diff options
| author | Matthias Springer <me@m-sp.org> | 2025-01-06 12:00:11 +0100 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-01-06 12:00:11 +0100 |
| commit | 599c73990532333e62edf8ba19a5302b543f976f (patch) | |
| tree | 8852f372db066ec3e5a41d04b0166178aa29eeb9 /mlir/lib/Conversion/OpenMPToLLVM/OpenMPToLLVM.cpp | |
| parent | a13bcf3ced35b0df89ac13670690b4482052e47f (diff) | |
| download | llvm-599c73990532333e62edf8ba19a5302b543f976f.zip llvm-599c73990532333e62edf8ba19a5302b543f976f.tar.gz llvm-599c73990532333e62edf8ba19a5302b543f976f.tar.bz2 | |
[mlir][GPU] Add NVVM-specific `cf.assert` lowering (#120431)
This commit add an NVIDIA-specific lowering of `cf.assert` to to
`__assertfail`.
Note: `getUniqueFormatGlobalName`, `getOrCreateFormatStringConstant` and
`getOrDefineFunction` are moved to `GPUOpsLowering.h`, so that they can
be reused.
Diffstat (limited to 'mlir/lib/Conversion/OpenMPToLLVM/OpenMPToLLVM.cpp')
| -rw-r--r-- | mlir/lib/Conversion/OpenMPToLLVM/OpenMPToLLVM.cpp | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/mlir/lib/Conversion/OpenMPToLLVM/OpenMPToLLVM.cpp b/mlir/lib/Conversion/OpenMPToLLVM/OpenMPToLLVM.cpp index 58fd3d5..5d00039 100644 --- a/mlir/lib/Conversion/OpenMPToLLVM/OpenMPToLLVM.cpp +++ b/mlir/lib/Conversion/OpenMPToLLVM/OpenMPToLLVM.cpp @@ -304,6 +304,7 @@ void ConvertOpenMPToLLVMPass::runOnOperation() { LLVMTypeConverter converter(&getContext()); arith::populateArithToLLVMConversionPatterns(converter, patterns); cf::populateControlFlowToLLVMConversionPatterns(converter, patterns); + cf::populateAssertToLLVMConversionPattern(converter, patterns); populateFinalizeMemRefToLLVMConversionPatterns(converter, patterns); populateFuncToLLVMConversionPatterns(converter, patterns); populateOpenMPToLLVMConversionPatterns(converter, patterns); |