Use __double_as_longlong and __longong_as_double on compute capability 1.0 GPU?

Accelerated Computing CUDA CUDA Programming and Performance
1

I saw they are declared in sm_13_functions.h and wrapped by the macro ARCH >= 130.

Is there any way to use these two functions on compute cap 1.0 GPU?

Thanks!

2

Well, CC1.0 does not support double precision in the first place, so I don’t see how that is going to work.