2019/11/12 by Mehrzad Nejat, Madhavan Manivannan, Nejat, Mehrzad +5
Computer Science · #Cloud Computing and Resource Management #FOS: Computer and information sciences #Hardware Architecture (cs.AR) #Interconnection Networks and Systems #Parallel Computing and Optimization Techniques
paper · pdf · doi:10.48550/arxiv.1911.05101
openalex publication_date 2019/11/12 · openalex created_date 2022/07/26 · openalex updated_date 2026/07/28
Reducing the energy expended to carry out a computational task is important.\nIn this work, we explore the prospects of meeting Quality-of-Service\nrequirements of tasks on a multi-core system while adjusting resources to\nexpend a minimum of energy. This paper considers, for the first time, a\nQoS-driven coordinated resource management algorithm (RMA) that dynamically\nadjusts the size of the per-core last-level cache partitions and the per-core\nvoltage-frequency settings to save energy while respecting QoS requirements of\nevery application in multi-programmed workloads run on multi-core systems. It\ndoes so by doing configuration-space exploration across the spectrum of LLC\npartition sizes and Dynamic Voltage Frequency Scaling (DVFS) settings at\nruntime at negligible overhead. We show that the energy of 4-core and 8-core\nsystems can be reduced by up to 18% and 14%, respectively, compared to a\nbaseline with even distribution of cache resources and a fixed mid-range core\nvoltage-frequency setting. The energy savings can potentially reach 29% if the\nQoS targets are relaxed to 40% longer execution time.\n