Function transpose

XM/include/Dense/transpose.h:18–22

// transpose a matrix
template <typename T>
void transpose(T* out, const T* in, size_s width, size_s height) {
    dim3 blockDim(32, 32); 
    dim3 gridDim((width + blockDim.x - 1) / blockDim.x, (height + blockDim.y - 1) / blockDim.y); 
    transposeKernel<<<gridDim, blockDim>>>(out, in, width, height);
}

template <typename T>
__global__ void symKernel(T* out, const T* in, int mat_size) {