/**
* Matrix multiplication (CUDA Kernel) on the device: C = A * B
* wA is A's width and wB is B's width
*/
template <int BLOCK_SIZE> __global__ void
matrixMulCUDA_WSP(float *C, float *A, float *B, int width)
{
    // Block index
    int bx = blockIdx.x;
    int by = blockIdx.y;

    // Thread index
    int tx = threadIdx.x;
    int ty = threadIdx.y;

    // Index of the first sub-matrix of A processed by the block
    int aBegin = width * BLOCK_SIZE * by;

    // Index of the last sub-matrix of A processed by the block
    int aEnd = aBegin + width - 1;

    // Step size used to iterate through the sub-matrices of A
    int aStep = BLOCK_SIZE;

    // Index of the first sub-matrix of B processed by the block
    int bBegin = BLOCK_SIZE * bx;

    // Step size used to iterate through the sub-matrices of B
    int bStep = BLOCK_SIZE * width;

    // Csub is used to store the element of the block sub-matrix
    // that is computed by the thread
    float Csub = 0;


    // Declaration of the shared memory array As used to
    // store the sub-matrix of A
    __shared__ float As[BLOCK_SIZE][BLOCK_SIZE];

    // Declaration of the shared memory array Bs used to
    // store the sub-matrix of B
    __shared__ float Bs[BLOCK_SIZE][BLOCK_SIZE];


    __shared__ float A_shared[BLOCK_SIZE][BLOCK_SIZE];

    // Declaration of the shared memory array Bs used to
    // store the sub-matrix of B
    __shared__ float B_shared[BLOCK_SIZE][BLOCK_SIZE];

    // Load the matrices from device memory
    // to shared memory; each thread loads
    // one element of each matrix
    As[ty][tx] = A[0 + width * ty + tx];
    Bs[ty][tx] = B[0 + width * ty + tx];

    // Loop over all the sub-matrices of A and B
    // required to compute the block sub-matrix
    for (int a = aBegin, b = bBegin;
        a <= aEnd;
        a += aStep, b += bStep) {


        // Load the matrices from device memory
        // to shared memory; each thread loads
        // one element of each matrix
        As[ty][tx] = A[a + width * ty + tx];
        Bs[ty][tx] = B[b + width * ty + tx];

        // Synchronize to make sure the matrices are loaded
        __syncthreads();

        As[ty][tx] = A_shared[a + width * ty + tx];
        Bs[ty][tx] = B_shared[b + width * ty + tx];

        // Multiply the two matrices together;
        // each thread computes one element
        // of the block sub-matrix
#pragma unroll

        for (int k = 0; k < BLOCK_SIZE; ++k) {
            Csub += As[ty][k] * Bs[k][tx];
        }

        // Synchronize to make sure that the preceding
        // computation is done before loading two new
        // sub-matrices of A and B in the next iteration
        __syncthreads();
    }

    // Write the block sub-matrix to device memory;
    // each thread writes one element
    int c = width * BLOCK_SIZE * by + BLOCK_SIZE * bx;
    C[c + width * ty + tx] = Csub;
}