Warp-centric GPU meta-meshing and fast triangulation of billion-scale lattice structures

2024-05-24

AI Summary

To address the severe memory explosion and excessive computational overhead in STL triangulation of lattice structures comprising billions of struts, this paper introduces *meta-mesh*—a novel intermediate representation that replaces conventional direct triangulation. Methodologically, we propose the first warp-centric GPU framework for meta-mesh generation, integrating custom compact encoding, cache-aware data structures, and dynamic load-balanced scheduling to substantially mitigate memory bandwidth pressure and warp divergence. A CPU–GPU asynchronous pipelining strategy enables efficient heterogeneous coordination. Evaluated on billion-scale lattice structures, our approach achieves two orders-of-magnitude speedup over state-of-the-art methods. Moreover, the generated meta-mesh supports resolution-agnostic remeshing, ensuring both high efficiency and broad reusability across downstream applications.

Technology Category

• Machine Learning: Hardware-aware ML
• Search and Optimization: Metareasoning and Metaheuristics
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

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
• Web Mining and Content Analysis: Bridging structured and unstructured data

Abstract

Lattice structures have been widely used in applications due to their superior mechanical properties. To fabricate such structures, a geometric processing step called triangulation is often employed to transform them into the STL format before sending them to 3D printers. Because lattice structures tend to have high geometric complexity, this step usually generates a large amount of triangles, a memory and compute-intensive task. This problem manifests itself clearly through large-scale lattice structures that have millions or billions of struts. To address this problem, this paper proposes to transform a lattice structure into an intermediate model called meta-mesh before undergoing real triangulation. Compared to triangular meshes, meta-meshes are very lightweight and much less compute-demanding. The meta-mesh can also work as a base mesh reusable for conveniently and efficiently triangulating lattice structures with arbitrary resolutions. A CPU+GPU asynchronous meta-meshing pipeline has been developed to efficiently generate meta-meshes from lattice structures. It shifts from the thread-centric GPU algorithm design paradigm commonly used in CAD to the recent warp-centric design paradigm to achieve high performance. This is achieved by a new data compression method, a GPU cache-aware data structure, and a workload-balanced scheduling method that can significantly reduce memory divergence and branch divergence. Experimenting with various billion-scale lattice structures, the proposed method is seen to be two orders of magnitude faster than previously achievable.

Problem

• Optimize triangulation of billion-scale lattice structures
• Propose meta-mesh for efficient STL transformation
• Implement warp-centric GPU meta-meshing pipeline

Innovation

• Warp-centric GPU meta-meshing
• CPU+GPU asynchronous pipeline
• Lightweight meta-mesh for triangulation