|
|
Parallel Programming in Rust Language
Šlampa, Ondřej ; Bařina, David (referee) ; Kobrtek, Jozef (advisor)
Topic of this thesis is parallelization in Rust. Aim of this thesis is to compare performance and usability of Rust language with already used alternative - OpenMP. Computation of n-dimensional comvolution was used for benchmark. In conclusion there is evaluation of results and suggestions for their future use.
|
|
|
Porting and Optimization Algorithms for Detecting Finger Veins on DSP Blackfin
Trhoň, Adam ; Drahanský, Martin (referee) ; Marvan, Aleš (advisor)
This thesis discuss optimizations of algorithms for finger vein map extraction from finger image taken in NIR spectrum. The algorithm is also ported on development kit with DSP Blackfin. For optimization the median filtering was mainly considered (resulting in histogram-based median filter) and the amount of memory used during extraction (resulting in semi-parallel pipeline of image filters). Simple hardware abstraction layer is also implemented.
|
|
|
Real-Time Object Localization
Rydlo, Štěpán ; Chudý, Peter (referee) ; Kolář, Dušan (advisor)
This bachelor thesis purposes solution of a radio signal processing to determine actual receiver position on computers using software defined radio. The purpose of this thesis is to create and parallelize program to achieve real-time processing . To achieve real-time processing we will use GPU . This work contains a description of two independent possibilities of data transfer and processing .
|
|
|
Real-Time Object Localization
Rydlo, Štěpán ; Chudý, Peter (referee) ; Kolář, Dušan (advisor)
This bachelor thesis purposes solution of a radio signal processing to determine actual receiver position on computers using software defined radio. The purpose of this thesis is to create and parallelize program to achieve real-time processing . To achieve real-time processing we will use GPU . This work contains a description of two independent possibilities of data transfer and processing .
|
|
|
Parallel Programming in Rust Language
Šlampa, Ondřej ; Bařina, David (referee) ; Kobrtek, Jozef (advisor)
Topic of this thesis is parallelization in Rust. Aim of this thesis is to compare performance and usability of Rust language with already used alternative - OpenMP. Computation of n-dimensional comvolution was used for benchmark. In conclusion there is evaluation of results and suggestions for their future use.
|
|
|
Porting and Optimization Algorithms for Detecting Finger Veins on DSP Blackfin
Trhoň, Adam ; Drahanský, Martin (referee) ; Marvan, Aleš (advisor)
This thesis discuss optimizations of algorithms for finger vein map extraction from finger image taken in NIR spectrum. The algorithm is also ported on development kit with DSP Blackfin. For optimization the median filtering was mainly considered (resulting in histogram-based median filter) and the amount of memory used during extraction (resulting in semi-parallel pipeline of image filters). Simple hardware abstraction layer is also implemented.
|
|
|
Generating Complex Procedural Terrains Using the GPU
Ryba, Jan ; Bartoň, Radek (referee) ; Herout, Adam (advisor)
Generating fully 3D terrains is a dificult task, meaning that we need to store a lot of data or do a lot of computing or both. We can reduce or completly eliminate the data srorage by using a procedural approch, but this is where the problem gets realy computationaly costly and the CUDA platform comes in. CUDA kernels runinng parallely on graphic accelerators can rapidly decrease time needed for computation, allowing even these complex calculations to work in real time or even better. Finding its use in game or movie industry.
|
|
|
Accelerated Image Resampling Library
Hamrský, Jan ; Bařina, David (referee) ; Polok, Lukáš (advisor)
This work deals with the task of image scaling using GPU paralelization. Portion of text is devoted to signal processing and his affection of whole result including measuring it's quality. Describtion of the most important methods including super-resolution is given further in the text. An important part of this thesis is library implementing choosen methods with usage of paralelization on graphic chip. Achieved results of paralelization are demonstrated on set of speed tests.
|
guest ::
