[all-commits] [llvm/llvm-project] 98d097: [AMDGPU] Re-enabling divergence predicates for min...

[alex-t via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 98d09705e15c5927f41009e5627c926ba1e87c26
      https://github.com/llvm/llvm-project/commit/98d09705e15c5927f41009e5627c926ba1e87c26
  Author: alex-t <alexander.timofeev at amd.com>
  Date:   2021-12-20 (Mon, 20 Dec 2021)

  Changed paths:
    M llvm/lib/Target/AMDGPU/SOPInstructions.td
    A llvm/test/CodeGen/AMDGPU/divergence-driven-min-max.ll

  Log Message:
  -----------
  [AMDGPU] Re-enabling divergence predicates for min/max

This patch enables divergence predicates for min/max nodes.
It makes ISD::MIN/MAX selected to S_MIN_I(U)32/S_MAX_I(U)32 or V_MIN_I(U)32_e64/V_MAX_I(U)32_e64

Reviewed By: rampitec

Differential Revision: https://reviews.llvm.org/D115954