Ising-Model Optimizer with Parallel-Trial Bit-Sieve Engine

We propose a hardware architecture for solving combinatorial optimization problems and implemented it on an FPGA. The hardware minimizes the energy of Ising model with 1,024 state variables fully connectable through 16-bit weights, which ease restrictions on mapping problems onto the Ising model. The system uses a hardware bit-sieve engine that performs a Markov-chain Monte-Carlo search with a parallel-evaluation of the energy increment prior to the bit selection, achieving a speedup while guaranteeing convergence. The engine is implemented on an Arria 10 GX FPGA and solves 32-city traveling salesman problems 104 times faster than simulated annealing running on a 3.5-GHz Intel Xeon E5-1620v3 processor.

[1]  Fuji Ren,et al.  A Boltzmann Machine with Non-rejective Move , 2002, IEICE Trans. Fundam. Electron. Commun. Comput. Sci..

[2]  N. Metropolis,et al.  Equation of State Calculations by Fast Computing Machines , 1953, Resonance.

[3]  P. Faraboschi,et al.  Application specific parallel architectures , 1994, Proceedings of the First International Conference on Massively Parallel Computing Systems (MPCS) The Challenges of General-Purpose and Special-Purpose Computing.

[4]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[5]  Marcin Skubiszewski,et al.  An exact hardware implementation of the Boltzmann machine , 1992, [1992] Proceedings of the Fourth IEEE Symposium on Parallel and Distributed Processing.

[6]  K. Hukushima,et al.  Exchange Monte Carlo Method and Application to Spin Glass Simulations , 1995, cond-mat/9512035.

[7]  Tim P. Schulze,et al.  Efficient kinetic Monte Carlo simulation , 2008, J. Comput. Phys..

[8]  Mark W. Johnson,et al.  Architectural Considerations in the Design of a Superconducting Quantum Annealing Processor , 2014, IEEE Transactions on Applied Superconductivity.

[9]  M. W. Johnson,et al.  Quantum annealing with manufactured spins , 2011, Nature.

[10]  Bernard Brezzo,et al.  TrueNorth: Design and Tool Flow of a 65 mW 1 Million Neuron Programmable Neurosynaptic Chip , 2015, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[11]  David A. Patterson,et al.  In-datacenter performance analysis of a tensor processing unit , 2017, 2017 ACM/IEEE 44th Annual International Symposium on Computer Architecture (ISCA).

[12]  Emile H. L. Aarts,et al.  Boltzmann Machines and their Applications , 1987, PARLE.

[13]  Hiroyuki Mizuno,et al.  24.3 20k-spin Ising chip for combinational optimization problem with CMOS annealing , 2015, 2015 IEEE International Solid-State Circuits Conference - (ISSCC) Digest of Technical Papers.

[14]  Andrew S. Cassidy,et al.  A million spiking-neuron integrated circuit with a scalable communication network and interface , 2014, Science.

[15]  A. B. Bortz,et al.  A new algorithm for Monte Carlo simulation of Ising spin systems , 1975 .