Thesis Details

Akcelerace aplikací na GPU v jazyce Python

Bachelor's Thesis Student: Turcel Matej Academic Year: 2016/2017 Supervisor: Čudová Marta, Ing.
English title
Acceleration of Python Applications on GPU
Language
Czech
Abstract

Compiled languages, such as C++, are conventionally used in the field of high performance computing (HPC). However, scripting languages like Python are more convenient and application development is quicker and simpler in these languages. This work compares C++ and Python in terms of the possibilities of computation acceleration on graphics card. Its aim is to show that scripting languages are also suitable for the implementation of HPC applications, and point out their advantages and disadvantages compared to compiled languages. To this purpose, a number of programs have been implemented. Several smaller programs for testing purposes and a larger one, implementing a computationally intensive problem. The implementations of these programs in C++ and Python are compared in terms of performance, as well as difficulty of implementation.

Keywords

high performance computing, acceleration of computation, graphics card, GPU acceleration, scripting languages, compiled languages, Python, C++, CUDA, PyCUDA, performance comparison, code size

Department
Degree Programme
Information Technology
Files
Status
defended, grade A
Date
14 June 2017
Reviewer
Committee
Sekanina Lukáš, prof. Ing., Ph.D. (DCSY FIT BUT), předseda
Dytrych Jaroslav, Ing., Ph.D. (DCGM FIT BUT), člen
Hrubý Martin, Ing., Ph.D. (DITS FIT BUT), člen
Kořenek Jan, doc. Ing., Ph.D. (DCSY FIT BUT), člen
Švéda Miroslav, prof. Ing., CSc. (DIFS FIT BUT), člen
Citation
TURCEL, Matej. Akcelerace aplikací na GPU v jazyce Python. Brno, 2017. Bachelor's Thesis. Brno University of Technology, Faculty of Information Technology. 2017-06-14. Supervised by Čudová Marta. Available from: https://www.fit.vut.cz/study/thesis/19652/
BibTeX
@bachelorsthesis{FITBT19652,
    author = "Matej Turcel",
    type = "Bachelor's thesis",
    title = "Akcelerace aplikac\'{i} na GPU v jazyce Python",
    school = "Brno University of Technology, Faculty of Information Technology",
    year = 2017,
    location = "Brno, CZ",
    language = "czech",
    url = "https://www.fit.vut.cz/study/thesis/19652/"
}
Back to top