Graphulo Implementation of Server-Side Sparse Matrix Multiply in the Accumulo Database

TL;DR

This paper presents a server-side implementation of GraphBLAS sparse matrix multiplication within the Accumulo database, enabling efficient graph analytics directly in the database environment.

Contribution

It introduces a novel server-side sparse matrix multiplication method in Accumulo using native iterators, enhancing graph analytics capabilities.

Findings

Outer product implementation achieves near-peak performance

Comparison of inner and outer product methods

Integration with Graphulo library for graph analytics

Abstract

The Apache Accumulo database excels at distributed storage and indexing and is ideally suited for storing graph data. Many big data analytics compute on graph data and persist their results back to the database. These graph calculations are often best performed inside the database server. The GraphBLAS standard provides a compact and efficient basis for a wide range of graph applications through a small number of sparse matrix operations. In this article, we implement GraphBLAS sparse matrix multiplication server-side by leveraging Accumulo's native, high-performance iterators. We compare the mathematics and performance of inner and outer product implementations, and show how an outer product implementation achieves optimal performance near Accumulo's peak write rate. We offer our work as a core component to the Graphulo library that will deliver matrix math primitives for graph analytics within Accumulo.