[all-commits] [llvm/llvm-project] aecb76: [mlir][gpu] GPUToROCDL/NVVM: use generic llvm conv...

[Ivan Butygin via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: aecb764cc2e026ecb5c418dd56f2722c6f263e8b
      https://github.com/llvm/llvm-project/commit/aecb764cc2e026ecb5c418dd56f2722c6f263e8b
  Author: Ivan Butygin <ivan.butygin at gmail.com>
  Date:   2025-02-13 (Thu, 13 Feb 2025)

  Changed paths:
    M mlir/include/mlir/Conversion/Passes.td
    M mlir/lib/Conversion/GPUToNVVM/LowerGpuOpsToNVVMOps.cpp
    M mlir/lib/Conversion/GPUToROCDL/LowerGpuOpsToROCDLOps.cpp
    A mlir/test/Conversion/GPUToNVVM/gpu-to-nvvm-invalid-dialect.mlir
    M mlir/test/Conversion/GPUToNVVM/gpu-to-nvvm.mlir
    A mlir/test/Conversion/GPUToROCDL/gpu-to-rocdl-invalid-dialect.mlir
    M mlir/test/Conversion/GPUToROCDL/gpu-to-rocdl.mlir

  Log Message:
  -----------
  [mlir][gpu] GPUToROCDL/NVVM: use generic llvm conversion interface instead of hardcoded conversions. (#124439)

Using `ConvertToLLVMPatternInterface` allows to unhardcode specific
dialect conversions from passes and, more importantly, allows downstream
projects to inject their ops/types translation here by registering
corresponding interface.

Add `allowed-dialects` option so user can control which dialects can be
used to populate conversions.



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