-
Notifications
You must be signed in to change notification settings - Fork 608
Qualcomm AI Engine Direct - Implement sdk profiler and intergrate with Qnn profiler #2227
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Qualcomm AI Engine Direct - Implement sdk profiler and intergrate with Qnn profiler #2227
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/2227
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 New FailureAs of commit 2db56a1 with merge base 588c391 ( NEW FAILURE - The following job has failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
Thanks for making and sharing the draft diff! This is great progress. I'll get back to you soon with answers to the questions you asked. |
Just a little note for the two questions,
For ExternalProject_Add, it builds on x86 toolchain but does not install to _host_build folder.
|
3e67470
to
f1bc714
Compare
Sorry for taking a while to get back to you.
Thanks for finding a workaround for it. @tarun292 will verify if the workaround breaks anything else of the sdk, if not, I think we can merge this PR.
This is something that's on our TODO list but unfortunately there's no way to set different units at this moment. |
…th Qnn profiler Summary: - Implement Qnn Profiler for htp backend For now, only support kProfileDetailed to profile the performance of each operator with cycle unit. Follow up item: Add more qnn profile item - Intergrated with sdk profiler - Add the argument etdump_path to dump etdump which analyzes the contents by INSPECTOR in qnn_executorch_runner - Add unit test to test profile - Add export example to generate etrecord
f1bc714
to
9980080
Compare
Thanks for your response. I am looking forward for this feature which set the unit for profile item. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Hey, could you please make sure you add the comment Dave suggested in the cmake file? Thanks for finding the workaround by the way, we think it's OK to land, but should be well documented. And thanks a lot for doing the integration and sorry for taking a while to review it
@Olivia-liu has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
It is a short-term workaround for flatcc. Co-authored-by: Dave Bort <[email protected]>
I added it in the cmake file. |
@Olivia-liu has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
@Olivia-liu merged this pull request in 0b12daf. |
Summary:
For now, only support kProfileDetailed to profile the performance of each operator with cycle unit.
Follow up item: Add more qnn profile item
Reproduce commands: