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 |
---|---|---|---|---|---|---|---|---|---|---|---|---|
2 | conv2d0 | _FusedConv2D | 9872.00 | 0.00 | 9872.00 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | NaN | true |
3 | maxpool0 | MaxPool | 693.00 | 0.00 | 693.00 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | NaN | true |
4 | localresponsenorm0 | LRN | 606.00 | 0.00 | 606.00 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | NaN | true |
5 | conv2d1 | _FusedConv2D | 502.00 | 0.00 | 502.00 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | NaN | true |
6 | conv2d2 | _FusedConv2D | 9774.00 | 0.00 | 9774.00 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | NaN | true |
7 | localresponsenorm1 | LRN | 3460.00 | 0.00 | 3460.00 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | NaN | true |
8 | maxpool1 | MaxPool | 331.67 | 0.00 | 331.67 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | NaN | true |
9 | mixed3a_5x5_bottleneck | _FusedConv2D | 622.33 | 0.00 | 622.33 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | NaN | true |
10 | mixed3a_pool | MaxPool | 502.67 | 0.00 | 502.67 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | NaN | true |
11 | mixed3a_1x1 | _FusedConv2D | 1239.67 | 0.00 | 1239.67 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | NaN | true |
12 | mixed3a_pool_reduce | _FusedConv2D | 681.00 | 0.00 | 681.00 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | NaN | true |
13 | mixed3a_3x3_bottleneck | _FusedConv2D | 1318.33 | 0.00 | 1318.33 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | NaN | true |
14 | mixed3a_5x5 | _FusedConv2D | 1103.33 | 0.00 | 1103.33 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | NaN | true |
15 | mixed3a_3x3 | _FusedConv2D | 2641.00 | 0.00 | 2641.00 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | NaN | true |
16 | mixed3a | Concat | 137.33 | 0.00 | 137.33 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | NaN | true |
17 | mixed3b_pool | MaxPool | 536.33 | 0.00 | 536.33 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | NaN | true |
18 | mixed3b_5x5_bottleneck | _FusedConv2D | 1358.33 | 0.00 | 1358.33 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | NaN | true |
19 | mixed3b_pool_reduce | _FusedConv2D | 1560.33 | 0.00 | 1560.33 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | NaN | true |
20 | mixed3b_1x1 | _FusedConv2D | 2008.67 | 0.00 | 2008.67 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | NaN | true |
21 | mixed3b_3x3_bottleneck | _FusedConv2D | 2371.33 | 0.00 | 2371.33 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | NaN | true |
22 | mixed3b_5x5 | _FusedConv2D | 4768.33 | 0.00 | 4768.33 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | NaN | true |
23 | mixed3b_3x3 | _FusedConv2D | 6039.00 | 0.00 | 6039.00 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | NaN | true |
24 | mixed3b | Concat | 188.67 | 0.00 | 188.67 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | NaN | true |
25 | maxpool4 | MaxPool | 176.33 | 0.00 | 176.33 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | NaN | true |
26 | mixed4a_pool | MaxPool | 269.33 | 0.00 | 269.33 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | NaN | true |
27 | mixed4a_5x5_bottleneck | _FusedConv2D | 630.00 | 0.00 | 630.00 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | NaN | true |
28 | mixed4a_3x3_bottleneck | _FusedConv2D | 957.67 | 0.00 | 957.67 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | NaN | true |
29 | mixed4a_pool_reduce | _FusedConv2D | 716.00 | 0.00 | 716.00 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | NaN | true |
30 | mixed4a_5x5 | _FusedConv2D | 617.67 | 0.00 | 617.67 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | NaN | true |
31 | mixed4a_1x1 | _FusedConv2D | 1596.67 | 0.00 | 1596.67 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | NaN | true |
32 | mixed4a_3x3 | _FusedConv2D | 1344.33 | 0.00 | 1344.33 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | NaN | true |
33 | mixed4a | Concat | 117.33 | 0.00 | 117.33 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | NaN | true |
34 | head0_pool | AvgPool | 76.67 | 0.00 | 76.67 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | NaN | true |
35 | head0_bottleneck | _FusedConv2D | 120.33 | 0.00 | 120.33 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | NaN | true |
36 | head0_bottleneck/reshape | Reshape | 10.33 | 0.00 | 10.33 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | NaN | true |
37 | nn0_pre_relu/matmul | MatMul | 838.67 | 0.00 | 838.67 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | NaN | true |
38 | nn0_pre_relu | BiasAdd | 11.67 | 0.00 | 11.67 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | NaN | true |
39 | nn0 | Relu | 6.33 | 0.00 | 6.33 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | NaN | true |
40 | softmax0_pre_activation/matmul | MatMul | 415.67 | 0.00 | 415.67 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | NaN | true |
41 | softmax0_pre_activation | BiasAdd | 7.00 | 0.00 | 7.00 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | NaN | true |
42 | softmax0 | Softmax | 39.33 | 0.00 | 39.33 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | NaN | true |
43 | output | Identity | 5.00 | 0.00 | 5.00 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | NaN | true |
Showing 1 to 42 of 42 entries