Fixes from Jorge's ocean benchmarks - #157
Merged
Merged
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
@JorgeG94's ocean benchmarks found three real bugs in the frontend, so this fixes them. Double
fmax/fmin/fmodwere missing, sema stopped counting call arguments at 16 and then blamed a correct 23-argument call for the difference, and Metal was quietly narrowing double kernels to float.The one that isn't Jorge's is worse. Semantic errors were only fatal under
--sema, so every other mode printed them, carried on into codegen, wrote an output file and exited zero. Both ocean kernels now compile on ptx, amdgpu, cpu and rv64.