# LL-GNN: Low Latency Graph Neural Networks on FPGAs for High Energy Physics

arXiv: https://arxiv.org/abs/2209.14065 · HTML: https://mlsanity.com/paper/2209.14065/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 60 references that are in the map.
- First posted on arXiv 28 Sep 2022.

## Builds on (most cited first, 30 of 31)

- [Graph Convolutional Neural Networks for Web-Scale Recommender Systems](https://mlsanity.com/paper/1806.01973/) (2018)
- [MoleculeNet: A Benchmark for Molecular Machine Learning](https://mlsanity.com/paper/1703.00564/) (2017)
- [Graph Neural Networks for Social Recommendation](https://mlsanity.com/paper/1902.07243/) (2019)
- [Interaction Networks for Learning about Objects, Relations and Physics](https://mlsanity.com/paper/1612.00222/) (2016)
- [AliGraph: A Comprehensive Graph Neural Network Platform](https://mlsanity.com/paper/1902.08730/) (2019)
- [Fast inference of deep neural networks in FPGAs for particle physics](https://mlsanity.com/paper/1804.06913/) (2018)
- [Automatic heterogeneous quantization of deep neural networks for low-latency inference on the edge for particle detectors](https://mlsanity.com/paper/2006.10159/) (2020)
- [HyGCN: A GCN Accelerator with Hybrid Architecture](https://mlsanity.com/paper/2001.02514/) (2020)
- [FINN-R: An End-to-End Deep-Learning Framework for Fast Exploration of Quantized Neural Networks](https://mlsanity.com/paper/1809.04570/) (2018)
- [ESE: Efficient Speech Recognition Engine with Sparse LSTM on FPGA](https://mlsanity.com/paper/1612.00694/) (2016)
- [Learning representations of irregular particle-detector geometry with distance-weighted graph networks](https://mlsanity.com/paper/1902.07987/) (2019)
- [EnGN: A High-Throughput and Energy-Efficient Accelerator for Large Graph Neural Networks](https://mlsanity.com/paper/1909.00155/) (2019)
- [Distance-Weighted Graph Neural Networks on FPGAs for Real-Time Particle Reconstruction in High Energy Physics](https://mlsanity.com/paper/2008.03601/) (2020)
- [GraphACT: Accelerating GCN Training on CPU-FPGA Heterogeneous Platforms](https://mlsanity.com/paper/2001.02498/) (2019)
- [Performance of a Geometric Deep Learning Pipeline for HL-LHC Particle Tracking](https://mlsanity.com/paper/2103.06995/) (2021)
- [Maximizing CNN Accelerator Efficiency Through Resource Partitioning](https://mlsanity.com/paper/1607.00064/) (2016)
- [Parallel and Distributed Graph Neural Networks: An In-Depth Concurrency Analysis](https://mlsanity.com/paper/2205.09702/) (2022)
- [I-GCN: A Graph Convolutional Network Accelerator with Runtime Locality Enhancement through Islandization](https://mlsanity.com/paper/2203.03606/) (2022)
- [DNNExplorer: A Framework for Modeling and Exploring a Novel Paradigm of FPGA-based DNN Accelerator](https://mlsanity.com/paper/2008.12745/) (2020)
- [Graph Neural Networks for Charged Particle Tracking on FPGAs](https://mlsanity.com/paper/2112.02048/) (2021)
- [G-CoS: GNN-Accelerator Co-Search Towards Both Better Accuracy and Efficiency](https://mlsanity.com/paper/2109.08983/) (2021)
- [GCoD: Graph Convolutional Network Acceleration via Dedicated Algorithm and Accelerator Co-Design](https://mlsanity.com/paper/2112.11594/) (2021)
- [Accelerating Recurrent Neural Networks for Gravitational Wave Experiments](https://mlsanity.com/paper/2106.14089/) (2021)
- [Model-Architecture Co-Design for High Performance Temporal GNN Inference on FPGA](https://mlsanity.com/paper/2203.05095/) (2022)
- [Graph Neural Networks in Particle Physics: Implementations, Innovations, and Challenges](https://mlsanity.com/paper/2203.12852/) (2022)
- [HP-GNN: Generating High Throughput GNN Training Implementation on CPU-FPGA Heterogeneous Platform](https://mlsanity.com/paper/2112.11684/) (2021)
- [GenGNN: A Generic FPGA Framework for Graph Neural Network Acceleration](https://mlsanity.com/paper/2201.08475/) (2022)
- [GROW: A Row-Stationary Sparse-Dense GEMM Accelerator for Memory-Efficient Graph Convolutional Neural Networks](https://mlsanity.com/paper/2203.00158/) (2022)
- [Understanding the Design-Space of Sparse/Dense Multiphase GNN dataflows on Spatial Accelerators](https://mlsanity.com/paper/2103.07977/) (2021)
- [ReGraph: Scaling Graph Processing on HBM-enabled FPGAs with Heterogeneous Pipelines](https://mlsanity.com/paper/2203.02676/) (2022)

