RT Journal Article
T1 CPU and GPU oriented optimizations for LiDAR data processing
A1 Muñoz, Felipe
A1 Asenjo-Plaza, Rafael
A1 Navarro, Ángeles
A1 Cabaleiro, J. Carlos
K1 Radar óptico
K1 Ordenadores - Memorias
AB Digital Terrain Models (DTM) can be accurately obtained from clouds of LiDAR points but the correspondingcloud processing time can be prohibitive. This paper describes several optimization techniques that have beenapplied to the Overlap Window Method (OWM) that is a key component in DTM applications. OWM wasoriginally implemented in R which translates into serious limitations in terms of the size of the LiDAR pointcloud that can be processed. We have ported the code to C++, significantly optimized the data structure tominimize memory accesses, and developed parallel implementations for CPU and GPU commodity devices usingoneAPI libraries and tools. This results in CPU and GPU versions that are up to 19x and 83x faster, respectively,than an OpenMP baseline that uses eight CPU cores. Most importantly, the proposed optimizations for CPUand GPU can be paramount to get the most out of other LiDAR-based algorithms in which the careful selectionof the right data structure, parallelization strategies and memory access reduction techniques will certainlyresult in significant performance improvements.
PB Elsevier
YR 2024
FD 2024-07
LK https://hdl.handle.net/10630/31410
UL https://hdl.handle.net/10630/31410
LA eng
NO Muñoz, Felipe , Asenjo, Rafael , Navarro Angeles , Cabaleiro J. Carlos. (2024). CPU and GPU oriented optimizations for LiDAR data processing, Journal of Computational Science, Volume 79, 2024, 102317, ISSN 1877-7503
NO Funding for open access charge: Universidad de Málag / CBUA
DS RIUMA. Repositorio Institucional de la Universidad de Málaga
RD 20 ene 2026