dadopuccio/n-gram

OpenMP implementation of an algorithm to extract word N-Grams histogram

N-Gram

OpenMP implementation of an algorithm to extract word n-grams histograms.
The aim of this work is to compare the computational costs of a sequentail and a parallel version of an n-grams histogram extractor on words, evaluating the speedup achieved in several test situations.

Requirements

In order to run the code are required:

• OpenMP
• C++17 or newer (as the library std::filesystem, used to deal with files and folders, was introduced in C++17)

Acknowledgements

This project is a mid term project for the course of Parallel Computing, held by professor Marco Bertini at University of Florence.