[all-commits] [llvm/llvm-project] 4c597d: [mlir][xegpu] Support boundary checks only for blo...

[Adam Siemieniuk via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 4c597d42dca13220c19661a021a11e28e2af801b
      https://github.com/llvm/llvm-project/commit/4c597d42dca13220c19661a021a11e28e2af801b
  Author: Adam Siemieniuk <adam.siemieniuk at intel.com>
  Date:   2024-12-13 (Fri, 13 Dec 2024)

  Changed paths:
    M mlir/lib/Conversion/VectorToXeGPU/VectorToXeGPU.cpp
    M mlir/test/Conversion/VectorToXeGPU/load-to-xegpu.mlir
    M mlir/test/Conversion/VectorToXeGPU/store-to-xegpu.mlir
    M mlir/test/Conversion/VectorToXeGPU/transfer-read-to-xegpu.mlir
    M mlir/test/Conversion/VectorToXeGPU/transfer-write-to-xegpu.mlir

  Log Message:
  -----------
  [mlir][xegpu] Support boundary checks only for block instructions (#119380)

Constrains Vector lowering to apply boundary checks only to data
transfers operating on block shapes.

This further aligns lowering with the current Xe instructions'
restrictions.



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