AVX2指令集浮点乘法性能分析

FOR j := 0 to 3
	i := j*64
	dst[i+63:i] := a[i+63:i] * b[i+63:i]
ENDFOR
dst[MAX:256] := 0

uint64_t lowbit(uint64_t x)
{
    return x & (-x);
}
uint64_t extTo2Power(uint64_t n, int i)//arraysize datasize
{
    while(lowbit(n) < i)
        n += lowbit(n);
    return n;
}

template <typename T>
T* getArray(uint64_t size)
{
    uint64_t ExSize = extTo2Power(size, 32/sizeof(T));
    T* arr = new T[ExSize];
    for (uint64_t i = 0; i < size; i++)
        arr[i] = 1.0+1e-8;
    for (uint64_t i = size; i < ExSize; i++)
        arr[i] = 1.0;
    return arr;
}
}

template <typename T>
T simpleProduct(T* arr, uint64_t size)
{
    T product = 1;
    for (uint64_t i = 0; i < size; i++)
        product *= arr[i];
    return product;
}

float avx2Product(float* arr, uint64_t size)
{
    float product[8] = {1};
    __m256 product256 = _mm256_setr_ps(1, 1, 1, 1, 1, 1, 1, 1);
    __m256 load256 = _mm256_setzero_ps();
    for (uint64_t i = 0; i < size; i += 8)
    {
        load256 = _mm256_loadu_ps(&arr[i]);
        product256 = _mm256_mul_ps(product256, load256);
    }
    _mm256_storeu_ps(product, product256);
    product[0] *= product[1] * product[2] * product[3] * product[4] * product[5] * product[6] * product[7];
    return product[0];
}

double avx2Product(double* arr, uint64_t size)
{
    double product[4] = {1};
    __m256d product256 = _mm256_setr_pd(1, 1, 1, 1);
    __m256d load256 = _mm256_setzero_pd();
    for (uint64_t i = 0; i < size; i += 4)
    {
        load256 = _mm256_loadu_pd(&arr[i]);
        product256 = _mm256_mul_pd(product256, load256);
    }
    _mm256_storeu_pd(product, product256);
    product[0] *= product[1] * product[2] * product[3];
    return product[0];
}

uint64_t getTime()
{
    uint64_t timems = std::chrono::duration_cast<std::chrono::milliseconds>(std::chrono::system_clock::now().time_since_epoch()).count();
    return timems;
}

	uint64_t N = 1e8;
    // compare the performance of simpleProduct and avx2Product
    uint64_t start, end;
    //compare float
    cout << "compare float product" << endl;
    float* arr = getArray<float>(N);
    start = getTime();
    float simpleProductResult = simpleProduct(arr, N);
    end = getTime();
    cout << "Simple product: " << simpleProductResult << endl;
    cout << "Time: " << end - start << " ms" << endl;
    cout << endl;
    start = getTime();
    float avx2ProductResult = avx2Product(arr, N);
    end = getTime();
    cout << "AVX2 product: " << avx2ProductResult << endl;
    cout << "Time: " << end - start << " ms" << endl;
    cout << endl;
    delete[] arr;
    //compare double
    cout << "compare double product" << endl;
    double* arr2 = getArray<double>(N);
    start = getTime();
    double simpleProductResult2 = simpleProduct(arr2, N);
    end = getTime();
    cout << "Simple product: " << simpleProductResult2 << endl;
    cout << "Time: " << end - start << " ms" << endl;
    cout << endl;
    start = getTime();
    double avx2ProductResult2 = avx2Product(arr2, N);
    end = getTime();
    cout << "AVX2 product: " << avx2ProductResult2 << endl;
    cout << "Time: " << end - start << " ms" << endl;
    cout << endl;
    delete[] arr2;

g++ -mavx2 avx_product.cpp 
./a.out

g++ -O2 -mavx2 avx_product.cpp 
./a.out