Sanmukh R. Kuppannagari

Sanmukh Kuppannagari

Sanmukh R. Kuppannagari

James C. Wyant Assistant Professor
Computer and Data Sciences
Case Western Reserve University
Nord 100, 2095 Martin Luther King Jr Drive, Cleveland, OH - 44106
Telephone: +1 (213) 280-6229
Email: sanmukh.kuppannagari@case.edu
CV · Google Scholar Profile · LinkedIn Profile
Github Profile·

I am looking for motivated undergraduate, masters, and PhD students to join my research group starting Fall 2022. My research primarily focuses on Algorithmic Innovations for Accelerating AI/ML Workloads targeting CPUs, GPUs, and FPGAs. If you are interested, please send me an email with your resume and (unofficial) transcript.

News

July 2022	Our paper "Behind-the-Meter Solar Generation Disaggregation at Varying Aggregation Levels Using Consumer Mixture Models" has been accepted for publication in the IEEE Transactions on Sustainable Computing, 2022.
April 2022	Our paper "Safe Building HVAC Control via Batch Reinforcement Learning" has been accepted for publication in the IEEE Transactions on Sustainable Computing, 2022.
March 2022	Our paper "FPGA Accelerator for Homomorphic Encrypted Sparse Convolutional Neural Network Inference" has been accepted for publication in the proceedings of the IEEE 30th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM), 2022.
March 2022	Our paper "NTTGen: a framework for generating low latency NTT implementations on FPGA" has been accepted for publication in the proceedings of the 19th ACM International Conference on Computing Frontiers (CF), 2022.
December 2021	Our paper "PPOAccel: A High-Throughput Acceleration Framework for Proximal Policy Optimization" has been accepted for publication in the proceedings of the IEEE Transactions on Parallel and Distributed Systems, 2021.
August 2021	Our paper "Efficient Neighbor-Sampling-based GNN Training on CPU-FPGA Heterogeneous Platform" received Outstanding Student Paper Award in the 2021 IEEE High Performance Extreme Computing Virtual Conference (HPEC), 2021.
May 2021	Our proposal "SaTC: CORE: Small: Accelerating Privacy Preserving Deep Learning for Real-time Secure Applications" has been funded by the U.S. National Science Foundation. PI: Viktor Prasanna. Co-PI: Sanmukh Kuppannagari.

Biography

I am an Assistant Professor at the Department of Computer and Data Sciences. I work on a diverse set of research areas which include accelerating AI algorithms on heterogeneous platforms (CPU-GPU, CPU-FPGA) and developing accelerators for Homomorphic Encryption based Deep Neural Networks. I received my PhD in Computer Engineering from the University of Southern California in August 2018.

Research Interests

Accelerating Privacy Preserving Machine Learning, Accelerating Deep Reinforcement Learning, Reconfigurable Computing, Parallel Computing, Combinatorial Optimization, Approximation Algorithms

Dissertation

The focus of my PhD dissertation was to develop polynomial runtime complexity approximation algorithms to perform cost optimal supply demand matching in smart grids targeting various objective functions and constraints such as cost minimization, fairness, network constraints etc. Using both theoretical analysis and practical evaluations, we showed that our supply demand matching algorithms provide solutions which are close to optimal in a small amount of time.

PhD Defense Slides

PhD Dissertation

PhD Defense Committee: Viktor K. Prasanna (chair), Mohammed Beshir, Shaddin Dughmi, Mihailo Jovanovic, Rajgopal Kannan