Vahid Geraeinejad

Vahid's research is focused at the intersection of computer architecture and high-performance computing, focusing on optimizing Graphics Processing Units (GPUs) for emerging AI and data-intensive applications. His work explores how to enhance the efficiency of both conventional workloads on CUDA cores and AI-specific workloads on Tensor Cores by improving computational utilization, memory hierarchies, and on-chip interconnection networks. By proposing new techniques to boost performance and energy efficiency across these components, he aims to accelerate different applications, enabling GPUs to better meet the growing demands of modern high-performance computing applications.