[all-commits] [llvm/llvm-project] a6f2c2: [mlir][GPUToNVVM] Fix bug in mma elementwise lowering

[Thomas via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: a6f2c2291ede82777fb3b92c6f2ea78d56e97aca
      https://github.com/llvm/llvm-project/commit/a6f2c2291ede82777fb3b92c6f2ea78d56e97aca
  Author: Thomas Raoux <thomasraoux at google.com>
  Date:   2022-06-15 (Wed, 15 Jun 2022)

  Changed paths:
    M mlir/lib/Conversion/GPUToNVVM/WmmaOpsToNvvm.cpp
    M mlir/test/Conversion/GPUToNVVM/wmma-ops-to-nvvm.mlir

  Log Message:
  -----------
  [mlir][GPUToNVVM] Fix bug in mma elementwise lowering

The maxf implementation of wmma elementwise op was incorrect as the
operands of the select to check for Nan were swapped.

Differential Revision: https://reviews.llvm.org/D127879