c55d9f3dad
make raptor also emit input sizes
30 KiB
30 KiB
| 1 | Operation | Arch | Result (l) | Result (t) | Compile (l) | Host mem (l) | Cores mem (l) | Cores (l) | Xbars (l) | Latency (l) | Power (l) | Energy (l) | Compile (t) | Host mem (t) | Cores mem (t) | Cores (t) | Xbars (t) | Avg latency (t) | Throughput (t) | Avg power (t) | Avg energy (t) |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | add/after_gemm | arch-a | PASS | FAIL | 0.057 s | 0.01 MiB | 0.01 MiB | 5 | 4 | 0.01 ms | 104.70 mW | 815012.96 pJ | 0.055 s | 0.01 MiB | 0.01 MiB | 6 | 4 | 277000.00 samples/s | 0.00 ms | 45.81 mW | 190085.16 pJ/it |
| 3 | add/basic | arch-a | PASS | PASS | 0.047 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 0.00 ms | 78.22 mW | 25266.00 pJ | 0.048 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 3120000.00 samples/s | 0.00 ms | 2.23 mW | 658.67 pJ/it |
| 4 | add/broadcast_row | arch-a | PASS | PASS | 0.049 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 0.00 ms | 78.22 mW | 25266.00 pJ | 0.049 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 3120000.00 samples/s | 0.00 ms | 2.23 mW | 658.67 pJ/it |
| 5 | add/channel_broadcast_1024 | arch-a | PASS | PASS | 0.048 s | 0.02 MiB | 0.01 MiB | 1 | 0 | 0.01 ms | 78.12 mW | 540030.00 pJ | 0.048 s | 0.02 MiB | 0.01 MiB | 1 | 0 | 145000.00 samples/s | 0.01 ms | 2.11 mW | 13388.67 pJ/it |
| 6 | add/leading_dimension_broadcast | arch-a | PASS | PASS | 0.052 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 0.00 ms | 78.22 mW | 25266.00 pJ | 0.048 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 3120000.00 samples/s | 0.00 ms | 2.23 mW | 658.67 pJ/it |
| 7 | concat/channel_axis | arch-a | PASS | PASS | 0.053 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 0.00 ms | 78.16 mW | 35718.00 pJ | 0.047 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 2200000.00 samples/s | 0.00 ms | 2.16 mW | 934.67 pJ/it |
| 8 | concat/negative_axis | arch-a | PASS | PASS | 0.047 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 0.00 ms | 78.09 mW | 81450.00 pJ | 0.049 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 961000.00 samples/s | 0.00 ms | 2.09 mW | 2108.00 pJ/it |
| 9 | concat/three_inputs_channel_axis | arch-a | PASS | PASS | 0.049 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 0.00 ms | 78.15 mW | 50328.00 pJ | 0.045 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 1560000.00 samples/s | 0.00 ms | 2.15 mW | 1332.67 pJ/it |
| 10 | conv/batch_2 | arch-a | PASS | PASS | 0.058 s | 0.00 MiB | 0.00 MiB | 2 | 2 | 0.01 ms | 82.62 mW | 1131451.48 pJ | 0.057 s | 0.00 MiB | 0.01 MiB | 4 | 2 | 168000.00 samples/s | 0.01 ms | 53.33 mW | 343254.69 pJ/it |
| 11 | conv/batch_4_pointwise | arch-a | PASS | FAIL | 0.055 s | 0.00 MiB | 0.01 MiB | 5 | 4 | 0.00 ms | 116.08 mW | 456420.96 pJ | 0.060 s | 0.00 MiB | 0.01 MiB | 5 | 4 | 486000.00 samples/s | 0.00 ms | 70.89 mW | 160104.45 pJ/it |
| 12 | conv/depthwise_1024_channels | arch-a | PASS | FAIL | 0.081 s | 0.19 MiB | 0.38 MiB | 129 | 128 | 0.22 ms | 178.45 mW | 39393966.72 pJ | - | - | - | - | - | - | - | - | - |
| 13 | conv/depthwise_grouped | arch-a | PASS | FAIL | 0.055 s | 0.01 MiB | 0.00 MiB | 5 | 4 | 0.01 ms | 107.78 mW | 671878.96 pJ | - | - | - | - | - | - | - | - | - |
| 14 | conv/dilated_3x3 | arch-a | PASS | PASS | 0.060 s | 0.01 MiB | 0.01 MiB | 10 | 9 | 0.01 ms | 118.77 mW | 1034819.16 pJ | 0.067 s | 0.01 MiB | 0.01 MiB | 12 | 9 | 189000.00 samples/s | 0.01 ms | 75.03 mW | 435165.28 pJ/it |
| 15 | conv/dynamic | arch-a | PASS | FAIL | 0.056 s | 0.00 MiB | 0.00 MiB | 5 | 0 | 0.00 ms | 92.28 mW | 169336.00 pJ | 0.057 s | 0.00 MiB | 0.00 MiB | 6 | 0 | 661000.00 samples/s | 0.00 ms | 18.68 mW | 30964.00 pJ/it |
| 16 | conv/explicit_padding | arch-a | PASS | FAIL | 0.062 s | 0.01 MiB | 0.02 MiB | 17 | 16 | 0.01 ms | 145.34 mW | 1454397.84 pJ | - | - | - | - | - | - | - | - | - |
| 17 | conv/grouped_many_groups | arch-a | PASS | FAIL | 0.486 s | 0.05 MiB | 0.09 MiB | 65 | 64 | 0.18 ms | 142.21 mW | 25867112.36 pJ | 0.500 s | 0.11 MiB | 0.79 MiB | 127 | 64 | 569.00 samples/s | 1.76 ms | 141.19 mW | 252570125.00 pJ/it |
| 18 | conv/grouped_two_groups | arch-a | PASS | FAIL | 0.063 s | 0.00 MiB | 0.00 MiB | 3 | 2 | 0.01 ms | 101.46 mW | 543914.48 pJ | 0.061 s | 0.00 MiB | 0.01 MiB | 9 | 2 | 327000.00 samples/s | 0.00 ms | 116.36 mW | 453237.70 pJ/it |
| 19 | conv/huge_pointwise_1024 | arch-a | PASS | FAIL | 0.160 s | 0.01 MiB | 0.11 MiB | 73 | 64 | 0.02 ms | 249.55 mW | 3896647.36 pJ | 0.176 s | 0.04 MiB | 0.11 MiB | 74 | 64 | 35300.00 samples/s | 0.03 ms | 136.81 mW | 4031965.75 pJ/it |
| 20 | conv/huge_pointwise_1024_dynamic | arch-a | PASS | FAIL | 0.101 s | 8.04 MiB | 12.61 MiB | 168 | 0 | 2.63 ms | 169.52 mW | 445489032.00 pJ | - | - | - | - | - | - | - | - | - |
| 21 | conv/input_224_7x7_stride2 | arch-a | PASS | FAIL | 1.124 s | 24.14 MiB | 61.87 MiB | 168 | 169 | 38.41 ms | 185.26 mW | 7116544212.12 pJ | - | - | - | - | - | - | - | - | - |
| 22 | conv/kernel_2x2 | arch-a | PASS | FAIL | 0.064 s | 0.00 MiB | 0.00 MiB | 1 | 1 | 0.00 ms | 83.83 mW | 360568.24 pJ | 0.099 s | 0.00 MiB | 0.00 MiB | 3 | 1 | 380000.00 samples/s | 0.00 ms | 52.64 mW | 151421.99 pJ/it |
