I am interested in research areas related to Programming Languages, GPU Architecture, and Multicore Architecture. Currently, I am working to resolve performance issues arising from data sharing across multiple GPUs.  My research interests lie in identifying and mitigating performance bottlenecks in parallel systems, including cache contention in CPU multithreaded applications, memory oversubscription in UVM-enabled GPU workloads, and data migration in multi-GPU systems. I have practical experience with cache coherence protocols, modeling and evaluating coherence mechanisms using SLICC in the Gem5 simulator. Additionally, I have experience using ANTLR to build migration and transformation tools, including parsing and translating legacy system languages into a newer technology stack. Further, I am interested in exploring the hardware-software co-design to identify the concurrency bugs in multithreaded programs.