calculate_k             time:   [20.444 ns 20.447 ns 20.450 ns]
                        change: [-0.2596% -0.1009% -0.0106%] (p = 0.13 > 0.05)
                        No change in performance detected.
Found 3 outliers among 100 measurements (3.00%)
  2 (2.00%) high mild
  1 (1.00%) high severe

data_generation/synthesize_displacement/200
                        time:   [2.4531 µs 2.4535 µs 2.4539 µs]
                        thrpt:  [81.501 Melem/s 81.515 Melem/s 81.528 Melem/s]
                 change:
                        time:   [-0.2017% -0.1254% -0.0314%] (p = 0.00 < 0.05)
                        thrpt:  [+0.0314% +0.1256% +0.2021%]
                        Change within noise threshold.
Found 2 outliers among 100 measurements (2.00%)
  1 (1.00%) high mild
  1 (1.00%) high severe
data_generation/synthesize_displacement/1000
                        time:   [11.830 µs 11.832 µs 11.833 µs]
                        thrpt:  [84.511 Melem/s 84.520 Melem/s 84.527 Melem/s]
                 change:
                        time:   [+0.0946% +0.1050% +0.1157%] (p = 0.00 < 0.05)
                        thrpt:  [-0.1156% -0.1048% -0.0945%]
                        Change within noise threshold.
Found 2 outliers among 100 measurements (2.00%)
  1 (1.00%) low mild
  1 (1.00%) high severe
data_generation/synthesize_displacement/10000
                        time:   [114.99 µs 115.00 µs 115.01 µs]
                        thrpt:  [86.950 Melem/s 86.958 Melem/s 86.964 Melem/s]
                 change:
                        time:   [-0.0402% -0.0251% -0.0121%] (p = 0.00 < 0.05)
                        thrpt:  [+0.0121% +0.0251% +0.0402%]
                        Change within noise threshold.
Found 11 outliers among 100 measurements (11.00%)
  2 (2.00%) low mild
  6 (6.00%) high mild
  3 (3.00%) high severe
data_generation/synthesize_displacement/100000
                        time:   [1.1595 ms 1.1597 ms 1.1599 ms]
                        thrpt:  [86.213 Melem/s 86.231 Melem/s 86.242 Melem/s]
                 change:
                        time:   [-0.0617% -0.0254% +0.0049%] (p = 0.13 > 0.05)
                        thrpt:  [-0.0049% +0.0254% +0.0617%]
                        No change in performance detected.
Found 7 outliers among 100 measurements (7.00%)
  5 (5.00%) high mild
  2 (2.00%) high severe

forward_pass/lffn_mlp/200
                        time:   [1.3635 ms 1.3642 ms 1.3648 ms]
                        thrpt:  [146.54 Kelem/s 146.61 Kelem/s 146.68 Kelem/s]
                 change:
                        time:   [+35.709% +35.830% +35.952%] (p = 0.00 < 0.05)
                        thrpt:  [-26.444% -26.379% -26.313%]
                        Performance has regressed.
Found 2 outliers among 50 measurements (4.00%)
  1 (2.00%) high mild
  1 (2.00%) high severe
forward_pass/lffn_mlp/1000
                        time:   [5.0988 ms 5.1021 ms 5.1056 ms]
                        thrpt:  [195.86 Kelem/s 196.00 Kelem/s 196.13 Kelem/s]
                 change:
                        time:   [-36.382% -36.310% -36.237%] (p = 0.00 < 0.05)
                        thrpt:  [+56.832% +57.011% +57.189%]
                        Performance has improved.
Found 7 outliers among 50 measurements (14.00%)
  1 (2.00%) low severe
  6 (12.00%) low mild
forward_pass/lffn_mlp/10000
                        time:   [48.058 ms 48.165 ms 48.316 ms]
                        thrpt:  [206.97 Kelem/s 207.62 Kelem/s 208.08 Kelem/s]
                 change:
                        time:   [-42.362% -42.232% -42.054%] (p = 0.00 < 0.05)
                        thrpt:  [+72.574% +73.108% +73.497%]
                        Performance has improved.
Found 5 outliers among 50 measurements (10.00%)
  2 (4.00%) high mild
  3 (6.00%) high severe

