ 16x8] |     2.04x |          1150.20  |      2351.12
chroma_p2s[ 16x8]        |      5.45x |          266.40   |      1452.91
chroma_p2s_aligned[ 16x8]        |      5.69x |          259.93   |      1478.42
chroma_hpp[ 4x32] |     7.88x |          1074.41  |      8461.03
chroma_hps[ 4x32] |     3.83x |          1606.44  |      6154.07
chroma_vpp[ 4x32] |     6.41x |          1050.16  |      6726.51
chroma_vps[ 4x32] |     5.64x |          950.60   |      5365.26
chroma_vsp[ 4x32] |     4.11x |          1619.48  |      6653.40
chroma_vss[ 4x32] |     4.10x |          1298.03  |      5328.15
chroma_p2s[ 4x32]        |      4.37x |          441.59   |      1929.36
chroma_p2s_aligned[ 4x32]        |      4.38x |          441.66   |      1932.41
chroma_hpp[32x48] |     4.40x |          6806.30  |      29974.03
chroma_hps[32x48] |     1.42x |          7544.10  |      10744.12
chroma_vpp[32x48] |     8.82x |          6234.22  |      55007.51
chroma_vps[32x48] |     1.60x |          6222.42  |      9950.94
chroma_vsp[32x48] |     4.45x |          16022.73 |      71256.54
chroma_vss[32x48] |     2.25x |          12989.35 |      29255.56
chroma_p2s[32x48]        |      1.55x |          2236.62  |      3477.41
chroma_p2s_aligned[32x48]        |      1.64x |          2237.50  |      3668.82
chroma_hpp[24x64] |     4.75x |          7170.07  |      34028.22
chroma_hps[24x64] |     1.71x |          6952.21  |      11904.50
chroma_vpp[24x64] |     12.13x |         5271.86  |      63939.70
chroma_vps[24x64] |     2.51x |          5238.78  |      13171.28
chroma_vsp[24x64] |     4.49x |          16396.17 |      73537.73
chroma_vss[24x64] |     2.23x |          13512.95 |      30146.08
chroma_p2s[24x64]        |      7.55x |          2207.75  |      16677.40
chroma_p2s_aligned[24x64]        |      7.44x |          2152.60  |      
16013.93
chroma_hpp[32x16] |     4.68x |          2177.22  |      10186.56
chroma_hps[32x16] |     1.46x |          2818.73  |      4113.75
chroma_vpp[32x16] |     9.15x |          1988.51  |      18187.00
chroma_vps[32x16] |     1.72x |          2000.13  |      3439.69
chroma_vsp[32x16] |     4.11x |          5378.06  |      22080.68
chroma_vss[32x16] |     2.17x |          4454.92  |      9678.85
chroma_p2s[32x16]        |      1.50x |          794.28   |      1193.82
chroma_p2s_aligned[32x16]        |      1.54x |          794.24   |      1220.40
chroma_hpp[ 8x64] |     11.07x |         3373.56  |      37357.62
chroma_hps[ 8x64] |     6.79x |          3234.83  |      21969.56
chroma_vpp[ 8x64] |     15.06x |         1941.04  |      29226.20
chroma_vps[ 8x64] |     9.22x |          2205.29  |      20328.40
chroma_vsp[ 8x64] |     5.46x |          4655.16  |      25418.46
chroma_vss[ 8x64] |     5.33x |          3858.10  |      20572.48
chroma_p2s[ 8x64]        |      6.95x |          894.41   |      6217.21
chroma_p2s_aligned[ 8x64]        |      7.32x |          849.69   |      6220.02
= Color Space i444 =
chroma_hpp[  4x4] |     7.79x |          149.59   |      1164.57
chroma_hps[  4x4] |     4.60x |          314.92   |      1449.58
chroma_vpp[  4x4] |     5.48x |          187.78   |      1028.86
chroma_vps[  4x4] |     4.83x |          160.15   |      774.23
chroma_vsp[  4x4] |     3.96x |          238.11   |      943.60
chroma_vss[  4x4] |     3.67x |          213.21   |      781.92
chroma_p2s[  4x4]        |      2.82x |          79.55    |      224.08
chroma_p2s_aligned[  4x4]        |      2.68x |          83.75    |      224.79
chroma_hpp[  8x8] |     10.31x |         429.52   |      4430.52
chroma_hps[  8x8] |     6.63x |          544.84   |      3614.77
chroma_vpp[  8x8] |     12.48x |         276.37   |      3448.54
chroma_vps[  8x8] |     9.82x |          260.29   |      2556.45
chroma_vsp[  8x8] |     5.63x |          571.61   |      3219.38
chroma_vss[  8x8] |     4.78x |          526.28   |      2516.35
chroma_p2s[  8x8]        |      5.64x |          147.08   |      830.17
chroma_p2s_aligned[  8x8]        |      5.22x |          158.88   |      830.13
chroma_hpp[16x16] |     3.65x |          1218.69  |      4450.77
chroma_hps[16x16] |     1.71x |          1469.58  |      2509.73
chroma_vpp[16x16] |     9.85x |          954.48   |      9405.21
chroma_vps[16x16] |     2.41x |          945.29   |      2279.65
chroma_vsp[16x16] |     4.57x |          2766.65  |      12654.83
chroma_vss[16x16] |     1.91x |          2251.18  |      4289.40
