•  
  •  
 

Bulletin of Chinese Academy of Sciences (Chinese Version)

Keywords

high performance computing (HPC); high throughput computing (HTC); datacenter; sys-entropy

Document Type

Article

Abstract

With the rapid development of Internet technologies, the main applications of high performance computing (HPC) are changing form scientific and engineering applications to those focusing on data processing. This situation poses grave challenges for traditional high performance computing architecture, thus high throughput computing (HTC) comes into being. This paper explains the difference between HPC and HTC according to the application features, as well as introduces the basic theory and key technologies of HTC. We also show the research results of HTC chips and systems. Through the breakthrough of above HTC key technologies, it is expected to relieve the bottleneck of core chips, and make due contribution to the China's new high performance platform in the era of intelligent Internet of Things (IoT).

First page

648

Last Page

656

Language

Chinese

Publisher

Bulletin of Chinese Academy of Sciences

References

Barroso L A, Clidaras J, Holzle U. The Datacenter as a Computer:An Introduction to the Design of Warehousescale Machines. 2nd ed. San Rafael, CA:Morgan & Claypool Publishers. 2013:96.

Sun N, Bao Y, Fan D. The rise of high-throughput computing. Frontiers of Information Technology & Electronic Engineering, 2018, 19(10):1245-1250.

Fan D, Zhang H, Wang D, et al. Godson-T:An Efficient ManyCore Processor Exploring Thread-Level Parallelism. IEEE Micro, 2012, 32(2):38-47.

Fan D, Li W, Ye X, et al. SmarCo: An Efficient Many-Core Processor for High-Throughput Applications in Datacenters//. IEEE International Symposium on High Performance Computer Architecture (HPCA). Washington DC: IEEE Computer Society, 2018: 596-607.

Ma J, Sui X, Sun N, et al. Supporting Differentiated Services in Computers via Programmable Architecture for Resourcingon-Demand (PARD)//Twentieth International Conference on Architectural Support for Programming Languages & Operating Systems. New York: ACM, 2015: 131-143.

Bao Y, Wang S. Labeled von Neumann architecture for software-defined cloud. Journal of Computer Science and Technology, 2017, 32(2):219-223.

包云岗, 范东睿, 陈明宇, 等. "计算机即网络"理念与高通量计算.中国计算机学会通讯, 2016, 12(3):10-16

新华网.快速"吞吐"大数据——前瞻计算机"高通量"时代.[2018-10-26]. http://www.xinhuanet.com/politics/2018-10/26/c_1123620065.htm.

Download
Request a Copy

Share

COinS