Quick Overview

This project demonstrates how to perform a simple element-wise summation of three arrays using both CPU and GPU (CUDA) approaches. It includes:

CPU Implementation: A standard loop-based summation using C++.
GPU Implementation: A CUDA kernel that sums three arrays in parallel.
Performance Comparison: Execution times are measured using C++ chrono for the CPU and CUDA events for the GPU.

This example is ideal for beginners looking to understand CUDA programming and the nuances of performance measurement between CPU and GPU executions.