[AOT][Testing] Improve output mismatch information on test failure #16765
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Enhanced AOT test harness to include overall mismatch percentage and the individual mismatch positions from the output tensor for debugging test failures. Both of these are still gated behind `print_output_on_mismatch == True`. I also added tests to check for the presence and correctness of this new debug information. Sample output: ``` Element [Position]: Actual, Reference ------------------------------------- Element [0, 8, 8, 7]: 521.846313, 521.847412 Element [0, 9, 8, 51]: 478.874359, 478.875549 Element [0, 9, 9, 6]: 462.901001, 462.899658 Mismatched elements: 3 / 16384 (0.02%) ... ```
lhutton1
reviewed
Mar 22, 2024
Contributor
lhutton1
left a comment
lhutton1
left a comment
There was a problem hiding this comment.
Very nice improvement, thanks @Anndrey24 :)
lhutton1
approved these changes
Mar 25, 2024
Contributor
|
Thanks @Anndrey24 @ekalda! |
thaisacs
pushed a commit
to thaisacs/tvm
that referenced
this pull request
Apr 3, 2024
…pache#16765) Enhanced AOT test harness to include overall mismatch percentage and the individual mismatch positions from the output tensor for debugging test failures. Both of these are still gated behind `print_output_on_mismatch == True`. I also added tests to check for the presence and correctness of this new debug information. Sample output: ``` Element [Position]: Actual, Reference ------------------------------------- Element [0, 8, 8, 7]: 521.846313, 521.847412 Element [0, 9, 8, 51]: 478.874359, 478.875549 Element [0, 9, 9, 6]: 462.901001, 462.899658 Mismatched elements: 3 / 16384 (0.02%) ... ```
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Enhanced AOT test harness to include overall mismatch percentage and the individual mismatch positions from the output tensor for debugging test failures. Both of these are still gated behind
print_output_on_mismatch == True.I also added tests to check for the presence and correctness of this new debug information.
Sample output:
cc @lhutton1 @ekalda