Bachelor's theses of year 2020
Theses and projects (PhD, MSc, BSc, Project)
-
Übertragung von Umweltdaten in eingeschränkten Netzwerken mithilfe von TinyIPFIX in RIOT.
12
2020.
BibTeX Entry
@misc{holg20, author = {Thomas Holger}, title = {Übertragung von {Umweltdaten} in eingeschränkten {Netzwerken} mithilfe von {TinyIPFIX} in {RIOT}}, year = {2020}, key = {holg20}, month = {12}, school = {Ludwig-Maximilians-Universität München}, supervisors = {Corinna Schmitt}, type = {Bachelorthesis}, } -
ARMv8 Virtualization Using VMware ESXi Hypervisor.
3
2020.
PDF
Abstract
One of the fastest-growing sectors in the digital technology market is the embedded device domain. Embedded devices are simple computing devices that form the basis of nearly all complex systems. However, embedded device development is limited by issues such as system complexity, security vulnerabilities, and resource constraints. Virtualization has been used since the 1970s to solve these same issues in mainframes and later servers and personal computers. This paper aims to answer whether hardware virtualization is a practical solution to the problems embedded devices currently face. First, the constraints that an embedded hypervisor would need to adhere to are elucidated and use cases examined for virtualization on embedded devices. A feasibility study was performed using VMware's ESXi hypervisor, which supports many of the use cases identified in the server domain. The ESXi hypervisor, programmed initially to only run on x86 processors, was modified to run on ARM processors, one of the market leaders in the embedded devices domain. Using the benchmarking suites LMbench3 and MiBench, it was found that the ESXi hypervisor on the MACCHIATObin Single Shot development board equipped with an ARMv8 processor has modest virtualization overhead compared to native execution. Additionally, ESXi was able to host up to five virtual machines, with variable virtualization overhead depending on the application. Although the evaluated ESXi hypervisor may already be suitable for some embedded devices, further evaluation and work needs to be performed on the scheduling policy of ESXi for devices that have real-time needs. Using Linux's cyclictest, it was determined that ESXi significantly increased the scheduling latency, which lowered the deterministic behavior of the system and increased the worst-case execution time, both crucial characteristics of real-time devices.BibTeX Entry
@misc{fran20, author = {Caroline Frank}, title = {{ARMv8} {Virtualization} {Using} {VMware} {ESXi} {Hypervisor}}, year = {2020}, pdf = {https://bib.nm.ifi.lmu.de/pdf/fran20.pdf}, abstract = {One of the fastest-growing sectors in the digital technology market is the embedded device domain. Embedded devices are simple computing devices that form the basis of nearly all complex systems. However, embedded device development is limited by issues such as system complexity, security vulnerabilities, and resource constraints. Virtualization has been used since the 1970s to solve these same issues in mainframes and later servers and personal computers. This paper aims to answer whether hardware virtualization is a practical solution to the problems embedded devices currently face. First, the constraints that an embedded hypervisor would need to adhere to are elucidated and use cases examined for virtualization on embedded devices. A feasibility study was performed using VMware's ESXi hypervisor, which supports many of the use cases identified in the server domain. The ESXi hypervisor, programmed initially to only run on x86 processors, was modified to run on ARM processors, one of the market leaders in the embedded devices domain. Using the benchmarking suites LMbench3 and MiBench, it was found that the ESXi hypervisor on the MACCHIATObin Single Shot development board equipped with an ARMv8 processor has modest virtualization overhead compared to native execution. Additionally, ESXi was able to host up to five virtual machines, with variable virtualization overhead depending on the application. Although the evaluated ESXi hypervisor may already be suitable for some embedded devices, further evaluation and work needs to be performed on the scheduling policy of ESXi for devices that have real-time needs. Using Linux's cyclictest, it was determined that ESXi significantly increased the scheduling latency, which lowered the deterministic behavior of the system and increased the worst-case execution time, both crucial characteristics of real-time devices.}, key = {fran20}, month = {3}, school = {Ludwig-Maximilians-Universität München}, supervisors = {Tobias Lindinger and Jan Schmidt}, type = {Bachelorthesis}, } -
Pattern Recognition with an Artificial Neuron on a Quantum Computer.
7
2020.
BibTeX Entry
@misc{beka20, author = {Besmir Beka}, title = {{Pattern} {Recognition} with an {Artificial} {Neuron} on a {Quantum} {Computer}}, year = {2020}, key = {beka20}, month = {7}, school = {Ludwig-Maximilians-Universität München}, supervisors = {Tobias Guggemos and Maximilian Höb}, type = {Bachelorthesis}, } -
Theoretical study of photon mapping with stratification.
7
2020.
PDF
Abstract
In the last decades computer-generated images have become indispensable. From product design over the game and film industry until medical analysis - computer graphics plays a significant role in all of these sectors. The photon mapping algorithm is a relevant method used for generating especially photo realistic images. In this work the bias of photon mapping in combination with stratified sampling is examined. For this purpose three types of scenes are considered: a one dimensional setup, surface illumination and volumetric effects. The theoretical study of all three setups detects an overestimation bias similar to the bias described in "Describing and Solution of an Unreported Intrinsic Bias in Photon Mapping Density Estimation with Constant Kernel" by Garcìa et al. This overestimation bias is verified afterwards with an experimental study of stratified photon mapping. With different estimates for calculating the irradiance that were used in other theoretical studies of photon mapping it is investigated how the detected overestimation bias for stratified photon mapping behaves. The estimate proposed by Garcìa et al. leads to a small underestimation bias while the another estimate presented in "A Practical Guide to Global Illumination using Photon Mapping" by Jensen et al. reduces the absolute value of the bias, showing a mixture between over- and underestimation. In the end it is presented scientific research that applies the theoretical concept behind photon mapping and it is proposed a study of variance in combination with stratified photon mapping for a future research area.BibTeX Entry
@misc{hart20, author = {Kathrin Hartmann}, title = {{Theoretical} study of photon mapping with stratification}, year = {2020}, pdf = {https://bib.nm.ifi.lmu.de/pdf/hart20.pdf}, abstract = {In the last decades computer-generated images have become indispensable. From product design over the game and film industry until medical analysis - computer graphics plays a significant role in all of these sectors. The photon mapping algorithm is a relevant method used for generating especially photo realistic images. In this work the bias of photon mapping in combination with stratified sampling is examined. For this purpose three types of scenes are considered: a one dimensional setup, surface illumination and volumetric effects. The theoretical study of all three setups detects an overestimation bias similar to the bias described in "Describing and Solution of an Unreported Intrinsic Bias in Photon Mapping Density Estimation with Constant Kernel" by Garcìa et al. This overestimation bias is verified afterwards with an experimental study of stratified photon mapping. With different estimates for calculating the irradiance that were used in other theoretical studies of photon mapping it is investigated how the detected overestimation bias for stratified photon mapping behaves. The estimate proposed by Garcìa et al. leads to a small underestimation bias while the another estimate presented in "A Practical Guide to Global Illumination using Photon Mapping" by Jensen et al. reduces the absolute value of the bias, showing a mixture between over- and underestimation. In the end it is presented scientific research that applies the theoretical concept behind photon mapping and it is proposed a study of variance in combination with stratified photon mapping for a future research area.}, key = {hart20}, month = {7}, school = {Ludwig-Maximilians-Universität München}, supervisors = {Ruben Garcia Hernandez}, type = {Bachelorthesis}, } -
Performanceanalyse von Stencil-Kernels auf FPGAs.
1
2020.
PDF
Abstract
In dieser Arbeit wird die Performance von OpenCL Stencil-Kernels auf Field-programmable Gate Arrays (FPGAs) untersucht. Ausgehend von einer naiven Implementierung werden inkrementell algorithmische und FPGA-spezifische OpenCL Compiler-Optimierungen ange- wandt und deren Auswirkung auf die Performance analysiert. Zur gezielten Optimierung und Analyse der Performance wird die Hardware-Architektur von FPGAs studiert. Es wird gezeigt, dass eine optimierte Implementierung, welche FPGA-spezifische Architek- tureigenschaften ausnutzt, eine Beschleunigung um einen Faktor von über 150 gegenüber einer naiven Implementierung eines Stencil-Algorithmus erreichen kann. Die erwartete Ener- gieeffizienz des optimierten Kernels liegt in der selben Größenordnung, wie die der besten Supercomputer aus der Green500-Liste im November 2019. In this study the performance of OpenCL stencil kernels on Field-programmable Gate Ar- rays (FPGAs) is investigated. Starting from a naive implementation, incremental algorithmic and FPGA-specific OpenCL compiler optimizations are applied and their impact on perfor- mance is analyzed. The hardware architecture of FPGAs is studied to optimize and analyze the performance in a targeted manner. It is shown that an optimized implementation, which takes advantage of FPGA-specific architecture properties, can achieve an acceleration by a factor of over 150 compared to a naive implementation of a stencil algorithm. The expected energy efficiency of the optimi- zed kernel is of the same order of magnitude as that of the best supercomputers from the Green500 list in November 2019.BibTeX Entry
