Skip to content
This repository has been archived by the owner on Oct 18, 2020. It is now read-only.
/ radix-sort Public archive

Radix Sort Implementation running on CPU and GPU (CUDA)

Notifications You must be signed in to change notification settings

whatevermarch/radix-sort

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 

Repository files navigation

Radix Sort

This is my project task demonstrating how to implement radix sort in both serialized version and parallel version using CUDA. The execution time of each version is also measured to compare the performance of the algorithm.

System Requirements

  • Any NVIDIA GPU with compute capability > 3.0 ( > 6.0 is recommended because of a hardware-based atomic operation on shared memory)

You can check the compute capability corresponding to your GPU here.

How to build

Just compile the single-file code with nvcc. The compiler is already bundled with CUDA SDK.

References

Le Grand, Scott. Chapter 32. Broad-Phase Collision Detection with CUDA. GPU Gems 3. NVIDIA Corporation.

About

Radix Sort Implementation running on CPU and GPU (CUDA)

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages