Integrate llvm-project@8244f8210f2e #20404
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
krzysz00
requested review from
Groverkss,
MaheshRavishankar,
antiagainst,
hanhanW,
kuhar,
pashu123 and
qedawkins
as code owners
Contributor
Author
|
@Groverkss Please review changes related to your upstream refactoring of vector lowering patterns |
kuhar
approved these changes
Mar 31, 2025
Member
kuhar
left a comment
kuhar
left a comment
There was a problem hiding this comment.
Nice, thanks for figuring this out and unblocking us
bangtianliu
pushed a commit
to bangtianliu/iree
that referenced
this pull request
Apr 8, 2025
- Add calls to `populateVectorGatherLoweringPatterns` and `populateVectorGatherToConditionalLoadPatterns` as needed to handle upstream llvm/llvm-project#132206 - Update ROCDL tests to account for llvm/llvm-project#131850 - Disable `tosa.reduce_prod` and `tosa.clamp` tests on integers temporarily since they're failing Tosa verification - see iree-org#20422 Explicitly set `amdhsa_code_object_version` when constructing ROCm LLVM modules, explicitly pass `-mcode-object-version=N` to microkernel compiles, and explicitly set the `__oclc_ABI_version` global, so that we don't get hit with errors about being unable to run our binaries from the compiler default code object version getting bumped further than what our users or CI support. The default code object version in LLVM as of this commit is 6, we pin to 5. The followup work to update to v6 is iree-org#20423 .
AWoloszyn
pushed a commit
that referenced
this pull request
Dec 1, 2025
- Add calls to `populateVectorGatherLoweringPatterns` and `populateVectorGatherToConditionalLoadPatterns` as needed to handle upstream llvm/llvm-project#132206 - Update ROCDL tests to account for llvm/llvm-project#131850 - Disable `tosa.reduce_prod` and `tosa.clamp` tests on integers temporarily since they're failing Tosa verification - see #20422 Explicitly set `amdhsa_code_object_version` when constructing ROCm LLVM modules, explicitly pass `-mcode-object-version=N` to microkernel compiles, and explicitly set the `__oclc_ABI_version` global, so that we don't get hit with errors about being unable to run our binaries from the compiler default code object version getting bumped further than what our users or CI support. The default code object version in LLVM as of this commit is 6, we pin to 5. The followup work to update to v6 is #20423 .
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.
populateVectorGatherLoweringPatternsandpopulateVectorGatherToConditionalLoadPatternsas needed to handle upstream [mlir][vector] Decouple unrolling gather and gather to llvm lowering llvm/llvm-project#132206tosa.reduce_prodandtosa.clamptests on integers temporarily since they're failing Tosa verification - see Restore Tosa tests removed in integrate #20422Explicitly set
amdhsa_code_object_versionwhen constructing ROCm LLVM modules, explicitly pass-mcode-object-version=Nto microkernel compiles, and explicitly set the__oclc_ABI_versionglobal, so that we don't get hit with errors about being unable to run our binaries from the compiler default code object version getting bumped further than what our users or CI support.The default code object version in LLVM as of this commit is 6, we pin to 5. The followup work to update to v6 is #20423 .