HLS4PC: A Parametrizable Framework For Accelerating Point-Based 3D Point Cloud Models on FPGA
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917171506970624 |
|---|---|
| author | Pal, Amur Saqib Ghaffar, Muhammad Mohsin Shafait, Faisal Weis, Christian Wehn, Norbert |
| author_facet | Pal, Amur Saqib Ghaffar, Muhammad Mohsin Shafait, Faisal Weis, Christian Wehn, Norbert |
| contents | Point-based 3D point cloud models employ computation and memory intensive mapping functions alongside NN layers for classification/segmentation, and are executed on server-grade GPUs. The sparse, and unstructured nature of 3D point cloud data leads to high memory and computational demand, hindering real-time performance in safety critical applications due to GPU under-utilization. To address this challenge, we present HLS4PC, a parameterizable HLS framework for FPGA acceleration. Our approach leverages FPGA parallelization and algorithmic optimizations to enable efficient fixed-point implementations of both mapping and NN functions. We explore several hardware-aware compression techniques on a state-of-the-art PointMLP-Elite model, including replacing FPS with URS, parameter quantization, layer fusion, and input-points pruning, yielding PointMLP-Lite, a 4x less complex variant with only 2% accuracy drop on ModelNet40. Secondly, we demonstrate that the FPGA acceleration of the PointMLP-Lite results in 3.56x higher throughput than previous works. Furthermore, our implementation achieves 2.3x and 22x higher throughput compared to the GPU and CPU implementations, respectively. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_22139 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | HLS4PC: A Parametrizable Framework For Accelerating Point-Based 3D Point Cloud Models on FPGA Pal, Amur Saqib Ghaffar, Muhammad Mohsin Shafait, Faisal Weis, Christian Wehn, Norbert Distributed, Parallel, and Cluster Computing Artificial Intelligence Hardware Architecture Robotics Point-based 3D point cloud models employ computation and memory intensive mapping functions alongside NN layers for classification/segmentation, and are executed on server-grade GPUs. The sparse, and unstructured nature of 3D point cloud data leads to high memory and computational demand, hindering real-time performance in safety critical applications due to GPU under-utilization. To address this challenge, we present HLS4PC, a parameterizable HLS framework for FPGA acceleration. Our approach leverages FPGA parallelization and algorithmic optimizations to enable efficient fixed-point implementations of both mapping and NN functions. We explore several hardware-aware compression techniques on a state-of-the-art PointMLP-Elite model, including replacing FPS with URS, parameter quantization, layer fusion, and input-points pruning, yielding PointMLP-Lite, a 4x less complex variant with only 2% accuracy drop on ModelNet40. Secondly, we demonstrate that the FPGA acceleration of the PointMLP-Lite results in 3.56x higher throughput than previous works. Furthermore, our implementation achieves 2.3x and 22x higher throughput compared to the GPU and CPU implementations, respectively. |
| title | HLS4PC: A Parametrizable Framework For Accelerating Point-Based 3D Point Cloud Models on FPGA |
| topic | Distributed, Parallel, and Cluster Computing Artificial Intelligence Hardware Architecture Robotics |
| url | https://arxiv.org/abs/2512.22139 |