Gnuplot not found, using plotters backend
Benchmarking grayscale_u8_rgb/256
Benchmarking grayscale_u8_rgb/256: Warming up for 500.00 ms
Benchmarking grayscale_u8_rgb/256: Collecting 20 samples in estimated 2.0176 s (24k iterations)
Benchmarking grayscale_u8_rgb/256: Analyzing
grayscale_u8_rgb/256    time:   [15.418 µs 18.484 µs 20.885 µs]
                        change: [-5.6614% +5.6327% +18.689%] (p = 0.38 > 0.05)
                        No change in performance detected.
Found 3 outliers among 20 measurements (15.00%)
  1 (5.00%) high mild
  2 (10.00%) high severe
Benchmarking grayscale_u8_rgb/512
Benchmarking grayscale_u8_rgb/512: Warming up for 500.00 ms
Benchmarking grayscale_u8_rgb/512: Collecting 20 samples in estimated 2.0149 s (7980 iterations)
Benchmarking grayscale_u8_rgb/512: Analyzing
grayscale_u8_rgb/512    time:   [64.389 µs 68.832 µs 72.236 µs]
                        change: [+5.4411% +11.164% +16.950%] (p = 0.00 < 0.05)
                        Performance has regressed.
Found 2 outliers among 20 measurements (10.00%)
  2 (10.00%) high mild
Benchmarking grayscale_u8_rgb/1024
Benchmarking grayscale_u8_rgb/1024: Warming up for 500.00 ms
Benchmarking grayscale_u8_rgb/1024: Collecting 20 samples in estimated 2.0955 s (3570 iterations)
Benchmarking grayscale_u8_rgb/1024: Analyzing
grayscale_u8_rgb/1024   time:   [249.87 µs 262.29 µs 281.36 µs]
                        change: [+0.5264% +7.5446% +15.622%] (p = 0.06 > 0.05)
                        No change in performance detected.

Benchmarking grayscale_f32_rgb/256
Benchmarking grayscale_f32_rgb/256: Warming up for 500.00 ms
Benchmarking grayscale_f32_rgb/256: Collecting 20 samples in estimated 2.0240 s (17k iterations)
Benchmarking grayscale_f32_rgb/256: Analyzing
grayscale_f32_rgb/256   time:   [51.924 µs 56.506 µs 60.092 µs]
                        change: [-51.235% -47.691% -43.691%] (p = 0.00 < 0.05)
                        Performance has improved.
Benchmarking grayscale_f32_rgb/512
Benchmarking grayscale_f32_rgb/512: Warming up for 500.00 ms
Benchmarking grayscale_f32_rgb/512: Collecting 20 samples in estimated 2.0278 s (3360 iterations)
Benchmarking grayscale_f32_rgb/512: Analyzing
grayscale_f32_rgb/512   time:   [239.36 µs 260.21 µs 276.74 µs]
                        change: [-43.518% -38.093% -32.376%] (p = 0.00 < 0.05)
                        Performance has improved.
Benchmarking grayscale_f32_rgb/1024
Benchmarking grayscale_f32_rgb/1024: Warming up for 500.00 ms
Benchmarking grayscale_f32_rgb/1024: Collecting 20 samples in estimated 2.4101 s (840 iterations)
Benchmarking grayscale_f32_rgb/1024: Analyzing
grayscale_f32_rgb/1024  time:   [1.1649 ms 1.2234 ms 1.3107 ms]
                        change: [-40.911% -28.081% -12.762%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 3 outliers among 20 measurements (15.00%)
  1 (5.00%) high mild
  2 (10.00%) high severe

Benchmarking threshold_u8/256
Benchmarking threshold_u8/256: Warming up for 500.00 ms
Benchmarking threshold_u8/256: Collecting 20 samples in estimated 2.0007 s (292k iterations)
Benchmarking threshold_u8/256: Analyzing
threshold_u8/256        time:   [2.6887 µs 2.8047 µs 2.8885 µs]
                        change: [-16.252% -9.2963% -1.8592%] (p = 0.02 < 0.05)
                        Performance has improved.
Benchmarking threshold_u8/512
Benchmarking threshold_u8/512: Warming up for 500.00 ms
Benchmarking threshold_u8/512: Collecting 20 samples in estimated 2.0026 s (83k iterations)
Benchmarking threshold_u8/512: Analyzing
threshold_u8/512        time:   [9.4559 µs 10.273 µs 10.873 µs]
                        change: [-15.486% -4.3630% +8.1185%] (p = 0.49 > 0.05)
                        No change in performance detected.
Benchmarking threshold_u8/1024
Benchmarking threshold_u8/1024: Warming up for 500.00 ms
Benchmarking threshold_u8/1024: Collecting 20 samples in estimated 2.0227 s (17k iterations)
Benchmarking threshold_u8/1024: Analyzing
threshold_u8/1024       time:   [40.446 µs 43.721 µs 46.019 µs]
                        change: [-9.2923% +4.3724% +19.032%] (p = 0.56 > 0.05)
                        No change in performance detected.

Benchmarking threshold_u8_cropped/256
Benchmarking threshold_u8_cropped/256: Warming up for 500.00 ms
Benchmarking threshold_u8_cropped/256: Collecting 20 samples in estimated 2.0005 s (227k iterations)
Benchmarking threshold_u8_cropped/256: Analyzing
threshold_u8_cropped/256
                        time:   [6.1821 µs 7.0513 µs 7.8215 µs]
                        change: [-14.748% -4.8865% +5.5365%] (p = 0.38 > 0.05)
                        No change in performance detected.
Found 2 outliers among 20 measurements (10.00%)
  2 (10.00%) high mild
Benchmarking threshold_u8_cropped/512
Benchmarking threshold_u8_cropped/512: Warming up for 500.00 ms
Benchmarking threshold_u8_cropped/512: Collecting 20 samples in estimated 2.0012 s (62k iterations)
Benchmarking threshold_u8_cropped/512: Analyzing
threshold_u8_cropped/512
                        time:   [16.392 µs 17.718 µs 18.935 µs]
                        change: [-13.500% -5.4300% +4.1846%] (p = 0.26 > 0.05)
                        No change in performance detected.
Benchmarking threshold_u8_cropped/1024
Benchmarking threshold_u8_cropped/1024: Warming up for 500.00 ms
Benchmarking threshold_u8_cropped/1024: Collecting 20 samples in estimated 2.0219 s (11k iterations)
Benchmarking threshold_u8_cropped/1024: Analyzing
threshold_u8_cropped/1024
                        time:   [91.285 µs 94.108 µs 97.592 µs]
                        change: [+5.1690% +8.9050% +12.951%] (p = 0.00 < 0.05)
                        Performance has regressed.