chroma_p2s[16x16]        |      6.22x |          486.02   |      3023.78
chroma_p2s_aligned[16x16]        |      5.96x |          489.62   |      2916.99
chroma_hpp[32x32] |     4.37x |          4601.10  |      20120.23
chroma_hps[32x32] |     1.45x |          5289.03  |      7655.95
chroma_vpp[32x32] |     8.81x |          4290.30  |      37779.21
chroma_vps[32x32] |     1.64x |          4336.11  |      7094.77
chroma_vsp[32x32] |     4.22x |          10710.05 |      45188.38
chroma_vss[32x32] |     2.27x |          8591.29  |      19484.68
chroma_p2s[32x32]        |      1.42x |          1752.47  |      2489.08
chroma_p2s_aligned[32x32]        |      1.48x |          1711.05  |      2525.40
chroma_hpp[64x64] |     4.92x |          16319.65 |      80270.07
chroma_hps[64x64] |     1.47x |          16772.00 |      24731.77
chroma_vpp[64x64] |     8.88x |          16245.63 |      144314.61
chroma_vps[64x64] |     1.41x |          15983.93 |      22583.73
chroma_vsp[64x64] |     3.88x |          44198.86 |      171328.28
chroma_vss[64x64] |     1.92x |          34940.57 |      67219.63
chroma_p2s[64x64]        |      1.19x |          6454.91  |      7675.32
chroma_p2s_aligned[64x64]        |      1.18x |          6416.44  |      7550.38
chroma_hpp[  8x4] |     9.44x |          232.28   |      2192.27
chroma_hps[  8x4] |     6.32x |          370.61   |      2344.01
chroma_vpp[  8x4] |     9.55x |          181.27   |      1730.31
chroma_vps[  8x4] |     7.59x |          177.65   |      1349.11
chroma_vsp[  8x4] |     5.24x |          324.15   |      1698.05
chroma_vss[  8x4] |     4.75x |          291.28   |      1383.06
chroma_p2s[  8x4]        |      4.19x |          99.77    |      417.90
chroma_p2s_aligned[  8x4]        |      4.29x |          97.20    |      416.99
chroma_hpp[  4x8] |     7.86x |          290.64   |      2284.24
chroma_hps[  4x8] |     4.51x |          443.16   |      2000.53
chroma_vpp[  4x8] |     5.69x |          313.61   |      1785.45
chroma_vps[  4x8] |     5.15x |          271.28   |      1397.06
chroma_vsp[  4x8] |     4.28x |          412.37   |      1766.41
chroma_vss[  4x8] |     3.78x |          373.81   |      1413.50
chroma_p2s[  4x8]        |      3.18x |          131.14   |      417.35
chroma_p2s_aligned[  4x8]        |      3.14x |          134.11   |      421.59
chroma_hpp[ 16x8] |     3.78x |          625.70   |      2363.27
chroma_hps[ 16x8] |     1.68x |          854.28   |      1433.99
chroma_vpp[ 16x8] |     10.51x |         498.54   |      5238.74
chroma_vps[ 16x8] |     2.42x |          500.62   |      1210.61
chroma_vsp[ 16x8] |     4.42x |          1394.88  |      6161.00
chroma_vss[ 16x8] |     2.02x |          1152.44  |      2326.67
chroma_p2s[ 16x8]        |      5.67x |          260.82   |      1478.18
chroma_p2s_aligned[ 16x8]        |      5.63x |          260.54   |      1465.70
chroma_hpp[ 8x16] |     11.27x |         782.27   |      8816.20
chroma_hps[ 8x16] |     6.69x |          904.43   |      6053.39
chroma_vpp[ 8x16] |     13.27x |         508.50   |      6748.41
chroma_vps[ 8x16] |     10.44x |         470.45   |      4910.09
chroma_vsp[ 8x16] |     5.79x |          1092.64  |      6321.19
chroma_vss[ 8x16] |     5.36x |          979.02   |      5249.05
chroma_p2s[ 8x16]        |      5.40x |          292.65   |      1580.05
chroma_p2s_aligned[ 8x16]        |      5.78x |          277.45   |      1604.61
chroma_hpp[32x16] |     4.71x |          2235.41  |      10526.74
chroma_hps[32x16] |     1.47x |          2900.47  |      4257.00
chroma_vpp[32x16] |     8.81x |          2130.10  |      18768.49
chroma_vps[32x16] |     1.66x |          2058.91  |      3419.76
chroma_vsp[32x16] |     4.17x |          5381.87  |      22462.48
chroma_vss[32x16] |     2.22x |          4364.59  |      9702.99
chroma_p2s[32x16]        |      1.44x |          894.32   |      1288.28
chroma_p2s_aligned[32x16]        |      1.39x |          927.98   |      1287.72
chroma_hpp[16x32] |     3.50x |          2570.69  |      8988.56
chroma_hps[16x32] |     1.50x |          2970.65  |      4443.05
chroma_vpp[16x32] |     10.11x |         1802.67  |      18228.08
chroma_vps[16x32] |     2.37x |          1814.58  |      4300.42
chroma_vsp[16x32] |     4.46x |          5523.49  |      24648.10
chroma_vss[16x32] |     1.85x |          4415.95  |      8190.12
