Chih-Chun Chang

Chih-Chun Chang

Ph.D. Candidate
Department of Electrical and Computer Engineering
University of Wisconsin–Madison

GPU Performance • Heterogeneous Computing • ML Compilers • High-Performance Computing

chang292 _at_ wisc _dot_ edu

About

I am a fourth-year Ph.D. candidate in the Department of Electrical and Computer Engineering at the University of Wisconsin–Madison, advised by Prof. Tsung-Wei (TW) Huang. I also received my M.S. in Electrical and Computer Engineering from UW–Madison.

My research focuses on GPU performance optimization, heterogeneous computing, ML compilers, and high-performance computing. I develop efficient GPU software for large-scale graph analytics and statistical static timing analysis, with an emphasis on CUDA, Triton, memory-aware scheduling, and GPU kernel optimization.

Through multiple internships at Cadence Design Systems, I developed GPU-accelerated timing analysis algorithms for industrial-scale electronic design automation (EDA). My long-term interests include GPU systems, machine learning infrastructure, compiler technologies, and high-performance computing.

Research Highlights

SSTA-X

Industrial timing analysis

CUDA • GPU scheduling • EDA

Accelerating statistical static timing analysis on GPUs for large-scale industrial EDA workloads.

GSAP

GPU graph analytics

ICPP 2024 • CUDA • HPC

GPU-accelerated stochastic graph partitioning for large-scale graph and timing-analysis workloads.

3× Cadence

Industry experience

2024 • 2025 • 2026

Multiple internships focused on GPU acceleration, performance optimization, and timing analysis.

Selected Projects

GPU-Accelerated SSTA

GPU-Accelerated SSTA

CUDA • GPU Scheduling • EDA

GPU acceleration for statistical static timing analysis with memory-aware scheduling for industrial-scale timing workloads.

GSAP

GSAP

CUDA • Graph Analytics • Parallel Algorithms

A GPU-accelerated stochastic graph partitioner for large-scale graph analytics and timing-analysis workloads.

uSAP

uSAP

Taskflow • Parallel Computing • Graph Algorithms

An ultra-fast stochastic graph partitioner based on task-parallel programming and high-performance computing techniques.

Selected Publications

View all publications

SSTA-X: GPU-Accelerated First-Order Block-Based Statistical Static Timing Analysis [paper]
Chih-Chun Chang, Yi-Hua Chung, Wan-Luan Lee, Boyang Zhang, and Tsung-Wei Huang
IEEE Transactions on Computer-aided Design of Integrated Circuits and Systems (TCAD), to appear, 2026

G-STAR: GPU-Accelerated Statistical Static Timing Analysis using Level-by-level Replication [paper]
Boyang Zhang, Chih-Chun Chang, Yi-Hua Chung, Che Chang, Cheng-Hsiang Chiu, Aditya Das Sarma, and Tsung-Wei Huang
International European Conference on Parallel and Distributed Computing (Euro-Par), Pisa, Italy, 2026

iHyperG: Incremental Hypergraph Partitioning on GPU [paper]
Wan-Luan Lee, Aditya Das Sarma, Che Chang, Chih-Chun Chang, and Tsung-Wei Huang
ACM/IEEE Design Automation Conference (DAC), Long Beach, CA, 2026

Optimizing CUDA Graph Scheduling with Reinforcement Learning: A Case Study in SSTA Propagation [paper]
Cheng-Hsiang Chiu, Chedi Morchdi, Chih-Chun Chang, Cunxi Yu, Yi Zhou, and Tsung-Wei Huang
ACM/IEEE International Symposium on Machine Learning for CAD (MLCAD), Santa Cruz, CA, 2025

Statistical Timing Graph Scheduling Algorithm for GPU Computation [paper] [project] [poster]
Chih-Chun Chang and Tsung-Wei Huang
ACM/IEEE Design Automation Conference Late-Breaking Result (DAC-LBR), San Francisco, CA, 2025

BQSim: GPU-accelerated Batch Quantum Circuit Simulation using Decision Diagram [paper] [project]
Shui Jiang, Yi-Hua Chung, Chih-Chun Chang, Tsung-Yi Ho, and Tsung-Wei Huang
ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS), Rotterdam, Netherlands, 2025

iTAP: An Incremental Task Graph Partitioner for Task-parallel Static Timing Analysis [paper] [project]
Boyang Zhang, Che Chang, Cheng-Hsiang Chiu, Dian-Lun Lin, Yang Sui, Chih-Chun Chang, Yi-Hua Chung, Wan-Luan Lee, Zizheng Guo, Yibo Lin, and Tsung-Wei Huang
IEEE/ACM Asia and South Pacific Design Automation Conference (ASP-DAC), Tokyo, Japan, 2025

