[Zurück]

A. Carpen-Amarie, A. Rougier, F. Lübbe:
"Stepping Stones to Reproducible Research: A Study of Current Practices in Parallel Computing";
Vortrag: 1st International Workshop on Reproducibility in Parallel Computing (REPPAR 2014) in conjunction with Euro-Par 2014, Porto Portugal; 25.08.2014 - 29.08.2014; in: "Euro-Par 2014: Parallel Processing Workshops - Euro-Par 2014 International Workshops, Revised Selected Papers, Part I, LNCS 8805", L. Lopes, J. Zilinskas, A. Costan, R. Cascella, G. Kecskemeti, E. Jeannot, M. Cannataro, L. Ricci, S. Benkner, S. Petit, V. Scarano, J. Gracia, S. Hunold, S. Scott, S. Lankes, C. Lengauer, J. Carretero, J. Breitbart, M. Alexander (Hrg.); Springer International Publishing, LNCS 8805 (2014), ISBN: 978-3-319-14324-8; S. 499 - 510.

Experimental research plays an important role in parallel computing, as in this field scientific discovery often relies on experimental findings, which complement and validate theoretical models. However, parallel hardware and applications have become extremely complex to study, due to their diversity and rapid evolution. Furthermore, applications are designed to run on thousands of nodes, often spanning across several programming models and generating large amounts of data. In this context, reproducibility is essential to foster reliable scientific results. In this paper we aim at studying the requirements and pitfalls of each stage of experimental research, from data acquisition to data analysis, with respect to achieving reproducible results. We investigate state-of-the-art experimental practices in parallel computing by conducting a survey on the papers published in EuroMPI 2013, a major conference targeting the MPI community. Our findings show that while there is a clear concern for reproducibility in the parallel computing community, a better understanding of the criteria for achieving it is necessary.

http://dx.doi.org/10.1007/978-3-319-14325-5_43