Benchmarking cast_f32_to_u8/256
Benchmarking cast_f32_to_u8/256: Warming up for 500.00 ms
Benchmarking cast_f32_to_u8/256: Collecting 20 samples in estimated 2.0063 s (13k iterations)
Benchmarking cast_f32_to_u8/256: Analyzing
cast_f32_to_u8/256      time:   [92.184 µs 100.62 µs 109.00 µs]
                        change: [+3.0613% +8.7456% +15.116%] (p = 0.01 < 0.05)
                        Performance has regressed.
Benchmarking cast_f32_to_u8/512
Benchmarking cast_f32_to_u8/512: Warming up for 500.00 ms
Benchmarking cast_f32_to_u8/512: Collecting 20 samples in estimated 2.1282 s (3150 iterations)
Benchmarking cast_f32_to_u8/512: Analyzing
cast_f32_to_u8/512      time:   [372.17 µs 381.92 µs 396.11 µs]
                        change: [+6.0029% +8.8942% +12.040%] (p = 0.00 < 0.05)
                        Performance has regressed.
Found 1 outliers among 20 measurements (5.00%)
  1 (5.00%) high mild
Benchmarking cast_f32_to_u8/1024
Benchmarking cast_f32_to_u8/1024: Warming up for 500.00 ms
Benchmarking cast_f32_to_u8/1024: Collecting 20 samples in estimated 2.9063 s (630 iterations)
Benchmarking cast_f32_to_u8/1024: Analyzing
cast_f32_to_u8/1024     time:   [1.9285 ms 2.1611 ms 2.4846 ms]
                        change: [+16.087% +31.912% +48.728%] (p = 0.00 < 0.05)
                        Performance has regressed.

Benchmarking cast_u8_to_f32/256
Benchmarking cast_u8_to_f32/256: Warming up for 500.00 ms
Benchmarking cast_u8_to_f32/256: Collecting 20 samples in estimated 2.0071 s (34k iterations)
Benchmarking cast_u8_to_f32/256: Analyzing
cast_u8_to_f32/256      time:   [41.582 µs 46.402 µs 49.808 µs]
                        change: [-13.357% +4.3656% +24.564%] (p = 0.66 > 0.05)
                        No change in performance detected.
Benchmarking cast_u8_to_f32/512
Benchmarking cast_u8_to_f32/512: Warming up for 500.00 ms
Benchmarking cast_u8_to_f32/512: Collecting 20 samples in estimated 2.0255 s (8190 iterations)
Benchmarking cast_u8_to_f32/512: Analyzing
cast_u8_to_f32/512      time:   [176.95 µs 179.11 µs 182.19 µs]
                        change: [-3.0664% -1.1517% +0.7285%] (p = 0.26 > 0.05)
                        No change in performance detected.
Benchmarking cast_u8_to_f32/1024
Benchmarking cast_u8_to_f32/1024: Warming up for 500.00 ms
Benchmarking cast_u8_to_f32/1024: Collecting 20 samples in estimated 2.1963 s (2100 iterations)
Benchmarking cast_u8_to_f32/1024: Analyzing
cast_u8_to_f32/1024     time:   [697.58 µs 704.85 µs 714.70 µs]
                        change: [-6.4639% -4.1555% -1.9132%] (p = 0.00 < 0.05)
                        Performance has improved.

Benchmarking invert_u8/256
Benchmarking invert_u8/256: Warming up for 500.00 ms
Benchmarking invert_u8/256: Collecting 20 samples in estimated 2.0026 s (125k iterations)
Benchmarking invert_u8/256: Analyzing
invert_u8/256           time:   [6.3662 µs 7.1074 µs 7.7023 µs]
                        change: [-9.6324% -1.1329% +8.0700%] (p = 0.81 > 0.05)
                        No change in performance detected.
Found 2 outliers among 20 measurements (10.00%)
  2 (10.00%) high mild
Benchmarking invert_u8/512
Benchmarking invert_u8/512: Warming up for 500.00 ms
Benchmarking invert_u8/512: Collecting 20 samples in estimated 2.0144 s (24k iterations)
Benchmarking invert_u8/512: Analyzing
invert_u8/512           time:   [27.806 µs 30.035 µs 31.636 µs]
                        change: [-10.246% +1.9878% +15.298%] (p = 0.76 > 0.05)
                        No change in performance detected.
Benchmarking invert_u8/1024
Benchmarking invert_u8/1024: Warming up for 500.00 ms
Benchmarking invert_u8/1024: Collecting 20 samples in estimated 2.0278 s (5040 iterations)
Benchmarking invert_u8/1024: Analyzing
invert_u8/1024          time:   [136.57 µs 137.41 µs 138.54 µs]
                        change: [-6.5143% -4.0171% -1.5568%] (p = 0.00 < 0.05)
                        Performance has improved.

Benchmarking adjust_gamma_u8/256
Benchmarking adjust_gamma_u8/256: Warming up for 500.00 ms
Benchmarking adjust_gamma_u8/256: Collecting 20 samples in estimated 2.0159 s (26k iterations)
Benchmarking adjust_gamma_u8/256: Analyzing
adjust_gamma_u8/256     time:   [66.705 µs 71.204 µs 76.409 µs]
                        change: [-23.049% -7.9159% +7.5533%] (p = 0.42 > 0.05)
                        No change in performance detected.
Benchmarking adjust_gamma_u8/512
Benchmarking adjust_gamma_u8/512: Warming up for 500.00 ms
Benchmarking adjust_gamma_u8/512: Collecting 20 samples in estimated 2.0348 s (5040 iterations)
Benchmarking adjust_gamma_u8/512: Analyzing
adjust_gamma_u8/512     time:   [265.04 µs 286.12 µs 304.67 µs]
                        change: [-3.8694% +3.5648% +11.266%] (p = 0.38 > 0.05)
                        No change in performance detected.
Found 1 outliers among 20 measurements (5.00%)
  1 (5.00%) high mild
Benchmarking adjust_gamma_u8/1024
Benchmarking adjust_gamma_u8/1024: Warming up for 500.00 ms
Benchmarking adjust_gamma_u8/1024: Collecting 20 samples in estimated 2.2548 s (1470 iterations)
Benchmarking adjust_gamma_u8/1024: Analyzing
adjust_gamma_u8/1024    time:   [1.1883 ms 1.2236 ms 1.2709 ms]
                        change: [-4.0707% +1.2620% +7.3221%] (p = 0.68 > 0.05)
                        No change in performance detected.
Found 1 outliers among 20 measurements (5.00%)
  1 (5.00%) high severe

