Performance of parallel FDTD method for shared- and distributed-memory architectures: Application tobioelectromagnetics
This work provides an in-depth computational performance study of the parallel finite-difference time-domain (FDTD) method. The parallelization is done at various levels including: shared- (OpenMP) and distributed- (MPI) memory paradigms and vectorization on three different architectures: Intel’s Kn...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2020-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7485784/?tool=EBI |
| _version_ | 1818260314678886400 |
|---|---|
| author | Miguel Ruiz-Cabello N. Maksims Abaļenkovs Luis M. Diaz Angulo Clemente Cobos Sanchez Franco Moglie Salvador G. Garcia Rashid Mehmood |
| author_facet | Miguel Ruiz-Cabello N. Maksims Abaļenkovs Luis M. Diaz Angulo Clemente Cobos Sanchez Franco Moglie Salvador G. Garcia Rashid Mehmood |
| author_sort | Miguel Ruiz-Cabello N. |
| collection | DOAJ |
| description | This work provides an in-depth computational performance study of the parallel finite-difference time-domain (FDTD) method. The parallelization is done at various levels including: shared- (OpenMP) and distributed- (MPI) memory paradigms and vectorization on three different architectures: Intel’s Knights Landing, Skylake and ARM’s Cavium ThunderX2. This study contributes to prove, in a systematic manner, the well-established claim within the Computational Electromagnetic community, that the main factor limiting FDTD performance, in realistic problems, is the memory bandwidth. Consequently a memory bandwidth threshold can be assessed depending on the problem size in order to attain optimal performance. Finally, the results of this study have been used to optimize the workload balancing of simulation of a bioelectromagnetic problem consisting in the exposure of a human model to a reverberation chamber-like environment. |
| first_indexed | 2024-12-12T18:29:22Z |
| format | Article |
| id | doaj.art-839b4660d94146f1923bd86170cea354 |
| institution | Directory Open Access Journal |
| issn | 1932-6203 |
| language | English |
| last_indexed | 2024-12-12T18:29:22Z |
| publishDate | 2020-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj.art-839b4660d94146f1923bd86170cea3542022-12-22T00:15:58ZengPublic Library of Science (PLoS)PLoS ONE1932-62032020-01-01159Performance of parallel FDTD method for shared- and distributed-memory architectures: Application tobioelectromagneticsMiguel Ruiz-Cabello N.Maksims AbaļenkovsLuis M. Diaz AnguloClemente Cobos SanchezFranco MoglieSalvador G. GarciaRashid MehmoodThis work provides an in-depth computational performance study of the parallel finite-difference time-domain (FDTD) method. The parallelization is done at various levels including: shared- (OpenMP) and distributed- (MPI) memory paradigms and vectorization on three different architectures: Intel’s Knights Landing, Skylake and ARM’s Cavium ThunderX2. This study contributes to prove, in a systematic manner, the well-established claim within the Computational Electromagnetic community, that the main factor limiting FDTD performance, in realistic problems, is the memory bandwidth. Consequently a memory bandwidth threshold can be assessed depending on the problem size in order to attain optimal performance. Finally, the results of this study have been used to optimize the workload balancing of simulation of a bioelectromagnetic problem consisting in the exposure of a human model to a reverberation chamber-like environment.https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7485784/?tool=EBI |
| spellingShingle | Miguel Ruiz-Cabello N. Maksims Abaļenkovs Luis M. Diaz Angulo Clemente Cobos Sanchez Franco Moglie Salvador G. Garcia Rashid Mehmood Performance of parallel FDTD method for shared- and distributed-memory architectures: Application tobioelectromagnetics PLoS ONE |
| title | Performance of parallel FDTD method for shared- and distributed-memory architectures: Application tobioelectromagnetics |
| title_full | Performance of parallel FDTD method for shared- and distributed-memory architectures: Application tobioelectromagnetics |
| title_fullStr | Performance of parallel FDTD method for shared- and distributed-memory architectures: Application tobioelectromagnetics |
| title_full_unstemmed | Performance of parallel FDTD method for shared- and distributed-memory architectures: Application tobioelectromagnetics |
| title_short | Performance of parallel FDTD method for shared- and distributed-memory architectures: Application tobioelectromagnetics |
| title_sort | performance of parallel fdtd method for shared and distributed memory architectures application tobioelectromagnetics |
| url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7485784/?tool=EBI |
| work_keys_str_mv | AT miguelruizcabellon performanceofparallelfdtdmethodforsharedanddistributedmemoryarchitecturesapplicationtobioelectromagnetics AT maksimsabalenkovs performanceofparallelfdtdmethodforsharedanddistributedmemoryarchitecturesapplicationtobioelectromagnetics AT luismdiazangulo performanceofparallelfdtdmethodforsharedanddistributedmemoryarchitecturesapplicationtobioelectromagnetics AT clementecobossanchez performanceofparallelfdtdmethodforsharedanddistributedmemoryarchitecturesapplicationtobioelectromagnetics AT francomoglie performanceofparallelfdtdmethodforsharedanddistributedmemoryarchitecturesapplicationtobioelectromagnetics AT salvadorggarcia performanceofparallelfdtdmethodforsharedanddistributedmemoryarchitecturesapplicationtobioelectromagnetics AT rashidmehmood performanceofparallelfdtdmethodforsharedanddistributedmemoryarchitecturesapplicationtobioelectromagnetics |