A PCI AER Co-Processor Evaluation Based on CPUs Performance Counters

Image processing in digital computer systems usually considers the visual information as a sequence of frames. These frames are from cameras that capture reality for a short period of time. They are renewed and transmitted at a rate of 25-30 frames per second, in a typical real-time scenario. Digita...

Descripción completa

Detalles Bibliográficos
Autores: Domínguez Morales, Manuel Jesús, Linares Barranco, Alejandro, Íñigo Blasco, Pablo, Font Calvo, Juan Luis, Cascado Caballero, Daniel, Jiménez Moreno, Gabriel, Díaz del Río, Fernando, Sevillano Ramos, José Luis
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2012
País:España
Institución:Universidad de Sevilla (US)
Repositorio:idUS. Depósito de Investigación de la Universidad de Sevilla
OAI Identifier:oai:idus.us.es:11441/75066
Acceso en línea:https://hdl.handle.net/11441/75066
Access Level:acceso abierto
Palabra clave:Spiking neurons
Address-Event
PCI
FPGA
Synthetic AER generation
Descripción
Sumario:Image processing in digital computer systems usually considers the visual information as a sequence of frames. These frames are from cameras that capture reality for a short period of time. They are renewed and transmitted at a rate of 25-30 frames per second, in a typical real-time scenario. Digital video processing has to process each frame in order to obtain a filter result or detect a feature on the input. This processing is usually based on very complex and expensive (in resources) operations for an efficient real-time application. Brain can perform very complex visual processing in real-time using relatively simple cells, called neurons, which codify the information into spikes. Spike-based processing is a relatively new approach that implements the processing by manipulating spikes one by one at the time they are transmitted, like a human brain. The spike-based philosophy for visual information processing based on the neuro-inspired Address Event Representation (AER) is achieving nowadays very high performances. In this work we study the low level performance for real-time scenarios of a spike-based co-processor connected to a conventional PC and implemented through a PCI board. These low level lacks are focused both in the software conversion of static frames into AER format and in the bottleneck of the PCI interface.