Kyeongwon Lee
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Kyeongwon Lee has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Woojoo Lee
Chung-Ang University
10 shared publications - Jongin Choi
Chung-Ang University, Seoul, Republic of Korea
4 shared publications - Jae-Jin Lee
Electronics and Telecommunications Research Institute (ETRI)
3 shared publications - Jeongmin Jin
Chung-Ang University, Seoul, Republic of Korea
2 shared publications - Kangju Lee
Chung-Ang University
2 shared publications - Massoud Pedram
University of Southern California, USA
2 shared publications
Latest Publications
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 75 (11) , 3854-3868
Quantum at the Edge: Scalable Standalone FPGA Emulator for QAOA-Based Weighted-MaxCut
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 75 (11) , 3854-3868
Quantum at the Edge: Scalable Standalone FPGA Emulator for QAOA-Based Weighted-MaxCut
- Open Access
- 5 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-7
CMAX-CAMEL: A Coarse-to-Fine Adaptive, Memory-Efficient, and Low-Power Edge Processor for Contrast Maximization
Contrast maximization (CMAX) is a direct geometric framework for event-based motion estimation, but its iterative warp-and-accumulate pipeline incurs input-dependent computation and frequent memory accesses, limiting real-time, low-power edge deployment. We present CMAX-CAMEL, a coarse-to-fine adaptive, memory-efficient, low-power edge processor that combines runtime-adaptive execution with a memory-centric architecture. CMAX-CAMEL adapts coarse-to-fine execution to the observed event distribution, prioritizing accuracy-improving stages while suppressing low-value iterations and unnecessary transitions. Its banked parallel memory organization sustains real-time throughput, while subsampling-coupled accumulation reduces memory-access activity along the warp-and-accumulate dataflow. On a 200 MHz Virtex FPGA prototype, CMAX-CAMEL improves estimation accuracy by up to 19%, reduces latency by 53.3%, lowers effective memory accesses by 42%, and cuts total system energy by 52.2%, demonstrating an HW-SW co-designed edge processor for real-time, low-power event-based motion estimation.
- 5 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Open AccessCMAX-CAMEL: A Coarse-to-Fine Adaptive, Memory-Efficient, and Low-Power Edge Processor for Contrast Maximization
Contrast maximization (CMAX) is a direct geometric framework for event-based motion estimation, but its iterative warp-and-accumulate pipeline incurs input-dependent computation and frequent memory accesses, limiting real-time, low-power edge deployment. We present CMAX-CAMEL, a coarse-to-fine adaptive, memory-efficient, low-power edge processor that combines runtime-adaptive execution with a memory-centric architecture. CMAX-CAMEL adapts coarse-to-fine execution to the observed event distribution, prioritizing accuracy-improving stages while suppressing low-value iterations and unnecessary transitions. Its banked parallel memory organization sustains real-time throughput, while subsampling-coupled accumulation reduces memory-access activity along the warp-and-accumulate dataflow. On a 200 MHz Virtex FPGA prototype, CMAX-CAMEL improves estimation accuracy by up to 19%, reduces latency by 53.3%, lowers effective memory accesses by 42%, and cuts total system energy by 52.2%, demonstrating an HW-SW co-designed edge processor for real-time, low-power event-based motion estimation.
- Open Access
- 5 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-7
SA-Kura: An Energy-Efficient Systolic Array Accelerator for Locally-Coupled Kuramoto Drift in Diffusion Sampling
Diffusion inference remains costly for edge deployment, yet existing accelerators focus almost exclusively on score networks because standard drift is merely a trivial linear scaling. Kuramoto orientation diffusion replaces this drift with locally coupled phase interactions, improving sampling efficiency but introducing a new hardware bottleneck: a center-dependent nonlinear 5 × 5 stencil evaluated at every reverse step that maps poorly to conventional CNN accelerators and matrix-oriented engines. We present SA-Kura, to our knowledge the first digital systolic-array accelerator dedicated to locally coupled Kuramoto drift. By reformulating pairwise sinusoidal coupling into center-independent neighbor accumulation followed by a single center-dependent multiply-subtract, SA-Kura eliminates in-PE transcendental units and enables register-level-reuse systolic execution. Implemented in synthesizable RTL, integrated into a lightweight RISC-V-based SoC, prototyped on FPGA, and evaluated through 45 nm CMOS synthesis and power analysis, SA-Kura reduces drift-kernel latency and energy by 193× and 69.4× over same-SoC processor software, and is 6.57× faster with 46.0× lower energy per pixel than a Jetson Orin Nano CUDA implementation.
