diff options
| author | Slava Zakharin <szakharin@nvidia.com> | 2022-12-13 21:45:07 -0800 |
|---|---|---|
| committer | Slava Zakharin <szakharin@nvidia.com> | 2022-12-14 10:15:05 -0800 |
| commit | 70174b8035da3f28ef651ee8de96bcfa6d688ada (patch) | |
| tree | c432c02d417730922378eb976b803bdc5c6744fc /mlir/lib/Conversion/MathToLLVM/MathToLLVM.cpp | |
| parent | 88f9b525085b4292080aec6aba835801ca5793b6 (diff) | |
[mlir][math] Added math::FPowI conversion to LLVM dialect.
The operations are converted into LLVM::PowIOp.
Reviewed By: Mogball
Differential Revision: https://reviews.llvm.org/D129812
Diffstat (limited to 'mlir/lib/Conversion/MathToLLVM/MathToLLVM.cpp')
| -rw-r--r-- | mlir/lib/Conversion/MathToLLVM/MathToLLVM.cpp | 3 |
1 files changed, 3 insertions, 0 deletions
diff --git a/mlir/lib/Conversion/MathToLLVM/MathToLLVM.cpp b/mlir/lib/Conversion/MathToLLVM/MathToLLVM.cpp index b5ce019b2083..ece80921e29b 100644 --- a/mlir/lib/Conversion/MathToLLVM/MathToLLVM.cpp +++ b/mlir/lib/Conversion/MathToLLVM/MathToLLVM.cpp @@ -50,6 +50,8 @@ using Log10OpLowering = using Log2OpLowering = ConvertFMFMathToLLVMPattern<math::Log2Op, LLVM::Log2Op>; using LogOpLowering = ConvertFMFMathToLLVMPattern<math::LogOp, LLVM::LogOp>; using PowFOpLowering = ConvertFMFMathToLLVMPattern<math::PowFOp, LLVM::PowOp>; +using FPowIOpLowering = + ConvertFMFMathToLLVMPattern<math::FPowIOp, LLVM::PowIOp>; using RoundEvenOpLowering = ConvertFMFMathToLLVMPattern<math::RoundEvenOp, LLVM::RoundEvenOp>; using RoundOpLowering = @@ -313,6 +315,7 @@ void mlir::populateMathToLLVMConversionPatterns(LLVMTypeConverter &converter, Exp2OpLowering, ExpM1OpLowering, ExpOpLowering, + FPowIOpLowering, FloorOpLowering, FmaOpLowering, Log10OpLowering, |