DocumentCode :
2704908
Title :
MPACP: An Approach for Automatic Matching of Parallel Application Communication Patterns
Author :
Ma, Chao ; He, Yanxiang ; Xiong, Naixue
Author_Institution :
Comput. Sch., Wuhan Univ., Wuhan
fYear :
2008
fDate :
9-12 Dec. 2008
Firstpage :
1517
Lastpage :
1522
Abstract :
Current trends in HPC (high performance computing) suggest that clusters will soon consist with hundreds, if not thousands, processors and the size of current scientific problems becomes much larger than before. Many researchers have predicted that the communication among these processors has dominated the execution time of the scientific parallel applications. Users will need well understanding on communication patterns among scientific parallel applications and their similarities so that users benefit not only from cost saving on constructing the running environment for these applications but also from obtaining better performance. In this paper, we address the communication pattern matching, and focus on point-to-point communication, which is primarily utilized (over 90% all MPI (message passing interface) calls) in most MPI codes and has much more impact on the communication performance than collective communication does. In this work, our contribution is that we propose a new approach MPACP (matching of parallel application communication patterns) to automate the analysis of the similarity between two parallel applications and provide a reliable report which will help users or developers understand the similarity among communication patterns of parallel applications. Furthermore, experimental results demonstrate the effective performance of our scheme in terms of the automatic matching of parallel application communication patterns.
Keywords :
message passing; parallel processing; automatic matching; high performance computing; message passing interface; parallel application communication pattern matching; point-to-point communication; Application software; Chaotic communication; Computer science; Concurrent computing; Costs; Network topology; Parallel processing; Pattern matching; Scalability; USA Councils; HPC; MPI; communication pattern; parallel application; point-to-point communication;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Asia-Pacific Services Computing Conference, 2008. APSCC '08. IEEE
Conference_Location :
Yilan
Print_ISBN :
978-0-7695-3473-2
Electronic_ISBN :
978-0-7695-3473-2
Type :
conf
DOI :
10.1109/APSCC.2008.54
Filename :
4780895
Link To Document :
بازگشت