This is my first project using NVIDIA CUDA to compare how fast a CPU and GPU can complete large matrix multiplications. The program will create randomly filled matrices A and B of size N x N, and complete the matrix multiplication of A and B using the CPU, then GPU. The program will print the runtime of both the CPU and GPU for each instance, then calculate the average speedup for GPU vs. CPU after 10 instances.
Author: Evan Cooper
GitHub: PickleCoop