Shahar Kvatinsky

Bio: Shahar Kvatinsky is an academic researcher from Technion – Israel Institute of Technology. The author has contributed to research in topics: Memristor & Computer science. The author has an hindex of 28, co-authored 113 publications receiving 3855 citations. Previous affiliations of Shahar Kvatinsky include University of California, Berkeley & Stanford University.

TEAM: ThrEshold Adaptive Memristor Model

Abstract: Memristive devices are novel devices, which can be used in applications ranging from memory and logic to neuromorphic systems. A memristive device offers several advantages: nonvolatility, good scalability, effectively no leakage current, and compatibility with CMOS technology, both electrically and in terms of manufacturing. Several models for memristive devices have been developed and are discussed in this paper. Digital applications such as memory and logic require a model that is highly nonlinear, simple for calculations, and sufficiently accurate. In this paper, a new memristive device model is presented-TEAM, ThrEshold Adaptive Memristor model. This model is flexible and can be fit to any practical memristive device. Previously published models are compared in this paper to the proposed TEAM model. It is shown that the proposed model is reasonably accurate and computationally efficient, and is more appropriate for circuit simulation than previously published models.

MAGIC—Memristor-Aided Logic

Abstract: Memristors are passive components with a varying resistance that depends on the previous voltage applied across the device. While memristors are naturally used as memory, memristors can also be used for other applications, including logic circuits. In this brief, a memristor-only logic family, i.e., memristor-aided logic (MAGIC), is presented. In each MAGIC logic gate, memristors serve as an input with previously stored data, and an additional memristor serves as an output. The topology of a MAGIC nor gate is similar to the structure of a common memristor-based crossbar memory array. A MAGIC nor gate can therefore be placed within memory, providing opportunities for novel non-von Neumann computer architectures. Other MAGIC gates also exist (e.g., and , or , not , and nand ) and are described in this brief.

VTEAM: A General Model for Voltage-Controlled Memristors

Abstract: Memristors are novel electrical devices used for a variety of applications, including memory, logic circuits, and neuromorphic systems. Memristive technologies are attractive due to their nonvolatility, scalability, and compatibility with CMOS. Numerous physical experiments have shown the existence of a threshold voltage in some physical memristors. Additionally, as shown in this brief, some applications require voltage-controlled memristors to operate properly. In this brief, a Voltage ThrEshold Adaptive Memristor (VTEAM) model is proposed to describe the behavior of voltage-controlled memristors. The VTEAM model extends the previously proposed ThrEshold Adaptive Memristor (TEAM) model, which describes current-controlled memristors. The VTEAM model has similar advantages as the TEAM model, i.e., it is simple, general, and flexible, and can characterize different voltage-controlled memristors. The VTEAM model is accurate (below 1.5% in terms of the relative root-mean-square error) and computationally efficient as compared with existing memristor models and experimental results describing different memristive technologies.

Memristor-Based Material Implication (IMPLY) Logic: Design Principles and Methodologies

Abstract: Memristors are novel devices, useful as memory at all hierarchies. These devices can also behave as logic circuits. In this paper, the IMPLY logic gate, a memristor-based logic circuit, is described. In this memristive logic family, each memristor is used as an input, output, computational logic element, and latch in different stages of the computing process. The logical state is determined by the resistance of the memristor. This logic family can be integrated within a memristor-based crossbar, commonly used for memory. In this paper, a methodology for designing this logic family is proposed. The design methodology is based on a general design flow, suitable for all deterministic memristive logic families, and includes some additional design constraints to support the IMPLY logic family. An IMPLY 8-bit full adder based on this design methodology is presented as a case study.