Benchmarking normalize_preset_u8_to_f32/256
Benchmarking normalize_preset_u8_to_f32/256: Warming up for 500.00 ms
Benchmarking normalize_preset_u8_to_f32/256: Collecting 20 samples in estimated 2.0099 s (25k iterations)
Benchmarking normalize_preset_u8_to_f32/256: Analyzing
normalize_preset_u8_to_f32/256
                        time:   [73.438 µs 81.309 µs 87.508 µs]
                        change: [-44.511% -38.805% -32.916%] (p = 0.00 < 0.05)
                        Performance has improved.
Benchmarking normalize_preset_u8_to_f32/512
Benchmarking normalize_preset_u8_to_f32/512: Warming up for 500.00 ms
Benchmarking normalize_preset_u8_to_f32/512: Collecting 20 samples in estimated 2.0570 s (6300 iterations)
Benchmarking normalize_preset_u8_to_f32/512: Analyzing
normalize_preset_u8_to_f32/512
                        time:   [281.41 µs 299.17 µs 325.40 µs]
                        change: [-56.083% -50.830% -44.886%] (p = 0.00 < 0.05)
                        Performance has improved.
Benchmarking normalize_preset_u8_to_f32/1024
Benchmarking normalize_preset_u8_to_f32/1024: Warming up for 500.00 ms
Benchmarking normalize_preset_u8_to_f32/1024: Collecting 20 samples in estimated 2.0166 s (1260 iterations)
Benchmarking normalize_preset_u8_to_f32/1024: Analyzing
normalize_preset_u8_to_f32/1024
                        time:   [1.2682 ms 1.3885 ms 1.5304 ms]
                        change: [-37.522% -31.589% -25.509%] (p = 0.00 < 0.05)
                        Performance has improved.

Benchmarking normalize_zscore_u8/256
Benchmarking normalize_zscore_u8/256: Warming up for 500.00 ms
Benchmarking normalize_zscore_u8/256: Collecting 20 samples in estimated 2.0083 s (6930 iterations)
Benchmarking normalize_zscore_u8/256: Analyzing
normalize_zscore_u8/256 time:   [251.08 µs 267.69 µs 282.30 µs]
                        change: [-3.0241% +1.3268% +6.2599%] (p = 0.60 > 0.05)
                        No change in performance detected.
Benchmarking normalize_zscore_u8/512
Benchmarking normalize_zscore_u8/512: Warming up for 500.00 ms
Benchmarking normalize_zscore_u8/512: Collecting 20 samples in estimated 2.2402 s (1890 iterations)
Benchmarking normalize_zscore_u8/512: Analyzing
normalize_zscore_u8/512 time:   [1.0225 ms 1.0585 ms 1.0958 ms]
                        change: [-12.365% -9.9694% -7.0500%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 3 outliers among 20 measurements (15.00%)
  1 (5.00%) high mild
  2 (10.00%) high severe
Benchmarking normalize_zscore_u8/1024
Benchmarking normalize_zscore_u8/1024: Warming up for 500.00 ms
Benchmarking normalize_zscore_u8/1024: Collecting 20 samples in estimated 2.3086 s (420 iterations)
Benchmarking normalize_zscore_u8/1024: Analyzing
normalize_zscore_u8/1024
                        time:   [4.2885 ms 4.3935 ms 4.5909 ms]
                        change: [-7.1607% +0.8021% +8.1681%] (p = 0.84 > 0.05)
                        No change in performance detected.

Benchmarking adjust_contrast_u8/256
Benchmarking adjust_contrast_u8/256: Warming up for 500.00 ms
Benchmarking adjust_contrast_u8/256: Collecting 20 samples in estimated 2.0215 s (14k iterations)
Benchmarking adjust_contrast_u8/256: Analyzing
adjust_contrast_u8/256  time:   [114.91 µs 129.18 µs 139.09 µs]
                        change: [-15.896% -8.6175% -1.7908%] (p = 0.03 < 0.05)
                        Performance has improved.
Benchmarking adjust_contrast_u8/512
Benchmarking adjust_contrast_u8/512: Warming up for 500.00 ms
Benchmarking adjust_contrast_u8/512: Collecting 20 samples in estimated 2.0048 s (3150 iterations)
Benchmarking adjust_contrast_u8/512: Analyzing
adjust_contrast_u8/512  time:   [476.98 µs 501.77 µs 535.57 µs]
                        change: [-38.306% -35.010% -31.631%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 1 outliers among 20 measurements (5.00%)
  1 (5.00%) high mild
Benchmarking adjust_contrast_u8/1024
Benchmarking adjust_contrast_u8/1024: Warming up for 500.00 ms
Benchmarking adjust_contrast_u8/1024: Collecting 20 samples in estimated 2.0492 s (630 iterations)
Benchmarking adjust_contrast_u8/1024: Analyzing
adjust_contrast_u8/1024 time:   [2.0439 ms 2.1937 ms 2.4119 ms]
                        change: [-37.808% -30.116% -21.859%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 1 outliers among 20 measurements (5.00%)
  1 (5.00%) high mild

Benchmarking scale_u8/256
Benchmarking scale_u8/256: Warming up for 500.00 ms
Benchmarking scale_u8/256: Collecting 20 samples in estimated 2.0098 s (24k iterations)
Benchmarking scale_u8/256: Analyzing
scale_u8/256            time:   [72.690 µs 78.163 µs 81.896 µs]
                        change: [-2.1618% +14.195% +32.269%] (p = 0.10 > 0.05)
                        No change in performance detected.
Benchmarking scale_u8/512
Benchmarking scale_u8/512: Warming up for 500.00 ms
Benchmarking scale_u8/512: Collecting 20 samples in estimated 2.0673 s (5250 iterations)
Benchmarking scale_u8/512: Analyzing
scale_u8/512            time:   [280.51 µs 295.51 µs 310.77 µs]
                        change: [-18.260% -14.539% -11.061%] (p = 0.00 < 0.05)
                        Performance has improved.
Benchmarking scale_u8/1024
Benchmarking scale_u8/1024: Warming up for 500.00 ms
Benchmarking scale_u8/1024: Collecting 20 samples in estimated 2.0650 s (1260 iterations)
Benchmarking scale_u8/1024: Analyzing
scale_u8/1024           time:   [1.0445 ms 1.1096 ms 1.1677 ms]
                        change: [-37.601% -34.186% -30.216%] (p = 0.00 < 0.05)
                        Performance has improved.

Benchmarking normalize_preset_f32/256
Benchmarking normalize_preset_f32/256: Warming up for 500.00 ms
Benchmarking normalize_preset_f32/256: Collecting 20 samples in estimated 2.0520 s (4620 iterations)
Benchmarking normalize_preset_f32/256: Analyzing
normalize_preset_f32/256
                        time:   [513.44 µs 564.56 µs 619.83 µs]
                        change: [+25.023% +41.760% +54.929%] (p = 0.00 < 0.05)
                        Performance has regressed.
Benchmarking normalize_preset_f32/512
Benchmarking normalize_preset_f32/512: Warming up for 500.00 ms
Benchmarking normalize_preset_f32/512: Collecting 20 samples in estimated 2.1310 s (1050 iterations)
Benchmarking normalize_preset_f32/512: Analyzing
normalize_preset_f32/512
                        time:   [1.5510 ms 1.6214 ms 1.7091 ms]
                        change: [-4.4936% -0.3677% +3.8641%] (p = 0.87 > 0.05)
                        No change in performance detected.
Found 1 outliers among 20 measurements (5.00%)
  1 (5.00%) high mild
Benchmarking normalize_preset_f32/1024
Benchmarking normalize_preset_f32/1024: Warming up for 500.00 ms
Benchmarking normalize_preset_f32/1024: Collecting 20 samples in estimated 3.5137 s (420 iterations)
Benchmarking normalize_preset_f32/1024: Analyzing
normalize_preset_f32/1024
                        time:   [6.2839 ms 6.4837 ms 6.8032 ms]
                        change: [-29.972% -23.018% -14.986%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 1 outliers among 20 measurements (5.00%)
  1 (5.00%) high mild

Benchmarking fused_chain_u8/256
Benchmarking fused_chain_u8/256: Warming up for 500.00 ms
Benchmarking fused_chain_u8/256: Collecting 20 samples in estimated 2.0319 s (11k iterations)
Benchmarking fused_chain_u8/256: Analyzing
fused_chain_u8/256      time:   [159.05 µs 160.67 µs 162.95 µs]
                        change: [-3.3445% -0.1107% +3.1223%] (p = 0.95 > 0.05)
                        No change in performance detected.
Benchmarking fused_chain_u8/512
Benchmarking fused_chain_u8/512: Warming up for 500.00 ms
Benchmarking fused_chain_u8/512: Collecting 20 samples in estimated 2.0527 s (2730 iterations)
Benchmarking fused_chain_u8/512: Analyzing
fused_chain_u8/512      time:   [661.88 µs 689.99 µs 724.60 µs]
                        change: [+8.2469% +14.537% +21.670%] (p = 0.00 < 0.05)
                        Performance has regressed.
Benchmarking fused_chain_u8/1024
Benchmarking fused_chain_u8/1024: Warming up for 500.00 ms
Benchmarking fused_chain_u8/1024: Collecting 20 samples in estimated 2.5399 s (840 iterations)
Benchmarking fused_chain_u8/1024: Analyzing
fused_chain_u8/1024     time:   [2.6435 ms 2.7298 ms 2.8129 ms]
                        change: [+3.0277% +5.7561% +8.6692%] (p = 0.00 < 0.05)
                        Performance has regressed.
Found 2 outliers among 20 measurements (10.00%)
  2 (10.00%) high mild

Benchmarking fused_chain_f32/256
Benchmarking fused_chain_f32/256: Warming up for 500.00 ms
Benchmarking fused_chain_f32/256: Collecting 20 samples in estimated 2.0010 s (16k iterations)
Benchmarking fused_chain_f32/256: Analyzing
fused_chain_f32/256     time:   [64.293 µs 67.824 µs 71.856 µs]
                        change: [-12.472% -6.9176% -1.3290%] (p = 0.03 < 0.05)
                        Performance has improved.
Benchmarking fused_chain_f32/512
Benchmarking fused_chain_f32/512: Warming up for 500.00 ms
Benchmarking fused_chain_f32/512: Collecting 20 samples in estimated 2.0671 s (3780 iterations)
Benchmarking fused_chain_f32/512: Analyzing
fused_chain_f32/512     time:   [257.67 µs 267.40 µs 279.10 µs]
                        change: [-34.369% -31.819% -29.280%] (p = 0.00 < 0.05)
                        Performance has improved.
Benchmarking fused_chain_f32/1024
Benchmarking fused_chain_f32/1024: Warming up for 500.00 ms
Benchmarking fused_chain_f32/1024: Collecting 20 samples in estimated 2.4639 s (1050 iterations)
Benchmarking fused_chain_f32/1024: Analyzing
fused_chain_f32/1024    time:   [941.73 µs 977.98 µs 1.0095 ms]
                        change: [-58.864% -56.289% -53.544%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 2 outliers among 20 measurements (10.00%)
  2 (10.00%) high mild

Benchmarking normalize_zscore_f32/256
Benchmarking normalize_zscore_f32/256: Warming up for 500.00 ms
Benchmarking normalize_zscore_f32/256: Collecting 20 samples in estimated 2.0385 s (5040 iterations)
Benchmarking normalize_zscore_f32/256: Analyzing
normalize_zscore_f32/256
                        time:   [376.20 µs 383.99 µs 392.89 µs]
                        change: [-20.096% -16.717% -12.874%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 2 outliers among 20 measurements (10.00%)
  2 (10.00%) high mild
Benchmarking normalize_zscore_f32/512
Benchmarking normalize_zscore_f32/512: Warming up for 500.00 ms
Benchmarking normalize_zscore_f32/512: Collecting 20 samples in estimated 2.0771 s (1050 iterations)
Benchmarking normalize_zscore_f32/512: Analyzing
normalize_zscore_f32/512
                        time:   [1.4593 ms 1.4876 ms 1.5290 ms]
                        change: [-17.339% -12.496% -7.1381%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 3 outliers among 20 measurements (15.00%)
  2 (10.00%) high mild
  1 (5.00%) high severe
Benchmarking normalize_zscore_f32/1024
Benchmarking normalize_zscore_f32/1024: Warming up for 500.00 ms
Benchmarking normalize_zscore_f32/1024: Collecting 20 samples in estimated 3.1256 s (420 iterations)
Benchmarking normalize_zscore_f32/1024: Analyzing
normalize_zscore_f32/1024
                        time:   [6.2465 ms 6.3804 ms 6.5261 ms]
                        change: [-68.090% -66.301% -64.262%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 2 outliers among 20 measurements (10.00%)
  2 (10.00%) high mild

