Energy-efficient scheduling method with cross-loop model for resource-limited CNN accelerator designs

Kaiyi Yang, Shihao Wang, Jianbin Zhou, Takeshi Yoshimura

研究成果: Conference contribution

4 被引用数 (Scopus)

抄録

The state-of-the-art customized accelerators of convolution neural networks (CNN) have achieved high throughput while the huge amount of data movements still remains as the dominant part of the total energy costs. In this paper, we propose an energy-efficient scheduling approach to find an efficient dataflow that minimizes data movements with limited hardware resource budgets. In detail, two-level nested loop transformations are proposed to separate memory and computing resource constraints. This allows us to fully exploit the potential of available memory resources for reducing off-chip memory traffic. Further, the proposed cross-loop model is capable of figuring out the data locality across nested loops in CNN algorithms. Finally, energy-delay production is employed as the evaluation criteria to balancing energy and throughput performance. The experimental results show our cross-loop model can reduce the off-chip data movements by 11-21% and achieve the theoretical optimum. Therefore, the proposed scheduling method can increase the energy efficiency by at least 8.7 times.

本文言語English
ホスト出版物のタイトルIEEE International Symposium on Circuits and Systems
ホスト出版物のサブタイトルFrom Dreams to Innovation, ISCAS 2017 - Conference Proceedings
出版社Institute of Electrical and Electronics Engineers Inc.
ISBN(電子版)9781467368520
DOI
出版ステータスPublished - 2017 9 25
イベント50th IEEE International Symposium on Circuits and Systems, ISCAS 2017 - Baltimore, United States
継続期間: 2017 5 282017 5 31

Other

Other50th IEEE International Symposium on Circuits and Systems, ISCAS 2017
国/地域United States
CityBaltimore
Period17/5/2817/5/31

ASJC Scopus subject areas

  • 電子工学および電気工学

フィンガープリント

「Energy-efficient scheduling method with cross-loop model for resource-limited CNN accelerator designs」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル