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 2.0059 s (32k iterations)
Benchmarking grayscale_u8_rgb/256: Analyzing
grayscale_u8_rgb/256    time:   [17.110 µs 18.635 µs 19.826 µs]
                        change: [-16.327% -3.5659% +10.313%] (p = 0.63 > 0.05)
                        No change in performance detected.
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 2.0144 s (9870 iterations)
Benchmarking grayscale_u8_rgb/512: Analyzing
grayscale_u8_rgb/512    time:   [55.598 µs 57.820 µs 60.743 µs]
                        change: [-18.917% -12.210% -5.8952%] (p = 0.00 < 0.05)
                        Performance has improved.
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 2.0332 s (3990 iterations)
Benchmarking grayscale_u8_rgb/1024: Analyzing
grayscale_u8_rgb/1024   time:   [232.97 µs 241.69 µs 250.78 µs]
                        change: [-23.265% -17.245% -11.036%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 4 outliers among 20 measurements (20.00%)
  2 (10.00%) high mild
  2 (10.00%) high severe

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 2.0083 s (21k iterations)
Benchmarking grayscale_f32_rgb/256: Analyzing
grayscale_f32_rgb/256   time:   [47.888 µs 51.235 µs 54.820 µs]
                        change: [-58.951% -56.304% -53.366%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 2 outliers among 20 measurements (10.00%)
  2 (10.00%) high mild
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 2.0378 s (1890 iterations)
Benchmarking grayscale_f32_rgb/512: Analyzing
grayscale_f32_rgb/512   time:   [208.10 µs 224.52 µs 237.11 µs]
                        change: [-49.485% -46.794% -43.841%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 3 outliers among 20 measurements (15.00%)
  3 (15.00%) high mild
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 2.4131 s (1050 iterations)
Benchmarking grayscale_f32_rgb/1024: Analyzing
grayscale_f32_rgb/1024  time:   [983.88 µs 1.0129 ms 1.0458 ms]
                        change: [-50.293% -43.559% -36.316%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 2 outliers among 20 measurements (10.00%)
  1 (5.00%) high mild
  1 (5.00%) 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 2.0000 s (300k iterations)
Benchmarking threshold_u8/256: Analyzing
threshold_u8/256        time:   [2.8517 µs 3.0112 µs 3.1652 µs]
                        change: [+1.0908% +7.4322% +14.492%] (p = 0.04 < 0.05)
                        Performance has regressed.
Benchmarking threshold_u8/512
Benchmarking threshold_u8/512: Warming up for 500.00 ms
Benchmarking threshold_u8/512: Collecting 20 samples in estimated 2.0023 s (84k iterations)
Benchmarking threshold_u8/512: Analyzing
threshold_u8/512        time:   [8.7357 µs 9.2372 µs 9.5570 µs]
                        change: [-11.706% -2.8352% +7.1192%] (p = 0.57 > 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 2.0028 s (17k iterations)
Benchmarking threshold_u8/1024: Analyzing
threshold_u8/1024       time:   [36.249 µs 40.468 µs 42.958 µs]
