Skip to content

Latest commit

 

History

History
18 lines (15 loc) · 1 KB

README.md

File metadata and controls

18 lines (15 loc) · 1 KB

Capgemini OpenCL tasks

Tasks were implemented and tested on:

  • Windows laptop: GPU: NVIDIA GTX 1050; CPU: Intel Core i7-7700HQ.
  • Linux AWS instance machine: GPU: Nvidia Tesla m60; CPU: Intel Xeon CPU E5-2686.

Tasks list:

  • vectors addition;
  • matrix multiplication using tiles, GPU shared memory, and matrix transposition;
  • reduction (sum);
  • sorting using a custom implementation of the Bitonic sort algorithm.

Getting Started

As both machines have NVIDIA GPU and installed CUDA toolkit, I've used OpenCL SDK from the CUDA toolkit.

  • Install CUDA Toolkit or OpenCL SDK separately.
  • [optional] Install Intel CPU Runtime for OpenCL to enable OpenCL on Intel CPU.
  • Check OpenCL .lib and headers in the Linux makefile and Windows solution for proper linking.
  • Run programs using Make on Linux and Visual Studio 2022 on Windows.