[all-commits] [llvm/llvm-project] 4df492: AMDGPU/SDAG: Custom SETCC (i.e. ballot) is always ...

[Nicolai Hähnle via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 4df4922da6cd9d4f58aa17bd3a54435d947570fd
      https://github.com/llvm/llvm-project/commit/4df4922da6cd9d4f58aa17bd3a54435d947570fd
  Author: Nicolai Hähnle <nicolai.haehnle at amd.com>
  Date:   2022-04-11 (Mon, 11 Apr 2022)

  Changed paths:
    M llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp
    M llvm/test/CodeGen/AMDGPU/llvm.amdgcn.ballot.i32.ll
    M llvm/test/CodeGen/AMDGPU/llvm.amdgcn.ballot.i64.ll

  Log Message:
  -----------
  AMDGPU/SDAG: Custom SETCC (i.e. ballot) is always uniform

The AMDGPUISD::SETCC node is like ISD::SETCC, but returns a lane mask
instead of a per-lane boolean. The lane mask is uniform.

This improves instruction selection for code patterns like
ctpop(ballot(x)), which can now use an S_BCNT1_* instruction instead
of V_BCNT_*.

GlobalISel already selects scalar instructions (an earlier commit
added a test case)..

Differential Revision: https://reviews.llvm.org/D123432