<p>In this thesis project we have successfully added an MPI extension layer to the LOIS framework. The framework defines an infrastructure for executing and connecting continuous stream processing applications. The MPI extension provides the same amount of stream based data as the framework’s original transport. We assert that an MPI-2 compatible implementation can be a candidate to extend the given framework with an adaptive and flexible communication sub-system. Adaptability is required since the communication subsystem has to be resilient to changes, either due to optimizations or system requirements.</p>

Software developers are faced with several challenges when creating applications for the new generation of mobile devices. Smartphones and tablets have limited processing power and memory resources, and a small battery is the only thing that keeps the hardware components running. End users have little patience for slow applications that drain the batteries of their devices. To satisfy the needs of their customers, developers must take these hardware limitations into account; they must make an effort to optimize the performance and energy efficiency of their applications. This thesis provides a general overview of performance and energy optimization in the mobile domain. A specific sub-area is explored in great detail: the use of native C code for performance and energy optimization of Android applications. An experiment was conducted to see how the performance of native code compares to that of Java. This is the first time that such measurements have been made on both emulators and physical devices. The devices were running recent versions of Android that have not been used for similar experiments before: 2.3.3, 3.2 and 4.0.3. It is also the first time that native code has been compared to Java in terms of energy consumption. The results show that the latest updates to the Android platform have brought Java closer to native code in terms of performance, but native code is still the best choice for certain types of operations. It is also evident that there is a close correlation between performance and energy efficiency. Finally, the results show that Android emulators are unreliable for performance measurements. This could be a reason to question the validity of previous research.

In this thesis project we have successfully added an MPI extension layer to the LOIS framework. The framework defines an infrastructure for executing and connecting continuous stream processing applications. The MPI extension provides the same amount of stream based data as the framework’s original transport. We assert that an MPI-2 compatible implementation can be a candidate to extend the given framework with an adaptive and flexible communication sub-system. Adaptability is required since the communication subsystem has to be resilient to changes, either due to optimizations or system requirements.

In der heutigen Zeit werden autonome Roboter in sehr vielen Bereichen eingesetzt. Wichtige Voraussetzungen für viele dieser Einsatzbereiche sind die Kartierung einer Umgebung sowie die autonome Navigation und Orientierung innerhalb dieser Karte. Dafür kann SLAM (Simultaneous Localization And Mapping) eingesetzt werden. Der Google Cartographer ist eine Software, die solche Funktionen bereitstellt. Diese Arbeit gibt zu Beginn einen grundlegenden Überblick über die vielseitigen Anwendungsgebiete und unterschiedlichen Funktionsweisen von SLAM. Im Weiteren wurden einzelne Algorithmen des Google Cartographers analysiert, sowie die Ergebnisse und deren Genauigkeit mit einem anderen SLAM Algorithmus verglichen. Weiterhin zeigt die Arbeit eine mögliche Anbindung des in C++ entwickelten Google Cartographers an Java über JNI (Java Native Interface). Abschließend wurden die Ergebnisse der Arbeit und der Nutzen der aus der Arbeit entstandenen Erkenntnisse und des entwickelten JNI ausgewertet. / In today's world, autonomous robots are used in many areas. Important requirements for many of these fields of application are the mapping of an environment as well as autonomous navigation and orientation within this map. SLAM (Simultaneous Localization And Mapping) can be used for this purpose. The Google Cartographer is a software that provides such functions. At the beginning, this thesis gives a basic overview of the versatile application areas and different functionalities of SLAM. Furthermore, individual algorithms of the Google Cartographer were analyzed and results and accuracy were compared with another SLAM algorithm. Furthermore the thesis shows a possible connection of the Google Cartographers developed in C++ to Java over JNI (Java Native Interface). Finally, the results and the benefits of the knowledge, gained from the thesis and the developed JNI, were evaluated.

The aim of this study is to examine the capability, performance, and relevance of a signal processing toolkit in Java, a programming language for Web-based applications. Due to the simplicity, ease and application use of the toolkit and with the advanced Internet technologies such as Remote Method Invocation (RMI), a spectral estimation applet has been created in the Java environment. This toolkit also provides an interactive and visual approach in understanding the various theoretical concepts of spectral estimation and shows the need to create more application applets to better understand the various concepts of signal and image processing. This study also focuses on creating a Java toolkit for embedded systems, such as Personal Digital Assistants (PDAs), embedded Java board, and supporting integer precision, and utilizing COordinate Rotation DIgital Computer (CORDIC) algorithm, both aimed to provide good performance in resource-limited environments. The results show a feasibility and necessity of developing a standardized Application Programming Interface (API) for the fixed-point signal processing library.

Points-to analysis is a static program analysis that tries to predict the dynamic behavior of programs without running them. It computes reference information by approximating for each pointer in the program a set of possible objects to which it could point to at runtime. In order to justify new analysis techniques, they need to be compared to the state of the art regarding their accuracy and efficiency. One of the main parameters influencing precision in points-to analysis is context-sensitivity that provides the analysis of each method separately for different contexts it was called on. The problem raised due to providing such a property to points-to analysis is decreasing of analysis scalability along with increasing memory consumption used during analysis process. The goal of this thesis is to present a comparison of precision and scalability of context-sensitive and context-insensitive analysis using three different points-to analysis techniques (Spark, Paddle, P2SSA) produced by two research groups. This comparison provides basic trade-offs regarding scalability on the one hand and efficiency and accuracy on the other. This work was intended to involve previous research work in this field consequently to investigate and implement several specific metrics covering each type of analysis regardless context-sensitivity – Spark, Paddle and P2SSA. These three approaches for points-to analysis demonstrate the intended achievements of different research groups. Common output format enables to choose the most efficient type of analysis for particular purpose.

Programmers compose programs in multiple languages to combine the advantages of innovations in new high-level programming languages with decades of engineering effort in legacy libraries and systems. For language inter-operation, language designers provide two classes of multilingual programming interfaces: (1) foreign function interfaces and (2) code generation interfaces. These interfaces embody the semantic mismatch for developers and multilingual systems builders. Their programming rules are difficult or impossible to verify. As a direct consequence, multilingual programs are full of bugs at interface boundaries, and debuggers cannot assist developers across these lines. This dissertation shows how to use composition of single language systems and interposition to improve the safety of multilingual programs. Our compositional approach is scalable by construction because it does not require any changes to single-language systems, and it leverages their engineering efforts. We show it is effective by composing a variety of multilingual tools that help programmers eliminate bugs. We present the first concise taxonomy and formal description of multilingual programming interfaces and their programming rules. We next compose three classes of multilingual tools: (1) Dynamic bug checkers for foreign function interfaces. We demonstrate a new approach for automatically generating a dynamic bug checker by interposing on foreign function interfaces, and we show that it finds bugs in real-world applications including Eclipse, Subversion, and Java Gnome. (2) Multilingual debuggers for foreign function interfaces. We introduce an intermediate agent that wraps all the methods and functions at language boundaries. This intermediate agent is sufficient to build all the essential debugging features used in single-language debuggers. (3) Safe macros for code generation interfaces. We design a safe macro language, called Marco, that generates programs in any language and demonstrate it by implementing checkers for SQL and C++ generators. To check the correctness of the generated programs, Marco queries single-language compilers and interpreters through code generation interfaces. Using their error messages, Marco points out the errors in program generators. In summary, this dissertation presents the first concise taxonomy and formal specification of multilingual interfaces and, based on this taxonomy, shows how to compose multilingual tools to improve safety in multilingual programs. Our results show that our compositional approach is scalable and effective for improving safety in real-world multilingual programs. / text