chroma_p2s[16x32]        |      5.85x |          973.52   |      5691.60
chroma_p2s_aligned[16x32]        |      5.89x |          958.95   |      5651.87
chroma_hpp[64x32] |     4.92x |          8188.25  |      40268.81
chroma_hps[64x32] |     1.48x |          8707.96  |      12907.71
chroma_vpp[64x32] |     9.55x |          7981.42  |      76252.05
chroma_vps[64x32] |     1.47x |          8289.56  |      12145.61
chroma_vsp[64x32] |     3.91x |          22010.04 |      85951.80
chroma_vss[64x32] |     2.02x |          17201.16 |      34792.17
chroma_p2s[64x32]        |      1.21x |          3259.44  |      3955.39
chroma_p2s_aligned[64x32]        |      1.25x |          3216.39  |      4023.50
chroma_hpp[32x64] |     4.30x |          9133.45  |      39259.43
chroma_hps[32x64] |     1.39x |          9840.54  |      13635.89
chroma_vpp[32x64] |     9.06x |          8072.54  |      73161.23
chroma_vps[32x64] |     1.69x |          7938.44  |      13439.59
chroma_vsp[32x64] |     4.16x |          21618.39 |      89873.09
chroma_vss[32x64] |     2.15x |          17427.22 |      37397.46
chroma_p2s[32x64]        |      1.36x |          3332.91  |      4532.42
chroma_p2s_aligned[32x64]        |      1.36x |          3333.12  |      4535.58
chroma_hpp[16x12] |     3.69x |          909.59   |      3352.44
chroma_hps[16x12] |     1.81x |          1139.79  |      2061.45
chroma_vpp[16x12] |     10.17x |         738.66   |      7514.29
chroma_vps[16x12] |     2.26x |          728.99   |      1644.36
chroma_vsp[16x12] |     4.66x |          2106.95  |      9818.71
chroma_vss[16x12] |     1.87x |          1814.70  |      3400.16
chroma_p2s[16x12]        |      5.70x |          376.79   |      2146.17
chroma_p2s_aligned[16x12]        |      5.69x |          376.82   |      2144.59
chroma_hpp[12x16] |     10.47x |         1221.39  |      12790.24
chroma_hps[12x16] |     5.95x |          1311.49  |      7808.15
chroma_vpp[12x16] |     24.99x |         1028.02  |      25689.78
chroma_vps[12x16] |     15.17x |         930.78   |      14116.90
chroma_vsp[12x16] |     14.02x |         2081.37  |      29186.73
chroma_vss[12x16] |     7.85x |          1747.25  |      13718.41
chroma_p2s[12x16]        |      5.25x |          445.70   |      2337.93
chroma_p2s_aligned[12x16]        |      5.30x |          440.84   |      2336.93
chroma_hpp[ 16x4] |     3.98x |          328.69   |      1306.94
chroma_hps[ 16x4] |     1.79x |          567.76   |      1013.81
chroma_vpp[ 16x4] |     9.03x |          281.59   |      2541.40
chroma_vps[ 16x4] |     3.81x |          288.81   |      1098.92
chroma_vsp[ 16x4] |     4.49x |          725.94   |      3256.98
chroma_vss[ 16x4] |     2.29x |          603.98   |      1384.99
chroma_p2s[ 16x4]        |      5.17x |          150.26   |      777.34
chroma_p2s_aligned[ 16x4]        |      5.17x |          150.32   |      777.08
chroma_hpp[ 4x16] |     8.15x |          511.42   |      4165.53
chroma_hps[ 4x16] |     4.71x |          717.83   |      3384.20
chroma_vpp[ 4x16] |     6.24x |          560.46   |      3495.23
chroma_vps[ 4x16] |     5.42x |          489.97   |      2657.01
chroma_vsp[ 4x16] |     4.38x |          820.78   |      3591.13
chroma_vss[ 4x16] |     4.01x |          673.65   |      2698.72
chroma_p2s[ 4x16]        |      3.95x |          254.19   |      1004.20
chroma_p2s_aligned[ 4x16]        |      4.00x |          249.54   |      999.32
chroma_hpp[32x24] |     4.64x |          3229.72  |      14989.80
chroma_hps[32x24] |     1.50x |          3798.99  |      5713.59
chroma_vpp[32x24] |     9.45x |          2956.60  |      27928.15
chroma_vps[32x24] |     1.72x |          3037.14  |      5219.49
chroma_vsp[32x24] |     4.20x |          8051.84  |      33811.77
chroma_vss[32x24] |     2.22x |          6441.47  |      14278.66
chroma_p2s[32x24]        |      1.42x |          1306.16  |      1851.51
chroma_p2s_aligned[32x24]        |      1.40x |          1325.07  |      1849.49
chroma_hpp[24x32] |     4.56x |          3768.46  |      17181.02
chroma_hps[24x32] |     1.71x |          3821.04  |      6532.74
chroma_vpp[24x32] |     11.55x |         2665.90  |      30784.39
chroma_vps[24x32] |     2.67x |          2679.31  |      7167.02
chroma_vsp[24x32] |     4.23x |          8491.46  |      35922.44
chroma_vss[24x32] |     2.26x |          6456.29  |      14600.82
chroma_p2s[24x32]        |      5.63x |          1406.97  |      7925.22