| 23 | conv/kernel_3x3 | arch-a | PASS | FAIL | 0.057 s | 0.01 MiB | 0.01 MiB | 10 | 9 | 0.01 ms | 123.80 mW | 889640.16 pJ | - | - | - | - | - | - | - | - | - |
| 24 | conv/kernel_equals_input_spatial | arch-a | PASS | PASS | 0.056 s | 0.00 MiB | 0.00 MiB | 2 | 2 | 0.00 ms | 89.61 mW | 415689.48 pJ | 0.059 s | 0.00 MiB | 0.00 MiB | 4 | 2 | 464000.00 samples/s | 0.00 ms | 68.91 mW | 166273.89 pJ/it |
| 25 | conv/large_input_channels_1x1 | arch-a | PASS | PASS | 0.087 s | 0.01 MiB | 0.02 MiB | 9 | 8 | 0.01 ms | 117.82 mW | 901121.92 pJ | 0.087 s | 0.01 MiB | 0.02 MiB | 10 | 8 | 306000.00 samples/s | 0.00 ms | 91.39 mW | 360779.57 pJ/it |
| 26 | conv/large_output_channels_1x1 | arch-a | PASS | PASS | 0.088 s | 0.01 MiB | 0.02 MiB | 17 | 8 | 0.01 ms | 128.44 mW | 1139415.92 pJ | 0.089 s | 0.01 MiB | 0.02 MiB | 18 | 8 | 207000.00 samples/s | 0.00 ms | 73.39 mW | 358350.06 pJ/it |
| 27 | conv/large_spatial | arch-a | PASS | FAIL | 0.060 s | 0.01 MiB | 0.04 MiB | 37 | 36 | 0.02 ms | 172.07 mW | 2928344.64 pJ | - | - | - | - | - | - | - | - | - |
| 28 | conv/multi_channel | arch-a | PASS | FAIL | 0.056 s | 0.00 MiB | 0.00 MiB | 4 | 3 | 0.01 ms | 105.68 mW | 685040.72 pJ | 0.057 s | 0.00 MiB | 0.00 MiB | 4 | 3 | 178000.00 samples/s | 0.01 ms | 32.10 mW | 185757.05 pJ/it |
| 29 | conv/non_square_kernel_1x3 | arch-a | PASS | PASS | 0.066 s | 0.00 MiB | 0.00 MiB | 3 | 2 | 0.01 ms | 99.35 mW | 679752.48 pJ | 0.054 s | 0.00 MiB | 0.00 MiB | 3 | 2 | 163000.00 samples/s | 0.01 ms | 13.04 mW | 81630.31 pJ/it |
| 30 | conv/non_square_kernel_3x1 | arch-a | PASS | PASS | 0.060 s | 0.00 MiB | 0.00 MiB | 3 | 2 | 0.01 ms | 95.89 mW | 1292976.48 pJ | 0.065 s | 0.00 MiB | 0.00 MiB | 3 | 2 | 77500.00 samples/s | 0.01 ms | 9.04 mW | 117499.65 pJ/it |
| 31 | conv/non_uniform_stride | arch-a | PASS | FAIL | 0.056 s | 0.00 MiB | 0.00 MiB | 4 | 3 | 0.01 ms | 104.05 mW | 790874.72 pJ | 0.056 s | 0.00 MiB | 0.00 MiB | 4 | 3 | 161000.00 samples/s | 0.01 ms | 30.89 mW | 198689.55 pJ/it |
| 32 | conv/output_channel_grouping_minimal | arch-a | PASS | FAIL | 0.083 s | 0.10 MiB | 0.34 MiB | 131 | 128 | 0.26 ms | 170.73 mW | 44125916.72 pJ | - | - | - | - | - | - | - | - | - |
| 33 | conv/pointwise_1x1 | arch-a | PASS | FAIL | 0.052 s | 0.00 MiB | 0.00 MiB | 1 | 1 | 0.01 ms | 80.24 mW | 987244.24 pJ | 0.055 s | 0.00 MiB | 0.00 MiB | 3 | 1 | 135000.00 samples/s | 0.01 ms | 47.15 mW | 371973.57 pJ/it |
| 34 | conv/pointwise_tiled_chain | arch-a | PASS | PASS | 0.699 s | 0.01 MiB | 0.04 MiB | 20 | 80 | 0.04 ms | 153.88 mW | 6445455.20 pJ | 0.634 s | 0.05 MiB | 0.08 MiB | 22 | 80 | 14300.00 samples/s | 0.07 ms | 71.96 mW | 5297594.20 pJ/it |
| 35 | conv/real_asymmetric_padding | arch-a | PASS | FAIL | 0.063 s | 0.01 MiB | 0.03 MiB | 29 | 28 | 0.01 ms | 153.67 mW | 2221606.72 pJ | - | - | - | - | - | - | - | - | - |
| 36 | conv/relu_conv_store | arch-a | PASS | FAIL | 0.094 s | 0.16 MiB | 0.67 MiB | 168 | 184 | 0.56 ms | 183.08 mW | 103057892.80 pJ | - | - | - | - | - | - | - | - | - |
| 37 | conv/same_lower_3x3 | arch-a | PASS | FAIL | 0.061 s | 0.01 MiB | 0.02 MiB | 26 | 25 | 0.01 ms | 166.15 mW | 2215009.00 pJ | - | - | - | - | - | - | - | - | - |
| 38 | conv/same_padding_3x3 | arch-a | PASS | FAIL | 0.059 s | 0.01 MiB | 0.02 MiB | 26 | 25 | 0.01 ms | 166.15 mW | 2215009.00 pJ | - | - | - | - | - | - | - | - | - |
| 39 | conv/strategy_depthwise_16 | arch-a | PASS | FAIL | 0.092 s | 0.06 MiB | 0.35 MiB | 168 | 168 | 0.34 ms | 197.94 mW | 66331479.08 pJ | - | - | - | - | - | - | - | - | - |
| 40 | conv/strategy_input_k_tiled | arch-a | PASS | FAIL | 0.084 s | 0.08 MiB | 0.27 MiB | 109 | 108 | 0.35 ms | 170.81 mW | 60422605.92 pJ | - | - | - | - | - | - | - | - | - |
| 41 | conv/strategy_output_channel_tiled | arch-a | PASS | FAIL | 0.071 s | 0.03 MiB | 0.16 MiB | 74 | 72 | 0.09 ms | 155.74 mW | 14244739.28 pJ | - | - | - | - | - | - | - | - | - |
| 42 | conv/strategy_streamed_packed | arch-a | PASS | FAIL | 0.184 s | 3.34 MiB | 7.89 MiB | 168 | 168 | 9.35 ms | 179.86 mW | 1682364509.56 pJ | - | - | - | - | - | - | - | - | - |
| 43 | conv/strategy_streamed_patch | arch-a | PASS | FAIL | 0.098 s | 0.34 MiB | 1.32 MiB | 168 | 168 | 1.90 ms | 181.91 mW | 346476645.64 pJ | - | - | - | - | - | - | - | - | - |
| 44 | conv/strategy_tiled_2d | arch-a | PASS | FAIL | 0.117 s | 0.11 MiB | 0.44 MiB | 168 | 168 | 0.42 ms | 182.13 mW | 75690907.84 pJ | - | - | - | - | - | - | - | - | - |
| 45 | conv/stride_2 | arch-a | PASS | FAIL | 0.059 s | 0.01 MiB | 0.00 MiB | 5 | 4 | 0.01 ms | 110.78 mW | 580154.96 pJ | - | - | - | - | - | - | - | - | - |
| 46 | conv/with_bias_3x3 | arch-a | PASS | FAIL | 0.057 s | 0.00 MiB | 0.01 MiB | 4 | 3 | 0.01 ms | 104.16 mW | 776220.72 pJ | 0.057 s | 0.00 MiB | 0.01 MiB | 4 | 3 | 165000.00 samples/s | 0.01 ms | 30.99 mW | 196092.89 pJ/it |
| 47 | conv/with_constant | arch-a | PASS | FAIL | 0.057 s | 0.00 MiB | 0.00 MiB | 1 | 1 | 0.01 ms | 81.74 mW | 541270.24 pJ | 0.059 s | 0.00 MiB | 0.00 MiB | 4 | 1 | 232000.00 samples/s | 0.00 ms | 92.34 mW | 438607.24 pJ/it |
| 48 | conv/without_kernel_shape_attr | arch-a | PASS | FAIL | 0.055 s | 0.01 MiB | 0.01 MiB | 10 | 9 | 0.01 ms | 123.80 mW | 889640.16 pJ | - | - | - | - | - | - | - | - | - |
