[SYCL] Preserve fpbuiltin-max-error information in fpmath metadata #17393
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
Signed-off-by: Sidorov, Dmitry <dmitry.sidorov@intel.com>
MrSidims
changed the title
VyacheslavLevytskyy
approved these changes
Mar 11, 2025
vmaksimo
approved these changes
Mar 11, 2025
asudarsa
reviewed
Mar 11, 2025
| if (auto *ReplacementI = dyn_cast<Instruction>(Replacement)) | ||
| if (auto *ReplacementI = dyn_cast<Instruction>(Replacement)) { | ||
| ReplacementI->copyFastMathFlags(&BuiltinCall); | ||
| // Copy accuracy from fp-max-error attribute to fpmath metadata just in case |
There was a problem hiding this comment.
Can this not be done when the BuiltinCall is generated by CodeGen? Is there a reason to wait till SYCLLowerIR stage?
This is mostly a nit/curiosity question. Not a blocker.
Thanks
There was a problem hiding this comment.
AFAIU only entering CodeGen we know, what AltMath library can offer us in terms of FPBuiltin implementations. So at this stage it makes sense to start modifying LLVM IR as we will go over fpbuiltin calls anyway.
|
@intel/llvm-gatekeepers please help with merge |
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Outdated suggestions cannot be applied.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.
FPBuiltinFnSelection pass is modified to create fpmath metadata during replacement of
llvm.fpbuiltin.* intrinsics with native LLVM instructions or LLVM std intrinsics.