forward_pass_optimized/lffn_mlp_workspace/200
                        time:   [45.318 µs 45.332 µs 45.345 µs]
                        thrpt:  [4.4106 Melem/s 4.4119 Melem/s 4.4132 Melem/s]
                 change:
                        time:   [-72.903% -72.816% -72.726%] (p = 0.00 < 0.05)
                        thrpt:  [+266.65% +267.86% +269.05%]
                        Performance has improved.
Found 1 outliers among 50 measurements (2.00%)
  1 (2.00%) high mild
forward_pass_optimized/lffn_mlp_workspace/1000
                        time:   [46.085 µs 46.103 µs 46.121 µs]
                        thrpt:  [21.682 Melem/s 21.690 Melem/s 21.699 Melem/s]
                 change:
                        time:   [-94.691% -94.668% -94.652%] (p = 0.00 < 0.05)
                        thrpt:  [+1769.7% +1775.5% +1783.7%]
                        Performance has improved.
Found 7 outliers among 50 measurements (14.00%)
  2 (4.00%) low severe
  2 (4.00%) low mild
  2 (4.00%) high mild
  1 (2.00%) high severe
forward_pass_optimized/lffn_mlp_workspace/10000
                        time:   [68.524 µs 68.546 µs 68.566 µs]
                        thrpt:  [145.84 Melem/s 145.89 Melem/s 145.93 Melem/s]
                 change:
                        time:   [-99.508% -99.492% -99.475%] (p = 0.00 < 0.05)
                        thrpt:  [+18942% +19578% +20226%]
                        Performance has improved.
Found 1 outliers among 50 measurements (2.00%)
  1 (2.00%) low severe
forward_pass_optimized/lffn_mlp_workspace/100000
                        time:   [306.75 µs 306.80 µs 306.84 µs]
                        thrpt:  [325.91 Melem/s 325.95 Melem/s 325.99 Melem/s]
                 change:
                        time:   [-99.797% -99.794% -99.792%] (p = 0.00 < 0.05)
                        thrpt:  [+48048% +48538% +49048%]
                        Performance has improved.
Found 5 outliers among 50 measurements (10.00%)
  2 (4.00%) low severe
  3 (6.00%) low mild

forward_pass_cuda_graph/lffn_mlp_cuda_graph/200
                        time:   [46.444 µs 46.454 µs 46.463 µs]
                        thrpt:  [4.3045 Melem/s 4.3054 Melem/s 4.3063 Melem/s]
Found 3 outliers among 50 measurements (6.00%)
  2 (4.00%) low severe
  1 (2.00%) high mild
forward_pass_cuda_graph/lffn_mlp_cuda_graph/1000
                        time:   [47.489 µs 47.504 µs 47.518 µs]
                        thrpt:  [21.045 Melem/s 21.051 Melem/s 21.057 Melem/s]
Found 2 outliers among 50 measurements (4.00%)
  1 (2.00%) low severe
  1 (2.00%) high severe
forward_pass_cuda_graph/lffn_mlp_cuda_graph/10000
                        time:   [69.181 µs 69.202 µs 69.223 µs]
                        thrpt:  [144.46 Melem/s 144.50 Melem/s 144.55 Melem/s]
Found 3 outliers among 50 measurements (6.00%)
  1 (2.00%) low severe
  2 (4.00%) high mild