| 49 | conv/yolo11n_depthwise_head | arch-a | PASS | FAIL | 2.274 s | 8.66 MiB | 34.24 MiB | 168 | 255 | 42.70 ms | 200.52 mW | 8562449708.00 pJ | - | - | - | - | - | - | - | - | - |
| 50 | conv/yolo11n_heavy | arch-a | PASS | FAIL | 0.478 s | 4.82 MiB | 19.10 MiB | 161 | 800 | 8.54 ms | 350.86 mW | 2994764012.00 pJ | - | - | - | - | - | - | - | - | - |
| 51 | conv/yolo11n_stem | arch-a | PASS | FAIL | 0.975 s | 12.86 MiB | 37.59 MiB | 168 | 488 | 14.24 ms | 301.23 mW | 4289558753.00 pJ | - | - | - | - | - | - | - | - | - |
| 52 | div/after_gemm | arch-a | PASS | FAIL | 0.056 s | 0.01 MiB | 0.01 MiB | 5 | 4 | 0.01 ms | 104.70 mW | 815012.96 pJ | 0.056 s | 0.01 MiB | 0.01 MiB | 6 | 4 | 277000.00 samples/s | 0.00 ms | 45.81 mW | 190085.16 pJ/it |
| 53 | div/basic | arch-a | PASS | PASS | 0.049 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 0.00 ms | 78.22 mW | 25266.00 pJ | 0.050 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 3120000.00 samples/s | 0.00 ms | 2.23 mW | 658.67 pJ/it |
| 54 | div/channel_broadcast_1024 | arch-a | PASS | PASS | 0.051 s | 0.02 MiB | 0.01 MiB | 1 | 0 | 0.01 ms | 78.12 mW | 540030.00 pJ | 0.055 s | 0.02 MiB | 0.01 MiB | 1 | 0 | 145000.00 samples/s | 0.01 ms | 2.11 mW | 13388.67 pJ/it |
| 55 | div/leading_dimension_broadcast | arch-a | PASS | PASS | 0.053 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 0.00 ms | 78.22 mW | 25266.00 pJ | 0.052 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 3120000.00 samples/s | 0.00 ms | 2.23 mW | 658.67 pJ/it |
| 56 | div/runtime_scalar_rhs | arch-a | PASS | PASS | 0.048 s | 0.02 MiB | 0.01 MiB | 1 | 0 | 0.01 ms | 78.12 mW | 540030.00 pJ | 0.051 s | 0.02 MiB | 0.01 MiB | 1 | 0 | 145000.00 samples/s | 0.01 ms | 2.11 mW | 13388.67 pJ/it |
| 57 | div/scalar_constant | arch-a | PASS | PASS | 0.057 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 0.00 ms | 78.22 mW | 25266.00 pJ | 0.059 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 3120000.00 samples/s | 0.00 ms | 2.23 mW | 658.67 pJ/it |
| 58 | gather/3d_input_axis1 | arch-a | PASS | PASS | 0.052 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 0.00 ms | 78.08 mW | 45990.00 pJ | 0.053 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 1700000.00 samples/s | 0.00 ms | 2.08 mW | 1174.67 pJ/it |
| 59 | gather/axis0_matrix_indices | arch-a | PASS | PASS | 0.055 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 0.00 ms | 78.07 mW | 54414.00 pJ | 0.052 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 1440000.00 samples/s | 0.00 ms | 2.07 mW | 1390.67 pJ/it |
| 60 | gather/axis1 | arch-a | PASS | PASS | 0.051 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 0.00 ms | 78.06 mW | 62526.00 pJ | 0.053 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 1250000.00 samples/s | 0.00 ms | 2.06 mW | 1598.67 pJ/it |
| 61 | gather/negative_axis | arch-a | PASS | PASS | 0.049 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 0.00 ms | 78.03 mW | 112134.00 pJ | 0.051 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 697000.00 samples/s | 0.00 ms | 2.03 mW | 2870.67 pJ/it |
| 62 | gather/negative_indices | arch-a | PASS | PASS | 0.052 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 0.00 ms | 78.13 mW | 29376.00 pJ | 0.058 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 2670000.00 samples/s | 0.00 ms | 2.12 mW | 748.67 pJ/it |
| 63 | gemm/alpha_beta | arch-a | PASS | FAIL | 0.059 s | 0.01 MiB | 0.01 MiB | 5 | 4 | 0.01 ms | 105.27 mW | 784908.96 pJ | 0.061 s | 0.01 MiB | 0.01 MiB | 6 | 4 | 304000.00 samples/s | 0.00 ms | 48.12 mW | 184972.16 pJ/it |
| 64 | gemm/bias_rank2_broadcast | arch-a | PASS | FAIL | 0.061 s | 0.00 MiB | 0.01 MiB | 5 | 4 | 0.01 ms | 105.98 mW | 749484.96 pJ | 0.058 s | 0.01 MiB | 0.01 MiB | 6 | 4 | 351000.00 samples/s | 0.00 ms | 52.58 mW | 176636.66 pJ/it |
| 65 | gemm/dynamic | arch-a | PASS | FAIL | 0.053 s | 0.00 MiB | 0.00 MiB | 5 | 0 | 0.00 ms | 91.48 mW | 221475.00 pJ | 0.056 s | 0.00 MiB | 0.00 MiB | 5 | 0 | 785000.00 samples/s | 0.00 ms | 20.31 mW | 27813.50 pJ/it |
| 66 | gemm/dynamic_alpha | arch-a | PASS | FAIL | 0.055 s | 0.00 MiB | 0.00 MiB | 5 | 0 | 0.00 ms | 91.42 mW | 298198.00 pJ | 0.056 s | 0.00 MiB | 0.00 MiB | 5 | 0 | 612000.00 samples/s | 0.00 ms | 20.35 mW | 37289.67 pJ/it |
| 67 | gemm/dynamic_beta | arch-a | PASS | FAIL | 0.056 s | 0.00 MiB | 0.00 MiB | 5 | 0 | 0.00 ms | 91.32 mW | 398595.00 pJ | 0.056 s | 0.00 MiB | 0.00 MiB | 5 | 0 | 359000.00 samples/s | 0.00 ms | 20.22 mW | 60212.83 pJ/it |
| 68 | gemm/dynamic_bias | arch-a | PASS | FAIL | 0.055 s | 0.00 MiB | 0.00 MiB | 5 | 0 | 0.00 ms | 91.45 mW | 243703.00 pJ | 0.055 s | 0.00 MiB | 0.00 MiB | 5 | 0 | 785000.00 samples/s | 0.00 ms | 20.32 mW | 28385.00 pJ/it |
| 69 | gemm/dynamic_bias_alpha_beta | arch-a | PASS | FAIL | 0.055 s | 0.00 MiB | 0.00 MiB | 5 | 0 | 0.01 ms | 91.28 mW | 513811.00 pJ | 0.056 s | 0.00 MiB | 0.00 MiB | 5 | 0 | 247000.00 samples/s | 0.00 ms | 20.20 mW | 85611.50 pJ/it |
| 70 | gemm/dynamic_transpose_b | arch-a | PASS | FAIL | 0.053 s | 0.00 MiB | 0.00 MiB | 5 | 0 | 0.00 ms | 91.38 mW | 118883.00 pJ | 0.055 s | 0.00 MiB | 0.00 MiB | 5 | 0 | 1340000.00 samples/s | 0.00 ms | 20.55 mW | 16541.00 pJ/it |
