|
|
Acceleration of Applications on a Supercomputer Using Python
Čelka, Marek ; Jaroš, Jiří (referee) ; Jaroš, Marta (advisor)
Nowadays, all computers we use are capable of parallel processing that saves time in compute-intensive tasks such as scientific computations, various simulations or predictions. The theme of this thesis is acceleration of compute-intensive tasks on supercomputer. This is achieved by the parallelization of the problem. For better understanding the issue by scientists from diverse scientific fields, the python programming language was chosen. Python is very powerful and easy to use as well. The first part of the thesis deals with the parallel processing techniques. The set of microtests was designed and implemented for this purpose. Results are then discussed and used in the further work. The second part of the thesis deals with the problem of parallel image reconstruction. For a comparison, the sequential version of the problem was also implemented. Both versions, sequential and parallel, were tested on a set of images of a different size. Experiments focus on acceleration, spent time, memory bandwidth and latency. These outcomes are also presented and discussed.
|
|
|
Hough Transform for Line Detection
Leikep, Bořek ; Beran, Vítězslav (referee) ; Španěl, Michal (advisor)
This paper is describing use of the Hough Transform for line detection. It also contains theoretical description of circle detection and detection of more complex subjects. The goal of this work is to evaluate implementation of line detection in C# on Microsoft .NET platform mostly from a time consumption point of view. The paper contains description of implementation of the application Detektor which is part of this work.
|
|
|
Acceleration of Applications on a Supercomputer Using Python
Čelka, Marek ; Jaroš, Jiří (referee) ; Jaroš, Marta (advisor)
Nowadays, all computers we use are capable of parallel processing that saves time in compute-intensive tasks such as scientific computations, various simulations or predictions. The theme of this thesis is acceleration of compute-intensive tasks on supercomputer. This is achieved by the parallelization of the problem. For better understanding the issue by scientists from diverse scientific fields, the python programming language was chosen. Python is very powerful and easy to use as well. The first part of the thesis deals with the parallel processing techniques. The set of microtests was designed and implemented for this purpose. Results are then discussed and used in the further work. The second part of the thesis deals with the problem of parallel image reconstruction. For a comparison, the sequential version of the problem was also implemented. Both versions, sequential and parallel, were tested on a set of images of a different size. Experiments focus on acceleration, spent time, memory bandwidth and latency. These outcomes are also presented and discussed.
|
|
|
Hough Transform for Line Detection
Leikep, Bořek ; Beran, Vítězslav (referee) ; Španěl, Michal (advisor)
This paper is describing use of the Hough Transform for line detection. It also contains theoretical description of circle detection and detection of more complex subjects. The goal of this work is to evaluate implementation of line detection in C# on Microsoft .NET platform mostly from a time consumption point of view. The paper contains description of implementation of the application Detektor which is part of this work.
|
guest ::
