CURRICULUM VITAE
Hans P. Zima studied at the University of Vienna, where he received his Ph.D. degree in Mathematics in 1964. He began his career in Computer Science in 1964 at a company owned by the German computer pioneer Konrad Zuse and continued to work for computer manufacturers and software companies in Germany and the USA until 1973. During this period he was responsible for the development of a commercial optimizing Algol 60 compiler (1969) and for the design and implementation of PROGRESS, one of the first high-level real-time programming languages (1970-1973).
In 1973, Dr. Zima accepted a research position at the University of Karlsruhe, Germany; two years later he was appointed Professor for Computer Science at the University of Bonn, Germany, a position which he held until 1989. His research during that period initially had a more theoretical orientation, dealing with the modeling of systems of parallel processes and their cooperation. This led to his first book "Operating Systems: Parallel Processes" (1976, in German). Research on data flow analysis and optimization algorithms in compilers for imperative programming languages resulted in the publication of his second and third book (in German) both of which deal with the theory and practice of optimizing compiler development (1982/83). During a sabbatical semester spent at the IBM Research Laboratory in San Jose, California, he worked for a year with Peter Lucas on constraint languages and expert systems (1983/84). Starting in 1985, he headed a research group in the national German supercomputer project "SUPRENUM" which developed SUPERB, the first Fortran-based compilation system for distributed-memory architectures. SUPERB converts sequential Fortran 77 programs augmented with data distribution directives into explicitly parallel message-passing programs. This work, which was continued until 1989, resulted in the first Ph.D. thesis (by Michael Gerndt) in this field, and was an important step in the direction towards high-level languages for scalable architectures.
Between 1988 and 1989 Dr. Zima spent a year at Rice University working with Ken Kennedy and his group on parallelizing compiler technology. During that period he finished his fourth book, "Supercompilers for Parallel and Vector Computers", written together with Barbara Chapman (1990). This was the first book to coherently describe analysis and compilation technology for parallelizing compilers.
After returning from Rice University he left the University of Bonn and accepted a professorship for Applied Computer Science at the University of Vienna (1989). At that time, his focus of research shifted from compiler technology to language design. This led to the data-parallel Vienna Fortran language (1992), defined in cooperation with Piyush Mehrotra from ICASE, NASA Langley Research Center, Barbara Chapman and other members of his institute. Vienna Fortran was the first language to provide a complete specification of mapping constructs in the context of Fortran, offering high-level features for data distribution and alignment as well as work distribution; it became a major input for the High Performance Fortran (HPF) development. The language work of the Vienna Institute headed by Dr. Zima was continued beyond HPF-2, with the objective of improving target code efficiency and broadening the application spectrum. This resulted in the HPF+ and Opus languages, and in the development of the Vienna Fortran Compiler, a Fortran 90-based compilation and runtime system supporting irregular, adaptive, and heterogeneous applications. The design of HPF+ (1996-1998), conducted within a European Union ESPRIT project in cooperation with industrial application developers, focused on enhancing the performance of advanced applications such as weather forecasting, crash simulation, and combustion engine simulation; Opus provides a high-level task-parallel interface for multidisciplinary applications running on heterogeneous systems. Additional work in the Vienna research group led to a range of tools supporting high-level programming for parallel machines, in particular for performance analysis and debugging.
Much of the work described above has been performed in the framework of research projects funded by the Austrian Science Foundation, the European Union, and industry. Currently the most important active project headed by Dr. Zima is the Special Research Program Aurora which was initiated in 1997 as a ten-year program. Aurora involves a number of institutes from different universities in an attempt to achieve synergy between language, compiler and tool designers on the one hand, and application developers in fields such as quantum mechanics, semiconductor simulation and financial optimization on the other hand.
As a result of spending a sabbatical semester at the California Institute of Technology in 1999/2000 Dr. Zima started a new line of work in cooperation with Thomas Sterling from Caltech/JPL. He developed an object-based distributed programming and execution model for massively parallel arrays of Processor-in-Memory Systems called "Macroservers". This model is expected to guide the development of the hardware and low-level software layers for a new PiM-based parallel architecture.
Dr. Zima is the author or co-author of more than 130 publications, including 4 books and about 100 refereed publications. He has presented more than 200 scientific lectures at universities, research institutions, and international conferences. He served as General Chair of the ACM International Conference on Supercomputing (ICS'97) in Vienna, as Program Chair or Vice Program Chair at a number of international conferences, and has been a member of more than 40 Program Committees over the past 10 years.
He is currently on the editorial boards of Concurrency: Practice and Experience, Parallel Processing Letters, The Journal for Universal Computer Science (J.UCS), and Parallel Computing.
Dr. Zima has reviewed a large number of papers for international conferences and journals, including IEEE Transactions on Parallel and Distributed Systems, Parallel Computing, and Concurrency: Practice and Experience. Furthermore, he reviewed project proposals submitted to the National Science Foundation and was a member of review panels for the European Union's ESPRIT Research Program as well as national research agencies in Germany and Austria.
Furthermore, he served on the European Union's HPCN Advisory Board, and he is a member of the Steering Committee of the ACM International Conference on Supercomputing and of the Advisory Board of the EUROPAR Series of Conferences.
Dr. Zima is a member of the Association for Computing (ACM), IEEE, Gesellschaft für Informatik (Germany), the Austrian Computer Society, and the Planetary Society in Pasadena, California.