[all-commits] [llvm/llvm-project] fb7771: [clang][AMDGPU] Widen ballot for read_exec_lo/hi t...

[Arseniy Obolenskiy via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: fb77712fd1dd911330bd432d1fd9313081b40c59
      https://github.com/llvm/llvm-project/commit/fb77712fd1dd911330bd432d1fd9313081b40c59
  Author: Arseniy Obolenskiy <arseniy.obolenskiy at amd.com>
  Date:   2026-08-03 (Mon, 03 Aug 2026)

  Changed paths:
    M clang/lib/Basic/Targets/SPIR.h
    M clang/lib/CodeGen/TargetBuiltins/AMDGPU.cpp
    M clang/test/CodeGenOpenCL/builtins-amdgcn-wave64.cl
    M clang/test/CodeGenOpenCL/builtins-amdgcn.cl

  Log Message:
  -----------
  [clang][AMDGPU] Widen ballot for read_exec_lo/hi to wavefront size (#212813)

GlobalISel cannot select a ballot narrower than the wavefront width,
since it can't represent one bit per lane

Widen the ballot to the wave size and narrow the result afterwards

This is a prerequisite for relanding
https://github.com/llvm/llvm-project/pull/211493 (reverted in
https://github.com/llvm/llvm-project/pull/212628 to unblock buildbot) to
prevent device libs side failures

---------

Co-authored-by: Matt Arsenault <arsenm2 at gmail.com>



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