This paper describes the design and implementation of MATLAB*G, a parallel MATLAB on the ALiCE Grid. ALiCE (Adaptive and scaLable internet-based Computing Engine), developed at NUS, is a lightweight grid-computing middleware. Grid applications in ALiCE are written in Java and use the distributed shared memory programming model. Utilizing existing MATLAB functions, MATLAB*G provides distributed matrix computation to the user through a set of simple commands. Currently two forms of parallelism for distributed matrix computation are implemented: task parallelism and job parallelism. Experiments are carried out to investigate the performance of MATLAB*G on each type of parallelism. Results indicate that for large matrix sizes MATLAB*G can be a faster alternative to sequential MATLAB. / Singapore-MIT Alliance (SMA)
Identifer | oai:union.ndltd.org:MIT/oai:dspace.mit.edu:1721.1/3863 |
Date | 01 1900 |
Creators | Chen, Ying, Tan, Suan Fong |
Source Sets | M.I.T. Theses and Dissertation |
Language | en_US |
Detected Language | English |
Type | Article |
Format | 89158 bytes, application/pdf |
Relation | Computer Science (CS); |
Page generated in 0.0011 seconds