Distributed Strategy for Power Re-Allocation in High Performance Applications

• 作者: Masha Sosonkina Vaibhav Sundriyal
• 来源期刊: 电脑和通信(英文)
• 学科: 工学
• 关键词: Multinode Power Allocation RAPL UFS DVFS Maximizing Performance Component Power
• 年，卷（期）: 2020,（12）
• 页码范围: 142-158
• 页数: 17页
• 分类号: TP3

摘要

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.