Please use this identifier to cite or link to this item:
|Title:||General Purpose Computing on GPU's||Authors:||VANDEN BOER, Dirk||Issue Date:||2005||Abstract:||GPGPU stands for General-Purpose computation on GPUs. With the increasing programmability of commodity graphics processing units (GPUs), these chips are capable of performing more than the specific graphics computations for which they were designed. They are now capable coprocessors, and their high speed makes them useful for a variety of applications . We give a brief history of the GPU to see how it has developed over the last couple of years, discuss the benefits and drawbacks of using the GPU and show why it is so useful for solving general problems. We also take a look at what the future GPUs will probably look like. To get some insight of how programming on the GPU works we explain the stream programming model used to program on GPUs and discuss the operations that are available on the GPU and how to deal with operations that are not available. Also, some mechanisms are presented that are often used to convert algorithms from the Central Processing Unit (CPU) to the GPU. To give an idea of the applicability of GPGPU we give an overview of the most important research areas in which the GPU can be used for generalpurpose computing and we give some successful examples for each research area. We go into more detail on a paper by Fan et al.  to get acquainted with the use of the GPU as general purpose processor. The paper describes a streaming collision detection algorithm between star shaped objects that is mapped to a stream processor. Finally we made some implementations that use the GPU to speed up computations. We discuss our implementation of a particle system that runs on the GPU, give an overview of the algorithm and discuss the results we achieved. We also discuss our implementation of a math-library on the GPU. The library supports various vector and matrix operations that are performed on the GPU by storing the data in textures. As a conclusion we compare the speed of the GPU implementation with CPU based methods||Document URI:||http://hdl.handle.net/1942/1114||Category:||T2||Type:||Theses and Dissertations|
|Appears in Collections:||Master theses|
Show full item record
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.