GNNHLS: Evaluating Graph Neural Network Inference via High-Level Synthesis
This work addresses the need for efficient GNN inference on FPGAs, which is incremental as it provides a framework for evaluation rather than a new method.
The paper tackles the problem of efficient Graph Neural Network (GNN) inference by proposing GNNHLS, an open-source framework for evaluating GNN acceleration on FPGAs using High-Level Synthesis, achieving up to 50.8x speedup and 423x energy reduction compared to CPU baselines.
With the ever-growing popularity of Graph Neural Networks (GNNs), efficient GNN inference is gaining tremendous attention. Field-Programming Gate Arrays (FPGAs) are a promising execution platform due to their fine-grained parallelism, low-power consumption, reconfigurability, and concurrent execution. Even better, High-Level Synthesis (HLS) tools bridge the gap between the non-trivial FPGA development efforts and rapid emergence of new GNN models. In this paper, we propose GNNHLS, an open-source framework to comprehensively evaluate GNN inference acceleration on FPGAs via HLS, containing a software stack for data generation and baseline deployment, and FPGA implementations of 6 well-tuned GNN HLS kernels. We evaluate GNNHLS on 4 graph datasets with distinct topologies and scales. The results show that GNNHLS achieves up to 50.8x speedup and 423x energy reduction relative to the CPU baselines. Compared with the GPU baselines, GNNHLS achieves up to 5.16x speedup and 74.5x energy reduction.