Update tune-performance.md with tooling info for opening .json perf traces (#14906)

### Description
-WPA OSS plugins
-Pertetto UI which is recommended by Google over deprecated
chrome://tracing experience


### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- I tried both chrome://tracing and Perfetto to open the .json and it's
not a great expreince. If on Windows, WPA is a MUCH better experience
and easier to work with the data/report. Also Google recommends Perfetto
vs chrome://tracing so updated that as well
This commit is contained in:
ivberg 2023-04-06 14:59:32 -07:00 committed by GitHub
parent b7f6ce3239
commit c88ced49d3
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23

View file

@ -35,11 +35,14 @@ sess_options.enable_profiling = True
If you are using the onnxruntime_perf_test.exe tool, you can add `-p [profile_file]` to enable performance profiling.
In both cases, you will get a JSON file which contains the detailed performance data (threading, latency of each operator, etc). This file is a standard performance tracing file, and to view it in a user-friendly way, you can open it by using chrome://tracing:
In both cases, you will get a JSON file which contains the detailed performance data (threading, latency of each operator, etc). This file is a standard performance tracing file, and to view it in a user-friendly way, you can open it by using multiple tools.
* Open Chrome browser
* Type chrome://tracing in the address bar
* Load the generated JSON file
* (Windows) Use the WPA GUI to open the trace using the Perfetto OSS plugin - [Microsoft-Performance-Tools-Linux-Android](https://github.com/microsoft/Microsoft-Performance-Tools-Linux-Android)
* [Perfetto UI](https://www.ui.perfetto.dev/) - Successor to Chrome Tracing UI
* chrome://tracing:
* Open a Chromium based browser such as Edge or Chrome
* Type chrome://tracing in the address bar
* Load the generated JSON file
To profile CUDA kernels, please add the cupti library to your PATH and use the onnxruntime binary built from source with `--enable_cuda_profiling`.
To profile ROCm kernels, please add the roctracer library to your PATH and use the onnxruntime binary built from source with `--enable_rocm_profiling`.