Online frequency-based performance and power estimation for clustered multi-processor systems

doi:10.1016/j.compeleceng.2021.106971

Online frequency-based performance and power estimation for clustered multi-processor systems

2021-03-01

5

OA

AI

Iraklis Anagnostopoulos

DOI：10.1016/j.compeleceng.2021.106971

原文链接

查看原文

摘要

En 中文

Modern Chip Multi-Processors (CMPs) are required to be increasingly power efficient while also offering higher performance and lower costs. A combination of Dynamic Voltage?Frequency Scaling (DVFS) and sophisticated resource-aware scheduling is needed to address the underlying problem of maximizing performance-per-Watt of CMP architectures. In this paper, we propose a methodology to predict the power consumption and performance for groups of concurrently executing applications at all available frequencies of a CMP. The methodology uses a combina-tion of hardware-based application profiling, contention-aware scheduling, and artificial neural networks. Experimental results on an Odroid-XU3 board demonstrate an increase in average performance per Watt of 30.5% (A15 cluster) and 11.4% (A7 cluster) over Linux?s Completely Fair Scheduler (CFS) and power governors. In addition, our methodology outperforms three state-of-the-art resource managers, yielding the highest performance per Watt in all evaluated use cases. Modern Chip Multi-Processors (CMPs) are required to be increasingly power efficient while also offering higher performance and lower costs. A combination of Dynamic Voltage?Frequency Scaling (DVFS) and sophisticated resource-aware scheduling is needed to address the underlying problem of maximizing performance-per-Watt of CMP architectures. In this paper, we propose a methodology to predict the power consumption and performance for groups of concurrently executing applications at all available frequencies of a CMP. The methodology uses a combina-tion of hardware-based application profiling, contention-aware scheduling, and artificial neural networks. Experimental results on an Odroid-XU3 board demonstrate an increase in average performance per Watt of 30.5% (A15 cluster) and 11.4% (A7 cluster) over Linux?s Completely Fair Scheduler (CFS) and power governors. In addition, our methodology outperforms three state-of-the-art resource managers, yielding the highest performance per Watt in all evaluated use cases.

Keyword:

Power-efficient scheduling

Performance per watt

Chip multi-processors

Performance-aware scheduling

Neural networks

Online frequency-based performance and power estimation for clustered multi-processor systems

摘要

AI总结

期刊

机构

引用论文