Interests

AI accelerators, AI accelerators simulator, AI Compilers, Memory Systems, Computer Architecture, Operating systems, Low-Level Systems, GPU Computing.

Education

• Ph.D. in Graduate School of Artificial Intelligence  (Sep. 2024 – Present)

Pohang University of Science and Technology (POSTECH)

Research Area: AI Accelerator Architectures and AI Compilers

Advisor: Prof. Gwangsun Kim.

• M.S. in Computer Science and Engineering  (Sep. 2022 – 2024)

Pohang University of Science and Technology (POSTECH)

Thesis: A Fast, Detailed Simulation Methodology for Designing AI Accelerators.

Advisor: Prof. Gwangsun Kim.

• B.S. in Technology Fusion Engineering  (Feb. 2015 – 2020)

Double major: Computer Science and Engineering

Konkuk University

Teaching Experience

Fall 2024: Teaching Assistant for GPU and Accelerated Computing (CSED405-01) @ POSTECH

Fall 2022: Teaching Assistant for Parallel Computer Architecture&Programming (CSED490V-01) @ POSTECH

Spring 2018: Teaching Assistant for Numerical Analysis @ Konkuk University

Awards and Honors

• Encouragement Award for Konkuk University 2019 SW Competition (Sep. 2019)

Project: "Effective Scheduling of I/O-bound Processes"

• Scholarship for Academic Excellence. (Sep. 2015 − 2018)

Konkuk University

Publications

(*: co-first authors)

1. Wonhyuk Yang*, Yunseon Shin*, Okkyun Woo*, Geonwoo Park, Hyungkyu Ham, Jeehoon Kang, Jongse Park, Gwangsun Kim, "PyTorchSim: A Comprehensive, Fast, and Accurate NPU Simulation Framework" In Proceedings of the 58th IEEE/ACM International Symposium on Microarchitecture (MICRO), October 2025. Acceptance rate: 20.8%.

2. Hyungkyu Ham*, Jeongmin Hong*, Geonwoo Park, Yunseon Shin, Okkyun Woo, Wonhyuk Yang, Jinhoon Bae, Eunhyeok Park, Hyojin Sung, Euicheol Lim, and Gwangsun Kim, “Low-overhead General-purpose Near-Data Processing in CXL Memory Expanders.” In Proceedings of the 57th IEEE/ACM International Symposium on Microarchitecture (MICRO), November 2024. Acceptance rate: 22.7%.

3. Hyungkyu Ham*, Wonhyuk Yang*, Yunseon Shin, Okkyun Woo, Guseul Heo, Sangyeop Lee, Jongse Park, Gwangsun Kim, "ONNXim: A Fast, Cycle-level Multi-core NPU Simulator" IEEE Computer Architecture Letters, vol. 23, no. 2, pp. 219-222, July-Dec. 2024.

4. Jeongmin Hong, Sungjun Cho, Geonwoo Park, Wonhyuk Yang, Young-Ho Gong, and Gwangsun Kim,“Bandwidth-Effective DRAM Cache for GPUs with Storage-Class Memory.” In Proceedings of the 30th International Symposium on High-Performance Computer Architecture (HPCA), March 2024. Acceptance rate: 18.3%.

5. Wonhyuk Yang, Yunseon Shin, Okkyun Woo, Geonwoo Park, Hyungkyu Ham, Gwangsun Kim "Compiler-integrated,High-speed Simulation Methodology for Designing AI Accelerators.” In Proceedings of the Korea Computer Congress (KCC), June 2024.

6. Baik Song An, Myung Hoon Cha, Sang-Min Lee, Wonhyuk Yang, Hong Yeon Kim "Providing scalable single-operating-system NUMA abstraction of physically discrete resources" ETRI Journal, vol. 46, no. 3, pp. 501-512, July, 2024.

Open Source Contribution

1. PyTorchSim (Link)

   • Led the development of and currently maintain PyTorchSim, a comprehensive, fast, and accurate NPU simulation framework (MICRO’25).

2. GPGPU-Sim Project (Link)

   • Fixed a shader instruction dependency bug by restoring missing logic.

   • Pull request: accel-sim/gpgpu-sim_distribution/pull/72

3. ONNXim (Link)

   • Co-developed and currently maintain ONNXim, which provides a high-speed, cycle-level simulator for multi-core NPUs (CAL’24).

4. Linux Kernel Project (Link)

   • Contributed bug fixes, minor performance improvements, and refactoring across kernel subsystems like Per-CPU, Memory (Memblock, Compaction), and Trace.

   • Patchset: linux.git(author=Wonhyuk Yang)