This class provides an introduction to parallel computing for graduate
students. We will cover selected topics in high-performance systems including:
contemporary architectures, interconnection topologies, shared memory and
message-passing systems, multi-threaded kernels, latency avoidance and
hiding techniques, methods for data and workload partitioning, performance
profiling, and debugging. We will also talk about how high performance
computing is being applied to commerical systems including parallel databases
and e-commerce applications.
"Integrity without knowledge is weak and useless, and knowledge without integrity is dangerous and dreadful." Samuel Johnson (The History of Rasselas, ch. 41 (1759)).
Please read the statement on academic integrity.
Every student will particpate in a 2-3 person teams on semester long projects. The projects will be different for each group and will be open-ended research style projects (several projects from the last time this class was offered resulted in publications).
This page will be updated throughout the class to provide online access to course materials. This page and the assignments and lecture notes attached to it are copyrighted. Use of these pages by individuals and for the class CMSC714 at the University of Maryland is permitted. Any other use requires permission of the author Jeffrey K. Hollingsworth