This presentation will discuss some key issues in this context based on the objective of finding a viable compromise between the goals of providing an API at a high level of abstraction and meeting the challenges related to target code performance, power consumption, and fault tolerance. We will particularly address the question to which degree recent experiences in language design for peta-scale computing systems, such as those developed in the High-Productivity-Computing- Systems (HPCS) program, can contribute to the problem of programming multi-core systems in a productive, efficient, and reliable way.

The final part of the talk will deal with a new approach for exploiting the massive parallelism provided by the abundance of threads in future multi-core systems. Besides their conventional use for fine-grain parallelism in application programs, threads can be used to support introspection, enabling a software system to become self-aware by monitoring its execution behavior, reasoning about its internal state, and making decisions about appropriate changes of the system or system state when necessary. In addition to supporting graceful degradation in the case of faults, introspection can be also applied to areas such as performance tuning and power management.

Hans P. Zima is a Principal Scientist at the Jet Propulsion Laboratory, California Institute of Technology, and a Professor Emeritus of the University of Vienna, Austria. He received his Ph.D. degree in Mathematics and Astronomy from the University of Vienna in 1964.

His major research interests have been in the fields of high-level programming languages, compilers, and advanced software tools. In the early 1970s, while working in industry, he designed and implemented one of the first high-level real-time languages for the German Air Traffic Control Agency. During his tenure as a Professor of Computer Science at the University of Bonn, Germany, he contributed to the German supercomputer project "SUPRENUM", leading the design of the first Fortran-based compilation system for distributed-memory architectures (1989). After his move to the University of Vienna, he became the chief designer of the Vienna Fortran language (1992) that provided a major input for the High Performance Fortran de-facto standard. From 1997 to 2007, Dr. Zima headed the Priority Research Program "Aurora", a ten-year program funded by the Austrian Science Foundation. His research over the past years focused on the design of the "Chapel" programming language in the framework of the DARPA-sponsored HPCS project "Cascade". More recently, Dr. Zima has become involved in the design of space-borne fault-tolerant high capability computing systems.

Dr. Zima is the author or co-author of more than 170 publications, including 4 books.

Ivan Stojmenovic received Ph.D. degree in mathematics. He held positions in Serbia, Japan, USA, Canada, France, Mexico, Spain and UK. He is currently Chair Professor in Applied Computing at the University of Birmingham, UK. He published over 200 different papers, and edited four books on wireless, ad hoc and sensor networks and applied algorithms with Wiley/IEEE. He is currently editor of over dozen journals, and founder and editor-in-chief of three journals (Journal of Multiple-Valued Logic and Soft Computing, International Journal of Parallel, Emergent and Distributed Systems, and Ad Hoc & Sensor Networks, An International Journal). Stojmenovic is in the top 0.56% most cited authors in Computer Science (Citeseer 2006). One of his articles was recognized as the Fast Breaking Paper, for October 2003 (as the only one for all of computer science), by Thomson ISI Essential Science Indicators. He is recipient of the Royal Society Research Merit Award, UK. He is recently elected to IEEE Fellow status (class 2008). He chaired and/or organized >30 workshops and conferences, and served in over 100 program committees since 2004. Among others, he was/is program co/vice-chair at IEEE AINA-07, IEEE MASS-04 and -07, EUC-05, WONS-05, MSN-05 and -06, ISPA-05 and -07, founded workshop series at IEEE MASS, IEEE ICDCS and IEEE DCOSS, and Workshop Chair at ACM Mobicom/Mobihoc 2007. He presented over dozen tutorials.

Each processor has its OOPDataManager object which administers TPZSaveable objects and the access requests issued by the OOPTask objects.

Task objects implement part of a parallel algorithm acting upon and transforming distributed data objects. Task objects are submitted to a TaskManager object. Each processor has a unique TaskManager object. In order to sequence tasks in the proper order, a version is associated with distributed data objects and tasks depend on a distributed data object with a certain version. After transforming a distributed data object, the task object increments the version of the data object.

Task objects are assigned a processor number. When submitted to the TaskManager on the current processor, the manager will send the task object to the assigned processor using the the serialization mechanism defined by the TPZSaveable class. The parallel execution of the algorithm depends on the distribution of the tasks over the pool of processors.

OOPar is useful for both parallelizing existing software and implementing new algorithms. The environment has been successfully applied to the parallelization of a three dimensional computational fluid dynamics software including turbulence models and explicit/implicit solvers. A parallel implementation of an error estimator has also been implemented using OOPar.

Currently substructuring techniques are being implemented within OOPar with the intent of developing a parallel finite element solver for three dimensional problems.

OOPar is a public domain software project and can be downloaded from our cvs server at our laboratory. Instructions can be found at the web server of the laboratory : http://labmec.fec.unicamp.br

Professor Philippe Devloo graduated in electro-mechanical engineering at Gent University, Belgium. He also did a one-year specialization in computer science at Leuven University, Belgium. From 1982 to 1987 he did his PhD. in Texas University, Austin, in the area of computational mechanics, where he developed h-p adaptive techniques, applied to simulation of Navier Stokes comprehensive equations. After his arrival to Brazil in 1998, Professor Devloo dedicated himself to the study of object-oriented code structures, applied to scientific computing. He is the author of an object-oriented development environment, applied to finite elements method; and another environment focused on parallel computing algorithms development. Since 1992, Prof. Devloo is a lecturer at the Faculty of Civil Engineering, Architecture and Urbanism of UNICAMP. He had developed research projects in collaboration with Embraer, Petrobras and Commodity Systems.

and/or end users that regulate the usage of systems internally, are also agreements. Enforcing these agreements requires flexible management mechanisms. However, when we look into the structure of proposed management systems, there are major challenges that have not been resolved, such as:

· How to monitor the service;
· How to analyze collected service status against the knowledge;
· How to plan and enforce executions if necessary;
· How to scale the system to meet demand; and
· How to represent agreements and other information as knowledge;
One possible solution to scalability is the adoption of cloud computing models. Here we further look at what cloud computing concepts can bring to SaaS, and whether peer to peer clouds can offer SaaS solutions.

Professor Mark Perry is jointly appointed to the Faculty of Science, Computer Science, and the Faculty of Law at the University of Western Ontario, London, Canada. He is a Faculty Fellow at IBM's Center for Advanced Studies, a Barrister and Solicitor of the Law Society of Upper Canada, a Correspondent for the Computer Law and Security Report, a member of the International Association for the Advancement of Teaching and Research in Intellectual Property, the IEEE, the Intellectual Property Institute of Canada, and the ACM. He is a committee member of the ACM SIGCAS, the College of Reviewers of the Canada Research Chairs, a reviewer for Canadian Foundation for Innovation, a member in the Seldon Society and the Computer Research Association, on the executive committee for the ACM Special Interest Group on Computers and Society, in the UWO Bioethics Research Group, and a reviewer for Natural Science and Engineering Research Council (NSERC) and the Social Science and Humanities Research Council (SSHRC). Professor Perry's research is focused on the nexus of science and law, and in the area of autonomic computing system development. He holds grants from NSERC and SSHRC to pursue his research in both law and science, and has supervised numerous graduate and undergraduate theses. He has been invited by universities in Australia, India, New Zealand, United Kingdom, United States, and Canada to speak at research-intensive colloquia and classes. He regularly contributes to the media on technology and law issues. More information can be found at http://www.csd.uwo.ca/~markp