Skip to content
Open access

FlexVector: A SpMM Vector Accelerator With Flexible VRF for GCNs on Varying-Sparsity Graphs

Dec 2026 · IEEE transactions on computers · Vol 75, pp. 4727-4741 · 0 citations · 22 references

Abstract

Graph Convolutional Networks (GCNs) are widely adopted for tasks involving relational or graph-structured data and can be formulated as two-stage sparse–dense matrix multiplication (SpMM) during inference. However, existing accelerators often struggle with the irregular workloads induced by power-law node degree distributions. In this work, we propose <italic>FlexVector</italic>, a domain-specific vector accelerator that efficiently executes SpMM for GCN inference under irregular workloads. FlexVector adopts a row-wise, product-based dataflow that regularizes SpMM execution and exposes vector parallelism through full-row access to vector registers, eliminating the need for multi-banked register file designs. Building on this dataflow, it introduces software-managed, flexible vector register files (VRFs) that adapt to irregular data access patterns, without sacrificing memory access efficiency. To further exploit these architectural capabilities, we develop a graph preprocessing strategy that restructures irregular graph workloads to better match the row-wise dataflow and VRF capacity. This hardware–software co-design reduces memory traffic, leading to significant performance and energy efficiency gains on real-world GCN workloads. Experimental results on five real-world GCN datasets show that the VRF-centric FlexVector achieves a <inline-formula><tex-math notation="LaTeX">$\mathbf{3.78\times}$</tex-math><alternatives><mml:math><mml:mrow><mml:mn mathvariant="bold">3.78</mml:mn><mml:mo>×</mml:mo></mml:mrow></mml:math><inline-graphic xlink:href="yang-ieq1-3742755.gif"/></alternatives></inline-formula> speedup and 40.5% lower energy at comparable area cost relative to a state-of-the-art cache-centric baseline with buffers of the same size.

Read PDF

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.