https://github.com/jonmarty/pycuda-kmeans

A parallelized PyCuda implementation of the KMeans clustering algorithm.
https://github.com/jonmarty/pycuda-kmeans

cuda kmeans pycuda

Last synced: about 2 months ago
JSON representation

A parallelized PyCuda implementation of the KMeans clustering algorithm.

• Host: GitHub
• URL: https://github.com/jonmarty/pycuda-kmeans
• Owner: jonmarty
• Created: 2019-03-09T17:13:00.000Z (over 7 years ago)
• Default Branch: master
• Last Pushed: 2019-03-18T14:16:06.000Z (over 7 years ago)
• Last Synced: 2025-04-10T19:47:36.680Z (about 1 year ago)
• Topics: cuda, kmeans, pycuda
• Language: Python
• Size: 5.86 KB
• Stars: 0
• Watchers: 0
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# PyCuda-KMeans

A parallelized PyCuda implementation of the KMeans clustering algorithm.

## Setup

First, install the CUDA Toolkit on your computer. Downloads and instructions can be found at [https://developer.nvidia.com/cuda-downloads].

Then, install the pycuda library with

  

  pip install pycuda

  

You will also need numpy, if you don't have it, you can install it with

  

  pip install numpy

  

Verify that the pycuda library is working properly using

  

  python PyCudaCheck.py

  

This piece of code generates the array {1 2 3 ... 398 399 400}, which is sent to the gpu. The array is retrieved from the gpu and printed. Then a function is applied to the array that doubles all the values, and the array is again retrieved from the gpu and printed, the result should be {2 4 6 ... 796 798 800}.