|
|
Simulation of Heat Diffusion in the Brain Using the OpenACC Library
Oškera, Josef ; Kadlubiak, Kristián (referee) ; Jaroš, Jiří (advisor)
The aim of this work is to rewrite the implementation of heat transfer in brain written in programming language Matlab (available in the k-Wave package) into C / C ++, accelerate it on GPU using library OpenACC and CUDA, and then compare these libraries in performance and complexity of implementation. The solution describes how to program a graphics card and how to apply this knowledge. The created program is able to simulate heat dissipation on CPU and GPU.
|
|
|
Efficient Implementation of High Performance Algorithms on Intel Xeon Phi
Šimek, Dominik ; Hrbáček, Radek (referee) ; Jaroš, Jiří (advisor)
This thesis is dedicated to the implementation of high performance algorithms on the Intel Xeon Phi coprocessor. The Xeon phi was introduced by Intel as a new MIC (Many Integrated Core) architecture in 2012. The theoretical part of the thesis is focused on the architecture of the coprocessor (with peak performance of 2 tFLOPS for a single precision data) and on the procedure of algorithms implementation and optimization. The theoretical knowledge is then applied to a practical examples with demonstration of the implementation and the optimization of algorithms and work with the coprocessor. In the practical part of the thesis, simple benchmarks such as a vector matrix multiplication and a matrix multiplication are explained and implemented. In the first benchmark 6.5% of theoretical coprocessor performance was achieved, in the second it was much more. In following chapter a more complex benchmark - simulation of a particles system (N-Body), that reached more than 35% of coprocessor performance (725 gFLOPS), is discussed. The following section is dedicated to some interesting problems such as optimization of a MATLAB module k-Wave (propagation of the ultrasound waves), extraction of I-vector (speech processing), cross-compilation of existing libraries, modules and programs. In the conclusion of the thesis the usage the potential of the Intel Xeon Phi is evaluated.
|
|
|
Ultrasound Simulation in Python
Černý, David ; Olšák, Ondřej (referee) ; Jaroš, Jiří (advisor)
k-Wave je MATLAB nástroj pro simulaci šíření zvukových vln. Cílem této práce je reimplementovat část nástroje k-Wave v jazyce Python se zaměřením na výpočetní výkon. Druhým cílem je formulace sady doporučení pro transformaci zdrojových kódu z jazyka MATLAB do jazyka Python, které by mohly přispět při dalším vývoji. Tato práce nejprve shrnuje klíčové funkce nástroje k-Wave, zkoumá technologie pro vysoce výkonné výpočty dostupné v jazyce Python a zdůrazňuje nejzásadnější aspekty transformace zdrojových kódů z jazyka MATLAB do jazyka Python. Druhá část práce se zabývá architekturou, testováním a měřením výkonu výsledné Python implementace. Výsledkem této práce je implementace trojrozměrné simulace šíření zvuku, která je kompatibilní s k-Wave. Nová implementace vylepšuje strukturu původního nástroje a poskytuje výkon srovnatelný s původním nástrojem, v určitých případech výkon původního balíku převyšuje.
|
|
| |
|
|
Parallelisation of Ultrasound Simulations on Intel Xeon Phi Accelerator
Vrbenský, Andrej ; Hrbáček, Radek (referee) ; Jaroš, Jiří (advisor)
Nowadays, the simulation of ultrasound acoustic waves has a wide range of practical usage. As one of them we can name the simulation in realistic tissue media, which is successfully used in medicine. There are several software applications dedicated to perform such simulations. k-Wave is one of them. The computational difficulty of the simulation itself is very high, and this leaves a space to explore new speed-up methods. In this master's thesis, we proposed a way to speed-up the simulation based on parallelization using Intel Xeon Phi accelerator. The accelerator contains large amount of cores and an extra-wide vector unit, and therefore, is ideal for purpose of parallelization and vectorization. The implementation is using OpenMP version 4.0, which brings some new options such as explicit vectorization. Results were measured during extensive experiments.