| 71 | gemm/huge_1024 | arch-a | PASS | FAIL | 0.144 s | 0.01 MiB | 0.10 MiB | 73 | 64 | 0.02 ms | 215.04 mW | 3767885.36 pJ | 0.167 s | 0.03 MiB | 0.10 MiB | 73 | 64 | 14900.00 samples/s | 0.07 ms | 154.31 mW | 10866697.65 pJ/it |
| 72 | gemm/large | arch-a | PASS | FAIL | 0.058 s | 0.02 MiB | 0.03 MiB | 17 | 16 | 0.01 ms | 140.15 mW | 1573768.84 pJ | 0.063 s | 0.02 MiB | 0.03 MiB | 17 | 16 | 142000.00 samples/s | 0.01 ms | 118.27 mW | 830693.99 pJ/it |
| 73 | gemm/large_k_small_n | arch-a | PASS | FAIL | 0.084 s | 0.01 MiB | 0.01 MiB | 9 | 8 | 0.00 ms | 133.48 mW | 633769.92 pJ | 0.089 s | 0.01 MiB | 0.01 MiB | 9 | 8 | 439000.00 samples/s | 0.00 ms | 125.25 mW | 329671.91 pJ/it |
| 74 | gemm/non_square | arch-a | PASS | FAIL | 0.060 s | 0.00 MiB | 0.01 MiB | 5 | 4 | 0.00 ms | 118.96 mW | 419565.96 pJ | 0.060 s | 0.00 MiB | 0.01 MiB | 5 | 4 | 486000.00 samples/s | 0.00 ms | 70.69 mW | 160313.79 pJ/it |
| 75 | gemm/scalar_bias | arch-a | PASS | FAIL | 0.059 s | 0.00 MiB | 0.01 MiB | 5 | 4 | 0.01 ms | 105.98 mW | 749484.96 pJ | 0.056 s | 0.01 MiB | 0.01 MiB | 6 | 4 | 351000.00 samples/s | 0.00 ms | 52.58 mW | 176636.66 pJ/it |
| 76 | gemm/small | arch-a | PASS | PASS | 0.056 s | 0.00 MiB | 0.00 MiB | 2 | 2 | 0.00 ms | 90.14 mW | 398436.48 pJ | 0.055 s | 0.00 MiB | 0.00 MiB | 4 | 2 | 464000.00 samples/s | 0.00 ms | 69.74 mW | 162693.89 pJ/it |
| 77 | gemm/small_k_large_n | arch-a | PASS | PASS | 0.092 s | 0.01 MiB | 0.02 MiB | 17 | 8 | 0.01 ms | 131.01 mW | 1043061.92 pJ | 0.089 s | 0.01 MiB | 0.02 MiB | 18 | 8 | 248000.00 samples/s | 0.00 ms | 82.00 mW | 345641.89 pJ/it |
| 78 | gemm/square_weights | arch-a | PASS | FAIL | 0.076 s | 0.03 MiB | 0.08 MiB | 42 | 40 | 0.02 ms | 151.77 mW | 3284393.60 pJ | - | - | - | - | - | - | - | - | - |
| 79 | gemm/transpose_a | arch-a | PASS | FAIL | 0.056 s | 0.00 MiB | 0.01 MiB | 5 | 4 | 0.01 ms | 109.14 mW | 628868.96 pJ | 0.057 s | 0.00 MiB | 0.01 MiB | 6 | 4 | 424000.00 samples/s | 0.00 ms | 58.98 mW | 162091.12 pJ/it |
| 80 | gemm/transpose_a_and_b | arch-a | PASS | FAIL | 0.055 s | 0.00 MiB | 0.01 MiB | 5 | 4 | 0.01 ms | 109.14 mW | 628868.96 pJ | 0.056 s | 0.00 MiB | 0.01 MiB | 6 | 4 | 424000.00 samples/s | 0.00 ms | 58.98 mW | 162091.12 pJ/it |
| 81 | gemm/transpose_b | arch-a | PASS | FAIL | 0.061 s | 0.00 MiB | 0.01 MiB | 5 | 4 | 0.00 ms | 118.96 mW | 419565.96 pJ | 0.059 s | 0.00 MiB | 0.01 MiB | 5 | 4 | 486000.00 samples/s | 0.00 ms | 70.69 mW | 160313.79 pJ/it |
| 82 | gemm/transpose_b_with_bias | arch-a | PASS | FAIL | 0.064 s | 0.01 MiB | 0.01 MiB | 5 | 4 | 0.01 ms | 110.55 mW | 557818.96 pJ | 0.057 s | 0.01 MiB | 0.01 MiB | 5 | 4 | 339000.00 samples/s | 0.00 ms | 55.18 mW | 180359.12 pJ/it |
| 83 | gemm/with_bias | arch-a | PASS | FAIL | 0.050 s | 0.01 MiB | 0.01 MiB | 5 | 4 | 0.01 ms | 108.77 mW | 604966.96 pJ | 0.055 s | 0.01 MiB | 0.01 MiB | 5 | 4 | 288000.00 samples/s | 0.00 ms | 52.44 mW | 186098.45 pJ/it |
| 84 | gemv/all_constant | arch-a | PASS | PASS | 0.050 s | 0.00 MiB | 0.00 MiB | 0 | 0 | 0.00 ms | 2.00 mW | 0.00 pJ | 0.052 s | 0.00 MiB | 0.00 MiB | 0 | 0 | 0.00 samples/s | 0.00 ms | 2.00 mW | 0.00 pJ/it |
| 85 | gemv/constant_weight | arch-a | PASS | FAIL | 0.062 s | 0.00 MiB | 0.01 MiB | 6 | 4 | 0.01 ms | 111.15 mW | 573535.96 pJ | 0.063 s | 0.00 MiB | 0.01 MiB | 8 | 4 | 412000.00 samples/s | 0.00 ms | 86.05 mW | 242243.79 pJ/it |
| 86 | gemv/non_uniform_bias | arch-a | PASS | FAIL | 0.063 s | 0.00 MiB | 0.01 MiB | 6 | 4 | 0.01 ms | 109.82 mW | 609371.96 pJ | 0.063 s | 0.00 MiB | 0.01 MiB | 8 | 4 | 376000.00 samples/s | 0.00 ms | 82.45 mW | 254539.29 pJ/it |
| 87 | gemv/scalar_bias | arch-a | PASS | FAIL | 0.063 s | 0.00 MiB | 0.01 MiB | 6 | 4 | 0.01 ms | 109.82 mW | 609371.96 pJ | 0.064 s | 0.00 MiB | 0.01 MiB | 8 | 4 | 376000.00 samples/s | 0.00 ms | 82.45 mW | 254539.29 pJ/it |
| 88 | gemv/uniform_bias | arch-a | PASS | FAIL | 0.064 s | 0.00 MiB | 0.01 MiB | 6 | 4 | 0.01 ms | 109.82 mW | 609371.96 pJ | 0.063 s | 0.00 MiB | 0.01 MiB | 8 | 4 | 376000.00 samples/s | 0.00 ms | 82.45 mW | 254539.29 pJ/it |
| 89 | matmul/basic | arch-a | PASS | PASS | 0.057 s | 0.00 MiB | 0.00 MiB | 2 | 2 | 0.00 ms | 90.14 mW | 398436.48 pJ | 0.056 s | 0.00 MiB | 0.00 MiB | 4 | 2 | 464000.00 samples/s | 0.00 ms | 69.74 mW | 162693.89 pJ/it |
| 90 | matmul/batched_3d | arch-a | PASS | FAIL | 0.058 s | 0.00 MiB | 0.01 MiB | 5 | 4 | 0.01 ms | 108.59 mW | 646972.96 pJ | 0.059 s | 0.00 MiB | 0.01 MiB | 6 | 4 | 438000.00 samples/s | 0.00 ms | 59.21 mW | 161865.62 pJ/it |
| 91 | matmul/batched_3d_dynamic | arch-a | PASS | PASS | 0.054 s | 0.00 MiB | 0.00 MiB | 4 | 0 | 0.00 ms | 92.19 mW | 167975.00 pJ | 0.054 s | 0.00 MiB | 0.00 MiB | 5 | 0 | 1140000.00 samples/s | 0.00 ms | 17.43 mW | 16336.83 pJ/it |
| 92 | matmul/batched_left_constant | arch-a | PASS | FAIL | 0.061 s | 0.00 MiB | 0.02 MiB | 9 | 8 | 0.01 ms | 114.39 mW | 1009105.92 pJ | - | - | - | - | - | - | - | - | - |
| 93 | matmul/batched_lhs_broadcast | arch-a | PASS | FAIL | 0.057 s | 0.00 MiB | 0.01 MiB | 5 | 4 | 0.01 ms | 109.39 mW | 621440.96 pJ | 0.071 s | 0.00 MiB | 0.01 MiB | 6 | 4 | 441000.00 samples/s | 0.00 ms | 60.34 mW | 160658.62 pJ/it |
| 94 | matmul/batched_rhs_broadcast | arch-a | PASS | FAIL | 0.056 s | 0.00 MiB | 0.01 MiB | 5 | 4 | 0.01 ms | 108.59 mW | 646972.96 pJ | 0.056 s | 0.00 MiB | 0.01 MiB | 6 | 4 | 438000.00 samples/s | 0.00 ms | 59.21 mW | 161865.62 pJ/it |