forward_pass_matmuls_graph/hybrid_graph/200
                        time:   [41.742 µs 41.752 µs 41.762 µs]
                        thrpt:  [4.7891 Melem/s 4.7902 Melem/s 4.7913 Melem/s]
Found 9 outliers among 100 measurements (9.00%)
  3 (3.00%) low severe
  2 (2.00%) low mild
  4 (4.00%) high mild
forward_pass_matmuls_graph/hybrid_graph/1000
                        time:   [41.707 µs 41.713 µs 41.719 µs]
                        thrpt:  [23.970 Melem/s 23.974 Melem/s 23.977 Melem/s]
Found 4 outliers among 100 measurements (4.00%)
  1 (1.00%) low mild
  3 (3.00%) high mild
forward_pass_matmuls_graph/hybrid_graph/10000
                        time:   [67.193 µs 67.214 µs 67.233 µs]
                        thrpt:  [148.74 Melem/s 148.78 Melem/s 148.82 Melem/s]
Found 8 outliers among 100 measurements (8.00%)
  1 (1.00%) low severe
  4 (4.00%) low mild
  1 (1.00%) high mild
  2 (2.00%) high severe

forward_pass_uber_kernel/uber_value_only/200
                        time:   [332.54 µs 332.59 µs 332.65 µs]
                        thrpt:  [601.24 Kelem/s 601.34 Kelem/s 601.43 Kelem/s]
Found 1 outliers among 100 measurements (1.00%)
  1 (1.00%) low severe
forward_pass_uber_kernel/uber_with_gradients/200
                        time:   [590.93 µs 591.06 µs 591.20 µs]
                        thrpt:  [338.29 Kelem/s 338.37 Kelem/s 338.45 Kelem/s]
Found 5 outliers among 100 measurements (5.00%)
  2 (2.00%) low severe
  1 (1.00%) low mild
  2 (2.00%) high mild
forward_pass_uber_kernel/uber_value_only/1000
                        time:   [345.45 µs 345.46 µs 345.48 µs]
                        thrpt:  [2.8946 Melem/s 2.8947 Melem/s 2.8948 Melem/s]
Found 9 outliers among 100 measurements (9.00%)
  3 (3.00%) low severe
  3 (3.00%) low mild
  3 (3.00%) high severe
forward_pass_uber_kernel/uber_with_gradients/1000
                        time:   [607.77 µs 607.87 µs 607.98 µs]
                        thrpt:  [1.6448 Melem/s 1.6451 Melem/s 1.6454 Melem/s]
Found 5 outliers among 100 measurements (5.00%)
  2 (2.00%) low severe
  3 (3.00%) high mild
forward_pass_uber_kernel/uber_value_only/10000
                        time:   [346.90 µs 346.91 µs 346.93 µs]
                        thrpt:  [28.825 Melem/s 28.826 Melem/s 28.827 Melem/s]
Found 6 outliers among 100 measurements (6.00%)
  2 (2.00%) low severe
  1 (1.00%) low mild
  1 (1.00%) high mild
  2 (2.00%) high severe
forward_pass_uber_kernel/uber_with_gradients/10000
                        time:   [616.27 µs 616.34 µs 616.40 µs]
                        thrpt:  [16.223 Melem/s 16.225 Melem/s 16.227 Melem/s]
Found 4 outliers among 100 measurements (4.00%)
  1 (1.00%) low severe
  1 (1.00%) low mild
  1 (1.00%) high mild
  1 (1.00%) high severe

forward_pass_uber_kernel_zero_alloc/uber_zero_alloc/200
                        time:   [329.89 µs 329.89 µs 329.89 µs]
                        thrpt:  [606.26 Kelem/s 606.26 Kelem/s 606.27 Kelem/s]
Found 37 outliers among 200 measurements (18.50%)
  11 (5.50%) low severe
  6 (3.00%) low mild
  10 (5.00%) high mild
  10 (5.00%) high severe
forward_pass_uber_kernel_zero_alloc/uber_zero_alloc/1000
                        time:   [342.35 µs 342.36 µs 342.38 µs]
                        thrpt:  [2.9208 Melem/s 2.9209 Melem/s 2.9210 Melem/s]
Found 16 outliers among 200 measurements (8.00%)
  5 (2.50%) low severe
  5 (2.50%) low mild
  1 (0.50%) high mild
  5 (2.50%) high severe
forward_pass_uber_kernel_zero_alloc/uber_zero_alloc/10000
                        time:   [343.81 µs 343.81 µs 343.82 µs]
                        thrpt:  [29.085 Melem/s 29.086 Melem/s 29.086 Melem/s]
Found 19 outliers among 200 measurements (9.50%)
  3 (1.50%) low severe
  4 (2.00%) low mild
  9 (4.50%) high mild
  3 (1.50%) high severe

