Modern computers are capable of completing most of the tasks in fairly short time, however there are areas in what calculations can last for months and even years. Parallel algorithms are one of the ways to accelerate long-lasting calculations. In the thesis we analyze parallel computing technologies OpenMP (shared memory) and MPI (distributed memory), cons and pros of their architecture. We identify potential parts of program code of Curonian lagoon model for parallelizing, in which chosen parallel computing technologies OpenMP and MPI is applied. Also we make the runtime speedup analysis.
| Identifer | oai:union.ndltd.org:LABT_ETD/oai:elaba.lt:LT-eLABa-0001:E.02~2005~D_20050614_122654-32066 |
| Date | 14 June 2005 |
| Creators | Bliūdžiutė, Lina |
| Contributors | Andziulis, Arūnas, Denisov, Vitalij, Lupeikienė, Audronė, Razinkovas, Artūras, Ramašauskas, Olegas, Bielskis, Antanas Andrius, Klaipeda University |
| Publisher | Lithuanian Academic Libraries Network (LABT), Klaipeda University |
| Source Sets | Lithuanian ETD submission system |
| Language | Lithuanian |
| Detected Language | English |
| Type | Master thesis |
| Format | application/pdf |
| Source | http://vddb.library.lt/obj/LT-eLABa-0001:E.02~2005~D_20050614_122654-32066 |
| Rights | Unrestricted |
Page generated in 0.002 seconds