Benchmarking cast_u8_to_f32_flip_h/256
Benchmarking cast_u8_to_f32_flip_h/256: Warming up for 500.00 ms
Benchmarking cast_u8_to_f32_flip_h/256: Collecting 20 samples in estimated 2.0134 s (23k iterations)
Benchmarking cast_u8_to_f32_flip_h/256: Analyzing
cast_u8_to_f32_flip_h/256
                        time:   [66.210 µs 69.235 µs 72.187 µs]
                        change: [-28.550% -19.583% -8.6555%] (p = 0.00 < 0.05)
                        Performance has improved.
Benchmarking cast_u8_to_f32_flip_h/512
Benchmarking cast_u8_to_f32_flip_h/512: Warming up for 500.00 ms
Benchmarking cast_u8_to_f32_flip_h/512: Collecting 20 samples in estimated 2.0069 s (5040 iterations)
Benchmarking cast_u8_to_f32_flip_h/512: Analyzing
cast_u8_to_f32_flip_h/512
                        time:   [303.01 µs 320.35 µs 336.90 µs]
                        change: [-30.415% -27.062% -22.917%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 3 outliers among 20 measurements (15.00%)
  2 (10.00%) high mild
  1 (5.00%) high severe
Benchmarking cast_u8_to_f32_flip_h/1024
Benchmarking cast_u8_to_f32_flip_h/1024: Warming up for 500.00 ms
Benchmarking cast_u8_to_f32_flip_h/1024: Collecting 20 samples in estimated 2.3283 s (1470 iterations)
Benchmarking cast_u8_to_f32_flip_h/1024: Analyzing
cast_u8_to_f32_flip_h/1024
                        time:   [1.3811 ms 1.4598 ms 1.5284 ms]
                        change: [-1.7190% +6.9059% +16.747%] (p = 0.14 > 0.05)
                        No change in performance detected.

Benchmarking scale_f32_transposed/256
Benchmarking scale_f32_transposed/256: Warming up for 500.00 ms
Benchmarking scale_f32_transposed/256: Collecting 20 samples in estimated 2.0302 s (9240 iterations)
Benchmarking scale_f32_transposed/256: Analyzing
scale_f32_transposed/256
                        time:   [161.49 µs 168.40 µs 176.85 µs]
                        change: [-6.9274% -1.3639% +4.8351%] (p = 0.67 > 0.05)
                        No change in performance detected.
Benchmarking scale_f32_transposed/512
Benchmarking scale_f32_transposed/512: Warming up for 500.00 ms
Benchmarking scale_f32_transposed/512: Collecting 20 samples in estimated 2.1875 s (2100 iterations)
Benchmarking scale_f32_transposed/512: Analyzing
scale_f32_transposed/512
                        time:   [779.11 µs 812.18 µs 854.54 µs]
                        change: [-10.680% -6.3022% -2.1079%] (p = 0.01 < 0.05)
                        Performance has improved.
Benchmarking scale_f32_transposed/1024
Benchmarking scale_f32_transposed/1024: Warming up for 500.00 ms
Benchmarking scale_f32_transposed/1024: Collecting 20 samples in estimated 2.0732 s (80 iterations)
Benchmarking scale_f32_transposed/1024: Analyzing
scale_f32_transposed/1024
                        time:   [13.557 ms 14.152 ms 14.989 ms]
                        change: [+7.9462% +13.459% +20.375%] (p = 0.00 < 0.05)
                        Performance has regressed.
Found 1 outliers among 20 measurements (5.00%)
  1 (5.00%) high severe

Benchmarking grayscale_u8_flip_h/256
Benchmarking grayscale_u8_flip_h/256: Warming up for 500.00 ms
Benchmarking grayscale_u8_flip_h/256: Collecting 20 samples in estimated 2.0073 s (33k iterations)
Benchmarking grayscale_u8_flip_h/256: Analyzing
grayscale_u8_flip_h/256 time:   [48.608 µs 52.401 µs 57.733 µs]
                        change: [-16.471% -7.1551% +4.2940%] (p = 0.19 > 0.05)
                        No change in performance detected.
Benchmarking grayscale_u8_flip_h/512
Benchmarking grayscale_u8_flip_h/512: Warming up for 500.00 ms
Benchmarking grayscale_u8_flip_h/512: Collecting 20 samples in estimated 2.0328 s (7560 iterations)
Benchmarking grayscale_u8_flip_h/512: Analyzing
grayscale_u8_flip_h/512 time:   [189.76 µs 199.39 µs 215.92 µs]
                        change: [-21.250% -13.426% -4.4589%] (p = 0.01 < 0.05)
                        Performance has improved.
Found 3 outliers among 20 measurements (15.00%)
  3 (15.00%) high mild
Benchmarking grayscale_u8_flip_h/1024
Benchmarking grayscale_u8_flip_h/1024: Warming up for 500.00 ms
Benchmarking grayscale_u8_flip_h/1024: Collecting 20 samples in estimated 2.1095 s (1890 iterations)
Benchmarking grayscale_u8_flip_h/1024: Analyzing
grayscale_u8_flip_h/1024
                        time:   [868.21 µs 937.02 µs 1.0347 ms]
                        change: [-16.200% -10.052% -3.3758%] (p = 0.01 < 0.05)
                        Performance has improved.
Found 2 outliers among 20 measurements (10.00%)
  1 (5.00%) high mild
  1 (5.00%) high severe

Benchmarking grayscale_u8_flip_v/256
Benchmarking grayscale_u8_flip_v/256: Warming up for 500.00 ms
Benchmarking grayscale_u8_flip_v/256: Collecting 20 samples in estimated 2.0058 s (67k iterations)
Benchmarking grayscale_u8_flip_v/256: Analyzing
grayscale_u8_flip_v/256 time:   [16.841 µs 17.723 µs 18.637 µs]
                        change: [-12.025% -6.5222% -0.3064%] (p = 0.04 < 0.05)
                        Change within noise threshold.
Found 2 outliers among 20 measurements (10.00%)
  2 (10.00%) high mild
Benchmarking grayscale_u8_flip_v/512
Benchmarking grayscale_u8_flip_v/512: Warming up for 500.00 ms
Benchmarking grayscale_u8_flip_v/512: Collecting 20 samples in estimated 2.0019 s (16k iterations)
Benchmarking grayscale_u8_flip_v/512: Analyzing
grayscale_u8_flip_v/512 time:   [72.585 µs 76.701 µs 79.880 µs]
                        change: [-9.4694% -1.4091% +7.5555%] (p = 0.75 > 0.05)
                        No change in performance detected.
Benchmarking grayscale_u8_flip_v/1024
Benchmarking grayscale_u8_flip_v/1024: Warming up for 500.00 ms
Benchmarking grayscale_u8_flip_v/1024: Collecting 20 samples in estimated 2.0540 s (3360 iterations)
Benchmarking grayscale_u8_flip_v/1024: Analyzing
grayscale_u8_flip_v/1024
                        time:   [298.67 µs 314.88 µs 332.12 µs]
                        change: [-3.5832% +3.1001% +9.9713%] (p = 0.42 > 0.05)
                        No change in performance detected.

