TY - GEN
T1 - Automated synthesis of memristor crossbars using deep neural networks
AU - Chakraborty, Dwaipayan
AU - Michel, Andy
AU - Pannu, Jodh S.
AU - Raj, Sunny
AU - Satapathy, Suresh Chandra
AU - Fernandes, Steven L.
AU - Jha, Sumit K.
N1 - Publisher Copyright:
© The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2021.
PY - 2021
Y1 - 2021
N2 - We present a machine learning based approach for automatically synthesizing a memristor crossbar design from the specification of a Boolean formula. In particular, our approach employs deep neural networks to explore the design space of crossbar circuits and conjecture the design of an approximately correct crossbar. Then, we employ simulated annealing to obtain the correct crossbar design from the approximately correct design. Our experimental investigations show that the deep learning system is able to prune the search space to less than $$0.0000011\%$$ of the original search space with high probability; thereby, making it easier for the simulated annealing algorithm to identify a correct crossbar design. We automatically design an adder, subtractor, comparator, and parity circuit using this combination of deep learning and simulated annealing, and demonstrate their correctness using circuit simulations. We also compare our approach to vanilla simulated annealing without the deep learning component, and show that our approach needs only 6.08% to 69.22% of the number of circuit simulation queries required by simulated annealing alone.
AB - We present a machine learning based approach for automatically synthesizing a memristor crossbar design from the specification of a Boolean formula. In particular, our approach employs deep neural networks to explore the design space of crossbar circuits and conjecture the design of an approximately correct crossbar. Then, we employ simulated annealing to obtain the correct crossbar design from the approximately correct design. Our experimental investigations show that the deep learning system is able to prune the search space to less than $$0.0000011\%$$ of the original search space with high probability; thereby, making it easier for the simulated annealing algorithm to identify a correct crossbar design. We automatically design an adder, subtractor, comparator, and parity circuit using this combination of deep learning and simulated annealing, and demonstrate their correctness using circuit simulations. We also compare our approach to vanilla simulated annealing without the deep learning component, and show that our approach needs only 6.08% to 69.22% of the number of circuit simulation queries required by simulated annealing alone.
UR - http://www.scopus.com/inward/record.url?scp=85091058711&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85091058711&partnerID=8YFLogxK
U2 - 10.1007/978-981-15-5679-1_32
DO - 10.1007/978-981-15-5679-1_32
M3 - Conference contribution
AN - SCOPUS:85091058711
SN - 9789811556784
T3 - Advances in Intelligent Systems and Computing
SP - 345
EP - 357
BT - Intelligent Data Engineering and Analytics - Frontiers in Intelligent Computing
A2 - Satapathy, Suresh Chandra
A2 - Zhang, Yu-Dong
A2 - Bhateja, Vikrant
A2 - Bhateja, Vikrant
A2 - Majhi, Ritanjali
PB - Springer Science and Business Media Deutschland GmbH
T2 - 8th International Conference on Frontiers of Intelligent Computing: Theory and Applications, FICTA 2020
Y2 - 4 January 2020 through 5 January 2020
ER -