LilyTask parallel language 3.5 - approach towards task parallel programming in heterogeneous SMP-clusters

In heterogeneous clusters, different nodes may have different computing powers, so traditional parallel languages or runtime libraries are not suitable there even for regular computations. Task parallel systems may be good candidates since they may easily support dynamic task assignment. But most of...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2005 International Conference on Parallel Processing Workshops (ICPPW'05) s. 305 - 312
Hlavní autoři: Tao Wang, Nan Di, Jian Shen, Min Liu
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 2005
Témata:
Computer networks
Concrete
Concurrent computing
Costs
Libraries
Message passing
Parallel languages
Parallel processing
Parallel programming
Programming profession
ISBN:9780769523811, 0769523811
ISSN:0190-3918
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:In heterogeneous clusters, different nodes may have different computing powers, so traditional parallel languages or runtime libraries are not suitable there even for regular computations. Task parallel systems may be good candidates since they may easily support dynamic task assignment. But most of them can achieve high performances only in SMPs. And some of them do not provide convenient programmability. This paper presents the rich enhancements in the latest version of a very easy-to-use task parallel language called LilyTask, with which programmers can easily handle tasks and avoid explicit synchronizations and message passings. This paper also tells how LilyTask is realized in heterogeneous SMP-clusters. Evaluations show that due to its feature of dynamic task parallelism and due to its elaborate implementation, the executing efficiency of LilyTask is better than that of OpenMP in SMPs and that of MPI in both SMPs and heterogeneous clusters.
ISBN:9780769523811
0769523811
ISSN:0190-3918
DOI:10.1109/ICPPW.2005.45