                        change: [-18.632% -4.5474% +11.940%] (p = 0.58 > 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 2.0009 s (222k iterations)
Benchmarking threshold_u8_cropped/256: Analyzing
threshold_u8_cropped/256
                        time:   [5.8927 µs 6.5402 µs 7.2815 µs]
                        change: [+4.4793% +15.065% +26.835%] (p = 0.01 < 0.05)
                        Performance has regressed.
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 2.0030 s (67k iterations)
Benchmarking threshold_u8_cropped/512: Analyzing
threshold_u8_cropped/512
                        time:   [16.064 µs 16.781 µs 17.438 µs]
                        change: [+12.789% +19.528% +26.454%] (p = 0.00 < 0.05)
                        Performance has regressed.
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 2.0266 s (13k iterations)
Benchmarking threshold_u8_cropped/1024: Analyzing
threshold_u8_cropped/1024
                        time:   [92.404 µs 96.905 µs 100.78 µs]
                        change: [+5.0547% +9.6442% +14.272%] (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 2.0052 s (14k iterations)
Benchmarking cast_f32_to_u8/256: Analyzing
cast_f32_to_u8/256      time:   [99.326 µs 104.79 µs 109.38 µs]
                        change: [+2.9912% +11.059% +18.345%] (p = 0.01 < 0.05)
                        Performance has regressed.
Found 1 outliers among 20 measurements (5.00%)
  1 (5.00%) high mild
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 2.0528 s (3150 iterations)
Benchmarking cast_f32_to_u8/512: Analyzing
cast_f32_to_u8/512      time:   [384.75 µs 430.97 µs 476.22 µs]
                        change: [-4.8067% +2.6045% +10.684%] (p = 0.54 > 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 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 2.1603 s (630 iterations)
Benchmarking cast_f32_to_u8/1024: Analyzing
cast_f32_to_u8/1024     time:   [1.7663 ms 1.8878 ms 2.0098 ms]
                        change: [+6.7130% +15.805% +26.025%] (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 2.0050 s (34k iterations)
Benchmarking cast_u8_to_f32/256: Analyzing
cast_u8_to_f32/256      time:   [41.047 µs 44.698 µs 47.377 µs]
                        change: [-16.822% +0.3667% +20.252%] (p = 0.97 > 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 2.0146 s (7980 iterations)
Benchmarking cast_u8_to_f32/512: Analyzing
cast_u8_to_f32/512      time:   [183.36 µs 187.12 µs 190.97 µs]
                        change: [-5.7146% -3.0104% -0.4147%] (p = 0.04 < 0.05)
                        Change within noise threshold.
Found 1 outliers among 20 measurements (5.00%)
  1 (5.00%) high mild
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 2.0206 s (1890 iterations)
Benchmarking cast_u8_to_f32/1024: Analyzing
cast_u8_to_f32/1024     time:   [775.50 µs 799.41 µs 821.54 µs]
                        change: [-0.5821% +3.7591% +7.8630%] (p = 0.09 > 0.05)
                        No change in performance detected.

