Jeongeun Kim
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Jeongeun Kim has a total of 30 co-authors. Here are the top co-authors by number of shared publications:
- Seung Eun Lee
Seoul National University of Science and Technology
3 shared publications - Youngwoo Jeong
Department of Electronic Engineering, Seoul National University of Science and Technology, Seoul 01811, Republic of Korea
2 shared publications Bum-Seok Yoo
Samsung Electronics Co., Ltd
1 shared publication- Chenjie Weng
University of Southern California, Los Angeles, California, USA
1 shared publication - Christopher Torng
University of Southern California, Los Angeles, California, USA
1 shared publication - Do Young Choi
Department of Electronic Engineering, Seoul National University of Science and Technology, Seoul 01811, Korea
1 shared publication
Latest Publications
- Open Access
- 5 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-7
PowerFlow-DNN: Compiler-Directed Fine-Grained Power Orchestration for End-to-End Edge AI Inference
Edge AI systems operate under stringent energy and volume constraints, demanding extreme efficiency on limited battery capacity, with requirements worsening as intelligent capabilities advance. Prior work suggests fine-grained power orchestration through DVFS and power gating significantly improves efficiency critical to meeting such constraints, but introduces new challenges. We observe that layer-level approaches incur unintended overheads due to inter-layer coupling of power-control decisions, and jointly managing these mechanisms under limited voltage rails and transition overheads leads to a rapidly growing combinatorial schedule space. We propose PowerFlow-DNN, a compiler-directed framework for end-to-end power-state orchestration in ultra-low-power accelerators. By constructing a rigorous problem formulation for deadline-constrained, real-time, periodic inference as a unified inter-layer power-scheduling problem, our framework discovers energy-minimal power-state schedules while accounting for inter-layer impacts. We evaluate the framework on a DNN accelerator VLSI implementation in TSMC 40nm technology. Across representative edge networks, our approach discovers near-optimal solutions and achieves energy within 0.04% of the exact ILP oracle, reducing energy by up to 48% compared to an aggressive baseline without power orchestration, while reasoning over a combinatorial schedule space of over 10160 possible power-state assignments, yet operating on a structured layered state graph that enables efficient optimization, achieving up to 2.14× solver speedup via lightweight pruning.
- 5 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Open AccessPowerFlow-DNN: Compiler-Directed Fine-Grained Power Orchestration for End-to-End Edge AI Inference
Edge AI systems operate under stringent energy and volume constraints, demanding extreme efficiency on limited battery capacity, with requirements worsening as intelligent capabilities advance. Prior work suggests fine-grained power orchestration through DVFS and power gating significantly improves efficiency critical to meeting such constraints, but introduces new challenges. We observe that layer-level approaches incur unintended overheads due to inter-layer coupling of power-control decisions, and jointly managing these mechanisms under limited voltage rails and transition overheads leads to a rapidly growing combinatorial schedule space. We propose PowerFlow-DNN, a compiler-directed framework for end-to-end power-state orchestration in ultra-low-power accelerators. By constructing a rigorous problem formulation for deadline-constrained, real-time, periodic inference as a unified inter-layer power-scheduling problem, our framework discovers energy-minimal power-state schedules while accounting for inter-layer impacts. We evaluate the framework on a DNN accelerator VLSI implementation in TSMC 40nm technology. Across representative edge networks, our approach discovers near-optimal solutions and achieves energy within 0.04% of the exact ILP oracle, reducing energy by up to 48% compared to an aggressive baseline without power orchestration, while reasoning over a combinatorial schedule space of over 10160 possible power-state assignments, yet operating on a structured layered state graph that enables efficient optimization, achieving up to 2.14× solver speedup via lightweight pruning.
