|
NCSU Institutional Repository >
NC State Theses and Dissertations >
Dissertations >
Please use this identifier to cite or link to this item:
http://www.lib.ncsu.edu/resolver/1840.16/3229
|
| Title: | Modeling, Predicting, And Optimizing
Parallel Performance Of Grid Stuctured Problems |
| Authors: | Smith, Frank Anderson |
| Advisors: | Jeffrey S. Scroggs, Committee Member
Edward W. Davis, Committee Member
Rex A. Dwyer, Committee Member
Robert E. Funderlic, Committee Chair
Carla D. Savage, Committee Member |
| Keywords: | parallel performance
performance modeling
nearest neighbor communication
optimization |
| Issue Date: | 4-Jun-2004 |
| Degree: | PhD |
| Discipline: | Computer Science |
| Abstract: | The performance of parallel computers can be greatly affected by a user's choices of data distribution and logical processor configuration. Selecting optimal choices for such user specifiable parameters may be easier if the performance of the target machine can be predicted by a performance model. Models for parallel performance on the IBM SP for grid structured problems are considered. Such problems are ubiquitous in scientific computing and frequently are characterized by a nearest neighbor communication pattern. Bounds are derived for the size of the solution space of data distributions and logical processor configurations for problems with nearest neighbor communication. Proofs are derived that exclude a substantial number of non-optimal choices of data distribution and logical processor configuration. Algorithms are given that are intended to predict parallel performance for a model application and allow the user to select optimal choices for parameters that can be specified. Experimental evidence is presented that suggests that performance on the SP is characterized fairly accurately by a specific model. Experimental evidence also suggests that an algorithm exists to optimize a user's choices of data distribution and logical processor configuration for grid structured problems on the SP. |
| URI: | http://www.lib.ncsu.edu/resolver/1840.16/3229 |
| Appears in Collections: | Dissertations
|
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
|