Benchmarking invert_u8/256
Benchmarking invert_u8/256: Warming up for 500.00 ms
Benchmarking invert_u8/256: Collecting 20 samples in estimated 2.0014 s (123k iterations)
Benchmarking invert_u8/256: Analyzing
invert_u8/256           time:   [6.4885 µs 7.0279 µs 7.4598 µs]
                        change: [-7.9574% +0.2316% +9.4304%] (p = 0.96 > 0.05)
                        No change in performance detected.
Benchmarking invert_u8/512
Benchmarking invert_u8/512: Warming up for 500.00 ms
Benchmarking invert_u8/512: Collecting 20 samples in estimated 2.0062 s (27k iterations)
Benchmarking invert_u8/512: Analyzing
invert_u8/512           time:   [28.226 µs 30.534 µs 32.080 µs]
                        change: [-8.1127% +5.7067% +21.140%] (p = 0.43 > 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 2.0842 s (5040 iterations)
Benchmarking invert_u8/1024: Analyzing
invert_u8/1024          time:   [144.32 µs 147.76 µs 151.55 µs]
                        change: [+0.2796% +3.8745% +7.4584%] (p = 0.04 < 0.05)
                        Change within noise threshold.

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 2.0121 s (26k iterations)
Benchmarking adjust_gamma_u8/256: Analyzing
adjust_gamma_u8/256     time:   [59.931 µs 65.172 µs 70.245 µs]
                        change: [-6.6214% -1.2782% +4.8269%] (p = 0.70 > 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 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 2.0341 s (6300 iterations)
Benchmarking adjust_gamma_u8/512: Analyzing
adjust_gamma_u8/512     time:   [246.02 µs 253.07 µs 264.56 µs]
                        change: [+6.1043% +11.108% +16.215%] (p = 0.00 < 0.05)
                        Performance has regressed.
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 2.2899 s (1470 iterations)
Benchmarking adjust_gamma_u8/1024: Analyzing
adjust_gamma_u8/1024    time:   [1.1211 ms 1.1344 ms 1.1590 ms]
                        change: [-4.3283% -0.3376% +3.8179%] (p = 0.88 > 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 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 2.0055 s (26k iterations)
Benchmarking normalize_preset_u8_to_f32/256: Analyzing
normalize_preset_u8_to_f32/256
                        time:   [66.696 µs 69.477 µs 72.046 µs]
                        change: [-45.338% -41.914% -38.652%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 2 outliers among 20 measurements (10.00%)
  2 (10.00%) high mild
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 2.0680 s (5460 iterations)
Benchmarking normalize_preset_u8_to_f32/512: Analyzing
normalize_preset_u8_to_f32/512
                        time:   [261.59 µs 280.74 µs 307.71 µs]
                        change: [-43.953% -39.521% -34.996%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 1 outliers among 20 measurements (5.00%)
  1 (5.00%) high mild
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 2.1024 s (1470 iterations)
Benchmarking normalize_preset_u8_to_f32/1024: Analyzing
normalize_preset_u8_to_f32/1024
                        time:   [1.1656 ms 1.2182 ms 1.2787 ms]
                        change: [-41.648% -38.545% -35.203%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 2 outliers among 20 measurements (10.00%)
  1 (5.00%) high mild
  1 (5.00%) high severe

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 2.0361 s (7770 iterations)
Benchmarking normalize_zscore_u8/256: Analyzing
normalize_zscore_u8/256 time:   [257.09 µs 265.34 µs 273.04 µs]
                        change: [+5.8885% +8.6073% +11.561%] (p = 0.00 < 0.05)
                        Performance has regressed.
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 2.1929 s (1890 iterations)
Benchmarking normalize_zscore_u8/512: Analyzing
normalize_zscore_u8/512 time:   [1.0953 ms 1.1234 ms 1.1595 ms]
                        change: [-1.3621% +2.1371% +5.5016%] (p = 0.26 > 0.05)
                        No change in performance detected.
Found 1 outliers among 20 measurements (5.00%)
  1 (5.00%) high mild
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 2.8492 s (630 iterations)
Benchmarking normalize_zscore_u8/1024: Analyzing
normalize_zscore_u8/1024
                        time:   [4.4223 ms 4.4963 ms 4.6099 ms]
                        change: [-3.4931% -0.0747% +3.6457%] (p = 0.97 > 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 2.0111 s (12k iterations)
Benchmarking adjust_contrast_u8/256: Analyzing
adjust_contrast_u8/256  time:   [122.06 µs 126.54 µs 132.88 µs]
                        change: [-11.346% -4.0220% +4.6389%] (p = 0.36 > 0.05)
                        No change in performance detected.
Found 4 outliers among 20 measurements (20.00%)
  1 (5.00%) high mild
  3 (15.00%) high severe
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 2.1203 s (3570 iterations)
Benchmarking adjust_contrast_u8/512: Analyzing
adjust_contrast_u8/512  time:   [573.91 µs 599.49 µs 633.14 µs]
                        change: [-24.889% -22.460% -19.598%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 3 outliers among 20 measurements (15.00%)
  1 (5.00%) low mild
  2 (10.00%) high severe
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 2.3945 s (1050 iterations)
Benchmarking adjust_contrast_u8/1024: Analyzing
adjust_contrast_u8/1024 time:   [2.3474 ms 2.4026 ms 2.4848 ms]
                        change: [-26.161% -23.551% -20.735%] (p = 0.00 < 0.05)
                        Performance has improved.

