Parallel Processing Course Plan
Parallel Processing Course Plan
Parallel Processing
S. Lakshmivarahan
School of Computer Science
University of Oklahoma
Norman, OK 73019 - USA
[email protected]
1) Course Outline:
Topics 1. Need for super computers, Grand challenges, Technology vs. architecture, Greater computing
power through parallelism in architecture, A classification of Parallel architectures.
Topic 2. Detailed discussion of shared vs. distributed memory architectures, Hardware architectural
back bone, Cayley graph based architectures - Rings, Toroids, Binary hypercube
Topic 4: Graph embedding as a means for porting algorithms across architectures, optimal embedding,
embedding of rings, toroids, binary trees into binary hypercube
Topic 5: Performance measures - speed up, processor efficiency, effect of communication on speed up
and efficiency, Parallel Complexity class
Topic 6: Examples of Parallel algorithm design - sorting, prefix problem, matrix problems, etc.
2. Modus Operandi:
IUCEE short course protocol calls four lectures each day for five days - a total of twenty lectures in all,
typically from Monday through Friday of a week. The four lectures on a given day are divided into two
in the morning and two in the afternoon with ample time for coffee breaks and lunch break to facilitate
good time for interaction. Each lecture may span for about 75 minutes with ample time for Q& A.
3. Course Material: The course will be based on the following two books on this topic:
1. S. Lakshmivarahan and S. K. Dhall (1990) Analysis and Design of Parallel Algorithms: arithmetic and
matrix problems, McGraw Hill, New York, 657 pages
2. S. Lakshmivarahan and S. K. Dhall (1994) Parallel Computing using the Prefix Problem, Oxford
University Press, New York, 294 pages