Towards Energy-Efficient Split Computing: A Hardware-Software Co-Design Perspective

This poster was presented at the poster session of EuroSys 2025, the European Conference on Computer Systems, held from March 30 to April 3, 2025, in Rotterdam, Netherlands. It visualizes our work on a hardware-software co-design framework for energy-efficient split computing on edge devices. The approach dynamically selects optimal configurations across the edge-cloud continuum to minimize energy consumption while satisfying latency constraints for machine learning inference. The poster accompanies our accepted extended abstract, which is available here.