Hardware-Accelerated GNN-based Hit Filtering for the Belle II Level-1 Trigger
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914142006280192 |
|---|---|
| author | Heine, Greta Mayer, Fabio Neu, Marc Becker, Jürgen Ferber, Torben |
| author_facet | Heine, Greta Mayer, Fabio Neu, Marc Becker, Jürgen Ferber, Torben |
| contents | We present a hardware-accelerated hit filtering system employing Graph Neural Networks (GNNs) on Field-Programmable Gate Arrays (FPGAs) for the Belle II Level-1 Trigger. The GNN exploits spatial and temporal relationships among sense wire hits and is optimized for high-throughput hardware operation via quantization, pruning, and static graph-building. Sector-wise spatial parallelization permits scaling to full-detector coverage, satisfying stringent latency and throughput requirements. At a sustained throughput of 31.804 MHz, the system processes sense wire data in real-time and achieves detector-level background suppression with a measured latency of 632.4 ns while utilizing 35.65% of Look-Up Tables (LUTs), and 29.75% of Flip-Flops, with zero Digital Signal Processing (DSP) usage, as demonstrated in a prototype implementation for a single sector on an AMD Ultrascale XVCU190. Offline validation using Belle II data yields a background hit rejection of 83% while maintaining 95% signal hit efficiency. This work establishes hit-level GNN-based filtering on FPGAs as a scalable low-latency solution for real-time data reduction in high-luminosity collider conditions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_04731 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Hardware-Accelerated GNN-based Hit Filtering for the Belle II Level-1 Trigger Heine, Greta Mayer, Fabio Neu, Marc Becker, Jürgen Ferber, Torben Instrumentation and Detectors High Energy Physics - Experiment We present a hardware-accelerated hit filtering system employing Graph Neural Networks (GNNs) on Field-Programmable Gate Arrays (FPGAs) for the Belle II Level-1 Trigger. The GNN exploits spatial and temporal relationships among sense wire hits and is optimized for high-throughput hardware operation via quantization, pruning, and static graph-building. Sector-wise spatial parallelization permits scaling to full-detector coverage, satisfying stringent latency and throughput requirements. At a sustained throughput of 31.804 MHz, the system processes sense wire data in real-time and achieves detector-level background suppression with a measured latency of 632.4 ns while utilizing 35.65% of Look-Up Tables (LUTs), and 29.75% of Flip-Flops, with zero Digital Signal Processing (DSP) usage, as demonstrated in a prototype implementation for a single sector on an AMD Ultrascale XVCU190. Offline validation using Belle II data yields a background hit rejection of 83% while maintaining 95% signal hit efficiency. This work establishes hit-level GNN-based filtering on FPGAs as a scalable low-latency solution for real-time data reduction in high-luminosity collider conditions. |
| title | Hardware-Accelerated GNN-based Hit Filtering for the Belle II Level-1 Trigger |
| topic | Instrumentation and Detectors High Energy Physics - Experiment |
| url | https://arxiv.org/abs/2511.04731 |