Benchmarking grayscale_u8_transpose/256
Benchmarking grayscale_u8_transpose/256: Warming up for 500.00 ms
Benchmarking grayscale_u8_transpose/256: Collecting 20 samples in estimated 2.0138 s (18k iterations)
Benchmarking grayscale_u8_transpose/256: Analyzing
grayscale_u8_transpose/256
                        time:   [103.58 µs 105.66 µs 108.11 µs]
                        change: [-1.6334% +0.9205% +3.9827%] (p = 0.52 > 0.05)
                        No change in performance detected.
Found 1 outliers among 20 measurements (5.00%)
  1 (5.00%) high mild
Benchmarking grayscale_u8_transpose/512
Benchmarking grayscale_u8_transpose/512: Warming up for 500.00 ms
Benchmarking grayscale_u8_transpose/512: Collecting 20 samples in estimated 2.0126 s (4410 iterations)
Benchmarking grayscale_u8_transpose/512: Analyzing
grayscale_u8_transpose/512
                        time:   [431.82 µs 490.54 µs 587.55 µs]
                        change: [-5.4304% +3.9079% +18.549%] (p = 0.55 > 0.05)
                        No change in performance detected.
Found 2 outliers among 20 measurements (10.00%)
  1 (5.00%) high mild
  1 (5.00%) high severe
Benchmarking grayscale_u8_transpose/1024
Benchmarking grayscale_u8_transpose/1024: Warming up for 500.00 ms
Benchmarking grayscale_u8_transpose/1024: Collecting 20 samples in estimated 2.3929 s (1260 iterations)
Benchmarking grayscale_u8_transpose/1024: Analyzing
grayscale_u8_transpose/1024
                        time:   [1.5659 ms 1.6230 ms 1.6758 ms]
                        change: [-17.082% -13.349% -9.5330%] (p = 0.00 < 0.05)
                        Performance has improved.

Benchmarking grayscale_u16_flip_v/256
Benchmarking grayscale_u16_flip_v/256: Warming up for 500.00 ms
Benchmarking grayscale_u16_flip_v/256: Collecting 20 samples in estimated 2.0106 s (12k iterations)
Benchmarking grayscale_u16_flip_v/256: Analyzing
grayscale_u16_flip_v/256
                        time:   [147.04 µs 149.39 µs 152.29 µs]
                        change: [-54.938% -54.134% -53.238%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 1 outliers among 20 measurements (5.00%)
  1 (5.00%) high severe
Benchmarking grayscale_u16_flip_v/512
Benchmarking grayscale_u16_flip_v/512: Warming up for 500.00 ms
Benchmarking grayscale_u16_flip_v/512: Collecting 20 samples in estimated 2.0594 s (2730 iterations)
Benchmarking grayscale_u16_flip_v/512: Analyzing
grayscale_u16_flip_v/512
                        time:   [629.18 µs 658.11 µs 699.15 µs]
                        change: [-56.890% -54.209% -51.218%] (p = 0.00 < 0.05)
                        Performance has improved.
Benchmarking grayscale_u16_flip_v/1024
Benchmarking grayscale_u16_flip_v/1024: Warming up for 500.00 ms
Benchmarking grayscale_u16_flip_v/1024: Collecting 20 samples in estimated 2.5279 s (840 iterations)
Benchmarking grayscale_u16_flip_v/1024: Analyzing
grayscale_u16_flip_v/1024
                        time:   [2.5144 ms 2.7085 ms 3.0065 ms]
                        change: [-59.590% -55.316% -50.412%] (p = 0.00 < 0.05)
                        Performance has improved.

Benchmarking invert_u8_flip_h/256
Benchmarking invert_u8_flip_h/256: Warming up for 500.00 ms
Benchmarking invert_u8_flip_h/256: Collecting 20 samples in estimated 2.0098 s (38k iterations)
Benchmarking invert_u8_flip_h/256: Analyzing
invert_u8_flip_h/256    time:   [41.517 µs 45.448 µs 51.004 µs]
                        change: [-11.969% -6.4488% +0.0956%] (p = 0.04 < 0.05)
                        Change within noise threshold.
Found 3 outliers among 20 measurements (15.00%)
  1 (5.00%) high mild
  2 (10.00%) high severe
Benchmarking invert_u8_flip_h/512
Benchmarking invert_u8_flip_h/512: Warming up for 500.00 ms
Benchmarking invert_u8_flip_h/512: Collecting 20 samples in estimated 2.0488 s (8190 iterations)
Benchmarking invert_u8_flip_h/512: Analyzing
invert_u8_flip_h/512    time:   [185.91 µs 204.21 µs 222.57 µs]
                        change: [-17.728% -12.859% -6.6662%] (p = 0.00 < 0.05)
                        Performance has improved.
Benchmarking invert_u8_flip_h/1024
Benchmarking invert_u8_flip_h/1024: Warming up for 500.00 ms
Benchmarking invert_u8_flip_h/1024: Collecting 20 samples in estimated 2.2053 s (1680 iterations)
Benchmarking invert_u8_flip_h/1024: Analyzing
invert_u8_flip_h/1024   time:   [859.37 µs 932.95 µs 997.41 µs]
                        change: [-22.691% -15.499% -7.3995%] (p = 0.00 < 0.05)
                        Performance has improved.

Benchmarking adjust_gamma_u8_flip_v/256
Benchmarking adjust_gamma_u8_flip_v/256: Warming up for 500.00 ms
Benchmarking adjust_gamma_u8_flip_v/256: Collecting 20 samples in estimated 2.0056 s (21k iterations)
Benchmarking adjust_gamma_u8_flip_v/256: Analyzing
adjust_gamma_u8_flip_v/256
                        time:   [66.403 µs 67.670 µs 68.791 µs]
                        change: [-37.248% -29.121% -19.553%] (p = 0.00 < 0.05)
                        Performance has improved.
Benchmarking adjust_gamma_u8_flip_v/512
Benchmarking adjust_gamma_u8_flip_v/512: Warming up for 500.00 ms
Benchmarking adjust_gamma_u8_flip_v/512: Collecting 20 samples in estimated 2.0463 s (5040 iterations)
Benchmarking adjust_gamma_u8_flip_v/512: Analyzing
adjust_gamma_u8_flip_v/512
                        time:   [289.14 µs 310.75 µs 336.26 µs]
                        change: [-26.463% -19.031% -10.738%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 1 outliers among 20 measurements (5.00%)
  1 (5.00%) high mild
Benchmarking adjust_gamma_u8_flip_v/1024
Benchmarking adjust_gamma_u8_flip_v/1024: Warming up for 500.00 ms
Benchmarking adjust_gamma_u8_flip_v/1024: Collecting 20 samples in estimated 2.2245 s (1260 iterations)
Benchmarking adjust_gamma_u8_flip_v/1024: Analyzing
adjust_gamma_u8_flip_v/1024
                        time:   [1.3506 ms 1.3865 ms 1.4160 ms]
                        change: [-19.664% -13.962% -7.3711%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 1 outliers among 20 measurements (5.00%)
  1 (5.00%) high severe