forward_pass_fused_lite/fused_lite/200
                        time:   [261.04 µs 261.09 µs 261.14 µs]
                        thrpt:  [765.86 Kelem/s 766.02 Kelem/s 766.16 Kelem/s]
Found 1 outliers among 200 measurements (0.50%)
  1 (0.50%) high mild
forward_pass_fused_lite/fused_lite/1000
                        time:   [266.63 µs 266.66 µs 266.69 µs]
                        thrpt:  [3.7497 Melem/s 3.7501 Melem/s 3.7505 Melem/s]
Found 16 outliers among 200 measurements (8.00%)
  4 (2.00%) low severe
  5 (2.50%) low mild
  2 (1.00%) high mild
  5 (2.50%) high severe
forward_pass_fused_lite/fused_lite/10000
                        time:   [272.84 µs 272.85 µs 272.87 µs]
                        thrpt:  [36.648 Melem/s 36.650 Melem/s 36.652 Melem/s]
Found 12 outliers among 200 measurements (6.00%)
  3 (1.50%) low severe
  5 (2.50%) low mild
  4 (2.00%) high mild

matmul_tensor_cores/fp32_sgemm/200x128x64
                        time:   [19.679 µs 19.683 µs 19.687 µs]
                        thrpt:  [166.44 Gelem/s 166.48 Gelem/s 166.51 Gelem/s]
Found 6 outliers among 100 measurements (6.00%)
  2 (2.00%) low mild
  3 (3.00%) high mild
  1 (1.00%) high severe
matmul_tensor_cores/fp16_tensor_cores/200x128x64
                        time:   [17.718 µs 17.721 µs 17.724 µs]
                        thrpt:  [184.88 Gelem/s 184.91 Gelem/s 184.94 Gelem/s]
Found 3 outliers among 100 measurements (3.00%)
  1 (1.00%) low mild
  2 (2.00%) high mild
matmul_tensor_cores/fp32_sgemm/200x64x64
                        time:   [19.754 µs 19.758 µs 19.762 µs]
                        thrpt:  [82.907 Gelem/s 82.923 Gelem/s 82.939 Gelem/s]
Found 9 outliers among 100 measurements (9.00%)
  2 (2.00%) low mild
  5 (5.00%) high mild
  2 (2.00%) high severe
matmul_tensor_cores/fp16_tensor_cores/200x64x64
                        time:   [17.811 µs 17.814 µs 17.816 µs]
                        thrpt:  [91.960 Gelem/s 91.975 Gelem/s 91.989 Gelem/s]
Found 2 outliers among 100 measurements (2.00%)
  2 (2.00%) high mild
matmul_tensor_cores/fp32_sgemm/1000x128x64
                        time:   [21.346 µs 21.351 µs 21.357 µs]
                        thrpt:  [767.16 Gelem/s 767.36 Gelem/s 767.56 Gelem/s]
Found 13 outliers among 100 measurements (13.00%)
  5 (5.00%) low severe
  4 (4.00%) low mild
  2 (2.00%) high mild
  2 (2.00%) high severe
matmul_tensor_cores/fp16_tensor_cores/1000x128x64
                        time:   [17.878 µs 17.886 µs 17.894 µs]
                        thrpt:  [915.63 Gelem/s 916.01 Gelem/s 916.42 Gelem/s]
Found 1 outliers among 100 measurements (1.00%)
  1 (1.00%) high severe
matmul_tensor_cores/fp32_sgemm/1000x64x64
                        time:   [18.837 µs 18.842 µs 18.848 µs]
                        thrpt:  [434.64 Gelem/s 434.76 Gelem/s 434.89 Gelem/s]
Found 9 outliers among 100 measurements (9.00%)
  3 (3.00%) low severe
  4 (4.00%) low mild
  1 (1.00%) high mild
  1 (1.00%) high severe
matmul_tensor_cores/fp16_tensor_cores/1000x64x64
                        time:   [17.858 µs 17.861 µs 17.863 µs]
                        thrpt:  [458.59 Gelem/s 458.66 Gelem/s 458.73 Gelem/s]
Found 1 outliers among 100 measurements (1.00%)
  1 (1.00%) high severe
matmul_tensor_cores/fp32_sgemm/10000x128x64
                        time:   [28.129 µs 28.138 µs 28.146 µs]
                        thrpt:  [5821.2 Gelem/s 5822.8 Gelem/s 5824.5 Gelem/s]
Found 5 outliers among 100 measurements (5.00%)
  1 (1.00%) low severe
  2 (2.00%) low mild
  2 (2.00%) high mild
matmul_tensor_cores/fp16_tensor_cores/10000x128x64
                        time:   [20.381 µs 20.389 µs 20.397 µs]
                        thrpt:  [8032.6 Gelem/s 8035.7 Gelem/s 8038.9 Gelem/s]
Found 6 outliers among 100 measurements (6.00%)
  4 (4.00%) low mild
  1 (1.00%) high mild
  1 (1.00%) high severe

