ECE Research on Energy-Efficient Serverless Computing Recognized at SC25
ECE Associate Professor Devesh Tiwari’s research group received the Best Paper Finalist honor at The International Conference for High Performance Computing, Networking, Storage, and Analysis (SC25), the premier international conference for High Performance Computing (HPC). The paper, “GreenMix: Energy-Efficient Serverless Computing via Randomized Sketching on Asymmetric Multi-Cores,” presents a novel technique to significantly improve energy efficiency in modern serverless computing systems. The SC (Supercomputing) conference draws over 16,000 global attendees and is the flagship event for the HPC community.
Abstract:
GreenMix is motivated by the renewed interest in asymmetric multi-core processors and the emergence of the serverless computing model. Asymmetric multi-cores offer better energy and performance trade-offs by placing different core types on the same die. However, existing serverless scheduling techniques do not leverage these benefits. GreenMix is the first serverless work to reduce energy and serverless keep-alive costs while meeting QoS targets by leveraging asymmetric multi-cores. GreenMix employs randomized sketching, tailored for serverless function execution and keep-alive, and leverages processor asymmetry, to perform within 10% of the optimal solution in terms of energy efficiency and keep-alive cost reduction. GreenMix’s effectiveness is demonstrated through evaluations with production-grade serverless function invocation traces on different clusters made up of ARM big.LITTLE and Intel Alder asymmetric multi-core processors. GreenMix outperforms competing serverless frameworks and asymmetric core-aware schedulers, offering a novel approach for energy-efficient serverless computing.