In partial fulfillment of the Requirements for the Degree of
Master of Science
Jun Lang
will defend his thesis
THE OPENMP VERSION OF POP
Abstract
OpenMP has emerged as the most popular standard for shared memory parallel
programming in the past ten years. In this thesis, we parallelize POP - Parallel Ocean
Program - from Los Alamos National Laboratory with OpenMP and achieve superior
performance. We explore an efficient and safe way to use OpenMP with non-trivial
structured Fortran 90 applications, discuss the data transfer problem between the cache
and the memory of a shared memory platform, and provide a good solution.
Date: Tuesday, November 26, 2002
Time: 11:00 AM
Place: 550-PGH
Faculty, students, and the general public are invited.
Thesis Advisor: Dr.Chapman, Barbara Mary