Journal of Computer and Communications
To improve the power consumption of parallel applications at the runtime, modern processors provide frequency scaling and power limiting capabilities. In this work, a runtime strategy is proposed to distribute a given power allocation among the cluster nodes assigned to the application while balancing their performance change. The strategy operates in a timeslice-based manner to estimate the current application performance and power usage per node followed by power redistribution across the nodes. Experiments, performed on four nodes (112 cores) of a modern computing platform interconnected with Infiniband showed that even a significant power budget reduction of 20% may result in a performance degradation of as low as 1% under the proposed strategy compared with the execution in the unlimited power case
Copyright © 2020 by Authors and Scientific Research Publishing Inc.
This work is licensed under the Creative Commons Attribution 4.0 International (CC BY 4.0) License.
Original Publication Citation
Sundriyal, V., & Sosonkina, M. (2020). Distributed strategy for power re-allocation in high performance applications. Journal of Computer and Communications, 8(12), 142-158. https://doi.org/10.4236/jcc.2020.812014
Sundriyal, Vaibhav and Sosonkina, Masha, "Distributed Strategy for Power Re-Allocation in High Performance Applications" (2020). Electrical & Computer Engineering Faculty Publications. 352.