Simulating the Behaviour of the Human Brain on NVIDIA GPU: cuHinesBatch & cuThomasBatch implementations

Understand the human brain is one of the century challenges. On this work we are going to achieve a small step towards this objective presenting a novel data layout in order to compute more efficiently the Hines algorithm on GPU. A more general tridiagonal solver is going to be presented too.

Detalles Bibliográficos
Autor: Martínez Pérez, Ivan
Tipo de recurso: tesis de maestría
Fecha de publicación:2018
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/117810
Acceso en línea:https://hdl.handle.net/2117/117810
Access Level:acceso abierto
Palabra clave:Parallel processing (Electronic computers)
Multiprocessors
Neurona
Algoritme de Hines
GPUs
Multiprocessador
Sistema Tri-diagonal Lineal
Escalabilitat
Algoritme de Thomas
PCR
CR
Processament Paral·lel
cuSPARSE
CUDA
Human Brain
Neuron
Hines Algorithm
Parallel Computing
Multicore
Tridiagonal Linear Systems
Scalability
Thomas Algorithm
Parallel Processing
Processament en paral·lel (Ordinadors)
Multiprocessadors
Àrees temàtiques de la UPC::Informàtica
Descripción
Sumario:Understand the human brain is one of the century challenges. On this work we are going to achieve a small step towards this objective presenting a novel data layout in order to compute more efficiently the Hines algorithm on GPU. A more general tridiagonal solver is going to be presented too.