Patent · US Active

Method and system for compressing application data for operations on multi-core systems

US11599367B2 · kind B2 · utility

1Cited by
0References
19Claims
0Family size

Assignee

Inventor

Key dates

Filing dateJan 24, 2020
Grant dateMar 7, 2023
Priority date
Expiry dateAug 4, 2041

Classification

  • Technology area (CPC H)Electricity
  • CPC primaryH03M7/6017
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A system and method to compress application control data, such as weights for a layer of a convolutional neural network, is disclosed. A multi-core system for executing at least one layer of the convolutional neural network includes a storage device storing a compressed weight matrix of a set of weights of the at least one layer of the convolutional network and a decompression matrix. The compressed weight matrix is formed by matrix factorization and quantization of a floating point value of each weight to a floating point format. A decompression module is operable to obtain an approximation of the weight values by decompressing the compressed weight matrix through the decompression matrix. A plurality of cores executes the at least one layer of the convolutional neural network with the approximation of weight values to produce an inference output.

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