A Custom 7nm CMOS Standard Cell Library for Implementing TNN-based Neuromorphic Processors

Add code
Dec 10, 2020
Harideep Nair, Prabhu Vellaisamy, Santha Bhasuthkar, John Paul Shen
Figure 1 for A Custom 7nm CMOS Standard Cell Library for Implementing TNN-based Neuromorphic Processors
Figure 2 for A Custom 7nm CMOS Standard Cell Library for Implementing TNN-based Neuromorphic Processors
Figure 3 for A Custom 7nm CMOS Standard Cell Library for Implementing TNN-based Neuromorphic Processors
Figure 4 for A Custom 7nm CMOS Standard Cell Library for Implementing TNN-based Neuromorphic Processors

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon

A set of highly-optimized custom macro extensions is developed for a 7nm CMOS cell library for implementing Temporal Neural Networks (TNNs) that can mimic brain-like sensory processing with extreme energy efficiency. A TNN prototype (13,750 neurons and 315,000 synapses) for MNIST requires only 1.56mm2 die area and consumes only 1.69mW.

* 4 pages  
View paper onarxiv icon

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon