Created
January 26, 2021 04:59
-
-
Save vkuzo/11a7bed73fe60e340862d37e7975e9cd to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # after | |
| (pytorch2) [vasiliy@devgpu108.ash6 ~/local/pytorch/benchmarks/operator_benchmark] python -m pt.quantization_test | |
| # ---------------------------------------- | |
| # PyTorch/Caffe2 Operator Micro-benchmarks | |
| # ---------------------------------------- | |
| # Tag : short | |
| # Benchmarking PyTorch: FakeQuantize | |
| # Mode: Eager | |
| # Name: FakeQuantize_N1_C3_H512_W512_cpu | |
| # Input: N: 1, C: 3, H: 512, W: 512, device: cpu | |
| Forward Execution Time (us) : 934.408 | |
| # Benchmarking PyTorch: FakeQuantize | |
| # Mode: Eager | |
| # Name: FakeQuantize_N1_C3_H512_W512_cuda | |
| # Input: N: 1, C: 3, H: 512, W: 512, device: cuda | |
| Forward Execution Time (us) : 780.428 | |
| # Benchmarking PyTorch: FakeQuantize | |
| # Mode: Eager | |
| # Name: FakeQuantize_N1_C32_H1024_W1024_cpu | |
| # Input: N: 1, C: 32, H: 1024, W: 1024, device: cpu | |
| Forward Execution Time (us) : 36511.692 | |
| # Benchmarking PyTorch: FakeQuantize | |
| # Mode: Eager | |
| # Name: FakeQuantize_N1_C32_H1024_W1024_cuda | |
| # Input: N: 1, C: 32, H: 1024, W: 1024, device: cuda | |
| Forward Execution Time (us) : 1469.467 | |
| (pytorch2) [vasiliy@devgpu108.ash6 ~/local/pytorch/benchmarks/operator_benchmark] | |
| # before | |
| (pytorch2) [vasiliy@devgpu108.ash6 ~/local/pytorch/benchmarks/operator_benchmark] python -m pt.quantization_test | |
| # ---------------------------------------- | |
| # PyTorch/Caffe2 Operator Micro-benchmarks | |
| # ---------------------------------------- | |
| # Tag : short | |
| # Benchmarking PyTorch: FakeQuantize | |
| # Mode: Eager | |
| # Name: FakeQuantize_N1_C3_H512_W512_cpu | |
| # Input: N: 1, C: 3, H: 512, W: 512, device: cpu | |
| Forward Execution Time (us) : 960.386 | |
| # Benchmarking PyTorch: FakeQuantize | |
| # Mode: Eager | |
| # Name: FakeQuantize_N1_C3_H512_W512_cuda | |
| # Input: N: 1, C: 3, H: 512, W: 512, device: cuda | |
| Forward Execution Time (us) : 727.115 | |
| # Benchmarking PyTorch: FakeQuantize | |
| # Mode: Eager | |
| # Name: FakeQuantize_N1_C32_H1024_W1024_cpu | |
| # Input: N: 1, C: 32, H: 1024, W: 1024, device: cpu | |
| Forward Execution Time (us) : 29881.734 | |
| # Benchmarking PyTorch: FakeQuantize | |
| # Mode: Eager | |
| # Name: FakeQuantize_N1_C32_H1024_W1024_cuda | |
| # Input: N: 1, C: 32, H: 1024, W: 1024, device: cuda | |
| Forward Execution Time (us) : 1526.125 | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment