Thesis (Selection of subject)Thesis (Selection of subject)(version: 285)
Assignment details
   Login via CAS
Parallel data-processing on GPGPU
Thesis title in Czech: Parallel data-processing on GPGPU
Thesis title in English: Parallel data-processing on GPGPU
Key words: paralelní, GPU, OpenCL, třídění, průnik množin
English key words: parallel, GPU, OpenCL, sorting, set intersection
Academic year of topic announcement: 2010/2011
Type of assignment: diploma thesis
Thesis language: angličtina
Department: Department of Software Engineering (32-KSI)
Supervisor: RNDr. Martin Kruliš, Ph.D.
Author: hidden - assigned and confirmed by the Study Dept.
Date of registration: 08.11.2010
Date of assignment: 08.11.2010
Date and time of defence: 28.05.2012 09:00
Date of electronic submission:12.04.2012
Date of submission of printed version:12.04.2012
Date of proceeded defence: 28.05.2012
Reviewers: RNDr. Filip Zavoral, Ph.D.
 
 
 
Guidelines
Modern graphics cards are no longer limited to execution of hardwired operations designed for 3D rendering, but also allow parallel processing of non-graphical data. This new architecture can yield much higher performance than conventional CPUs, for certain applications even in orders of magnitude. The main objective of this thesis is to determine which applications can prosper from GPGPU, and which ones prove themselves rather unsuitable for this architecture. The work will focus mainly on data-processing problems known in database systems; however, other problems (e.g. graph algorithms) will not escape our attention. Several example algorithms will be implemented and benchmarked. Based on the retrieved results, rules and hints for software developers will be formulated to help them decide whether particular algorithm is worth implementing on GPGPUs.
References
* Luebke, D. and Harris, M. and Govindaraju, N. and Lefohn, A. and Houston, M. and Owens, J. and Segal, M. and Papakipos, M. and Buck, I.: GPGPU: general-purpose computation on graphics hardware, Proceedings of the 2006 ACM/IEEE conference on Supercomputing, ACM 2006
* Frederic P. Miller, Agnes F. Vandome, and John McBrewster: GPGPU, Amazon
* Ryoji Tsuchiyama, Takashi Nakamura, Takuro Iizuka, and Akihiro Asahara: The OpenCL Programming Book, Amazon
* Bakkum, P. and Skadron, K.: Accelerating SQL database operations on a GPU with CUDA, Proceedings of the 3rd Workshop on General-Purpose Computation on Graphics Processing Units, ACM 2010
 
Charles University | Information system of Charles University | http://www.cuni.cz/UKEN-329.html