Work

Greedy Prefetch for Reducing Off-Chip Memory Accesses in Convolutional Neural Network Inference

Year: 2025

Type: article

Abstract: The high parameter and memory access demands of CNNs highlight the need to reduce off-chip memory accesses. While recent approaches have improved data reuse to lessen these accesses, simple and efficient prefetching methods are still lacking. This paper introduces a greedy prefetch method that uses data repetition to optimize the prefetching route, thus decreasing off-chip memory accesses. The method is also implemented in a hardware simulator to organize an deployment strategy with additional optimizations. Our deployment strategy outperforms recent works, with a maximum data reuse improvement of 1.98×.

Source: Information

DOI: 10.3390/info16030164

Authors: Dengtian Yang, Lan Chen

Institutions: Chinese Academy of Sciences, Institute of Microelectronics, University of Chinese Academy of Sciences

Language: English

Topic: Parallel Computing and Optimization Techniques

Subfield: Hardware and Architecture

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $1,930

Funders: Chinese Academy of Sciences, Institute of Microelectronics of the Chinese Academy of Sciences