[all-commits] [llvm/llvm-project] 8306f7: [mlir][arith] Add minimumnumf and maximumnumf oper...

[lorenzo chelini via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 8306f7777172718453729ee941734bab9217c9fa
      https://github.com/llvm/llvm-project/commit/8306f7777172718453729ee941734bab9217c9fa
  Author: lorenzo chelini <l.chelini at icloud.com>
  Date:   2026-09-22 (Tue, 22 Sep 2026)

  Changed paths:
    M mlir/include/mlir/Dialect/Arith/IR/ArithOps.td
    M mlir/include/mlir/Dialect/LLVMIR/LLVMIntrinsicOps.td
    M mlir/include/mlir/Dialect/Vector/IR/VectorAttributes.td
    M mlir/lib/Conversion/ArithToLLVM/ArithToLLVM.cpp
    M mlir/lib/Conversion/VectorToLLVM/ConvertVectorToLLVM.cpp
    M mlir/lib/Dialect/Arith/IR/ArithOps.cpp
    M mlir/lib/Dialect/Linalg/Transforms/Vectorization.cpp
    M mlir/lib/Dialect/Vector/IR/VectorOps.cpp
    M mlir/lib/Dialect/Vector/Transforms/LowerVectorContract.cpp
    M mlir/lib/Dialect/Vector/Transforms/LowerVectorScan.cpp
    M mlir/lib/Dialect/XeGPU/Utils/XeGPUUtils.cpp
    M mlir/test/Conversion/ArithToLLVM/arith-to-llvm.mlir
    M mlir/test/Conversion/VectorToLLVM/vector-reduction-to-llvm.mlir
    M mlir/test/Conversion/VectorToLLVM/vector-to-llvm-interface.mlir
    M mlir/test/Dialect/Arith/ops.mlir
    M mlir/test/Dialect/Vector/ops.mlir
    M mlir/test/Dialect/XeGPU/xegpu-wg-to-sg.mlir
    A mlir/test/Integration/Dialect/Vector/CPU/reductions-masked-minmaxnum-f32.mlir
    M mlir/test/Target/LLVMIR/Import/intrinsic.ll
    M mlir/test/Target/LLVMIR/llvmir-intrinsics.mlir

  Log Message:
  -----------
  [mlir][arith] Add minimumnumf and maximumnumf operations (#221658)

Add `arith.minimumnumf` and `arith.maximumnumf`, following
`minimumNumber` and `maximumNumber` from IEEE 754-2019 and the
`llvm.minimumnum`/`llvm.maximumnum` intrinsics. They differ from the
existing `arith.minnumf`/`arith.maxnumf` only in their treatment of
signaling NaNs: the new ops deterministically return the non-NaN
operand, whereas minnumf/maxnumf may return either NaN or the other
operand.



To unsubscribe from these emails, change your notification settings at https://github.com/llvm/llvm-project/settings/notifications