Stochastic p-bits for Invertible Logic

Abstract

Conventional logic and memory devices are built out of deterministic units such as transistors, or magnets with energy barriers in excess of 40-60 kT. We show that stochastic units, p-bits, can be interconnected to create robust correlations that implement Boolean functions with impressive accuracy, comparable to standard circuits. Also they are invertible, a unique property that is absent in digital circuits. When operated in the direct mode, the input is clamped, and the network provides the correct output. In the inverted mode, the output is clamped, and the network fluctuates among possible inputs consistent with that output. We present an implementation of an invertible gate to bring out the key role of a three-terminal building block to enable the construction of correlated p-bit networks. The results for this implementation agree well with those from a universal model, showing that p-bits need not be magnet-based: any three-terminal tunable random bit generator should be suitable. We present an algorithm for designing a Boltzmann machine (BM) with symmetric connections that implements a given truth table. We then show how BM Full Adders can be interconnected in a partially directed manner to implement large operations such as 32-bit addition. Hundreds of p-bits get precisely correlated such that the correct answer out of 2^33 possibilities can be extracted by looking at the mode of a number of time samples. With perfect directivity a small number of samples is enough, while for less directed connections more samples are needed, but even in the former case invertibility is largely preserved. This combination of accuracy and invertibility is enabled by the hybrid design that uses bidirectional units to construct circuits with partially directed connections. We establish this result with examples including a 4-bit multiplier which in inverted mode functions as a factorizer.

This is the third in a series of papers on probabilistic spin logic (PSL). The other papers are: arXiv:1606.00130, arXiv:1608.00679, arXiv:1611.05477

References in corpus (5)

• Large-scale Ising spin network based on degenerate optical parametric oscillators
• Intrinsic optimization using stochastic nanomagnets
• Non-volatile Spin Switch for Boolean and Non-Boolean Logic
• Non-perturbative k-body to two-body commuting conversion Hamiltonians and embedding problem instances into Ising spins
• A building block for hardware belief networks

Cited by in corpus (99)

