Search

Probabilistic bit (p-bit)-based compute engines utilize the unique capability of a p-bit to probabilistically switch between two states to solve computationally challenging problems. However, when solving problems that require more than two states (e.g., problems such as Max-3-Cut, verifying if a graph is K-partite (K>2) etc.), additional pre-processing steps such as graph reduction are required to make the problem compatible with a two-state p-bit platform. Moreover, this not only increases the problem size by entailing the use of auxiliary variables but can also degrade the solution quality. In this work, we develop a unique framework for implementing a K-state (K>2) p-bit engine. Furthermore, from an implementation standpoint, we show that such a K-state p-bit engine can be implemented using N traditional (2-state) p-bits, and one multi-state p-bit -- a novel concept proposed here. Augmenting traditional p-bit platforms, our approach enables us to solve an archetypal combinatoric problem class requiring multiple states, namely Max-K-Cut (K=3, 4 shown here), without using any additional auxiliary variables. Thus, our work fundamentally advances the functional capability of p-bit engines, enabling them to solve a broader class of computationally challenging problems more efficiently.

Big data applications are on the rise, and so is the number of data centers. The ever-increasing massive data pool needs to be periodically backed up in a secure environment. Moreover, a massive amount of securely backed-up data is required for training binary convolutional neural networks for image classification. XOR and XNOR operations are essential for large-scale data copy verification, encryption, and classification algorithms. The disproportionate speed of existing compute and memory units makes the von Neumann architecture inefficient to perform these Boolean operations. Compute-in-memory (CiM) has proved to be an optimum approach for such bulk computations. The existing CiM-based XOR/XNOR techniques either require multiple cycles for computing or add to the complexity of the fabrication process. Here, we propose a CMOS-based hardware topology for single-cycle in-memory XOR/XNOR operations. Our design provides at least 2 times improvement in the latency compared with other existing CMOS-compatible solutions. We verify the proposed system through circuit/system-level simulations and evaluate its robustness using a 5000-point Monte Carlo variation analysis. This all-CMOS design paves the way for practical implementation of CiM XOR/XNOR at scaled technology nodes., Comment: 12 pages, 6 figures, 1 table

The rich non-linear dynamics of the coupled oscillators (under second harmonic injection) can be leveraged to solve computationally hard problems in combinatorial optimization such as finding the ground state of the Ising Hamiltonian. While prior work on the stability of the so-called Oscillator Ising Machines (OIMs) has used the linearization method, in this letter, we present a complementary method to analyze stability using the second order derivative test of the energy / cost function. We establish the equivalence between the two methods, thus augmenting the tool kit for the design and implementation of OIMs.

Nonlinear dynamical systems such as coupled oscillators are being actively investigated as Ising machines for solving computationally hard problems in combinatorial optimization. Prior works have established the equivalence between the global minima of the Lyapunov function (commonly referred to as the energy function) describing the coupled oscillator system and the ground state of the Ising Hamiltonian. However, the properties of the oscillator Ising machine (OIM) from a nonlinear control viewpoint, such as the stability of the OIM solutions remains unexplored. Therefore, in this work, using nonlinear control-theoretic analysis, we (i) Identify the conditions required to ensure the functionality of the coupled oscillators as an Ising machine; (ii) Show that all globally optimal phase configurations may not always be stable, resulting in some configurations being more favored over others, and thus, creating a biased OIM; (c) Elucidate the impact of the stability of locally optimal phase configurations on the quality of the solution computed by the system. Our work, fostered through the unique convergence between nonlinear control theory and analog systems for computing, provides a new toolbox for the design and implementation of dynamical system-based computing platforms.

The Ising model provides a natural mapping for many computationally hard combinatorial optimization problems (COPs). Consequently, dynamical system-inspired computing models and hardware platforms that minimize the Ising Hamiltonian, have recently been proposed as a potential candidate for solving COPs, with the promise of significant performance benefit. However, the Ising model, and consequently, the corresponding dynamical system-based computational models primarily consider quadratic interactions among the nodes. Computational models considering higher order interactions among Ising spins remain largely unexplored. Therefore, in this work, we propose dynamical-system-based computational models to consider higher order (>2) interactions among the Ising spins, which subsequently, enables us to propose computational models to directly solve many COPs that entail such higher order interactions (COPs on hypergraphs). Specifically, we demonstrate our approach by developing dynamical systems to compute the solution for the Boolean NAE-K-SAT (K is greater than 3) problem as well as solve the Max-K-Cut of a hypergraph. Our work advances the potential of the physics-inspired 'toolbox' for solving COPs.

