A High Performance Cluster System Design by Adaptie Power Control

The first order design constraint in dense packaged clusters is power consumption. The currently developed cluster systems are conservatively designed so that the expected peak power does not exceed the power limit. However, practical power consumption seldom reaches the peak power. In this paper, we propose a new approach to design a high performance cluster system by an adaptive power control technique. Our approach is to integrate many computation nodes into a system whose total theoretical peak power exceeds the limit and to control runtime effective power by optimizing the number of working nodes and/or the clock frequency of the processors. We show the algorithm of the adaptive power control and performance evaluation by using a real cluster system. Evaluation results show that our proposed approach greatly improves performance as large as 46% compared to a conventional cluster system.

[1]  Wu-chun Feng,et al.  A Feasibility Analysis of Power Awareness in Commodity-Based High-Performance Clusters , 2005, 2005 IEEE International Conference on Cluster Computing.

[2]  Feng Pan,et al.  Exploring the energy-time tradeoff in MPI programs on a power-scalable cluster , 2005, 19th IEEE International Parallel and Distributed Processing Symposium.

[3]  Karthick Rajamani,et al.  A performance-conserving approach for reducing peak power consumption in server systems , 2005, ICS '05.

[4]  Wu-chun Feng,et al.  High-Density Computing: A 240-Processor Beowulf in One Cubic Meter , 2002, ACM/IEEE SC 2002 Conference (SC'02).

[5]  David H. Bailey,et al.  The Nas Parallel Benchmarks , 1991, Int. J. High Perform. Comput. Appl..

[6]  Karthick Rajamani,et al.  Dynamic Processor Overclocking for Improving Performance of Power-Constrained Systems , 2005 .

[7]  Ramakrishna Kotla,et al.  Scheduling processor voltage and frequency in server and cluster systems , 2005, 19th IEEE International Parallel and Distributed Processing Symposium.

[8]  David K. Lowenthal,et al.  Minimizing execution time in MPI programs on an energy-constrained, power-scalable cluster , 2006, PPoPP '06.

[9]  David F. Heidel,et al.  An Overview of the BlueGene/L Supercomputer , 2002, ACM/IEEE SC 2002 Conference (SC'02).

[10]  David K. Lowenthal,et al.  Using multiple energy gears in MPI programs on a power-scalable cluster , 2005, PPoPP.

[11]  David K. Lowenthal,et al.  Just In Time Dynamic Voltage Scaling: Exploiting Inter-Node Slack to Save Energy in MPI Programs , 2005, ACM/IEEE SC 2005 Conference (SC'05).

[12]  Rong Ge,et al.  Power and energy profiling of scientific applications on distributed systems , 2005, 19th IEEE International Parallel and Distributed Processing Symposium.

[13]  Margaret Martonosi,et al.  Runtime Power Monitoring in High-End Processors: Methodology and Empirical Data , 2003, MICRO.

[14]  Jian Li,et al.  Dynamic power-performance adaptation of parallel computation on chip multiprocessors , 2006, The Twelfth International Symposium on High-Performance Computer Architecture, 2006..

[15]  Taisuke Boku,et al.  Measurement and characterization of power consumption of microproce-sors for power-aware cluster , 2004 .

[16]  S. Matsuoka,et al.  MegaProto: 1 TFlops/10kW Rack Is Feasible Even with Only Commodity Technology , 2005, ACM/IEEE SC 2005 Conference (SC'05).

[17]  Rong Ge,et al.  Improvement of power-performance efficiency for high-end computing , 2005, 19th IEEE International Parallel and Distributed Processing Symposium.

[18]  Wu-chun Feng,et al.  A Power-Aware Run-Time System for High-Performance Computing , 2005, ACM/IEEE SC 2005 Conference (SC'05).