Probir Roy

Probir Roy is an Assistant Professor in the Department of Computer and Information Science at the University of Michigan-Dearborn, College of Engineering and Computer Science. His research focuses on developing practical program analysis tools to address performance bottlenecks and optimization opportunities in complex computational systems.

• Ph.D., College of William and Mary
• B.S., Bangladesh University of Engineering and Technology

Dr. Roy's work spans performance optimization, memory profiling, and cloud computing. He has contributed to NUMA-aware systems, serverless cold-start mitigation, and secure performance metrics for cache systems. His research emphasizes scalable tools for microservices and HPC applications.

Recent publications highlight trends in cloud computing, microservice optimization, and secure hardware design. Key subfields include profile-guided optimization, data transfer attribution, and empirical HPC bug analysis.

Scientific recognition includes:

• NSF Research Grant (2020)
• NSF and ACM-SIGPLAN Student Travel Grants (2018, 2016)
• WM GSA Conference Travel Grant (2017)

Dr. Roy mentors students in system research, with advisees contributing to serverless architecture, performance commit mining, and NUMA-aware deep learning. He has secured NSF funding for projects like 'EduPerf' and 'Towards Efficient Cloud Services', and collaborates on tools like MicroProf for code-level profiling.