pde_residual_analytical/helmholtz_cpu/200
                        time:   [5.2211 µs 5.2224 µs 5.2238 µs]
                        thrpt:  [38.287 Melem/s 38.297 Melem/s 38.306 Melem/s]
                 change:
                        time:   [+0.0170% +0.0454% +0.0769%] (p = 0.00 < 0.05)
                        thrpt:  [-0.0768% -0.0454% -0.0170%]
                        Change within noise threshold.
pde_residual_analytical/helmholtz_cpu/1000
                        time:   [25.163 µs 25.164 µs 25.164 µs]
                        thrpt:  [39.739 Melem/s 39.740 Melem/s 39.741 Melem/s]
                 change:
                        time:   [-0.0626% -0.0350% -0.0158%] (p = 0.00 < 0.05)
                        thrpt:  [+0.0158% +0.0350% +0.0626%]
                        Change within noise threshold.
Found 3 outliers among 50 measurements (6.00%)
  1 (2.00%) low mild
  1 (2.00%) high mild
  1 (2.00%) high severe
pde_residual_analytical/helmholtz_cpu/10000
                        time:   [245.36 µs 245.37 µs 245.38 µs]
                        thrpt:  [40.753 Melem/s 40.755 Melem/s 40.757 Melem/s]
                 change:
                        time:   [+0.3082% +0.3181% +0.3303%] (p = 0.00 < 0.05)
                        thrpt:  [-0.3292% -0.3171% -0.3073%]
                        Change within noise threshold.
Found 5 outliers among 50 measurements (10.00%)
  1 (2.00%) low severe
  3 (6.00%) high mild
  1 (2.00%) high severe

pde_residual_tensor/helmholtz_tensor/200
                        time:   [177.85 µs 177.90 µs 177.96 µs]
                        thrpt:  [1.1238 Melem/s 1.1242 Melem/s 1.1245 Melem/s]
                 change:
                        time:   [+1877.5% +1878.6% +1879.7%] (p = 0.00 < 0.05)
                        thrpt:  [-94.949% -94.946% -94.943%]
                        Performance has regressed.
Found 6 outliers among 50 measurements (12.00%)
  1 (2.00%) low severe
  3 (6.00%) low mild
  1 (2.00%) high mild
  1 (2.00%) high severe
pde_residual_tensor/helmholtz_tensor/1000
                        time:   [240.61 µs 240.75 µs 240.89 µs]
                        thrpt:  [4.1513 Melem/s 4.1536 Melem/s 4.1560 Melem/s]
                 change:
                        time:   [+639.97% +641.03% +641.73%] (p = 0.00 < 0.05)
                        thrpt:  [-86.518% -86.505% -86.486%]
                        Performance has regressed.
Found 1 outliers among 50 measurements (2.00%)
  1 (2.00%) low severe
pde_residual_tensor/helmholtz_tensor/10000
                        time:   [598.41 µs 598.60 µs 598.79 µs]
                        thrpt:  [16.700 Melem/s 16.706 Melem/s 16.711 Melem/s]
                 change:
                        time:   [+108.95% +109.04% +109.15%] (p = 0.00 < 0.05)
                        thrpt:  [-52.186% -52.161% -52.141%]
                        Performance has regressed.
Found 1 outliers among 50 measurements (2.00%)
  1 (2.00%) high severe

