VPH News - Application Hosting Environment V2.0 released
Simplifying grid computing for research and medical purposes
We are pleased to announce the release of AHE 2.0, a lightweight middleware tool designed to facilitate scientific investigations using grid resources. AHE provides scientists with application specific services to utilize grid resources in a quick, transparent manner with the scientific objective as the main driver of the activity.
Today’s scientists and clinicians face a growing number of challenges that affect their ability to fully exploit computational resources available to them. Unprecedented amounts of available computational power, compounded by the growth in hybrid computational architectures, present new challenges to scientific disciplines and researchers that rely on computer based modelling and simulation.
In order to meet this challenge researchers at UCL, as part of the EPSRC funded RealityGrid project, have developed the Application Hosting Environment (AHE), a tool that allows scientists to run computational applications on high-performance grid computing (HPC) resources in a quick, transparent manner.
Grid computing - the application of several computers to a single computational problem at the same time – is meant to ensure that scientists have access to resources that are more that just a sum of their individual parts. Version 2.0 of the AHE is intended to bring us a step closer to this goal, ensuring that HPC grids are fully transparent to the scientist user, with the focus constantly on simplifying grid and HPC use.
The key aspect of AHE V2.0, say UCL researchers, is the adoption of a novel approach to simplifying the use of grid computing: grid application virtualisation. The motivation behind this approach is to simplify grid use: a layer of user friendly Web services have been placed between the user and the computer grid resources, which hides much of its complexity and provides a virtual interface for any given scientific application in deployment.
The AHE will also manage computer simulations started by a scientist, taking care of the many data files that need to be moved around the computational grid. By removing the need for the scientist user to remember the complex series of commands associated with manual simulation, the AHE allows the scientist to concentrate on doing actual science.
Use of the AHE also applies to clinical practice, where biomedical modelling and simulation is set to increasingly augment the clinical decision making process. The AHE has been used in such a situation within GENIUS(1), an EPSRC funded project concerned with the use of real-time patient-specific blood flow modelling and simulation in the diagnosis and treatment of cerebral aneurysms. The AHE will also form a part of the VPH ToolKit, and be made freely available to the VPH community.
AHE V2.0 is a necessary step towards opening up grid infrastructure, and therefore making the use of HPC a reality for both researchers and clinicians. A development roadmap has been drafted, covering the future technological, security and privacy challenges which must be overcome if grid computing – be it as part of basic research practice, or in patient-specific medical modelling and simulation-related applications - is to become a reality.
For full information see: http://ccs.chem.ucl.ac.uk/projects/AHE2_0_full.pdf)
The development of the AHE is funded by the EPSRC "Rapid Prototyping of Usable Grid Middleware" Project, GR/T27488/01, and by OMII under the Managed Programme RAHWL project. Find out more and download the latest release at http://www.realitygrid.org/AHE.
(1) S. K. Sadiq, M. D. Mazzeo, S. J. Zasada, S. Manos, I. Stoica, C. V. Gale, S. J. Watson, P. Kellam, S. Brew, P. V. Coveney, "Patient-specific simulation as a basis for clinical decision-making", Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 366, (1878), 3199-3219, (2008), DOI: 10.1098/rsta.2008.0100.