Dynamical systems can offer a novel non-Boolean approach to computing. Specifically, the natural minimization of energy in the system is a valuable property for minimizing the objective functions of combinatorial optimization problems, many of which are still challenging to solve using conventional digital solvers. In this work, we formulate two oscillator-inspired dynamical systems to solve quintessential computationally intractable problems in Boolean satisfiability (SAT). The system dynamics are engineered such that they facilitate solutions to two different flavors of the SAT problem. We formulate the first dynamical system to compute the solution to the 3-SAT problem, while for the second system, we show that its dynamics map to the solution of the Max-NAE-3-SAT problem. Our work advances understanding of how this physics-inspired approach can be used to address challenging problems in computing.

The intrinsic energy minimization in dynamical systems offers a valuable tool for minimizing the objective functions of computationally challenging problems in combinatorial optimization. However, most prior works have focused on mapping such dynamics to combinatorial optimization problems whose objective functions have quadratic degree (e.g., MaxCut); such problems can be represented and analyzed using graphs. However, the work on developing such models for problems that need objective functions with degree greater than two, and subsequently, entail the use of hypergraph data structures, is relatively sparse. In this work, we develop dynamical system-inspired computational models for several such problems. Specifically, we define the 'energy function' for hypergraph-based combinatorial problems ranging from Boolean SAT and its variants to integer factorization, and subsequently, define the resulting system dynamics. We also show that the design approach is applicable to optimization problems with quadratic degree, and use it develop a new dynamical system formulation for minimizing the Ising Hamiltonian. Our work not only expands on the scope of problems that can be directly mapped to, and solved using physics-inspired models, but also creates new opportunities to design high-performance accelerators for solving combinatorial optimization.

The equivalence between the natural minimization of energy in a dynamical system and the minimization of an objective function characterizing a combinatorial optimization problem offers a promising approach to designing dynamical system-inspired computational models and solvers for such problems. For instance, the ground state energy of coupled electronic oscillators, under second harmonic injection, can be directly mapped to the optimal solution of the Maximum Cut problem. However, prior work has focused on a limited set of such problems. Therefore, in this work, we formulate computing models based on synchronized oscillator dynamics for a broad spectrum of combinatorial optimization problems ranging from the Max-K-Cut (the general version of the Maximum Cut problem) to the Traveling Salesman Problem. We show that synchronized oscillator dynamics can be engineered to solve these different combinatorial optimization problems by appropriately designing the coupling function and the external injection to the oscillators. Our work marks a step forward towards expanding the functionalities of oscillator-based analog accelerators and furthers the scope of dynamical system solvers for combinatorial optimization problems., Comment: 38 pages, 10 figures

Realizing compact and scalable Ising machines that are compatible with CMOS-process technology is crucial to the effectiveness and practicality of using such hardware platforms for accelerating computationally intractable problems. Besides the need for realizing compact Ising spins, the implementation of the coupling network, which describes the spin interaction, is also a potential bottleneck in the scalability of such platforms. Therefore, in this work, we propose an Ising machine platform that exploits the novel behavior of compact bi-stable CMOS-latches (cross-coupled inverters) as classical Ising spins interacting through highly scalable and CMOS-process compatible ferroelectric-HfO2-based Ferroelectric FETs (FeFETs) which act as coupling elements. We experimentally demonstrate the prototype building blocks of this system, and evaluate the behavior of the scaled system using simulations. We project that the proposed architecture can compute Ising solutions with an efficiency of ~1.04 x 10^8 solutions/W/second. Our work not only provides a pathway to realizing CMOS-compatible designs but also to overcoming their scaling challenges., Comment: 29 pages, 10 figures

The quest to solve hard combinatorial optimization problems efficiently -- still a longstanding challenge for traditional digital computers -- has inspired the exploration of many alternate computing models and platforms. As a case in point, oscillator networks offer a potentially promising energy efficient and scalable option. However, prior oscillator-based combinatorial optimization solvers have primarily focused on quadratic combinatorial optimization problems that consider only pairwise interaction among the oscillators. In this work, we propose a new computational model based on the maximum entropy production (MEP) principle that exploits higher order interactions among the oscillators, and demonstrate its application in solving the non-quadratic maximum satisfiability (MaxSAT) problem. We demonstrate that the solution to the MaxSAT problem can be directly mapped to the entropy production rate in the oscillator network, and subsequently, propose an area-efficient hardware implementation that leverages Compute-in-Memory (CiM) primitives. Using experiments along with analytical and circuit simulations, we elucidate the performance of the proposed approach in computing high-quality optimal / near-optimal solutions to the MaxSAT problem. Our work not only reveals how oscillators can solve non-quadratic combinatorial optimization problems such as MaxSAT but also extends the application of this dynamical system-based approach to a broader class of problems that can be easily decomposed to the MaxSAT solution.

