John Tran

John is a Director in the GPU Architecture group at NVIDIA. He joined NVIDIA in 2005, contributing to almost every major GPU architecture released since then. He spent a few years in NVIDIA Research, but is now back in the GPU Architecture team, leading several of NVIDIA’s Deep Learning architecture and software efforts. John completed his Master’s degree at the University of Virginia and undergraduate degree at Duke University.

Posts by John Tran

AI / Deep Learning

Tips for Optimizing GPU Performance Using Tensor Cores

Our most popular question is "What can I do to get great GPU performance for deep learning?" We’ve recently published a detailed Deep Learning Performance Guide… 13 MIN READ
Artificial Intelligence

CUTLASS: Fast Linear Algebra in CUDA C++

Update May 21, 2018: CUTLASS 1.0 is now available as Open Source software at the CUTLASS repository. CUTLASS 1.0 has changed substantially from our preview… 25 MIN READ