000198734 001__ 198734
000198734 005__ 20190316235914.0
000198734 037__ $$aCONF
000198734 245__ $$aHigh-Throughput Maps on Message-Passing Manycore Architectures: Partitioning versus Replication
000198734 269__ $$a2014
000198734 260__ $$c2014
000198734 336__ $$aConference Papers
000198734 520__ $$aThe advent of manycore architectures raises new scalability challenges for concurrent applications. Implementing scalable data structures is one of them. Several manycore architectures provide hardware message passing as a means to efficiently exchange data between cores. In this paper, we study the implementation of high-throughput concurrent maps in message-passing manycores. Partitioning and replication are the two approaches to achieve high throughput in a message-passing system. Our paper presents and compares different strongly-consistent map algorithms based on partitioning and replication. To assess the performance of these algorithms independently of architecture-specific features, we propose a communication model of message-passing manycores to express the throughput of each algorithm. The model is validated through experiments on a 36-core TILE-Gx8036 processor. Evaluations show that replication outperforms partitioning only in a narrow domain.
000198734 6531_ $$aHigh-throughput Map
000198734 6531_ $$aMessage-Passing Manycore Architecture
000198734 6531_ $$aReplication
000198734 6531_ $$aPartitioning
000198734 700__ $$0243467$$aShahmirzadi, Omid$$g179262
000198734 700__ $$0245454$$aRopars, Thomas$$g213142
000198734 700__ $$0241767$$aSchiper, André$$g106377
000198734 7112_ $$a20th International European Conference on Parallel Processing$$cPorto, Portugal$$dAugust 25-29, 2014
000198734 8564_ $$s455331$$uhttps://infoscience.epfl.ch/record/198734/files/europar2014.pdf$$yPublisher's version$$zPublisher's version
000198734 909C0 $$0252206$$pLSR$$xU10411
000198734 909CO $$ooai:infoscience.tind.io:198734$$pconf$$pIC$$qGLOBAL_SET
000198734 917Z8 $$x179262
000198734 917Z8 $$x179262
000198734 917Z8 $$x179262
000198734 937__ $$aEPFL-CONF-198734
000198734 973__ $$aEPFL$$rREVIEWED$$sACCEPTED
000198734 980__ $$aCONF