Patent · US Active

Method of neural network model computation-oriented intermediate representation by constructing physical computation graph, inferring information of input and output tensor edges of each node therein, performing memory optimization on tensor edges, and optimizing physical computation graph

US11823053B2 · kind B2 · utility

0Cited by
0References
13Claims
0Family size

Assignee

Inventors

Key dates

Filing dateApr 6, 2022
Grant dateNov 21, 2023
Priority date
Expiry dateApr 6, 2042

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/045
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

The disclosure discloses a method of neural network model computation-oriented intermediate representation and apparatus thereof. The method includes the following steps: S1, parsing an input model file so as to acquire topological structure information of a neural network; S2, constructing a logical computation graph; S21, inferring physical layout information of each operator in the logical computation graph; S22, inferring meta attributes of each operator in the logical computation graph; S23, inferring description information of input and output logical tensors of each operator in the logical computation graph; S3, constructing a physical computation graph; S31, generating a physical computation graph, etc.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.