Assessing Application Efficiency and Performance Portability in Single-Source Programming for Heterogeneous Parallel Systems
PELAB, Department of Computer and Information Science, Linköping University, Linköping, Sweden
International Journal of Parallel Programming, 2022
@article{ernstsson2022assessing,
title={Assessing Application Efficiency and Performance Portability in Single-Source Programming for Heterogeneous Parallel Systems},
author={Ernstsson, August and Griebler, Dalvan and Kessler, Christoph},
journal={International Journal of Parallel Programming},
pages={1–22},
year={2022},
publisher={Springer}
}
We analyze the performance portability of the skeleton-based, single-source multi-backend high-level programming framework SkePU across multiple different CPU–GPU heterogeneous systems. Thereby, we provide a systematic application efficiency characterization of SkePU-generated code in comparison to equivalent hand-written code in more low-level parallel programming models such as OpenMP and CUDA. For this purpose, we contribute ports of the STREAM benchmark suite and of a part of the NAS Parallel Benchmark suite to SkePU. We show that for STREAM and the EP benchmark, SkePU regularly scores efficiency values above 80% and in particular for CPU systems, SkePU can outperform hand-written code.
December 11, 2022 by hgpu
