TY - CONF
AU - Jiang, Mingrui
AU - Shan, Keyi
AU - Sheng, Xia
AU - Graves, Cat
AU - Strachan, John Paul
AU - Li, Can
TI - An efficient synchronous-updating memristor-based Ising solver for combinatorial optimization
PB - IEEE
M1 - FZJ-2024-00959
SP - 22.2.1-22.2.4
PY - 2022
AB - Despite showing significant potential in solving combinatorial optimization problems, existing memristor-based solvers update node states asynchronously by performing matrix multiplication column-by-column, leaving the massive parallelism of the crossbar not fully exploited. In this work, we propose and experimentally demonstrate solving the optimization problems with a synchronous-updating memristor-based Ising solver, which is realized by a binary neural network-inspired updating algorithm and a physics-inspired annealing method. The newly proposed method saves more than 5x time and 35x energy consumption compared to the state-of-the-art mem-HNN for finding the optimal solution to a 60-node Max-cut problem.
T2 - 2022 IEEE International Electron Devices Meeting (IEDM)
CY - 3 Dec 2022 - 7 Dec 2022, San Francisco (USA)
Y2 - 3 Dec 2022 - 7 Dec 2022
M2 - San Francisco, USA
LB - PUB:(DE-HGF)8
UR - <Go to ISI:>//WOS:000968800700008
DO - DOI:10.1109/IEDM45625.2022.10019348
UR - https://juser.fz-juelich.de/record/1021714
ER -