Rajeshwari Devaramani

Rajeshwari Devaramani is a solutions architect at NVIDIA as part of the company's new college grad program. She is working with the CUDA technical marketing engineering team. Rajeshwari holds a Master’s degree in computational science and engineering from the Georgia Institute of Technology. Her background includes GPU programming, high-performance computing, and deep learning.
Avatar photo

Posts by Rajeshwari Devaramani

Models / Libraries / Frameworks

Unlock GPU Performance: Global Memory Access in CUDA

Managing memory is one of the most important performance characteristics to consider when writing a GPU kernel.  This post walks you through the important... 15 MIN READ
GPU Pro Tip
Simulation / Modeling / Design

CUDA Pro Tip: Increase Performance with Vectorized Memory Access

Many CUDA kernels are bandwidth bound, and the increasing ratio of flops to bandwidth in new hardware results in more bandwidth bound kernels. This makes it... 6 MIN READ