arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2102.10423cs.LGcs.AR
收藏

卷积神经网络边缘TPU加速器的评价

An Evaluation of Edge TPU Accelerators for Convolutional Neural Networks

Enfabrica;Google(谷歌);Cruise;Google Research(谷歌研究院)

Kiran Seshadri, Berkin Akin, James Laudon, Ravi Narayanaswami, Amir Yazdanbakhsh

摘要:

Edge TPU是低功耗边缘设备的加速器领域,广泛用于Coral和Pixel设备等各种Google产品。在本文中,我们首先讨论了边缘TPU的主要微架构细节。然后,我们广泛评估了三类边缘TPU,涵盖不同的计算生态系统,这些TPU目前部署在Google产品中,或者是423 K独特的卷积神经网络中的产品管道。基于这一广泛的研究,我们讨论了关键的和可解释的微架构的见解研究类边缘TPU。我们主要讨论Edge TPU加速器如何在具有不同结构的卷积神经网络上执行。最后,我们介绍了我们正在努力开发高精度的学习机器学习模型,以估计加速器的主要性能指标,如延迟和能耗。这些学习的模型使加速器的评估速度大大加快(以毫秒为单位),作为耗时的周期精确模拟器的替代方案,并为快速硬件/软件协同设计提供了令人兴奋的机会。

英文摘要:

Edge TPUs are a domain of accelerators for low-power, edge devices and are widely used in various Google products such as Coral and Pixel devices. In this paper, we first discuss the major microarchitectural details of Edge TPUs. Then, we extensively evaluate three classes of Edge TPUs, covering different computing ecosystems, that are either currently deployed in Google products or are the product pipeline, across 423K unique convolutional neural networks. Building upon this extensive study, we discuss critical and interpretable microarchitectural insights about the studied classes of Edge TPUs. Mainly, we discuss how Edge TPU accelerators perform across convolutional neural networks with different structures. Finally, we present our ongoing efforts in developing high-accuracy learned machine learning models to estimate the major performance metrics of accelerators such as latency and energy consumption. These learned models enable significantly faster (in the order of milliseconds) evaluations of accelerators as an alternative to time-consuming cycle-accurate simulators and establish an exciting opportunity for rapid hard-ware/software co-design.

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。

↑