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.

, , , ,
Anaconda, Inc , Intel Corp. Software Engineering Institute
2021 IEEE International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2021 Virtual, Portland 2021-05-17
Centrum Wiskunde & Informatica, Amsterdam, The Netherlands

Szárnyas, G, Bader, D.A, Davis, T.A, Kitchen, J, Mattson, T.G, McMillan, S, & Welch, E. (2021). LAGraph: Linear algebra, network analysis libraries, and the study of graph algorithms. In IEEE International Parallel and Distributed Processing Symposium Workshops (pp. 243–252). doi:10.1109/IPDPSW52791.2021.00046