Real-Time Graph-based Point Cloud Networks on FPGAs via Stall-Free Deep Pipelining
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_ | 1866909677569179648 |
|---|---|
| author | Neu, Marc Haide, Isabel Justinger, Timo Rädler, Till Dajaku, Valdrin Ferber, Torben Becker, Jürgen |
| author_facet | Neu, Marc Haide, Isabel Justinger, Timo Rädler, Till Dajaku, Valdrin Ferber, Torben Becker, Jürgen |
| contents | Graph-based Point Cloud Networks (PCNs) are powerful tools for processing sparse sensor data with irregular geometries, as found in high-energy physics detectors. However, deploying models in such environments remains challenging due to stringent real-time requirements for both latency, and throughput. In this work, we present a deeply pipelined dataflow architecture for executing graph-based PCNs on FPGAs. Our method supports efficient processing of dynamic, sparse point clouds while meeting hard real-time constraints. We introduce specialized processing elements for core graph operations, such as GraVNet convolution and condensation point clustering, and demonstrate our design on the AMD Versal VCK190. Compared to a GPU baseline, our FPGA implementation achieves up to 5.25x speedup in throughput while maintaining latencies below 10 μs, satisfying the demands of real-time trigger systems in particle physics experiments. An open-source reference implementation is provided. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_05099 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Real-Time Graph-based Point Cloud Networks on FPGAs via Stall-Free Deep Pipelining Neu, Marc Haide, Isabel Justinger, Timo Rädler, Till Dajaku, Valdrin Ferber, Torben Becker, Jürgen Signal Processing High Energy Physics - Experiment Graph-based Point Cloud Networks (PCNs) are powerful tools for processing sparse sensor data with irregular geometries, as found in high-energy physics detectors. However, deploying models in such environments remains challenging due to stringent real-time requirements for both latency, and throughput. In this work, we present a deeply pipelined dataflow architecture for executing graph-based PCNs on FPGAs. Our method supports efficient processing of dynamic, sparse point clouds while meeting hard real-time constraints. We introduce specialized processing elements for core graph operations, such as GraVNet convolution and condensation point clustering, and demonstrate our design on the AMD Versal VCK190. Compared to a GPU baseline, our FPGA implementation achieves up to 5.25x speedup in throughput while maintaining latencies below 10 μs, satisfying the demands of real-time trigger systems in particle physics experiments. An open-source reference implementation is provided. |
| title | Real-Time Graph-based Point Cloud Networks on FPGAs via Stall-Free Deep Pipelining |
| topic | Signal Processing High Energy Physics - Experiment |
| url | https://arxiv.org/abs/2507.05099 |