Benchmarking scale_u8/256
Benchmarking scale_u8/256: Warming up for 500.00 ms
Benchmarking scale_u8/256: Collecting 20 samples in estimated 2.0031 s (24k iterations)
Benchmarking scale_u8/256: Analyzing
scale_u8/256            time:   [55.807 µs 57.820 µs 59.924 µs]
                        change: [-13.453% -4.8069% +5.6700%] (p = 0.36 > 0.05)
                        No change in performance detected.
Found 3 outliers among 20 measurements (15.00%)
  3 (15.00%) high severe
Benchmarking scale_u8/512
Benchmarking scale_u8/512: Warming up for 500.00 ms
Benchmarking scale_u8/512: Collecting 20 samples in estimated 2.0587 s (5250 iterations)
Benchmarking scale_u8/512: Analyzing
scale_u8/512            time:   [321.25 µs 328.34 µs 340.08 µs]
                        change: [-17.150% -13.239% -8.7275%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 2 outliers among 20 measurements (10.00%)
  2 (10.00%) high severe
Benchmarking scale_u8/1024
Benchmarking scale_u8/1024: Warming up for 500.00 ms
Benchmarking scale_u8/1024: Collecting 20 samples in estimated 2.0243 s (1470 iterations)
Benchmarking scale_u8/1024: Analyzing
scale_u8/1024           time:   [1.2659 ms 1.2986 ms 1.3328 ms]
                        change: [-16.900% -14.228% -11.747%] (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 2.0526 s (4620 iterations)
Benchmarking normalize_preset_f32/256: Analyzing
normalize_preset_f32/256
                        time:   [378.42 µs 386.33 µs 394.61 µs]
                        change: [-15.873% -9.6133% -3.1581%] (p = 0.01 < 0.05)
                        Performance has improved.
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 2.3914 s (1260 iterations)
Benchmarking normalize_preset_f32/512: Analyzing
normalize_preset_f32/512
                        time:   [1.5852 ms 1.6587 ms 1.7446 ms]
                        change: [-3.1127% +1.6031% +6.5644%] (p = 0.51 > 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 3.8242 s (420 iterations)
Benchmarking normalize_preset_f32/1024: Analyzing
normalize_preset_f32/1024
                        time:   [6.0914 ms 6.2970 ms 6.5456 ms]
                        change: [-41.508% -33.273% -24.087%] (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 2.0339 s (11k iterations)
Benchmarking fused_chain_u8/256: Analyzing
fused_chain_u8/256      time:   [157.46 µs 159.85 µs 162.16 µs]
                        change: [-11.986% -8.4941% -4.7312%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 1 outliers among 20 measurements (5.00%)
  1 (5.00%) high mild
Benchmarking fused_chain_u8/512
Benchmarking fused_chain_u8/512: Warming up for 500.00 ms
Benchmarking fused_chain_u8/512: Collecting 20 samples in estimated 2.0608 s (2730 iterations)
Benchmarking fused_chain_u8/512: Analyzing
fused_chain_u8/512      time:   [641.71 µs 661.62 µs 684.85 µs]
                        change: [-9.9966% -3.4575% +2.9584%] (p = 0.34 > 0.05)
                        No change in performance detected.
Found 1 outliers among 20 measurements (5.00%)
  1 (5.00%) high mild
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 2.5104 s (840 iterations)
Benchmarking fused_chain_u8/1024: Analyzing
fused_chain_u8/1024     time:   [2.6848 ms 2.8290 ms 3.0309 ms]
                        change: [+0.8492% +6.8197% +12.962%] (p = 0.04 < 0.05)
                        Change within noise threshold.

