Stem Intiative

Algorithm Optimization and High Performance Parallel Computing with Multi-Core Machines

Student(s):  Cedric Carter, North Carolina A&T State University


SALSA project is funded by Microsoft research to investigate new programming models of parallel multicore computing and Cloud/Grid Computing. It aims at developing and applying parallel and distributed Cyberinfrastructure to support large scale data analysis. Cedric Cater choses to work on algorithm optimization and performance measurements of parallel pairwise algorithm, which includes parallel matrix multiplication and eigenvector calculation using MPI. This sub-project work synergistically as parts of SALSA project as data scalable data analysis research in Grid, biomedicine and particle physics. One of the main goals in this age is to process huge chunks of data, Gigabytes 1 x 10^9 bytes, Terabytes 1 x 10^12 bytes, and Petabytes 1 x 10^15 bytes, in a short amount of time. One technique used for this process is to develope programs in parallel using MPI. MPI, Message Passing Interface, is a library specification for core message-passing, proposed as a standard by a broadly based committee of vendors, implementers, and users. For technical computing, MPI has displaced most other message-passing systems.