Venkata Krishnan
NVIDIA

PGH 232

Modern Graphics Processing Units (GPUs) have evolved into massively parallel processors, playing a pivotal role in accelerating high-performance computing, artificial intelligence, and graphics rendering. This talk describes the foundational architecture of NVIDIAs GPUs. It will also cover NVIDIA’s NVLink communication fabric features – one that enables efficient scaling of multi-GPU systems for large-scale computing and is a foundational technology in DGX systems.

Dr. Venkat Krishnan has over 25 years of system architecture expertise spanning processor architecture, networking, and accelerators. He holds a BTech from the Indian Institute of Technology (IIT) Madras and a PhD from University of Illinois at Urbana-Champaign – both degrees in Computer Science. He is currently a distinguished architect at Nvidia focusing on GPU scale-out architectures.