| 95 | matmul/dynamic | arch-a | PASS | FAIL | 0.055 s | 0.00 MiB | 0.00 MiB | 5 | 0 | 0.00 ms | 91.42 mW | 148195.00 pJ | 0.058 s | 0.00 MiB | 0.00 MiB | 5 | 0 | 1310000.00 samples/s | 0.00 ms | 20.49 mW | 18009.67 pJ/it |
| 96 | matmul/huge_1024 | arch-a | PASS | FAIL | 0.151 s | 0.01 MiB | 0.10 MiB | 73 | 64 | 0.02 ms | 215.04 mW | 3767885.36 pJ | 0.172 s | 0.03 MiB | 0.10 MiB | 73 | 64 | 14900.00 samples/s | 0.07 ms | 154.31 mW | 10866697.65 pJ/it |
| 97 | matmul/left_constant | arch-a | PASS | FAIL | 0.058 s | 0.00 MiB | 0.01 MiB | 5 | 4 | 0.01 ms | 108.86 mW | 637168.96 pJ | 0.064 s | 0.00 MiB | 0.01 MiB | 6 | 4 | 424000.00 samples/s | 0.00 ms | 58.67 mW | 162346.12 pJ/it |
| 98 | matmul/matrix_vector | arch-a | PASS | FAIL | 0.102 s | 0.52 MiB | 0.78 MiB | 168 | 173 | 0.38 ms | 202.13 mW | 77751814.88 pJ | - | - | - | - | - | - | - | - | - |
| 99 | matmul/vector_matrix | arch-a | PASS | FAIL | 0.085 s | 0.01 MiB | 0.01 MiB | 9 | 8 | 0.01 ms | 118.68 mW | 879301.92 pJ | - | - | - | - | - | - | - | - | - |
| 100 | matmul/yolo_attention | arch-a | PASS | FAIL | 0.483 s | 1.02 MiB | 43.44 MiB | 168 | 0 | 8.15 ms | 170.00 mW | 1385775865.00 pJ | - | - | - | - | - | - | - | - | - |
| 101 | mul/after_conv | arch-a | PASS | FAIL | 0.074 s | 0.00 MiB | 0.00 MiB | 4 | 3 | 0.01 ms | 107.64 mW | 586955.72 pJ | 0.062 s | 0.00 MiB | 0.00 MiB | 4 | 3 | 220000.00 samples/s | 0.00 ms | 34.96 mW | 162998.05 pJ/it |
| 102 | mul/after_conv_scalar_constant | arch-a | PASS | FAIL | 0.063 s | 0.00 MiB | 0.00 MiB | 4 | 3 | 0.01 ms | 107.64 mW | 586955.72 pJ | 0.061 s | 0.00 MiB | 0.00 MiB | 4 | 3 | 220000.00 samples/s | 0.00 ms | 34.96 mW | 162998.05 pJ/it |
| 103 | mul/basic | arch-a | PASS | PASS | 0.055 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 0.00 ms | 78.22 mW | 25266.00 pJ | 0.052 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 3120000.00 samples/s | 0.00 ms | 2.23 mW | 658.67 pJ/it |
| 104 | mul/channel_broadcast_1024 | arch-a | PASS | PASS | 0.049 s | 0.02 MiB | 0.01 MiB | 1 | 0 | 0.01 ms | 78.12 mW | 540030.00 pJ | 0.049 s | 0.02 MiB | 0.01 MiB | 1 | 0 | 145000.00 samples/s | 0.01 ms | 2.11 mW | 13388.67 pJ/it |
| 105 | mul/leading_dimension_broadcast | arch-a | PASS | PASS | 0.052 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 0.00 ms | 78.22 mW | 25266.00 pJ | 0.053 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 3120000.00 samples/s | 0.00 ms | 2.23 mW | 658.67 pJ/it |
| 106 | mul/scalar_constant | arch-a | PASS | PASS | 0.055 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 0.00 ms | 78.22 mW | 25266.00 pJ | 0.051 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 3120000.00 samples/s | 0.00 ms | 2.23 mW | 658.67 pJ/it |
| 107 | pool/avg_basic | arch-a | PASS | PASS | 0.057 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 0.01 ms | 78.02 mW | 931506.00 pJ | 0.052 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 84000.00 samples/s | 0.01 ms | 2.02 mW | 24067.00 pJ/it |
| 108 | pool/avg_ceil_mode | arch-a | PASS | PASS | 0.055 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 0.00 ms | 78.03 mW | 340146.00 pJ | 0.055 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 230000.00 samples/s | 0.00 ms | 2.03 mW | 8810.67 pJ/it |
| 109 | pool/avg_explicit_padding | arch-a | PASS | PASS | 0.056 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 0.01 ms | 78.03 mW | 688356.00 pJ | 0.058 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 114000.00 samples/s | 0.01 ms | 2.03 mW | 17809.00 pJ/it |
| 110 | pool/avg_include_pad | arch-a | PASS | PASS | 0.056 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 0.01 ms | 78.02 mW | 663612.00 pJ | 0.058 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 118000.00 samples/s | 0.01 ms | 2.02 mW | 17081.00 pJ/it |
| 111 | pool/avg_large_channels | arch-a | PASS | PASS | 0.064 s | 0.04 MiB | 0.02 MiB | 1 | 0 | 0.24 ms | 78.00 mW | 18399156.00 pJ | 0.060 s | 0.04 MiB | 0.02 MiB | 1 | 0 | 4250.00 samples/s | 0.24 ms | 2.00 mW | 471428.00 pJ/it |
| 112 | pool/avg_non_uniform_stride | arch-a | PASS | PASS | 0.055 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 0.01 ms | 78.02 mW | 1132254.00 pJ | 0.052 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 69100.00 samples/s | 0.01 ms | 2.02 mW | 29191.00 pJ/it |
| 113 | pool/avg_real_asymmetric_padding | arch-a | PASS | PASS | 0.055 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 0.03 ms | 78.02 mW | 1966692.00 pJ | 0.057 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 39700.00 samples/s | 0.03 ms | 2.02 mW | 50961.00 pJ/it |
| 114 | pool/max_after_conv | arch-a | PASS | FAIL | 0.059 s | 0.00 MiB | 0.00 MiB | 5 | 4 | 0.01 ms | 99.12 mW | 1210689.96 pJ | 0.061 s | 0.00 MiB | 0.00 MiB | 5 | 4 | 142000.00 samples/s | 0.01 ms | 34.60 mW | 273954.62 pJ/it |
| 115 | pool/max_basic | arch-a | PASS | PASS | 0.053 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 0.00 ms | 78.06 mW | 324744.00 pJ | 0.052 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 241000.00 samples/s | 0.00 ms | 2.06 mW | 8532.67 pJ/it |
