On the Accelerating of Two-dimensional Smart Laplacian Smoothing on the GPU

TL;DR

This paper introduces a GPU-accelerated implementation of 2D Smart Laplacian smoothing for mesh processing, achieving significant speedups and exploring data layouts, iteration forms, and CUDA Dynamic Parallelism to optimize performance.

Contribution

It presents a novel GPU implementation of Smart Laplacian smoothing that leverages different data layouts, iteration strategies, and CUDA features for enhanced efficiency.

Findings

Achieved up to 44x speedup on GPU GT640.

AoS data layout outperforms SoA in efficiency.

Using CUDA Dynamic Parallelism slightly improves performance.

Abstract

This paper presents a GPU-accelerated implementation of two-dimensional Smart Laplacian smoothing. This implementation is developed under the guideline of our paradigm for accelerating Laplacianbased mesh smoothing [13]. Two types of commonly used data layouts, Array-of-Structures (AoS) and Structure-of-Arrays (SoA) are used to represent triangular meshes in our implementation. Two iteration forms that have different choices of the swapping of intermediate data are also adopted. Furthermore, the feature CUDA Dynamic Parallelism (CDP) is employed to realize the nested parallelization in Smart Laplacian smoothing. Experimental results demonstrate that: (1) our implementation can achieve the speedups of up to 44x on the GPU GT640; (2) the data layout AoS can always obtain better efficiency than the SoA layout; (3) the form that needs to swap intermediate nodal coordinates is always slower than the one that does not swap data; (4) the version of our implementation with the use of the feature CDP is slightly faster than the version where the CDP is not adopted.