Method and system for compressing application data for operations on multi-core systems
US11599367B2 · kind B2 · utility
Assignee
Inventor
Key dates
| Filing date | Jan 24, 2020 |
| Grant date | Mar 7, 2023 |
| Priority date | — |
| Expiry date | Aug 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.