Accelerated quantized multiply-and-add operations
US10678508B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Mar 23, 2018 |
| Grant date | Jun 9, 2020 |
| Priority date | — |
| Expiry date | May 28, 2038 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/045
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Disclosed herein are techniques for accelerating convolution operations or other matrix multiplications in applications such as neural network. A computer-implemented method includes receiving low-precision inputs for a convolution operation from a storage device, and subtracting a low-precision value representing a high-precision zero value from the low-precision inputs to generate difference values, where the low-precision inputs are asymmetrically quantized from high-precision inputs. The method also includes performing multiplication and summation operations on the difference values to generate a sum of products, and generating a high-precision output by scaling the sum of products with a scaling factor.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.