arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2207.01209cs.ARcs.AI
收藏

边缘端可持续 AI 处理

Sustainable AI Processing at the Edge

University of Pittsburgh(匹兹堡大学)

Sébastien Ollivier, Sheng Li, Yue Tang, Chayanika Chaudhuri, Peipei Zhou, Xulong Tang, Jingtong Hu, Alex K. Jones

AI总结:

本文评估边缘 CNN 推理与在线训练加速器的可持续性,比较 PIM、移动 GPU、FPGA 与新型 Racetrack memory PIM 的内含能量和活动率权衡。

摘要:

边缘计算是加速支持移动设备的机器学习算法的热门目标,无需承担在云端处理这些算法所带来的通信延迟。机器学习的边缘部署主要考虑传统问题,例如安装时的 SWaP 约束(尺寸、重量和功率)。然而,鉴于内含能量和碳的显著贡献,这些指标并不足以全面考虑计算对环境的影响。本文探讨了用于推理和在线训练的卷积神经网络加速引擎之间的权衡。具体而言,作者研究了存内处理(PIM)方法、移动 GPU 加速器以及近期发布的 FPGA 的使用,并将它们与新型 Racetrack memory PIM 进行比较。用 Racetrack memory PIM 替换支持 PIM 的 DDR3,最快可在 1 年内收回其内含能量。对于高活动率,移动 GPU 可能更具可持续性,但与支持 PIM 的 Racetrack memory 相比,其需要克服更高的内含能量。

英文摘要:

Edge computing is a popular target for accelerating machine learning algorithms supporting mobile devices without requiring the communication latencies to handle them in the cloud. Edge deployments of machine learning primarily consider traditional concerns such as SWaP constraints (Size, Weight, and Power) for their installations. However, such metrics are not entirely sufficient to consider environmental impacts from computing given the significant contributions from embodied energy and carbon. In this paper we explore the tradeoffs of convolutional neural network acceleration engines for both inference and on-line training. In particular, we explore the use of processing-in-memory (PIM) approaches, mobile GPU accelerators, and recently released FPGAs, and compare them with novel Racetrack memory PIM. Replacing PIM-enabled DDR3 with Racetrack memory PIM can recover its embodied energy as quickly as 1 year. For high activity ratios, mobile GPUs can be more sustainable but have higher embodied energy to overcome compared to PIM-enabled Racetrack memory.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