template <int BLOCK_SIZE> __global__ void
matrixMulCUDA_3_1w2w(float* C, float* A, float* B, int wA, int wB)
{
	// 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 = wA * BLOCK_SIZE * by;

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

	// Step size used to iterate through the sub-matrices of A
	int aStep = 2 * 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 * wB;

	// Csub is used to store the element of the block sub-matrix
	// that is computed by the thread
	float CSub[2] = { 0,0 };

	// 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)
	{

		// Declaration of the shared memory array As used to
		// store the sub-matrix of A
		__shared__ float As[BLOCK_SIZE][2 * BLOCK_SIZE];

		// Declaration of the shared memory array Bs used to
		// store the sub-matrix of B
		__shared__ float Bs[BLOCK_SIZE][2 * BLOCK_SIZE];

		// Load the matrices from device memory
		// to shared memory; each thread loads
		// 2 elements of each matrix
		As[ty][tx] = A[a + wA * ty + tx];
		As[ty][tx + BLOCK_SIZE] = A[a + BLOCK_SIZE + wA * ty + tx];
		Bs[ty][tx] = B[b + wB * ty + tx];
		Bs[ty][tx + BLOCK_SIZE] = B[b + BLOCK_SIZE * wB * ty + tx];

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

		// Multiply the two matrices together;
		// each thread computes one element
		// of the block sub-matrix
		for (int g = 0; g < 2; g++) {
#pragma unroll
			for (int k = 0; k < BLOCK_SIZE; ++k)
			{
				CSub[g] += As[ty][k + (g * BLOCK_SIZE)] * Bs[k][tx + (g * BLOCK_SIZE)];
			}
		}

		// 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 = wB * BLOCK_SIZE * by + BLOCK_SIZE * bx;
	for (int g = 0; g < 2; g++) {
		C[c + (BLOCK_SIZE * g) + wB * ty + tx] = CSub[g];
	}
}