GPU Kernel Information Aggregated by Layer
layer_index | layer_name | layer_type | layer_duration (us) | layer_gpu_duration (us) | layer_cpu_duration (us) | layer_flops | layer_dram_read_bytes | layer_dram_write_bytes | layer_achieved_occupancy (%) | layer_arithmetic_intensity (flops/byte) | layer_arithmetic_throughput (GFlops) | layer_memory_bound |
---|
layer_index | layer_name | layer_type | layer_duration (us) | layer_gpu_duration (us) | layer_cpu_duration (us) | layer_flops | layer_dram_read_bytes | layer_dram_write_bytes | layer_achieved_occupancy (%) | layer_arithmetic_intensity (flops/byte) | layer_arithmetic_throughput (GFlops) | layer_memory_bound |
---|---|---|---|---|---|---|---|---|---|---|---|---|
1 | mobilenet2_batchnorm0_fwd | BatchNorm | 456.33 | 10.00 | 446.33 | 1212416 | 0.00 | 0.00 | 0.00 | 0.00 | 121.24 | true |
2 | mobilenet2_relu0_fwd | Activation | 34.00 | 4.00 | 30.00 | 401408 | 0.00 | 0.00 | 0.00 | 0.00 | 100.35 | true |
3 | mobilenet2_conv1_fwd | Convolution | 6140.67 | 216.20 | 5924.47 | 166985728 | 0.00 | 0.00 | 0.00 | 0.00 | 772.37 | true |
4 | mobilenet2_batchnorm1_fwd | BatchNorm | 448.67 | 10.00 | 438.67 | 1212416 | 0.00 | 0.00 | 0.00 | 0.00 | 121.24 | true |
5 | mobilenet2_relu1_fwd | Activation | 33.33 | 4.00 | 29.33 | 401408 | 0.00 | 0.00 | 0.00 | 0.00 | 100.35 | true |
6 | mobilenet2_conv2_fwd | Convolution | 5186.33 | 13.67 | 5172.67 | 13647872 | 0.00 | 0.00 | 0.00 | 0.00 | 998.60 | true |
7 | mobilenet2_batchnorm2_fwd | BatchNorm | 172.00 | 10.00 | 162.00 | 2424832 | 0.00 | 0.00 | 0.00 | 0.00 | 242.48 | true |
8 | mobilenet2_relu2_fwd | Activation | 46.67 | 6.00 | 40.67 | 802816 | 0.00 | 0.00 | 0.00 | 0.00 | 133.80 | true |
9 | mobilenet2_conv3_fwd | Convolution | 2895.33 | 379.32 | 2516.01 | 85196800 | 0.00 | 0.00 | 0.00 | 0.00 | 224.60 | true |
10 | mobilenet2_batchnorm3_fwd | BatchNorm | 69.67 | 5.00 | 64.67 | 618496 | 0.00 | 0.00 | 0.00 | 0.00 | 123.70 | true |
11 | mobilenet2_relu3_fwd | Activation | 19.00 | 4.00 | 15.00 | 200704 | 0.00 | 0.00 | 0.00 | 0.00 | 50.18 | true |
12 | mobilenet2_conv4_fwd | Convolution | 2529.67 | 20.33 | 2509.33 | 13516800 | 0.00 | 0.00 | 0.00 | 0.00 | 664.77 | true |
13 | mobilenet2_batchnorm4_fwd | BatchNorm | 64.67 | 5.00 | 59.67 | 1236992 | 0.00 | 0.00 | 0.00 | 0.00 | 247.40 | true |
14 | mobilenet2_relu4_fwd | Activation | 24.00 | 4.00 | 20.00 | 401408 | 0.00 | 0.00 | 0.00 | 0.00 | 100.35 | true |
15 | mobilenet2_conv5_fwd | Convolution | 4482.67 | 896.00 | 3586.67 | 558792704 | 0.00 | 0.00 | 0.00 | 0.00 | 623.65 | true |
16 | mobilenet2_batchnorm5_fwd | BatchNorm | 166.67 | 5.17 | 161.50 | 1236992 | 0.00 | 0.00 | 0.00 | 0.00 | 239.40 | true |
