Instructor: Jiarong Xing, Office: DCH 2099
Lectures: 3:00-4:15 pm, Friday
Location: DCH 1042
This graduate seminar explores the design and implementation of modern computer systems. We will read and discuss classic and contemporary research papers across various system topics, with an emphasis on critical analysis and in-class discussion.
Topics include (but are not limited to):
The class meets once per week. Each week, there will be a leader of the discussion who will present the paper and lead the discussion. The rest of the class will deeply engage in the discussion, asking questions, providing feedback, and sharing their own insights.
After each class, students will need to submit a summary of the discussion.
Depending on the registered students, we might invite external speakers to give talks on related topics.
There is no exam for this course.
Students with a documented disability needing academic adjustments or accommodations are encouraged to contact the instructor and Disability Support Services (Allen Center, Room 111).
| Date | Topic | Paper/Talk | Speaker |
|---|---|---|---|
| 1/16/2026 | Introduction | Course Logistics and New Trends in Computer Systems | Jiarong Xing |
| 1/23/2026 | GPU Sharing | Efficient Performance-Aware GPU Sharing with Compatibility and Isolation through Kernel Space Interception | Rixin Liu |
| 1/30/2026 | Prompt Evolution | GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning | Louie Lu |
| 2/6/2026 | Research methodology | You and your research | Jiarong Xing |
| SPRING RECESS (NO SCHEDULED CLASSES) | |||
| 2/20/2026 | GPU Sharing | MLaaS in the Wild: Workload Analysis and Scheduling in Large-Scale Heterogeneous GPU Clusters | Xingqi Cui |
| 2/27/2026 | LLM inference | MEDUSA: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads | Shen Zhang |
| 3/6/2026 | GPU OS | Motivation and The Future of GPU OS | Jiarong Xing |
| 3/13/2026 | MoE serving optimization | External lecture: Resource-Efficient MoE LLM Serving via Fine-Grained Expert Offloading | Hanfei Yu |
| SPRING BREAK (NO SCHEDULED CLASSES) | |||
| 3/27/2026 | LLM Routing | Lookahead Routing for Large Language Models | George Zhang |
| 4/3/2026 | ADRS | External lecture: AI-Driven Discovery: From Algorithm Generation to Self-Improving Research Loops | Shu Liu |
| 4/10/2026 | AI for kernel generation | External lecture: LEO: Cross-Vendor GPU Performance Root Cause Analysis and LLM-Guided Optimization | Yuning Xia |
| 4/17/2026 | AI training privacy | Keeping LLMs from Exposing Sensitive Data - A VaultGemma Case Study | Peter Pham |
| 4/24/2026 | AI training resiliency | Resilient Distributed Training under Failures: A ReCycle Case Study | ChaoHsuan Ho |