SOLAR: Services-Oriented Deep Learning Architectures-Deep Learning as a Service.

  • SCI-E
  • EI
作者: Chao Wang;Lei Gong;Xi Li;Qi Yu;Aili Wang;Patrick Hung;Xuehai Zhou
作者机构: Computer Science, Universiity of Science and Technology of China, Hefei, Anhui China (e-mail: llxx@ustc.edu.cn)
Software Engineering, University of Science and Technology of China, Suzhou, Jiangsu China (e-mail: wangal@ustc.edu.cn)
Faculty of Business and Information Technology, University of Ontario Institute of Technology (UOIT), Oshawa, Ontario Canada L1H 7K4 (e-mail: patrick.hung@uoit.ca)
Computer Science, Universiity of Science and Technology of China, Suzhou, Jiangsu China 215123 (e-mail: saintwc@mail.ustc.edu.cn)
Computer Science Department, University of Science and Technology of China, Hefei, Anhui China (e-mail: xhzhou@ustc.edu.cn)
Computer Science, Universiity of Science and Technology of China, Suzhou, Jiangsu China (e-mail: leigong0203@mail.ustc.edu.cn)
语种: 英文
关键词: Diverse applications - Hardware accelerators - High performance implementations - Learning architectures - Learning neural networks - Programming models - Services oriented architecture - Software processor
期刊: IEEE Transactions on Services Computing
ISSN: 1939-1374
年: 2021
摘要: Deep learning has been an emerging field of machine learning during past decades. However, the diversity and large scale data size have posed significant challenge to construct a flexible and high performance implementations of deep learning neural networks. In order to improve the performance as well to maintain the scalability, in this paper we present SOLAR, a services-oriented deep learning architecture using various ac-celerators like GPU and FPGA. SOLAR provides a uniform programming model to users so that the hardware implemen-tation and the scheduling is invisible to the programmers. At runtime, the services can be executed either on the software processors or the hardware accelerators. To leverage the trade-offs between the metrics among performance, power, energy, and efficiency, we present a multitarget design space explora-tion. Experimental results on the real state-of-the-art FPGA board demonstrate that the SOLAR is able to provide a ubiq-uitous framework for diverse applications without increasing the burden of the programmers. Moreover, the speedup of the GPU and FPGA hardware accelerator in SOLAR can achieve significant speedup comparing to the conventional Intel i5 pro-cessors with great scalability.<br/> IEEE

文件格式:
导出字段:
导出
关闭
SOLAR: Services-Oriented Deep Learning Architectures-Deep Learning as a Service.
有问题请联系我们,邮箱:常见的失败原因