Speaker: Carl Albing,
Cray Inc, USA and ACET, University of Reading.
Date/Time: 8th October 2008, 13:00-14:00.
Location: Room G74, Philip Lyle Building.
Map: http://www.info.rdg.ac.uk/maps/maps-display.asp
Abstract:
Petascale Supercomputing uses 10’s of thousands of processors; post-mortem reset and clean-up after job failure requires massively parallel execution of parameterized tasks. Message queuing and task farms can be used to address these challenges. We are interested in mechanisms that are more generically usable over a wider range of tasks. Current e-science work needs distributed computational resources, but those resources are hard to use effectively. Can we make distributed computing available to e-science as easy as a mashup?
Valid XHTML | Copyright | Last Modified: 6/Oct/2008 |