| 116 | pool/max_ceil_mode | arch-a | PASS | PASS | 0.051 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 0.00 ms | 78.07 mW | 151464.00 pJ | 0.049 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 516000.00 samples/s | 0.00 ms | 2.07 mW | 3972.67 pJ/it |
| 117 | pool/max_global_style_kernel_equals_input | arch-a | PASS | PASS | 0.054 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 0.01 ms | 78.01 mW | 658626.00 pJ | 0.056 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 119000.00 samples/s | 0.01 ms | 2.01 mW | 16871.00 pJ/it |
| 118 | pool/max_non_square_kernel | arch-a | PASS | PASS | 0.052 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 0.01 ms | 78.02 mW | 1063068.00 pJ | 0.051 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 73600.00 samples/s | 0.01 ms | 2.02 mW | 27417.00 pJ/it |
| 119 | pool/max_real_asymmetric_padding | arch-a | PASS | PASS | 0.054 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 0.01 ms | 78.03 mW | 814992.00 pJ | 0.058 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 96100.00 samples/s | 0.01 ms | 2.03 mW | 21173.00 pJ/it |
| 120 | pool/max_same_upper | arch-a | PASS | PASS | 0.057 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 0.01 ms | 78.04 mW | 625068.00 pJ | 0.052 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 125000.00 samples/s | 0.01 ms | 2.04 mW | 16233.00 pJ/it |
| 121 | pool/max_stride2_multichannel | arch-a | PASS | PASS | 0.051 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 0.02 ms | 78.02 mW | 1247274.00 pJ | 0.051 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 62700.00 samples/s | 0.02 ms | 2.02 mW | 32153.00 pJ/it |
| 122 | reduce_mean/4d_spatial | arch-a | PASS | FAIL | 0.053 s | 0.00 MiB | 0.00 MiB | 3 | 0 | 0.00 ms | 92.45 mW | 29676.00 pJ | 0.055 s | 0.00 MiB | 0.00 MiB | 3 | 0 | 2560000.00 samples/s | 0.00 ms | 4.38 mW | 1667.33 pJ/it |
| 123 | reduce_mean/4d_spatial_keepdims_0 | arch-a | PASS | FAIL | 0.052 s | 0.00 MiB | 0.00 MiB | 4 | 0 | 0.00 ms | 94.35 mW | 61801.00 pJ | 0.053 s | 0.00 MiB | 0.00 MiB | 4 | 0 | 2390000.00 samples/s | 0.00 ms | 19.52 mW | 9025.83 pJ/it |
| 124 | reduce_mean/after_conv | arch-a | PASS | FAIL | 0.059 s | 0.00 MiB | 0.00 MiB | 5 | 3 | 0.01 ms | 106.95 mW | 571332.72 pJ | 0.063 s | 0.00 MiB | 0.00 MiB | 5 | 3 | 220000.00 samples/s | 0.00 ms | 21.90 mW | 102726.72 pJ/it |
| 125 | reduce_mean/all_axes_keepdims_0 | arch-a | PASS | PASS | 0.050 s | 0.00 MiB | 0.00 MiB | 2 | 0 | 0.00 ms | 79.24 mW | 30982.00 pJ | 0.052 s | 0.00 MiB | 0.00 MiB | 2 | 0 | 4520000.00 samples/s | 0.00 ms | 3.41 mW | 775.00 pJ/it |
| 126 | reduce_mean/all_axes_keepdims_1 | arch-a | PASS | PASS | 0.052 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 0.00 ms | 78.22 mW | 17286.00 pJ | 0.048 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 4570000.00 samples/s | 0.00 ms | 2.22 mW | 437.33 pJ/it |
| 127 | reduce_mean/basic | arch-a | PASS | FAIL | 0.052 s | 0.00 MiB | 0.00 MiB | 4 | 0 | 0.00 ms | 93.51 mW | 34881.00 pJ | 0.053 s | 0.00 MiB | 0.00 MiB | 4 | 0 | 2780000.00 samples/s | 0.00 ms | 5.56 mW | 1904.50 pJ/it |
| 128 | reduce_mean/channel_axis_nchw | arch-a | PASS | FAIL | 0.052 s | 0.03 MiB | 0.02 MiB | 4 | 0 | 0.16 ms | 93.60 mW | 15436518.00 pJ | 0.055 s | 0.03 MiB | 0.08 MiB | 4 | 0 | 16000.00 samples/s | 0.06 ms | 5.00 mW | 323993.33 pJ/it |
| 129 | reduce_mean/keepdims_0 | arch-a | PASS | FAIL | 0.055 s | 0.00 MiB | 0.00 MiB | 5 | 0 | 0.00 ms | 91.40 mW | 68368.00 pJ | 0.054 s | 0.00 MiB | 0.00 MiB | 5 | 0 | 1880000.00 samples/s | 0.00 ms | 20.60 mW | 11458.17 pJ/it |
| 130 | reduce_mean/large_dimension_1024 | arch-a | PASS | PASS | 0.053 s | 0.01 MiB | 0.00 MiB | 1 | 0 | 0.00 ms | 78.02 mW | 217278.00 pJ | 0.052 s | 0.01 MiB | 0.00 MiB | 1 | 0 | 359000.00 samples/s | 0.00 ms | 2.02 mW | 5274.00 pJ/it |
| 131 | reduce_mean/legacy_axes_1_2_keepdims_1 | arch-a | PASS | FAIL | 0.052 s | 0.00 MiB | 0.00 MiB | 2 | 0 | 0.00 ms | 79.35 mW | 21505.00 pJ | 0.052 s | 0.00 MiB | 0.00 MiB | 2 | 0 | 3860000.00 samples/s | 0.00 ms | 3.37 mW | 798.00 pJ/it |
| 132 | reduce_mean/legacy_axis1_keepdims_0 | arch-a | PASS | FAIL | 0.071 s | 0.00 MiB | 0.00 MiB | 9 | 0 | 0.00 ms | 92.50 mW | 183708.00 pJ | 0.061 s | 0.00 MiB | 0.00 MiB | 9 | 0 | 1010000.00 samples/s | 0.00 ms | 38.63 mW | 41198.50 pJ/it |
| 133 | reduce_mean/legacy_axis1_keepdims_1 | arch-a | PASS | FAIL | 0.053 s | 0.00 MiB | 0.00 MiB | 8 | 0 | 0.00 ms | 94.56 mW | 129830.00 pJ | 0.054 s | 0.00 MiB | 0.00 MiB | 8 | 0 | 1390000.00 samples/s | 0.00 ms | 9.56 mW | 6733.50 pJ/it |
| 134 | reduce_mean/legacy_empty_axes_noop | arch-a | PASS | PASS | 0.050 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 0.00 ms | 78.22 mW | 17286.00 pJ | 0.048 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 4570000.00 samples/s | 0.00 ms | 2.22 mW | 437.33 pJ/it |
| 135 | reduce_mean/legacy_nchw_spatial | arch-a | PASS | FAIL | 0.054 s | 0.00 MiB | 0.00 MiB | 3 | 0 | 0.00 ms | 92.45 mW | 29676.00 pJ | 0.056 s | 0.00 MiB | 0.00 MiB | 3 | 0 | 1960000.00 samples/s | 0.00 ms | 4.28 mW | 2167.33 pJ/it |
| 136 | reduce_mean/legacy_negative_axis | arch-a | PASS | FAIL | 0.051 s | 0.00 MiB | 0.00 MiB | 6 | 0 | 0.00 ms | 93.52 mW | 51717.00 pJ | 0.057 s | 0.00 MiB | 0.00 MiB | 6 | 0 | 1850000.00 samples/s | 0.00 ms | 7.57 mW | 3828.83 pJ/it |