17 | mobilenet2_relu5_fwd | Activation | 24.00 | 4.00 | 20.00 | 401408 | 0.00 | 0.00 | 0.00 | 0.00 | 100.35 | true |
18 | mobilenet2_conv6_fwd | Convolution | 2952.33 | 27.14 | 2925.19 | 26624000 | 0.00 | 0.00 | 0.00 | 0.00 | 980.88 | true |
19 | mobilenet2_batchnorm6_fwd | BatchNorm | 129.33 | 5.00 | 124.33 | 1236992 | 0.00 | 0.00 | 0.00 | 0.00 | 247.40 | true |
20 | mobilenet2_relu6_fwd | Activation | 23.00 | 4.00 | 19.00 | 401408 | 0.00 | 0.00 | 0.00 | 0.00 | 100.35 | true |
21 | mobilenet2_conv7_fwd | Convolution | 1654.33 | 756.89 | 897.45 | 47710208 | 0.00 | 0.00 | 0.00 | 0.00 | 63.03 | true |
22 | mobilenet2_batchnorm7_fwd | BatchNorm | 23.00 | 4.00 | 19.00 | 317440 | 0.00 | 0.00 | 0.00 | 0.00 | 79.36 | true |
23 | mobilenet2_relu7_fwd | Activation | 25.67 | 4.00 | 21.67 | 100352 | 0.00 | 0.00 | 0.00 | 0.00 | 25.09 | true |
24 | mobilenet2_conv8_fwd | Convolution | 1597.00 | 31.00 | 1566.00 | 14909440 | 0.00 | 0.00 | 0.00 | 0.00 | 480.95 | true |
25 | mobilenet2_batchnorm8_fwd | BatchNorm | 38.00 | 4.00 | 34.00 | 634880 | 0.00 | 0.00 | 0.00 | 0.00 | 158.72 | true |
26 | mobilenet2_relu8_fwd | Activation | 23.33 | 4.00 | 19.33 | 200704 | 0.00 | 0.00 | 0.00 | 0.00 | 50.18 | true |
27 | mobilenet2_conv9_fwd | Convolution | 2906.00 | 1792.00 | 1114.00 | 320667648 | 0.00 | 0.00 | 0.00 | 0.00 | 178.94 | true |
28 | mobilenet2_batchnorm9_fwd | BatchNorm | 114.67 | 4.00 | 110.67 | 634880 | 0.00 | 0.00 | 0.00 | 0.00 | 158.72 | true |
29 | mobilenet2_relu9_fwd | Activation | 15.67 | 4.00 | 11.67 | 200704 | 0.00 | 0.00 | 0.00 | 0.00 | 50.18 | true |
30 | mobilenet2_conv10_fwd | Convolution | 2836.00 | 47.00 | 2789.00 | 29589504 | 0.00 | 0.00 | 0.00 | 0.00 | 629.56 | true |
31 | mobilenet2_batchnorm10_fwd | BatchNorm | 107.00 | 4.00 | 103.00 | 634880 | 0.00 | 0.00 | 0.00 | 0.00 | 158.72 | true |
32 | mobilenet2_relu10_fwd | Activation | 15.67 | 4.00 | 11.67 | 200704 | 0.00 | 0.00 | 0.00 | 0.00 | 50.18 | true |
33 | mobilenet2_conv11_fwd | Convolution | 899.67 | 1466.56 | -566.89 | 29385216 | 0.00 | 0.00 | 0.00 | 0.00 | 20.04 | true |
34 | mobilenet2_batchnorm11_fwd | BatchNorm | 20.33 | 4.00 | 16.33 | 158720 | 0.00 | 0.00 | 0.00 | 0.00 | 39.68 | true |
35 | mobilenet2_relu11_fwd | Activation | 13.00 | 3.00 | 10.00 | 50176 | 0.00 | 0.00 | 0.00 | 0.00 | 16.73 | true |
36 | mobilenet2_conv12_fwd | Convolution | 1341.67 | 48.00 | 1293.67 | 16908288 | 0.00 | 0.00 | 0.00 | 0.00 | 352.26 | true |
37 | mobilenet2_batchnorm12_fwd | BatchNorm | 32.33 | 4.00 | 28.33 | 317440 | 0.00 | 0.00 | 0.00 | 0.00 | 79.36 | true |
38 | mobilenet2_relu12_fwd | Activation | 21.00 | 3.25 | 17.75 | 100352 | 0.00 | 0.00 | 0.00 | 0.00 | 30.88 | true |
39 | mobilenet2_conv13_fwd | Convolution | 1787.67 | 3584.00 | -1796.33 | 163184640 | 0.00 | 0.00 | 0.00 | 0.00 | 45.53 | true |
