Implementation of CAPI and Traditional PCIe and Delay of Comparison

CORC > 沈阳自动化研究所 > 中国科学院沈阳自动化研究所 > 工业控制网络与系统研究室

	Implementation of CAPI and Traditional PCIe and Delay of Comparison
	Wang FD(王福东)2,3,4; Zhang T(张涛)1,2,3,4; Zhao BJ(赵冰洁)2,3,4; Yang F(杨帆)2,3,4; Li QX(李庆鑫)2,3,4; Li ZY(李子阳)2,3,4
	2020
会议日期	April 10-13, 2020
会议地点	Chengdu, China
关键词	Heterogeneous computing CAPI PCIe
页码	246-249
英文摘要	With the development of artificial intelligence technology and heterogeneous computing, heterogeneous communication speed is becoming more and more important. The latency of transmitting data determines whether a heterogeneous computing architecture is available. Current acceleration cards usually use PCIe interface. IBM developed the CAPI communication architecture for heterogeneous computing. This paper compares the technical principles and delays of the Power CAPI architecture and a high speed PCIe communication method. © 2020 IEEE.
产权排序	1
会议录	2020 IEEE 5th International Conference on Cloud Computing and Big Data Analytics, ICCCBDA 2020
会议录出版者	IEEE
会议录出版地	New York
语种	英语
ISBN号	978-1-7281-6024-5
内容类型	会议论文
源URL	[http://ir.sia.cn/handle/173321/26940]
专题	沈阳自动化研究所_工业控制网络与系统研究室
通讯作者	Wang FD(王福东)
作者单位	1.Dalian University of Technology 2.Key Laboratory of Networked Control Systemsm, Chinese Academy of Sciences 3.Shenyang Institute of Automation, Chinese Academy of Sciences 4.Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences
推荐引用方式 GB/T 7714	Wang FD,Zhang T,Zhao BJ,et al. Implementation of CAPI and Traditional PCIe and Delay of Comparison[C]. 见:. Chengdu, China. April 10-13, 2020.