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 2.0098 s (17k iterations)
Benchmarking fused_chain_f32/256: Analyzing
fused_chain_f32/256     time:   [59.981 µs 63.549 µs 66.860 µs]
                        change: [-15.651% -10.619% -5.0107%] (p = 0.00 < 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 2.0226 s (3780 iterations)
Benchmarking fused_chain_f32/512: Analyzing
fused_chain_f32/512     time:   [234.92 µs 238.13 µs 240.55 µs]
                        change: [-50.816% -49.544% -48.324%] (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 2.3230 s (1050 iterations)
Benchmarking fused_chain_f32/1024: Analyzing
fused_chain_f32/1024    time:   [884.13 µs 918.90 µs 972.21 µs]
                        change: [-57.350% -54.630% -51.811%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 2 outliers among 20 measurements (10.00%)
  1 (5.00%) high mild
  1 (5.00%) high severe

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 2.0288 s (4620 iterations)
Benchmarking normalize_zscore_f32/256: Analyzing
normalize_zscore_f32/256
                        time:   [355.67 µs 362.58 µs 371.33 µs]
                        change: [-13.249% -10.976% -8.6899%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 1 outliers among 20 measurements (5.00%)
  1 (5.00%) 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 2.2638 s (1260 iterations)
Benchmarking normalize_zscore_f32/512: Analyzing
normalize_zscore_f32/512
                        time:   [1.4706 ms 1.5253 ms 1.5970 ms]
                        change: [-16.804% -13.876% -10.766%] (p = 0.00 < 0.05)
                        Performance has improved.
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 3.6543 s (420 iterations)
Benchmarking normalize_zscore_f32/1024: Analyzing
normalize_zscore_f32/1024
                        time:   [6.0675 ms 6.2946 ms 6.5964 ms]
                        change: [-58.141% -56.085% -54.039%] (p = 0.00 < 0.05)
                        Performance has improved.

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 2.0054 s (23k iterations)
Benchmarking cast_u8_to_f32_flip_h/256: Analyzing
cast_u8_to_f32_flip_h/256
                        time:   [65.757 µs 68.144 µs 70.086 µs]
                        change: [-7.9878% -2.7322% +2.5889%] (p = 0.33 > 0.05)
                        No change in performance detected.
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 2.0522 s (5460 iterations)
Benchmarking cast_u8_to_f32_flip_h/512: Analyzing
cast_u8_to_f32_flip_h/512
                        time:   [311.63 µs 317.27 µs 323.07 µs]
                        change: [-15.890% -10.945% -5.4924%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 4 outliers among 20 measurements (20.00%)
  3 (15.00%) 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 2.1239 s (1260 iterations)
Benchmarking cast_u8_to_f32_flip_h/1024: Analyzing
cast_u8_to_f32_flip_h/1024
                        time:   [1.3059 ms 1.3282 ms 1.3503 ms]
                        change: [-22.473% -15.348% -6.7936%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 1 outliers among 20 measurements (5.00%)
  1 (5.00%) high severe

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 2.0471 s (8610 iterations)
Benchmarking scale_f32_transposed/256: Analyzing
scale_f32_transposed/256
                        time:   [163.81 µs 171.61 µs 181.48 µs]
                        change: [+0.3785% +6.6000% +13.331%] (p = 0.05 < 0.05)
                        Change within noise threshold.
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 2.2201 s (2100 iterations)
Benchmarking scale_f32_transposed/512: Analyzing
scale_f32_transposed/512
                        time:   [774.88 µs 792.18 µs 811.55 µs]
                        change: [-8.8557% -6.2116% -3.3690%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 1 outliers among 20 measurements (5.00%)
  1 (5.00%) high mild
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 2.2574 s (100 iterations)
Benchmarking scale_f32_transposed/1024: Analyzing
scale_f32_transposed/1024
                        time:   [13.467 ms 14.062 ms 14.669 ms]
                        change: [+7.7911% +13.604% +19.244%] (p = 0.00 < 0.05)
                        Performance has regressed.

