Donghyuk Kim

Donghyuk Kim

Auto-generated profile, based on publicly available information

Donghyuk Kim

School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
17 March 2022 in IEEE Journal on Emerging and Selected Topics in Circuits and Systems
Verified
Journal Article
Open access
DKDonghyuk Kim
Donghyuk Kim
CYChengshuo Yu
Chengshuo Yu
SXShanshan Xie
Shanshan Xie
YCYuzong Chen
Yuzong Chen
Joo-Young KimJoo-Young Kim
Joo-Young Kim
KHKim Tae Hyoung
Kim Tae Hyoung
Artificial intelligence (AI) and machine learning (ML) are revolutionizing many fields of study, such as visual recognition, natural language processing, autonomous vehicles, and prediction. Traditional von-Neumann computing architecture with separated processing elements and memory devices have been improving their computing performances rapidly with the scaling of process technology. However, in the era of AI and ML, data transfer between memory devices and processing elements becomes the bottleneck of the system. To address this data movement issue, memory-centric computing takes an approach of merging the memory devices with processing elements so that computations can be done in the same location without moving any data. Processing-In-Memory (PIM) has attracted research community’s attention because it can improve the energy efficiency of memory-centric computing systems substantially by minimizing the data movement. Even though the benefits of PIM are well accepted, its limitations and challenges have not been investigated thoroughly. This paper presents a comprehensive investigation of state-of-the-art PIM research works based on various memory device types, such as static-random-access-memory (SRAM), dynamic-random-access-memory (DRAM), and resistive memory (ReRAM). We will present the overview of PIM designs in each memory type, covering from bit cells, circuits, and architecture. Then, a new software stack standard and its challenges for incorporating PIM with the conventional computing architecture will be discussed. Finally, we will discuss various future research directions in PIM for further reducing the data conversion overhead, improving test accuracy, and minimizing intra-memory data movement.

23 March 2023 in IEEE Transactions on Circuits and Systems I: Regular Papers
Verified
Journal Article
Closed access
DKDonghyuk Kim
Donghyuk Kim
SJSanghyun Jeong
Sanghyun Jeong
Joo-Young KimJoo-Young Kim
Joo-Young Kim
We propose a software/hardware co-design framework called Agamotto for the complete design automation and performance optimization of the row stationary-based CNN accelerator. We design a scalable accelerator template whose critical design parameters can be configured. Based on the hardware template, Agamotto estimates the performance of the numerous possible hardware implementations for the target FPGA device and CNN model using the latency modeling tool. It chooses the best hardware design and generates the instructions and optimal runtime variables for each target CNN layer. As a result, Agamotto can generate the best hardware design within 61.67 seconds, achieving up to 2.8x higher hardware utilization than the original accelerator. In addition, experimental results show that the performance estimation is accurate, showing only 4.8% difference against the FPGA runtime for the end-to-end CNN model execution. The accelerator implemented on the Xilinx VCU118 evaluation board achieves 402 giga operations per second (GOPS) at 200 MHz, resulting in 13 frames per second (FPS) for the end-to-end execution of VGG-16. It is flexible enough to run more complex CNN models such as ResNet-50 and DarkNet-53, achieving 29.3 FPS and 16.9 FPS, respectively.

4 June 2025 in IEEE Transactions on Computers
Verified
Journal Article
Closed access
WHWontak Han
Wontak Han
HCHyunjun Cho
Hyunjun Cho
DKDonghyuk Kim
Donghyuk Kim
Joo-Young KimJoo-Young Kim
Joo-Young Kim
Text generation is a compelling sub-field of natural language processing, aiming to generate human-readable text from input words. Although many deep learning models have been proposed, the recent emergence of transformer-based large language models advances its academic research and industry development, showing remarkable qualitative results in text generation. In particular, the decoder-only generative models, such as generative pre-trained transformer (GPT), are widely used for text generation, with two major computational stages: summarization and generation. Unlike the summarization stage, which can process the input tokens in parallel, the generation stage is difficult to accelerate due to its sequential generation of output tokens through iteration. Moreover, each iteration requires reading a whole model with little data reuse opportunity. Therefore, the workload of transformer-based text generation is severely memory-bound, making the external memory bandwidth system bottleneck. In this paper, we propose a subarray-level processing-in-memory (PIM) architecture named SAL-PIM, the first HBM-based PIM architecture for the end-to-end acceleration of transformer-based text generation. With optimized data mapping schemes for different operations, SAL-PIM utilizes higher internal bandwidth by integrating multiple subarray-level arithmetic logic units (S-ALUs) next to memory subarrays. To minimize the area overhead for S-ALU, it uses shared MACs leveraging slow clock frequency of commands for the same bank. In addition, a few subarrays in the bank are used as look-up tables (LUTs) to handle non-linear functions in PIM, supporting multiple addressing to select sections for linear interpolation. Lastly, the channel-level arithmetic logic unit (C-ALU) is added in the buffer die of HBM to perform the accumulation and reduce-sum operations of data across multiple banks, completing end-to-end inference on PIM. To validate the SAL-PIM architecture, we built a cycle-accurate simulator based on Ramulator. We also implemented the SAL-PIM’s logic units in 28-nm CMOS technology and scaled the results to DRAM technology to verify its feasibility. We measured the end-to-end latency of SAL-PIM when it runs various text generation workloads on the GPT-2 medium model (with 345 million parameters), in which the input and output token numbers vary from 32 to 128 and from 1 to 256, respectively. As a result, with 4.81% area overhead, SAL-PIM achieves up to 4.72× speedup (1.83× on average) over the Nvidia Titan RTX GPU running Faster Transformer Framework.

