Exploring Spiking Neural Network on Coarse-Grain Reconfigurable Architectures

Sergei Dytckov; Masoud Daneshtalab; Syed M. A. H. Jafri; Ahmed Hemani; Hassan Anwar; Masoumeh Ebrahimi
Exploring Spiking Neural Network on Coarse-Grain Reconfigurable Architectures

Sergei Dytckov
Masoud Daneshtalab
Syed M. A. H. Jafri
Ahmed Hemani
Hassan Anwar
Masoumeh Ebrahimi
Katso/Avaa
Lataukset: 

doi:10.1145/2613908.2613916
URI
http://dl.acm.org/citation.cfm?id=2613916
Näytä kaikki kuvailutiedot
Julkaisun pysyvä osoite on:
https://urn.fi/URN:NBN:fi-fe2021042714223
Tiivistelmä


Today, recongurable architectures are becoming increas-

ingly popular as the candidate platforms for neural net-

works. Existing works, that map neural networks on re-

congurable architectures, only address either FPGAs or

Networks-on-chip, without any reference to the Coarse-Grain

Recongurable Architectures (CGRAs). In this paper we

investigate the overheads imposed by implementing spiking

neural networks on a Coarse Grained Recongurable Ar-

chitecture (CGRAs). Experimental results (using point to

point connectivity) reveal that up to 1000 neurons can be

connected, with an average response time of 4.4 msec.

Kokoelmat