[all-commits] [llvm/llvm-project] f25f2f: [MLIR][XeGPU] Extend unrolling support for scatter...

[Jianhui Li via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: f25f2f7de4f8264d89ba3c4dc9daddb10a90c13f
      https://github.com/llvm/llvm-project/commit/f25f2f7de4f8264d89ba3c4dc9daddb10a90c13f
  Author: Jianhui Li <jian.hui.li at intel.com>
  Date:   2025-06-17 (Tue, 17 Jun 2025)

  Changed paths:
    M mlir/lib/Dialect/XeGPU/Transforms/XeGPUUnroll.cpp
    M mlir/test/Dialect/XeGPU/xegpu-unroll-patterns.mlir
    M mlir/test/lib/Dialect/XeGPU/TestXeGPUTransforms.cpp

  Log Message:
  -----------
  [MLIR][XeGPU] Extend unrolling support for scatter ops with chunk_size (#144447)

Add support for load/store with chunk_size, which requires special
consideration for the operand blocking since offests and masks are
 n-D and tensor are n+1-D. Support operations including create_tdesc,
update_tdesc, load, store, and prefetch.

---------

Co-authored-by: Adam Siemieniuk <adam.siemieniuk at intel.com>



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