Dissertation zur Erlangung des Grades eines

zur Erlangung des akademischen Grades eines Doktor-Ingenieur (Dr.-Ing.)

Power-gating is the most promising run-time technique in order to reduce leakage currents in sub-100nm CMOS devices but its application is associated with numerous problems. Overhead costs in terms of additional state transition costs occur, the targeted circuit is slowed down while being in the active state, additional interfacing circuits are necessary, and in general the total impact of the power-gating technique is hard to predict at early design stages. The goal of this thesis is to develop power-gating models for functional units at RT-level to enable design tradeoffs and to optimize the high-level synthesis for the use of this design technique. Main contributions of this work are • Fast and accurate power-gating models for an estimation of the functional unit’s energy demand during the static active and sleep state as well as during a state transition, • Optimized scheduling, binding, and allocation approaches that are able to increase the profitability of a cycle-wise power-gating and to expand the design-space exploration, and • A consistent design flow of the high-level synthesis decisions to subsequent design tools. In this thesis, such an estimation and optimization framework is proposed. The models are characterized

Unterstützung wäre diese Arbeit nicht möchlicht gewesen. Dafür sei an dieser Stelle gedankt. Mein besonderer Dank gilt Herrn Prof. Dr.-Ing. Hans Fahlenkamp für die stetes wohlwollende

Dissertation zur Erlangung des naturwissenschaftlichen Doktorgrades der Julius–Maximilians–Universität Würzburg vorgelegt von Barbara Staehle aus

zur

zur Erlangung des akademischen Grades eines

Dissertation zur Erlangung des akademischen Grades eines

ii iii Acknowledgment It is my pleasure to write down a few lines about the people who made my Ph.D. a nice, interesting, and rewarding experience. I found them always with me whenever I looked around. I would like to thank them for motivating and encouraging me during this venture. First and foremost, I am proudly grateful to my supervisor, Prof. Dr. Mesut Güne, whose thoughtful and logical guidance, insightful vision, continuing sup-port, and frank nature have leaded me to grow immensely over the couple of years. He not only motivated me on technical grounds and provided friendly and enlight-ening environment but also gave me full freedom to explore my research interests. How to start with research, how to formulate research problems, how to narrow down research interests, what is the technical writing and many more `hows ' and `whats ' I have learnt from him. His suggestions other than technical ones are also of higher value to my future life. In simple, this work would have never happened if it wasn't with him. I would like to express my special gratitude to Prof. Dr. Jochen Schiller for being cooperative and helpful throughout these years. Taking this opportunity, I would also like to thank Dr. Abd-Al-Basset Al-Mamou, Bastian Blywis, Qasim Mushtaq, Felix Juraschek, Hans Peter Heitzman, and all other colleagues for their constant support and help. I am deeply indebted to my wife and children for bearing with me during my research time and for being away from parents, relatives, and friends whilst sacrificing own education, language, culture, and much more. I have no words to explain incessant support from my mother, brothers, sisters, and friends during this time. This achievement is only possible with their understanding, patience, and encouragement. Thank you very much.

iAbstract Self-managing (or autonomic) databases are intended to reduce the total cost of ownership for a DBS by automatically adapting to evolving workloads and environments. To reach this goal, commercial database management systems (DBMS) have recently been equipped with self-management