chroma_p2s_aligned[24x32]        |      5.75x |          1376.71  |      7913.13
chroma_hpp[ 32x8] |     4.63x |          1089.67  |      5040.89
chroma_hps[ 32x8] |     1.53x |          1535.78  |      2347.36
chroma_vpp[ 32x8] |     8.68x |          1061.46  |      9215.38
chroma_vps[ 32x8] |     1.65x |          1039.68  |      1713.10
chroma_vsp[ 32x8] |     4.28x |          2696.27  |      11528.11
chroma_vss[ 32x8] |     2.19x |          2192.72  |      4808.45
chroma_p2s[ 32x8]        |      3.36x |          438.85   |      1473.53
chroma_p2s_aligned[ 32x8]        |      3.29x |          441.60   |      1453.74
chroma_hpp[ 8x32] |     10.30x |         1659.10  |      17089.24
chroma_hps[ 8x32] |     6.02x |          1861.67  |      11206.37
chroma_vpp[ 8x32] |     13.04x |         1007.70  |      13137.54
chroma_vps[ 8x32] |     10.55x |         929.96   |      9808.05
chroma_vsp[ 8x32] |     5.69x |          2221.92  |      12652.67
chroma_vss[ 8x32] |     5.20x |          1872.03  |      9725.74
chroma_p2s[ 8x32]        |      6.01x |          513.94   |      3086.20
chroma_p2s_aligned[ 8x32]        |      5.83x |          528.60   |      3079.68
chroma_hpp[64x48] |     4.92x |          11978.64 |      58973.95
chroma_hps[64x48] |     1.46x |          12683.81 |      18578.88
chroma_vpp[64x48] |     8.89x |          12053.25 |      107100.50
chroma_vps[64x48] |     1.43x |          11750.78 |      16816.01
chroma_vsp[64x48] |     4.02x |          32002.59 |      128551.63
chroma_vss[64x48] |     1.94x |          26428.06 |      51294.61
chroma_p2s[64x48]        |      1.23x |          4888.00  |      5999.00
chroma_p2s_aligned[64x48]        |      1.19x |          5110.81  |      6083.19
chroma_hpp[48x64] |     4.85x |          12520.19 |      60680.74
chroma_hps[48x64] |     1.54x |          12867.80 |      19875.59
chroma_vpp[48x64] |     9.37x |          12121.06 |      113617.49
chroma_vps[48x64] |     1.43x |          12082.70 |      17291.08
chroma_vsp[48x64] |     4.09x |          32648.08 |      133432.31
chroma_vss[48x64] |     2.05x |          25918.63 |      53199.06
chroma_p2s[48x64]        |      1.24x |          4906.88  |      6060.90
chroma_p2s_aligned[48x64]        |      1.25x |          4992.84  |      6219.91
chroma_hpp[64x16] |     4.96x |          3946.05  |      19558.00
chroma_hps[64x16] |     1.53x |          4781.80  |      7312.97
chroma_vpp[64x16] |     9.65x |          4056.01  |      39122.49
chroma_vps[64x16] |     1.49x |          3934.78  |      5878.69
chroma_vsp[64x16] |     4.06x |          10976.82 |      44523.09
chroma_vss[64x16] |     2.03x |          8544.23  |      17381.42
chroma_p2s[64x16]        |      1.18x |          1636.00  |      1932.25
chroma_p2s_aligned[64x16]        |      1.18x |          1635.50  |      1931.50
chroma_hpp[16x64] |     3.37x |          5073.91  |      17103.47
chroma_hps[16x64] |     1.46x |          5438.25  |      7954.09
chroma_vpp[16x64] |     10.07x |         3696.12  |      37209.95
chroma_vps[16x64] |     2.15x |          3698.16  |      7965.47
chroma_vsp[16x64] |     4.61x |          10971.83 |      50610.48
chroma_vss[16x64] |     1.78x |          8836.42  |      15762.27
chroma_p2s[16x64]        |      6.33x |          1850.36  |      11715.58
chroma_p2s_aligned[16x64]        |      6.11x |          1841.15  |      
11249.70
== intrapred primitives ==
intra_planar_4x4 |      3.06x |          155.32   |      475.87
intra_dc_4x4[f=0] |     1.63x |          79.52    |      129.48
intra_dc_4x4[f=1] |     1.90x |          153.06   |      290.49
intra_allangs4x4 |      15.73x |         2322.48  |      36538.63
intra_ang_4x4[ 2] |     5.95x |          84.08    |      500.45
intra_ang_4x4[ 3] |     7.57x |          140.95   |      1067.30
intra_ang_4x4[ 4] |     7.57x |          141.08   |      1067.49
intra_ang_4x4[ 5] |     7.49x |          142.40   |      1067.00
intra_ang_4x4[ 6] |     8.09x |          131.92   |      1067.40
intra_ang_4x4[ 7] |     7.75x |          137.54   |      1066.52
intra_ang_4x4[ 8] |     8.34x |          127.97   |      1066.97
intra_ang_4x4[ 9] |     8.50x |          125.52   |      1067.22
intra_ang_4x4[10] |     4.62x |          105.19   |      486.39
intra_ang_4x4[11] |     9.43x |          123.76   |      1167.63
intra_ang_4x4[12] |     8.71x |          137.89   |      1200.90
intra_ang_4x4[13] |     7.88x |          148.50   |      1170.12