40 | mobilenet2_batchnorm13_fwd | BatchNorm | 48.00 | 4.00 | 44.00 | 317440 | 0.00 | 0.00 | 0.00 | 0.00 | 79.36 | true |
41 | mobilenet2_relu13_fwd | Activation | 19.00 | 3.60 | 15.40 | 100352 | 0.00 | 0.00 | 0.00 | 0.00 | 27.88 | true |
42 | mobilenet2_conv14_fwd | Convolution | 2574.67 | 81.75 | 2492.92 | 33685504 | 0.00 | 0.00 | 0.00 | 0.00 | 412.06 | true |
43 | mobilenet2_batchnorm14_fwd | BatchNorm | 104.33 | 4.00 | 100.33 | 317440 | 0.00 | 0.00 | 0.00 | 0.00 | 79.36 | true |
44 | mobilenet2_relu14_fwd | Activation | 16.67 | 3.50 | 13.17 | 100352 | 0.00 | 0.00 | 0.00 | 0.00 | 28.67 | true |
45 | mobilenet2_conv15_fwd | Convolution | 1775.33 | 3584.00 | -1808.67 | 163184640 | 0.00 | 0.00 | 0.00 | 0.00 | 45.53 | true |
46 | mobilenet2_batchnorm15_fwd | BatchNorm | 50.67 | 4.00 | 46.67 | 317440 | 0.00 | 0.00 | 0.00 | 0.00 | 79.36 | true |
47 | mobilenet2_relu15_fwd | Activation | 19.33 | 4.00 | 15.33 | 100352 | 0.00 | 0.00 | 0.00 | 0.00 | 25.09 | true |
48 | mobilenet2_conv16_fwd | Convolution | 2574.33 | 81.75 | 2492.58 | 33685504 | 0.00 | 0.00 | 0.00 | 0.00 | 412.06 | true |
49 | mobilenet2_batchnorm16_fwd | BatchNorm | 89.00 | 4.00 | 85.00 | 317440 | 0.00 | 0.00 | 0.00 | 0.00 | 79.36 | true |
50 | mobilenet2_relu16_fwd | Activation | 21.33 | 3.75 | 17.58 | 100352 | 0.00 | 0.00 | 0.00 | 0.00 | 26.76 | true |
51 | mobilenet2_conv17_fwd | Convolution | 1774.00 | 3584.00 | -1810.00 | 163184640 | 0.00 | 0.00 | 0.00 | 0.00 | 45.53 | true |
52 | mobilenet2_batchnorm17_fwd | BatchNorm | 50.67 | 4.00 | 46.67 | 317440 | 0.00 | 0.00 | 0.00 | 0.00 | 79.36 | true |
53 | mobilenet2_relu17_fwd | Activation | 16.00 | 3.80 | 12.20 | 100352 | 0.00 | 0.00 | 0.00 | 0.00 | 26.41 | true |
54 | mobilenet2_conv18_fwd | Convolution | 2574.00 | 81.83 | 2492.17 | 33685504 | 0.00 | 0.00 | 0.00 | 0.00 | 411.64 | true |
55 | mobilenet2_batchnorm18_fwd | BatchNorm | 114.00 | 4.00 | 110.00 | 317440 | 0.00 | 0.00 | 0.00 | 0.00 | 79.36 | true |
56 | mobilenet2_relu18_fwd | Activation | 14.67 | 3.33 | 11.33 | 100352 | 0.00 | 0.00 | 0.00 | 0.00 | 30.11 | true |
57 | mobilenet2_conv19_fwd | Convolution | 1776.33 | 3584.00 | -1807.67 | 163184640 | 0.00 | 0.00 | 0.00 | 0.00 | 45.53 | true |
58 | mobilenet2_batchnorm19_fwd | BatchNorm | 55.67 | 4.00 | 51.67 | 317440 | 0.00 | 0.00 | 0.00 | 0.00 | 79.36 | true |
59 | mobilenet2_relu19_fwd | Activation | 17.67 | 4.00 | 13.67 | 100352 | 0.00 | 0.00 | 0.00 | 0.00 | 25.09 | true |
60 | mobilenet2_conv20_fwd | Convolution | 2569.33 | 82.00 | 2487.33 | 33685504 | 0.00 | 0.00 | 0.00 | 0.00 | 410.80 | true |
61 | mobilenet2_batchnorm20_fwd | BatchNorm | 111.33 | 4.00 | 107.33 | 317440 | 0.00 | 0.00 | 0.00 | 0.00 | 79.36 | true |
