Cargando…
GPUs Outperform Current HPC and Neuromorphic Solutions in Terms of Speed and Energy When Simulating a Highly-Connected Cortical Model
While neuromorphic systems may be the ultimate platform for deploying spiking neural networks (SNNs), their distributed nature and optimization for specific types of models makes them unwieldy tools for developing them. Instead, SNN models tend to be developed and simulated on computers or clusters...
Autores principales: | Knight, James C., Nowotny, Thomas |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2018
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6299048/ https://www.ncbi.nlm.nih.gov/pubmed/30618570 http://dx.doi.org/10.3389/fnins.2018.00941 |
Ejemplares similares
-
HPC: programming Nvidia GPUs with CUDA
por: Alvarez Conde, Daniel
Publicado: (2023) -
Fast Simulations of Highly-Connected Spiking Cortical Models Using GPUs
por: Golosio, Bruno, et al.
Publicado: (2021) -
Real-time cortical simulation on neuromorphic hardware
por: Rhodes, Oliver, et al.
Publicado: (2020) -
Simulating Collective Effects on GPUs
por: Hegglin, Stefan Eduard
Publicado: (2016) -
Speeding up convolution operations in RooFit with GPUs
por: Olvhammar, Hanna Maria
Publicado: (2022)