Memristive devices can not only be used as nonvolatile memories but also enable computation-in-memory (CIM) computing paradigms. CIM architectures show prospects in significantly reducing the data interaction time and energy consumption between processors and storage, thus addressing the bottleneck problem of the von Neumann architecture. Additionally, the capability of memristive devices to store multiple (resistance) states in one cell offer vast potential for CIM’s multi-valued logic, as they greatly enhance data storage density and computational efficiency. In this study, a novel concept for ternary Łukasiewicz logic utilizing the voltage divider of two (anti-)serially connected memristive devices is proposed. As this approach does not require any switching in the computation process and features a straightforward circuit architecture, a low energy consumption per operation is achieved. In addition, the concept is crossbar-array compatible. The concept is validated by circuit simulations using the JART VCM v1b model that has been calibrated to experimental data of a Pt/Ta2O5/W memristive device.

The field of neuromorphic computing is approaching an era of rapid adoption driven by the urgent need of a substitute for the von Neumann computing architecture. NEUROTEC I: “Neuro-inspired Artificial Intelligence Technologies for the Elec-tronics of the Future” project is an initiative sponsored by the German Federal Ministry of Education and Research (BMBF for its initials in German), that aims to effectively advance the foundations for the utilization and exploitation of neuromorphic computing. NEUROTEC I stands at its successful “final stage” driven by the collaboration from more than 8 institutes from the Jiilich Research Center and the RWTH Aachen University, as well as collaboration from several high-tech industry partners. The NEUROTEC I project considers the field interplay among materials, circuits, design and simulation tools. This paper provides an overview of the project's overall structure and discusses the scientific achievements of its individual activities.

Memristive devices, such as ReRAM devices, enable Computation-In-Memory operations such as vector-matrix multiplications, which are basic kernels for neuromorphic computing. These devices, however, suffer from parasitic sneak path currents in memory arrays, which make a satisfactory performance on large-scale arrays impossible. To overcome this issue, for example, a bipolar rectifying element (‘select device’) in series to a resistive switching device (1S1R) is introduced at each cross-point junction. In this work, we investigate the design of 1S1R arrays for VMM operations and show the impact of wire resistances on these operations. We derive guidelines that give a quantitative relationship between the array size, wire resistance values, resistance states of the ReRAM and the select device and resulting current levels.

As the cost of keeping Moore’s law alive is ever increasing, unconventional device and circuit concepts are being explored, both in industry and in academic research arena. Among the new devices being explored are two terminals redox-based memristive devices, which can function as both a nonvolatile memory and a computing element. For enabling Computation-in-Memory (CIM) concepts, these devices are generally integrated in a passive configuration or in an active configuration, where transistors are employed together with the memristive switches. However, the reliability and variability of the memristive devices might impact the performance of CIM circuits. In this work, we experimentally demonstrate the impact of device-to-device (D2D) and cycle-to-cycle (C2C) variability on a simple IMPLY logic gate realized in passive and active configurations. The experimental data is theoretically verified by a physics based Verilog-A model of the memristive devices. Our findings suggest that the success rate of the logic operation can be increased by exploiting the D2D variability in the memristive devices.

Computation-in-Memory (CiM) with emerging non-volatile memories leads to significant performance and energy efficiency, which is a promising approach to address so-called memory wall of conventional von Neumann architectures. Redox-based Random access memory (ReRAM) is an appropriate candidate for the realization of CiM concepts in CMOS co-integrated crossbar structures. However, ReRAM devices suffer from inherent variability in fabrication and operation. In this paper, we propose a statistical failure probability framework for the reliability evaluation of ReRAM-based CiM. Based on this, a comprehensive reliability analysis is performed for logic operations in ReRAM-based Scouting and MAGIC concepts at the crossbar level. Our proposed framework shows that existing logic operation in the crossbar architecture has a high failure probability due to the variability and crossbar non-idealities. Hence, a modified crossbar design is proposed to achieve the target reliability requirements.

