698e9f71cd
### Description 1. Update /Zi to /Z7 in abseil project while using cache 2. Skip target_precompile_headers while using cache ### Motivation and Context There're about 1/4 uncacheable calls in Windows GPU compilation with cache. ``` Uncacheable calls: 441 / 1641 (26.87%) Could not use precompiled header: 361 / 441 (81.86%) Preprocessing failed: 1 / 441 ( 0.23%) Unsupported compiler option: 79 / 441 (17.91%) ``` https://dev.azure.com/onnxruntime/onnxruntime/_build/results?buildId=961916&view=logs&j=5076e696-f193-5f12-2d8a-703dda41a79b&t=9b927034-e3ef-5e25-c6df-387bc37acd63&l=21 The root cause of `Unsupported compiler option` is that /Zi in Abseil isn't updated to /Z7. The root cause of `Could not use precompiled header` is the `target_precompile_headers` creates cmake_pch.pch every time and it's hash value is changed too. ### Result It could reduce compilation time by another 20%. For example: It took 16m43 in CUDA training compilation on Windows. It takes 13m32 after the change. https://dev.azure.com/onnxruntime/onnxruntime/_build/results?buildId=964002&view=logs&s=959c6b43-5937-53e5-5f36-e53cb0249117 ### N.B. In winml project, it's using own target_precompile**d**_header https://github.com/microsoft/onnxruntime/blob/main/cmake/precompiled_header.cmake. Just let it be. |
||
|---|---|---|
| .config | ||
| .devcontainer | ||
| .gdn | ||
| .github | ||
| .pipelines | ||
| .vscode | ||
| cgmanifests | ||
| cmake | ||
| csharp | ||
| dockerfiles | ||
| docs | ||
| include/onnxruntime/core | ||
| java | ||
| js | ||
| objectivec | ||
| onnxruntime | ||
| orttraining | ||
| package/rpm | ||
| rust | ||
| samples | ||
| tools | ||
| winml | ||
| .clang-format | ||
| .clang-tidy | ||
| .dockerignore | ||
| .gitattributes | ||
| .gitignore | ||
| .gitmodules | ||
| .lintrunner.toml | ||
| build.amd64.1411.bat | ||
| build.bat | ||
| build.sh | ||
| CITATION.cff | ||
| CODEOWNERS | ||
| CONTRIBUTING.md | ||
| lgtm.yml | ||
| LICENSE | ||
| NuGet.config | ||
| ort.wprp | ||
| ORT_icon_for_light_bg.png | ||
| packages.config | ||
| pyproject.toml | ||
| README.md | ||
| requirements-dev.txt | ||
| requirements-doc.txt | ||
| requirements-training.txt | ||
| requirements.txt.in | ||
| SECURITY.md | ||
| setup.py | ||
| ThirdPartyNotices.txt | ||
| VERSION_NUMBER | ||
ONNX Runtime is a cross-platform inference and training machine-learning accelerator.
ONNX Runtime inference can enable faster customer experiences and lower costs, supporting models from deep learning frameworks such as PyTorch and TensorFlow/Keras as well as classical machine learning libraries such as scikit-learn, LightGBM, XGBoost, etc. ONNX Runtime is compatible with different hardware, drivers, and operating systems, and provides optimal performance by leveraging hardware accelerators where applicable alongside graph optimizations and transforms. Learn more →
ONNX Runtime training can accelerate the model training time on multi-node NVIDIA GPUs for transformer models with a one-line addition for existing PyTorch training scripts. Learn more →
Get Started & Resources
-
General Information: onnxruntime.ai
-
Usage documention and tutorials: onnxruntime.ai/docs
-
YouTube video tutorials: youtube.com/@ONNXRuntime
-
Companion sample repositories:
- ONNX Runtime Inferencing: microsoft/onnxruntime-inference-examples
- ONNX Runtime Training: microsoft/onnxruntime-training-examples
Build Pipeline Status
| System | Inference | Training |
|---|---|---|
| Windows | ||
| Linux | ||
| Mac | ||
| Android | ||
| iOS | ||
| Web | ||
| Other |
Data/Telemetry
Windows distributions of this project may collect usage data and send it to Microsoft to help improve our products and services. See the privacy statement for more details.
Contributions and Feedback
We welcome contributions! Please see the contribution guidelines.
For feature requests or bug reports, please file a GitHub Issue.
For general discussion or questions, please use GitHub Discussions.
Code of Conduct
This project has adopted the Microsoft Open Source Code of Conduct. For more information see the Code of Conduct FAQ or contact opencode@microsoft.com with any additional questions or comments.
License
This project is licensed under the MIT License.