CS8163: Parallel and Distributed Scientific Computing

• Instructor: Ed Luke
• Office: Butler 330 (Engineering Research Center 220)
• Office Hours: 3:15-5:00pm M W Butler 330 (Or by appointment)
• Meeting Place: Butler 104
• Meeting Time: 2:00pm-3:15pm M W
• Web Site: http://www.cs.msstate.edu/~luke/Courses/fl02/CS8163
• Instructor E-Mail: luke@cs.msstate.edu
• Course Topics:
• High Performance Techniques for Modern Serial Processors
• Models for Cache Performance and Memory Hierarchy
• Cache Oblivious Algorithms
• Compiler Optimization Issues
• Self Tuning Libraries
• Template Meta-Programming
• Domain Specific Compiler Approaches
• High Performance Techniques for Parallel Processors
• Parallel Models (Programming and Performance)
• Advanced Load Balancing Techniques
• Advanced Adaptive, Dynamic and Irregular Parallel Algorithms:
• Convex Hull
• Delaunay Triangulation
• Graph and Search Algorithms
• Advanced Numerical Methods
• Sparse Linear System Solvers
• N-Body Modeling
• Fourier Transform
• Required Text: Introduction to Parallel Computing by Vipin Kumar et. al. (Second edition when available)
• References
• Class Notes
• Grading:
• Two Research Projects : 50%
• First Project: High Performance Dense Matrix Multiplication
• Individual Effort
• Topics: Cache aware and cache oblivious algorithms, template meta-programming
• Due Date: October 9th, 2pm (No Late Submissions allowed!)
• Second Project: High Performace, Parallel, N-Body Simulations
• Group Project
• Topics: Parallel Algorithms, Parallel Convex Hull, Parallel Random Number Generation, Robust Geometric Predicate (HPC Implementations of), Load Balancing
• Due Date: December 4th, 2002
• Two Exams: 50%
• First Exam: Covers Serial Performance Optimization
• Topics: Cache Oblivious Algorithms, template metaprogramming, FFTW, sparse matrix-vector multiply
• Date: October 21, 2002
• Second Exam: Advanced Parallel Programming Techniques
• Topics: TBA
• Date: TBA
• Research Project Grading Policy:
• Project Report: This is a research project, not just a programming assignment. I expect to receive, in addition to any program source developed, a comprehensive report that documents:
• Background Material Researched in Support of the Project
• Techniques and Methods used in the Report
• Results presented in sufficient detail that the results are reproduce-able from the description
• Analysis: What are the lessons learned. What general principles can be observed from the results.
• ALL NON-ORIGINAL work must be cited!
• No mercy will be given to students that submit plagiarized material. Any student that submits the work of others represented as their own will face disciplinary sanctions!
• Academic Honesty:
• The Departmental policy is a must-reading for all students.
• All web material used should be acknowledged otherwise you are culpable
• Remember, if caught -- NO EXCEPTIONS, NO MERCY.
• Submission: E-mail attachments sent to luke@cs.msstate.edu
• No Late Submission, submit what you have by the due date.
• Submit all source and include files and makefiles
• Do not submit binaries PLEASE !!!