[all-commits] [llvm/llvm-project] dccf83: [AMDGPU] SIOptimizeExecMaskingPreRA should check c...

[alex-t via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: dccf83acf95530da0425ab6293addb410fb062fd
      https://github.com/llvm/llvm-project/commit/dccf83acf95530da0425ab6293addb410fb062fd
  Author: alex-t <alexander.timofeev at amd.com>
  Date:   2021-03-24 (Wed, 24 Mar 2021)

  Changed paths:
    M llvm/lib/Target/AMDGPU/SIOptimizeExecMaskingPreRA.cpp
    A llvm/test/CodeGen/AMDGPU/opt_exec_copy_fold.mir

  Log Message:
  -----------
  [AMDGPU] SIOptimizeExecMaskingPreRA should check constant bus constraint when folds EXEC copy

Folding EXEC copy into it's single use may lead to constant bus constraint violation as it adds one more SGPR operand.
         This change makes it validate the user instruction with the new SGPR operand and only fold it if it is legal.

Reviewed By: rampitec, arsenm

Differential Revision: https://reviews.llvm.org/D98888