Skip to content

OpenMP and CUDA parallel versions of the Bellman-Ford algorithm

Notifications You must be signed in to change notification settings

danielenapo/parallel-bellman-ford

Repository files navigation

Parallel Bellman-Ford

Project exam for the course "Architectures and Platforms for Artificial Infelligence" (Module 1), of the Master's degree in Artificial Intelligence, University of Bologna.
The scope of this project is to write two parallel version of the Bellman-Ford Algorithm using:

  • OpenMP
  • CUDA

Their performance are evaluate and compared. The work and is discussed in detail in the report.pdf file.

Instructions

This project was thought to run in the SLURM environment of Unibo's GPU cluster. After accessing the server and copying the folder in it, just run:

sbatch project.sbatch

Graph generator

The program graphGenerator.c can generate random graphs compatible with the algorithm, given the number of vertices:

./generate_graphs.sh <number of edges>

To generate a text file containing the graph info in the folder graphs. (This process is already done by project.sbatch)

About

OpenMP and CUDA parallel versions of the Bellman-Ford algorithm

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages