Patent · US Active

Intermediate representation method and apparatus for parallel execution of graph computation

US11782723B1 · kind B1 · utility

0Cited by
0References
7Claims
0Family size

Assignee

Inventors

Key dates

Filing dateNov 22, 2022
Grant dateOct 10, 2023
Priority date
Expiry dateNov 22, 2042

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/063
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Disclosed are an intermediate representation method and apparatus for parallel execution of graph computation. The method includes the following steps: S1: compiling a neural network into a computational graph on a computer; S2: defining branch states of tensor variables in the computational graph; S3: defining a data dependency relationship of the tensor variables in the computational graph; S4: defining a control dependency relationship of the tensor variables in the computational graph; S5: building a data dependency relationship graph of the tensor variables in the computational graph; S6: building a control dependency relationship graph of the tensor variables in the computational graph; and S7: transforming control dependencies into data dependencies. The present application derives, based on the dependency relationship, a parallel computing method that can execute the branch threads in parallel in the global computational graph, and optimizes the compilation efficiency of the computational graph.

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