LAGraph: Linear Algebra, Network Analysis Libraries, and the Study of Graph Algorithms
Document Type
Conference Proceeding
Publication Date
6-1-2021
Abstract
Graph algorithms can be expressed in terms of linear algebra. GraphBLAS is a library of low-level building blocks for such algorithms that targets algorithm developers. LAGraph builds on top of the GraphBLAS to target users of graph algorithms with high-level algorithms common in network analysis. In this paper, we describe the first release of the LAGraph library, the design decisions behind the library, and performance using the GAP benchmark suite. LAGraph, however, is much more than a library. It is also a project to document and analyze the full range of algorithms enabled by the GraphBLAS. To that end, we have developed a compact and intuitive notation for describing these algorithms. In this paper, we present that notation with examples from the GAP benchmark suite.
Identifier
85114442304 (Scopus)
ISBN
[9781665435772]
Publication Title
2021 IEEE International Parallel and Distributed Processing Symposium Workshops Ipdpsw 2021 in Conjunction with IEEE IPDPS 2021
External Full Text Location
https://doi.org/10.1109/IPDPSW52791.2021.00046
First Page
243
Last Page
252
Grant
DM21-0298
Fund Ref
International Business Machines Corporation
Recommended Citation
Szarnyas, Gabor; Bader, David A.; Davis, Timothy A.; Kitchen, James; Mattson, Timothy G.; McMillan, Scott; and Welch, Erik, "LAGraph: Linear Algebra, Network Analysis Libraries, and the Study of Graph Algorithms" (2021). Faculty Publications. 4094.
https://digitalcommons.njit.edu/fac_pubs/4094