Making the most ef?cient use of computer systems has rapidly become a leading topic of interest for the computer industry and its customers alike. However, the focus of these discussions is often on single, isolated, and speci?c architectural and technological improvements for power reduction and conservation, while ignoring the fact that power ef?ciency as a ratio of performance to power consumption is equally in?uenced by performance improvements and architectural power red- tion. Furthermore, ef?ciency can be in?uenced on all levels of today's system hi- archies from single cores all the way to distributed Grid environments. To improve execution and power ef?ciency requires progress in such diverse ?elds as program optimization, optimization of program scheduling, and power reduction of idling system components for all levels of the system hierarchy. Improving computer system ef?ciency requires improving system performance and reducing system power consumption. To research and reach reasonable conc- sions about system performance we need to not only understand the architectures of our computer systems and the available array of code transformations for p- formance optimizations, but we also need to be able to express this understanding in performance models good enough to guide decisions about code optimizations for speci?c systems. This understanding is necessary on all levels of the system hierarchy from single cores to nodes to full high performance computing (HPC) systems, and eventually to Grid environments with multiple systems and resources.

Making the most ef?cient use of computer systems has rapidly become a leading topic of interest for the computer industry and its customers alike. However, the focus of these discussions is often on single, isolated, and speci?c architectural and technological improvements for power reduction and conservation, while ignoring the fact that power ef?ciency as a ratio of performance to power consumption is equally in?uenced by performance improvements and architectural power red- tion. Furthermore, ef?ciency can be in?uenced on all levels of today's system hi- archies from single cores all the way to distributed Grid environments. To improve execution and power ef?ciency requires progress in such diverse ?elds as program optimization, optimization of program scheduling, and power reduction of idling system components for all levels of the system hierarchy. Improving computer system ef?ciency requires improving system performance and reducing system power consumption. To research and reach reasonable conc- sions about system performance we need to not only understand the architectures of our computer systems and the available array of code transformations for p- formance optimizations, but we also need to be able to express this understanding in performance models good enough to guide decisions about code optimizations for speci?c systems. This understanding is necessary on all levels of the system hierarchy from single cores to nodes to full high performance computing (HPC) systems, and eventually to Grid environments with multiple systems and resources.

For more than ten years we have been working with the ideal linear MHD equations used to study the stability of thermonuc1ear plasmas. Even though the equations are simple and the problem is mathematically well formulated, the numerical problems were much harder to solve than anticipated. Already in the one-dimensional cylindrical case, what we called "spectral pollution" appeared. We were able to eliminate it by our "ecological solution." This solution was applied to the two-dimensional axisymmetric toroidal geometry. Even though the spectrum was unpolluted the precision was not good enough. Too many mesh points were necessary to obtain the demanded precision. Our solution was what we called the "finite hybrid elements." These elements are efficient and cheap. They have also proved their power when applied to calculating equilibrium solutions and will certainly penetrate into other domains in physics and engineering. During all these years, many colleagues have contributed to the construc tion, testing and using of our stability code ERATO. We would like to thank them here. Some ofthem gave partial contributions to the book. Among them we mention Dr. Kurt Appert, Marie-Christine Festeau-Barrioz, Roberto Iacono, Marie-Alix Secretan, Sandro Semenzato, Dr. Jan Vac1avik, Laurent Villard and Peter Merkel who kindly agreed to write Chap. 6. Special thanks go to Hans Saurenmann who drew most of the figures, to Dr."

th This volume contains the papers presented at the 8 International Conference on - vanced Parallel Processing Technologies, APPT 2009. This series of conferences originated from collaborations between researchers from China and Germany and has evolved into an international conference for reporting advances in parallel processing technologies. APPT 2009 addressed the entire gamut of related topics, ranging from the architectural aspects of parallel computer hardware and system software to the applied technologies for novel applications. For this conference, we received over 76 full submissions from researchers all over the world. All the papers were peer reviewed in depth and qualitatively graded on their relevance, originality, significance, presentation, and the overall appropriateness for their acceptance. Any concerns raised were discussed by the Program Committee. The Organizing Committee did an excellent job in selecting 36 papers for presen- tion. In short, the papers included here represent the forefront of research from China, Switzerland, Germany, and other countries.