Overflowing emerging neural network inference tasks from the GPU to the CPU on heterogeneous servers

Author:

Kumar Adithya1,Sivasubramaniam Anand1,Zhu Timothy1

Affiliation:

1. The Pennsylvania State University

Funder

NSF

Publisher

ACM

Reference67 articles.

1. Martín Abadi , Paul Barham , Jianmin Chen , Zhifeng Chen , Andy Davis , Jeffrey Dean , Matthieu Devin , Sanjay Ghemawat , Geoffrey Irving , Michael Isard , 2016 . {TensorFlow}: A System for {Large-Scale} Machine Learning . In Proceedings of the Symposium on Operating Systems Design and Implementation (OSDI). USENIX , Boston, MA, 265--283. Martín Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, et al. 2016. {TensorFlow}: A System for {Large-Scale} Machine Learning. In Proceedings of the Symposium on Operating Systems Design and Implementation (OSDI). USENIX, Boston, MA, 265--283.

2. Ravichandra Addanki , Shaileshh Bojja Venkatakrishnan , Shreyan Gupta , Hongzi Mao , and Mohammad Alizadeh . 2018 . Placeto: Efficient progressive device placement optimization . In NIPS Machine Learning for Systems Workshop. NeurIPS , San Diego, CA, USA. Ravichandra Addanki, Shaileshh Bojja Venkatakrishnan, Shreyan Gupta, Hongzi Mao, and Mohammad Alizadeh. 2018. Placeto: Efficient progressive device placement optimization. In NIPS Machine Learning for Systems Workshop. NeurIPS, San Diego, CA, USA.

3. StarPU: a unified platform for task scheduling on heterogeneous multicore architectures

4. Junjie Bai , Fang Lu , Ke Zhang , 2019 . ONNX: Open Neural Network Exchange. https://github.com/onnx/onnx. Junjie Bai, Fang Lu, Ke Zhang, et al. 2019. ONNX: Open Neural Network Exchange. https://github.com/onnx/onnx.

5. Decentralized Offload-based Execution on Memory-centric Compute Cores

Cited by 3 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Rapid calibration method for head-mounted eye-tracker;International Conference on Frontiers of Applied Optics and Computer Engineering (AOCE 2024);2024-02-21

2. Hybrid photonic integrated circuits for neuromorphic computing [Invited];Optical Materials Express;2023-11-28

3. Optimizing CPU Performance for Recommendation Systems At-Scale;Proceedings of the 50th Annual International Symposium on Computer Architecture;2023-06-17

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3