Mahesh Doijade

Mahesh Doijade is a compute developer technology engineer at NVIDIA. His work is focused on accelerating machine learning, deep learning workloads on GPU. He also contributes to GROMACS, an open-source molecular dynamics package, mainly focusing on its performance improvements on multi-node multi-GPU systems. In the past, he contributed apps that demonstrated best practices for the CUDA Toolkit.
Avatar photo

Posts by Mahesh Doijade

Data Science

Accelerated Vector Search: Approximating with NVIDIA cuVS Inverted Index

Performing an exhaustive exact k-nearest neighbor (kNN) search, also known as brute-force search, is expensive, and it doesn’t scale particularly well to... 15 MIN READ
Robotics

Sharing CUDA Resources Through Interoperability with NvSciBuf and NvSciSync

There is a growing need among embedded and HPC applications to share resources and control execution for pipelined workflows spanning multiple hardware engines... 13 MIN READ