[all-commits] [llvm/llvm-project] edff43: GlobalISel: Don't use GISelMatchGenericTypes for f...

[Petar Avramovic via All-commits]

  Branch: refs/heads/users/petar-avramovic/fp-GISelMatchGenericTypes
  Home:   https://github.com/llvm/llvm-project
  Commit: edff43101cfa9d3e147ac0ca05209fecf27020a8
      https://github.com/llvm/llvm-project/commit/edff43101cfa9d3e147ac0ca05209fecf27020a8
  Author: Petar Avramovic <Petar.Avramovic at amd.com>
  Date:   2026-07-30 (Thu, 30 Jul 2026)

  Changed paths:
    M llvm/include/llvm/Target/GenericOpcodes.td
    M llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-atomicrmw-fadd-local.mir
    M llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-atomicrmw-fadd-region.mir
    M llvm/test/CodeGen/AMDGPU/flat-saddr-atomics.ll

  Log Message:
  -----------
  GlobalISel: Don't use GISelMatchGenericTypes for floating point opcodes

With GISelMatchGenericTypes, AMDGPU had the same input pattern for
G_ATOMICRMW_FADD that checks for v2s16, so the one that is first
in the tablegen table always fires (it was v2f16 in this case).
Should explicitly check for v2f16/v2bf16.



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