14-18 October 2013
Amsterdam, Beurs van Berlage
Europe/Amsterdam timezone

GooFit: A massively-parallel fitting framework

15 Oct 2013, 14:38
Effectenbeurszaal (Amsterdam, Beurs van Berlage)


Amsterdam, Beurs van Berlage

Oral presentation to parallel session Software Engineering, Parallelism & Multi-Core Software Engineering, Parallelism & Multi-Core


Rolf Edward Andreassen (University of Cincinnati (US))


We present a general framework for maximum-likelihood fitting, in which GPUs are used to massively parallelise the per-event probability calculation. For realistic physics fits we achieve speedups, relative to executing the same algorithm on a single CPU, of several hundred.

Primary author

Rolf Edward Andreassen (University of Cincinnati (US))


Brian Meadows (University of Cincinnati (US)) Dr Karen Tomko (Ohio Supercomputer Center) Michael Sokoloff (University of Cincinnati) Weeraddana De Silva (University of Cincinnati (US))

Presentation Materials