[all-commits] [llvm/llvm-project] 1a4bc3: [AMDGPU] Avoid unnecessary graph visits during WQM...

[Carl Ritson via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 1a4bc3aba360522983692ac933b2b6daaa5f5082
      https://github.com/llvm/llvm-project/commit/1a4bc3aba360522983692ac933b2b6daaa5f5082
  Author: Carl Ritson <carl.ritson at amd.com>
  Date:   2021-03-18 (Thu, 18 Mar 2021)

  Changed paths:
    M llvm/lib/Target/AMDGPU/SIWholeQuadMode.cpp

  Log Message:
  -----------
  [AMDGPU] Avoid unnecessary graph visits during WQM marking

Avoid revisiting nodes with the same set of defined lanes by
using a unified visited set which integrates lanes into the key.
This retains the intent of the original code by still revisiting
a subgraph if a different set of lanes is defined and hence
marking might progress differently.

Note: default size of the visited set has been confirmed to
cover >99% of invocations in large array of test shaders.

Reviewed By: piotr

Differential Revision: https://reviews.llvm.org/D98772