Efficient in-memory representation of computation graph for fast serialization and comparison
AssigneeAlibaba Group Holding Limited
InventorWeifeng ZHANG
Life of this patent
Estimating the term…
Loading patent…
AssigneeAlibaba Group Holding Limited
InventorWeifeng ZHANG
Estimating the term…
Embodiments of the present disclosure introduce an offset-based representation for a computation graph of a neural network model. In this representation, the edges in the graph are implemented as offsets to the base address of the graph when the model is loaded into memory rather than pointers to address locations in memory. By replacing the pointer fields with offsets, the model in memory is no longer dependent on the allocation of memory. This overcomes the limitations of performance and/or power that is critical for comparing two models and copying a model to another memory location in latency sensitive applications and in mobile environments.
A method performed by a computing device for providing a data structure associated with a computation graph having a plurality of nodes, the method comprising:
A computing device for providing a data structure associated with a computation graph having a plurality of nodes, the computing device comprising:
A non-transitory computer readable medium that stores a set of instructions that is executable by at least one processor of a computing device to cause the computing device to perform a method for providing a data structure associated with a computation graph having a plurality of nodes, the method comprising:
22-30. (canceled)
Dependencies are inferred from the claim text.