Martin Sevior and/or Thomas Fifield - Using Amazon EC2 for high energy physics.

From LUV
Revision as of 18:19, 1 September 2009 by Kattekrab (talk | contribs)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to navigation Jump to search

Abstract: The Belle II project to increase the Luminosity of the KEKB collider by a factor 50 will search for Physics beyond the Standard Model through precision measurements and the investigation of rare processes in Flavour Physics. The data rate expected from the experiment is comparable to a current era LHC experiment with commensurate Computing needs. Both Belle the LHC experiments employ extremely large scale distributed computing clusters running Linux.

Incorporating commercial cloud computing, such as that provided by the Amazon Elastic Computing Cloud (EC2), into the Belle II computing model may provide a lower Total Cost of Ownership for the Belle II computing solution.

To investigate this possibility, we have deployed the complete Belle Monte-Carlo simulation chain on EC2 to benchmark the cost and performance of the service. This presentation will describe how we used Scientific Linux to test this as well as the bottlenecks and costs of large-scale Monte-Carlo production on EC2.

Martin Sevior obtained his Ph.D. in the field of Nuclear Astro-Physics from the University of Melbourne in 1984. In 1985 he worked at the TRIUMF cyclotron accelerator in Vancouver, Canada. In 1993 he returned to the University of Melbourne and is now working in the field of Experimental Particle Physics. He performs experiments with the world's highest intensity and energy particle accelerators in Japan and at CERN in Switzerland. His employs these to investigate the cause of the Universal Matter-AntiMatter asymmetry (at the KEK lab in Japan) and the origin of mass at the Large Hadron Collider at CERN in Switzerland. Both experiments probe conditions that last existed less than 1 billionth of a second after the Big Bang. Last year, the Belle experiment was cited cited as providing the crucial evidence that led to the awarding of the 2008 Nobel Prize to Nambu, Koboyashi and Maskawa.

Martin has published over 350 papers in refereed Journals and has supervised 12 Ph.D. students to completion.

He leads the Distributed Computing group for the Belle II experiment which aims to increase the data taking rate over the original Belle experiment by a factor of 50.

Since 2006 then Martin has made numerous contributions to the debate surrounding energy issues relating to Nuclear Power. These include scientific journal articles, presentations to conferences and forums, online discussions, opinion pieces to newspapers and many broadcast media interviews.

Finally Martin is a core developer of the Free Software Word Processor, AbiWord and last year described the peer-to-peer collaboration feature, AbiCollab, developed for AbiWord and OLPC Write at 2008 at the March LUV meeting.

Tom Fifield is a software engineer who does far too much sysadmin work. For the past few years he's been dabbling in large scale distributed computing with the experimental particle physics group at the university of melbourne (after inadvertently getting into a distro war in the interview!). After gaining experience in grid computing working to support ATLAS at the LHC, he is now applying the knowledge to new scientific endeavours (eg Belle II) and investigating cloud based solutions.