triton.experimental.gluon.language.amd.cdna5.tdm

Functions

update_tensor_descriptor	Update selected fields of a TDM descriptor; return a new descriptor SSA value.
async_load	Load a block of tensor specified in tensor descriptor from global memory to shared memory asynchronously.
async_load_fused	Emit one explicit fused TDM load for 2-4 descriptor/destination pairs.
async_wait	Wait for the outstanding asynchronous tensor operations to complete.
make_tensor_descriptor	Make a tensor descriptor object.
prefetch	Prefetches a block of tensor specified in tensor descriptor from global memory into L2.
async_store	Store a block of tensor specified in tensor descriptor from shared memory to global memory asynchronously.
async_scatter	Scatter data from shared memory to non-contiguous rows in global memory asynchronously.
async_gather	Gather data from non-contiguous rows in global memory to shared memory asynchronously.

Classes

tensor_descriptor	A descriptor representing a tensor in global memory.
tensor_descriptor_type	The type for a tensor descriptor.