edoc

Reproducible experiments in parallel computing: concepts and stencil compiler benchmark study

Burkhart, Helmar and Guerrera, Danilo and Maffia, Antonio. (2014) Reproducible experiments in parallel computing: concepts and stencil compiler benchmark study. In: Euro-Par 2014: Parallel Processing Workshops : Euro-Par 2014 International Workshops, Porto, Portugal, August 25-26, 2014 ; revised selected papers, Part 1. Cham, pp. 464-474.

Full text not available from this repository.

Official URL: http://edoc.unibas.ch/dok/A6357887

Downloads: Statistics Overview

Abstract

For decades, the majority of the experiments on parallel computers have been reported at conferences and in journals usually without the possibility to verify the results presented. Thus, one of the major principles of science, reproducible results as a kind of correctness proof, has been neglected in the field of experimental high-performance computing. While this is still the state-of-the-art, current research targets for solutions to this problem. We discuss early results regarding reproducibility from a benchmark case study we did. In our experiments we explore the class of stencil calculations that are part of many scientific kernels and compare the performance results of four stencil compilers. In order to make these experiments reproducible from remote, a first prototype of an replication engine has been developed that can be accessed via the internet.
Faculties and Departments:05 Faculty of Science > Departement Mathematik und Informatik > Ehemalige Einheiten Mathematik & Informatik > High Performance and Web Computing (Burkhart)
UniBasel Contributors:Burkhart, Helmar
Item Type:Conference or Workshop Item, refereed
Conference or workshop item Subtype:Conference Paper
Publisher:Springer
Note:Publication type according to Uni Basel Research Database: Conference paper
Related URLs:
Identification Number:
Last Modified:08 Aug 2019 14:17
Deposited On:03 Jul 2015 08:53

Repository Staff Only: item control page