Benchmarking threshold_u8_flip_h/256
Benchmarking threshold_u8_flip_h/256: Warming up for 500.00 ms
Benchmarking threshold_u8_flip_h/256: Collecting 20 samples in estimated 2.0008 s (85k iterations)
Benchmarking threshold_u8_flip_h/256: Analyzing
threshold_u8_flip_h/256 time:   [19.081 µs 19.419 µs 19.921 µs]
                        change: [-15.484% -6.2404% +4.9837%] (p = 0.28 > 0.05)
                        No change in performance detected.
Found 4 outliers among 20 measurements (20.00%)
  4 (20.00%) high mild
Benchmarking threshold_u8_flip_h/512
Benchmarking threshold_u8_flip_h/512: Warming up for 500.00 ms
Benchmarking threshold_u8_flip_h/512: Collecting 20 samples in estimated 2.0009 s (26k iterations)
Benchmarking threshold_u8_flip_h/512: Analyzing
threshold_u8_flip_h/512 time:   [74.038 µs 79.588 µs 85.472 µs]
                        change: [-17.214% -9.4244% -0.9005%] (p = 0.04 < 0.05)
                        Change within noise threshold.
Found 1 outliers among 20 measurements (5.00%)
  1 (5.00%) high mild
Benchmarking threshold_u8_flip_h/1024
Benchmarking threshold_u8_flip_h/1024: Warming up for 500.00 ms
Benchmarking threshold_u8_flip_h/1024: Collecting 20 samples in estimated 2.0823 s (5250 iterations)
Benchmarking threshold_u8_flip_h/1024: Analyzing
threshold_u8_flip_h/1024
                        time:   [311.84 µs 328.63 µs 350.41 µs]
                        change: [-31.269% -26.571% -21.187%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 1 outliers among 20 measurements (5.00%)
  1 (5.00%) high mild

Benchmarking f16_per_element_f32/256
Benchmarking f16_per_element_f32/256: Warming up for 500.00 ms
Benchmarking f16_per_element_f32/256: Collecting 20 samples in estimated 2.0467 s (3990 iterations)
Benchmarking f16_per_element_f32/256: Analyzing
f16_per_element_f32/256 time:   [441.05 µs 452.32 µs 466.39 µs]
                        change: [+4.0395% +8.9560% +14.236%] (p = 0.00 < 0.05)
                        Performance has regressed.
Found 2 outliers among 20 measurements (10.00%)
  2 (10.00%) high mild
Benchmarking f16_per_element_f32/512
Benchmarking f16_per_element_f32/512: Warming up for 500.00 ms
Benchmarking f16_per_element_f32/512: Collecting 20 samples in estimated 2.2216 s (1050 iterations)
Benchmarking f16_per_element_f32/512: Analyzing
f16_per_element_f32/512 time:   [1.6590 ms 1.7089 ms 1.7823 ms]
                        change: [-2.6909% +2.0986% +7.1342%] (p = 0.41 > 0.05)
                        No change in performance detected.
Benchmarking f16_per_element_f32/1024
Benchmarking f16_per_element_f32/1024: Warming up for 500.00 ms

Warning: Unable to complete 20 samples in 2.0s. You may wish to increase target time to 2.2s, enable flat sampling, or reduce sample count to 10.
Benchmarking f16_per_element_f32/1024: Collecting 20 samples in estimated 2.2201 s (210 iterations)
Benchmarking f16_per_element_f32/1024: Analyzing
f16_per_element_f32/1024
                        time:   [8.3068 ms 9.4018 ms 10.410 ms]
                        change: [+7.3475% +19.528% +32.844%] (p = 0.00 < 0.05)
                        Performance has regressed.

Benchmarking f16_bits_f32/256
Benchmarking f16_bits_f32/256: Warming up for 500.00 ms
Benchmarking f16_bits_f32/256: Collecting 20 samples in estimated 2.0090 s (14k iterations)
Benchmarking f16_bits_f32/256: Analyzing
f16_bits_f32/256        time:   [76.179 µs 86.338 µs 93.389 µs]
                        change: [-11.872% -3.5810% +6.4781%] (p = 0.46 > 0.05)
                        No change in performance detected.
Benchmarking f16_bits_f32/512
Benchmarking f16_bits_f32/512: Warming up for 500.00 ms
Benchmarking f16_bits_f32/512: Collecting 20 samples in estimated 2.0880 s (3150 iterations)
Benchmarking f16_bits_f32/512: Analyzing
f16_bits_f32/512        time:   [376.04 µs 401.36 µs 432.47 µs]
                        change: [-5.6000% +0.2422% +6.4885%] (p = 0.94 > 0.05)
                        No change in performance detected.
Found 2 outliers among 20 measurements (10.00%)
  2 (10.00%) high severe
Benchmarking f16_bits_f32/1024
Benchmarking f16_bits_f32/1024: Warming up for 500.00 ms
Benchmarking f16_bits_f32/1024: Collecting 20 samples in estimated 2.9132 s (630 iterations)
Benchmarking f16_bits_f32/1024: Analyzing
f16_bits_f32/1024       time:   [2.3418 ms 2.5178 ms 2.6613 ms]
                        change: [+7.2375% +21.305% +35.466%] (p = 0.00 < 0.05)
                        Performance has regressed.

Benchmarking f16_per_element_u8/256
Benchmarking f16_per_element_u8/256: Warming up for 500.00 ms
Benchmarking f16_per_element_u8/256: Collecting 20 samples in estimated 2.0980 s (3990 iterations)
Benchmarking f16_per_element_u8/256: Analyzing
f16_per_element_u8/256  time:   [484.78 µs 514.89 µs 548.48 µs]
                        change: [-1.7759% +8.4749% +19.534%] (p = 0.12 > 0.05)
                        No change in performance detected.
Found 2 outliers among 20 measurements (10.00%)
  2 (10.00%) high mild
Benchmarking f16_per_element_u8/512
Benchmarking f16_per_element_u8/512: Warming up for 500.00 ms
Benchmarking f16_per_element_u8/512: Collecting 20 samples in estimated 2.2448 s (1050 iterations)
Benchmarking f16_per_element_u8/512: Analyzing
f16_per_element_u8/512  time:   [1.9763 ms 2.0508 ms 2.1228 ms]
                        change: [-7.0717% +0.2816% +7.8018%] (p = 0.94 > 0.05)
                        No change in performance detected.
Found 2 outliers among 20 measurements (10.00%)
  1 (5.00%) high mild
  1 (5.00%) high severe
Benchmarking f16_per_element_u8/1024
Benchmarking f16_per_element_u8/1024: Warming up for 500.00 ms