- 5 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Open AccessSA-Kura: An Energy-Efficient Systolic Array Accelerator for Locally-Coupled Kuramoto Drift in Diffusion Sampling
Diffusion inference remains costly for edge deployment, yet existing accelerators focus almost exclusively on score networks because standard drift is merely a trivial linear scaling. Kuramoto orientation diffusion replaces this drift with locally coupled phase interactions, improving sampling efficiency but introducing a new hardware bottleneck: a center-dependent nonlinear 5 × 5 stencil evaluated at every reverse step that maps poorly to conventional CNN accelerators and matrix-oriented engines. We present SA-Kura, to our knowledge the first digital systolic-array accelerator dedicated to locally coupled Kuramoto drift. By reformulating pairwise sinusoidal coupling into center-independent neighbor accumulation followed by a single center-dependent multiply-subtract, SA-Kura eliminates in-PE transcendental units and enables register-level-reuse systolic execution. Implemented in synthesizable RTL, integrated into a lightweight RISC-V-based SoC, prototyped on FPGA, and evaluated through 45 nm CMOS synthesis and power analysis, SA-Kura reduces drift-kernel latency and energy by 193× and 69.4× over same-SoC processor software, and is 6.57× faster with 46.0× lower energy per pixel than a Jetson Orin Nano CUDA implementation.
- Open Access
- 5 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-2
Demo Abstract: An Energy-Efficient Crossbar-Free Oscillatory Neural Network Accelerator for Near-Sensor Edge AI
- 5 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-2
Open AccessDemo Abstract: An Energy-Efficient Crossbar-Free Oscillatory Neural Network Accelerator for Near-Sensor Edge AI
- Open Access
- 6 August 2025
- Published by Springer Nature in Research Square
Precision-Aware Fixed-Point Emulation of Grover’s Algorithm: Asymptotic Error Bounds and Design Guidelines
We propose a rigorous precision-aware framework for fixed-point emulation of Grover’s quantum search algorithm, systematically analyzing how truncation errors propagate and accumulate through quantum gate operations. Although fixed-point arithmetic significantly reduces resource requirements in quantum computing emulators, limited fractional-bit precision introduces non-negligible numerical errors, adversely impacting algorithm accuracy. To address this, we introduce a simplified two-amplitude quantum state representation that captures Grover’s algorithmic structure across iterations. Leveraging this model, we analytically derive explicit asymptotic error bounds on the emulated measurement probability distribution, demonstrating that errors scale exponentially as O(2n−f ), where n is the number of qubits and f is fractional-bit precision. Extensive numerical simulations and practical experiments on an actual fixed-point quantum emulator validate our theoretical predictions, confirming the accuracy and robustness of our error analysis. Finally, we present a closed-form expression to determine the minimal fractional-bit precision needed to meet a specified accuracy threshold, providing concrete, actionable guidelines for designing resource-efficient quantum computing emulators.
- 6 August 2025
- Published by Springer Nature in Research Square
Open AccessPrecision-Aware Fixed-Point Emulation of Grover’s Algorithm: Asymptotic Error Bounds and Design Guidelines
We propose a rigorous precision-aware framework for fixed-point emulation of Grover’s quantum search algorithm, systematically analyzing how truncation errors propagate and accumulate through quantum gate operations. Although fixed-point arithmetic significantly reduces resource requirements in quantum computing emulators, limited fractional-bit precision introduces non-negligible numerical errors, adversely impacting algorithm accuracy. To address this, we introduce a simplified two-amplitude quantum state representation that captures Grover’s algorithmic structure across iterations. Leveraging this model, we analytically derive explicit asymptotic error bounds on the emulated measurement probability distribution, demonstrating that errors scale exponentially as O(2n−f ), where n is the number of qubits and f is fractional-bit precision. Extensive numerical simulations and practical experiments on an actual fixed-point quantum emulator validate our theoretical predictions, confirming the accuracy and robustness of our error analysis. Finally, we present a closed-form expression to determine the minimal fractional-bit precision needed to meet a specified accuracy threshold, providing concrete, actionable guidelines for designing resource-efficient quantum computing emulators.
