From 30eba559926c33f261e8bc0fd78b0b10a5c67620 Mon Sep 17 00:00:00 2001
From: RandySheriffH <48490400+RandySheriffH@users.noreply.github.com>
Date: Mon, 29 Nov 2021 21:46:42 -0800
Subject: [PATCH] Explain usage of --enable_cuda_profiling (#9882)
* explain usage of --enable_cuda_profiling
* remove cupti dependency
---
docs/execution-providers/CUDA-ExecutionProvider.md | 6 +++---
docs/performance/tune-performance.md | 2 +-
2 files changed, 4 insertions(+), 4 deletions(-)
diff --git a/docs/execution-providers/CUDA-ExecutionProvider.md b/docs/execution-providers/CUDA-ExecutionProvider.md
index 17e3c278fd..494387ac28 100644
--- a/docs/execution-providers/CUDA-ExecutionProvider.md
+++ b/docs/execution-providers/CUDA-ExecutionProvider.md
@@ -27,9 +27,9 @@ Please reference table below for official GPU packages dependencies for the ONNX
|ONNX Runtime|CUDA|cuDNN|Notes|
|---|---|---|---|
-|1.10|11.4|8.2.4 (Linux)
8.2.2.26 (Windows)|libcudart 11.4.43
libcufft 10.5.2.100
libcurand 10.2.5.120
libcublasLt 11.6.1.51
libcublas 11.6.1.51
libcudnn 8.2.4
libcupti.so 2021.2.2|
-|1.9|11.4|8.2.4 (Linux)
8.2.2.26 (Windows)|libcudart 11.4.43
libcufft 10.5.2.100
libcurand 10.2.5.120
libcublasLt 11.6.1.51
libcublas 11.6.1.51
libcudnn 8.2.4
libcupti.so 2021.2.2|
-|1.8|11.0.3|8.0.4 (Linux)
8.0.2.39 (Windows)|libcudart 11.0.221
libcufft 10.2.1.245
libcurand 10.2.1.245
libcublasLt 11.2.0.252
libcublas 11.2.0.252
libcudnn 8.0.4
libcupti.so 2020.1.1|
+|1.10|11.4|8.2.4 (Linux)
8.2.2.26 (Windows)|libcudart 11.4.43
libcufft 10.5.2.100
libcurand 10.2.5.120
libcublasLt 11.6.1.51
libcublas 11.6.1.51
libcudnn 8.2.4|
+|1.9|11.4|8.2.4 (Linux)
8.2.2.26 (Windows)|libcudart 11.4.43
libcufft 10.5.2.100
libcurand 10.2.5.120
libcublasLt 11.6.1.51
libcublas 11.6.1.51
libcudnn 8.2.4|
+|1.8|11.0.3|8.0.4 (Linux)
8.0.2.39 (Windows)|libcudart 11.0.221
libcufft 10.2.1.245
libcurand 10.2.1.245
libcublasLt 11.2.0.252
libcublas 11.2.0.252
libcudnn 8.0.4|
|1.7|11.0.3|8.0.4 (Linux)
8.0.2.39 (Windows)|libcudart 11.0.221
libcufft 10.2.1.245
libcurand 10.2.1.245
libcublasLt 11.2.0.252
libcublas 11.2.0.252
libcudnn 8.0.4|
|1.5-1.6|10.2|8.0.3|CUDA 11 can be built from source|
|1.2-1.4|10.1|7.6.5|Requires cublas10-10.2.1.243; cublas 10.1.x will not work|
diff --git a/docs/performance/tune-performance.md b/docs/performance/tune-performance.md
index 4fbbbe4875..507e7fc77d 100644
--- a/docs/performance/tune-performance.md
+++ b/docs/performance/tune-performance.md
@@ -51,7 +51,7 @@ In both cases, you will get a JSON file which contains the detailed performance
* Type chrome://tracing in the address bar
* Load the generated JSON file
-For CUDA EP, performance numbers from device will be attached to those from host. For example:
+To profile CUDA kernels, please add cupti library to PATH and use onnxruntime binary built from source with `--enable_cuda_profiling`, performance numbers from device will then be attached to those from host. For example:
```
{"cat":"Node", "name":"Add_1234", "dur":17, ...}
{"cat":"Kernel", "name":"ort_add_cuda_kernel", dur:33, ...}