[all-commits] [llvm/llvm-project] ac370b: [MLIR][Linalg] Fix LinalgSpecializeGenericOpsPass ...

[Hugo Trachino via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: ac370b8e838ada3dd482560c4b8a568e760f95b5
      https://github.com/llvm/llvm-project/commit/ac370b8e838ada3dd482560c4b8a568e760f95b5
  Author: Hugo Trachino <hugo.trachino at huawei.com>
  Date:   2026-07-13 (Mon, 13 Jul 2026)

  Changed paths:
    M mlir/lib/Dialect/Linalg/Transforms/DecomposeGenericByUnfoldingPermutation.cpp
    M mlir/test/Dialect/Linalg/specialize-generic-ops-fail.mlir

  Log Message:
  -----------
  [MLIR][Linalg] Fix LinalgSpecializeGenericOpsPass for scalar inputs (#208466)

The test case added would crash because the Ranked Tensor-ness of
operands was assumed but never checked. This crash only happened when there
were multiple inputs as it must bail out somewhere else when there is only
1 input.



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