MKMinsuk Koo

Minsuk Koo

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Minsuk Koo has a total of 59 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Voltage-Summation-Based Compute-in-Memory SRAM Macro With Input-Bit and Synaptic-Bit Slicing

    by Jung Nam Kim, Yong Woo Kim, Won Joo Lee, Minsuk Koo, Yoon Kim

    Compute-in-memory (CIM) technology has emerged as a promising solution for energy-efficient matrix-vector multiplication (MVM), addressing the inherent limitations of von Neumann architecture. However, conventional Kirchhoff’s current law based CIM technologies suffer from drawbacks such as I-R drop and energy inefficiency due to static current flow over a wide dynamic range. This paper introduces an energy-efficient and I-R drop-free CIM architecture based on capacitive coupling principle. Synaptic weights represented in 4-bit two’s complement format are stored in SRAM-based 9T1C bit-cells. The architecture utilizes input-bit slicing method to perform MVM operations without the need for multi-bit digital-to-analog converters (DACs), significantly improving energy efficiency. A neuron circuit employs successive integration and rescaling (SIR) process to handle input-bit slicing encoded analog MVM results efficiently. The fabricated 16 kb, 28-nm prototype chip achieves an energy efficiency of 230 TOPS/W and a throughput of 32.19 GOPS for MVM operation with 4-bit resolution input and synaptic weights at a 100 MHz clock frequency. Even with ADC-induced analog variability, the proposed architecture achieves 90.64% and 97.99% inference accuracy for single-layer and multi-layer networks on the MNIST dataset, and 86.25% on CIFAR-10, validating its effectiveness and practical viability for low-power edge inference in complex workloads.

  • Open Access

    ES-SNN: e-Flash Memory-Based Stochastic Spiking Neural Networks for Edge Inference

    by Hyeyeon Jeon, Jungnam Kim, Yoon Kim, Minsuk Koo

    In this work, we propose an e-Flash memory-based Stochastic Spiking Neural Network (ES-SNN), which integrates stochastic spiking neurons with e-Flash memory-based multi-level synapses for probabilistic computation. We design an energy-efficient, capacitor-less stochastic output neuron using a 28 nm CMOS process. The e-Flash-based non-volatile synapses achieve 3-bit weight storage per cell, enabling compact and energy-efficient inference. System level evaluation results demonstrate that the proposed ES-SNN achieves an energy efficiency of 608 Tera Operations per Second per Watt (TOPS/W) for a single-layer fully connected SNN, highlighting its potential for low-power neuromorphic computing applications.


  • Implementation of Boolean Logic Operation in Embedded Flash Memory for In-Memory Computing Applications

    by Jinhyeok Kim, Sung Jin Bang, Min Sung Kim, Minsuk Koo, Yoon Kim

    This article presents, for the first time, a sequential logic-in-memory technique using embedded flash (eFlash) memory to address the integration challenges of previous methods that relied on memristor devices. In this work, Boolean primitives are executed and retained as a nonvolatile cell state inside the eFlash array, while cascaded operations are performed through a system-level sequential execution. The incompatibility of memristor devices with standard CMOS logic processes has limited their practical integration. The proposed eFlash-based approach offers full compatibility with CMOS circuits, resulting in improved operating speed and reduced energy consumption. A test chip was designed and fabricated using a 180-nm low-power CMOS process, successfully demonstrating arbitrary Boolean logic operations on a fabricated embedded nor flash memory test chip.

  • Advancing phase-change random access memory: materials innovation neuromorphic applications, and scalability challenges

