GPU accelerated particle visualization with Splotch
Splotch is a rendering algorithm for exploration and visual discovery in particle-based datasets coming from astronomical observations or numerical simulations. The strengths of the approach are production of high quality imagery and support for very large-scale datasets through an effective mix of...
| Main Authors: | , , , , |
|---|---|
| Format: | Journal article |
| Language: | English |
| Published: |
Elsevier
2014
|
| _version_ | 1826293502213881856 |
|---|---|
| author | Rivi, M Gheller, C Dykes, T Krokos, M Dolag, K |
| author_facet | Rivi, M Gheller, C Dykes, T Krokos, M Dolag, K |
| author_sort | Rivi, M |
| collection | OXFORD |
| description | Splotch is a rendering algorithm for exploration and visual discovery in particle-based datasets coming from astronomical observations or numerical simulations. The strengths of the approach are production of high quality imagery and support for very large-scale datasets through an effective mix of the OpenMP and MPI parallel programming paradigms. This article reports our experiences in re-designing Splotch for exploiting emerging HPC architectures nowadays increasingly populated with GPUs. A performance model is introduced to guide our re-factoring of Splotch. A number of parallelization issues are discussed, in particular relating to race conditions and workload balancing, towards achieving optimal performances. Our implementation was accomplished by using the CUDA programming paradigm. Our strategy is founded on novel schemes achieving optimized data organization and classification of particles. We deploy a reference cosmological simulation to present performance results on acceleration gains and scalability. We finally outline our vision for future work developments including possibilities for further optimizations and exploitation of hybrid systems and emerging accelerators. © 2014 Elsevier B.V. |
| first_indexed | 2024-03-07T03:31:05Z |
| format | Journal article |
| id | oxford-uuid:babe31b8-6971-429f-b2b7-78de49c423c2 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-07T03:31:05Z |
| publishDate | 2014 |
| publisher | Elsevier |
| record_format | dspace |
| spelling | oxford-uuid:babe31b8-6971-429f-b2b7-78de49c423c22022-03-27T05:11:57ZGPU accelerated particle visualization with SplotchJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:babe31b8-6971-429f-b2b7-78de49c423c2EnglishSymplectic Elements at OxfordElsevier2014Rivi, MGheller, CDykes, TKrokos, MDolag, KSplotch is a rendering algorithm for exploration and visual discovery in particle-based datasets coming from astronomical observations or numerical simulations. The strengths of the approach are production of high quality imagery and support for very large-scale datasets through an effective mix of the OpenMP and MPI parallel programming paradigms. This article reports our experiences in re-designing Splotch for exploiting emerging HPC architectures nowadays increasingly populated with GPUs. A performance model is introduced to guide our re-factoring of Splotch. A number of parallelization issues are discussed, in particular relating to race conditions and workload balancing, towards achieving optimal performances. Our implementation was accomplished by using the CUDA programming paradigm. Our strategy is founded on novel schemes achieving optimized data organization and classification of particles. We deploy a reference cosmological simulation to present performance results on acceleration gains and scalability. We finally outline our vision for future work developments including possibilities for further optimizations and exploitation of hybrid systems and emerging accelerators. © 2014 Elsevier B.V. |
| spellingShingle | Rivi, M Gheller, C Dykes, T Krokos, M Dolag, K GPU accelerated particle visualization with Splotch |
| title | GPU accelerated particle visualization with Splotch |
| title_full | GPU accelerated particle visualization with Splotch |
| title_fullStr | GPU accelerated particle visualization with Splotch |
| title_full_unstemmed | GPU accelerated particle visualization with Splotch |
| title_short | GPU accelerated particle visualization with Splotch |
| title_sort | gpu accelerated particle visualization with splotch |
| work_keys_str_mv | AT rivim gpuacceleratedparticlevisualizationwithsplotch AT ghellerc gpuacceleratedparticlevisualizationwithsplotch AT dykest gpuacceleratedparticlevisualizationwithsplotch AT krokosm gpuacceleratedparticlevisualizationwithsplotch AT dolagk gpuacceleratedparticlevisualizationwithsplotch |