- Open Access
- 22 May 2024
- Published by MDPI AG in Electronics
- Vol. 13 (11) , 2024
Lightweight and Error-Tolerant Stereo Matching with a Stochastic Computing Processor
Stereo matching, utilized in diverse fields, poses a challenge to systems in resource-constrained environments due to the significant growth of computational load with image resolution. The challenge is crucial for the systems because fields utilizing stereo matching require short operational time for real-time applications and low power architecture. Stochastic computing (SC) is able to be a valuable approach to address the challenge by reducing the computational load by representing binary numbers with stochastic sequences, which are encoded as a probability value, and by leveraging the concept of mathematical probability. Also, it is possible for a system to be error-tolerant by utilizing the characteristics of stochastic computing. Therefore, in this paper, we propose an approach for lightweight and error-tolerant stereo matching with a hardware-implemented stochastic computing processor. To verify the feasibility and error tolerance of the proposed system, we implemented the proposed system and conducted experiments comparing depth maps with or without stochastic computing by calculating similarities. According to the experimental results, the proposed system indicated no significant differences in output depth maps and achieved an improvement in the depth maps from error-injected input images by an average of 58.95%. Therefore, we demonstrated that stereo matching with stochastic computing is feasible and error-tolerant.
- 22 May 2024
- Published by MDPI AG in Electronics
- Vol. 13 (11) , 2024
Open AccessLightweight and Error-Tolerant Stereo Matching with a Stochastic Computing Processor
Stereo matching, utilized in diverse fields, poses a challenge to systems in resource-constrained environments due to the significant growth of computational load with image resolution. The challenge is crucial for the systems because fields utilizing stereo matching require short operational time for real-time applications and low power architecture. Stochastic computing (SC) is able to be a valuable approach to address the challenge by reducing the computational load by representing binary numbers with stochastic sequences, which are encoded as a probability value, and by leveraging the concept of mathematical probability. Also, it is possible for a system to be error-tolerant by utilizing the characteristics of stochastic computing. Therefore, in this paper, we propose an approach for lightweight and error-tolerant stereo matching with a hardware-implemented stochastic computing processor. To verify the feasibility and error tolerance of the proposed system, we implemented the proposed system and conducted experiments comparing depth maps with or without stochastic computing by calculating similarities. According to the experimental results, the proposed system indicated no significant differences in output depth maps and achieved an improvement in the depth maps from error-injected input images by an average of 58.95%. Therefore, we demonstrated that stereo matching with stochastic computing is feasible and error-tolerant.
- Open Access
- 6 April 2023
- Published by MDPI AG in Electronics
- Vol. 12 (7) , 1749
Parallel Stochastic Computing Architecture for Computationally Intensive Applications
Stochastic computing requires random number generators to generate stochastic sequences that represent probability values. In the case of an 8-bit operation, a 256-bit length of a stochastic sequence is required, which results in latency issues. In this paper, a stochastic computing architecture is proposed to address the latency issue by employing parallel linear feedback shift registers (LFSRs). The proposed architecture reduces the latency in the stochastic sequence generation process without losing accuracy. In addition, the proposed architecture achieves area efficiency by reducing 69% of flip-flops and 70.4% of LUTs compared to architecture employing shared LFSRs, and 74% of flip-flops and 58% of LUTs compared to the architecture applying multiple LFSRs with the same computational time.
- 6 April 2023
- Published by MDPI AG in Electronics
- Vol. 12 (7) , 1749
Open AccessParallel Stochastic Computing Architecture for Computationally Intensive Applications
Stochastic computing requires random number generators to generate stochastic sequences that represent probability values. In the case of an 8-bit operation, a 256-bit length of a stochastic sequence is required, which results in latency issues. In this paper, a stochastic computing architecture is proposed to address the latency issue by employing parallel linear feedback shift registers (LFSRs). The proposed architecture reduces the latency in the stochastic sequence generation process without losing accuracy. In addition, the proposed architecture achieves area efficiency by reducing 69% of flip-flops and 70.4% of LUTs compared to architecture employing shared LFSRs, and 74% of flip-flops and 58% of LUTs compared to the architecture applying multiple LFSRs with the same computational time.