    by Seoyoung Park, Minsuk Koo, Sungjun Kim

    Phase-change random access memory (PRAM) is an emerging high-speed, non-volatile memory technology that leverages the reversible phase transitions of chalcogenide materials such as Ge–Sb–Te to enable efficient data storage and retrieval. This paper provides a comprehensive analysis of PRAM’s core operational mechanisms, including rapid switching speeds, high endurance, and multilevel storage enabled through precise control of phase transitions. Recent advancements in materials engineering, such as nitrogen and carbon doping, superlattice-like structures, and thermoelectric effect integration, are explored for their contributions to improving thermal stability, endurance, and energy efficiency. Beyond traditional memory applications, PRAM’s unique ability to achieve tunable resistance states makes it a promising candidate for neuromorphic computing. The paper discusses PRAM’s role in emulating biological synaptic functions, such as synaptic weight modulation, spike-timing-dependent plasticity, and long-term potentiation/depression, enabling efficient learning and inference in artificial neural networks. The integration of PRAM into crossbar arrays and multi-memristive synapses is examined to develop scalable and energy-efficient neural network architectures for artificial intelligence applications. Key challenges, including sneak current phenomena, endurance degradation over repeated switching cycles, and power consumption in large-scale PRAM arrays, are critically analyzed. Potential solutions, such as selector devices, voltage scaling techniques, advanced thermal management strategies, and processing-in-memory architectures, are evaluated to address these issues. These advancements position PRAM as a pivotal technology for next-generation memory and neuromorphic computing, offering scalable, energy-efficient solutions for future high-performance and artificial intelligence-driven applications.


  • Enhancing non-volatile memory and neuromorphic computing: integration of PRAM and OTS for scalable, energy-efficient architectures

    by Seoyoung Park, Minsuk Koo, Sungjun Kim

    This paper investigates the integration of Phase-Change Random Access Memory (PRAM) and Ovonic Threshold Switch (OTS) devices, emphasizing their ability to advance non-volatile memory (NVM) technologies, neuromorphic computing architectures, and energy-efficient systems. OTS devices' nonlinear threshold switching effectively mitigates sneak currents in high-density crossbar arrays, while challenges like resistivity drift and structural relaxation are addressed through advanced modeling and experimental analysis. The study highlights innovations in phase-change materials, such as oxygen-doped Sb₂Te₃ and Sb₂Te₃-GeTe superlattices and leverages Atomic Layer Deposition (ALD) to enhance thermal stability, switching speed, and cycling endurance. PRAM-OTS hybrid systems demonstrate exceptional performance in spiking and multi-layer neural networks, replicating neuronal behaviors such as integrate-and-fire dynamics and spike-timing-dependent plasticity for low-latency, energy-efficient processing in artificial intelligence, robotics, and IoT applications. These scalable and reliable systems provide a robust framework for next-generation high-performance computational platforms, addressing key challenges in scalability, energy efficiency, and operational longevity.

  • Open Access

    A Fully Integrated Analog Processing‐in‐Memory System Based on Charge‐Trap Flash Synapse Arrays and Successive Integration‐and‐Rescaling Neurons

    by Sojoong Kim, Yeonwoo Kim, Woo Young Choi, Minsuk Koo, Yoon Kim

    The increasing demands of data‐centric applications continue to expose the fundamental bandwidth bottleneck of the von Neumann architecture, where memory and computation are separated. Analog processing‐in‐memory (PIM) offers a promising pathway to overcome this limitation, and charge‐trap flash (CTF) synapses stand out as attractive candidates owing to their scalability, multilevel storage, and complementary metal‐oxide‐semiconductor (CMOS) compatibility. In this work, a hardware‐level analog PIM system is presented that integrates CTF synapse arrays, CMOS‐based wordline drivers, and a novel successive integration‐and‐rescaling (SIR) neuron circuit in a chip‐on‐board configuration. Unlike conventional neuron designs that rely heavily on analog‐to‐digital conversion, the proposed SIR neuron performs bit‐sliced accumulation entirely in the analog domain. This architecture not only minimizes analog‐to‐digital converter overhead but also achieves excellent linearity through input‐node stabilization and functional capacitor separation, thereby enhancing both computational accuracy and area efficiency. The fabricated system is validated through handwritten digit classification on the modified national institute of standards and technology dataset, achieving an accuracy of 72.93%, which is only 3.91 percentage points lower than the software baseline under identical precision. These results underscore the pivotal role of the SIR neuron in bridging device‐level innovations with system‐level integration, positioning CTF‐based analog PIM as a scalable and energy‐efficient platform for neuromorphic computing.

