[all-commits] [llvm/llvm-project] a528ce: [mlir][vector] Improve `makeArithReduction` expans...

[Jakub Kuderski via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: a528cee2242f7d5f70ea74408af10152ac25a193
      https://github.com/llvm/llvm-project/commit/a528cee2242f7d5f70ea74408af10152ac25a193
  Author: Jakub Kuderski <jakub at nod-labs.com>
  Date:   2023-12-18 (Mon, 18 Dec 2023)

  Changed paths:
    M mlir/include/mlir/Dialect/Vector/IR/VectorOps.h
    M mlir/lib/Dialect/Vector/IR/VectorOps.cpp
    M mlir/lib/Dialect/Vector/Transforms/LowerVectorContract.cpp
    M mlir/test/Conversion/VectorToLLVM/vector-to-llvm.mlir
    M mlir/test/Dialect/Vector/canonicalize.mlir
    M mlir/test/Dialect/Vector/vector-multi-reduction-outer-lowering.mlir

  Log Message:
  -----------
  [mlir][vector] Improve `makeArithReduction` expansion (#75846)

Propagate fast math flags.
Distinguish `minf`/`maxf` and `minimumf`/`maximumf`.

Required for future patterns in
https://github.com/llvm/llvm-project/pull/75727.