Area of research
Electrical and Electronic Engineering · Hardware and Architecture
Research interest
Research interests include Photonic and Optical Devices, Parallel Computing and Optimization Techniques, Optical Network Technologies, and Neural Networks and Reservoir Computing.
TrioSim: A Lightweight Simulator for Large-Scale DNN Workloads on Multi-GPU Systems
A blueprint for precise and fault-tolerant analog neural networks
Mirage: An RNS-Based Photonic Accelerator for DNN Training
FAB: An FPGA-based Accelerator for Bootstrappable Fully Homomorphic Encryption
An Electro-Photonic System for Accelerating Deep Neural Networks
GME: GPU-based Microarchitectural Extensions to Accelerate Homomorphic Encryption
MAD: Memory-Aware Design Techniques for Accelerating Fully Homomorphic Encryption
ProcessorFuzz: Processor Fuzzing with Control and Status Registers Guidance
RACE: RISC-V SoC for En/decryption Acceleration on the Edge for Homomorphic Computation
Network-on-Chip Microarchitecture-based Covert Channel in GPUs
Cross-Layer Co-Optimization of Network Design and Chiplet Placement in 2.5-D Systems
Profiling DNN Workloads on a Volta-based DGX-1 System
Leveraging thermally-aware chiplet organization in 2.5D systems to reclaim dark silicon
A cross-layer methodology for design and optimization of networks in 2.5D systems
Adaptive Tuning of Photonic Devices in a Photonic NoC Through Dynamic Workload Allocation
Energy-Efficient Adaptive Classifier Design for Mobile Systems
Asymmetric NoC Architectures for GPU Systems
Detecting hardware trojans using backside optical imaging of embedded watermarks
Managing Laser Power in Silicon-Photonic NoC Through Cache and NoC Reconfiguration
Thermal management of manycore systems with silicon-photonic networks
Sharing and placement of on-chip laser sources in silicon-photonic NoCs
Design and Optimization of Nonvolatile Multibit 1T1R Resistive RAM
Runtime Management of Laser Power in Silicon-Photonic Multibus NoC Architecture
Designing Chip-Level Nanophotonic Interconnection Networks
Collaborative Research: ASCENT: Heterogeneously Integrated Electronic Photonic AI Accelerators (HIEPAA)
I-Corps: Translation Potential of Practical Privacy-preserving Computing using Fully Homomorphic Encryption
Collaborative Research: CSR: Medium: Architecting GPUs for Practical Homomorphic Encryption-based Computing
SHF: Small: Architecting the COSMOS:A Combined System of Optical Phase Change Memory and Optical Links
CNS:CSR Collaborative Research: Leveraging Intra-chip/Inter-chip Silicon-Photonic Networks for Designing Next-Generation Accelerators
CAREER: System-level Run-time Management Techniques for Energy-efficient Silicon-Photonic Manycore Systems