URAM blocks have fixed width of 72-bit, so our storage layout depends on how wide each element is.
When the data element has no more than 72bits, the helper class will try to store as many as possible within 72bits and pad zeros when space is left. For example, to store 20k 16-bit elements, 2 URAMs would be used, as each line can store 4 elements and each URAM has fixed depth of 4k.
When the data element has more than 72bits, the helper class will use line of multiple URAM blocks to store each element. This ensures that each cycle we can initiate an element access. So to store 10k 128-bit elements, 6 URAM blocks are required.