Szczegóły publikacji
Opis bibliograficzny
Parallel algorithm for concurrent integration of three-dimensional B-spline functions / Anna Szyszka, Maciej WOŹNIAK // W: Computational Science – ICCS 2023 : 23rd international conference : Prague, Czech Republic, July 3–5, 2023 : proceedings, Pt. 2 / eds. Jiří Mikyška [et al.]. — Cham, Switzerland : Springer, cop. 2023. — (Lecture Notes in Computer Science ; ISSN 0302-9743 ; LNCS 14074). — ISBN: 978-3-031-36020-6; e-ISBN: 978-3-031-36021-3. — S. 590–596. — Bibliogr., Abstr. — Publikacja dostępna online od: 2023-06-26
Autorzy (2)
Słowa kluczowe
Dane bibliometryczne
| ID BaDAP | 147738 |
|---|---|
| Data dodania do BaDAP | 2023-07-20 |
| DOI | 10.1007/978-3-031-36021-3_57 |
| Rok publikacji | 2023 |
| Typ publikacji | materiały konferencyjne (aut.) |
| Otwarty dostęp |  |
| Wydawca | Springer |
| Konferencja | International Conference on Computational Science 2023 |
| Czasopismo/seria | Lecture Notes in Computer Science |
Abstract
In this paper, we discuss the concurrent integration applied to the 3D isogeometric finite element method. It has been proven that integration over individual elements with Gaussian quadrature is independent of each other, and a concurrent algorithm for integrating a single element has been created. The suboptimal integration algorithm over each element is developed as a sequence of basic atomic computational tasks, and the dependency relation between them is identified. We show how to prepare independent sets of tasks that can be automatically executed concurrently on a GPU card. This is done with the help of Diekert’s graph, which expresses the dependency between tasks. The execution time of the concurrent GPU integration is compared with the sequential integration executed on CPU.
