Max Systems Lab
Building ML-driven systems for architecture simulation, HPC, and co-design.
Santosh Pandey Lab
ML-driven systems research for computer architecture and HPC.
Our lab develops machine-learning methods that make architecture and systems research faster, more scalable, and more predictive. We focus on replacing expensive simulation workflows with accurate learned surrogates and intelligent data-generation strategies.
We work across the stack: microarchitecture simulation, GPU design-space exploration, LLM/HPC performance analysis, and automated hardware-software optimization.
Actively recruiting fully funded PhD students interested in ML systems, architecture simulation, and HPC.
ML for Architecture Simulation
Accurate and reusable learning-based simulation approaches for modern CPU/GPU systems.
Systems for ML/HPC
Optimized runtime and hardware-software strategies for scaling ML and HPC applications.
Automated Stack Optimization
Generative and predictive modeling for program, compiler, and architecture co-optimization.
news
| May 15, 2025 | Pricipal Investigator Santosh Pandey awarded Rutgers ECE Graduate Leadership and Service Award. |
|---|---|
| Mar 21, 2025 | One paper Concorde: Fast and Accurate CPU Performance Modeling with Compositional Analytical-ML Fusion, led by Arash, accepted at ISCA’25. A great collaborative work during my time at Google.  |