Ferroelectrics offer a promising materials platform to realize energy-efficient non-volatile memory technology with the FeFET-based implementations being one of the most area-efficient ferroelectric memory architectures. However, the FeFET operation entails a fundamental trade-off between the read and the program operations. To overcome this trade-off, we propose in this work, a novel device, Mott-FeFET, that aims to replace the Silicon channel of the FeFET with VO2- a material that exhibits an electrically driven insulator-metal phase transition. The Mott-FeFET design, which demonstrates a (ferroelectric) polarization-dependent threshold voltage, enables the read current distinguishability (i.e., the ratio of current sensed when the Mott-FeFET is in state 1 and 0, respectively) to be independent of the program voltage. This enables the device to be programmed at low voltages without affecting the ability to sense/read the state of the device. Our work provides a pathway to realize low-voltage and energy-efficient non-volatile memory solutions., Comment: 23 pages, manuscript and supplementary information combined

Coupled electronic oscillators have recently been explored as a compact, integrated circuit- and room temperature operation- compatible hardware platform to design Ising machines. However, such implementations presently require the injection of an externally generated second-harmonic signal to impose the phase bipartition among the oscillators. In this work, we experimentally demonstrate a new electronic autaptic oscillator (EAO) that uses engineered feedback to eliminate the need for the generation and injection of the external second harmonic signal to minimize the Ising Hamiltonian. The feedback in the EAO is engineered to effectively generate the second harmonic signal internally. Using this oscillator design, we show experimentally, that a system of capacitively coupled EAOs exhibits the desired bipartition in the oscillator phases, and subsequently, demonstrate its application in solving the computationally hard Maximum Cut (MaxCut) problem. Our work not only establishes a new oscillator design aligned to the needs of the oscillator Ising machine but also advances the efforts to creating application specific analog computing platforms., Comment: 18 pages, 5 figures

CNF-based SAT and MaxSAT solvers are central to logic synthesis and verification systems. The increasing popularity of these constraint problems in electronic design automation encourages studies on different SAT problems and their properties for further computational efficiency. There has been both theoretical and practical success of modern Conflict-driven clause learning SAT solvers, which allows solving very large industrial instances in a relatively short amount of time. Recently, machine learning approaches provide a new dimension to solving this challenging problem. Neural symbolic models could serve as generic solvers that can be specialized for specific domains based on data without any changes to the structure of the model. In this work, we propose a one-shot model derived from the Transformer architecture to solve the MaxSAT problem, which is the optimization version of SAT where the goal is to satisfy the maximum number of clauses. Our model has a scale-free structure which could process varying size of instances. We use meta-path and self-attention mechanism to capture interactions among homogeneous nodes. We adopt cross-attention mechanisms on the bipartite graph to capture interactions among heterogeneous nodes. We further apply an iterative algorithm to our model to satisfy additional clauses, enabling a solution approaching that of an exact-SAT problem. The attention mechanisms leverage the parallelism for speedup. Our evaluation indicates improved speedup compared to heuristic approaches and improved completion rate compared to machine learning approaches.

Noise is expected to play an important role in the dynamics of analog systems such as coupled oscillators which have recently been explored as a hardware platform for application in computing. In this work, we experimentally investigate the effect of noise on the synchronization of relaxation oscillators and their computational properties. Specifically, in contrast to its typically expected adverse effect, we first demonstrate that a common white noise input induces global frequency synchronization among uncoupled oscillators. Experiments show that the minimum noise voltage required to induce synchronization increases linearly with the amplitude of the oscillator output whereas it decreases with increasing number of oscillators. Further, our work reveals that in a coupled system of oscillators - relevant to solving computational problems such as graph coloring, the injection of white noise helps reduce the minimum required capacitive coupling strength. With the injection of noise, the coupled system demonstrates frequency synchronization along with the desired phase-based computational properties at 5x lower coupling strength than that required when no external noise is introduced. Consequently, this can reduce the footprint of the coupling element and the corresponding area-intensive coupling architecture. Our work shows that noise can be utilized as an effective knob to optimize the implementation of coupled oscillator-based computing platforms.