mse_loss/mse_computation/200
                        time:   [50.598 µs 50.617 µs 50.634 µs]
                        thrpt:  [7.8999 Melem/s 7.9025 Melem/s 7.9054 Melem/s]
                 change:
                        time:   [+3960.9% +3963.6% +3966.0%] (p = 0.00 < 0.05)
                        thrpt:  [-97.541% -97.539% -97.537%]
                        Performance has regressed.
Found 3 outliers among 50 measurements (6.00%)
  1 (2.00%) low severe
  2 (4.00%) low mild
mse_loss/mse_computation/1000
                        time:   [61.058 µs 61.107 µs 61.155 µs]
                        thrpt:  [32.704 Melem/s 32.730 Melem/s 32.756 Melem/s]
                 change:
                        time:   [+2256.2% +2258.5% +2261.0%] (p = 0.00 < 0.05)
                        thrpt:  [-95.764% -95.760% -95.756%]
                        Performance has regressed.
mse_loss/mse_computation/10000
                        time:   [118.77 µs 118.81 µs 118.85 µs]
                        thrpt:  [168.28 Melem/s 168.33 Melem/s 168.39 Melem/s]
                 change:
                        time:   [+489.57% +490.01% +490.52%] (p = 0.00 < 0.05)
                        thrpt:  [-83.066% -83.051% -83.038%]
                        Performance has regressed.
Found 2 outliers among 50 measurements (4.00%)
  1 (2.00%) high mild
  1 (2.00%) high severe

training_step/single_step/200
                        time:   [1.6020 ms 1.6025 ms 1.6031 ms]
                        thrpt:  [124.76 Kelem/s 124.80 Kelem/s 124.85 Kelem/s]
                 change:
                        time:   [+53.952% +54.130% +54.302%] (p = 0.00 < 0.05)
                        thrpt:  [-35.192% -35.120% -35.045%]
                        Performance has regressed.
Found 3 outliers among 30 measurements (10.00%)
  3 (10.00%) low mild
training_step/single_step/1000
                        time:   [5.3790 ms 5.3831 ms 5.3875 ms]
                        thrpt:  [185.62 Kelem/s 185.77 Kelem/s 185.91 Kelem/s]
                 change:
                        time:   [-33.396% -33.149% -32.955%] (p = 0.00 < 0.05)
                        thrpt:  [+49.153% +49.586% +50.141%]
                        Performance has improved.
Found 2 outliers among 30 measurements (6.67%)
  1 (3.33%) high mild
  1 (3.33%) high severe

training_step_optimized/single_step_workspace/200
                        time:   [288.90 µs 289.06 µs 289.21 µs]
                        thrpt:  [691.53 Kelem/s 691.90 Kelem/s 692.28 Kelem/s]
                 change:
                        time:   [+68.047% +68.707% +69.331%] (p = 0.00 < 0.05)
                        thrpt:  [-40.944% -40.726% -40.493%]
                        Performance has regressed.
training_step_optimized/single_step_workspace/1000
                        time:   [352.56 µs 352.74 µs 352.94 µs]
                        thrpt:  [2.8334 Melem/s 2.8349 Melem/s 2.8364 Melem/s]
                 change:
                        time:   [-61.113% -60.815% -60.622%] (p = 0.00 < 0.05)
                        thrpt:  [+153.95% +155.20% +157.15%]
                        Performance has improved.
Found 2 outliers among 30 measurements (6.67%)
  1 (3.33%) low severe
  1 (3.33%) low mild