intra_ang_4x4[14] |     8.11x |          153.63   |      1246.26
intra_ang_4x4[15] |     7.13x |          176.99   |      1261.54
intra_ang_4x4[16] |     7.40x |          162.36   |      1201.14
intra_ang_4x4[17] |     6.87x |          175.15   |      1204.07
intra_ang_4x4[18] |     4.50x |          109.52   |      492.41
intra_ang_4x4[19] |     6.52x |          177.63   |      1157.63
intra_ang_4x4[20] |     6.67x |          172.63   |      1150.76
intra_ang_4x4[21] |     6.58x |          165.82   |      1091.33
intra_ang_4x4[22] |     7.42x |          151.27   |      1122.44
intra_ang_4x4[23] |     7.49x |          149.80   |      1121.54
intra_ang_4x4[24] |     8.21x |          133.29   |      1094.23
intra_ang_4x4[25] |     8.44x |          129.88   |      1096.14
intra_ang_4x4[26] |     3.28x |          126.83   |      416.05
intra_ang_4x4[27] |     8.16x |          123.31   |      1006.40
intra_ang_4x4[28] |     8.07x |          130.32   |      1051.79
intra_ang_4x4[29] |     7.49x |          139.66   |      1045.54
intra_ang_4x4[30] |     7.90x |          133.19   |      1052.30
intra_ang_4x4[31] |     7.13x |          139.82   |      997.55
intra_ang_4x4[32] |     7.51x |          131.87   |      989.91
intra_ang_4x4[33] |     7.26x |          135.65   |      984.83
intra_ang_4x4[34] |     4.82x |          78.17    |      376.67
intra_filter_4x4 |      3.07x |          117.22   |      359.29
intra_planar_8x8 |      6.78x |          264.15   |      1790.59
intra_dc_8x8[f=0] |     1.75x |          103.50   |      181.20
intra_dc_8x8[f=1] |     1.98x |          238.33   |      471.58
intra_allangs8x8 |      23.18x |         4030.62  |      93425.34
intra_ang_8x8[ 2] |     12.66x |         103.69   |      1312.55
intra_ang_8x8[ 3] |     10.94x |         288.54   |      3157.23
intra_ang_8x8[ 4] |     11.11x |         265.74   |      2953.39
intra_ang_8x8[ 5] |     11.53x |         257.30   |      2965.51
intra_ang_8x8[ 6] |     11.27x |         263.00   |      2964.39
intra_ang_8x8[ 7] |     11.70x |         252.25   |      2952.35
intra_ang_8x8[ 8] |     11.04x |         270.55   |      2987.91
intra_ang_8x8[ 9] |     12.11x |         244.53   |      2961.94
intra_ang_8x8[10] |     12.65x |         111.94   |      1415.67
intra_ang_8x8[11] |     11.92x |         265.19   |      3161.84
intra_ang_8x8[12] |     11.97x |         267.19   |      3197.20
intra_ang_8x8[13] |     11.12x |         275.52   |      3065.08
intra_ang_8x8[14] |     10.64x |         289.78   |      3082.26
intra_ang_8x8[15] |     10.52x |         291.70   |      3069.86
intra_ang_8x8[16] |     10.42x |         295.37   |      3078.28
intra_ang_8x8[17] |     11.21x |         278.85   |      3127.12
intra_ang_8x8[18] |     9.41x |          101.34   |      953.27
intra_ang_8x8[19] |     13.00x |         206.54   |      2684.73
intra_ang_8x8[20] |     12.61x |         211.17   |      2662.95
intra_ang_8x8[21] |     13.38x |         204.16   |      2731.57
intra_ang_8x8[22] |     12.18x |         215.60   |      2625.99
intra_ang_8x8[23] |     13.25x |         197.74   |      2620.61
intra_ang_8x8[24] |     13.99x |         184.75   |      2585.31
intra_ang_8x8[25] |     13.39x |         192.66   |      2580.60
intra_ang_8x8[26] |     6.01x |          158.07   |      950.46
intra_ang_8x8[27] |     13.04x |         194.34   |      2535.04
intra_ang_8x8[28] |     12.28x |         206.52   |      2535.90
intra_ang_8x8[29] |     12.09x |         209.69   |      2535.80
intra_ang_8x8[30] |     12.29x |         206.32   |      2535.74
intra_ang_8x8[31] |     12.01x |         211.08   |      2535.18
intra_ang_8x8[32] |     12.15x |         217.12   |      2638.32
intra_ang_8x8[33] |     12.06x |         210.19   |      2535.81
intra_ang_8x8[34] |     8.47x |          97.06    |      822.55
intra_filter_8x8 |      7.56x |          184.09   |      1392.29
intra_planar_16x16 |    6.25x |          705.44   |      4406.89
intra_dc_16x16[f=0] |   1.73x |          169.39   |      292.83
intra_dc_16x16[f=1] |   2.37x |          362.40   |      858.23
intra_allangs16x16 |    14.73x |         15028.29 |      221422.11
intra_ang_16x16[ 2] |   29.84x |         192.84   |      5753.64
intra_ang_16x16[ 3] |   6.67x |          988.17   |      6591.57
intra_ang_16x16[ 4] |   6.63x |          999.95   |      6627.85
intra_ang_16x16[ 5] |   8.57x |          774.88   |      6642.60
