Career Profile
I am a Ph.D. student at Yonsei University, Korea, studying computer architecture (advisor: Won Woo Ro). My research primarily focuses on enhancing the performance and energy efficiency of parallel processing units (e.g., GPUs and Domain-Specific Accelerators) by innovating their computing models. I believe such devices can help humanity expand its full capabilities, but it requires making their computing model more intelligent. Driven by this vision, I am enthusiastic about dedicating my talents and passion to empowering humanity to be more creative, intelligent, efficient, and fulfilled.
I am seeking a job/postdoctoral program in the United States with visa support (my expected graduation date is Aug 2024)
Education
Publications
MAD MAcce: Supporting Multiply-Add Operations for Democratizing Matrix-Multiplication Accelerators
The 56th International Symposium on Microarchitecture (MICRO 2023)
TensorCV: Accelerating Inference-Adjacent Computation Using Tensor Processors
The 2023 International Symposium on Low Power Electronics and Design (ISLPED’23)
R2D2: Removing ReDunDancy Utilizing Linearity of Address Generation in GPUs
The 50th International Symposium on Computer Architecture (ISCA 2023)
Investigation on NVIDIA Ampere GPU Architecture With Reverse Engineering
The 22th International Conference on Electronics, Information, and Communication (ICEIC 2023)
Detecting Pattern of Warp Register Value Differences in CTA using GPU Compiler
The 19th International Conference on Electronics, Information, and Communication (ICEIC 2020)
Hardware Accelerator Systems for Artificial Intelligence and Machine Learning
Advances in Computers, Elsvier, vol. 122: Academic Press; 2020, Chapter 6
Trends of High-End Graphic Processing Unit Development
Korean Information Science Society (2019)
---
Optimizing Quantum Program (QAOA)
Designing Sparse/Dense NPU
Democratizing Tensor Cores more
Optimizing General Quantum Program
Handling Outlier in AI/ML Applications
Proposing Datacenter GPU Management Strategy
Designing Low-Bitwidth-based NPU
Extending Ray Tracing Cores
Extending Matrix Multiplication Units
Professional Experiences
Industry Projects
Development of Data Center Many-core NPU Architecture and Memory Interface
- Samsung, 2019-2020
- Samsung, 2019-2020
Development of CPU-GPU Heterogeneous Computing Simulation Environment
- SK Hynix, 2019-2020
- SK Hynix, 2019-2020
Development of the Identification Data Processing Technology for On-site Police Officers
- Korea National Police Agency, 2018-2023
- Korea National Police Agency, 2018-2023
Development of Multi-GPU Based High Speed Ray-Tracing Engine
- Samsung, 2017-2018
- Samsung, 2017-2018
Skills & Proficiency
GPU Architecture
Accelerator Architecture
C/C++
Python
Verilog HDL
CUDA, cuBLAS, cuTlass, TensorRT, cuFFT, OpenCV, Vulkan, Optix, GPGPU-Sim, Accel-Sim, and Vulkan-Sim