[all-commits] [llvm/llvm-project] 58e3ec: [AMDGPU] Validate scale_sel in v_cvt_scale_*

[Stanislav Mekhanoshin via All-commits]

  Branch: refs/heads/users/rampitec/block16-validate-scale
  Home:   https://github.com/llvm/llvm-project
  Commit: 58e3ec49acbd10411712491ee54064d433540b3d
      https://github.com/llvm/llvm-project/commit/58e3ec49acbd10411712491ee54064d433540b3d
  Author: Stanislav Mekhanoshin <Stanislav.Mekhanoshin at amd.com>
  Date:   2026-09-30 (Wed, 30 Sep 2026)

  Changed paths:
    M clang/include/clang/Basic/BuiltinsAMDGPU.td
    M clang/test/SemaOpenCL/builtins-amdgcn-error-gfx1250-strict.cl
    M llvm/include/llvm/IR/IntrinsicsAMDGPU.td
    M llvm/lib/Target/AMDGPU/AMDGPULowerIntrinsics.cpp
    M llvm/lib/Target/AMDGPU/AsmParser/AMDGPUAsmParser.cpp
    M llvm/lib/Target/AMDGPU/VOP3Instructions.td
    A llvm/test/CodeGen/AMDGPU/llvm.amdgcn.cvt.scale.pk-scale-range.ll
    M llvm/test/CodeGen/AMDGPU/llvm.amdgcn.cvt.scale.pk.ll
    M llvm/test/MC/AMDGPU/gfx1250-strict_err.s

  Log Message:
  -----------
  [AMDGPU] Validate scale_sel in v_cvt_scale_*

These instructions can be block16 or block32 depending on the target
and scale_sel bits. Block16 is not supported in strict mode.

Re-enable the rest of the instructions in the strict mode but validate
the scale selector.



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