| 137 | reduce_mean/legacy_reduce_all_keepdims_1 | arch-a | PASS | PASS | 0.051 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 0.00 ms | 78.22 mW | 17286.00 pJ | 0.048 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 4570000.00 samples/s | 0.00 ms | 2.22 mW | 437.33 pJ/it |
| 138 | reduce_mean/negative_axis | arch-a | PASS | FAIL | 0.058 s | 0.00 MiB | 0.00 MiB | 6 | 0 | 0.00 ms | 93.52 mW | 51717.00 pJ | 0.054 s | 0.00 MiB | 0.00 MiB | 6 | 0 | 1850000.00 samples/s | 0.00 ms | 7.57 mW | 3828.83 pJ/it |
| 139 | relu/4d | arch-a | PASS | PASS | 0.052 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 0.00 ms | 78.18 mW | 40734.00 pJ | 0.049 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 1930000.00 samples/s | 0.00 ms | 2.18 mW | 1014.00 pJ/it |
| 140 | relu/after_conv | arch-a | PASS | FAIL | 0.058 s | 0.00 MiB | 0.00 MiB | 4 | 3 | 0.01 ms | 107.89 mW | 577437.72 pJ | 0.060 s | 0.00 MiB | 0.00 MiB | 4 | 3 | 220000.00 samples/s | 0.00 ms | 34.98 mW | 162801.39 pJ/it |
| 141 | relu/after_gemm | arch-a | PASS | FAIL | 0.061 s | 0.01 MiB | 0.01 MiB | 5 | 4 | 0.01 ms | 105.16 mW | 790056.96 pJ | 0.059 s | 0.01 MiB | 0.01 MiB | 6 | 4 | 291000.00 samples/s | 0.00 ms | 47.08 mW | 187063.49 pJ/it |
| 142 | relu/basic | arch-a | PASS | PASS | 0.052 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 0.00 ms | 78.22 mW | 17286.00 pJ | 0.050 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 4570000.00 samples/s | 0.00 ms | 2.22 mW | 437.33 pJ/it |
| 143 | reshape/4d_to_2d_flatten | arch-a | PASS | PASS | 0.047 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 0.00 ms | 78.28 mW | 20196.00 pJ | 0.050 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 3910000.00 samples/s | 0.00 ms | 2.28 mW | 488.00 pJ/it |
| 144 | reshape/infer_dim_minus_one | arch-a | PASS | PASS | 0.054 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 0.00 ms | 78.30 mW | 12684.00 pJ | 0.048 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 6250000.00 samples/s | 0.00 ms | 2.30 mW | 308.00 pJ/it |
| 145 | reshape/same_rank | arch-a | PASS | PASS | 0.056 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 0.00 ms | 78.30 mW | 12684.00 pJ | 0.048 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 6250000.00 samples/s | 0.00 ms | 2.30 mW | 308.00 pJ/it |
| 146 | reshape/zero_copies_input_dim | arch-a | PASS | PASS | 0.056 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 0.00 ms | 78.30 mW | 12684.00 pJ | 0.056 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 6250000.00 samples/s | 0.00 ms | 2.30 mW | 308.00 pJ/it |
| 147 | resize/height_only | arch-a | PASS | FAIL | 0.054 s | 0.00 MiB | 0.00 MiB | 4 | 0 | 0.00 ms | 93.55 mW | 64833.00 pJ | 0.055 s | 0.00 MiB | 0.00 MiB | 4 | 0 | 2430000.00 samples/s | 0.00 ms | 5.46 mW | 2298.25 pJ/it |
| 148 | resize/nearest_2x | arch-a | PASS | FAIL | 0.055 s | 0.00 MiB | 0.00 MiB | 4 | 0 | 0.00 ms | 93.57 mW | 109761.00 pJ | 0.051 s | 0.00 MiB | 0.00 MiB | 4 | 0 | 1760000.00 samples/s | 0.00 ms | 5.33 mW | 3085.12 pJ/it |
| 149 | resize/nearest_downsample | arch-a | PASS | FAIL | 0.054 s | 0.00 MiB | 0.00 MiB | 2 | 0 | 0.00 ms | 79.45 mW | 33925.00 pJ | 0.052 s | 0.00 MiB | 0.00 MiB | 2 | 0 | 2420000.00 samples/s | 0.00 ms | 3.22 mW | 1262.50 pJ/it |
| 150 | resize/non_uniform_scales | arch-a | PASS | FAIL | 0.054 s | 0.00 MiB | 0.00 MiB | 6 | 0 | 0.00 ms | 93.58 mW | 164037.00 pJ | 0.055 s | 0.00 MiB | 0.00 MiB | 6 | 0 | 1750000.00 samples/s | 0.00 ms | 7.49 mW | 4551.90 pJ/it |
| 151 | resize/width_only | arch-a | PASS | FAIL | 0.051 s | 0.00 MiB | 0.00 MiB | 2 | 0 | 0.00 ms | 79.50 mW | 53029.00 pJ | 0.052 s | 0.00 MiB | 0.00 MiB | 2 | 0 | 1750000.00 samples/s | 0.00 ms | 3.16 mW | 1735.50 pJ/it |
| 152 | resize/with_sizes | arch-a | PASS | FAIL | 0.054 s | 0.00 MiB | 0.00 MiB | 3 | 0 | 0.00 ms | 92.54 mW | 73756.00 pJ | 0.056 s | 0.00 MiB | 0.00 MiB | 3 | 0 | 1930000.00 samples/s | 0.00 ms | 4.27 mW | 2196.00 pJ/it |
| 153 | sigmoid/4d | arch-a | PASS | PASS | 0.050 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 0.00 ms | 78.18 mW | 40734.00 pJ | 0.055 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 1930000.00 samples/s | 0.00 ms | 2.18 mW | 1014.00 pJ/it |
| 154 | sigmoid/after_gemm | arch-a | PASS | FAIL | 0.056 s | 0.01 MiB | 0.01 MiB | 5 | 4 | 0.01 ms | 105.16 mW | 790056.96 pJ | 0.058 s | 0.01 MiB | 0.01 MiB | 6 | 4 | 291000.00 samples/s | 0.00 ms | 47.08 mW | 187063.49 pJ/it |
| 155 | sigmoid/basic | arch-a | PASS | PASS | 0.053 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 0.00 ms | 78.22 mW | 17286.00 pJ | 0.049 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 4570000.00 samples/s | 0.00 ms | 2.22 mW | 437.33 pJ/it |
| 156 | slice/2d_basic | arch-a | PASS | PASS | 0.051 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 0.00 ms | 78.30 mW | 18948.00 pJ | 0.048 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 4170000.00 samples/s | 0.00 ms | 2.30 mW | 491.67 pJ/it |
| 157 | slice/after_conv | arch-a | PASS | FAIL | 0.062 s | 0.00 MiB | 0.01 MiB | 7 | 6 | 0.01 ms | 118.19 mW | 1335082.88 pJ | 0.069 s | 0.00 MiB | 0.01 MiB | 7 | 6 | 130000.00 samples/s | 0.01 ms | 58.48 mW | 484364.44 pJ/it |
