Authors: Piatkowski, Nico
Title: Parallel Algorithms for GPU accelerated Probabilistic Inference
Language (ISO): en
Abstract: Real world data is likely to contain an inherent structure. Those structures may be represented with graphs which encode independence assumptions within the data. Performing inference in those models is nearly intractable on mobile devices or casual workstations. This work introduces and compares two approaches for ac- celerating the inference in graphical models by using GPUs as parallel processing units. It is empirically showed, that in order to achieve a scaleable parallel algo- rithm, one has to distribute the workload equally among all processing units of a GPU. We accomplished this by introducing Thread-Cooperative message compu- tations.
Issue Date: 2012-02-21
Is part of: Big Learning Workshop on Algorithms, Systems, and Tools for Learning at Scale
Appears in Collections:Sonderforschungsbereich (SFB) 876

Files in This Item:
File Description SizeFormat 
piatkowski_2011c.pdfDNB239.06 kBAdobe PDFView/Open

This item is protected by original copyright

Items in Eldorado are protected by copyright, with all rights reserved, unless otherwise indicated.