triton.experimental.gluon.language.nvidia.blackwell.tma.async_copy_global_to_shared

triton.experimental.gluon.language.nvidia.blackwell.tma.async_copy_global_to_shared(tensor_desc, coord, barrier, result, pred=True, multicast=False, _semantic=None)

Load data from global memory to shared memory using TMA.

Parameters:

• tensor_desc – Tensor descriptor (tiled)

• coord – Coordinates in the source tensor

• barrier – Barrier for synchronization

• result – Destination memory descriptor

• pred – Predicate for conditional execution

• multicast – Enable multicast