| 158 | slice/default_axes | arch-a | PASS | PASS | 0.051 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 0.00 ms | 78.30 mW | 18948.00 pJ | 0.052 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 4170000.00 samples/s | 0.00 ms | 2.30 mW | 491.67 pJ/it |
| 159 | slice/large_channel_1024 | arch-a | PASS | PASS | 0.051 s | 0.01 MiB | 0.00 MiB | 1 | 0 | 0.00 ms | 78.14 mW | 221304.00 pJ | 0.050 s | 0.01 MiB | 0.00 MiB | 1 | 0 | 353000.00 samples/s | 0.00 ms | 2.14 mW | 5058.00 pJ/it |
| 160 | slice/nchw_spatial_crop | arch-a | PASS | PASS | 0.053 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 0.00 ms | 78.24 mW | 101868.00 pJ | 0.047 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 769000.00 samples/s | 0.00 ms | 2.24 mW | 2851.67 pJ/it |
| 161 | slice/negative_axis | arch-a | PASS | PASS | 0.050 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 0.00 ms | 78.30 mW | 44004.00 pJ | 0.049 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 1790000.00 samples/s | 0.00 ms | 2.30 mW | 1227.67 pJ/it |
| 162 | slice/negative_indices | arch-a | PASS | PASS | 0.048 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 0.00 ms | 78.30 mW | 25212.00 pJ | 0.051 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 3120000.00 samples/s | 0.00 ms | 2.30 mW | 675.67 pJ/it |
| 163 | slice/step2 | arch-a | PASS | PASS | 0.053 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 0.00 ms | 78.29 mW | 159876.00 pJ | 0.052 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 490000.00 samples/s | 0.00 ms | 2.29 mW | 4619.67 pJ/it |
| 164 | softmax/3d_last_axis | arch-a | PASS | PASS | 0.052 s | 0.00 MiB | 0.00 MiB | 1 | 0 | UNSUPPORTED | UNSUPPORTED | UNSUPPORTED | 0.053 s | 0.00 MiB | 0.00 MiB | 1 | 0 | UNSUPPORTED | UNSUPPORTED | UNSUPPORTED | UNSUPPORTED |
| 165 | softmax/basic | arch-a | PASS | PASS | 0.050 s | 0.00 MiB | 0.00 MiB | 1 | 0 | UNSUPPORTED | UNSUPPORTED | UNSUPPORTED | 0.053 s | 0.00 MiB | 0.00 MiB | 1 | 0 | UNSUPPORTED | UNSUPPORTED | UNSUPPORTED | UNSUPPORTED |
| 166 | softmax/channel_axis | arch-a | PASS | FAIL | 0.051 s | 0.00 MiB | 0.00 MiB | 1 | 0 | UNSUPPORTED | UNSUPPORTED | UNSUPPORTED | 0.052 s | 0.00 MiB | 0.00 MiB | 3 | 0 | UNSUPPORTED | UNSUPPORTED | UNSUPPORTED | UNSUPPORTED |
| 167 | softmax/large_dimension_1024 | arch-a | PASS | PASS | 0.049 s | 0.01 MiB | 0.01 MiB | 1 | 0 | UNSUPPORTED | UNSUPPORTED | UNSUPPORTED | 0.052 s | 0.01 MiB | 0.01 MiB | 1 | 0 | UNSUPPORTED | UNSUPPORTED | UNSUPPORTED | UNSUPPORTED |
| 168 | softmax/negative_axis | arch-a | PASS | PASS | 0.050 s | 0.00 MiB | 0.00 MiB | 1 | 0 | UNSUPPORTED | UNSUPPORTED | UNSUPPORTED | 0.049 s | 0.00 MiB | 0.00 MiB | 1 | 0 | UNSUPPORTED | UNSUPPORTED | UNSUPPORTED | UNSUPPORTED |
| 169 | split/basic | arch-a | PASS | PASS | 0.048 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 0.00 ms | 78.30 mW | 31554.00 pJ | 0.052 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 2490000.00 samples/s | 0.00 ms | 2.30 mW | 861.67 pJ/it |
| 170 | split/equal_three_way | arch-a | PASS | PASS | 0.049 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 0.00 ms | 78.30 mW | 44160.00 pJ | 0.052 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 1780000.00 samples/s | 0.00 ms | 2.30 mW | 1231.67 pJ/it |
| 171 | split/negative_axis | arch-a | PASS | PASS | 0.051 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 0.00 ms | 78.29 mW | 84786.00 pJ | 0.050 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 925000.00 samples/s | 0.00 ms | 2.29 mW | 2413.67 pJ/it |
| 172 | split/uneven_channel_axis_4d | arch-a | PASS | PASS | 0.051 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 0.00 ms | 78.30 mW | 18948.00 pJ | 0.049 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 4170000.00 samples/s | 0.00 ms | 2.30 mW | 491.67 pJ/it |
| 173 | sub/after_gemm | arch-a | PASS | FAIL | 0.058 s | 0.01 MiB | 0.01 MiB | 5 | 4 | 0.01 ms | 104.70 mW | 815012.96 pJ | 0.057 s | 0.01 MiB | 0.01 MiB | 6 | 4 | 277000.00 samples/s | 0.00 ms | 45.81 mW | 190085.16 pJ/it |
| 174 | sub/basic | arch-a | PASS | PASS | 0.049 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 0.00 ms | 78.22 mW | 25266.00 pJ | 0.048 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 3120000.00 samples/s | 0.00 ms | 2.23 mW | 658.67 pJ/it |
| 175 | sub/broadcast_row | arch-a | PASS | PASS | 0.049 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 0.00 ms | 78.22 mW | 25266.00 pJ | 0.051 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 3120000.00 samples/s | 0.00 ms | 2.23 mW | 658.67 pJ/it |
| 176 | sub/channel_broadcast_1024 | arch-a | PASS | PASS | 0.058 s | 0.02 MiB | 0.01 MiB | 1 | 0 | 0.01 ms | 78.12 mW | 540030.00 pJ | 0.053 s | 0.02 MiB | 0.01 MiB | 1 | 0 | 145000.00 samples/s | 0.01 ms | 2.11 mW | 13388.67 pJ/it |
| 177 | sub/constant_lhs_broadcast | arch-a | PASS | PASS | 0.049 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 0.00 ms | 78.22 mW | 25188.00 pJ | 0.051 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 3120000.00 samples/s | 0.00 ms | 2.23 mW | 656.67 pJ/it |
| 178 | sub/leading_dimension_broadcast | arch-a | PASS | PASS | 0.050 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 0.00 ms | 78.22 mW | 25266.00 pJ | 0.050 s | 0.00 MiB | 0.00 MiB | 1 | 0 | 3120000.00 samples/s | 0.00 ms | 2.23 mW | 658.67 pJ/it |