  • Open Access

    Voltage‐Summation‐Based Compute‐in‐Memory Technology with Capacitive Synaptic Devices

    by Jung Nam Kim, Yong Woo Kim, Boram Kim, Doo‐Hyun Kim, Gil Sung Lee, Dong‐Hyuk Chae, Minkyu Je, Minsuk Koo, Yoon Kim

    Previous compute‐in‐memory (CIM) technologies use current summation for executing matrix–vector multiplication (MVM) operations and are gaining attention as next‐generation artificial intelligence (AI) computing systems. Despite their advantages, these technologies encounter significant difficulties, such as managing wide current ranges in large arrays, overcoming substantial “IR (current‐resistance)‐drop” issues, and integrating with complementary metal–oxide–semiconductor operating circuits. Herein, an innovative voltage‐summation‐based CIM (V‐CIM) technology is introduced; this technology represents a paradigm shift that employs capacitive coupling at a floating voltage summation node for MVM operations. By using a differential pair of input voltages (|Δ V |) with opposite signs relative to the reference voltage, the accumulated MVM results at the floating summation node cancel out, eliminating IR‐drop. Representing the MVM result as an analog voltage simplifies the neuron circuit design and significantly reduces energy consumption. V‐CIM technology is reported with two types of capacitive synaptic devices: read‐only and programmable. A prototype V‐CIM chip using read‐only capacitors is developed, demonstrating the superiority of V‐CIM in image classification applications. For programmable capacitive synaptic devices, a memcapacitor device based on logic‐compatible embedded flash memory is introduced. The work sheds light on ultralow‐power, highly integrated, and highly reliable AI computing systems based on CIM technology.


  • Open Access

    Oxygen-Plasma-Treated Al/TaOX/Al Resistive Memory for Enhanced Synaptic Characteristics

    by Gyeongpyo Kim, Seoyoung Park, Minsuk Koo, Sungjun Kim

    In this study, we investigate the impact of O2 plasma treatment on the performance of Al/TaOX/Al-based resistive random-access memory (RRAM) devices, focusing on applications in neuromorphic systems. Comparative analysis using scanning electron microscopy and X-ray photoelectron spectroscopy confirmed the differences in chemical composition between O2-plasma-treated and untreated RRAM cells. Direct-current measurements showed that O2-plasma-treated RRAM cells exhibited significant improvements over untreated RRAM cells, including higher on/off ratios, improved uniformity and distribution, longer retention times, and enhanced durability. The conduction mechanism is investigated by current–voltage (I–V) curve fitting. In addition, paired-pulse facilitation (PPF) is observed using partial short-term memory. Furthermore, 3- and 4-bit weight tuning with auto-pulse-tuning algorithms was achieved to improve the controllability of the synapse weight for the neuromorphic system, maintaining retention times exceeding 103 s in the multiple states. Neuromorphic simulation with an MNIST dataset is conducted to evaluate the synaptic device.


  • HfAlOx-based ferroelectric memristor for nociceptor and synapse functions

    by Dongyeol Ju, Yongjin Park, Minseo Noh, Minsuk Koo, Sungjun Kim

    Efficient data processing is heavily reliant on prioritizing specific stimuli and categorizing incoming information. Within human biological systems, dorsal root ganglions (particularly nociceptors situated in the skin) perform a pivotal role in detecting external stimuli. These neurons send warnings to our brain, priming it to anticipate potential harm and prevent injury. In this study, we explore the potential of using a ferroelectric memristor device structured as a metal–ferroelectric–insulator–semiconductor as an artificial nociceptor. The aim of this device is to electrically receive external damage and interpret signals of danger. The TiN/HfAlOx (HAO)/HfSiOx (HSO)/n+ Si configuration of this device replicates the key functions of a biological nociceptor. The emulation includes crucial aspects, such as threshold reactivity, relaxation, no adaptation, and sensitization phenomena known as “allodynia” and “hyperalgesia.” Moreover, we propose establishing a connection between nociceptors and synapses by training the Hebbian learning rule. This involves exposing the device to injurious stimuli and using this experience to enhance its responsiveness, replicating synaptic plasticity.