[all-commits] [llvm/llvm-project] dad089: AMDGPU: Remove wavefrontsize64 feature from dummy ...

[Matt Arsenault via All-commits]

  Branch: refs/heads/users/arsenm/remove-wave64-feature-from-default-target
  Home:   https://github.com/llvm/llvm-project
  Commit: dad089846eba71cc8d9c8cbe96ea6a0d67900593
      https://github.com/llvm/llvm-project/commit/dad089846eba71cc8d9c8cbe96ea6a0d67900593
  Author: Matt Arsenault <Matthew.Arsenault at amd.com>
  Date:   2024-11-22 (Fri, 22 Nov 2024)

  Changed paths:
    M llvm/lib/Target/AMDGPU/GCNProcessors.td
    M llvm/lib/Target/AMDGPU/GCNSubtarget.cpp
    M llvm/lib/Target/AMDGPU/GCNSubtarget.h
    M llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUInstPrinter.cpp

  Log Message:
  -----------
  AMDGPU: Remove wavefrontsize64 feature from dummy target

This is a refinement for the existing hack. With this,
the default target will have neither wavefrontsize feature
present, unless it was explicitly specified. That is,
getWavefrontSize() == 64 no longer implies +wavefrontsize64.
getWavefrontSize() == 32 does imply +wavefrontsize32.

Continue to assume the value is 64 with no wavesize feature.
This maintains the codegenable property without any code
that directly cares about the wavesize needs to worry about it.

Introduce an isWaveSizeKnown helper to check if we know the
wavesize is accurate based on having one of the features explicitly
set, or a known target-cpu.



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