[all-commits] [llvm/llvm-project] c563ed: AMDGPU/GlobalISel: Clean up fp LLT usage in AMDGPU...

[Petar Avramovic via All-commits]

  Branch: refs/heads/users/petar-avramovic/extendedLLTs-fp-legalizer
  Home:   https://github.com/llvm/llvm-project
  Commit: c563edbd5c9b6b19d5457178c86609bac2eaa5ad
      https://github.com/llvm/llvm-project/commit/c563edbd5c9b6b19d5457178c86609bac2eaa5ad
  Author: Petar Avramovic <Petar.Avramovic at amd.com>
  Date:   2026-07-21 (Tue, 21 Jul 2026)

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

  Log Message:
  -----------
  AMDGPU/GlobalISel: Clean up fp LLT usage in AMDGPULegalizerInfo

Remove local variables in favor of global F16/BF16/F32/F64/V2F16/V2BF16.
These are now proper floating point LLTs instead of LLT::scalar.
A couple of legalizer actions now use fp extended LLT for type checks.
This is intended and is planned for all floating point opcodes.
In most cases the current S16/S32/S64 action on floating point opcodes was
intended for F16/F32/F64, and we will need to define an action for BF16.



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