@misc{brei20, author = {Sergej Breiter}, title = {{Performanceanalyse} von {Stencil-Kernels} auf {FPGAs}}, year = {2020}, pdf = {https://bib.nm.ifi.lmu.de/pdf/brei20.pdf}, abstract = {In dieser Arbeit wird die Performance von OpenCL Stencil-Kernels auf Field-programmable Gate Arrays (FPGAs) untersucht. Ausgehend von einer naiven Implementierung werden inkrementell algorithmische und FPGA-spezifische OpenCL Compiler-Optimierungen ange- wandt und deren Auswirkung auf die Performance analysiert. Zur gezielten Optimierung und Analyse der Performance wird die Hardware-Architektur von FPGAs studiert. Es wird gezeigt, dass eine optimierte Implementierung, welche FPGA-spezifische Architek- tureigenschaften ausnutzt, eine Beschleunigung um einen Faktor von über 150 gegenüber einer naiven Implementierung eines Stencil-Algorithmus erreichen kann. Die erwartete Ener- gieeffizienz des optimierten Kernels liegt in der selben Größenordnung, wie die der besten Supercomputer aus der Green500-Liste im November 2019. In this study the performance of OpenCL stencil kernels on Field-programmable Gate Ar- rays (FPGAs) is investigated. Starting from a naive implementation, incremental algorithmic and FPGA-specific OpenCL compiler optimizations are applied and their impact on perfor- mance is analyzed. The hardware architecture of FPGAs is studied to optimize and analyze the performance in a targeted manner. It is shown that an optimized implementation, which takes advantage of FPGA-specific architecture properties, can achieve an acceleration by a factor of over 150 compared to a naive implementation of a stencil algorithm. The expected energy efficiency of the optimi- zed kernel is of the same order of magnitude as that of the best supercomputers from the Green500 list in November 2019.}, key = {brei20}, month = {1}, school = {Ludwig-Maximilians-Universität München}, supervisors = {Pascal Jungblut}, type = {Bachelorthesis}, } -
Technology Comparison for long-term Retention of Contract Data.
1
2020.
PDF
Abstract
With the emergent development of blockchain technology, the number and variety of applications increases. Businesses, such as life insurance companies, are considering using it as their storage solution. It has potential benefits over the traditional option of relational databases like immutable data. For life insurance companies a significant part of IT projects is data migration. In the worst case, contract durations can be up to 120 years. This thesis helps deciding if blockchain is a suitable candidate for long retention of contracts. Mandatory technology features of data storage and native data migration will be collected. Based on these, blockchain technology will be compared with relational databases management systems. To select the most suitable blockchain system, several approaches are compared regarding their data model. Hyperledger Fabric determined to be the best choice. Since the comparison focused on the use case of this thesis relational databases show clear advantages over the blockchain technology Hyperledger Fabric.BibTeX Entry
@misc{geig20, author = {Luca Geiger}, title = {{Technology} {Comparison} for long-term {Retention} of {Contract} {Data}}, year = {2020}, pdf = {https://bib.nm.ifi.lmu.de/pdf/geig20.pdf}, abstract = {With the emergent development of blockchain technology, the number and variety of applications increases. Businesses, such as life insurance companies, are considering using it as their storage solution. It has potential benefits over the traditional option of relational databases like immutable data. For life insurance companies a significant part of IT projects is data migration. In the worst case, contract durations can be up to 120 years. This thesis helps deciding if blockchain is a suitable candidate for long retention of contracts. Mandatory technology features of data storage and native data migration will be collected. Based on these, blockchain technology will be compared with relational databases management systems. To select the most suitable blockchain system, several approaches are compared regarding their data model. Hyperledger Fabric determined to be the best choice. Since the comparison focused on the use case of this thesis relational databases show clear advantages over the blockchain technology Hyperledger Fabric.}, key = {geig20}, month = {1}, school = {Ludwig-Maximilians-Universität München}, supervisors = {Maximilian Höb and Peter Blenninger}, type = {Bachelorthesis}, } -
Asymptotic and Experimental Analysis of k-way Merging Algorithms.
8
2020.
BibTeX Entry
@misc{wach20, author = {Henrik Wachowitz}, title = {{Asymptotic} and {Experimental} {Analysis} of k-way {Merging} {Algorithms}}, year = {2020}, key = {wach20}, month = {8}, school = {Ludwig-Maximilians-Universität München}, supervisors = {Roger Kowalewski}, type = {Bachelorthesis}, } -
Extension and Parallelisation of Voro++ for Moving-Mesh Hydrodynamical Simulations.
8
2020.
BibTeX Entry
@misc{lutz20a, author = {Maximilian Lutz}, title = {{Extension} and {Parallelisation} of {Voro++} for {Moving-Mesh} {Hydrodynamical} {Simulations}}, year = {2020}, key = {lutz20a}, month = {8}, school = {Ludwig-Maximilians-Universität München}, supervisors = {Karl Fuerlinger}, type = {Bachelorthesis}, } -
Evaluation of the interaction with and emotional reaction to stereoscopic digital testimonies.