|
|
|
Parallelization of Ultrasound Simulations Using 2D Decomposition
Nikl, Vojtěch ; Dvořák, Václav (referee) ; Jaroš, Jiří (advisor)
This thesis is a part of the k-Wave project, which is a toolbox for the simulation and reconstruction of acoustic wave felds and one of its main contributions is the planning of focused ultrasound surgeries (HIFU). One simulation can take tens of hours and about 60% of the simulation time is taken by the calculation of the 3D Fast Fourier transforms. Up until now the 3D FFT has been calculated purely by the FFTW library and its 1D decomposition, whose major limitation is the maximum number of employable cores. Therefore we introduce a new approach, called the 2D hybrid decomposition of the 3D FFT (HybridFFT), where we combine both MPI processes and OpenMP threads to reach as best performance as possible. On a low number of cores, on the order of a few hundreds, we are about as fast or slightly faster than FFTW and pure MPI 2D decomposition libraries (PFFT and P3DFFT). One of the best results was achieved on a 512^3FFT using 512 cores, where our hybrid version run 31ms, FFTW run 39ms and PFFT run 44ms. The most significant performance advantage should be seen when employing around 8-16 thousand cores, however we haven't had an access to a machine with such resources. Almost a linear scalability has been proven for up to 2048 employed cores.
|
|
|
Visualisation of Ultrasound Propagation in Human Body
Klepárník, Petr ; Jaroš, Jiří (referee) ; Španěl, Michal (advisor)
This work deals with the 2D and 3D visualization of simulation outputs from the k-Wave toolbox. This toolbox, designed to accurately model the propagation of ultrasound waves in the human body, usually generates immense amounts of output data (up to hundreds of GB). That is why new methods for both the visualization and the effective data representation are necessary to be developed to help users to easily understand the simulation results. This thesis elaborates on the data format, simulation outputs are stored in, with the use of the HDF5 library and looking for the best way to quickly read the simulation data. Finally, the thesis presents the design and the implementation of the console-based application for big simulation data pre-processing and the GUI-based application for interactive visualization of the pre-processed data. The most significant features of these applications are downsampling data, changing the format of storing, viewing 2D sections, planar and volumetric visualization and animation of the simulation process. The proposed implementation allows parts of the simulation domain to be visualised within tens of milliseconds even if the simulation domain comprises GBs of data - This significantly streamlines the work of scientists and clinicians in the field of HIFU.
|
|
|
Acceleration of Ultrasound Neurostimulation Using Multi-GPU Systems
Bayer, David ; Kadlubiak, Kristián (referee) ; Jaroš, Jiří (advisor)
This theses is focused on extending the accelerated implementation of propagating acoustic waves in a medium simulation of k-Wave toolbox by the possibility of using multiple GPUs for the computation. It first describes multi-GPU systems in general and the tools that can be used to work with them. It continues with a description of the k-Wave toolbox and an analysis of existing accelerated implementations. Selected technologies are then tested on a heat diffusion in a medium simulation and the results are used to select tools for the design a resulting implementation. Finally, it summarizes the results obtained.
|
|
|
Estimation of Algorithm Execution Time Using Machine Learning
Buchta, Martin ; Chlebík, Jakub (referee) ; Jaroš, Jiří (advisor)
This work aims to predict the execution time of k-Wave ultrasound simulations on supercomputers based on a given domain size. The program uses MPI and can be run on multiple nodes. Prediction models were developed using symbolic regression and neural networks, both of which trained on captured data and compared against each other. The results demonstrate that the models outperform existing solutions. Specifically, the symbolic regression model achieved an average error of 5.64% for suitable tasks, while the neural network model achieved an average error of 8.25% on unseen domain sizes and across all tasks, including those not optimized for k-Wave simulations. This work contributes a new, more accurate model for predicting execution time, and compares the effectiveness of neural networks and symbolic regression for this specific type of regression problem. Overall, these findings suggest that new models will have important practical applications in the field of k-Wave ultrasound simulations.
|
|
|
Acceleration of Ultrasound Neurostimulation Using Mixed-Precision Arithmetic
Duchoň, Radek ; Olšák, Ondřej (referee) ; Jaroš, Jiří (advisor)
K-Wave is an open source tool for acoustic and ultrasound simulation. Current available implementations are written in C++ and Matlab. The aim of this thesis is to accelerate the existing implementation of ultrasound simulation by means of lower precision calculations on Nvidia graphics cards using the CUDA software platform. Another benefit of this work should be a reduced memory requirement, which will enable larger simulations to be performed. However, due to the use, for example, for neurostimulation of the brain, the reduced accuracy must not disturb the results as a whole too much. It is therefore important to identify suitable quantities that can be stored in lower precision. In this work, possible approaches and their effectiveness in utilizing lower precision will be analyzed. Furthermore, a solution proposal will be made, which will include identifying potential variables for reduction. This will be followed by specifying the achieved implementation and its testing. The conclusion will focus on evaluating the solution based on the results obtained from the testing.
|
guest ::