training_step_cached/single_step_cached/200
                        time:   [1.5824 ms 1.5829 ms 1.5835 ms]
                        thrpt:  [126.31 Kelem/s 126.35 Kelem/s 126.39 Kelem/s]
                 change:
                        time:   [+55.274% +55.412% +55.544%] (p = 0.00 < 0.05)
                        thrpt:  [-35.709% -35.655% -35.598%]
                        Performance has regressed.
Found 3 outliers among 30 measurements (10.00%)
  1 (3.33%) high mild
  2 (6.67%) high severe
training_step_cached/single_step_cached/1000
                        time:   [5.3466 ms 5.3529 ms 5.3596 ms]
                        thrpt:  [186.58 Kelem/s 186.81 Kelem/s 187.03 Kelem/s]
                 change:
                        time:   [-33.297% -33.201% -33.114%] (p = 0.00 < 0.05)
                        thrpt:  [+49.508% +49.703% +49.918%]
                        Performance has improved.
Found 1 outliers among 30 measurements (3.33%)
  1 (3.33%) high mild

training_step_fully_optimized/single_step_fully_opt/200
                        time:   [268.67 µs 268.83 µs 268.99 µs]
                        thrpt:  [743.52 Kelem/s 743.97 Kelem/s 744.41 Kelem/s]
                 change:
                        time:   [+62.589% +63.069% +63.656%] (p = 0.00 < 0.05)
                        thrpt:  [-38.896% -38.676% -38.495%]
                        Performance has regressed.
Found 1 outliers among 30 measurements (3.33%)
  1 (3.33%) high mild
training_step_fully_optimized/single_step_fully_opt/1000
                        time:   [312.08 µs 312.29 µs 312.48 µs]
                        thrpt:  [3.2002 Melem/s 3.2022 Melem/s 3.2043 Melem/s]
                 change:
                        time:   [-63.992% -63.932% -63.867%] (p = 0.00 < 0.05)
                        thrpt:  [+176.75% +177.25% +177.72%]
                        Performance has improved.

training_step_deferred_loss/no_loss_step/200
                        time:   [45.941 µs 45.949 µs 45.957 µs]
                        thrpt:  [4.3519 Melem/s 4.3526 Melem/s 4.3534 Melem/s]
training_step_deferred_loss/with_loss_step/200
                        time:   [269.24 µs 269.39 µs 269.56 µs]
                        thrpt:  [741.95 Kelem/s 742.43 Kelem/s 742.82 Kelem/s]
Found 1 outliers among 30 measurements (3.33%)
  1 (3.33%) high mild
training_step_deferred_loss/no_loss_step/1000
                        time:   [47.423 µs 47.440 µs 47.457 µs]
                        thrpt:  [21.072 Melem/s 21.079 Melem/s 21.087 Melem/s]
Found 2 outliers among 30 measurements (6.67%)
  1 (3.33%) low severe
  1 (3.33%) high mild
training_step_deferred_loss/with_loss_step/1000
                        time:   [312.35 µs 312.53 µs 312.73 µs]
                        thrpt:  [3.1976 Melem/s 3.1997 Melem/s 3.2015 Melem/s]
Found 1 outliers among 30 measurements (3.33%)
  1 (3.33%) high severe

training_step_zero_sync/single_step_zero_sync/200
                        time:   [346.53 µs 346.74 µs 346.91 µs]
                        thrpt:  [576.52 Kelem/s 576.80 Kelem/s 577.14 Kelem/s]
Found 2 outliers among 30 measurements (6.67%)
  1 (3.33%) low mild
  1 (3.33%) high severe
training_step_zero_sync/single_step_zero_sync/1000
                        time:   [389.64 µs 390.01 µs 390.38 µs]
                        thrpt:  [2.5616 Melem/s 2.5640 Melem/s 2.5665 Melem/s]
Found 3 outliers among 30 measurements (10.00%)
  1 (3.33%) low mild
  2 (6.67%) high mild

