GreenFaaS: Maximizing Energy Efficiency of HPC Workloads with FaaS

• DOI: 10.48550/arxiv.2406.17710
• Publication Date: 2024-06-25
• Authors: Alok Kamatar; Valérie Hayot-Sasson; Yadu Babuji; André Bauer; Gourav Rattihalli; Ninad Hogade; Dejan Milojičić; Kyle Chard; Ian Foster
• Keywords: FOS: Computer and information sciences; Computer Science - Distributed, Parallel, and Cluster Computing; Distributed, Parallel, and Cluster Computing (cs.DC)

Application energy efficiency can be improved by executing each application component on the compute element that consumes least while also satisfying time constraints. In principle, function as a service (FaaS) paradigm should simplify such optimizations abstracting away location, but existing FaaS systems do not provide for user transparency over consumption or task placement. Here we present GreenFaaS, novel open source framework bridges this gap between energy-efficient applications and platforms. GreenFaaS deployed end users providers across to monitor use, task-specific feedback, schedule tasks in an energy-aware manner. We demonstrate intelligent placement of both reduce improve performance. For synthetic workload, reduces energy-delay product 45% compared alternatives. Furthermore, running molecular design through 21% runtime 63% better matching with machines.