OSCA: End-to-End Serial Stochastic Computing Neural Acceleration with Fine-Grained Scaling and Piecewise Activation

End-to-end stochastic computing (SC) emerges as a promising paradigm for efficient neural acceleration. However, existing serial SC accelerators face serious accuracy challenges due to errors in addition, limited activation compatibility, and limited bitstream multiplication. In this paper, we propo...

Full description

Bibliographic Details

Published in:	Digest of technical papers - IEEE/ACM International Conference on Computer-Aided Design pp. 1 - 9
Main Authors:	Hu, Yixuan, Jia, Yikang, Li, Meng, Wang, Yuan, Wang, Runsheng, Huang, Ru
Format:	Conference Proceeding
Language:	English
Published:	ACM 27.10.2024
Subjects:	Accuracy Adders Binary sequences Circuit synthesis Correlation Design automation End-to-end serial stochastic computing Faces Fine-grained scaling Piecewise activation function Quantization (signal) Root mean square
ISSN:	1558-2434
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!