Uday Kurkure

Uday Kurkure works on accelerators for machine learning at VMware. He has a very broad skill set ranging from writing compilers, designing ASICS/FPGAs for computer graphics, and working on reconfigurable computing to virtualizing systems with VMware products. His current interests are machine learning (ML) and high performance computing (HPC). VMware awarded him the most prolific inventor award twice: he has 25 granted patents and 14 pending patent applications. He has published 13 research papers. His educational background includes an MS degree in Computer Science from Stanford and a B Tech in Electronics and Telecommunications from the Indian Institute of Technology. Before VMware, he worked for Synopsys, Adobe Systems, Transmeta, and MIPS Computers.

Author's Posts

Machine Learning

No Virtualization Tax for MLPerf Inference v3.0 Using NVIDIA Hopper and Ampere vGPUs and NVIDIA AI Software with vSphere 8.0.1

In this blog, we show the MLPerf Inference v3.0 test results for the VMware vSphere virtualization platform with NVIDIA H100 and A100-based vGPUs. Our tests show that when NVIDIA vGPUs are used in vSphere, the workload performance is the same as or better than it is when run on a bare metal system.