[all-commits] [llvm/llvm-project] dd0c7f: [MLIR][Linalg] Fix crash in tileToForallOpImpl for...

[Mehdi Amini via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: dd0c7f1f344f22a29d3c483966f89ffb5f70850e
      https://github.com/llvm/llvm-project/commit/dd0c7f1f344f22a29d3c483966f89ffb5f70850e
  Author: Mehdi Amini <joker.eph at gmail.com>
  Date:   2026-04-13 (Mon, 13 Apr 2026)

  Changed paths:
    M mlir/lib/Dialect/Linalg/TransformOps/LinalgTransformOps.cpp
    M mlir/test/Dialect/Linalg/tile-to-forall.mlir

  Log Message:
  -----------
  [MLIR][Linalg] Fix crash in tileToForallOpImpl for rank-0 ops (#189000)

When tiling a rank-0 linalg.generic op, tileUsingSCF returns an empty
loops vector (rank-0 ops have no parallel dimensions and produce no
scf.forall). Two call sites unconditionally accessed
tilingResult.loops.front(), causing a crash:

- tileToForallOpImpl: the loop normalization block was entered whenever
mixedNumThreads was empty, regardless of whether any loops exist. Guard
it with \!tilingResult.loops.empty().

- TileUsingForallOp::apply: tileOps.push_back was called
unconditionally. Guard it with \!tilingResult.loops.empty().

Add regression tests for both the tile_sizes and num_threads paths,
verifying that the linalg.generic is preserved and no scf.forall is
emitted.

Fixes #187073

Assisted-by: Claude Code



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