|
|
Water Simulation Using GPU
Hanzlíček, Jiří ; Jaroš, Jiří (referee) ; Vaverka, Filip (advisor)
The goal of this thesis is to find a suitable model of fluids, the numerical simulation of which can be realized as interactive program. This requirement leads to a solution based on highly parallel algorithm. The implementation is built not only for CPU, but also GPU in a way, that allows to compare computational performance of each device on selected model.
|
|
|
Non-Blocking Input/Output for the k-Wave Toolbox
Kondula, Václav ; Vaverka, Filip (referee) ; Jaroš, Jiří (advisor)
This thesis deals with an implementation of non-blocking I/O interface for the k-Wave project, which is designed for time-domain simulation of ultrasound propagation. Main focus is on large domain simulations that, due to high computing power requirements, must run on supercomputers and produce tens of GB of data in a single simulation step. In this thesis, I have designed and implemented a non-blocking interface for storing data using dedicated threads, which allows to overlap simulation calculations with disk operations in order to speed up the simulation. An acceleration of up to 33% was achieved compared to the current implementation of project k-Wave, which resulted, among other things, also to reduce cost of the simulation.
|
|
|
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 .
|
|
|
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.
|
|
|
Configurable Parallel Execution of System Tests within the Strimzi Project
Orsák, Maroš ; Rogalewicz, Adam (referee) ; Češka, Milan (advisor)
V poslednych rokoch mnoho spolocnosti prijalo Kubernetes a architekturu mikrosluzieb, ktoru umoznuje. Tato technologia otvorila nove moznosti nielen pre velke spolocnosti, ale aj pre malych vyvojarov softveru. Kubernetes je system riadenia kontajnerov a nedavno sa objavil novy koncept, ako efektivnejsie organizovat kontajnery - vzor operatora. Jeden takyto operator je vyvinuty a udrziavany v ramci open-source projektu s nazvom Strimzi. Projekt Strimzi spaja niekolko nastrojov, ktore sa staraju o nasadenie Apache Kafka na Kubernetes. Kedze Kafka je komplexny, horizontalne skalovatelny, distribuovany system, viete si predstavit, ze jeho instalacia je pomerne zlozita akcia. Preto jednou z najvacsich vyziev pouzivania Kubernetes je, ako efektivne a rychlo otestovat projekty ako Kafka a Strimzi a zaroven overit integraciu s inymi podobnymi produktmi. Zdroje, ktore potrebuje Kubernetes, su ovela narocnejsie v porovnani s nasadenim Kafka na virtualne stroje alebo typicke instancie kontajnerov. Aby sme tento problem vyriesili, prijali sme principy par- alelneho vykonavania a vytvorili mechanizmus v ramci systemovych testov Strimzi, ktory paralelne spusta testy iba proti jedinemu klastru Kubernetes. Okrem toho sme navrhli uplne novu architekturu pre end-to-end testy. Vylepsenia su zamerane na skalovatelnost a skratenie casu vykonavania . Prostrednictvom niekolkych experimentov tato praca ukazuje, ze navrhovany mechanizmus s roznymi konfiguraciami klastra Kubernetes (vratane pocet uzlov Kubernetes , pocet paralelne vykonavanych testov a sad ) vyrazne urychlil vykonavanie testov.
