FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2917950505> ?p ?o ?g. }

• W2917950505 endingPage "334" @default.
• W2917950505 startingPage "321" @default.
• W2917950505 abstract "Distributed-memory clusters are used for in-memory processing of very large graphs with billions of nodes and edges. This requires partitioning the graph among the machines in the cluster. When a graph is partitioned, a node in the graph may be replicated on several machines, and communication is required to keep these replicas synchronized. Good partitioning policies attempt to reduce this synchronization overhead while keeping the computational load balanced across machines. A number of recent studies have looked at ways to control replication of nodes, but these studies are not conclusive because they were performed on small clusters with eight to sixteen machines, did not consider work-efficient data-driven algorithms, or did not optimize communication for the partitioning strategies they studied. This paper presents an experimental study of partitioning strategies for work-efficient graph analytics applications on large KNL and Skylake clusters with up to 256 machines using the Gluon communication runtime which implements partitioning-specific communication optimizations. Evaluation results show that although simple partitioning strategies like Edge-Cuts perform well on a small number of machines, an alternative partitioning strategy called Cartesian Vertex-Cut (CVC) performs better at scale even though paradoxically it has a higher replication factor and performs more communication than Edge-Cut partitioning does. Results from communication micro-benchmarks resolve this paradox by showing that communication overhead depends not only on communication volume but also on the communication pattern among the partitions. These experiments suggest that high-performance graph analytics systems should support multiple partitioning strategies, like Gluon does, as no single graph partitioning strategy is best for all cluster sizes. For such systems, a decision tree for selecting a good partitioning strategy based on characteristics of the computation and the cluster is presented." @default.
• W2917950505 created "2019-03-02" @default.
• W2917950505 creator A5013181067 @default.
• W2917950505 creator A5040636191 @default.
• W2917950505 creator A5056166013 @default.
• W2917950505 creator A5062677813 @default.
• W2917950505 date "2018-12-01" @default.
• W2917950505 modified "2023-10-17" @default.
• W2917950505 title "A study of partitioning policies for graph analytics on large-scale distributed platforms" @default.
• W2917950505 cites W1971630691 @default.
• W2917950505 cites W1975171529 @default.
• W2917950505 cites W1982003698 @default.
• W2917950505 cites W1985625491 @default.
• W2917950505 cites W1986603225 @default.
• W2917950505 cites W1994727615 @default.
• W2917950505 cites W2000041758 @default.
• W2917950505 cites W2004053910 @default.
• W2917950505 cites W2006023152 @default.
• W2917950505 cites W2031709923 @default.
• W2917950505 cites W2034102265 @default.
• W2917950505 cites W2052138473 @default.
• W2917950505 cites W2056116767 @default.
• W2917950505 cites W2056883060 @default.
• W2917950505 cites W2064635301 @default.
• W2917950505 cites W2069277577 @default.
• W2917950505 cites W2082773934 @default.
• W2917950505 cites W2085494605 @default.
• W2917950505 cites W2093053744 @default.
• W2917950505 cites W2109220922 @default.
• W2917950505 cites W2124200646 @default.
• W2917950505 cites W2131071574 @default.
• W2917950505 cites W2131183411 @default.
• W2917950505 cites W2141380216 @default.
• W2917950505 cites W2142931311 @default.
• W2917950505 cites W2166469213 @default.
• W2917950505 cites W2170616854 @default.
• W2917950505 cites W2237283101 @default.
• W2917950505 cites W2270949707 @default.
• W2917950505 cites W2296407087 @default.
• W2917950505 cites W2343527030 @default.
• W2917950505 cites W2561911856 @default.
• W2917950505 cites W2579818174 @default.
• W2917950505 cites W2731415668 @default.
• W2917950505 cites W2752238980 @default.
• W2917950505 cites W2798525482 @default.
• W2917950505 cites W2885289883 @default.
• W2917950505 cites W2889350994 @default.
• W2917950505 cites W2963804743 @default.
• W2917950505 cites W3004555699 @default.
• W2917950505 cites W3009233884 @default.
• W2917950505 doi "https://doi.org/10.14778/3297753.3297754" @default.
• W2917950505 hasPublicationYear "2018" @default.
• W2917950505 type Work @default.
• W2917950505 sameAs 2917950505 @default.
• W2917950505 citedByCount "21" @default.
• W2917950505 countsByYear W29179505052019 @default.
• W2917950505 countsByYear W29179505052020 @default.
• W2917950505 countsByYear W29179505052021 @default.
• W2917950505 countsByYear W29179505052022 @default.
• W2917950505 countsByYear W29179505052023 @default.
• W2917950505 crossrefType "journal-article" @default.
• W2917950505 hasAuthorship W2917950505A5013181067 @default.
• W2917950505 hasAuthorship W2917950505A5040636191 @default.
• W2917950505 hasAuthorship W2917950505A5056166013 @default.
• W2917950505 hasAuthorship W2917950505A5062677813 @default.
• W2917950505 hasConcept C111919701 @default.
• W2917950505 hasConcept C120314980 @default.
• W2917950505 hasConcept C124101348 @default.
• W2917950505 hasConcept C132525143 @default.
• W2917950505 hasConcept C173608175 @default.
• W2917950505 hasConcept C2779960059 @default.
• W2917950505 hasConcept C41008148 @default.
• W2917950505 hasConcept C48044578 @default.
• W2917950505 hasConcept C48903430 @default.
• W2917950505 hasConcept C79158427 @default.
• W2917950505 hasConcept C80444323 @default.
• W2917950505 hasConceptScore W2917950505C111919701 @default.
• W2917950505 hasConceptScore W2917950505C120314980 @default.
• W2917950505 hasConceptScore W2917950505C124101348 @default.
• W2917950505 hasConceptScore W2917950505C132525143 @default.
• W2917950505 hasConceptScore W2917950505C173608175 @default.
• W2917950505 hasConceptScore W2917950505C2779960059 @default.
• W2917950505 hasConceptScore W2917950505C41008148 @default.
• W2917950505 hasConceptScore W2917950505C48044578 @default.
• W2917950505 hasConceptScore W2917950505C48903430 @default.
• W2917950505 hasConceptScore W2917950505C79158427 @default.
• W2917950505 hasConceptScore W2917950505C80444323 @default.
• W2917950505 hasIssue "4" @default.
• W2917950505 hasLocation W29179505051 @default.
• W2917950505 hasOpenAccess W2917950505 @default.
• W2917950505 hasPrimaryLocation W29179505051 @default.
• W2917950505 hasRelatedWork W1992741870 @default.
• W2917950505 hasRelatedWork W2027487876 @default.
• W2917950505 hasRelatedWork W2036438393 @default.
• W2917950505 hasRelatedWork W2364921833 @default.
• W2917950505 hasRelatedWork W2380023786 @default.
• W2917950505 hasRelatedWork W2385146268 @default.
• W2917950505 hasRelatedWork W2391167130 @default.

• next