intra_ang_16x16[ 6] |   8.30x |          798.70   |      6631.41
intra_ang_16x16[ 7] |   8.73x |          779.70   |      6809.49
intra_ang_16x16[ 8] |   8.51x |          778.89   |      6630.98
intra_ang_16x16[ 9] |   8.39x |          783.27   |      6571.59
intra_ang_16x16[10] |   28.57x |         226.58   |      6473.86
intra_ang_16x16[11] |   8.89x |          772.14   |      6865.21
intra_ang_16x16[12] |   8.98x |          756.29   |      6794.98
intra_ang_16x16[13] |   8.81x |          768.62   |      6771.03
intra_ang_16x16[14] |   8.80x |          791.87   |      6970.60
intra_ang_16x16[15] |   9.04x |          778.73   |      7036.39
intra_ang_16x16[16] |   8.61x |          805.51   |      6936.75
intra_ang_16x16[17] |   8.83x |          778.30   |      6873.83
intra_ang_16x16[18] |   16.01x |         174.60   |      2795.76
intra_ang_16x16[19] |   6.04x |          594.02   |      3589.59
intra_ang_16x16[20] |   5.93x |          611.48   |      3626.78
intra_ang_16x16[21] |   6.37x |          568.47   |      3623.16
intra_ang_16x16[22] |   6.31x |          573.15   |      3619.21
intra_ang_16x16[23] |   6.26x |          563.40   |      3527.83
intra_ang_16x16[24] |   6.27x |          562.87   |      3528.46
intra_ang_16x16[25] |   5.58x |          597.52   |      3336.07
intra_ang_16x16[26] |   9.83x |          299.57   |      2944.08
intra_ang_16x16[27] |   6.43x |          508.10   |      3265.63
intra_ang_16x16[28] |   4.97x |          715.99   |      3555.11
intra_ang_16x16[29] |   4.90x |          683.54   |      3349.90
intra_ang_16x16[30] |   4.90x |          683.64   |      3351.96
intra_ang_16x16[31] |   6.00x |          562.69   |      3375.75
intra_ang_16x16[32] |   4.31x |          814.40   |      3506.14
intra_ang_16x16[33] |   3.98x |          820.61   |      3266.99
intra_ang_16x16[34] |   13.33x |         184.07   |      2454.42
intra_filter_16x16 |    3.63x |          278.03   |      1007.87
intra_planar_32x32 |    8.27x |          2571.91  |      21270.71
intra_dc_32x32[f=0] |   1.43x |          615.06   |      876.70
intra_allangs32x32 |    5.65x |          113582.92 |     641725.88
intra_ang_32x32[ 2] |   23.35x |         574.96   |      13425.14
intra_ang_32x32[ 3] |   4.82x |          4062.34  |      19566.63
intra_ang_32x32[ 4] |   5.04x |          4091.26  |      20632.02
intra_ang_32x32[ 5] |   5.05x |          3925.89  |      19842.28
intra_ang_32x32[ 6] |   5.19x |          3825.76  |      19859.36
intra_ang_32x32[ 7] |   5.00x |          3892.47  |      19460.21
intra_ang_32x32[ 8] |   6.00x |          3247.86  |      19484.06
intra_ang_32x32[ 9] |   5.45x |          3600.33  |      19610.05
intra_ang_32x32[10] |   38.33x |         557.10   |      21352.24
intra_ang_32x32[11] |   5.93x |          3258.55  |      19326.55
intra_ang_32x32[12] |   5.90x |          3311.81  |      19551.93
intra_ang_32x32[13] |   5.84x |          3425.32  |      19986.82
intra_ang_32x32[14] |   4.97x |          3978.13  |      19761.64
intra_ang_32x32[15] |   5.00x |          3972.00  |      19846.10
intra_ang_32x32[16] |   4.96x |          4057.24  |      20130.15
intra_ang_32x32[17] |   4.87x |          4162.86  |      20281.20
intra_ang_32x32[18] |   4.82x |          548.04   |      2641.46
intra_ang_32x32[19] |   2.98x |          2845.86  |      8492.86
intra_ang_32x32[20] |   3.00x |          2833.57  |      8508.10
intra_ang_32x32[21] |   3.01x |          2769.80  |      8325.21
intra_ang_32x32[22] |   3.00x |          2745.21  |      8246.38
intra_ang_32x32[23] |   2.92x |          2906.07  |      8482.00
intra_ang_32x32[24] |   2.96x |          2758.11  |      8175.15
intra_ang_32x32[25] |   3.20x |          2489.41  |      7971.38
intra_ang_32x32[26] |   11.33x |         752.05   |      8521.50
intra_ang_32x32[27] |   2.76x |          2792.58  |      7713.92
intra_ang_32x32[28] |   2.86x |          2771.87  |      7925.92
intra_ang_32x32[29] |   2.50x |          3156.72  |      7888.80
intra_ang_32x32[30] |   2.49x |          3215.05  |      8018.94
intra_ang_32x32[31] |   2.38x |          3321.53  |      7917.10
intra_ang_32x32[32] |   2.47x |          3228.91  |      7967.44
intra_ang_32x32[33] |   2.40x |          3222.46  |      7732.45
intra_ang_32x32[34] |   3.81x |          547.37   |      2084.58
intra_filter_32x32 |    1.77x |          515.83   |      913.78
== mcstf primitives ==

