[all-commits] [llvm/llvm-project] 34810e: [mlir] Add patterns to lower Math operations to LL...

Tres via All-commits all-commits at lists.llvm.org
Tue Apr 20 02:39:36 PDT 2021


  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 34810e1b9c4554976d9d8249b18f48ff083b55fa
      https://github.com/llvm/llvm-project/commit/34810e1b9c4554976d9d8249b18f48ff083b55fa
  Author: Tres Popp <tpopp at google.com>
  Date:   2021-04-20 (Tue, 20 Apr 2021)

  Changed paths:
    A mlir/include/mlir/Conversion/MathToLibm/MathToLibm.h
    M mlir/include/mlir/Conversion/Passes.h
    M mlir/include/mlir/Conversion/Passes.td
    M mlir/lib/Conversion/CMakeLists.txt
    A mlir/lib/Conversion/MathToLibm/CMakeLists.txt
    A mlir/lib/Conversion/MathToLibm/MathToLibm.cpp
    A mlir/test/Conversion/MathToLLVM/convert-to-libm.mlir

  Log Message:
  -----------
  [mlir] Add patterns to lower Math operations to LLVM based libm calls.

Some Math operations do not have an equivalent in LLVM. In these cases,
allow a low priority fallback of calling the libm functions. This is to
give functionality and is not a performant option.

Differential Revision: https://reviews.llvm.org/D100367




More information about the All-commits mailing list