Conventional von Neumann architectures cannot successfully meet the demands of emerging computation and data-intensive applications. These shortcomings can be improved by embracing new architectural paradigms using emerging technologies. In particular, Computation-In-Memory (CiM) using emerging technologies such as Resistive Random Access Memory (ReRAM) is a promising approach to meet the computational demands of data-intensive applications such as neural networks and database queries. In CiM, computation is done in an analog manner; digitization of the results is costly in several aspects, such as area, energy, and performance, which hinders the potential of CiM. In this article, we propose an efficient Voltage-Controlled-Oscillator (VCO)–based analog-to-digital converter (ADC) design to improve the performance and energy efficiency of the CiM architecture. Due to its efficiency, the proposed ADC can be assigned in a per-column manner instead of sharing one ADC among multiple columns. This will boost the parallel execution and overall efficiency of the CiM crossbar array. The proposed ADC is evaluated using a Multiplication and Accumulation (MAC) operation implemented in ReRAM-based CiM crossbar arrays. Simulations results show that our proposed ADC can distinguish up to 32 levels within 10 ns while consuming less than 5.2 pJ of energy. In addition, our proposed ADC can tolerate ≈30% variability with a negligible impact on the performance of the ADC.

In recent years, we are witnessing a trend toward in-memory computing for future generations of computers that differs from traditional von-Neumann architecture in which there is a clear distinction between computing and memory units. Considering that data movements between the central processing unit (CPU) and memory consume several orders of magnitude more energy compared to simple arithmetic operations in the CPU, in-memory computing will lead to huge energy savings as data no longer needs to be moved around between these units. In an initial step toward this goal, new non-volatile memory technologies, e.g., resistive RAM (ReRAM) and phase-change memory (PCM), are being explored. This has led to a large body of research that mainly focuses on the design of the memory array and its peripheral circuitry. In this article, we mainly focus on the tile architecture (comprising a memory array and peripheral circuitry) in which storage and compute operations are performed in the (analog) memory array and the results are produced in the (digital) periphery. Such an architecture is termed compute-in-memory-periphery (CIM-P). More precisely, we derive an abstract CIM-tile architecture and define its main building blocks. To bridge the gap between higher-level programming languages and the underlying (analog) circuit designs, an instruction-set architecture is defined that is intended to control and, in turn, sequence the operations within this CIM tile to perform higher-level more complex operations. Moreover, we define a procedure to pipeline the CIM-tile operations to further improve the performance. To simulate the tile and perform design space exploration considering different technologies and parameters, we introduce the fully parameterized first-of-its-kind CIM tile simulator and compiler. Furthermore, the compiler is technology-aware when scheduling the CIM-tile instructions. Finally, using the simulator, we perform several preliminary design space explorations regarding the three competing technologies, ReRAM, PCM, and STT-MRAM concerning CIM-tile parameters, e.g., the number of ADCs. Additionally, we investigate the effect of pipelining in relation to the clock speeds of the digital periphery assuming the three technologies. In the end, we demonstrate that our simulator is also capable of reporting energy consumption for each building block within the CIM tile after the execution of in-memory kernels considering the data-dependency on the energy consumption of the memory array. All the source codes are publicly available.

In the group of emerging non-volatile storage technologies, redox-based memristive devices stand out due to their possibility for extreme dense integration, low power consumption and multilevel capabilities. The opportunity to directly perform Boolean logic operations using memristive devices opens a promising path towards Computation-in-Memory. Recently 7- state memristive devices based on TaOx were used to realize a ternary adder circuit as well as a ternary Łukasiewicz logic and fuzzy logic. Logic that uses more than two truth values promises to reduce the number of devices that are needed for a certain operation and thereby further increases the integration density. In this work, we propose a multinary logic for three, five and seven truth values based on the Łukasiewicz logic and show the performance for the implication and negation operation. We, therefore, used the physics-based compact model JART VCM v1b to describe the relation between RESET voltage and high resistive state and then performed the logic operations.