Binaryware: A High-Performance Digital Hardware Accelerator for Binary Neural Networks

Citations

WEB OF SCIENCE

3
Citations

SCOPUS

5

초록

Binary neural networks (BNNs) largely reduce the memory footprint and computational complexity, so they are gaining interests on various mobile applications. In the BNNs, the first layer often accounts for the largest part of the entire computing time because the layer usually uses multi-bit multiplications. However, traditional hardware designed for BNN computing focuses primarily on the rest layers, resulting in significant performance degradation. In this brief, we introduce Binaryware architecture which achieves the high-performance computation on both the first and rest layers. Experimental results show that our Binaryware improves the throughput per compute area by 1.5-13.3x on various BNN workloads.

키워드

Artificial intelligencebinary neural networks (BNNs)hardware acceleratorquantization
제목
Binaryware: A High-Performance Digital Hardware Accelerator for Binary Neural Networks
저자
Ryu, SungjuOh, YoungtaekKim, Jae-Joon
DOI
10.1109/TVLSI.2023.3324834
발행일
2023-12
유형
Article
저널명
IEEE Transactions on Very Large Scale Integration (VLSI) Systems
31
12
페이지
2137 ~ 2141