Logic Design Within Memristive Memories Using Memristor-Aided loGIC (MAGIC)

Abstract: Realizing logic operations within passive crossbar memory arrays is a promising approach to enable novel computer architectures, different from conventional von Neumann architecture. Attractive candidates to enable such architectures are memristors, nonvolatile memory elements commonly used within a crossbar, that can also perform logic operations. In such novel architectures, data are stored and processed within the same entity, which we term as memristive memory processing unit (MPU). In this paper, Memristor-Aided loGIC (MAGIC) family is discussed with various design considerations and novel techniques to execute logic within an MPU. We present a novel resistive memory-the transpose memory, which adds additional functionality to the memristive memory, and compare it with a conventional memristive memory. A case study of an adder is presented to demonstrate the design issues discussed in this paper. We compare the proposed design techniques with the memristive IMPLY logic in terms of speed, area, and energy. Our evaluation shows that the proposed MAGIC design is 2.4 × faster and consumes 66.3% less energy as compared with the IMPLY-based computing for N-bit addition within memristive crossbar memory. Additionally, we compare the proposed design with IMPLY logic family on ISCAS-85 benchmarks, which shows significant improvements in speed (2×) and energy (10×), with similar area.

Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Abstract: We introduce a method to train Binarized Neural Networks (BNNs) - neural networks with binary weights and activations at run-time. At training-time the binary weights and activations are used for computing the parameters gradients. During the forward pass, BNNs drastically reduce memory size and accesses, and replace most arithmetic operations with bit-wise operations, which is expected to substantially improve power-efficiency. To validate the effectiveness of BNNs we conduct two sets of experiments on the Torch7 and Theano frameworks. On both, BNNs achieved nearly state-of-the-art results over the MNIST, CIFAR-10 and SVHN datasets. Last but not least, we wrote a binary matrix multiplication GPU kernel with which it is possible to run our MNIST BNN 7 times faster than with an unoptimized GPU kernel, without suffering any loss in classification accuracy. The code for training and running our BNNs is available on-line.

In-memory computing with resistive switching devices

Abstract: Modern computers are based on the von Neumann architecture in which computation and storage are physically separated: data are fetched from the memory unit, shuttled to the processing unit (where computation takes place) and then shuttled back to the memory unit to be stored. The rate at which data can be transferred between the processing unit and the memory unit represents a fundamental limitation of modern computers, known as the memory wall. In-memory computing is an approach that attempts to address this issue by designing systems that compute within the memory, thus eliminating the energy-intensive and time-consuming data movement that plagues current designs. Here we review the development of in-memory computing using resistive switching devices, where the two-terminal structure of the devices, their resistive switching properties, and direct data processing in the memory can enable area- and energy-efficient computation. We examine the different digital, analogue, and stochastic computing schemes that have been proposed, and explore the microscopic physical mechanisms involved. Finally, we discuss the challenges in-memory computing faces, including the required scaling characteristics, in delivering next-generation computing. This Review Article examines the development of in-memory computing using resistive switching devices.

Memory devices and applications for in-memory computing

Abstract: Traditional von Neumann computing systems involve separate processing and memory units. However, data movement is costly in terms of time and energy and this problem is aggravated by the recent explosive growth in highly data-centric applications related to artificial intelligence. This calls for a radical departure from the traditional systems and one such non-von Neumann computational approach is in-memory computing. Hereby certain computational tasks are performed in place in the memory itself by exploiting the physical attributes of the memory devices. Both charge-based and resistance-based memory devices are being explored for in-memory computing. In this Review, we provide a broad overview of the key computational primitives enabled by these memory devices as well as their applications spanning scientific computing, signal processing, optimization, machine learning, deep learning and stochastic computing. This Review provides an overview of memory devices and the key computational primitives for in-memory computing, and examines the possibilities of applying this computing approach to a wide range of applications.

Binarized Neural Networks

Abstract: We introduce a method to train Binarized Neural Networks (BNNs) - neural networks with binary weights and activations at run-time and when computing the parameters' gradient at train-time. We conduct two sets of experiments, each based on a different framework, namely Torch7 and Theano, where we train BNNs on MNIST, CIFAR-10 and SVHN, and achieve nearly state-of-the-art results. During the forward pass, BNNs drastically reduce memory size and accesses, and replace most arithmetic operations with bit-wise operations, which might lead to a great increase in power-efficiency. Last but not least, we wrote a binary matrix multiplication GPU kernel with which it is possible to run our MNIST BNN 7 times faster than with an unoptimized GPU kernel, without suffering any loss in classification accuracy. The code for training and running our BNNs is available.

Neuromorphic computing using non-volatile memory

Abstract: Dense crossbar arrays of non-volatile memory (NVM) devices represent one possible path for implementing massively-parallel and highly energy-efficient neuromorphic computing systems. We first revie...