Appropriate usage of cudaGetSymbolAddress and cudaMemcpyToSymbol with global memory?

Question

I am fairly new to CUDA and am familiar with the normal usage of cudaMalloc and cudaMemcpy and also with cudaMemcpyToSymbol f

Answer 1

When global memory is allocated dynamically using cudaMalloc, then the correct copying API to use is cudaMemcpy.

When global memory is allocated statically:

__device__  int my_data[DSIZE];

then the correct API to use is cudaMemcpyToSymbol or cudaMemcpyFromSymbol