At the threshold to exascale computing, limitations of the MPI programming model become more and more pronounced. HPC programmers have to design codes that can run and scale on systems with hundreds of thousands of cores. Setting up accordingly many communication buffers, point-to-point communication links, and using bulk-synchronous communication phases is contradicting scalability in these dimensions. Moreover, the reliability of upcoming systems will worsen.

The increasing volume of data describing human disease processes and the growing complexity of understanding, managing, and sharing such data presents a huge challenge for clinicians and medical researchers. This paper presents the @neurIST system, which provides an infrastructure for biomedical research while aiding clinical care, by bringing together heterogeneous data and complex processing and computing services. Although @neurIST targets the investigation and treatment of cerebral aneurysms, the system's architecture is generic enough that it could be adapted to the treatment of other diseases. Innovations in @neurIST include confining the patient data pertaining to aneurysms inside a single environment that offers clinicians the tools to analyze and interpret patient data and make use of knowledge-based guidance in planning their treatment. Medical researchers gain access to a critical mass of aneurysm related data due to the system's ability to federate distributed information sources. A semantically mediated grid infrastructure ensures that both clinicians and researchers are able to seamlessly access and work on data that is distributed across multiple sites in a secure way in addition to providing computing resources on demand for performing computationally intensive simulations for treatment planning and research.

The first part of this paper presents a selection of medical simulation applications, including image reconstruction, near-real-time registration for neuro-surgery, enhanced dose distribution calculation for radiotherapy, inhaled drug delivery prediction, plastic surgery planning and cardio-vascular system simulation. The latter two topics are discussed in some detail. In the second part, we show how such services can be made available to the clinical practitioner using grid technology. We discuss the developments made and the experience gained during the EU project GEMSS, which provides reliable, efficient, secure and lawful medical grid services.

Service-oriented Grid technologies are increasingly utilized for the realization of future biomedical IT infrastructures since they offer unprecedented opportunities for the integration of advanced analysis and simulation applications as well as distributed heterogeneous data sources and information systems. The European Union's @neurIST project is developing a Grid-based IT infrastructure for the management of all processes linked to research, diagnosis, and treatment development for complex and multifactorial diseases encompassing data repositories, computational analysis services, and information systems handling multiscale, multimodal information at distributed sites. This paper provides an overview of the @neurIST Grid middleware and outlines the infrastructure offered for the provision of advanced compute and data services to support computationally demanding modeling and simulation tasks and to access heterogeneous distributed data sources through semantic integration.

This paper reports on work carried out within the extension of the ESPRIT Project CAMAS (EP6756) which provides a link to the Europort-1 Action (EP8421). The PAM-CRASH core-code migrated to distributed-memory parallel machines using the message-passing programming paradigm, has been extended to include all features necessary for a full, industrial front or off-set car-crash simulation. The paper includes a description of the salient features of the parallelization approaches and of the industrial benchmark models. Performance results will be presented for the following platforms: IBM SP1&2, Meiko CS-2, Parsytec GC PowerPlus.

As the Internet revolutionised access to information, the Grid will revolutionise access to computer applications and software systems. In general, this includes the highly important aspect of access to information resources such as Grid database systems (datadriven Grid applications), but we concentrate here on computational services providing numerical simulations for analysis, prediction and virtual prototyping to the medical sector (bio-numerics). The aims and objectives of the European Commission project GEMSS [1] will be presented and a description of the potential impact of the bio-numerics applications through examples from previous or ongoing European projects involving GEMSS partners, such as SimBio, COPHIT and BloodSim.

We describe a software library for dynamic load balancing of finite element codes. The application code has to provide the current distributed mesh and information on the calculation and communication requirements, and receives from the library all necessary information to re-allocate the application data. The library computes a new partitioning, either via direct mesh migration or via parallel graph re-partitioning, by interfacing to the ParMetis or Jostle package. We describe the functionality of the DRAMA library and we present some results.

High Performance Fortran (HPF) is a data-parallel language providing the user with a high-level interface for programming scientific applications, while delegating to the compiler the task of producing explicitly parallel code. In this paper, we give an overview of the motivation and the results of the ESPRIT project “HPF+”.The project succeeded in demonstrating that HPF, with a small set of language extensions and an appropriate compiler and tool infrastructure, has the potential to be efficient for advanced industrial applications, sometimes approaching the performance of manually written message-passing code. We introduce v the applications which were used to guide and evaluate the development work in the project, provide an overview of the HPF+ language and discuss the Vienna Fortran Compiler (VFC) as well as the performance obtained for the project benchmarks.

This paper deals with the design and implementation of communications strategies for the migration to distributed-memory, MIMD machines of an industrial crashworthiness simulation program, PAM-CRASH, using message-passing. A summary of the algorithmic features and parallelization approach is followed by a discussion of options to minimize overheads introduced by the need for global communication. Implementation issues will be specific to the portable message-passing interfaces PARMACS and PVM, together with future possibilities offered by the MPI standard.