Back to results
US 12,632,269 B2Granted
Forward-style gradient GeMMs
AssigneeSambaNova Systems, Inc.
InventorsMingran Wang, Leon Zhang
Life of this patent
Estimating the term…
Loading patent…
Loading patent…
AssigneeSambaNova Systems, Inc.
InventorsMingran Wang, Leon Zhang
Estimating the term…
A method for improving runtime performance and alleviating place and route issues in a reconfigurable computing system includes receiving a compute graph for execution on a reconfigurable dataflow processor. The compute graph includes a node specifying a template-based operation on a first and second tensor having a shared batch dimension B. The node may be split into B nodes. Each of the template-based operations on the pair of tensors may be replace with a GeMM operation on the first reduced rank tensor slice and a tile. B nodes that specify the GeMM operation may be appended with at least one first addition node that accepts input from the B nodes to produce a first modified compute graph. The first modified compute graph may be executed. The method describes a significant improvement to overall compute utilization across gradient-sections. Spatial tiling of tensors facilitates gradient calculation without the use of accumulators.
A system for reducing latency and increasing throughput in reconfigurable dataflow processors, the system comprising:
A method for reducing latency and increasing throughput in a reconfigurable computing system, the method comprising:
A non-transitory computer program product comprising a non-transitory computer readable storage medium having program instructions embodied therewith, wherein the non-transitory computer readable storage medium is not a transitory signal per se, wherein the program instructions are executable by a processor to cause the processor to conduct a method comprising:
Dependencies are inferred from the claim text.