-
Notifications
You must be signed in to change notification settings - Fork 608
Implement dumping operator distribution for TOSA graph #4970
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
Conversation
Change-Id: I946e8487ad185d9994049ddcdcf7b08153c2597b Signed-off-by: Erik Lundell <[email protected]>
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/4970
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit dafdfaa with merge base 7b3549b ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
Nit: perhaps put example output in the commit message or PR summary? |
@digantdesai has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
@digantdesai has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
Updated the PR summary for both comments :) |
Seems like ci job |
Change-Id: I603e6b3245c95d5b7d720325c9467bf8896c630b
Seems like I updated the output message without updating the test, sorry about that. Should be corrected now. |
@digantdesai has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
@Erik-Lundell @digantdesai The Example failure (job):
|
@Erik-Lundell I've reverted this PR in #5131 |
When dumping the operator distribution after ArmTeste.partition, operators are counted both in the Edge IR and the TOSA graph. The complete output looks something like:
"operators: {op1: 3, op2: 5....}
TOSA operators: {op1: 2, op2: 3}"
Change-Id: I946e8487ad185d9994049ddcdcf7b08153c2597b