Graph neural networks are increasingly adopted in trigger systems for collider experiments, where strict latency and throughput constraints render deployment on embedded platforms challenging. As detectors move towards higher granularity, the number of inputs per inference increase and FPGA-only solutions face resource bottlenecks. This work presents an end-to-end demonstrator for the real-time deployment of a dynamic Graph Neural Network for the Belle II electromagnetic calorimeter hardware trigger on the AMD Versal VCK190, leveraging both FPGA fabric and AI Engine tiles. We develop a Python-based semi-automated design flow covering operator fusion, partitioning, mapping, spatial parallelization, and kernel-level optimization. Our design achieves a throughput of 2.94 million events per second at an end-to-end latency of 7.15 microseconds. Compared to the FPGA-only baseline, this represents a 53% throughput improvement while reducing DSP utilization from 99% to 19% at 29% AI Engine tile utilization. To validate the deployment, an interactive visualization pipeline enables real-time monitoring of inference results on the physical demonstrator.

翻译：图神经网络正越来越多地应用于对撞机实验的触发系统中，严格的延迟和吞吐量约束使得其在嵌入式平台上的部署面临挑战。随着探测器向更高粒度发展，单次推理的输入数量增加，纯FPGA解决方案面临资源瓶颈。本文提出了一种端到端演示系统，用于在AMD Versal VCK190上实时部署面向Belle II电磁量能器硬件触发的动态图神经网络，同时利用FPGA逻辑资源和AI Engine计算单元。我们开发了一种基于Python的半自动化设计流程，涵盖算子融合、划分、映射、空间并行化及内核级优化。我们的设计实现了每秒294万事件的吞吐量，端到端延迟为7.15微秒。与纯FPGA基线相比，吞吐量提升53%，DSP利用率从99%降至19%，AI Engine计算单元利用率为29%。为验证部署效果，交互式可视化流水线能够实时监控物理演示系统上的推理结果。