Warning: Unable to complete 20 samples in 2.0s. You may wish to increase target time to 2.1s, enable flat sampling, or reduce sample count to 10.
Benchmarking f16_per_element_u8/1024: Collecting 20 samples in estimated 2.0591 s (210 iterations)
Benchmarking f16_per_element_u8/1024: Analyzing
f16_per_element_u8/1024 time:   [8.5847 ms 8.9982 ms 9.5639 ms]
                        change: [-5.2678% +2.3454% +9.9352%] (p = 0.56 > 0.05)
                        No change in performance detected.
Found 4 outliers among 20 measurements (20.00%)
  4 (20.00%) high mild

Benchmarking f16_bits_u8/256
Benchmarking f16_bits_u8/256: Warming up for 500.00 ms
Benchmarking f16_bits_u8/256: Collecting 20 samples in estimated 2.0182 s (22k iterations)
Benchmarking f16_bits_u8/256: Analyzing
f16_bits_u8/256         time:   [66.542 µs 68.566 µs 72.028 µs]
                        change: [-2.8813% +3.0550% +10.454%] (p = 0.37 > 0.05)
                        No change in performance detected.
Found 2 outliers among 20 measurements (10.00%)
  1 (5.00%) high mild
  1 (5.00%) high severe
Benchmarking f16_bits_u8/512
Benchmarking f16_bits_u8/512: Warming up for 500.00 ms
Benchmarking f16_bits_u8/512: Collecting 20 samples in estimated 2.0365 s (5670 iterations)
Benchmarking f16_bits_u8/512: Analyzing
f16_bits_u8/512         time:   [319.96 µs 332.78 µs 348.79 µs]
                        change: [-1.8142% +3.3316% +8.6566%] (p = 0.23 > 0.05)
                        No change in performance detected.
Found 3 outliers among 20 measurements (15.00%)
  2 (10.00%) high mild
  1 (5.00%) high severe
Benchmarking f16_bits_u8/1024
Benchmarking f16_bits_u8/1024: Warming up for 500.00 ms
Benchmarking f16_bits_u8/1024: Collecting 20 samples in estimated 2.0455 s (1260 iterations)
Benchmarking f16_bits_u8/1024: Analyzing
f16_bits_u8/1024        time:   [1.3582 ms 1.4027 ms 1.4603 ms]
                        change: [-11.309% -5.1174% +1.7127%] (p = 0.16 > 0.05)
                        No change in performance detected.
Found 2 outliers among 20 measurements (10.00%)
  2 (10.00%) high mild

Benchmarking f16_per_element_f32_transposed/256
Benchmarking f16_per_element_f32_transposed/256: Warming up for 500.00 ms
Benchmarking f16_per_element_f32_transposed/256: Collecting 20 samples in estimated 2.1099 s (3570 iterations)
Benchmarking f16_per_element_f32_transposed/256: Analyzing
f16_per_element_f32_transposed/256
                        time:   [549.97 µs 566.35 µs 585.78 µs]
                        change: [-6.0406% -1.0604% +3.7765%] (p = 0.70 > 0.05)
                        No change in performance detected.
Found 2 outliers among 20 measurements (10.00%)
  2 (10.00%) high mild
Benchmarking f16_per_element_f32_transposed/512
Benchmarking f16_per_element_f32_transposed/512: Warming up for 500.00 ms
Benchmarking f16_per_element_f32_transposed/512: Collecting 20 samples in estimated 2.3566 s (840 iterations)
Benchmarking f16_per_element_f32_transposed/512: Analyzing
f16_per_element_f32_transposed/512
                        time:   [2.4814 ms 2.5828 ms 2.7230 ms]
                        change: [+0.4262% +6.0478% +11.591%] (p = 0.04 < 0.05)
                        Change within noise threshold.
Found 1 outliers among 20 measurements (5.00%)
  1 (5.00%) high mild
Benchmarking f16_per_element_f32_transposed/1024
Benchmarking f16_per_element_f32_transposed/1024: Warming up for 500.00 ms
Benchmarking f16_per_element_f32_transposed/1024: Collecting 20 samples in estimated 2.1052 s (60 iterations)
Benchmarking f16_per_element_f32_transposed/1024: Analyzing
f16_per_element_f32_transposed/1024
                        time:   [23.624 ms 24.371 ms 25.259 ms]
                        change: [-1.5013% +3.1457% +8.4521%] (p = 0.20 > 0.05)
                        No change in performance detected.
Found 2 outliers among 20 measurements (10.00%)
  1 (5.00%) high mild
  1 (5.00%) high severe

Benchmarking f16_bits_f32_transposed/256
Benchmarking f16_bits_f32_transposed/256: Warming up for 500.00 ms
Benchmarking f16_bits_f32_transposed/256: Collecting 20 samples in estimated 2.0394 s (8190 iterations)
Benchmarking f16_bits_f32_transposed/256: Analyzing
f16_bits_f32_transposed/256
                        time:   [171.96 µs 177.82 µs 184.86 µs]
                        change: [+0.4544% +7.7141% +14.842%] (p = 0.04 < 0.05)
                        Change within noise threshold.
Benchmarking f16_bits_f32_transposed/512
Benchmarking f16_bits_f32_transposed/512: Warming up for 500.00 ms
Benchmarking f16_bits_f32_transposed/512: Collecting 20 samples in estimated 2.0918 s (1890 iterations)
Benchmarking f16_bits_f32_transposed/512: Analyzing
f16_bits_f32_transposed/512
                        time:   [852.53 µs 885.76 µs 936.25 µs]
                        change: [+5.0320% +11.092% +17.493%] (p = 0.00 < 0.05)
                        Performance has regressed.
Benchmarking f16_bits_f32_transposed/1024
Benchmarking f16_bits_f32_transposed/1024: Warming up for 500.00 ms

Warning: Unable to complete 20 samples in 2.0s. You may wish to increase target time to 2.2s, enable flat sampling, or reduce sample count to 10.
Benchmarking f16_bits_f32_transposed/1024: Collecting 20 samples in estimated 2.1508 s (210 iterations)
Benchmarking f16_bits_f32_transposed/1024: Analyzing
f16_bits_f32_transposed/1024
                        time:   [7.1632 ms 7.4678 ms 7.8338 ms]
                        change: [+1.7841% +9.3734% +17.740%] (p = 0.02 < 0.05)
                        Performance has regressed.
Found 1 outliers among 20 measurements (5.00%)
  1 (5.00%) high mild