- Open Access
- 26 October 2021
- Published by MDPI AG in Micromachines
- Vol. 12 (11) , 1309
An FPGA-Based ECU for Remote Reconfiguration in Automotive Systems
Growing interest in intelligent vehicles is leading automotive systems to include numerous electronic control units (ECUs) inside. As a result, efficient implementation and management of automotive systems is gaining importance. Flexible updating and reconfiguration of ECUs is one appropriate strategy for these goals. Software updates to the ECUs are expected to improve performance and bug handling, but there are limitations due to the fixed hardware circuit. By applying hardware-reconfigurable ECUs to the automotive system, patches that are not able to be handled with only software updates are enabled. In this paper, a remotely hardware-reconfigurable ECU for automotive systems is proposed. The proposed ECU is implemented with a field programmable gate array (FPGA) and microcontroller unit (MCU) to support in-system reconfiguration (ISR). The communication interface between the FPGA and MCU employs Zipwire communication for high speed and resilient communication. For the Zipwire communication, a Zipwire controller is designed and implemented in the FPGA. The proposed hardware-reconfigurable ECU was successfully implemented, and feasibility was demonstrated.
- 26 October 2021
- Published by MDPI AG in Micromachines
- Vol. 12 (11) , 1309
Open AccessAn FPGA-Based ECU for Remote Reconfiguration in Automotive Systems
Growing interest in intelligent vehicles is leading automotive systems to include numerous electronic control units (ECUs) inside. As a result, efficient implementation and management of automotive systems is gaining importance. Flexible updating and reconfiguration of ECUs is one appropriate strategy for these goals. Software updates to the ECUs are expected to improve performance and bug handling, but there are limitations due to the fixed hardware circuit. By applying hardware-reconfigurable ECUs to the automotive system, patches that are not able to be handled with only software updates are enabled. In this paper, a remotely hardware-reconfigurable ECU for automotive systems is proposed. The proposed ECU is implemented with a field programmable gate array (FPGA) and microcontroller unit (MCU) to support in-system reconfiguration (ISR). The communication interface between the FPGA and MCU employs Zipwire communication for high speed and resilient communication. For the Zipwire communication, a Zipwire controller is designed and implemented in the FPGA. The proposed hardware-reconfigurable ECU was successfully implemented, and feasibility was demonstrated.
- Open Access
- 22 October 2006
- Published by Association for Computing Machinery (ACM)
- p. 235-240
Creation and utilization of a virtual platform for embedded software optimization:
Virtual platform (ViP), or ESL (electronic system level) simulation model, is one of the most widely renowned system level design techniques. In this paper, we present a case study of creating and applying the ViP in the development of a new hard disk system called hybrid-HDD that is one of the main features in the Windows VISTA (R). First, we summarize how we developed the ViP including the levels of timing accuracy of models, automatic generation of models from RTL code, external subsystem models, etc. Then, we explain how we exploited the ViP in software optimization. Compared with the conventional flow of software development, e. g. based on the real board, the ViP gives a better profiling capability thereby allowing designers to find more chances of code optimization. Based on the simulation and analysis with the ViP, the software optimization could improve system performance by more than 50%. However, in our case study, we found that the current ViP technique needs further improvements to become a true ESL design technique.
- 22 October 2006
- Published by Association for Computing Machinery (ACM)
- p. 235-240
Open AccessCreation and utilization of a virtual platform for embedded software optimization:
Virtual platform (ViP), or ESL (electronic system level) simulation model, is one of the most widely renowned system level design techniques. In this paper, we present a case study of creating and applying the ViP in the development of a new hard disk system called hybrid-HDD that is one of the main features in the Windows VISTA (R). First, we summarize how we developed the ViP including the levels of timing accuracy of models, automatic generation of models from RTL code, external subsystem models, etc. Then, we explain how we exploited the ViP in software optimization. Compared with the conventional flow of software development, e. g. based on the real board, the ViP gives a better profiling capability thereby allowing designers to find more chances of code optimization. Based on the simulation and analysis with the ViP, the software optimization could improve system performance by more than 50%. However, in our case study, we found that the current ViP technique needs further improvements to become a true ESL design technique.