Energy-Efficient Heterogenous Computing with SYNERGY
Energy-efficient computing aims to maximize the energy efficiency of computing systems. A key approach in modern parallel hardware is frequency scaling, enabled by Dynamic Voltage and Frequency Scaling. AMD, Intel, and NVIDIA GPUs provide APIs for power management and core frequency adjustment. Leveraging these capabilities allows optimizing both performance and energy consumption in GPU programs. In this presentation, Biagio will introduce SYnergy, a novel energy-efficient approach based on SYCL that leverages on frequency scaling to achieve unprecedented fine-grained energy savings on large-scale heterogeneous clusters. SYnergy was recently accepted for publication at SuperComputing 2023 and has been installed at CINECA Supercomputing.
Speaker(s)
Biagio Cosenza - University of Salerno/Assistant Professor
Biagio is an Assistant Professor in the Department of Computer Science at the University of Salerno, Italy. He joined the University in August 2019 through a national brain gain program and received the Abilitazione for Italian Associate Professorship. From 2015 to 2019, he was Senior Researcher at TU Berlin, Germany, where he was Principal Investigator for the DFG project Celerity and received the Habilitation from the Faculty IV. From 2011 to 2015, he was Postdoctoral researcher at the University of Innsbruck, Austria, contributing to the Insieme Compiler project and the DK-Plus multidisciplinary platform for Scientific Computing. His research is currently funded by the European HPC Joint Undertaking (LIGATE project), the Italian Ministry of Research (LibreRT project, PRIN 2022), and several industrial projects. Biagio’s main research interests are in high performance computing, programming models, compiler technology, optimization and tuning.
