L-PCN: A Point Cloud Accelerator Exploiting Spatial Locality through Octree-based Islandization

2026-04-12

AI Summary

Existing point cloud network accelerators fail to effectively exploit the spatial locality arising from overlapping point sets, resulting in redundant computation and excessive memory access overhead. This work is the first to identify and leverage such locality through an algorithm-hardware co-design approach: it introduces an octree-based island partitioning scheme coupled with a centroid scheduling mechanism, enabling feature computation at the island granularity and dynamic caching to reuse shared data within islands. This strategy substantially reduces feature extraction costs, theoretically cutting memory traffic by 55.2%–93.8% and computational workload by 45.4%–80.6%. A prototype FPGA implementation demonstrates an additional speedup of 1.2×–3.2× over state-of-the-art accelerators.

Technology Category

• Machine Learning: Hardware-aware ML
• Search and Optimization: Distributed Search
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• Security and Privacy: Large-scale security measurements

Abstract

Existing Point Cloud Networks (PCNs) have proven to achieve great success in many point cloud tasks such as object part segmentation, shape classification, and so on. The most popular point-based PCNs are usually composed of two sequential steps: Data Structuring (DS) and Feature Computation (FC). In this paper, we first describe an important characteristic of the PCN-specific DS step that has not been addressed in existing PCN accelerators: the spatial locality resulting from overlapping points of the gathered point subsets. Using algorithm-hardware co-design, L-PCN (Locality-aware PCN) proposes two novel techniques to exploit this characteristic to reduce the large amount of repetitive operations in the overall PCN. The first of which is a point cloud partitioning technique, Octree-based Islandization. Using Octree-based adjacency gathering, a point cloud is partitioned into islands in L-PCN, where the point subsets inside the same island exhibit a strong spatial correlation. After partitioning, L-PCN performs the rest of PCN steps at the granularity of islands. The second method of L-PCN is scheduling the intra-island computation with a Hub-based Scheduling to exploit the intra-island data reuse by dynamically caching, updating, and reusing the repeated data. The two methods are implemented in an Islandization Unit, which can be seamlessly integrated into standard PCN workflow. Our evaluation shows that based on our methods for exploiting spatial locality, L-PCN achieves a theoretical reduction in feature fetching ranging from 55.2% to 93.8% and in feature computation ranging from 45.4% to 80.6% during the PCN process. For experimentation, prototype L-PCN accelerators are implemented on the Intel Arria 10 GX FPGA. Experimental results prove that with the Islandization Unit as a plug-in, state-of-the-art PCN accelerators can achieve an additional speedup ranging from 1.2x to 3.2x.

Problem

• Point Cloud Networks
• Spatial Locality
• Data Structuring
• Feature Computation
• Accelerator

Innovation

• spatial locality
• Octree-based Islandization
• Hub-based Scheduling
• point cloud accelerator
• algorithm-hardware co-design