Welcome to the Computer Systems Integration (CompSi) Lab at the Elmore Family School of Electrical and Computer Engineering, Purdue University. Under the direction of Dr. Vikram Jain, our lab conducts cutting-edge research at the intersection of computer architecture, integrated circuits, and machine learning. Our mission is to design the next generation of energy-efficient, high-performance computing systems that will power the future of artificial intelligence.
OUR RESEARCH FOCUS
At the CompSI Lab, we address the critical challenges of modern computing by co-designing hardware and software. Our primary research areas include:
- AI Accelerators and Compute-in-Memory: We design custom hardware architectures optimized for machine learning workloads, including compute-in-memory (CIM) designs that reduce data-movement bottlenecks.
- Heterogeneous Integration and Chiplet Architectures: We explore innovative 2.5D and 3D chiplet-based system integration to build scalable, modular, and high-performance computing platforms.
- Hardware-Software Co-Design: We bridge the gap between algorithms and silicon, optimizing system performance from high-level software frameworks down to the physical transistor level.
- Energy-Efficient Edge Intelligence: We build low-power digital accelerators and RISC-V processor architectures to enable intelligent decision-making directly on edge devices.
OUR VISION
The CompSi Lab is committed to fostering a collaborative and highly innovative environment. We prepare students and researchers to tackle real-world engineering problems through hands-on chip design, hardware-software co-design, system simulation and emulation, and physical tapeouts. By bridging industry-grade engineering with academic rigor, we aim to lead the future of silicon and system integration.