2022
DOI: 10.1016/j.ascom.2021.100509
|View full text |Cite
|
Sign up to set email alerts
|

Optimizing the hybrid parallelization of BHAC

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1

Citation Types

0
3
0

Year Published

2022
2022
2023
2023

Publication Types

Select...
4
1

Relationship

0
5

Authors

Journals

citations
Cited by 5 publications
(3 citation statements)
references
References 22 publications
0
3
0
Order By: Relevance
“…We here document how various IMEX strategies can be used in Newtonian settings for MPI-AMRVAC 3.0. The hybrid OpenMP-MPI parallelization strategy was optimized for BHAC in Cielo et al (2022), and we inherited much of this functionality within MPI-AMRVAC 3.0. Other, completely independent GR-MHD software efforts that derived from earlier MPI-AMRVAC variants include GR-AMRVAC by Meliani et al (2016), the Gmunu code introduced in Cheong et al (2021Cheong et al ( , 2022, or the NOVAs effort presented in Varniere et al (2022).…”
Section: Open-source Strategy With Mpi-amrvacmentioning
confidence: 99%
See 1 more Smart Citation
“…We here document how various IMEX strategies can be used in Newtonian settings for MPI-AMRVAC 3.0. The hybrid OpenMP-MPI parallelization strategy was optimized for BHAC in Cielo et al (2022), and we inherited much of this functionality within MPI-AMRVAC 3.0. Other, completely independent GR-MHD software efforts that derived from earlier MPI-AMRVAC variants include GR-AMRVAC by Meliani et al (2016), the Gmunu code introduced in Cheong et al (2021Cheong et al ( , 2022, or the NOVAs effort presented in Varniere et al (2022).…”
Section: Open-source Strategy With Mpi-amrvacmentioning
confidence: 99%
“…The code can use hybrid OpenMP-MPI parallelism, where the OpenMP pragmas ensure thread-based parallelism over the blocks available within a shared memory. The related BHAC code considerably improved on this hybrid parallelization aspect (Cielo et al 2022). For truly extreme resolution simulations, one needs further code restructuring (especially the internal boundary exchange involved with AMR meshes) toward task-based parallelism.…”
Section: Future Directionsmentioning
confidence: 99%
“…The code can use hybrid OpenMP-MPI parallelism, where the OpenMP pragma's ensure thread-based parallelism over the blocks available within a shared memory. The related BHAC code considerably improved on this latter hybrid parallelization aspect (Cielo et al 2022). For truly extreme resolution simulations, one needs further code restructuring (especially the internal boundary exchange involved with AMR meshes) towards task-based parallelism.…”
Section: Future Directionsmentioning
confidence: 99%