[all-commits] [llvm/llvm-project] d8a656: [MLIR] AMDGPUToROCDL: Use a bitcast op to reintepr...

[Benoit Jacob via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: d8a656ffaf735ed689856daa5dc13a9274358072
      https://github.com/llvm/llvm-project/commit/d8a656ffaf735ed689856daa5dc13a9274358072
  Author: Benoit Jacob <jacob.benoit.1 at gmail.com>
  Date:   2024-10-07 (Mon, 07 Oct 2024)

  Changed paths:
    M mlir/lib/Conversion/AMDGPUToROCDL/AMDGPUToROCDL.cpp
    M mlir/test/Conversion/AMDGPUToROCDL/mfma.mlir

  Log Message:
  -----------
  [MLIR] AMDGPUToROCDL: Use a bitcast op to reintepret a vector of i8 as single integer. (#111400)

Found by inspecting AMDGPU assembly - so the arithmetic ops created
there were definitely making their way into the target ISA. A
`LLVM::BitcastOp` seems equivalent, and evaporates as expected in the
target asm.

Along the way, I thought that this helper function `mfmaConcatIfNeeded`
could be renamed to `convertMFMAVectorOperand` to better convey its
contract; so I don't need to think about whether a bitcast is a
legitimate "concat" :-)

---------

Signed-off-by: Benoit Jacob <jacob.benoit.1 at gmail.com>



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