https://github.com/artecs-group/k-means

Multi-device K-Means based on the He-Vialle implementation.
https://github.com/artecs-group/k-means

Last synced: 2 months ago
JSON representation

Multi-device K-Means based on the He-Vialle implementation.

• Host: GitHub
• URL: https://github.com/artecs-group/k-means
• Owner: artecs-group
• License: mit
• Created: 2023-05-12T06:08:46.000Z (over 1 year ago)
• Default Branch: master
• Last Pushed: 2023-05-12T06:26:41.000Z (over 1 year ago)
• Last Synced: 2024-08-02T15:09:58.867Z (5 months ago)
• Language: C++
• Size: 18.2 MB
• Stars: 0
• Watchers: 6
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-oneapi - Performance and Portability Evaluation of the K-Means Algorithm on SYCL with CPU-GPU architectures - This work uses the k-means algorithm to asses the performance portability of one of the most advanced implementations of the literature He-Vialle over different programming models (DPC++ CUDA OpenMP) and multi-vendor CPU-GPU architectures. (Table of Contents / AI - Machine Learning)

README

        
# K-Means



This repository contains a k-means implementation for CUDA and SYCL.

## Requirements

You have to intall the following dependencies:

* [CUDA Toolkit 11.7](https://developer.nvidia.com/cuda-11-7-0-download-archive)

* [oneAPI 2022.3](https://www.intel.com/content/www/us/en/developer/tools/oneapi/base-toolkit-download.html)

* [Intel Clang/LLVM](https://github.com/intel/llvm/blob/sycl/sycl/doc/GetStartedGuide.md) -> In order to run SYCL over Nvidia GPUs.

* [hipSYCL](https://github.com/OpenSYCL/OpenSYCL) -> Optional.

## Project Structure

The repository is ordered in this folders:

* [He_Vialle_impl](/He_Vialle_impl/): Has the original implementation, you can found it [here](https://gitlab-research.centralesupelec.fr/Stephane.Vialle/cpu-gpu-kmeans).

* [custom_impl](/custom_impl/): Has the CUDA and SYCL custom implementations based on the original one.

* [etc](/etc/): Has the scripts to automatically get the application times.

* [data](/data/): You have there all the data requiered to reproduce the experiments.

## Publications

* Youssef Faqir-Rhazoui and Carlos García (2023). "Exploring the Performance and Portability of the k-means Algorithm on SYCL Across CPU and GPU Architectures". The Journal of Supercomputing.

    * [Free available here](https://doi.org/10.21203/rs.3.rs-2402689/v1).

## Acknowledgements

This work has been supported by the EU (FEDER), the Spanish MINECO and CM under grants S2018/TCS-4423, PID2021-126576NB-I00 funded by MCIN/AEI/10.13039/501100011033 and by "ERDF A way of making Europe".