perun: Benchmarking Energy Consumption of High-Performance Computing Applications
Published in European Conference on Parallel Processing (Euro-Par), Springer, pp. 17–31, 2023
Understanding and reducing the energy footprint of high-performance computing applications is essential for sustainable AI and scientific computing. We introduce perun, an open-source tool for benchmarking the energy consumption of parallel and distributed applications across CPUs, GPUs, and full HPC nodes with minimal overhead. Perun provides fine-grained, reproducible energy measurements that support both individual researchers and larger-scale energy-efficiency studies.
Recommended citation: Gutiérrez Hermosillo Muriedas, J. P., Flügel, K., Debus, C., Obermaier, H., Streit, A., & Götz, M. (2023). "perun: Benchmarking Energy Consumption of High-Performance Computing Applications." In: European Conference on Parallel Processing. Springer, pp. 17–31.
Download Paper