Indexed Binary Operations in the GraphBLAS
GraphBLAS is a sparse matrix library for graph algorithms. We could improve the GraphBLAS and support a wider range of applications if we had an indexed binary operator; i.e., a binary operator that depends on elements from two matrices and their positions (indices). We propose a design for these operators and illustrate their impact on performance and expressiveness for several algorithms including breadth-firstsearch, argmin/argmax, vector search, and finite-element assembly.
Authors
- Matthias Maier (ORCID: https://orcid.org/0000-0002-2035-4012)
- Scott McMillan (ORCID: https://orcid.org/0000-0003-1868-5178)
- Timothy G. Mattson (ORCID: https://orcid.org/0000-0002-6106-8717)
- Manaswinee Bezbaruah
- Timothy A. Davis (ORCID: https://orcid.org/0000-0001-7614-6899)
- Erik Welch
- Michel Peletier
Institutions
- Software Engineering Institute (US)
- Nvidia (United Kingdom) (GB)
- Carnegie Mellon University (US)
- Texas A&M University (US)
Publication Details
- Published
- 2024-09-23
- DOI
- https://doi.org/10.1109/hpec62836.2024.10938456
- Primary Topic
- Graph Theory and Algorithms
- Type
- article
- Field-Weighted Citation Impact
- 0.00