[all-commits] [llvm/llvm-project] c2fc8d: [mlir][GPU] Allow bare pointer memrefs when callin...

[Krzysztof Drewniak via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: c2fc8d9b95bd98acb52a3174ed677c2a85aafe4d
      https://github.com/llvm/llvm-project/commit/c2fc8d9b95bd98acb52a3174ed677c2a85aafe4d
  Author: Krzysztof Drewniak <Krzysztof.Drewniak at amd.com>
  Date:   2022-08-02 (Tue, 02 Aug 2022)

  Changed paths:
    M mlir/include/mlir/Conversion/GPUCommon/GPUCommonPass.h
    M mlir/include/mlir/Conversion/GPUToROCDL/GPUToROCDLPass.h
    M mlir/include/mlir/Conversion/LLVMCommon/TypeConverter.h
    M mlir/include/mlir/Conversion/Passes.td
    M mlir/lib/Conversion/GPUCommon/GPUOpsLowering.cpp
    M mlir/lib/Conversion/GPUCommon/GPUToLLVMConversion.cpp
    M mlir/lib/Conversion/GPUToROCDL/LowerGpuOpsToROCDLOps.cpp
    A mlir/test/Conversion/GPUToROCDL/memref.mlir
    M mlir/test/Integration/GPU/ROCM/vecadd.mlir

  Log Message:
  -----------
  [mlir][GPU] Allow bare pointer memrefs when calling GPU kernels

In the ROCm runtime (and probably CUDA as well), all kernel arguments
are aligned. Therefore, enable using bare pointers for memref
arguments to kernels when these memrefs have static shape and a
trivial layout.

This is a substantial optimization to launching kernels that use
memrefs with known, static sizes, since it causes the kernel launch
packet to no longer include information already known to the kernel,
which can enable packing the kernel launch arguments into launch
packets instead of having to allocate an entire separate structure to
hold unneeded memref information.

Reviewed By: ftynse

Differential Revision: https://reviews.llvm.org/D130716