[all-commits] [llvm/llvm-project] 46ad54: [mlir][gpu][vector] Lower Vector dialect to GPU fo...

[Hsiangkai Wang via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 46ad5408fc8e31e97f5b1191320ca449c00f4191
      https://github.com/llvm/llvm-project/commit/46ad5408fc8e31e97f5b1191320ca449c00f4191
  Author: Hsiangkai Wang <hsiangkai.wang at arm.com>
  Date:   2025-09-17 (Wed, 17 Sep 2025)

  Changed paths:
    M mlir/lib/Conversion/VectorToGPU/VectorToGPU.cpp
    M mlir/test/Conversion/VectorToGPU/vector-to-mma-ops.mlir

  Log Message:
  -----------
  [mlir][gpu][vector] Lower Vector dialect to GPU for element-wise ops only (#159091)

Current convertVectorToMMAOps starts from vector.contract and finds its
dependencies as the targets to convert. In GPU dialect, we have
gpu.subgroup_mma_elementwise operation. We should be able to lower
element-wise operations to GPU MMA operations without vector.contract.
This patch adds this case to the pattern.



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