Deep neural network accelerator with fine-grained parallelism discovery
US11966835B2 · kind B2 · utility
0Cited by
10References
20Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Jan 23, 2019 |
| Grant date | Apr 23, 2024 |
| Priority date | — |
| Expiry date | Aug 6, 2041 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/0495
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A sparse convolutional neural network accelerator system that dynamically and efficiently identifies fine-grained parallelism in sparse convolution operations. The system determines matching pairs of non-zero input activations and weights from the compacted input activation and weight arrays utilizing a scalable, dynamic parallelism discovery unit (PDU) that performs a parallel search on the input activation array and the weight array to identify reducible input activation and weight pairs.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.