- Open Access
- 30 September 2024
- Published by MDPI AG in Micromachines
- Vol. 15 (10) , 1222
Dynamic Performance and Power Optimization with Heterogeneous Processing-in-Memory for AI Applications on Edge Devices
The rapid advancement of artificial intelligence (AI) technology, combined with the widespread proliferation of Internet of Things (IoT) devices, has significantly expanded the scope of AI applications, from data centers to edge devices. Running AI applications on edge devices requires a careful balance between data processing performance and energy efficiency. This challenge becomes even more critical when the computational load of applications dynamically changes over time, making it difficult to maintain optimal performance and energy efficiency simultaneously. To address these challenges, we propose a novel processing-in-memory (PIM) technology that dynamically optimizes performance and power consumption in response to real-time workload variations in AI applications. Our proposed solution consists of a new PIM architecture and an operational algorithm designed to maximize its effectiveness. The PIM architecture follows a well-established structure known for effectively handling data-centric tasks in AI applications. However, unlike conventional designs, it features a heterogeneous configuration of high-performance PIM (HP-PIM) modules and low-power PIM (LP-PIM) modules. This enables the system to dynamically adjust data processing based on varying computational load, optimizing energy efficiency according to the application’s workload demands. In addition, we present a data placement optimization algorithm to fully leverage the potential of the heterogeneous PIM architecture. This algorithm predicts changes in application workloads and optimally allocates data to the HP-PIM and LP-PIM modules, improving energy efficiency. To validate and evaluate the proposed technology, we implemented the PIM architecture and developed an embedded processor that integrates this architecture. We performed FPGA prototyping of the processor, and functional verification was successfully completed. Experimental results from running applications with varying workload demands on the prototype PIM processor demonstrate that the proposed technology achieves up to 29.54% energy savings.
- 30 September 2024
- Published by MDPI AG in Micromachines
- Vol. 15 (10) , 1222
Open AccessDynamic Performance and Power Optimization with Heterogeneous Processing-in-Memory for AI Applications on Edge Devices
The rapid advancement of artificial intelligence (AI) technology, combined with the widespread proliferation of Internet of Things (IoT) devices, has significantly expanded the scope of AI applications, from data centers to edge devices. Running AI applications on edge devices requires a careful balance between data processing performance and energy efficiency. This challenge becomes even more critical when the computational load of applications dynamically changes over time, making it difficult to maintain optimal performance and energy efficiency simultaneously. To address these challenges, we propose a novel processing-in-memory (PIM) technology that dynamically optimizes performance and power consumption in response to real-time workload variations in AI applications. Our proposed solution consists of a new PIM architecture and an operational algorithm designed to maximize its effectiveness. The PIM architecture follows a well-established structure known for effectively handling data-centric tasks in AI applications. However, unlike conventional designs, it features a heterogeneous configuration of high-performance PIM (HP-PIM) modules and low-power PIM (LP-PIM) modules. This enables the system to dynamically adjust data processing based on varying computational load, optimizing energy efficiency according to the application’s workload demands. In addition, we present a data placement optimization algorithm to fully leverage the potential of the heterogeneous PIM architecture. This algorithm predicts changes in application workloads and optimally allocates data to the HP-PIM and LP-PIM modules, improving energy efficiency. To validate and evaluate the proposed technology, we implemented the PIM architecture and developed an embedded processor that integrates this architecture. We performed FPGA prototyping of the processor, and functional verification was successfully completed. Experimental results from running applications with varying workload demands on the prototype PIM processor demonstrate that the proposed technology achieves up to 29.54% energy savings.
- 23 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. PP (1) , 1
Radar-PIM: Developing IoT Processors Utilizing Processing-in-Memory Architecture for Ultra-Wideband Radar-Based Respiration Detection
The adoption of Ultra-Wideband (UWB) radar technology in IoT and healthcare applications for respiration detection is rapidly expanding, opening up a wide array of potential use cases. Despite its burgeoning utility, the integration of UWB radar-based respiration detection in IoT endnode devices faces significant challenges due to the memory-intensive nature of these tasks, which strain the capabilities of IoT processors. This paper introduces a streamlined UWB radar-based respiration detection application designed for operation on IoT processors, emphasizing that when executed on conventional IoT processors, the limited processing power still results in significant data loss, underscoring the need for enhanced processing solutions. To address these challenges, we propose the adoption of Processing-in-Memory (PIM) technology and unveil the novel Radar-PIM architecture. This architecture is meticulously engineered to boost the efficiency of respiration detection while ensuring seamless integration with existing embedded processor frameworks. The paper extensively describes the Radar-PIM architecture and its operational mechanisms. We further demonstrate its superior performance by implementing and empirically testing a Radar-PIM processor prototype. Next, we present an optimization strategy tailored for designing energy-efficient Radar-PIM processors, specifically adapted for diverse UWB radar-based respiration detection applications. For instance, a Radar-PIM processor prototype, optimized for a particular application, achieved approximately 42% energy savings compared to its unoptimized counterpart and delivered performance nearly three times greater than that of a multicore processor with equivalent power consumption. This demonstrates the transformative potential of our proposed solution in enhancing the capabilities of radar-based respiration detection systems for IoT endnodes.
