[all-commits] [llvm/llvm-project] d85f64: AMDGPU: Fix incorrectly selecting fp8/bf8 conversi...

[Matt Arsenault via All-commits]

  Branch: refs/heads/users/arsenm/amdgpu-fix-wrong-predicates-fp8-conversion-intrinsics
  Home:   https://github.com/llvm/llvm-project
  Commit: d85f641e5cf9c777ed4d91f1d08e95098536d1bc
      https://github.com/llvm/llvm-project/commit/d85f641e5cf9c777ed4d91f1d08e95098536d1bc
  Author: Matt Arsenault <Matthew.Arsenault at amd.com>
  Date:   2024-10-01 (Tue, 01 Oct 2024)

  Changed paths:
    M llvm/lib/Target/AMDGPU/AMDGPU.td
    M llvm/lib/Target/AMDGPU/GCNSubtarget.h
    M llvm/lib/Target/AMDGPU/VOP1Instructions.td
    A llvm/test/CodeGen/AMDGPU/llvm.amdgcn.cvt.f32.fp8.err.ll

  Log Message:
  -----------
  AMDGPU: Fix incorrectly selecting fp8/bf8 conversion intrinsics

Trying to codegen these on targets without the instructions should
fail to select. Not sure if all the predicates are correct. We had
a fake one disconnected to a feature which was always true.

Fixes: SWDEV-482274


  Commit: 7f8fd29d11c3b189f2be583acbcf94d5d09ea29b
      https://github.com/llvm/llvm-project/commit/7f8fd29d11c3b189f2be583acbcf94d5d09ea29b
  Author: Matt Arsenault <Matthew.Arsenault at amd.com>
  Date:   2024-10-01 (Tue, 01 Oct 2024)

  Changed paths:
    M llvm/lib/Target/AMDGPU/AMDGPU.td

  Log Message:
  -----------
  Formatting


  Commit: cb93a8915bb6afd6ecc8ef650809d450cbb9dda7
      https://github.com/llvm/llvm-project/commit/cb93a8915bb6afd6ecc8ef650809d450cbb9dda7
  Author: Matt Arsenault <Matthew.Arsenault at amd.com>
  Date:   2024-10-01 (Tue, 01 Oct 2024)

  Changed paths:
    M llvm/lib/Target/AMDGPU/AMDGPU.td

  Log Message:
  -----------
  Remove from gfx12


  Commit: 5c72cf0c7d58699b6960f49a6dfee81893630198
      https://github.com/llvm/llvm-project/commit/5c72cf0c7d58699b6960f49a6dfee81893630198
  Author: Matt Arsenault <Matthew.Arsenault at amd.com>
  Date:   2024-10-01 (Tue, 01 Oct 2024)

  Changed paths:
    M llvm/lib/Target/AMDGPU/VOP1Instructions.td

  Log Message:
  -----------
  Remove HasSDWA OtherPredicate


  Commit: e5063d75e037660a3752de1922f211bfae9b4be5
      https://github.com/llvm/llvm-project/commit/e5063d75e037660a3752de1922f211bfae9b4be5
  Author: Matt Arsenault <Matthew.Arsenault at amd.com>
  Date:   2024-10-01 (Tue, 01 Oct 2024)

  Changed paths:
    M llvm/lib/Target/AMDGPU/GCNSubtarget.h

  Log Message:
  -----------
  Fix hasCvtFP8VOP1Bug predicate


  Commit: cc9a3b9e75442e4e811f73eb66ceed50d100fe14
      https://github.com/llvm/llvm-project/commit/cc9a3b9e75442e4e811f73eb66ceed50d100fe14
  Author: Matt Arsenault <Matthew.Arsenault at amd.com>
  Date:   2024-10-01 (Tue, 01 Oct 2024)

  Changed paths:
    M llvm/lib/Target/AMDGPU/VOP1Instructions.td

  Log Message:
  -----------
  Avoid selecting e32 case on gfx12; not sure how to best check for requiring the op_sel form


Compare: https://github.com/llvm/llvm-project/compare/394a284f3d0e...cc9a3b9e7544

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