Compute near memory convolution accelerator
US11726950B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Sep 28, 2019 |
| Grant date | Aug 15, 2023 |
| Priority date | — |
| Expiry date | Jul 17, 2041 |
Classification
- Technology area (CPC Y)Emerging Cross-Sectional Technologies
- CPC primaryY02D10/00
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A compute near memory (CNM) convolution accelerator enables a convolutional neural network (CNN) to use dedicated acceleration to achieve efficient in-place convolution operations with less impact on memory and energy consumption. A 2D convolution operation is reformulated as 1D row-wise convolution. The 1D row-wise convolution enables the CNM convolution accelerator to process input activations row-by-row, while using the weights one-by-one. Lightweight access circuits provide the ability to stream both weights and input rows as vectors to MAC units, which in turn enables modules of the CNM convolution accelerator to implement convolution for both [1×1] and chosen [n×n] sized filters.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.