DGNNFlow: A Streaming Dataflow Architecture for Real-Time Edge-based Dynamic GNN Inference in HL-LHC Trigger Systems
Dynamic GNN inference exhibits strong capability to model interactions over time, such as complex particle collision events in High Energy Physics (HEP) experiments at High Luminosity Large Hadron Collider (HL-LHC). With much larger scale of collision data captured in future HEP experiments to help unlocking physics discoveries and limitation in both offline compute capacity and storage, revamped trigger systems require FPGAs to run ultra-low-latency Machine Learning models with low power consumption for online filtering of useful events. Many state-of-the-art GNN accelerators relied on static graph structures, but this assumption breaks down in HL-LHC trigger systems and other edge-based dynamic GNN applications where edge embeddings can change in-place based on neighbor node embeddings during runtime. We propose DGNNFlow, a novel streaming dataflow architecture for real-time edge-based dynamic GNN inference applications (including but not limited to HL-LHC trigger systems) along with three key contributions. First, we introduce hardware enhancement for edge embedding dynamic computation. Second, we alleviate data dependencies in edge-based dynamic GNN dataflow with Node Embedding Broadcast. Third, we provide input dynamic graph construction for complete support of graphs without pre-defined edge embeddings. We deploy DGNNFlow using AMD Alveo U50 FPGA to evaluate performance at 200 MHz clock frequency. DGNNFlow achieved 2.59x-4.36x and 1.30x-2.14x speedup compared to NVIDIA RTX A6000 GPU (batch sizes 1 and 2) with 3.59x-3.70x less power consumption, achieved 2.29x-3.54x speedup with 1.93x-2.12x less power consumption compared to Intel Xeon Gold 6226R CPU. Our implementation is available on GitHub.