ONNX Runtime添加一個新的execution provider
execution provider從本質上來講就是一個針對不同硬件平臺的executor,ONNX Runtime目前提供了以下
-
MLAS (Microsoft Linear Algebra Subprograms)
-
NVIDIA CUDA
-
Intel MKL-ML
-
ACL (in preview, for ARM Compute Library)
10種特定的execution provider,涵蓋了ARM,Intel CPU,Nvidia的GPU,不同的操作系統,但是這對於目前紛繁的AI硬件市場遠遠不夠,假如我們自己想添加一個自己定製平臺的execution provider,就需要安裝如下教程添加自己的execution provider。
- 在 onnxruntime/core/providers下創建一個新的文件夾,取個名字如your_provider_name。
- 在 include/onnxruntime/core/providers下創建一個新的文件夾, 名字應該和第一步一樣爲your_provider_name.
- 創建一個新的類,必須繼承於IExecutionProvider。實現的源碼需要放在’onnxruntime/core/providers/[your_provider_name]'目錄下。
- 在 include/onnxruntime/core/providers/[your_provider_name]目錄下創建一個頭文件。這個有文件應該提供創建OrtProviderFactoryInterface的函數接口。你可以使用 'include/onnxruntime/core/providers/cpu/cpu_provider_factory.h’作爲模板,需要注意的是創建 MemoryInfo函數不是必須的。
- 在 'onnxruntime/core/providers/[your_provider_name]'目錄下面創建一個symbols.txt文件,該文件應該包含本execution provider導出的所有的函數名。通常只需一個函數即可創建execution provider工廠。
- 在onnxruntime_providers.cmake文件中增加你的execution provider編譯代碼,並編譯成一個靜態庫。
- 在 cmake/onnxruntime.cmake增加一行target_link_libraries函數,使得onnxruntime能鏈接上你的execution provider庫。
- Create a folder under onnxruntime/core/providers
- Create a folder under include/onnxruntime/core/providers, it should has the same name as the first step.
- Create a new class, which must inherit from IExecutionProvider. The source code should be put in ‘onnxruntime/core/providers/[your_provider_name]’
- Create a new header file under include/onnxruntime/core/providers/[your_provider_name]. The file should provide one function for creating an OrtProviderFactoryInterface. You may use ‘include/onnxruntime/core/providers/cpu/cpu_provider_factory.h’ as a template. You don’t need to provide a function for creating MemoryInfo.
- Put a symbols.txt under ‘onnxruntime/core/providers/[your_provider_name]’. The file should contain all the function names that would be exported from you provider. Usually, just a single function for creating provider factory is enough.
- Add your provider in onnxruntime_providers.cmake. Build it as a static lib.
- Add one line in cmake/onnxruntime.cmake, to the ‘target_link_libraries’ function call. Put your provider there.
Examples:
Using the execution provider
- Create a factory for that provider, by using the c function you exported in ‘symbols.txt’
- Put the provider factory into session options
- Create session from that session option
e.g.
OrtEnv* env;
OrtInitialize(ORT_LOGGING_LEVEL_WARNING, "test", &env)
OrtSessionOptions* session_option = OrtCreateSessionOptions();
OrtProviderFactoryInterface** factory;
OrtCreateCUDAExecutionProviderFactory(0, &factory);
OrtSessionOptionsAppendExecutionProvider(session_option, factory);
OrtReleaseObject(factory);
OrtCreateSession(env, model_path, session_option, &session);