In this work, we experimentally demonstrate an integrated circuit (IC) of 30 relaxation oscillators with reconfigurable capacitive coupling to solve the NP-Hard Maximum Cut (Max-Cut) problem. We show that under the influence of an external second-harmonic injection signal, the oscillator phases exhibit a bi-partition which can be used to calculate a high quality approximate Max-Cut solution. Leveraging the all-to-all reconfigurable coupling architecture, we experimentally evaluate the computational properties of the oscillators using randomly generated graph instances of varying size and edge density . Further, comparing the Max-Cut solutions with the optimal values, we show that the oscillators (after simple post-processing) produce a Max-Cut that is within 99% of the optimal value in 28 of the 36 measured graphs; importantly, the oscillators are particularly effective in dense graphs with the Max-Cut being optimal in seven out of nine measured graphs with edge density 0.8. Our work marks a step towards creating an efficient, room-temperature-compatible non-Boolean hardware-based solver for hard combinatorial optimization problems.

While Boolean logic has been the backbone of digital information processing, there are classes of computationally hard problems wherein this conventional paradigm is fundamentally inefficient. Vertex coloring of graphs, belonging to the class of combinatorial optimization represents such a problem; and is well studied for its wide spectrum of applications in data sciences, life sciences, social sciences and engineering and technology. This motivates alternate, and more efficient non-Boolean pathways to their solution. Here, we demonstrate a coupled relaxation oscillator based dynamical system that exploits the insulator-metal transition in vanadium dioxide (VO2), to efficiently solve the vertex coloring of graphs. By harnessing the natural analogue between optimization, pertinent to graph coloring solutions, and energy minimization processes in highly parallel, interconnected dynamical systems, we harness the physical manifestation of the latter process to approximate the optimal coloring of k-partite graphs. We further indicate a fundamental connection between the eigen properties of a linear dynamical system and the spectral algorithms that can solve approximate graph coloring. Our work not only elucidates a physics-based computing approach but also presents tantalizing opportunities for building customized analog co-processors for solving hard problems efficiently.

In this paper we review recent work on novel computing paradigms using coupled oscillatory dynamical systems. We explore systems of relaxation oscillators based on linear state transitioning devices, which switch between two discrete states with hysteresis. By harnessing the dynamics of complex, connected systems we embrace the philosophy of "let physics do the computing" and demonstrate how complex phase and frequency dynamics of such systems can be controlled, programmed and observed to solve computationally hard problems. Although our discussion in this paper is limited to Insulator-to-Metallic (IMT) state transition devices, the general philosophy of such computing paradigms can be translated to other mediums including optical systems. We present the necessary mathematical treatments necessary to understand the time evolution of these systems and demonstrate through recent experimental results the potential of such computational primitives., Comment: Submitted to Journal of Nanophotonics for review

Computing with networks of synchronous oscillators has attracted wide-spread attention as novel materials and device topologies have enabled realization of compact, scalable and low-power coupled oscillatory systems. Of particular interest are compact and low-power relaxation oscillators that have been recently demonstrated using MIT (metal- insulator-transition) devices using properties of correlated oxides. This paper presents an analysis of the dynamics and synchronization of a system of two such identical coupled relaxation oscillators implemented with MIT devices. We focus on two implementations of the oscillator: (a) a D-D configuration where complementary MIT devices (D) are connected in series to provide oscillations and (b) a D-R configuration where it is composed of a resistor (R) in series with a voltage-triggered state changing MIT device (D). The MIT device acts like a hysteresis resistor with different resistances in the two different states. The synchronization dynamics of such a system has been analyzed with purely charge based coupling using a resistive (Rc) and a capacitive (Cc) element in parallel. It is shown that in a D-D configuration symmetric, identical and capacitively coupled relaxation oscillator system synchronizes to an anti-phase locking state, whereas when coupled resistively the system locks in phase. Further, we demonstrate that for certain range of values of Rc and Cc, a bistable system is possible which can have potential applications in associative computing. In D-R configuration, we demonstrate the existence of rich dynamics including non-monotonic flows and complex phase relationship governed by the ratios of the coupling impedance. Finally, the developed theoretical formulations have been shown to explain experimentally measured waveforms of such pairwise coupled relaxation oscillators., Comment: Submitted for review to (AIP) Journal of Applied Physics