Skip to content

Instantly share code, notes, and snippets.

@leslie-fang-intel
Created February 17, 2023 02:30
Show Gist options
  • Select an option

  • Save leslie-fang-intel/b7f68bf22c44b43f8811863c2daf81ed to your computer and use it in GitHub Desktop.

Select an option

Save leslie-fang-intel/b7f68bf22c44b43f8811863c2daf81ed to your computer and use it in GitHub Desktop.
----------------------------------------------- ------------ ------------ ------------ ------------ ------------ ------------
Name Self CPU % Self CPU CPU total % CPU total CPU time avg # of Calls
----------------------------------------------- ------------ ------------ ------------ ------------ ------------ ------------
quantized::conv_relu_int8_packed_weight 13.77% 69.356ms 20.19% 101.737ms 3.083ms 33
quantized::conv_int8_packed_weight 13.59% 68.488ms 19.10% 96.245ms 4.812ms 20
graph_1_kernel_cpp_1 9.96% 50.175ms 9.96% 50.175ms 50.175ms 1
graph_1_kernel_cpp_2 9.32% 46.958ms 9.32% 46.958ms 46.958ms 1
graph_1_kernel_cpp_3 6.54% 32.936ms 6.54% 32.936ms 32.936ms 1
graph_1_kernel_cpp_4 6.45% 32.520ms 6.45% 32.520ms 32.520ms 1
aten::select 5.84% 29.401ms 5.86% 29.537ms 1.072us 27560
aten::copy_ 5.78% 29.127ms 5.78% 29.127ms 1.456ms 20
graph_1_kernel_cpp_5 4.78% 24.065ms 4.78% 24.065ms 24.065ms 1
graph_1_kernel_cpp_7 3.31% 16.680ms 3.31% 16.680ms 16.680ms 1
graph_1_kernel_cpp_6 3.30% 16.622ms 3.30% 16.622ms 16.622ms 1
graph_1_kernel_cpp_8 3.25% 16.352ms 3.25% 16.352ms 16.352ms 1
graph_1_kernel_cpp_9 1.62% 8.165ms 1.62% 8.165ms 8.165ms 1
graph_1_kernel_cpp_10 1.60% 8.064ms 1.60% 8.064ms 8.064ms 1
graph_1_kernel_cpp_11 1.58% 7.979ms 1.58% 7.979ms 7.979ms 1
graph_1_kernel_cpp_12 1.58% 7.975ms 1.58% 7.975ms 7.975ms 1
graph_1_kernel_cpp_14 1.57% 7.923ms 1.57% 7.923ms 7.923ms 1
graph_1_kernel_cpp_13 1.57% 7.907ms 1.57% 7.907ms 7.907ms 1
graph_1_kernel_cpp_17 0.95% 4.764ms 0.95% 4.764ms 4.764ms 1
graph_1_kernel_cpp_16 0.79% 3.982ms 0.79% 3.982ms 3.982ms 1
graph_1_kernel_cpp_15 0.70% 3.527ms 0.70% 3.527ms 3.527ms 1
quantized_decomposed::conv_unary_inductor 0.58% 2.918ms 39.92% 201.121ms 3.795ms 53
graph_1_kernel_cpp_0 0.48% 2.415ms 0.48% 2.415ms 2.415ms 1
quantized::linear_int8_packed_weight 0.48% 2.399ms 0.69% 3.493ms 3.493ms 1
aten::item 0.38% 1.913ms 0.40% 2.029ms 0.073us 27776
aten::empty 0.08% 428.000us 0.08% 428.000us 5.784us 74
aten::as_strided 0.05% 231.000us 0.05% 231.000us 0.008us 27581
aten::clone 0.04% 193.000us 5.86% 29.537ms 1.477ms 20
aten::_local_scalar_dense 0.03% 138.000us 0.03% 138.000us 0.005us 27776
aten::empty_like 0.01% 72.000us 0.04% 217.000us 10.850us 20
quantized_decomposed::linear_unary_inductor 0.01% 52.000us 0.70% 3.550ms 3.550ms 1
aten::contiguous 0.01% 50.000us 5.87% 29.587ms 1.479ms 20
aten::empty_strided 0.01% 45.000us 0.01% 45.000us 5.000us 9
graph_1_kernel_cpp_18 0.00% 8.000us 0.00% 8.000us 8.000us 1
----------------------------------------------- ------------ ------------ ------------ ------------ ------------ ------------
Self CPU time total: 503.828ms
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment