Replicating Data for Better Performances in X10

Autor:	Rocco De Nicola, Alberto Lluch Lafuente, Marina Andrić
Rok vydání:	2015
Předmět:	Consistency (database systems) Data access Theoretical computer science Computer science Distributed computing Parallel programming model Locality Consistency model Tuple space Programmer Replication (computing)
Zdroj:	Semantics, Logics, and Calculi ISBN: 9783319278094 Semantics, Logics, and Calculi
DOI:	10.1007/978-3-319-27810-0_12
Popis:	Linguistic primitives for replica-aware coordination offer suitable solutions to the challenging problems of data distribution and locality in large-scale high-performance computing. The data replication mechanisms that had previously been designed to extend Klaim with replicated tuples are now used to experiment with X10, a parallel programming language primarily targeting clusters of multi-core processors linked in a large-scale system via high-performance networks. Our approach aims at allowing the programmer to specify and coordinate the replication of shared data items by taking into account the desired consistency properties. The programmer can hence exploit such flexible mechanisms to adapt data distribution and locality to the needs of the application, in order to improve performance in terms of concurrency and data access. We investigate issues related to replica consistency and provide a performance analysis, which includes scenarios where replica-based specifications and relaxed consistency provide significant performance gains.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::26352f214b00e487982c2210b0daf570 https://doi.org/10.1007/978-3-319-27810-0_12 Zobrazit plný text záznamu