Modeling and optimizing PE utilization rate for systolic array based CNN accelerators

Minhui Hu; Jianhua Fan; Yongyang Hu; Rui Xu; Yang Guo

doi:10.1117/12.2682498

20 June 2023 Modeling and optimizing PE utilization rate for systolic array based CNN accelerators

Minhui Hu, Jianhua Fan, Yongyang Hu, Rui Xu, Yang Guo

Proceedings Volume 12715, Eighth International Conference on Electronic Technology and Information Science (ICETIS 2023); 127151R (2023) https://doi.org/10.1117/12.2682498
Event: Eighth International Conference on Electronic Technology and Information Science (ICETIS 2023), 2023, Dalian, China

Abstract

Due to its efficiency, energy-saving, and abundant data reuse, systolic array has been a popular choice for Convolutional Neural Network (CNN) accelerators. Dataflow of the systolic array defines computation mapping strategy and memory access and it is one of the most important design points of accelerators. Most conventional accelerator designs choose a single dataflow and optimize around it. This may influence the Processing Element (PE) utilization rate and cause waste of computing resources and energy. This work introduces a self-paced method to alleviate this problem. We analyse and quantify the PE utilization rate related to the three basic dataflows and build a model called PEU-sim to explore workload-oriented flexible dataflow. Experiments show by combining three dataflows, we are able to raise more than 10% of PE utilization rate for most neural networks and we get the highest of 12.4% for MobileNet.

Citation Download Citation

Minhui Hu, Jianhua Fan, Yongyang Hu, Rui Xu, and Yang Guo "Modeling and optimizing PE utilization rate for systolic array based CNN accelerators", Proc. SPIE 12715, Eighth International Conference on Electronic Technology and Information Science (ICETIS 2023), 127151R (20 June 2023); https://doi.org/10.1117/12.2682498

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available