how to copy 64 bit integer from host to device in cuda?

Question

i need to copy 64 bit integer data from host to device memory.
both of them are declared as "unsigned __int64" and i used cudaMemcpyToSymbol().
By checking with Parallel Nsight, the copied data is shown as a negative integer.
I guess the most significant bit of the lower 4 bytes is treated as a sign bit which is not supposed to be.
can anybody give me any direction to come up with this?

Answer 1

Oh, I found the reason.
Though every 64-bit data manipulation works fine, Parallel Nsight does not recognize any 64 bit integer.
It was Nsight problem. It really sucks.
This incomplete debugger made me waste time.