Performance Analysis of Parallelized GPS Navigation System Using OpenMP and CUDA

View at publisher Summarise with VIRAT
Authors: A. Sivaranjani, P. Priya Ponnusamy, C. P. Shabariram, S.K. Thai Bhuvana
Cited by: 0
References: 8

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Parallel computing using CUDA is used in various scientific applications like image processing, Gaming, Graphics and computer vision. GPUs are used in CUDA to run the applications and achieves parallel execution. Our proposed algorithm shows the performance improvement of the GPS navigation application by implementing using CUDA (Compute Unified Device Architecture). This GPS navigation application uses breadth first technique to navigate the locations and directions of 15 cities. The cities are considered as vertices in breadth first algorithm and is implemented using CUDA parallel processing architecture. GPS navigation application is implemented and testing in both CUDA and OpenMP (Open Multiprocessor) environments. Performance measure of GPS navigation for different cities within a particular distance is taken into consideration. The algorithm's runtime is analyzed for the different hardware configurations of CPU and the GPU systems. By varying the number of threads per each block in CUDA, time taken for each city is measured. By varying the number of threads and cities, the result is compared for both the algorithms. The result shows CUDA performs 70 % better in processing the cities than openMP. is varied and the time taken for each set of vertices in the graph are noted. The performance of execution time is measured and significantly reduced in CUDA since it is processed with high performance parallel computing technology and the same is compared with openMP which is traditional methods uses CPU.

Fields of Study & Subjects

Parallel Computing and Optimization Techniques Graph Theory and Algorithms Computer Graphics and Visualization Techniques

Publication details

Journal / source
International Conference on Intelligent Systems for Communication, IoT and Security (ICISCoIS)
Pages
1–7
Publication date
8 January 2026
Language
EN