triton.experimental.gluon.language.nvidia.rubin.mbarrier.expect

triton.experimental.gluon.language.nvidia.rubin.mbarrier.expect(mbarrier, bytes_per_cta=None, pred=True, *, from_cta=None, _semantic=None)

Expect a specific number of bytes being copied. When they are copied, the barrier is signaled.

Parameters:

  • mbarrier (shared_memory_descriptor) – Barrier that will be signaled when the operation is complete.

  • bytes_per_cta (int) – Expected byte count per CTA.

  • pred (bool) – Scalar predicate. Operation is skipped if predicate is False. Defaults to True.

  • from_cta (int, optional) – Mask of CTA-ID bits preserved when routing the arrival, in [0, num_ctas - 1]. Defaults to num_ctas - 1, which arrives from each CTA to itself; 0 routes from CTA 0 to every CTA.