AlgoWiki Project as an Extension of the Top500 Methodology

Alexander S Antonov, Jack Dongarra, Vladimir Voevodin

Abstract


The AlgoWiki project is dedicated to describing the parallel structure and key features of various algorithms. The descriptions are intended to provide complete information about algorithm's properties, which are needed to adequately assess their implementation efficiency for any computing platform. This work sets out the key areas for further development of the project which were recently developed based on working with the AlgoWiki encyclopedia. We are suggesting an approach to extend the Top500 methodology, which is commonly used to compare various computing platforms.


Full Text:

PDF

References


Press, W., Teukolsky, S.A., Vetterling, W.T., Flannery, B.P.: Numerical Recipes in C. Cambridge University Press, second edition, 1992.

Barrett, R., Berry, M., Chan, T.F., Demmel, J, Donato, J., Dongarra, J., Eijkhout, V., Pozo, R., Romine, C., Van der Vorst, H.: Templates for the Solution of Linear Systems: Building Blocks for Iterative Methods, 2nd Edition, SIAM, 1994. http://www.netlib.org/linalg/html_templates/Templates.html, accessed: 2018-03-22

List of algorithms, https://en.wikipedia.org/wiki/List_of_algorithms, accessed: 2018-03-22

Enabling AI in every Application, http://algorithmia.com/, accessed: 2018-03-22

ALGLIB, http://www.alglib.net/, accessed: 2018-03-22

A Library of Parallel Algorithms, http://www.cs.cmu.edu/~scandal/nesl/algorithms.html, accessed: 2018-03-22

Voevodin, Vl., Antonov, A., Dongarra, J.: AlgoWiki: an Open Encyclopedia of Parallel Algorithmic Features. Supercomputing Frontiers and Innovations, vol. 2, no. 1 (2015). pp. 4–18. http://dx.doi.org/10.14529/jsfi150101

Antonov, A., Voevodin, Vad., Voevodin, Vl., Teplov, A.: A Study of the Dynamic Characteristics of Software Implementation as an Essential Part for a Universal Description of Algorithm Properties. 24th Euromicro International Conference on Parallel, Distributed, and Network-Based Processing Proceedings, 17th–19th February 2016. pp. 359–363. DOI: 10.1109/PDP.2016.24

Voevodin, Vl., Antonov, A., Dongarra, J.: Why is it hard to describe properties of algorithms? Procedia Computer Science, vol. 101 (2016). pp. 4–7. http://dx.doi.org/10.1016/j.procs.2016.11.002

Dongarra, J.J., Bunch, J.R., Moler, G.B., Stewart, G.W.: LINPACK Users’ Guide. Society for Industrial and Applied Mathematics, 1979–1993.

Murphy, R.C., Wheeler, K.B., Barrett, B.W., Ang, J.A.: Introducing the Graph 500. Cray User’s Group (CUG), May 5, 2010, vol. 19, pp. 45–74.

Heroux, M., Dongarra, J.: Toward a New Metric for Ranking High Performance Computing Systems. UTK EECS Tech Report and Sandia National Labs Report SAND2013–4744, June 2013.

Shun, J., Blelloch, G.E.: Ligra: a lightweight graph processing framework for shared memory. ACM Sigplan Notices. vol. 48. no. 8. pp. 135–146. DOI: 10.1145/2517327.2442530

Beamer, S., Asanovi, K., Patterson, D.: The GAP Benchmark Suite. arXiv:1508.03619 [cs.DC], 2015.

Parallel Boost Graph Library, http://www.boost.org/doc/libs/1_51_0/libs/graph_parallel/doc/html/index.html, accessed: 2018-03-22




Publishing Center of South Ural State University (454080, Lenin prospekt, 76, Chelyabinsk, Russia)