English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Computer science is also an experimental science. This is particularly thecase for parallel computing, which is in a total state of flux, and whereexperiments are necessary to substantiate, complement, and challengetheoretical modeling and analysis. Here, experimental work is as important asare advances in theory, that are indeed often driven by the experimentalfindings. In parallel computing, scientific contributions presented in researcharticles are therefore often based on experimental data, with a substantialpart devoted to presenting and discussing the experimental findings. As in allof experimental science, experiments must be presented in a way that makesreproduction by other researchers possible, in principle. Despite appearance tothe contrary, we contend that reproducibility plays a small role, and istypically not achieved. As can be found, articles often do not have asufficiently detailed description of their experiments, and do not makeavailable the software used to obtain the claimed results. As a consequence,parallel computational results are most often impossible to reproduce, oftenquestionable, and therefore of little or no scientific value. We believe thatthe description of how to reproduce findings should play an important part inevery serious, experiment-based parallel computing research article. We aim toinitiate a discussion of the reproducibility issue in parallel computing, andelaborate on the importance of reproducible research for (1) better and soundertechnical/scientific papers, (2) a sounder and more efficient review processand (3) more effective collective work. This paper expresses our current viewon the subject and should be read as a position statement for discussion andfuture work. We do not consider the related (but no less important) issue ofthe quality of the experimental design.

On the State and Importance of Reproducible Experimental Research in Parallel Computing