triton.language.atomic_or(pointer, val, mask=None)

Performs an atomic logical or at the memory location specified by pointer.

Return the data stored at pointer before the atomic operation.

  • pointer (Block of dtype=triton.PointerDType) – The memory locations to apply logical or.

  • val (Block of dtype=`pointer.dtype.element_ty`) – The values to logical or in the atomic object.

  • mask (Block of triton.int1, optional) – If mask[idx] is false, do not apply logical or.