A simulator for SNN training energy picks an 'advanced WS' dataflow and 16x16 array, and the resulting 28nm accelerator is reported to beat prior inference chips in energy.
Towards artificial general intelligence with hybrid tianjicchiparchitecture
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.AR 1years
2025 1verdicts
REJECT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Energy-Oriented Computing Architecture Simulator for SNN Training
A simulator for SNN training energy picks an 'advanced WS' dataflow and 16x16 array, and the resulting 28nm accelerator is reported to beat prior inference chips in energy.