Inproceedings,

Pruning and Early-Exit Co-Optimization for CNN Acceleration on FPGAs

, , , , and .
2023 Design, Automation and Test in Europe Conference and Exhibition, DATE 2023 - Proceedings, United States of America, Institute of Electrical and Electronics Engineers Inc., (2023)Publisher Copyright: © 2023 EDAA.; 2023 Design, Automation and Test in Europe Conference and Exhibition, DATE 2023 ; Conference date: 17-04-2023 Through 19-04-2023.
DOI: 10.23919/DATE56975.2023.10137244

Abstract

The challenge of processing heavy-load ML tasks, particularly CNN-based ones at resource-constrained IoT devices, has encouraged the use of edge servers. The edge offers performance levels higher than the end devices and better latency and security levels than the Cloud. On top of that, the rising complexity of ML applications, the ever-increasing number of connected devices, and the current demands for energy efficiency require optimizing such CNN models. Pruning and early-exit are notable optimizations that have been successfully used to alleviate the computational cost of inference. However, these optimizations have not yet been exploited …(more)

Tags

Users

  • @scadsfct

Comments and Reviews