[all-commits] [llvm/llvm-project] b3c9d8: [AMDGPU] Fix 24-bit mul intrinsic generation for >...

[Abinav Puthan Purayil via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: b3c9d84e5a8ef49e33b20e1ea9608c5c9b935591
      https://github.com/llvm/llvm-project/commit/b3c9d84e5a8ef49e33b20e1ea9608c5c9b935591
  Author: Abinav Puthan Purayil <abinav.puthanpurayil at amd.com>
  Date:   2021-10-14 (Thu, 14 Oct 2021)

  Changed paths:
    M llvm/lib/Target/AMDGPU/AMDGPUCodeGenPrepare.cpp
    M llvm/test/CodeGen/AMDGPU/amdgpu-codegenprepare-mul24.ll

  Log Message:
  -----------
  [AMDGPU] Fix 24-bit mul intrinsic generation for > 32-bit result.

The 24-bit mul intrinsics yields the low-order 32 bits. We should only
do the transformation if the operands are known to be not wider than 24
bits and the result is known to be not wider than 32 bits.

Differential Revision: https://reviews.llvm.org/D111523