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 2.0107 s (30k iterations)
Benchmarking grayscale_u8_flip_h/256: Analyzing
grayscale_u8_flip_h/256 time:   [50.312 µs 52.467 µs 55.061 µs]
                        change: [-8.2929% -2.9147% +2.3821%] (p = 0.32 > 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 2.0212 s (7140 iterations)
Benchmarking grayscale_u8_flip_h/512: Analyzing
grayscale_u8_flip_h/512 time:   [195.72 µs 206.70 µs 217.65 µs]
                        change: [-15.677% -11.403% -6.6817%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 1 outliers among 20 measurements (5.00%)
  1 (5.00%) 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 2.1861 s (1890 iterations)
Benchmarking grayscale_u8_flip_h/1024: Analyzing
grayscale_u8_flip_h/1024
                        time:   [825.24 µs 875.61 µs 953.30 µs]
                        change: [-22.826% -17.549% -11.743%] (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 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 2.0001 s (64k iterations)
Benchmarking grayscale_u8_flip_v/256: Analyzing
grayscale_u8_flip_v/256 time:   [17.316 µs 18.371 µs 19.487 µs]
                        change: [+10.481% +16.264% +23.171%] (p = 0.00 < 0.05)
                        Performance has regressed.
Found 1 outliers among 20 measurements (5.00%)
  1 (5.00%) 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 2.0039 s (15k iterations)
Benchmarking grayscale_u8_flip_v/512: Analyzing
grayscale_u8_flip_v/512 time:   [73.675 µs 81.689 µs 88.883 µs]
                        change: [-2.3133% +8.6687% +21.087%] (p = 0.16 > 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 2.0897 s (3780 iterations)
Benchmarking grayscale_u8_flip_v/1024: Analyzing
grayscale_u8_flip_v/1024
                        time:   [332.77 µs 343.46 µs 356.68 µs]
                        change: [+12.097% +17.885% +24.321%] (p = 0.00 < 0.05)
                        Performance has regressed.

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 2.0177 s (17k iterations)
Benchmarking grayscale_u8_transpose/256: Analyzing
grayscale_u8_transpose/256
                        time:   [104.02 µs 106.04 µs 108.40 µs]
                        change: [+0.6751% +3.1558% +5.8021%] (p = 0.02 < 0.05)
                        Change within noise threshold.
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 2.0378 s (4620 iterations)
Benchmarking grayscale_u8_transpose/512: Analyzing
grayscale_u8_transpose/512
                        time:   [403.82 µs 421.26 µs 435.60 µs]
                        change: [-2.9354% +0.6713% +4.3792%] (p = 0.74 > 0.05)
                        No change in performance detected.
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 2.1824 s (1050 iterations)
Benchmarking grayscale_u8_transpose/1024: Analyzing
grayscale_u8_transpose/1024
                        time:   [1.5963 ms 1.6538 ms 1.7026 ms]
                        change: [-11.222% -6.9983% -2.6936%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 1 outliers among 20 measurements (5.00%)
  1 (5.00%) high mild

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 2.0152 s (12k iterations)
Benchmarking grayscale_u16_flip_v/256: Analyzing
grayscale_u16_flip_v/256
                        time:   [151.97 µs 158.78 µs 165.89 µs]
                        change: [-53.934% -51.383% -48.933%] (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 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 2.0329 s (2520 iterations)
Benchmarking grayscale_u16_flip_v/512: Analyzing
grayscale_u16_flip_v/512
                        time:   [630.70 µs 663.53 µs 705.85 µs]
                        change: [-51.480% -48.217% -45.070%] (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 2.6201 s (840 iterations)
Benchmarking grayscale_u16_flip_v/1024: Analyzing
grayscale_u16_flip_v/1024
                        time:   [2.5019 ms 2.5976 ms 2.7259 ms]
                        change: [-54.813% -52.323% -49.759%] (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 2.0105 s (37k iterations)
Benchmarking invert_u8_flip_h/256: Analyzing
invert_u8_flip_h/256    time:   [40.931 µs 42.691 µs 44.988 µs]
                        change: [-4.1128% -0.1361% +3.6216%] (p = 0.95 > 0.05)
                        No change in performance detected.
Found 2 outliers among 20 measurements (10.00%)
  2 (10.00%) high mild
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 2.0475 s (7980 iterations)
Benchmarking invert_u8_flip_h/512: Analyzing
invert_u8_flip_h/512    time:   [202.83 µs 219.14 µs 240.00 µs]
                        change: [-5.4607% +2.1618% +10.232%] (p = 0.62 > 0.05)
                        No change in performance detected.
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 2.1756 s (1890 iterations)
Benchmarking invert_u8_flip_h/1024: Analyzing
invert_u8_flip_h/1024   time:   [876.67 µs 916.88 µs 969.16 µs]
                        change: [-9.1811% -3.5171% +2.3330%] (p = 0.25 > 0.05)
                        No change in performance detected.

