Please use this identifier to cite or link to this item:
Title: Graph Processing on GPU
Keywords: Graph Processing, Heterogeneous, GPGPU, BSP Model, Asynchronous Computation, Generic API
Issue Date: 6-Aug-2013
Source: ZHANG JINGBO (2013-08-06). Graph Processing on GPU. ScholarBank@NUS Repository.
Abstract: This thesis has explored the state-of-the-art GPGPU techniques over large graph mining. By understanding the limitations of heterogeneous hardware, triangulation, as a representative of graph mining algorithms, was implemented to be accelerated by many-core GPUs. Afterwards, a synchronous iterative GPU-accelerated graph processing model was abstracted and proposed. A generic system (SIGPS) was then implemented based on this model. Specifically, a vertex API was provided for users who want to design their own algorithms with the assistance of a functional library of mining algorithms. Moreover, in order to further enhance the system performance, an asynchronous disk-based model was then designed to support asynchronous computing over GPUs. A novel parallel sliding windows method was employed on GPU memory. Two newer operational APIs named "sync" and "update" replaced the vertex API. Asynchronous-SIGPS (ASIGPS) could be used to execute several advanced data mining, graph mining, and machine learning algorithms on very large graphs.
Appears in Collections:Ph.D Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
ZhangJB.pdf2.7 MBAdobe PDF



Page view(s)

checked on Jan 19, 2018


checked on Jan 19, 2018

Google ScholarTM


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