Autonomous Probabilistic Coprocessing with Petaflips per Second

Abstract

In this paper we present a concrete design for a probabilistic (p-) computer based on a network of p-bits, robust classical entities fluctuating between -1 and +1, with probabilities that are controlled through an input constructed from the outputs of other p-bits. The architecture of this probabilistic computer is similar to a stochastic neural network with the p-bit playing the role of a binary stochastic neuron, but with one key difference: there is no sequencer used to enforce an ordering of p-bit updates, as is typically required. Instead, we explore \textit{sequencerless} designs where all p-bits are allowed to flip autonomously and demonstrate that such designs can allow ultrafast operation unconstrained by available clock speeds without compromising the solution's fidelity. Based on experimental results from a hardware benchmark of the autonomous design and benchmarked device models, we project that a nanomagnetic implementation can scale to achieve petaflips per second with millions of neurons. A key contribution of this paper is the focus on a hardware metric $-$ flips per second $-$ as a problem and substrate-independent figure-of-merit for an emerging class of hardware annealers known as Ising Machines. Much like the shrinking feature sizes of transistors that have continually driven Moore's Law, we believe that flips per second can be continually improved in later technology generations of a wide class of probabilistic, domain specific hardware.

arXiv comment13 pages, 8 figures, 1 table

References in corpus (30)

• Ising formulations of many NP problems
• Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1
• Computational complexity and fundamental limitations to fermionic quantum Monte Carlo simulations
• Quantum annealing with more than one hundred qubits
• Theory of Quantum Annealing of an Ising Spin Glass
• Physics-Inspired Optimization for Quadratic Unconstrained Problems Using a Digital Annealer
• Stochastic p-bits for Invertible Logic
• A Survey of Neuromorphic Computing and Neural Networks in Hardware
• Experimental investigation of performance differences between Coherent Ising Machines and a quantum annealer
• What is the Computational Value of Finite Range Tunneling?
• Minor-embedding in adiabatic quantum computation: II. Minor-universal graph design
• p-Bits for Probabilistic Spin Logic
• Intrinsic optimization using stochastic nanomagnets
• Quantum versus Classical Annealing of Ising Spin Glasses
• Switching Distributions for Perpendicular Spin-Torque Devices within the Macrospin Approximation
• Hardware emulation of stochastic p-bits for invertible logic
• Energy-efficient stochastic computing with superparamagnetic tunnel junctions
• Stochastic Spiking Neural Networks Enabled by Magnetic Tunnel Junctions: From Nontelegraphic to Telegraphic Switching Regimes
• Low Barrier Magnet Design for Efficient Hardware Binary Stochastic Neurons
• Janus II: a new generation application-driven computer for spin-system simulations
• A building block for hardware belief networks
• Scalable Emulation of Sign-Problem$-$Free Hamiltonians with Room Temperature p-bits
• Oscillator-based Ising Machine
• Composable Probabilistic Inference Networks Using MRAM-based Stochastic Neurons
• Experimental Demonstration of Probabilistic Spin Logic by Magnetic Tunnel Junctions
• Modular Compact Modeling of Magnetic Tunnel Junction Devices
• FPGA Hardware Acceleration of Monte Carlo Simulations for the Ising Model
• Harnessing Intrinsic Noise in Memristor Hopfield Neural Networks for Combinatorial Optimization
• Robustness and scalability of p-bits implemented with low energy barrier nanomagnets
• Quadratization in discrete optimization and quantum mechanics

Cited by in corpus (27)

• Massively Parallel Probabilistic Computing with Sparse Ising Machines
• A full-stack view of probabilistic computing with p-bits: devices, architectures and algorithms
• Demonstration of nanosecond operation in stochastic magnetic tunnel junctions
• Probabilistic computing with p-bits
• Hardware-aware $insitu$ Boltzmann machine learning using stochastic magnetic tunnel junctions
• CMOS + stochastic nanomagnets: heterogeneous computers for probabilistic inference and learning
• Experimental demonstration of an integrated on-chip p-bit core utilizing stochastic Magnetic Tunnel Junctions and 2D-MoS2 FETs
• Efficient Probabilistic Computing with Stochastic Perovskite Nickelates
• Accelerated Quantum Monte Carlo with Probabilistic Computers
• All-to-all reconfigurability with sparse and higher-order Ising machines
• Hardware Design for Autonomous Bayesian Networks
• Enhanced Convergence in p-bit Based Simulated Annealing with Partial Deactivation for Large-Scale Combinatorial Optimization Problems
• Lanthanide molecular nanomagnets as probabilistic bits
• Physics-inspired Ising Computing with Ring Oscillator Activated p-bits
• Noise-augmented Chaotic Ising Machines for Combinatorial Optimization and Sampling
• Emulating Quantum Interference with Generalized Ising Machines
• Pushing the Boundary of Quantum Advantage in Hard Combinatorial Optimization with Probabilistic Computers
• GPU-accelerated simulated annealing based on p-bits with real-world device-variability modeling
• pc-COP: An Efficient and Configurable 2048-p-Bit Fully-Connected Probabilistic Computing Accelerator for Combinatorial Optimization
• The First Hardware Demonstration of a Universal Programmable RRAM-based Probabilistic Computer for Molecular Docking
• Superparamagnetic and Stochastic-Write Magnetic Tunnel Junctions for High-Speed True Random Number Generation in Advanced Computing
• Application of Probabilistic-bit in Precision Measurements
• In-plane dominant anisotropy stochastic magnetic tunnel junction for probabilistic computing: A Fokker-Planck study
• Metrics for spin-based computing
• Improving deep neural network performance through sampling
• An improved update rule for probabilistic computers
• Predicting sampling advantage of stochastic Ising Machines for Quantum Simulations