CUDA

CUDA Tutorials, Samples, and Analysis

Running CUDA Profilers on Linux: GPU Optimizations

September 25, 2020 CUDA 4 min read

Instructions for installing and running several of Nvidia's profiling tools on linux.

CUDA Graph Usage: CUDA Feature Testing

September 25, 2020 CUDA 9 min read

Simple demonstration of CUDA graphs using the vector add code from Visual Studio's default CUDA project as a starting point.

cuRAND Usage: CUDA Feature Testing

September 15, 2020 CUDA 7 min read

This post explains one typical approach to using cuRAND followed by my own approach to using cuRAND which is simpler and has higher performance.

Peer-to-peer Memory Copy with NVLink: CUDA Feature Testing

September 14, 2020 CUDA 2 min read

Simplified CUDA P2P memory copy sample and performance results with and without NVLink.

Error Checking & Debugging GPU Code: CUDA Introduction Part 3

February 6, 2019 CUDA 14 min read

This post looks at methods of error checking and debugging GPU code. Primarily by creating helper functions and macros for checking for errors.

Thread Indexing and Memory: CUDA Introduction Part 2

December 17, 2018 CUDA 9 min read

Part 1 in a series of post introducing GPU programming using CUDA. This post looks specifically at thread indexing and memory usage.

Launching CUDA Functions: CUDA Introduction Part 1

December 14, 2018 CUDA 7 min read

Part 1 in a series of post introducing GPU programming using CUDA. This post looks specifically at launching functions on the GPU.