MERBIT: A GPU-Based SpMV Method for Iterative Workloads

TL;DR

MERBIT is a GPU-based SpMV method optimized for irregular, graph-like matrices, significantly improving performance over existing solutions in large-scale graph analytics.

Contribution

It introduces a novel GPU SpMV approach combining merge-path partitioning and bit-field encoding to enhance workload balance and memory access.

Findings

Outperforms cuSPARSE, Ginkgo, and academic methods on 50 datasets.

Achieves 1.27x and 1.25x speedups over cuSPARSE COO in single and double precision.

Demonstrates effectiveness on large irregular sparse matrices.

Abstract

Sparse Matrix-Vector Multiplication (SpMV) is the cornerstone in many iterative workloads, including large-scale graph analytics and sparse iterative solvers. Accelerating SpMV on real-world graphs remains challenging due to highly irregular sparsity patterns. In this paper, we propose MERBIT, a GPU SpMV method designed for repeated SpMV on irregular, graph-like sparse matrices, with PageRank as a representative motivating workload. MERBIT combines two key ideas from existing GPU SpMV methods. At the global level, it uses merge-path partitioning to balance work over nonzeros and row boundaries. At the local level, it encodes each merge-path segment using a compact bit-field descriptor. MERBIT improves workload balance and promotes coalesced memory access for both matrix loading and output writes; moreover, three optimization strategies are incorporated to further enhance performance. Experiments on 50 large irregular datasets demonstrate that MERBIT outperforms competitive baselines, including cuSPARSE, Ginkgo, and academic approaches, achieving average speedups of 1.27 and 1.25 over cuSPARSE COO in single and double precision, respectively.