/usr/local/lib/libx265.so.26.0 --> 
/usr/ports/pobj/x265-4.3/fake-amd64/usr/local/lib/libx265.so.27.0
Dynamic export changes:
added:
        _ZN4x26510ThreadPool16allocThreadPoolsEP10x265_paramRiS3_b
        _ZN4x26510ThreadedME10tryWakeOneEv
        _ZN4x26510ThreadedME7findJobEiRNS_16TmeProxyProviderE
        _ZN4x26510ThreadedME9bindPoolsEPNS_10ThreadPoolEi
        _ZN4x26511JobProviderC2Ev
        _ZN4x26511computeEdgeEPhPKhS0_liibhPi
        _ZN4x26514TemporalFilter11applyMotionEPNS_2MVEjPNS_6PicYuvES4_ii
        
_ZN4x26514TemporalFilter15bilateralFilterEPNS_5FrameEPNS_24TemporalFilterRefPicInfoEPNS_10ThreadPoolE
        
_ZN4x26514TemporalFilter19bilateralFilterCoreEPNS_5FrameEPNS_24TemporalFilterRefPicInfoEiii
        _ZN4x26516TmeProxyProvider7findJobEi
        _ZN4x26516TmeProxyProviderC1ERNS_10ThreadedMEEPNS_10ThreadPoolEi
        _ZN4x26516TmeProxyProviderC2ERNS_10ThreadedMEEPNS_10ThreadPoolEi
        _ZN4x26516TmeProxyProviderD0Ev
        _ZN4x26517CostEstimateGroup6addRowEiiiiiPNS_5FrameE
        _ZN4x26518MotionEstimatorTLD18motionErrorLumaSSDEPhiS1_iiiiii
        
