A Novel Implementation of QuickHull Algorithm on the GPU

TL;DR

This paper introduces a GPU-accelerated QuickHull algorithm that significantly speeds up convex hull computations for large point sets, demonstrating up to 11x faster performance than CPU methods.

Contribution

It presents a novel GPU implementation of QuickHull using parallel primitives, enabling efficient divide-and-conquer convex hull calculations on the GPU.

Findings

Achieves up to 10.98x speedup over CPU-based Qhull.

Finds convex hulls of 20 million points in approximately 0.2 seconds.

Demonstrates effective use of Thrust library primitives for parallel processing.

Abstract

We present a novel GPU-accelerated implementation of the QuickHull algorihtm for calculating convex hulls of planar point sets. We also describe a practical solution to demonstrate how to efficiently implement a typical Divide-and-Conquer algorithm on the GPU. We highly utilize the parallel primitives provided by the library Thrust such as the parallel segmented scan for better efficiency and simplicity. To evaluate the performance of our implementation, we carry out four groups of experimental tests using two groups of point sets in two modes on the GPU K20c. Experimental results indicate that: our implementation can achieve the speedups of up to 10.98x over the state-of-art CPU-based convex hull implementation Qhull [16]. In addition, our implementation can find the convex hull of 20M points in about 0.2 seconds.