HUSCARL

HUSCARL (Human-Centered System & Computer Architecture Lab), formerly known as the Scalable Architecture Lab, is a research lab in the Computer Science Department at William & Mary. HUSCARL is led by Dr. Yifan Sun. HUSCARL believes that computer systems and chips are designed by humans and for humans. HUSCARL bridges HCI and data visualization with chip design, building open-source simulators, visualization tools, and AI agents that help humans understand computer architectures and make architectures serve humans better.

Join HUSCARL

To become a Huscarl, you need to be able to drive your own research. Huscarls work with labmates and PIs as collaborators, shaping and leading their own research questions while seeking help from each other.

If you are interested in joining HUSCARL, either as a Ph.D. student, master's student, undergraduate researcher, or research intern, please fill out this form. Note that submitting the form does not replace the formal graduate or undergraduate program application through William & Mary.

Research Topics

Human-Centered Performance Analysis
Modern chips are too complex for designers to reason about from aggregate statistics. We build visualization tools and AI assistants, such as Daisen and DaisenBot, that show architects where time goes, why a bottleneck occurs, and what to change. We also study how experts actually perform performance analysis.
AI Agents for Computer Systems Research
AI agents can now write code, run experiments, and read results, but they still make mistakes that humans must catch. We design multi-agent systems, such as TheBotCompany, that develop and maintain research software, and we study how humans and agents can explore architecture designs together while humans stay able to verify the results.
Performance Modeling for Large-Scale AI Workloads
Cycle-level simulation cannot keep up with LLM training and inference that span thousands of GPUs. We develop lightweight, validated performance models, such as TrioSim, on top of our open-source Akita and MGPUSim frameworks, and we evaluate which modeling methods are accurate enough for which design questions.
Wafer-Scale and Multi-GPU Systems for AI
AI workloads are pushing GPUs beyond a single die, toward wafer-scale and multi-GPU systems where data movement dominates. We design address translation, memory, and interconnect techniques, including electro-photonic networks, that keep these systems efficient (e.g., HDPAT).

Sponsors

National Science Foundation logo
National Science Foundation
Advanced Micro Devices logo
Advanced Micro Devices
HUSCARL
Human-Centered System & Computer Architecture Lab
ISC 4 1365
540 Landrum Drive
Williamsburg, VA 23185
Resources
Branding
Website Designer
Yifan Sun