## Built on by (most cited first, 12 of 12)

- [Ultrafast jet classification on FPGAs for the HL-LHC](https://mlsanity.com/paper/2402.01876/) (2024)
- [HGQ: High Granularity Quantization for Real-time Neural Networks on FPGAs](https://mlsanity.com/paper/2405.00645/) (2024)
- [da4ml: Distributed Arithmetic for Real-time Neural Networks on FPGAs](https://mlsanity.com/paper/2507.04535/) (2025)
- [Sub-microsecond Transformers for Jet Tagging on FPGAs](https://mlsanity.com/paper/2510.24784/) (2025)
- [MetaML-Pro: Cross-Stage Design Flow Automation for Efficient Deep Learning Acceleration](https://mlsanity.com/paper/2502.05850/) (2025)
- [Efficient Mixed Precision Quantization in Graph Neural Networks](https://mlsanity.com/paper/2505.09361/) (2025)
- [JetFormer: A Scalable and Efficient Transformer for Jet Tagging from Offline Analysis to FPGA Triggers](https://mlsanity.com/paper/2601.17215/) (2026)
- [Research on Low-Latency Inference and Training Efficiency Optimization for Graph Neural Network and Large Language Model-Based Recommendation Systems](https://mlsanity.com/paper/2507.01035/) (2025)
- [Towards Tensor Network Models for Low-Latency Jet Tagging on FPGAs](https://mlsanity.com/paper/2601.10801/) (2026)
- [HGQ-LUT: Fast LUT-Aware Training and Efficient Architectures for DNN Inference](https://mlsanity.com/paper/2604.22293/) (2026)
- [19 Parameters Is All You Need: Tiny Neural Networks for Particle Physics](https://mlsanity.com/paper/2310.16121/) (2023)
- [Physics-Informed Graph Neural Networks for Transverse Momentum Estimation in CMS Trigger Systems](https://mlsanity.com/paper/2507.19205/) (2025)

## Abstract (arXiv)

This work presents a novel reconfigurable architecture for Low Latency Graph Neural Network (LL-GNN) designs for particle detectors, delivering unprecedented low latency performance. Incorporating FPGA-based GNNs into particle detectors presents a unique challenge since it requires sub-microsecond latency to deploy the networks for online event selection with a data rate of hundreds of terabytes per second in the Level-1 triggers at the CERN Large Hadron Collider experiments. This paper proposes a novel outer-product based matrix multiplication approach, which is enhanced by exploiting the structured adjacency matrix and a column-major data layout. Moreover, a fusion step is introduced to further reduce the end-to-end design latency by eliminating unnecessary boundaries. Furthermore, a GNN-specific algorithm-hardware co-design approach is presented which not only finds a design with a much better latency but also finds a high accuracy design under given latency constraints. To facilitate this, a customizable template for this low latency GNN hardware architecture has been designed and open-sourced, which enables the generation of low-latency FPGA designs with efficient resource utilization using a high-level synthesis tool. Evaluation results show that our FPGA implementation is up to 9.0 times faster and achieves up to 13.1 times higher power efficiency than a GPU implementation. Compared to the previous FPGA implementations, this work achieves 6.51 to 16.7 times lower latency. Moreover, the latency of our FPGA design is sufficiently low to enable deployment of GNNs in a sub-microsecond, real-time collider trigger system, enabling it to benefit from improved accuracy. The proposed LL-GNN design advances the next generation of trigger systems by enabling sophisticated algorithms to process experimental data efficiently.