_ZN4x26518MotionEstimatorTLD20motionEstimationLumaEPNS_2MVEjPhiiiS3_iiPKS1_ji
        
_ZN4x26518MotionEstimatorTLD29motionEstimationLumaDoubleResEPNS_2MVEjPNS_6PicYuvES4_PKS1_jiPiii
        _ZN4x26520BilateralFilterGroup11finishBatchEv
        _ZN4x26520BilateralFilterGroup12processTasksEi
        _ZN4x26524frameInitLowresCoreMCSTFEPKhPhS2_S2_S2_llii
        _ZN4x26524setupIntrinsicMCSTF_avx2ERNS_15MCSTFPrimitivesE
        _ZN4x26527setupMCSTFPrimitives_scalarERNS_15MCSTFPrimitivesE
        _ZN4x2656Lowres4initEPNS_6PicYuvEib
        _ZN4x2659Lookahead13estimateNoiseEPNS_5FrameE
        _ZN4x2659mcstfPrimE
        _ZTIN4x26516TmeProxyProviderE
        _ZTIN4x26520BilateralFilterGroupE
        _ZTSN4x26516TmeProxyProviderE
        _ZTSN4x26520BilateralFilterGroupE
        _ZTVN4x26516TmeProxyProviderE
        _ZTVN4x26520BilateralFilterGroupE
        _ZThn112_N4x26512FrameEncoder10threadMainEv
        _ZThn112_N4x26512FrameEncoderD0Ev
        _ZThn112_N4x26512FrameEncoderD1Ev
        x265_api_get_217
        x265_encoder_open_217

removed:
        _ZN4x26510ThreadPool16allocThreadPoolsEP10x265_paramRib
        _ZN4x26510ThreadedME7findJobEi
        _ZN4x26510ThreadedMEC2EP10x265_paramRNS_7EncoderE
        _ZN4x26511computeEdgeEPhS0_S0_liibh
        _ZN4x26514TemporalFilter11applyMotionEPNS_2MVEjPNS_6PicYuvES4_
        
_ZN4x26514TemporalFilter15bilateralFilterEPNS_5FrameEPNS_24TemporalFilterRefPicInfoEd
        
_ZN4x26517CostEstimateGroup20estimatelowresmotionERNS_18MotionEstimatorTLDEPNS_5FrameEi
        _ZN4x26518MotionEstimatorTLD18motionErrorLumaSADERS0_PhiS2_iiiiii
        _ZN4x26518MotionEstimatorTLD18motionErrorLumaSSDERS0_PhiS2_iiiiii
        
_ZN4x26518MotionEstimatorTLD20motionEstimationLumaERS0_PNS_2MVEjPhiiiS4_iiS3_ji
        
_ZN4x26518MotionEstimatorTLD29motionEstimationLumaDoubleResERS0_PNS_2MVEjPNS_6PicYuvES5_iS3_jiPi
        _ZN4x2656Lowres4initEPNS_6PicYuvEi
        _ZThn40_N4x26510ThreadedME10threadMainEv
        _ZThn40_N4x26510ThreadedMED0Ev
        _ZThn40_N4x26510ThreadedMED1Ev
        _ZThn88_N4x26512FrameEncoder10threadMainEv
        _ZThn88_N4x26512FrameEncoderD0Ev
        _ZThn88_N4x26512FrameEncoderD1Ev
        x265_api_get_216
        x265_encoder_open_216

data object sizes changes:
        _ZN4x26510primitivesE 18248 --> 18240
        _ZN4x26512g_puStartIdxE 4096 --> 4128
        _ZTIN4x26510ThreadedMEE 56 --> 24
        _ZTVN4x26510ThreadedMEE 88 --> 40
--
// I think that is fine?


# TRUSTED_PKG_PATH=/usr/ports/packages/amd64/all/ pkg_add -Dsnap -u x265
.libs-x265-4.1p0+x265-4.2->x265-4.3: ok

Recompiled ffmpeg and mpv after.


$ cd /usr/ports/graphics/ffmpeg && make clean=all clean && make patch build 
package test ; make port-lib-depends-check check-shlib-syms clean

# TRUSTED_PKG_PATH=/usr/ports/packages/amd64/all/ pkg_add -Dsnap -Dinstalled -r 
ffmpeg
ffmpeg-8.1.2v1->8.1.2v1: ok
--

$ cd /usr/ports/multimedia/mpv/ && make clean=all clean && make patch build 
package test ; make port-lib-depends-check check-shlib-syms clean

# TRUSTED_PKG_PATH=/usr/ports/packages/amd64/all/ pkg_add -Dsnap -Dinstalled -r 
mpv
mpv-0.41.0p0->0.41.0p0: ok
--

Played a few 'H.265/HEVC (High Effciency Video Coding) (Main 10)' files.

This was with current/amd64 with privsep using sway and xwayland if that
makes a difference. It used display 'gpu-next' with context 'x11egl'.

>From fastfetch:

CPU: Intel(R) Core(TM) i5-3340M (2) @ 2.70 GHz
GPU: Intel(R) HD Graphics 4000 (IVB GT2) [Integrated]
--

Sorry if this was too much noise.

Let me know if some more tests or I missed something.

Maybe someone else can attest arm64, newer amd64, or other
architectures?

Hope this helps. Happy hacking. May you stay cool and hydrated.
--
yaydn

Reply via email to