Nikolay Sakharnykh

Nikolay Sakharnykh is a senior AI developer technology manager at NVIDIA. He works on accelerating data analytics and machine learning applications on GPUs. He is interested in novel memory management techniques.

Posts by Nikolay Sakharnykh

Technical Walkthrough 0

Improving GPU Memory Oversubscription Performance

In this post, we dive into the performance characteristics of a micro-benchmark that stresses different memory access patterns for the oversubscription scenario. 16 MIN READ
Technical Walkthrough 0

Optimizing Data Transfer Using Lossless Compression with NVIDIA nvcomp

One of the most interesting applications of compression is optimizing communications in GPU applications. GPUs are getting faster every year. For some apps… 17 MIN READ
News 0

Introducing Low-Level GPU Virtual Memory Management

There is a growing need among CUDA applications to manage memory as quickly and as efficiently as possible. Before CUDA 10.2, the number of options available to… 23 MIN READ
Unified Memory
Technical Walkthrough 0

Maximizing Unified Memory Performance in CUDA

Many of today's applications process large volumes of data. While GPU architectures have very fast HBM or GDDR memory, they have limited capacity. 18 MIN READ
Figure 1: Dimethyl ether jet simulations designed to study complex new fuels. Image courtesy of the Center for Exascale Simulation of Combustion in Turbulence (ExaCT).
Technical Walkthrough 0

Beyond GPU Memory Limits with Unified Memory on Pascal

Unified Memory on NVIDIA Pascal GPUs enables applications to run out-of-the-box with larger memory footprints and achieve great baseline performance. 20 MIN READ
Technical Walkthrough 0

High-Performance Geometric Multi-Grid with GPU Acceleration

Algorithms and optimizations for accelerating geometric multi-grid in the HPGMG benchmark with GPUs, including scalability on supercomputers. 16 MIN READ