ABSTRACT
In response to the shift to multicore processors, the ACM-IEEE CS2013 curriculum recommendations [1] include parallel and distributed computing (PDC) as a new core knowledge area. Some of the key concepts in PDC are the distinctions between shared-memory, distributed-memory, and heterogeneous system architectures.
Most CS educators would agree that providing students with hands-on experience improves their students' learning. Given the ubiquity of multicore processors, it is quite easy to give today's students hands-on experience developing software on shared-memory architectures. By contrast, providing students with hands-on experience developing software for distributed architectures has typically required access to a Beowulf cluster, the price of which was beyond the reach of many institutions. However, hardware manufacturers have recently begun producing a variety of inexpensive --system on a board multiprocessors. Creative CS educators are using these multiprocessors to design and build inexpensive Beowulf clusters, and using them to provide students with hands-on experience with shared-memory, distributed-memory, and heterogeneous computing paradigms.
In this special session, several PDC educators will bring, present, and demonstrate their innovative Beowulf clusters; each designed and built using a different inexpensive multiprocessor board.
- ACM/IEEE CS Joint Task Force. "Computer Science Curriculum 2013". Online. Accessed 2014-08-01. http://ai.stanford.edu/users/sahami/CS2013/.Google Scholar
- J. Adams and T. Brom. "Microwulf: A Beowulf Cluster for Every Desk", Proc. of the 39th SIGCSE Technical Symposium, March, 2008, p. 121--125, DOI= 10.1145/1352135.1352178. Google ScholarDigital Library
- Adapteva. "Parallella". Online, accessed 2014-08-01: http://www.adapteva.com/parallella/.Google Scholar
- R. Brown, L. Shoop, J. Adams. "CSinParallel: Parallel Computing in the CS Curriculum". Online, accessed 2014-08-01. http://csinparallel.org.Google Scholar
- CubieBoard. "CubieBoard2". Online, accessed 2014-08-01: http://cubieboard.org/.Google Scholar
- Hardkernel. "ODROID-U3". Online, accessed 2014-08-01: http://hardkernel.com.Google Scholar
- Nvidia. "Jetson-Tk1". Online, accessed 2014-08-01: https://developer.nvidia.com/jetson-tk1.Google Scholar
- C. Peck, et al. "LittleFe: Parallel and Cluster Computing On The Move". Online, accessed 2014-08-01: http://littlefe.net.Google Scholar
- Raspberry Pi Foundation. "Raspberry Pi". Online, accessed 2014-08-01: http://www.raspberrypi.org.Google Scholar
Index Terms
- Budget Beowulfs: A Showcase of Inexpensive Clusters for Teaching PDC
Recommendations
The Micro-Cluster Showcase: 7 Inexpensive Beowulf Clusters for Teaching PDC
SIGCSE '16: Proceedings of the 47th ACM Technical Symposium on Computing Science EducationJust as a micro-computer is a personal, portable computer, a micro-cluster is a personal, portable, Beowulf cluster. In this special session, six cluster designers will bring and demonstrate micro-clusters they have built using inexpensive single-board ...
Teaching shared memory parallel concepts with OpenMP (abstract only)
SIGCSE '14: Proceedings of the 45th ACM technical symposium on Computer science educationCurriculum 2013 brings parallelism into the CS curricular mainstream. This hands-on workshop is intended for faculty with little or no background in parallel computing. OpenMP is a platform independent, industry-standard library for shared-memory ...
Technology workshops by in-service teachers for pre-service teachers
SIGUCCS '01: Proceedings of the 29th annual ACM SIGUCCS conference on User servicesThis project was an initiative through university courses to have graduate in-service teachers, who have learned the use of technology for classroom instruction, offer workshops to undergraduate pre-service teachers. The goals of the project were two-...
Comments