Performance Evaluation of Matrix Products on Multicore Architectures

Silva, SharlonAlmida de and Scepke, Claudio and Agrawal, Natuan (2022) Performance Evaluation of Matrix Products on Multicore Architectures. International Journal of Advances in Engineering and Management (IJAEM), 4 (7). pp. 195-199. ISSN 2395-5252

[img]
Preview
Text
Performance Evaluation of Matrix Products on Multicore Architectures.pdf

Download (183kB) | Preview

Abstract

Scientific applications tend to deal with large volumes of data, as is the case with simulations of natural phenomena, which demand high computational power. Alternatively, using multi-core computers for processing contribute to performance improvement. However, performing specific optimizations for the target architecture can further influence performance. Therefore, the the objective of this work is to evaluate the impact of optimization techniques on application performance as well as test the performance of these techniques in multi-core and many-core architectures. For that, a matrix multiplication algorithm was chosen for the application of Loop Interchange, and Loop Tiling techniques. Furthermore, this algorithm was parallelized with OpenMP and CUDA to explore the different processing cores of the computational architectures used. The results show that algorithms optimized for a target architecture gain performance, and this gain can reach 11 times in sequential optimizations for cache memory and 100 times in parallel execution with OpenMP on Intel Xeon E5-2650 processors. Furthermore, this performance gain can be leveraged on the NVidia TITAN Xp GPU up to 1720 times.

Item Type: Article
Keywords (Kata Kunci): Matrix Product, Algorithm Optimization, Multi-core, many-core architectures.
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Q Science > QA Mathematics > QA76 Computer software
Divisions: Fakultas Teknik
Depositing User: Dr Tso Chen
Date Deposited: 14 Jul 2022 23:32
Last Modified: 14 Jul 2022 23:32
URI: http://eprints.unram.ac.id/id/eprint/29840

Actions (login required)

View Item View Item