main.cpp

#include "cuda_runtime.h"
#include "device_launch_parameters.h"

#include <stdio.h>
#include <iostream>
#include <stdlib.h>

#include "kernel.cuh"

int main()
{
    const int arraySize = 5;
    const int a[arraySize] = { 1, 2, 3, 4, 5 };
    const int b[arraySize] = { 10, 20, 30, 40, 60 };
    int c[arraySize] = { 0 };

    int vectors_size = 100000;

    float* vectors = new float[vectors_size * 4];
    float* matrix = new float[16];
    float* output = new float[vectors_size * 4];

    std::srand(0);

    for (int i = 0; i < 16; i++) {
        matrix[i] = static_cast<float>(std::rand() % 101)/50.0f-1.0f;
    }
    for (int i = 0; i < vectors_size*4; i++) {
        vectors[i] = static_cast<float>(std::rand() % 101) / 50.0f - 1.0f;
    }


    // Add vectors in parallel.
    cudaError_t cudaStatus = vectorMultiCuda(vectors,vectors_size,matrix,output);
    if (cudaStatus != cudaSuccess) {
        fprintf(stderr, "addWithCuda failed!");
        return 1;
    }

    std::cout << "vector01: [" << vectors[0] << "," << vectors[1] << "," << vectors[2] << "," << vectors[3] << "]" << std::endl;

    std::cout << "matrix: [" << matrix[0] << "," << matrix[1] << "," << matrix[2] << "," << matrix[3] << "]" << std::endl;

    std::cout << "vector01: [" << output[0] << "," << output[1] << "," << output[2] << "," << output[3] << "]" << std::endl;

    std::cout << "vector02: [" << output[4] << "," << output[5] << "," << output[6] << "," << output[7] << "]" << std::endl;

    //printf("{1,2,3,4,5} + {10,20,30,40,50} = {%d,%d,%d,%d,%d}\n", c[0], c[1], c[2], c[3], c[4]);

    // cudaDeviceReset must be called before exiting in order for profiling and
    // tracing tools such as Nsight and Visual Profiler to show complete traces.
    cudaStatus = cudaDeviceReset();
    if (cudaStatus != cudaSuccess) {
        fprintf(stderr, "cudaDeviceReset failed!");
        return 1;
    }

    return 0;
}