An Educational Module Illustrating How Sparse Matrix-Vector Multiplication on Parallel Processors Connects to Graph Partitioning

Conference paper

DOI: 10.1007/978-3-319-27308-2_12

Part of the Lecture Notes in Computer Science book series (LNCS, volume 9523)
Cite this paper as:
Rostami M.A., Bücker H.M. (2015) An Educational Module Illustrating How Sparse Matrix-Vector Multiplication on Parallel Processors Connects to Graph Partitioning. In: Hunold S. et al. (eds) Euro-Par 2015: Parallel Processing Workshops. Euro-Par 2015. Lecture Notes in Computer Science, vol 9523. Springer, Cham

Abstract

The transition from a curriculum without parallelism topics to a re-designed curriculum that incorporates such issues can be a daunting and time-consuming process. Therefore, it is beneficial to complement this process by gradually integrating elements from parallel computing into existing courses that were previously designed without parallelism in mind. As an example, we propose the multiplication of a sparse matrix by a dense vector on parallel computers with distributed memory. A novel educational module is introduced that illustrates the intimate connection between distributing the data of the sparse matrix-vector multiplication to parallel processes and partitioning a suitably defined graph. This web-based module aims at better involving undergraduate students in the learning process by a high level of interactivity. It can be integrated into any course on data structures with minimal effort by the instructor.

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.Institute for Computer ScienceFriedrich Schiller UniversityJenaGermany
  2. 2.Michael Stifel Center Jena for Data-Driven and Simulation ScienceJenaGermany

Personalised recommendations