64-bit number support in CUDA

Question

I kind of found different opinions on this topic, which is why that is why I decided to ask here. My question starts with what computing capabilities are supported by int64_t on CUDA. I am running cuda 5 on a Quadro770M and the following code works without problems, although I read that 64-bit unsigned are supported, starting with the ability to compute 1.3. So what is the real answer to this question?

__device__ void printBinary(int64_t a) { int bits[64]; int i; for (i = 0; i < 64; i++) { bits[63 - i] = (a >> i) & 1; } for (int i = 0; i < 64; ++i) { cuPrintf("%d", bits[i]); } cuPrintf("\n"); cuPrintf("%016llX", a); } 

Answer 1

64-bit integers (signed and unsigned) are supported on all CUDA-enabled devices (although operations with them are mapped to several native 32-bit instructions).

Computing ability 1.3 contains 64-bit floating point numbers (which are supported initially).