Bibliographic Details
| Title: |
A Scalability Evaluation Between Open MP, MPI and Open CL. |
| Authors: |
Kartita, Mohsine, Barodi, Anass, Chahid, Mohamed, Benbrahim, Mohammed, Zemmouri, Abdelkarim |
| Source: |
International Journal of Microwave & Optical Technology; Mar2026, Vol. 21 Issue 2, p181-190, 10p |
| Subject Terms: |
OpenCL (Computer program language), Scalability, Benchmark problems (Computer science), Parallel computers, Parallel programming, Message passing (Computer science) |
| Abstract: |
This paper presents a study of the need to scale computing performance when a problem becomes more complex. When a relatively simple problem is due to its low cost, power efficiency, and compact design, a small micro-processor is initially chosen and sufficient to solve this problem. However, as the problem evolves and becomes more complex (for whatever reason) and more computing performance is needed, abandoning the use of the single processor is inevitable, and going through another solution which is parallelism is required. This allows tasks to be executed simultaneously, which will improve speed and efficiency. OpenMP, MPI and OpenCL Parallel Computing Methods (PCMs) are the ones used most nowadays, OpenMP and OpenCL are dedicated for the shared memory architectures and MPI is dedicated for the distributed memory architectures. Moreover, five benchmark applications are implemented using the mentioned PCMs above and a scalability evaluation has been performed. Therefore, the scalability evaluation demonstrated that OpenCL scaled better than OpenMP and MPI showing great performance improvements in 2 test cases, while MPI delivered better performance than OpenMP and OpenCL in 3 test cases. [ABSTRACT FROM AUTHOR] |
|
Copyright of International Journal of Microwave & Optical Technology is the property of International Journal of Microwave & Optical Technology and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) |
| Database: |
Complementary Index |