Speaker
Describe the added value of the Grid for the scientific/technical activity you (plan to) do on the Grid. This should include the scale of the activity and of the potential user community and the relevance for other scientific or business applications
Significant uses of symbolic computation systems, such as Maple, are found in
areas of physics, mathematics, biology, chemistry and engineering disciplines.
Worldwide, it is estimated that there are at least 1 million users. While symbolic
computations may have extremely high computational and data demands, at
present, however, only a few symbolic computation systems provide any form
of Grid accessibility. Most of these provide little more than wrappers to
standard Globus library calls, and none allows simultaneous deployment of Grid
services, access to external Grid services, and the coupling of symbolic
components into a coherent Grid application. In contrast, SymGrid provides
sophisticated interactive computational steering interfaces, with simple and
high-level access to Grid services. Common data and task interfaces
allow complex computations to be constructed by orchestrating heterogeneous
distributed components from various systems into a single system
With a forward look to future evolution, discuss the issues you have encountered (or that you expect) in using the EGEE infrastructure. Wherever possible, point out the experience limitations (both in terms of existing services or missing functionality)
The delays in porting the EGEE tools towards new WSRF-compliant Grid
architectures have created several discussions and problems in connecting
EGEE sites from SCIEnce with new non-EGEE sites build upon Globus Toolkit 4.
The SCIEnce team hopes that the new version gLite will solve this issue.
Describe the scientific/technical community and the scientific/technical activity using (planning to use) the EGEE infrastructure. A high-level description is needed (neither a detailed specialist report nor a list of references).
The EU SCIEnce infrastructure project targets users of symbolic computing
systems such as Maple. We aim to provide Grid-enabled symbolic computations
through providing: (1) computational steering tools integrating seamlessly with
existing tools; (2) the ability for users to identify symbolic components to form
part of a Grid-enabled application; (3) adaptive resource brokers supporting
the irregular workloads found in symbolic computations; (b4) large-scale
heterogeneous demonstrators.
Report on the experience (or the proposed activity). It would be very important to mention key services which are essential for the success of your activity on the EGEE infrastructure.
The two current components of SymGrid framework are SymGrid-Services and
SymGrid-Par. SymGrid-Services complies with the WSRF standard for Grid
services based on Globus Toolkit 4. A middleware package was designed in
order to allow the easy-to-use access in a uniform way from any computer
algebra system to Grid and Web services. It consists of a set of Java classes
and a set of computer algebra system libraries. SymGrid-Par allows symbolic
computations to be executed as parallel computations on a computational Grid.
The SymGrid-Par middleware is built on the GRID-GUM, Grid-enabled
implementation of Glasgow Parallel Haskell that provides various high-level
parallelism services providing a flexible, adaptive environment for managing
parallelism at various degrees of granularity. GRID-GUM uses MPICH-G2.
Moreover, GRID-GUM has been designed with novel dynamic load scheduling
mechanisms for shared hierarchical heterogeneous computational Grids based
on Globus Toolkit 2 or higher.
