C implementation of a neural network using OpenMP and CUDA for parallelization.
C implementation of a neural network using OpenMP and CUDA for parallelization.
This project was developed as a part of the course Architecture and Platforms for Artificial Intelligence (Mod. 2) - Alma Mater Studiorum Università di Bologna.
The report provides an in-depth analysis of the parallelization techniques employed and a description of the OpenMP and CUDA programs.