13 November 2024 in IEEE Transactions on Emerging Topics in Computing
Verified
Journal Article
Closed access
DKDonghyuk Kim
Donghyuk Kim
WHWontak Han
Wontak Han
JWJongsoon Won
Jongsoon Won
HCHaerang Choi
Haerang Choi
YKYongkee Kwon
Yongkee Kwon
Joo-Young KimJoo-Young Kim
Joo-Young Kim
We propose Darwin, a practical LRDIMM-based multi-level Processing-in-memory (PIM) architecture for data analytics, which exploits the internal bandwidth of DRAM using the bank-, bank group-, chip-, and rank-level parallelisms. Considering the properties of data analytics operators and DRAM's area constraints, Darwin maximizes the internal bandwidth by placing the PIM processing units, buffers, and control circuits across the hierarchy of DRAM. Darwin supports a novel PIM instruction architecture that concatenates instructions for multiple thread executions on bank group processing entities, addressing the command bottleneck by enabling separate control of up to 512 different in-memory processing units simultaneously. We build a cycle-accurate simulation framework to evaluate Darwin with various DRAM configurations, optimization schemes and workloads. Darwin achieves up to 14.7× speedup over the non-optimized version, leveraging many optimization schemes. Darwin architecture achieves 4.0×-43.9× higher throughput and reduces energy consumption by 85.7% than the baseline CPU system (Intel Xeon Gold 6226 + 4 channels of DDR4-2933) for essential data analytics operators. Compared to the state-of-the-art PIM, Darwin achieves up to 7.5× and 7.1× in the basic query operators and TPC-H queries, respectively. Darwin in GDDR6 configuration requires only 5.6% area overhead, suggesting a promising PIM solution for the future main memory system.

29 March 2022 in SAE International Journal of Advances and Current Practices in Mobility
Verified
Conference Paper
Closed access
Seunghyun KimSeunghyun Kim
Seunghyun Kim
JPJungwan Park
Jungwan Park
UBUntae Baek
Untae Baek
JNJanggeol Nam
Janggeol Nam
DKDonghyuk Kim
Donghyuk Kim
In the path following problem, a commercial vehicle has a delay of a hydraulic steering actuator and slow steering response accordingly. In addition, there are disturbances due to the harsh driving conditions of commercial vehicles. These disturbances may include uncertainties about actuator dynamic delay, modeling error and steering angle sensor offset. Designing a lateral controller with good performance that can overcome this problem is the key to successfully carrying out autonomous driving of commercial vehicles. Usually, it is difficult to consider disturbances with uncertainties in the geometric based control methods. Therefore, this paper proposed a lateral controller using feedback augmented disturbance observer for the commercial vehicle. First, a dynamics was modeled which can describe delay of the hydraulic actuator of the commercial vehicle. After that, a lateral controller was designed based on this dynamics model. The designed controller consists of three types of controllers such as feedforward control, curvature feedback control and disturbance observer. The feedforward controller has a form of conventional Pure Pursuit with additional differentiator controller. It has a role of lead compensator for the actuator delay. The feedback controller is designed to compensate turning radius error of the vehicle when the vehicle does not behave according to the kinematic model predicted. The disturbance observer has a role to compensate the steering wheel angle disturbance and modeling errors. The autonomous commercial vehicle experiments were conducted to evaluate proposed controller. The results confirmed that path following performance is much more improved when the lateral controller is designed considering the characteristics of commercial vehicles.

1 October 2025 in IEEE Journal of Solid-State Circuits
Verified
Journal Article
Closed access
DKDonghyuk Kim
Donghyuk Kim
JKJae-Young Kim
Jae-Young Kim
HCHyunjun Cho
Hyunjun Cho
SYSeungjae Yoo
Seungjae Yoo
SLSukjin Lee
Sukjin Lee
Joo-Young KimJoo-Young Kim
Joo-Young Kim
Transformer models have revolutionized artificial intelligence (AI) applications across various domains, but their increasing complexity poses significant challenges in terms of computational and memory demands. While processing-in-memory (PIM) paradigms have been adopted to address these limitations, existing PIM-based transformer accelerators still face hurdles such as: 1) focusing solely on optimizing attention layers; 2) lack of sparsity exploitation for transformers; and 3) limited PIM macro capacity and low cell density, which degrades on-chip data reuse and increases external memory access (EMA). This article presents DPIM, a novel 2T1C eDRAM-based transformer-in-memory chip that addresses these challenges through three key innovations: 1) a sparsity-aware quantization (SAQ) scheme that significantly increases bit-slice sparsity in both activation and weight data, achieving ratios of 83.3% and 88.4%, respectively, with minimal accuracy loss; 2) a heterogeneous PIM core capable of efficiently handling both sparse and dense matrix multiplications (MMs); and 3) a high-density 2T1C eDRAM cell with a density of 1.38 Mb/mm2, enabling large-capacity PIM macros. By integrating these features, DPIM achieves improved computational efficiency and reduced EMA with enhanced on-chip data reuse. The DPIM chip, fabricated using 28-nm CMOS technology, achieves a throughput of 3.03–12.12 TOPS and an energy efficiency of 4.84–19.36 TOPS/W, all measured across INT8 and INT4 operations, respectively. It achieves a throughput density of 0.55 TOPS/mm2 with INT8 operation. With a total macro size of 4608 kb, the chip occupies a die area of 20.25 mm2 and operates at frequencies from 50 to 285 MHz with a supply voltage of 0.85–1.0 V. The DPIM successfully executes BERT-Large on the general language understanding evaluation (GLUE) dataset. Its macro density is 1413 kb/mm2, and the resulting density figure-of-merit (FoM) (macro density $\times $ throughput density) is $1.6\times $ – $115.8\times $ higher than previous works, representing a significant advancement in hardware design for efficient transformer processing.