Indisponible

An der TU Chemnitz haben sich seit über zwei Jahrzehnten die Gebiete der rechnergestützten Wissenschaften (Computational Science) sowie des parallelen und verteilten Hochleistungsrechnens mit zunehmender Verzahnung entwickelt. Die Koordinierung und Bündelung entsprechender Forschungsarbeiten in der Profillinie 6 “Modellierung, Simulation, Hochleistungsrechnen” wird es ermöglichen, im internationalen Wettbewerb des Wissens mitzuhalten.

This thesis explores the possibility of using parallel algorithms to calculate the dynamics of driven quantum systems prevalent in atomic physics. In this process, new as well as existing algorithms are considered. The thesis is split into three parts. In the first part an attempt is made to develop a new formalism of the time dependent Schroedinger equation (TDSE) in the hope that the new formalism could lead to a parallel algorithm. The TDSE is written as an eigenvalue problem, the ground state of which represents the solution to the original TDSE. Even though mathematically sound and correct, it turns out the ground state of this eigenvalue problem cannot be easily found numerically, rendering the original hope a false one. In the second part we borrow a Bayesian global optimisation method from the machine learning community in an effort to find the optimum conditions in different systems quicker than textbook optimisation algorithms. This algorithm is specifically designed to find the optimum of expensive functions, and is used in this thesis to 1. maximise the electron yield of hydrogen, 2. maximise the asymmetry in the photo-electron angular distribution of hydrogen, 3. maximise the higher harmonic generation yield within a certain frequency range, 4. generate short pulses via combining higher harmonics generated by hydrogen. In the last part, the phenomenon of dynamic interference (temporal equivalent of the double-slit experiment) is discussed. The necessary conditions are derived from first principles and it is shown where some of the previous analytical and numerical studies have gone wrong; it turns out the choice of gauge plays a crucial role. Furthermore, a number of different scenarios are presented where interference in the photo-electron spectrum is expected to occur.

This thesis explores the possibility of using parallel algorithms to calculate the dynamics of driven quantum systems prevalent in atomic physics. In this process, new as well as existing algorithms are considered. The thesis is split into three parts. In the first part an attempt is made to develop a new formalism of the time dependent Schroedinger equation (TDSE) in the hope that the new formalism could lead to a parallel algorithm. The TDSE is written as an eigenvalue problem, the ground state of which represents the solution to the original TDSE. Even though mathematically sound and correct, it turns out the ground state of this eigenvalue problem cannot be easily found numerically, rendering the original hope a false one. In the second part we borrow a Bayesian global optimisation method from the machine learning community in an effort to find the optimum conditions in different systems quicker than textbook optimisation algorithms. This algorithm is specifically designed to find the optimum of expensive functions, and is used in this thesis to 1. maximise the electron yield of hydrogen, 2. maximise the asymmetry in the photo-electron angular distribution of hydrogen, 3. maximise the higher harmonic generation yield within a certain frequency range, 4. generate short pulses via combining higher harmonics generated by hydrogen. In the last part, the phenomenon of dynamic interference (temporal equivalent of the double-slit experiment) is discussed. The necessary conditions are derived from first principles and it is shown where some of the previous analytical and numerical studies have gone wrong; it turns out the choice of gauge plays a crucial role. Furthermore, a number of different scenarios are presented where interference in the photo-electron spectrum is expected to occur.

User-programmable, integrated circuits (ICs) e.g. Field Programmable Gate Arrays (FPGAs) are increasingly popular for embedded, high-performance data exploitation. They combine the parallelization capability and processing power of application specific integrated circuits (ASICs) with the exibility, scalability and adaptability of software-based processing solutions. FPGAs provide powerful processing resources due to an optimal adaptation to the target application and a well-balanced ratio of performance, efficiency and parallelization. One drawback of FPGA-based data exploitation is the limited memory capacity of reconfigurable integrated circuits. Large-scale Digital Signal Processor (DSP) FPGAs provide approximately 4MB on-board random access memory (RAM) which is not sufficient to buffer the broadband sensor and result data. Hence, additional external memory is connected to the FPGA to increase on-board storage capacities. External memory devices like double data rate three synchronous dynamic random access memories (DDR3-SDRAM) provide very fast and wide bandwidth interfaces that represent a bottleneck when used in highly parallelized processing architectures. Independent processing modules are demanding concurrent read and write access. Within the master thesis, a concept for the integration of an external DDR3- SDRAM into an FPGA-based parallelized processing architecture is developed and implemented. The solution realizes time division multiple access (TDMA) to the external memory and virtual, low-latency memory extension to the on-board buffer capabilities. The integration of the external RAM does not change the way how on-board buffers are used (control, data-fow).

So far, data warehousing has often been discussed in the light of complex OLAP queries and as reporting facility for operative data. We argue that business planning as a means to generate plan data is an equally important cornerstone of a data warehouse system, and we propose it to be a first-class citizen within an OLAP engine. We introduce an abstract model describing relevant aspects of the planning process in general and the requirements it poses to a planning engine. Furthermore, we show that business planning lends itself well to parallelization and benefits from a column-store much like traditional OLAP does. We then develop a physical model specifically targeted at a highly parallel column-store, and with our implementation, we show nearly linear scaling behavior.

Database Systems are often used as persistent layer for applications. This implies that database schemas are generated out of transient programming class descriptions. The basic idea of the MDA approach generalizes this principle by providing a framework to generate applications (and database schemas) for different programming platforms. Within our GignoMDA project [3]--which is subject of this demo proposal--we have extended classic concepts for code generation. That means, our approach provides a single point of truth describing all aspects of database applications (e.g. database schema, project documentation,...) with great potential for cross-layer optimization. These new cross-layer optimization hints are a novel way for the challenging global optimization issue of multi-tier database applications. The demo at VLDB comprises an in-depth explanation of our concepts and the prototypical implementation by directly demonstrating the modeling and the automatic generation of database applications.

Als offen angelegtes Experiment brachte Echohaus 2009 ein klassisch-modernes Ensemble mit einen elektronischen DIY-Musiker und einem Produzenten für Underground-Popmusik zusammen. Für die einwöchigen Aufnahmen in dem Hamburger Studio Electric Avenue galten einige Regeln: keine künstlichen Halleffekte oder digitalen Plug-Ins verwenden, nur die akustischen Reflexionen echter Räume, keine Overdubs. 2010 erschien aus dem Projekt ein Tonträger beim Hamburger Avantgarde-Label Dekorder. Im gleichen Jahr gab es eine Uraufführung beim Märzmusik Festival in den Berliner Sophiensaelen. Aus Anlaß des 10-jährigen Jubiläums des Raum-Klang-Projektes Echohaus sprachen die beiden Komponisten und Musiker Felix Kubin und Burkhard Friedrich über dieses Projekt und die grundlegende Bedeutung von Raum als Klangkörper, vom Komponieren durch Bewegung im Raum und von technisch generierten parallelen Räumen.

Frequent-itemset mining is an essential part of the association rule mining process, which has many application areas. It is a computation and memory intensive task with many opportunities for optimization. Many efficient sequential and parallel algorithms were proposed in the recent years. Most of the parallel algorithms, however, cannot cope with the huge number of threads that are provided by large multiprocessor or many-core systems. In this paper, we provide a highly parallel version of the well-known Eclat algorithm. It runs on both, multiprocessor systems and many-core coprocessors, and scales well up to a very large number of threads---244 in our experiments. To evaluate mcEclat's performance, we conducted many experiments on realistic datasets. mcEclat achieves high speedups of up to 11.5x and 100x on a 12-core multiprocessor system and a 61-core Xeon Phi many-core coprocessor, respectively. Furthermore, mcEclat is competitive with highly optimized existing frequent-itemset mining implementations taken from the FIMI repository.

In dieser Dissertation werden Programmtransformationen für die Klasse der regulär-irregulären Schleifenkomplexe, welche typischerweise in komplexen Simulationscodes für Vielteilchensysteme auftreten, betrachtet. Dabei wird die Effizienz der resultierenden Programme auf modernen Multicore-Systemen untersucht. Reguläre Schleifenkomplexe zeichnen sich durch feste Schleifengrenzen und eine regelmäßige Struktur der Abhängigkeiten der Berechnungen aus, bei irregulären Berechnungen sind Abhängigkeiten zwischen Berechnungen erst zur Laufzeit bekannt und stark von den Eingabedaten abhängig. Die hier betrachteten regulären-irregulären Berechnungen koppeln beide Arten von Berechnungen eng. Die Herausforderung der effizienten Realisierung regulär-irregulärer Schleifenkomplexe auf modernen Multicore-Systemen liegt in der Kombination von Transformationstechnicken, die sowohl ein hohes Maß an Parallelität erlauben als auch die Lokalität der Berechnungen berücksichtigen. Moderne Multicore-Systeme bestehen aus einer komplexen Speicherhierachie aus privaten und gemeinsam genutzten Caches, sowie einer gemeinsamen Speicheranbindung. Diese neuen architektonischen Merkmale machen es notwendig Programmtransformationen erneut zu betrachten und die Effizienz der Berechnungen neu zu bewerten. Es werden eine Reihe von Transformationen betrachtet, die sowohl die Reihenfolge der Berechnungen als auch die Reihenfolge der Abspeicherung der Daten im Speicher ändern, um eine erhöhte räumliche und zeitliche Lokalität zu erreichen. Parallelisierung und Lokalität sind eng verknüpft und beeinflussen gemeinsam die Effizienz von parallelen Programmen. Es werden in dieser Arbeit verschiedene Parallelisierungsstrategien für regulär-irreguläre Berechnungen für moderne Multicore-Systeme betrachtet. Einen weiteren Teil der Arbeit bildet die Betrachtung rein irregulärer Berechnungen, wie sie typisch für eine große Anzahl von Vielteilchensimualtionscodes sind. Auch diese Simulationscodes wurden für Multicore-Systeme betrachtet und daraufhin untersucht, inwieweit diese auf modernen Multicore-CPUs skalieren. Die neuartige Architektur von Multicore-System, im besonderen die in hohem Maße geteilte Speicherbandbreite, macht auch hier eine neue Betrachtung solcher rein irregulärer Berechnungen notwendig. Es werden Techniken betrachtet, die die Anzahl der zu ladenden Daten reduzieren und somit die Anforderungen an die gemeinsame Speicherbandbreite reduzieren.