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 2.0008 s (24k iterations)
Benchmarking adjust_gamma_u8_flip_v/256: Analyzing
adjust_gamma_u8_flip_v/256
                        time:   [69.412 µs 77.120 µs 84.932 µs]
                        change: [-5.9292% +1.3519% +10.240%] (p = 0.75 > 0.05)
                        No change in performance detected.
Found 2 outliers among 20 measurements (10.00%)
  2 (10.00%) high mild
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 2.0642 s (5460 iterations)
Benchmarking adjust_gamma_u8_flip_v/512: Analyzing
adjust_gamma_u8_flip_v/512
                        time:   [302.29 µs 331.28 µs 363.46 µs]
                        change: [-4.0813% +3.4882% +11.564%] (p = 0.39 > 0.05)
                        No change in performance detected.
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 2.2844 s (1050 iterations)
Benchmarking adjust_gamma_u8_flip_v/1024: Analyzing
adjust_gamma_u8_flip_v/1024
                        time:   [1.4741 ms 1.6028 ms 1.7610 ms]
                        change: [+6.4013% +14.384% +22.503%] (p = 0.00 < 0.05)
                        Performance has regressed.
Found 5 outliers among 20 measurements (25.00%)
  3 (15.00%) low severe
  1 (5.00%) low mild
  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 2.0009 s (70k iterations)
Benchmarking threshold_u8_flip_h/256: Analyzing
threshold_u8_flip_h/256 time:   [19.899 µs 21.044 µs 22.836 µs]
                        change: [+19.664% +35.346% +49.386%] (p = 0.00 < 0.05)
                        Performance has regressed.
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 2.0024 s (22k iterations)
Benchmarking threshold_u8_flip_h/512: Analyzing
threshold_u8_flip_h/512 time:   [65.258 µs 66.278 µs 67.794 µs]
                        change: [-23.994% -18.785% -13.618%] (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 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 2.0862 s (5040 iterations)
Benchmarking threshold_u8_flip_h/1024: Analyzing
threshold_u8_flip_h/1024
                        time:   [326.70 µs 342.24 µs 364.88 µs]
                        change: [-16.276% -8.9041% -1.5003%] (p = 0.04 < 0.05)
                        Performance has improved.

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 2.0591 s (3990 iterations)
Benchmarking f16_per_element_f32/256: Analyzing
f16_per_element_f32/256 time:   [425.11 µs 428.02 µs 431.90 µs]
Found 1 outliers among 20 measurements (5.00%)
  1 (5.00%) high severe
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 2.0785 s (1050 iterations)
Benchmarking f16_per_element_f32/512: Analyzing
f16_per_element_f32/512 time:   [1.6641 ms 1.7098 ms 1.7711 ms]
Benchmarking f16_per_element_f32/1024
Benchmarking f16_per_element_f32/1024: Warming up for 500.00 ms
Benchmarking f16_per_element_f32/1024: Collecting 20 samples in estimated 3.8799 s (420 iterations)
Benchmarking f16_per_element_f32/1024: Analyzing
f16_per_element_f32/1024
                        time:   [7.3933 ms 7.9579 ms 8.6217 ms]
Found 1 outliers among 20 measurements (5.00%)
  1 (5.00%) high mild