training_step_cuda_graph/single_step_cuda_graph/200
                        time:   [269.01 µs 269.26 µs 269.43 µs]
                        thrpt:  [742.30 Kelem/s 742.77 Kelem/s 743.46 Kelem/s]
Found 5 outliers among 30 measurements (16.67%)
  4 (13.33%) low mild
  1 (3.33%) high severe
training_step_cuda_graph/single_step_cuda_graph/1000
                        time:   [311.87 µs 312.07 µs 312.25 µs]
                        thrpt:  [3.2025 Melem/s 3.2044 Melem/s 3.2065 Melem/s]
Found 1 outliers among 30 measurements (3.33%)
  1 (3.33%) high severe

training_100_epochs/train_100/200
                        time:   [161.29 ms 161.36 ms 161.42 ms]
                        thrpt:  [619.48  elem/s 619.72  elem/s 620.00  elem/s]
                 change:
                        time:   [+54.470% +54.742% +55.007%] (p = 0.00 < 0.05)
                        thrpt:  [-35.487% -35.376% -35.263%]
                        Performance has regressed.

training_100_epochs_cached/train_100_cached/200
                        time:   [159.46 ms 159.56 ms 159.73 ms]
                        thrpt:  [626.05  elem/s 626.73  elem/s 627.12  elem/s]
                 change:
                        time:   [+54.743% +55.144% +55.504%] (p = 0.00 < 0.05)
                        thrpt:  [-35.693% -35.544% -35.377%]
                        Performance has regressed.
Found 1 outliers among 10 measurements (10.00%)
  1 (10.00%) high mild

training_100_epochs_fully_optimized/train_100_fully_opt/200
                        time:   [28.016 ms 28.030 ms 28.040 ms]
                        thrpt:  [3.5663 Kelem/s 3.5677 Kelem/s 3.5694 Kelem/s]
                 change:
                        time:   [+61.278% +63.573% +65.974%] (p = 0.00 < 0.05)
                        thrpt:  [-39.750% -38.865% -37.995%]
                        Performance has regressed.
Found 1 outliers among 10 measurements (10.00%)
  1 (10.00%) low mild

training_100_epochs_deferred_loss/train_100_deferred_loss/200
                        time:   [5.8959 ms 5.8975 ms 5.8997 ms]
                        thrpt:  [16.950 Kelem/s 16.956 Kelem/s 16.961 Kelem/s]

training_100_epochs_zero_sync/train_100_zero_sync/200
                        time:   [35.784 ms 35.806 ms 35.824 ms]
                        thrpt:  [2.7914 Kelem/s 2.7929 Kelem/s 2.7945 Kelem/s]

training_100_epochs_cuda_graph/train_100_cuda_graph/200
                        time:   [28.010 ms 28.020 ms 28.035 ms]
                        thrpt:  [3.5669 Kelem/s 3.5689 Kelem/s 3.5701 Kelem/s]

training_step_analytical/analytical_backprop/200
                        time:   [186.14 µs 186.19 µs 186.25 µs]
                        thrpt:  [1.0738 Melem/s 1.0742 Melem/s 1.0745 Melem/s]
Found 13 outliers among 200 measurements (6.50%)
  2 (1.00%) low severe
  6 (3.00%) low mild
  4 (2.00%) high mild
  1 (0.50%) high severe
training_step_analytical/analytical_backprop/1000
                        time:   [300.75 µs 300.83 µs 300.91 µs]
                        thrpt:  [3.3233 Melem/s 3.3242 Melem/s 3.3250 Melem/s]
Found 23 outliers among 200 measurements (11.50%)
  4 (2.00%) low severe
  8 (4.00%) low mild
  8 (4.00%) high mild
  3 (1.50%) high severe

training_100_epochs_analytical/train_100_analytical/200
                        time:   [17.807 ms 17.813 ms 17.819 ms]
                        thrpt:  [5.6120 Kelem/s 5.6139 Kelem/s 5.6156 Kelem/s]

