SENSEi: Input-Sensitive Compilation for Accelerating GNNs

arXiv:2306.15155v2 Announce Type: replace
Abstract: Over the years, many frameworks and optimization techniques have been proposed to accelerate graph neural networks (GNNs). Compared to the optimizations explored in these systems, we observe that different matrix re-associations of GNN computations lead to novel input-sensitive performance behavior. We leverage this observation to propose SENSEi, a system that exposes different sparse and dense matrix primitive compositions based on different matrix re-associations of GNN computations and selects the best among them based on input …

abstract arxiv behavior compilation cs.lg cs.pf frameworks gnn gnns graph graph neural networks matrix networks neural networks novel observation observe optimization performance systems type