Author : Sameer S. Chikane 1
Date of Publication :10th August 2017
Abstract: Fractional calculus a field dealing with mathematical analysis has its applications in various domains such as power transmission units, image processing, financial system design, automobiles and various control system. There are many advantages of fractional calculus in analytical world. But, the computational cost accompanied with it has prevented software implementations to achieve real-time performance for large and complex computations. This paper exhibits the parallel computing power of the Graphics Processing Unit (GPU) in the area of fractional-order integration. Numerical methods for implementing different fractional-order derivatives and integrations are available. By using MATLAB Parallel Computing Toolbox, GPU computational power can be easily accessed with minimum knowledge of GPU architecture and MATLAB code can be executed on the GPU. The fractional-order integration by Trapezoidal formula using NVIDIA GPU with support of MATLAB Parallel Computing Toolbox is implemented in order to achieve faster execution. Performance comparison of the algorithm for sequential implementation on CPU and parallel implementation on GPU is carried out. This new algorithm produces significant speedup in the computations of fractional-order integration and provide required result in much less time as compared to execution on CPU.
Reference :
-
- Keith Oldham and Jerome Spanier. The fractional calculus theory and applications of differentiation and integration to arbitrary order, volume 111. Elsevier, 1974.
- Igor Podlubny. Fractional differential equations: an introduction to fractional derivatives, fractional differential equations, to methods of their solution and some of their applications, volume 198. Academic press, 1998.
- Cristobal A Navarro, Nancy Hitschfeld-Kahler, and Luis Mateu. A survey on parallel computing and its applications in data-parallel problems using gpu architectures. Communications in Computational Physics, 15(02):285– 329, 2014.
- Ian Buck, Tim Foley, Daniel Horn, Jeremy Sugerman, Kayvon Fatahalian, Mike Houston, and Pat Hanrahan. Brook for gpus: stream computing on graphics hardware. In ACM Transactions on Graphics (TOG), volume 23, pages 777–786. ACM, 2004.
- Wei Zhang and Xing Cai. Efficient implementations of the adams-bashforth-moulton method for solving fractional differential equations. Proceedings of FDA12, 2012
- Parallel computation toolbox. URL https://in.mathworks. com/help/distcomp/.
- Karsten Ahnert, Denis Demidov, and Mario Mulansky. Solving ordinary differential equations on gpus. In Numerical Computations with GPUs, pages 125–157. Springer, 2014.
- Baida Zhang, Shuai Xu, Feng Zhang, Yuan Bi, and Linqi Huang. Accelerating matlab code using gpu: A review of tools and strategies. In Artificial Intelligence, Management Science and Electronic Commerce (AIMSEC), 2011 2nd International Conference on, pages 1875–1878. IEEE, 2011
- CPU versus GPU architecture. accessed 15 July, 2017. URL http://854320174.r.lightningbase-cdn.com/ wp-content/uploads/2013/03/gputech f2.png.
- Jacket - the gpu acceleration engine for matlab, 2017. URL http://www.omatrix.com/jacket.html.
- Peter Messmer, Paul J Mullowney, and Brian E Granger. Gpulib: Gpu computing in high-level languages. Computing in Science & Engineering, 10(5):70–73, 2008.
- Changpin Li and Fanhai Zeng. Numerical methods for fractional calculus, volume 24. CRC Press, 2015.
