Added a test case to show the 1.0 + -1.0 instruction time-out under f… #592
Conversation
This file contains 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
…loat_corner_test Fixed the missing check for the add/sub result being 0.0 in the normalizar state machine.
|
This is really great! |
stnolting
approved these changes
Apr 21, 2023
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
A specific corner test exist in the floating point add/sub function which results in the post add/sub normalizer running for sreg.exp cycles, which for the number 1.0f is enough to trigger the time-out in the execution engine.
An example has been added to the float_corner_test that performs: 1.0f + -1.0f which results in 0.0f but also times out.
A fix has been added to the normalizer in which the S_PERPARE_NORM state has an additional check whether mantissa_i is all 0's. If so the resulting add/sub is 0.0 and we set ctrl.cnt to 0 to ensure the exp is 0 and jump straight to S_FINALIZE. Which should now correctly generate a +/- 0.0f result.