[all-commits] [llvm/llvm-project] 6cae29: [MLIR][XeGPU] XeVM lowering support for load_matri...

[Jianhui Li via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 6cae29fb3a139c37bbaa09fbaa1179a643a231c9
      https://github.com/llvm/llvm-project/commit/6cae29fb3a139c37bbaa09fbaa1179a643a231c9
  Author: Jianhui Li <jian.hui.li at intel.com>
  Date:   2025-10-15 (Wed, 15 Oct 2025)

  Changed paths:
    M mlir/include/mlir/Dialect/XeGPU/IR/XeGPUAttrs.td
    M mlir/include/mlir/Dialect/XeGPU/IR/XeGPUOps.td
    M mlir/include/mlir/Dialect/XeGPU/IR/XeGPUTypes.td
    M mlir/lib/Conversion/XeGPUToXeVM/CMakeLists.txt
    M mlir/lib/Conversion/XeGPUToXeVM/XeGPUToXeVM.cpp
    M mlir/lib/Dialect/XeGPU/IR/XeGPUDialect.cpp
    M mlir/lib/Dialect/XeGPU/IR/XeGPUOps.cpp
    M mlir/lib/Dialect/XeGPU/Transforms/XeGPUUnroll.cpp
    M mlir/lib/Dialect/XeGPU/Transforms/XeGPUWgToSgDistribute.cpp
    M mlir/test/Conversion/XeGPUToXeVM/dpas.mlir
    A mlir/test/Conversion/XeGPUToXeVM/loadstore_matrix.mlir
    M mlir/test/Dialect/XeGPU/invalid.mlir
    M mlir/test/Dialect/XeGPU/ops.mlir

  Log Message:
  -----------
  [MLIR][XeGPU] XeVM lowering support for load_matrix/store_matrix (#162780)

This PR adds lowering of xegpu.load_matrix/store_matrix to
xevm.blockload/blockstore or and llvm.load/store, depending on wi level
attributes.
It includes a few components: 
   1. adds wi-level attributes: subgroup_block_io.   
2. expand load_matrix/store_matrix op definition to support scalar data
(besides vector data).
2. adds a member function to mem_desc to compute the linearized address
for a nd offsets.
   3. add lowering depending on wi-level attributes: 
a) if subgroup_block_io attribute presents, lower to
xevm.blockload/blockstore
c) else lower to llvm.load/store. If result is a vector, lower to
llvm.load/store with vector operand.



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