A breadth-first course in multicore and manycore programming

Abstract

The technique of scaling hardware performance through increasing the number of cores on a chip requires programmers to learn to write parallel code that can exploit this hardware. In order to expose students to a variety of multicore programming models, our university offered a breadth-first introduction to multicore and manycore programming for upper-level undergraduates. Our students gained programming experience with three different parallel programming models, two of which are less than five years old and targeted specifically to multicore and manycore computing. Assessments throughout the semester showed that the course gave students a broad base of experience from which they will be able to understand ongoing developments in the field.

Practical parallel and concurrent programming

“…Since there is not a clear consensus on whether any one parallel or concurrent programming model will emerge as a clear winner [22], we feel that students should be exposed to a variety of paradigms and topics. This course is tilted towards shared memory systems with multiple threads, since we feel it is important to prepare students to succeed in this common case.…”

“…Suzanne Rivore [22] presents a breadth-first course in multicore programming. This course is an upper-division elective which covers three different paradigms: shared memory with OpenMP, pattern-based parallel programming with Intel's Thread Building Blocks (TBB), and a graphics processors (GPU) programming model with nVidia's CUDA library.…”

Strategies for preparing computer science students for the multicore world

“…As another example, if students have already used OpenMP to implement data parallel solutions, they should more easily be able to consider message-passing solutions to problems requiring sophisticated task-parallel solutions, using any of a variety of tools, such as MPI or TBB. Rivoire describes an advanced undergraduate course that integrates several of these technologies [104].…”

Using clusters in undergraduate research: Distributed animation rendering, photo processing, and image transcoding

“…At some colleges, these topics are integrated directly into existing core courses such as CSI or CS2 [6], while at other institutions the topics may be offered in an upper level elective [7]. The focus of these efforts is not to teach any one particular technology or approach, but to instill an understanding of the fundamentals of parallel and distributed computing.…”