Notation for mass parallel algorithms: computing Petri net state space on GPU case study

We introduce a novel notation for mass parallel algorithms, in particular, algorithms for GPU, which is based on graphical specification of the cube of threads combined with textual expressions, specifying a thread algorithm. We abstract from the peculiarities of a definite GPU preserving basic feat...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:International journal of parallel, emergent and distributed systems Ročník 40; číslo 2; s. 101 - 115
Hlavní autori: Zaitsev, D. A., Zhang, Z., Liu, D., Shmeleva, T. R.
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Abingdon Taylor & Francis 04.03.2025
Taylor & Francis Ltd
Predmet:
Algorithms
CUDA
GPU
Graphics processing units
Mass parallel algorithm
parallel hash table
Petri net
Petri nets
reachability graph
ISSN:1744-5760, 1744-5779
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:We introduce a novel notation for mass parallel algorithms, in particular, algorithms for GPU, which is based on graphical specification of the cube of threads combined with textual expressions, specifying a thread algorithm. We abstract from the peculiarities of a definite GPU preserving basic features of mass-parallel computations. As a case study for the notation, we developed, and implemented in CUDA, a reachability graph algorithm for Petri nets. Parallel hash tables have been introduced to reduce the time complexity. About a hundred time speed-up has been obtained, compared with the best known toolset Tina.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1744-5760
1744-5779
DOI:10.1080/17445760.2024.2431545