[all-commits] [llvm/llvm-project] 31f5ae: [OpenACC] Honor precomputed active par dims on a p...

[Matsu via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 31f5ae6ba9105531001af6baa8357b6fb5613f46
      https://github.com/llvm/llvm-project/commit/31f5ae6ba9105531001af6baa8357b6fb5613f46
  Author: Matsu <47756807+khaki3 at users.noreply.github.com>
  Date:   2026-09-17 (Thu, 17 Sep 2026)

  Changed paths:
    M mlir/lib/Dialect/OpenACC/Transforms/ACCCGToGPU.cpp
    A mlir/test/Dialect/OpenACC/acc-cg-to-gpu-predicate-region-active-dims.mlir

  Log Message:
  -----------
  [OpenACC] Honor precomputed active par dims on a predicate region (#224390)

Example:
```mlir
acc.predicate_region {
  memref.store %updated, %shared[] : memref<f64>
} {acc.active_par_dims = #acc<active_par_dims[]>}
```
Code outside a gang-level loop runs on every thread block, so the block
dims are treated as active and never predicated away. That is right for a
redundant computation, but not for an in-place update of memory the whole
launch shares: every block applies it. The attribute above was ignored
here, because only a privatization could state which dims run it
unpredicated.

Fix: honor a precomputed active set on a predicate region too. An empty
set leaves one block and one thread performing the update; listing the
thread dims of the enclosing loops keeps a work-shared update distributing
its iterations. Behavior is unchanged for a region without the attribute.



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