• Current-induced spin-orbit torques in ferromagnetic and antiferromagnetic systems
• Roadmap of spin-orbit torques
• p-Bits for Probabilistic Spin Logic
• Massively Parallel Probabilistic Computing with Sparse Ising Machines
• The promise of spintronics for unconventional computing
• Maximizing Spin-Orbit Torque Generated by the Spin Hall Effect of Pt
• 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 emulation of stochastic p-bits for invertible logic
• Hardware-aware $insitu$ Boltzmann machine learning using stochastic magnetic tunnel junctions
• Energy-efficient stochastic computing with superparamagnetic tunnel junctions
• Roadmap for Unconventional Computing with Nanotechnology
• Implementing Bayesian Networks with Embedded Stochastic MRAM
• Weighted p-bits for FPGA implementation of probabilistic circuits
• Efficient CMOS Invertible Logic Using Stochastic Computing
• Stochastic Thermodynamics of Non-Linear Electronic Circuits: A Realistic Framework for Computing around kT
• Low Barrier Magnet Design for Efficient Hardware Binary Stochastic Neurons
• Autonomous Probabilistic Coprocessing with Petaflips per Second
• Scalable Emulation of Sign-Problem$-$Free Hamiltonians with Room Temperature p-bits
• Oscillator-based Ising Machine
• Low-Energy Deep Belief Networks using Intrinsic Sigmoidal Spintronic-based Probabilistic Neurons
• Subnanosecond Fluctuations in Low-Barrier Nanomagnets
• Spintronics-compatible approach to solving maximum satisfiability problems with probabilistic computing, invertible logic and parallel tempering
• Experimental Demonstration of Probabilistic Spin Logic by Magnetic Tunnel Junctions
• Composable Probabilistic Inference Networks Using MRAM-based Stochastic Neurons
• Modular Compact Modeling of Magnetic Tunnel Junction Devices
• Double Free-Layer Magnetic Tunnel Junctions for Probabilistic Bits
• Efficient Probabilistic Computing with Stochastic Perovskite Nickelates
• Quantitative Evaluation of Hardware Binary Stochastic Neurons
• Immunity of nanoscale magnetic tunnel junctions to ionizing radiation
• Evaluating spintronics-compatible implementations of Ising machines
• Instantons in self-organizing logic gates
• Emerging spintronics phenomena and applications
• Hardware Design for Autonomous Bayesian Networks
• Correlated fluctuations in spin orbit torque-coupled perpendicular nanomagnets
• Low Barrier Nanomagnet Design for Binary Stochastic Neurons: Design Challenges for Real Nanomagnets with Fabrication Defects
• Mutual control of stochastic switching for two electrically coupled superparamagnetic tunnel junctions
• Probabilistic-Bits based on Ferroelectric Field-Effect Transistors for Stochastic Computing
• Large deviations theory for noisy non-linear electronics: CMOS inverter as a case study
• Nanomagnetic Self-Organizing Logic Gates
• Probabilistic Circuits for Autonomous Learning: A simulation study
• Temporal Memory with Magnetic Racetracks
• Magnetization reversal in bent nanofibers of different cross-sections
• Voltage-driven Building Block for Hardware Belief Networks
• From materials to systems: a multiscale analysis of nanomagnetic switching
• Robustness and scalability of p-bits implemented with low energy barrier nanomagnets
• Design of a Low Voltage Analog-to-Digital Converter using Voltage Controlled Stochastic Switching of Low Barrier Nanomagnets
• Analog Coupled Oscillator Based Weighted Ising Machine
• Spin torque gate magnetic field sensor
• Analog Signal Processing Using Stochastic Magnets
• A vector magnetometer based on a single spin-orbit torque anomalous Hall device
• Physics-inspired Ising Computing with Ring Oscillator Activated p-bits
• Double-Free-Layer Stochastic Magnetic Tunnel Junctions with Synthetic Antiferromagnets
• Voltage-insensitive stochastic magnetic tunnel junctions with double free layers
• A Josephson Parametric Oscillator-Based Ising Machine
• Fast Solving Complete 2000-Node Optimization Using Stochastic-Computing Simulated Annealing
• Heisenberg machines with programmable spin-circuits
• Scalable Connectivity for Ising Machines: Dense to Sparse
• Voltage Control of Magnetic Monopoles in Artificial Spin Ice
• Choose your tools carefully: A Comparative Evaluation of Deterministic vs. Stochastic and Binary vs. Analog Neuron models for Implementing Emerging Computing Paradigms
• Equivalent Circuit for Magnetoelectric Read and Write Operations
• Circuit-Level Evaluation of the Generation of Truly Random Bits with Superparamagnetic Tunnel Junctions
• Local Energy Distribution Based Hyperparameter Determination for Stochastic Simulated Annealing
• Superior probabilistic computing using operationally stable probabilistic-bit constructed by manganite nanowire
• OIM: Oscillator-based Ising Machines for Solving Combinatorial Optimisation Problems
• Stochastic Simulated Quantum Annealing for Fast Solution of Combinatorial Optimization Problems
• Late Breaking Results: New Computational Results and Hardware Prototypes for Oscillator-based Ising Machines
• Comparison of measured and simulated spin-wave mode spectra of magnetic nanostructures
• High Convergence Rates of CMOS Invertible Logic Circuits Based on Many-Body Hamiltonians
• Overcoming device unreliability with continuous learning in a population coding based computing system
• A Deep Dive into the Computational Fidelity of High Variability Low Energy Barrier Magnet Technology for Accelerating Optimization and Bayesian Problems
• pc-COP: An Efficient and Configurable 2048-p-Bit Fully-Connected Probabilistic Computing Accelerator for Combinatorial Optimization
• Demonstration of a strain-mediated magnetoelectric write and read unit in a Co60Fe20B20/ Pb(Mg1/3Nb2/3)0.7Ti0.3O3 heterostructure
• Rectification in Spin-Orbit Materials Using Low Energy Barrier Magnets
• Engineering-Oriented Design of Drift-Resilient MTJ Random Number Generator via Hybrid Control Strategies
• Electrically Tunable Picosecond-scale Octupole Fluctuations in Chiral Antiferromagnets
• Machine Learning Quantum Systems with Magnetic p-bits
• Hardware based Spatio-Temporal Neural Processing Backend for Imaging Sensors: Towards a Smart Camera
• Magnetic tunnel junction as a real-time entropy source: Field-Programmable Gate Array based random bit generation without post-processing
• Logically Synthesized, Hardware-Accelerated, Restricted Boltzmann Machines for Combinatorial Optimization and Integer Factorization
• Superparamagnetic and Stochastic-Write Magnetic Tunnel Junctions for High-Speed True Random Number Generation in Advanced Computing
• Lagrange Oscillatory Neural Networks for Constraint Satisfaction and Optimization
• Noise-based Local Learning using Stochastic Magnetic Tunnel Junctions
• Spintronics for neuromorphic computing
• Orthogonal Spin-Orbit Torque-Induced Deterministic Switching in NiO
• Hardware implementation of Bayesian network building blocks with stochastic spintronic devices
• Sub-universal variational circuits for combinatorial optimization problems
• In-situ learning harnessing intrinsic resistive memory variability through Markov Chain Monte Carlo Sampling
• Self-Adaptive Ising Machines for Constrained Optimization
• Switching time of spin-torque-driven magnetization in biaxial ferromagnets
• Anatomy of Type-X Spin-Orbit Torque Switching
• SNRA: A Spintronic Neuromorphic Reconfigurable Array for In-Circuit Training and Evaluation of Deep Belief Networks
• Energy-Efficient p-Bit-Based Fully-Connected Quantum-Inspired Simulated Annealer with Dual BRAM Architecture
• Analog Seizure Detection for Implanted Responsive Neurostimulation
• A Toffoli Gadget for Magnetic Tunnel Junctions Boltzmann Machines
• Combining Learned Representations for Combinatorial Optimization
• An improved update rule for probabilistic computers
• AQuRate: MRAM-based Stochastic Oscillator for Adaptive Quantization Rate Sampling of Sparse Signals