#define SIMDPP_ARCH_X86_SSE4_1 true
#include <simdpp/simd.h>
#include <iostream>
#include <chrono>
//example where i got this from
//https://github.com/p12tic/libsimdpp/tree/2e5c0464a8069310d7eb3048e1afa0e96e08f344

// Initializes vector to store values
void init_vector(float* a, float* b, size_t size) {
    for (int i=0; i<size; i++) {
        a[i] = i * 1.0;
        b[i] = (size * 1.0) - i - 1;
    }
}



using namespace simdpp;
int main() {
    //1048576
    const unsigned long SIZE = 4 * 150000;

    float vec_a[SIZE];
    float vec_b[SIZE];
    float result[SIZE];

///////////////////////////*/
//LibSIMDpp
    //*
    auto t1 = std::chrono::high_resolution_clock::now();

    init_vector(vec_a, vec_b, SIZE);
    for (int i=0; i<SIZE; i+=4) {
        float32<4> xmmA = load(vec_a + i);  //loads 4 floats into xmmA
        float32<4> xmmB = load(vec_b + i);  //loads 4 floats into xmmB
        float32<4> xmmC = add(xmmA, xmmB);  //Vector add of xmmA and xmmB
        store(result + i, xmmC);            //Store result into the vector
    }

    auto t2 = std::chrono::high_resolution_clock::now();

    std::cout << std::chrono::duration_cast<std::chrono::milliseconds>(t2-t1).count()
              << " milliseconds\n";
    //*/


///////////////////////////*/
//standard
    //*
    init_vector(vec_a, vec_b, SIZE);
    t1 = std::chrono::high_resolution_clock::now();

    for (auto i = 0; i < SIZE; i++) {
        result[i] = vec_a[i]  + vec_b[i];
    }

    t2 = std::chrono::high_resolution_clock::now();

    std::cout << std::chrono::duration_cast<std::chrono::milliseconds>(t2-t1).count()
              << " milliseconds\n";
    //*/


    int i = 0;
    return 0;
}