GSAP: A GPU-Accelerated Stochastic Graph Partitioner [paper] [project]
Chih-Chun Chang, Boyang Zhang, and Tsung-Wei Huang
ACM International Conference on Parallel Processing (ICPP), Gotland, Sweden, 2024

G-PASTA: GPU-Accelerated Partitioning Algorithm for Static Timing Analysis [paper]
Boyang Zhang, Dian-Lun Lin, Che Chang, Cheng-Hsiang Chiu, Bojue Wang, Wan Luan Lee, Chih-Chun Chang, Donghao Fang, and Tsung-Wei Huang
ACM/IEEE Design Automation Conference (DAC), San Francisco, CA, 2024

uSAP: An Ultra-Fast Stochastic Graph Partitioner [paper] [project]
Chih-Chun Chang and Tsung-Wei Huang
IEEE High-performance and Extreme Computing Conference (HPEC), virtual, 2023

SoberMotion: Leveraging the Force of Probation Officers to Reduce the Risk of DUI Recidivism [Distinguished Paper Award] [paper]
Chuang-Wen You, Ya-Fang Lin, Yaliang Chuang, Ya-Han Lee, Pei-Yi Hsu, Shih-Yao Lin, Chih-Chun Chang, Yi-Ju Chung, Yi-Ling Chen, Ming-Chyi Huang, Ping-Hsuan Shen, Hsin-Tung Tseng, and Hao-Chuan Wang
ACM International Joint Conference on Pervasive and Ubiquitous Computing (ACM UbiComp), Singapore, 2018

A Mobile Support System to Assist DUI Offenders on Probation in Reducing DUI Relapse [paper]
Pei-Yi Hsu, Ya-Fang Lin, Jian-Lun Huang, Chih-Chun Chang, Shih-Yao Lin, Ya-Han Lee, Chuang-Wen You, Yaliang Chuang, Ming-Chyi Huang, Hsin-Tung Tseng, and Hao-Chuan Wang
ACM International Joint Conference on Pervasive and Ubiquitous Computing (ACM UbiComp), Hawaii, 2017

Industrial Experience

May 2026 – Aug. 2026

Graduate Intern

Cadence Design Systems, San Jose, CA, USA

GPU performance optimization for industrial-scale statistical static timing analysis.

GPU performance CUDA EDA SSTA

May 2025 – Aug. 2025

Graduate Intern

Cadence Design Systems, San Jose, CA, USA

GPU acceleration of statistical timing analysis using CUDA and Triton.

CUDA Triton GPU kernels Timing analysis

May 2024 – Dec. 2024

Graduate Intern

Cadence Design Systems, San Jose, CA, USA

Memory-aware scheduling for GPU-accelerated statistical static timing analysis.

Memory-aware scheduling GPU runtime CUDA EDA

June 2017 – Aug. 2018

Research Assistant

NTU IoX Center, Taipei, Taiwan

Jan. 2019 – July 2019

Software Intern

HOPE English, Taipei, Taiwan

Education

Sep. 2023 – Present (Expected Spring 2027)

Ph.D. in Electrical and Computer Engineering

University of Wisconsin–Madison, Madison, WI, USA

Advisor: Prof. Tsung-Wei (TW) Huang

Aug. 2023 - Aug. 2025

M.S. in Electrical and Computer Engineering

University of Wisconsin–Madison, Madison, WI, USA

Aug. 2019 – May 2022

M.S. in Computer Science

National Tsing Hua University, Hsinchu, Taiwan

Aug. 2013 – May 2017

B.S. in Electrical Engineering

National Tsing Hua University, Hsinchu, Taiwan

Skills

GPU Programming

CUDA Triton GPU kernel optimization Memory optimization Performance analysis

Parallel Computing

C++ Python OpenMP MPI Taskflow

Compiler / Runtime

Triton Torch Compile Runtime scheduling Code generation

Domains

Statistical timing analysis Graph partitioning EDA High-performance computing

Awards

IEEE HPEC Innovation Award

uSAP: An Ultra-Fast Stochastic Graph Partitioner, 2023

ACM UbiComp Distinguished Paper Award

SoberMotion, 2018

NVIDIA Smart Embedded Robotics Challenge Champion

2016