Evaluating different Java bindings for OpenCL

Medina Domínguez, Raquel

Publication:
Evaluating different Java bindings for OpenCL

dc.contributor.advisor	Yi, Youngmin
dc.contributor.advisor	Sierra Cámara, José María
dc.contributor.author	Medina Domínguez, Raquel
dc.contributor.departamento	UC3M. Departamento de Informática	es
dc.contributor.other	University of Seoul
dc.date.accessioned	2013-06-24T11:49:41Z
dc.date.available	2013-06-24T11:49:41Z
dc.date.issued	2012-12-07
dc.date.submitted	2013-03-08
dc.description.abstract	The traditional CPU is able to run only a few complex threads concurrently. By contrast, a GPU (Graphics Processing Unit) allows a concurrent execution of hundreds or thousands of simpler threads. The GPU was originally designed for a computer graphics, but nowadays it is being used for generalpurpose computation using a GPGPU (General Purpose GPU) technology. OpenCL, one of the GPGPU technologies, is introduced in this final project. OpenCL is an extension of C and enables efficient parallel programming for heterogeneous devices including both multi-core CPUs and GPUs. However, it provides a low level abstraction to utilize the hardware efficiently. This tends to a hurdle for productive parallel programming. On the other hand, Java is widely used in many application domains since it provides good productivity in software development. Recently, several methods that bind OpenCL and Java have been suggested: Joagamp, Jocl, JavaCL. In this final project, I evaluate these Java bindings for OpenCL in terms of execution time and the memory used. My own class for vector multiplication has been the baseline application in evaluating the libraries presented here. My results show that Joagamp is more efficient, and Jocl consumes less memory, while JavaCL is most productive in terms of the number of lines of code. ____________________________________________________________________________________________________________________
dc.description.abstract	Por una lado el CPU tradicional es capaz de ejecutar solo varios threads al mismo tiempo. Por otro lado, la tecnologia GPU permite ejecutar cientos o miles de simples threads. La tecnologia GPU fue originalmente disenada para graficos pero en estos dias esta siendo usada para calculos usando GPGPU tecnologia. OpenCL, una de las GPGPU tecnologias, es introducida en este projecto final. Metodos de coperacion entre Java y el lenguaje presentado. Varias librerias son prsentadas en este proyecto como Jogamp, JOCL y JavaCL. Mi propia clase multiplicacion de vectores ha sido usada como base de nuestra aplicaion para evaluar las diferentes librerias presentadas aqui. Diferentes medidas han sido usadas para evaular estas diferentes plataformas como son velocidad, tiempo y memoria usada. Acorde a estas medidas somos capaces de definir que tipo de libreria es mas adecuada para los diferntes proyectos que se deseen elaborar.
dc.description.degree	Ingeniería en Informática
dc.format.mimetype	text/plain
dc.format.mimetype	application/pdf
dc.format.mimetype	application/pdf
dc.identifier.uri	https://hdl.handle.net/10016/17183
dc.language.iso	eng
dc.rights	Atribución-NoComercial-SinDerivadas 3.0 España
dc.rights.accessRights	open access
dc.rights.uri	http://creativecommons.org/licenses/by-nc-nd/3.0/es/
dc.subject.eciencia	Informática
dc.subject.other	Java (Lenguaje de programación)
dc.subject.other	Tecnología GPU
dc.subject.other	Plataformas informáticas
dc.title	Evaluating different Java bindings for OpenCL
dc.title.alternative	Evaluación de diferentes plataformas Java usando OpenCL
dc.type	master thesis	*
dspace.entity.type	Publication