Accelerating scientific applications on GPUs

We have analyzed and accelerated two large scientific applications used at the Barcelona Supercomputer Center (BSC). With this, we want to show how two complex applications can be efficiently ported to GPUs. In addition, we have developed a mechanism to manage the coherency of CPU/GPU memories.

Detalhes bibliográficos
Autor: Farré Gonzalez, Pau
Formato: tesis de maestría
Fecha de publicación:2016
País:España
Recursos:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/105241
Acesso em linha:https://hdl.handle.net/2117/105241
Access Level:acceso abierto
Palavra-chave:Graphics processing units
GPU
CUDA
WARIS
PELE
Unitats de processament gràfic
Àrees temàtiques de la UPC::Informàtica::Aplicacions de la informàtica
Descrição
Resumo:We have analyzed and accelerated two large scientific applications used at the Barcelona Supercomputer Center (BSC). With this, we want to show how two complex applications can be efficiently ported to GPUs. In addition, we have developed a mechanism to manage the coherency of CPU/GPU memories.