9
2020.
BibTeX Entry
@misc{hoss20, author = {Roman Hosseini}, title = {{Evaluation} of the interaction with and emotional reaction to stereoscopic digital testimonies}, year = {2020}, key = {hoss20}, month = {9}, school = {Ludwig-Maximilians-Universität München}, supervisors = {Daniel Kolb}, type = {Bachelorthesis}, } -
DTLS-based Security Solution for Contrained Devices using Contiki.
9
2020.
BibTeX Entry
@misc{stur20, author = {Julian Sturm}, title = {{DTLS-based} {Security} {Solution} for {Contrained} {Devices} using {Contiki}}, year = {2020}, key = {stur20}, month = {9}, school = {Ludwig-Maximilians-Universität München}, supervisors = {Tobias Guggemos and Corinna Schmitt}, type = {Bachelorthesis}, } -
Quantifizierung von Default Routen in BGP.
10
2020.
BibTeX Entry
@misc{kozh20, author = {Oleksandra Kozhukhova}, title = {{Quantifizierung} von {Default} {Routen} in {BGP}}, year = {2020}, key = {kozh20}, month = {10}, school = {Ludwig-Maximilians-Universität München}, supervisors = {Nils Rodday}, type = {Bachelorthesis}, } -
Schwachstellenanalyse eines arduino basierten Abrechnungssystems.
10
2020.
BibTeX Entry
@misc{wagn20, author = {Maximilian Wagner}, title = {{Schwachstellenanalyse} eines arduino basierten {Abrechnungssystems}}, year = {2020}, key = {wagn20}, month = {10}, school = {Ludwig-Maximilians-Universität München}, supervisors = {David Schmitz and Helmut Tröbs}, type = {Bachelorthesis}, } -
Automated Neural Network Parallelization Strategy Finding on a Supercomputer.
11
2020.
BibTeX Entry
@misc{quan20, author = {Marcel Quanz}, title = {{Automated} {Neural} {Network} {Parallelization} {Strategy} {Finding} on a {Supercomputer}}, year = {2020}, key = {quan20}, month = {11}, school = {Ludwig-Maximilians-Universität München}, supervisors = {Karl Fuerlinger}, type = {Bachelorthesis}, } -
Vulnerabilities and Security Measures in Container Environments.
11
2020.
BibTeX Entry
@misc{schi20, author = {Stephan Schiller}, title = {{Vulnerabilities} and {Security} {Measures} in {Container} {Environments}}, year = {2020}, key = {schi20}, month = {11}, school = {Ludwig-Maximilians-Universität München}, supervisors = {Tobias Lindinger and Jan Schmidt}, type = {Bachelorthesis}, } -
OT-Security Requirements Ensuring Functional Safety in the Production Environment for Defense Against Cyber Attacks.
12
2020.
BibTeX Entry
@misc{lang20, author = {Tobias Langer}, title = {{OT-Security} {Requirements} {Ensuring} {Functional} {Safety} in the {Production} {Environment} for {Defense} {Against} {Cyber} {Attacks}}, year = {2020}, key = {lang20}, month = {12}, school = {Ludwig-Maximilians-Universität München}, supervisors = {Stefan Metzger and Michael Schmidt}, type = {Bachelorthesis}, } -
Home Automation System Integration in SecureWSN.
12
2020.
BibTeX Entry
@misc{webe20, author = {Marvin Weber}, title = {{Home} {Automation} {System} {Integration} in {SecureWSN}}, year = {2020}, key = {webe20}, month = {12}, school = {Ludwig-Maximilians-Universität München}, supervisors = {Corinna Schmitt}, type = {Bachelorthesis}, } -
Evaluation der LLC-Struktur von Prozessoren der "Intel Skylake-SP"-Serie.
12
2020.
BibTeX Entry
@misc{brin20, author = {Ferdinand Brinker}, title = {{Evaluation} der {LLC-Struktur} von {Prozessoren} der {"Intel} {Skylake-SP"-Serie}}, year = {2020}, key = {brin20}, month = {12}, school = {Ludwig-Maximilians-Universität München}, supervisors = {Amir Kabouteh and Pascal Jungblut}, type = {Bachelorthesis}, } -
Effects of Memory Bandwidth in Sorting Algorithm.
12
2020.
BibTeX Entry
@misc{amma20, author = {Philipp Ammann}, title = {{Effects} of {Memory} {Bandwidth} in {Sorting} {Algorithm}}, year = {2020}, key = {amma20}, month = {12}, school = {Ludwig-Maximilians-Universität München}, supervisors = {Roger Kowalewski}, type = {Bachelorthesis}, }
Disclaimer:
This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All person copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.