Improving the efficiency of graph algorithm executions on high‐performance computing
Summary The growing need for extracting information from large graphs has been pushing the development of parallel graph algorithms. However, the highly irregular structure of the real‐world graphs limits the performance and energy improvements of graph applications. In this paper, we show that, in...
Uloženo v:
| Vydáno v: | Concurrency and computation Ročník 35; číslo 18 |
|---|---|
| Hlavní autoři: | , , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Hoboken
Wiley Subscription Services, Inc
15.08.2023
|
| Témata: | |
| ISSN: | 1532-0626, 1532-0634 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Shrnutí: | Summary
The growing need for extracting information from large graphs has been pushing the development of parallel graph algorithms. However, the highly irregular structure of the real‐world graphs limits the performance and energy improvements of graph applications. In this paper, we show that, in most cases, using all the available cores of the multiprocessor is not the best option in terms of the aforementioned non‐functional requirements. Based on that, we propose GraphKat, a framework that enables the simultaneous processing of several algorithms/graphs instead of executing them serially (i.e., one after another), increasing efficiency in terms of performance and energy. GraphKat
works in two steps: (i) it characterizes the graph applications with a specific number of threads based on their efficiency levels; and (ii) it defines the execution order of all graph applications in the target system. Experimental results on three multicore processors (Intel and AMD) show that GraphKat improves the overall system's efficiency related to performance (up to 434.26×$$ 434.26\times $$) and energy‐saving (up to 245.21×$$ \times $$), and reduces the graph applications' execution time (up to 17.70×$$ 17.70\times $$) and energy consumption (up to 6.64×$$ \times $$) compared to the default execution of parallel applications on HPC systems. |
|---|---|
| Bibliografie: | Funding information Conselho Nacional de Desenvolvimento Científico e Tecnológico, Coordenação de Aperfeiçoamento de Pessoal de Nível Superior, Grant/Award Number: 001; Fundação de Amparo à Pesquisa do Estado do Rio Grande do Sul ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| ISSN: | 1532-0626 1532-0634 |
| DOI: | 10.1002/cpe.7419 |