Peachy Parallel Assignments (EduHPC 2021)

Written with Henri Casanova, Rafael Ferreira da Silva, Arturo Gonzalez-Escribano, Herman Li, and Yuri Torres.
Proceedings of the Workshop on Education for High-Performance Computing (EduHPC), 2021.


Abstract:

Peachy Parallel Assignments are high-quality assign- ments that are easy for other instructors to adopt and use in their own classes. They are selected competitively for presentation at the Edu* workshops based on ease of adoption and how "cool and inspirational" they are for students. The goals are to excite students about PDC, to save faculty the time and risk associated with creating new assignments, and to recognize faculty who create awesome assignments for their students.

In this paper, we present two assignments. The first assignment is a simulation of air flow in a wind tunnel, which students parallelize using OpenMP, MPI, and CUDA to illustrate the different techniques needed for these paradigms. The second assignment is a series of exercises to teach students the principles of batch scheduling and how to interact with a batch scheduler to submit parallel jobs. It uses simulation to allow students to quickly see the results of their decisions and to support revisiting an earlier decision.