Design and implementation of communication system of the Dawning 6000 supercomputer

Authors:
Qiang Li;Bo Li;Zhigang Huo;Ninghui Sun
Affiliations:
National Research Center for Intelligent Computing Systems, Beijing, China 100190 and Key Laboratory of Computer System and Architecture, Chinese Academy of Sciences, Beijing, China 100190 and Gra ...;National Research Center for Intelligent Computing Systems, Beijing, China 100190 and Key Laboratory of Computer System and Architecture, Chinese Academy of Sciences, Beijing, China 100190 and Gra ...;National Research Center for Intelligent Computing Systems, Beijing, China 100190 and Key Laboratory of Computer System and Architecture, Chinese Academy of Sciences, Beijing, China 100190;National Research Center for Intelligent Computing Systems, Beijing, China 100190 and Key Laboratory of Computer System and Architecture, Chinese Academy of Sciences, Beijing, China 100190
Venue:
Frontiers of Computer Science in China
Year:
2010

Citing 4
Cited 0

User-Level Communication in Cluster-Based Servers

HPCA '02 Proceedings of the 8th International Symposium on High-Performance Computer Architecture
Xen and the art of virtualization

SOSP '03 Proceedings of the nineteenth ACM symposium on Operating systems principles
Single System Image

International Journal of High Performance Computing Applications
Overview of the Blue Gene/L system architecture

IBM Journal of Research and Development

Quantified Score

Hi-index	0.00

Visualization

Abstract

An increasing number of supercomputers adopt a heterogeneous architecture, consisting of both general purpose CPUs and specialized accelerators. Such design is beneficial for scalability and power, but on the other hand, heterogeneity brings new challenges in communication systems to connect heterogeneous components and provide support for programming. The communication system of the Dawning 6000 connects two kinds of heterogeneous processors, Loongson and AMD, and adopts a three layer architecture with an intranode layer between heterogeneous components. To efficiently connect heterogeneous components, the system forms a global address space and provides a mechanism for message transmission via an in-node global store; and employing Infiniband network, provides an OS-bypassing virtualization method to share an Infiniband card between nodes. To facilitate programming on heterogeneous processors, it supports unified parallel C (UPC), with a modified complier based on global address space. Also, a special collective network is implemented for collective operations. Results obtained from a prototype system prove these features to be both feasible and efficient.