Abstract
Today, cluster-based computing is the mainstream architecture for high end computer systems. Balanced system design is critical for large scale cluster systems to achieve high efficiency. This paper addresses the practice on DeepComp high end computer systems toward a balanced system design. Methodologies of designing balanced large scale cluster systems are given. A method for balancing central processing unit (CPU) and memory hierarchy is addressed. For balancing computing nodes and I/O systems, two approaches are given: maximum bandwidth criterion and maximum number of computing nodes which can concurrently access I/O systems. Experiences of Lenovo high end cluster systems show that above methods are effective. Lenovo strategies toward a balanced system design for both peta and 10 peta scale high productivity computing systems (HPCSs).
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Lenovo Group. Technical Report of Lenovo DeepComp 6800. Beijing, 2003
Lenovo Group. Technical Report of Lenovo DeepComp 7000. Beijing, 2008
Zhu M. Lenovo DeepComp 6800 in China grid computing. In: Proceedings of Workshop of China HPC & Grid Computing, Super Computing Conference. 2004
Culler D, Gupta A, Sign J P. Parallel Computer Architecture: A Hardware/Software Approach. San Francisco: Morgan Kaufmann Publishers, 1998
Buyya R. High Performance Cluster Computing: Architectures and Systems, Vol. 1. Upper Saddle River: Prentice Hall, 1999
High Productivity Computing Systems (HPCS) Program. http://www.darpa.mil/ipto/Programs/hpcs/index.htm, USA, 2002
Krishnamurthy A. HPCS benchmarks and test and specification environments. In: Proceedings of SC05. 2005
Xiao L, Zhu M. Exploiting the Capabilities of the Interconnection Network on Dawning-1000. Journal of Computer Science and Technology, 1999, 14(1): 49–55
Xiao L, Zhu M. Active Messages on Dawning 1000. Nat. Res. Center for Intelligent Comput. Syst., Acad. Sinica, Beijing, 1996
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Zhu, M., Xiao, L., Ruan, L. et al. DeepComp: towards a balanced system design for high performance computer systems. Front. Comput. Sci. China 4, 475–479 (2010). https://doi.org/10.1007/s11704-010-0150-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11704-010-0150-z