|
|
|
Configurable Parallel Execution of System Tests within the Strimzi Project
Orsák, Maroš ; Rogalewicz, Adam (referee) ; Češka, Milan (advisor)
V poslednych rokoch mnoho spolocnosti prijalo Kubernetes a architekturu mikrosluzieb, ktoru umoznuje. Tato technologia otvorila nove moznosti nielen pre velke spolocnosti, ale aj pre malych vyvojarov softveru. Kubernetes je system riadenia kontajnerov a nedavno sa objavil novy koncept, ako efektivnejsie organizovat kontajnery - vzor operatora. Jeden takyto operator je vyvinuty a udrziavany v ramci open-source projektu s nazvom Strimzi. Projekt Strimzi spaja niekolko nastrojov, ktore sa staraju o nasadenie Apache Kafka na Kubernetes. Kedze Kafka je komplexny, horizontalne skalovatelny, distribuovany system, viete si predstavit, ze jeho instalacia je pomerne zlozita akcia. Preto jednou z najvacsich vyziev pouzivania Kubernetes je, ako efektivne a rychlo otestovat projekty ako Kafka a Strimzi a zaroven overit integraciu s inymi podobnymi produktmi. Zdroje, ktore potrebuje Kubernetes, su ovela narocnejsie v porovnani s nasadenim Kafka na virtualne stroje alebo typicke instancie kontajnerov. Aby sme tento problem vyriesili, prijali sme principy par- alelneho vykonavania a vytvorili mechanizmus v ramci systemovych testov Strimzi, ktory paralelne spusta testy iba proti jedinemu klastru Kubernetes. Okrem toho sme navrhli uplne novu architekturu pre end-to-end testy. Vylepsenia su zamerane na skalovatelnost a skratenie casu vykonavania . Prostrednictvom niekolkych experimentov tato praca ukazuje, ze navrhovany mechanizmus s roznymi konfiguraciami klastra Kubernetes (vratane pocet uzlov Kubernetes , pocet paralelne vykonavanych testov a sad ) vyrazne urychlil vykonavanie testov.
|
|
|
Analýza paralelizovatelnosti programů na základě jejich bytecode
Brabec, Michal ; Bednárek, David (advisor)
Analysis of automatic program parallelization based on bytecode There are many algorithms for automatic parallelization and this work explores the possible application of these algorithms to programs based on their bytecode or similar intermediate code. All these algorithms require the identification of independent code segments, because if two parts of code do not interfere with one another then they can be run in parallel without any danger of data corruption. Dependence testing is an extremely complicated problem and in general application, it is not algorithmically solvable. However, independences can be discovered in special cases and then they can be used as a basis for application of automatic parallelization, like the use of vector instructions. The first step is function inlining that allows the compiler to analyze the code more precisely, without unnecessary dependences caused by unknown functions. Next, it is necessary to identify all control flow constructs, like loops, and after that the compiler can attempt to locate dependences between the statements or instructions. Parallelization can be achieved only if the analysis discovered some independent parts in the code. This work is accompanied by an implementation of function inlining and code analysis for the .NET framework.
|
|
|
Non-Blocking Input/Output for the k-Wave Toolbox
Kondula, Václav ; Vaverka, Filip (referee) ; Jaroš, Jiří (advisor)
This thesis deals with an implementation of non-blocking I/O interface for the k-Wave project, which is designed for time-domain simulation of ultrasound propagation. Main focus is on large domain simulations that, due to high computing power requirements, must run on supercomputers and produce tens of GB of data in a single simulation step. In this thesis, I have designed and implemented a non-blocking interface for storing data using dedicated threads, which allows to overlap simulation calculations with disk operations in order to speed up the simulation. An acceleration of up to 33% was achieved compared to the current implementation of project k-Wave, which resulted, among other things, also to reduce cost of the simulation.
|
|
|
Analýza paralelizovatelnosti programů na základě jejich bytecode
Brabec, Michal ; Bednárek, David (advisor)
Analysis of automatic program parallelization based on bytecode There are many algorithms for automatic parallelization and this work explores the possible application of these algorithms to programs based on their bytecode or similar intermediate code. All these algorithms require the identification of independent code segments, because if two parts of code do not interfere with one another then they can be run in parallel without any danger of data corruption. Dependence testing is an extremely complicated problem and in general application, it is not algorithmically solvable. However, independences can be discovered in special cases and then they can be used as a basis for application of automatic parallelization, like the use of vector instructions. The first step is function inlining that allows the compiler to analyze the code more precisely, without unnecessary dependences caused by unknown functions. Next, it is necessary to identify all control flow constructs, like loops, and after that the compiler can attempt to locate dependences between the statements or instructions. Parallelization can be achieved only if the analysis discovered some independent parts in the code. This work is accompanied by an implementation of function inlining and code analysis for the .NET framework.
|
|
|
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 .
|
guest ::