- 23 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. PP (1) , 1
Radar-PIM: Developing IoT Processors Utilizing Processing-in-Memory Architecture for Ultra-Wideband Radar-Based Respiration Detection
The adoption of Ultra-Wideband (UWB) radar technology in IoT and healthcare applications for respiration detection is rapidly expanding, opening up a wide array of potential use cases. Despite its burgeoning utility, the integration of UWB radar-based respiration detection in IoT endnode devices faces significant challenges due to the memory-intensive nature of these tasks, which strain the capabilities of IoT processors. This paper introduces a streamlined UWB radar-based respiration detection application designed for operation on IoT processors, emphasizing that when executed on conventional IoT processors, the limited processing power still results in significant data loss, underscoring the need for enhanced processing solutions. To address these challenges, we propose the adoption of Processing-in-Memory (PIM) technology and unveil the novel Radar-PIM architecture. This architecture is meticulously engineered to boost the efficiency of respiration detection while ensuring seamless integration with existing embedded processor frameworks. The paper extensively describes the Radar-PIM architecture and its operational mechanisms. We further demonstrate its superior performance by implementing and empirically testing a Radar-PIM processor prototype. Next, we present an optimization strategy tailored for designing energy-efficient Radar-PIM processors, specifically adapted for diverse UWB radar-based respiration detection applications. For instance, a Radar-PIM processor prototype, optimized for a particular application, achieved approximately 42% energy savings compared to its unoptimized counterpart and delivered performance nearly three times greater than that of a multicore processor with equivalent power consumption. This demonstrates the transformative potential of our proposed solution in enhancing the capabilities of radar-based respiration detection systems for IoT endnodes.
- 18 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems I: Regular Papers
- Vol. 71 (9) , 4106-4119
Designing Low-Power RISC-V Multicore Processors With a Shared Lightweight Floating Point Unit for IoT Endnodes
The increasing interest in RISC-V from both academia and industry has motivated the development and release of a number of free, open-source cores based on the RISC-V instruction set architecture. Specifically, the use of lightweight RISC-V cores in processors tailored for IoT endnode devices is on the rise. As the range and complexity of these applications grow, there is an increasing demand for multicore processors that can handle floating-point operations. This poses a significant challenge because most lightweight RISC-V cores are integer cores lacking a floating-point unit (FPU). This limitation makes it difficult to design processors optimized for applications that require floating-point operations concurrently with integer operations. While it is inefficient to have a dedicated FPU per core in a multicore processor (because it would give rise to unnecessary power consumption), it is crucial to find a solution that balances performance and energy efficiency. To address this challenge, we propose to utilize an external lightweight FPU that can be added to any RISC-V integer core, along with a low-power multicore architecture that shares the said FPU. We have applied this concept to design a RISC-V processor that integrates these technologies, implemented it on an FPGA device, and completed the fabrication of a System-on-Chip for functional verification. Our experiments, which involved testing various applications on different processor prototypes, demonstrated significant energy savings of up to 79.6% in a quad-core processor prototype, highlighting the potential energy efficiency of our proposed technology.
- 18 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems I: Regular Papers
- Vol. 71 (9) , 4106-4119
Designing Low-Power RISC-V Multicore Processors With a Shared Lightweight Floating Point Unit for IoT Endnodes
The increasing interest in RISC-V from both academia and industry has motivated the development and release of a number of free, open-source cores based on the RISC-V instruction set architecture. Specifically, the use of lightweight RISC-V cores in processors tailored for IoT endnode devices is on the rise. As the range and complexity of these applications grow, there is an increasing demand for multicore processors that can handle floating-point operations. This poses a significant challenge because most lightweight RISC-V cores are integer cores lacking a floating-point unit (FPU). This limitation makes it difficult to design processors optimized for applications that require floating-point operations concurrently with integer operations. While it is inefficient to have a dedicated FPU per core in a multicore processor (because it would give rise to unnecessary power consumption), it is crucial to find a solution that balances performance and energy efficiency. To address this challenge, we propose to utilize an external lightweight FPU that can be added to any RISC-V integer core, along with a low-power multicore architecture that shares the said FPU. We have applied this concept to design a RISC-V processor that integrates these technologies, implemented it on an FPGA device, and completed the fabrication of a System-on-Chip for functional verification. Our experiments, which involved testing various applications on different processor prototypes, demonstrated significant energy savings of up to 79.6% in a quad-core processor prototype, highlighting the potential energy efficiency of our proposed technology.