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 2.0254 s (16k iterations)
Benchmarking f16_bits_f32/256: Analyzing
f16_bits_f32/256        time:   [81.885 µs 85.767 µs 88.824 µs]
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 2.0471 s (3150 iterations)
Benchmarking f16_bits_f32/512: Analyzing
f16_bits_f32/512        time:   [375.25 µs 398.63 µs 427.73 µs]
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 2.6634 s (840 iterations)
Benchmarking f16_bits_f32/1024: Analyzing
f16_bits_f32/1024       time:   [1.8274 ms 1.9270 ms 2.0410 ms]
Found 1 outliers among 20 measurements (5.00%)
  1 (5.00%) high severe

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 2.0527 s (3990 iterations)
Benchmarking f16_per_element_u8/256: Analyzing
f16_per_element_u8/256  time:   [442.75 µs 458.89 µs 486.73 µs]
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 2.0730 s (1050 iterations)
Benchmarking f16_per_element_u8/512: Analyzing
f16_per_element_u8/512  time:   [1.9987 ms 2.0880 ms 2.2076 ms]
Found 2 outliers among 20 measurements (10.00%)
  2 (10.00%) high severe
Benchmarking f16_per_element_u8/1024
Benchmarking f16_per_element_u8/1024: Warming up for 500.00 ms
Benchmarking f16_per_element_u8/1024: Collecting 20 samples in estimated 3.9295 s (420 iterations)
Benchmarking f16_per_element_u8/1024: Analyzing
f16_per_element_u8/1024 time:   [7.9507 ms 8.4762 ms 9.1340 ms]
Found 1 outliers among 20 measurements (5.00%)
  1 (5.00%) 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 2.0031 s (24k iterations)
Benchmarking f16_bits_u8/256: Analyzing
f16_bits_u8/256         time:   [71.983 µs 73.644 µs 74.812 µs]
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 2.0488 s (5460 iterations)
Benchmarking f16_bits_u8/512: Analyzing
f16_bits_u8/512         time:   [310.85 µs 322.45 µs 337.13 µs]
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 2.0884 s (1260 iterations)
Benchmarking f16_bits_u8/1024: Analyzing
f16_bits_u8/1024        time:   [1.4143 ms 1.4902 ms 1.5676 ms]

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 2.0113 s (3150 iterations)
Benchmarking f16_per_element_f32_transposed/256: Analyzing
f16_per_element_f32_transposed/256
                        time:   [554.80 µs 578.63 µs 610.84 µs]
Found 1 outliers among 20 measurements (5.00%)
  1 (5.00%) high severe
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 2.1599 s (840 iterations)
Benchmarking f16_per_element_f32_transposed/512: Analyzing
f16_per_element_f32_transposed/512
                        time:   [2.2578 ms 2.3649 ms 2.4856 ms]
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 2.6658 s (80 iterations)
Benchmarking f16_per_element_f32_transposed/1024: Analyzing
f16_per_element_f32_transposed/1024
                        time:   [22.979 ms 23.628 ms 24.389 ms]
Found 2 outliers among 20 measurements (10.00%)
  2 (10.00%) high mild

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 2.0054 s (8610 iterations)
Benchmarking f16_bits_f32_transposed/256: Analyzing
f16_bits_f32_transposed/256
                        time:   [167.47 µs 181.86 µs 196.49 µs]
Found 1 outliers among 20 measurements (5.00%)
  1 (5.00%) high mild
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 2.2744 s (1680 iterations)
Benchmarking f16_bits_f32_transposed/512: Analyzing
f16_bits_f32_transposed/512
                        time:   [796.02 µs 816.76 µs 845.34 µs]
Found 1 outliers among 20 measurements (5.00%)
  1 (5.00%) high mild
Benchmarking f16_bits_f32_transposed/1024
Benchmarking f16_bits_f32_transposed/1024: Warming up for 500.00 ms
Benchmarking f16_bits_f32_transposed/1024: Collecting 20 samples in estimated 3.6970 s (420 iterations)
Benchmarking f16_bits_f32_transposed/1024: Analyzing
f16_bits_f32_transposed/1024
                        time:   [6.7602 ms 6.9307 ms 7.1615 ms]
