Efficient Software Architecture Pattern for Accelerator Based Computing
Bhogendra Rao PVRR
Dr. PVRR Bhogendra Rao, Ph.D, JNTU, Hyderabad (Telangana), India.
Manuscript received on 25 February 2020 | Revised Manuscript received on 05 March 2020 | Manuscript Published on 15 March 2020 | PP: 64-69 | Volume-9 Issue-4S2 March 2020 | Retrieval Number: D10160394S220/2020©BEIESP | DOI: 10.35940/ijitee.D1016.0394S220
Open Access | Editorial and Publishing Policies | Cite | Zenodo | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open-access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Graphics Accelerators are increasingly used for general purpose high performance computing applications as they provide a low cost solution to high performance computing requirements. Intel also came out with a performance accelerator that offers a similar solution. However, the existing application software needs to be restructured to suit to the accelerator paradigm with a suitable software architecture pattern. In the present work, master-slave architecture is employed to convert CFD grid free Euler solvers in CUDA for GPGPU computing. The performance obtained using master-slave architecture for GPGPU computing is compared with that of sequential computing results.
Keywords: Software Architectures, Architecture Patterns, Parallel and Distributed Computing, GPGPU, CUDA Computing.
Scope of the Article: Software Engineering & Its Applications