DMCA
Power-aware and Temperature Restrain Modeling for Maximizing Performance and Reliability
BibTeX
@MISC{Kale_power-awareand,
author = {Laxmikant V. Kale and Akhil Langer and Osman Sarood},
title = {Power-aware and Temperature Restrain Modeling for Maximizing Performance and Reliability},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Ability to constrain power consumption in the recent hard-ware architectures is a powerful capability that can be lever-aged for efficient utilization of available power. We propose to develop power-aware performance models that can pre-dict job performance given a resource configuration, that is, the CPU/memory power cap, the number of nodes, etc. In addition to performance optimization under a fixed power budget, our proposed model also alleviates the difference in thermal profiles amongst different processors to achieve a balance in the overall temperature distribution of the data center. Reduced temperature of operation improves the re-liability of the system in addition to saving cooling energy of the data center, while minimizing the overall execution time of the jobs. The power-aware performance model can be used to determine the optimal resource configurations for a job or for a set of jobs, with the aim of efficient utilization of power.
Keyphrases
temperature restrain modeling maximizing performance power-aware performance model efficient utilization data center job performance overall temperature distribution resource configuration powerful capability overall execution time cpu memory power cap available power optimal resource configuration performance optimization thermal profile fixed power budget power consumption reduced temperature different processor recent hard-ware architecture
