Title :
Study on Distributing Pattern of Shared Data in CC-NUMA System
Author :
Pan, Guoteng ; Dou, Qiang ; Xie, Lunguo
Author_Institution :
Nat. Univ. of Defense Technol., Changsha
fDate :
July 30 2007-Aug. 1 2007
Abstract :
Nowadays, directory-based cache coherence protocols have been the best choice in designing large-scaled CC-NUMA systems. Directory contains the shared information of all memory blocks in system. The number of copies of shared data in system and their distributing characteristics are deeply influenced by the characteristics of application programs. In this paper, a Markov chains model is built for the distributing pattern of shared data in CC-NUMA systems. It´s proved that, the average number of cache copies of shared data is small in CC-NUMA systems. Especially, when the percentage of shared read operations in applications is lower than 80%, this number is less than 5.
Keywords :
cache storage; data handling; large-scale systems; protocols; CC-NUMA system; cache coherence protocols; distributing pattern; large-scaled systems; shared data; Artificial intelligence; Coherence; Computer networks; Concurrent computing; Distributed computing; Multiprocessing systems; Pattern analysis; Protocols; Software engineering; Writing;
Conference_Titel :
Software Engineering, Artificial Intelligence, Networking, and Parallel/Distributed Computing, 2007. SNPD 2007. Eighth ACIS International Conference on
Conference_Location :
Qingdao
Print_ISBN :
978-0-7695-2909-7
DOI :
10.1109/SNPD.2007.398