62 | mobilenet2_relu20_fwd | Activation | 13.67 | 3.80 | 9.87 | 100352 | 0.00 | 0.00 | 0.00 | 0.00 | 26.41 | true |
63 | mobilenet2_conv21_fwd | Convolution | 1778.33 | 3584.00 | -1805.67 | 163184640 | 0.00 | 0.00 | 0.00 | 0.00 | 45.53 | true |
64 | mobilenet2_batchnorm21_fwd | BatchNorm | 48.67 | 4.00 | 44.67 | 317440 | 0.00 | 0.00 | 0.00 | 0.00 | 79.36 | true |
65 | mobilenet2_relu21_fwd | Activation | 16.33 | 3.40 | 12.93 | 100352 | 0.00 | 0.00 | 0.00 | 0.00 | 29.52 | true |
66 | mobilenet2_conv22_fwd | Convolution | 2568.00 | 82.00 | 2486.00 | 33685504 | 0.00 | 0.00 | 0.00 | 0.00 | 410.80 | true |
67 | mobilenet2_batchnorm22_fwd | BatchNorm | 107.33 | 4.00 | 103.33 | 317440 | 0.00 | 0.00 | 0.00 | 0.00 | 79.36 | true |
68 | mobilenet2_relu22_fwd | Activation | 14.00 | 3.00 | 11.00 | 100352 | 0.00 | 0.00 | 0.00 | 0.00 | 33.45 | true |
69 | mobilenet2_conv23_fwd | Convolution | 588.00 | 2849.83 | -2261.83 | 16789760 | 0.00 | 0.00 | 0.00 | 0.00 | 5.89 | true |
70 | mobilenet2_batchnorm23_fwd | BatchNorm | 20.00 | 3.20 | 16.80 | 87808 | 0.00 | 0.00 | 0.00 | 0.00 | 27.44 | true |
71 | mobilenet2_relu23_fwd | Activation | 12.33 | 3.00 | 9.33 | 25088 | 0.00 | 0.00 | 0.00 | 0.00 | 8.36 | true |
72 | mobilenet2_conv24_fwd | Convolution | 1509.67 | 132.00 | 1377.67 | 16802304 | 0.00 | 0.00 | 0.00 | 0.00 | 127.29 | true |
73 | mobilenet2_batchnorm24_fwd | BatchNorm | 27.67 | 4.00 | 23.67 | 175616 | 0.00 | 0.00 | 0.00 | 0.00 | 43.90 | true |
74 | mobilenet2_relu24_fwd | Activation | 25.33 | 3.00 | 22.33 | 50176 | 0.00 | 0.00 | 0.00 | 0.00 | 16.73 | true |
75 | mobilenet2_conv25_fwd | Convolution | 1150.00 | 7168.00 | -6018.00 | 166985728 | 0.00 | 0.00 | 0.00 | 0.00 | 23.30 | true |
76 | mobilenet2_batchnorm25_fwd | BatchNorm | 25.67 | 4.00 | 21.67 | 175616 | 0.00 | 0.00 | 0.00 | 0.00 | 43.90 | true |
77 | mobilenet2_relu25_fwd | Activation | 23.67 | 3.00 | 20.67 | 50176 | 0.00 | 0.00 | 0.00 | 0.00 | 16.73 | true |
78 | mobilenet2_conv26_fwd | Convolution | 2810.33 | 155.50 | 2654.83 | 33579520 | 0.00 | 0.00 | 0.00 | 0.00 | 215.95 | true |
79 | mobilenet2_batchnorm26_fwd | BatchNorm | 97.67 | 4.00 | 93.67 | 175616 | 0.00 | 0.00 | 0.00 | 0.00 | 43.90 | true |
80 | mobilenet2_relu26_fwd | Activation | 22.67 | 3.00 | 19.67 | 50176 | 0.00 | 0.00 | 0.00 | 0.00 | 16.73 | true |
81 | mobilenet2_pool0_fwd | Pooling | 76.67 | 10.75 | 65.92 | 32287 | 0.00 | 0.00 | 0.00 | 0.00 | 3.00 | true |
82 | mobilenet2_flatten0_flatten0 | Flatten | 2.33 | 0.00 | 2.33 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | true |
83 | mobilenet2_dense0_fwd | FullyConnected | 733.67 | 13.00 | 720.67 | 1136000 | 0.00 | 0.00 | 0.00 | 0.00 | 87.38 | true |
Showing 1 to 83 of 83 entries