Abstract | ||
---|---|---|
The scalable architecture of a multiprocessor intended to efficiently accelerate the emulation of large-scale complex systems, in particular massively-parallel bioinspired neural networks, is introduced in this paper. In order to cope with the required processing complexity of a target network size of large number of neurons and synapses, the SIMD configuration is adopted. Special flow-control instructions are proposed to support conditional execution. Also, a modified digital AER scheme allows for the compact emulation of interconnects. Due to its programmable characteristics, the architecture is flexible enough to support the emulation of different neural models and other homogeneous parallel applications. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1109/AHS.2009.31 | AHS |
Keywords | Field | DocType |
scalable architecture,conditional execution,simd configuration,large-scale complex system,compact emulation,neural network,simd computing,large number,different neural model,complex neural bioinspired applications,modified digital aer scheme,homogeneous parallel application,parallel processing,complex system,flow control | Complex system,Architecture,Computer science,Parallel computing,SIMD,Multiprocessing,Emulation,Content-addressable storage,Artificial neural network,Conditional execution | Conference |
Citations | PageRank | References |
2 | 0.47 | 7 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jordi Madrenas | 1 | 150 | 27.87 |
J. Manuel Moreno | 2 | 28 | 4.71 |