[all-commits] [llvm/llvm-project] 6867e4: [mlir][spirv] Implement vector type legalization f...

[Angel Zhang via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 6867e49fc80c8468f9a5a8376ce7d3b89fd4fb51
      https://github.com/llvm/llvm-project/commit/6867e49fc80c8468f9a5a8376ce7d3b89fd4fb51
  Author: Angel Zhang <angel.zhang at amd.com>
  Date:   2024-07-17 (Wed, 17 Jul 2024)

  Changed paths:
    M mlir/include/mlir/Conversion/Passes.td
    M mlir/include/mlir/Dialect/SPIRV/Transforms/SPIRVConversion.h
    M mlir/lib/Conversion/ConvertToSPIRV/ConvertToSPIRVPass.cpp
    M mlir/lib/Dialect/SPIRV/Transforms/CMakeLists.txt
    M mlir/lib/Dialect/SPIRV/Transforms/SPIRVConversion.cpp
    M mlir/test/Conversion/ConvertToSPIRV/arith.mlir
    M mlir/test/Conversion/ConvertToSPIRV/combined.mlir
    A mlir/test/Conversion/ConvertToSPIRV/func-signature-vector-unroll.mlir
    M mlir/test/Conversion/ConvertToSPIRV/index.mlir
    M mlir/test/Conversion/ConvertToSPIRV/scf.mlir
    M mlir/test/Conversion/ConvertToSPIRV/simple.mlir
    M mlir/test/Conversion/ConvertToSPIRV/ub.mlir
    M mlir/test/Conversion/ConvertToSPIRV/vector.mlir
    M mlir/test/lib/Conversion/CMakeLists.txt
    A mlir/test/lib/Conversion/ConvertToSPIRV/CMakeLists.txt
    A mlir/test/lib/Conversion/ConvertToSPIRV/TestSPIRVFuncSignatureConversion.cpp
    M mlir/tools/mlir-opt/CMakeLists.txt
    M mlir/tools/mlir-opt/mlir-opt.cpp
    M utils/bazel/llvm-project-overlay/mlir/BUILD.bazel
    M utils/bazel/llvm-project-overlay/mlir/test/BUILD.bazel

  Log Message:
  -----------
  [mlir][spirv] Implement vector type legalization for function signatures (#98337)

### Description
This PR implements a minimal version of function signature conversion to
unroll vectors into 1D and with a size supported by SPIR-V (2, 3 or 4
depending on the original dimension). This PR also includes new unit
tests that only check for function signature conversion.

### Future Plans
- Check for capabilities that support vectors of size 8 or 16.
- Set up `OneToNTypeConversion` and `DialectConversion` to replace the
current implementation that uses `GreedyPatternRewriteDriver`.
- Introduce other vector unrolling patterns to cancel out the
`vector.insert_strided_slice` and `vector.extract_strided_slice` ops and
fully legalize the vector types in the function body.
- Handle `func::CallOp` and declarations.
- Restructure the code in `SPIRVConversion.cpp`.
- Create test passes for testing sets of patterns in isolation.
- Optimize the way original shape is splitted into target shapes, e.g.
`vector<5xi32>` can be splitted into `vector<4xi32>` and
`vector<1xi32>`.

---------

Co-authored-by: Jakub Kuderski <kubakuderski at gmail.com>



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