Scaling Semantic Graph Databases in Size and Performance

Author

Morari, Alessandro ; Castellana, Vito Giovanni ; Villa, Oreste ; Tumeo, Antonino ; Weaver, James ; Haglin, David ; Choudhury, Sankhayan ; Feo, John

Author_Institution

Pacific Northwest Nat. Lab., Richland, WA, USA

Volume

34

Issue

4

fYear

2014

fDate

July-Aug. 2014

Firstpage

16

Lastpage

26

Abstract

GEMS is a full software system that implements a large-scale, semantic graph database on commodity clusters. Its framework comprises a SPARQL-to-C++ compiler, a library of distributed data structures, and a custom multithreaded runtime library. The authors evaluated their software stack on the Berlin SPARQL benchmark with datasets of up to 10 billion graph edges, demonstrating scaling in dataset size and performance as they added cluster nodes.

Keywords

data structures; multi-threading; program compilers; software libraries; very large databases; workstation clusters; Berlin SPARQL benchmark; GEMS; SPARQL-to-C++ compiler; commodity clusters; distributed data structure library; large-scale semantic graph database; multithreaded runtime library; performance scaling; size scaling; software stack; Big data; Cluster approximation; Data structures; Distributed processing; Multithreading; Resource description framework; Runtime; Semantics; SPARQL; big data; cluster; data aggregation; data analysis; distributed systems; graph databases; multithreading;

fLanguage

English

Journal_Title

Micro, IEEE

Publisher

ieee

ISSN

0272-1732

Type

jour

DOI

10.1109/MM.2014.39

Filename

6785922