To cite the library itself, please use:
@software{p3-analysis-library,
author = {Pennycook, S. John and
Sewall, Jason and
Jacobsen, Douglas and
Deakin, Tom and
Zamora, Yuliana and
Lee, Kin Long Kelvin},
title = {{Performance, Portability and Productivity Analysis
Library}},
month = mar,
year = 2023,
publisher = {Zenodo},
doi = {10.5281/zenodo.7733678},
url = {https://doi.org/10.5281/zenodo.7733678}
}
Additional DOIs are generated for each release.
Some of the functionality implemented by the P3 Analysis Library was first introduced in academic papers, as detailed below.
The performance portability metric is discussed in the following papers:
- S.J. Pennycook, J.D. Sewall and V.W. Lee, "A Metric for Performance Portability", in Proceedings of the 7th International Workshop in Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems (PMBS), 2016
- S.J. Pennycook, J.D. Sewall and V.W. Lee, "Implications of a Metric for Performance Portability", in Future Generation Computer Systems, Volume 92, March 2019, Pages 947-958
- S.J. Pennycook and J.D. Sewall, "Revisiting a Metric for Performance Portability", in Proceedings of the IEEE/ACM International Workshop on Performance, Portability and Productivity in HPC (P3HPC), 2020
The code divergence metric is based on the one proposed in the following paper:
- S.L. Harrell, J. Kitson, et al., "Effective Performance Portability", in Proceedings of the IEEE/ACM International Workshop on Performance, Portability and Productivity in HPC (P3HPC), 2018
Cascade plots were first introduced in the following paper:
- J.D. Sewall, S.J. Pennycook, D. Jacobsen, T. Deakin and S. McIntosh-Smith, "Interpreting and Visualizing Performance Portability Metrics", in Proceedings of the IEEE/ACM International Workshop on Performance, Portability and Productivity in HPC (P3HPC), 2020
The end-to-end P3 analysis workflow was first described in the following article:
- S.J. Pennycook, J.D. Sewall, D. Jacobsen, T. Deakin and S. McIntosh-Smith, "Navigating Performance Portability", in Computing in Science & Engineering, Volume: 23, Issue: 5, 01 Sept.-Oct. 2021