The Community for Technology Leaders
2013 42nd International Conference on Parallel Processing (2007)
Xi'an, China
Sept. 10, 2007 to Sept. 14, 2007
ISSN: 0190-3918
ISBN: 0-7695-2933-X
pp: 18
Rong Ge , Virginia Tech, USA
Wu-chun Feng , Virginia Tech, USA
Xizhou Feng , Virginia Tech, USA
Kirk W. Cameron , Virginia Tech, USA
Performance and power are critical design constraints in today?s high-end computing systems. Reducing power consumption without impacting system performance is a challenge for the HPC community. We present a runtime system (CPU MISER) and an integrated performance model for performance-directed, power-aware cluster computing. CPU MISER supports system-wide, application-independent, fine-grain, dynamic voltage and frequency scaling (DVFS) based power management for a generic power-aware cluster. Experimental results show that CPU MISER can achieve as much as 20% energy savings for the NAS parallel benchmarks. In addition to energy savings, CPU MISER is able to constrain performance loss for most applications within user-specified limits. These constraints are achieved through accurate performance modeling and prediction, coupled with advanced control techniques.
Rong Ge, Wu-chun Feng, Xizhou Feng, Kirk W. Cameron, "CPU MISER: A Performance-Directed, Run-Time System for Power-Aware Clusters", 2013 42nd International Conference on Parallel Processing, vol. 00, no. , pp. 18, 2007, doi:10.1109/ICPP.2007.29
96 ms
(Ver 3.3 (11022016))