Performance evaluation of multidimensional parabolic type problems on distributed computing systems
Parabolic Partial Differential Equations (PDE) are well suited to multiprocessor implementation. However, the performance of a parallel program can be damaged by the mismatches between the parallelism available in the application and that available in the architecture. Communication cost, memory req...
Main Authors: | , , , , , , , |
---|---|
Format: | Conference or Workshop Item |
Published: |
2011
|
Subjects: |
_version_ | 1796858893780910080 |
---|---|
author | Che Teh, Che Rahim Islam, Md. Rajibul Satam, Noriza Alias, Norma Hamzah, Norhafiza Anwar, Rasiya Darwis, Roziha Abd. Ghaffar, Zarith Safiza |
author_facet | Che Teh, Che Rahim Islam, Md. Rajibul Satam, Noriza Alias, Norma Hamzah, Norhafiza Anwar, Rasiya Darwis, Roziha Abd. Ghaffar, Zarith Safiza |
author_sort | Che Teh, Che Rahim |
collection | ePrints |
description | Parabolic Partial Differential Equations (PDE) are well suited to multiprocessor implementation. However, the performance of a parallel program can be damaged by the mismatches between the parallelism available in the application and that available in the architecture. Communication cost, memory requirements, execution time, implementation cost, and others from a problem specific function should be considered to estimate a parallel program. In this paper, we present an optimizing technique called granularity analysis to evaluate the parallel algorithms particularly AGE families without degrading the performances. The resultant granularity analysis scheme is appropriate for developing adaptive parallelism of declarative programming languages on multiprocessors. The results recommend that the proposed method can be used for performance estimation of parallel programs. Red Black Gauss Seidel (GSRB) is selected as the benchmark for the differences numerical methods. |
first_indexed | 2024-03-05T19:19:08Z |
format | Conference or Workshop Item |
id | utm.eprints-46134 |
institution | Universiti Teknologi Malaysia - ePrints |
last_indexed | 2024-03-05T19:19:08Z |
publishDate | 2011 |
record_format | dspace |
spelling | utm.eprints-461342017-06-12T04:07:47Z http://eprints.utm.my/46134/ Performance evaluation of multidimensional parabolic type problems on distributed computing systems Che Teh, Che Rahim Islam, Md. Rajibul Satam, Noriza Alias, Norma Hamzah, Norhafiza Anwar, Rasiya Darwis, Roziha Abd. Ghaffar, Zarith Safiza QA Mathematics QA75 Electronic computers. Computer science QA76 Computer software Parabolic Partial Differential Equations (PDE) are well suited to multiprocessor implementation. However, the performance of a parallel program can be damaged by the mismatches between the parallelism available in the application and that available in the architecture. Communication cost, memory requirements, execution time, implementation cost, and others from a problem specific function should be considered to estimate a parallel program. In this paper, we present an optimizing technique called granularity analysis to evaluate the parallel algorithms particularly AGE families without degrading the performances. The resultant granularity analysis scheme is appropriate for developing adaptive parallelism of declarative programming languages on multiprocessors. The results recommend that the proposed method can be used for performance estimation of parallel programs. Red Black Gauss Seidel (GSRB) is selected as the benchmark for the differences numerical methods. 2011 Conference or Workshop Item PeerReviewed Che Teh, Che Rahim and Islam, Md. Rajibul and Satam, Noriza and Alias, Norma and Hamzah, Norhafiza and Anwar, Rasiya and Darwis, Roziha and Abd. Ghaffar, Zarith Safiza (2011) Performance evaluation of multidimensional parabolic type problems on distributed computing systems. In: The Sixteen IEEE Symposium On Computers And Communications (Iscc'11). http://dx.doi.org/ 10.1109/ISCC.2011.5984035 |
spellingShingle | QA Mathematics QA75 Electronic computers. Computer science QA76 Computer software Che Teh, Che Rahim Islam, Md. Rajibul Satam, Noriza Alias, Norma Hamzah, Norhafiza Anwar, Rasiya Darwis, Roziha Abd. Ghaffar, Zarith Safiza Performance evaluation of multidimensional parabolic type problems on distributed computing systems |
title | Performance evaluation of multidimensional parabolic type problems on distributed computing systems |
title_full | Performance evaluation of multidimensional parabolic type problems on distributed computing systems |
title_fullStr | Performance evaluation of multidimensional parabolic type problems on distributed computing systems |
title_full_unstemmed | Performance evaluation of multidimensional parabolic type problems on distributed computing systems |
title_short | Performance evaluation of multidimensional parabolic type problems on distributed computing systems |
title_sort | performance evaluation of multidimensional parabolic type problems on distributed computing systems |
topic | QA Mathematics QA75 Electronic computers. Computer science QA76 Computer software |
work_keys_str_mv | AT chetehcherahim performanceevaluationofmultidimensionalparabolictypeproblemsondistributedcomputingsystems AT islammdrajibul performanceevaluationofmultidimensionalparabolictypeproblemsondistributedcomputingsystems AT satamnoriza performanceevaluationofmultidimensionalparabolictypeproblemsondistributedcomputingsystems AT aliasnorma performanceevaluationofmultidimensionalparabolictypeproblemsondistributedcomputingsystems AT hamzahnorhafiza performanceevaluationofmultidimensionalparabolictypeproblemsondistributedcomputingsystems AT anwarrasiya performanceevaluationofmultidimensionalparabolictypeproblemsondistributedcomputingsystems AT darwisroziha performanceevaluationofmultidimensionalparabolictypeproblemsondistributedcomputingsystems AT abdghaffarzarithsafiza performanceevaluationofmultidimensionalparabolictypeproblemsondistributedcomputingsystems |