The week's pick
Reseach Article
A Comparative Study of GPU Computing by using CUDA and OpenCL
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 128 - Number 17 |
| Year of Publication: 2015 |
| Authors: Asad Mohhamad, Vikram Garg |
10.5120/ijca2015906022
|
Asad Mohhamad, Vikram Garg . A Comparative Study of GPU Computing by using CUDA and OpenCL. International Journal of Computer Applications. 128, 17 ( October 2015), 1-3. DOI=10.5120/ijca2015906022
Abstract
Parallel computing becomes a need to perform task as soon as possible. This can be done in two way improve hardware or use parallel programming language i.e. improve software. Improvement in the hardware is costlier solution compared to software solution. So we have two basic heterogeneous parallel languages CUDA and OpenCL which run on both CPU and GPU according to necessity. When program does not contain high parallelism it works on CPU which contains less number of cores. On other hand program contain high degree of parallelism so each independent code runs on separate core of GPU. This paper gives the basic idea of the parallel computing and how these carried out. Explain the working of both parallel language CUDA and OpenCL with their detailed architecture. In the last section comparison of both languages is described.
References
- J. D. Owens, D. Luebke, N. Govindaraju, M. Harris, J. Kru¨ger, A. E. Lefohn and T. Purcell B, “ A survey of general-purpose computation on graphics hardware”, Comput. Graph. Forum, vol. 26, no. 1, pp. 80–113, 2007.
- K. Fatahalian and M. Houston, “A closer look at GPUs,” Communications of the ACM, Vol. 51, No. 10, October 2008.
- Z. Fan, F. Qiu, A. Kaufman, S. Yoakum-Stove, “GPU Cluster for High Performance Computing,”, in Proc. ACM/IEEE conference on Supercomputing, 2004.
- D. Tarditi, S. Puri, and J. Oglesby, “Accelerator: Using data-parallelism to program GPUs for general-purpose uses”, in Proc. 12th Int. Conf. Architect. Support Program. Lang. Oper. Syst., pp. 325-335, Oct. 2006.
- John D. Owens, Mike Houston, David Luebke and Simon Green,” GPU Computing Graphics Processing Units-powerful, programmable, and highly parallel-are increasingly targeting general-purpose computing applications”, In the procd. Of IEEE Xplore, Vol. 96, no. 5, May 2008.
- John Nickolls, William J. Dally NVIDIA, “THE GPU COMPUTING ERA”, In the procd. Of IEEE Computer Society, page no. 56-69, March 2010.
- Danilo De Donno, Alessandra Esposito, Luciano Tarricone, and Luca Catarinucci, “Introduction to GPU Computing and CUDA Programming: A Case Study on FOlD” In the procd. Of IEEE Antennas and Propagation Magazine, Vol. 52, No.3, June 2010.
- NVIDIA Corporation Technical Staff, NVIDIA CUDA Programming Guide 2.2, NVIDIA Corporation, 2009.
- M. Harris, S. Sengupta, and J. D. Owens, “Parallel prefix sum (scan) with CUDA”, in GPU Gems 3, H. Nguyen, Ed. Reading, MA: Addison-Wesley, pp. 851–876, Aug. 2007.
- J. Nickolls et al., ‘‘Scalable Parallel Programming with CUDA,’’ ACM Queue, vol. 6, no. 2, pp. 40-53, 2008.
- Ching-Lung Su, Po-Yu Chen, Chun-Chieh Lan, Long-Sheng Huang, and Kuo-Hsuan Wu, “Overview and Comparison of OpenCL and CUDA Technology for GPGPU” In the procd. Of IEEE, Page no. 448-451, 2012.
- Misic, M.J., Durdevic, D.M. ; Tomasevic, M.V., “Evolution and trends in GPU computing” In the procd. Of IEEE 35th International Convention MIPRO, Page no. 289-294, 21-25 May 2012.
- Jääskeläinen, Pekka O., de La Lama, Carlos S, Huerta, Pablo, Takala and Jarmo H, "OpenCL-based design methodology for application-specific processors", In the procd. Of IEEE International Conference on Embedded Computer Systems (SAMOS), February 17, 2011.
- Benedict R Gaster, LEE Howes, David Kaeli, Perhaad Mistry and Dana Schaa, “Hetrogeneous Computing with OpenCL” Book publised by Elsevier, 2012.
- Aaftab Munshi, Benedict R. Gaster, Timothy G. Mattson, James Fung and Dan Ginsburg, “OpenCL Programming Guide”, Book publised by Pearson Education, 2012.
Index Terms
Keywords