Conference Paper

Teaching Model for Computational Science and Engineering Programme.

DOI: 10.1007/978-3-642-01973-9_5 Conference: Computational Science - ICCS 2009, 9th International Conference, Baton Rouge, LA, USA, May 25-27, 2009, Proceedings, Part II
Source: DBLP

ABSTRACT Computational Science and Engineering is an inherently multidisciplinary field, the increasingly important partner of theory
and experimentation in the development of knowledge. The Computer Architecture and Operating Systems department of the Universitat
Autònoma de Barcelona has created a new innovative masters degree programme with the aim of introducing students to core concepts
in this field such as large scale simulation and high performance computing. An innovative course model allows students without
a computational science background to enter this arena. Students from different fields have already completed the first edition
of the new course and positive feedback has been received from students and professors alike. The second edition is in development.

0 Bookmarks
 · 
82 Views
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Currently, the need to learn parallel applications topics in students has become an important issue due to the rapid growth in the parallel computing field. In fact, this topic has been included in Computer Science curriculum, but students present difficulties to design MPI parallel applications efficiently. We present a novel methodology for teaching parallel programming centered on improving parallel applications written by students through their experiences obtained during classes. The methodology integrates theoretical and practical sections which are focused on teaching two parallel paradigms, master/Worker and SPMD. These paradigms were selected due to their different communication and computation behaviors, which generate challenges for students when they wish to improve performance application metrics. Our methodology allows students to discover their own errors and how to correct them. In addition, students analyze the issues and advantages in the application designed in order to enhance the performance metrics. Applying this methodology gave us a significant progress in parallel applications designed by students, where we have observed an improvement of around 47% in the students’ skill about parallel programming when they design parallel applications.
    Procedia CS. 01/2010; 1(1):875-883.
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: A current challenge for computer users is to fully exploit performance of new Multicore systems. We propose a methodology for students in computational science to analyze the effect of memory hierarchy on application performance. The analysis is proposed in a experimental environment consisting of different systems with different configurations of memory hierarchy. New Multicore systems put tremendous pressure on memory hierarchy systems. The pressure is because, unfortunately, the effectiveness of the computing power offered by Multicore is affected by the data communications inter-chip and off-chip to the memory hierarchy, leading to significant problems in performance for many parallel applications. In the scope of computer science, it is important that students understand these problems. This methodology was successfully applied to students, where they acquired a significant improvement in their parallel application metrics assessment as was demonstrated in our evaluation.
    Procedia Computer Science 05/2010; 1:921-930.

Full-text (4 Sources)

Download
80 Downloads
Available from
Jun 4, 2014