[FEA]: Add __int128_t method for cuda::std::abs()

[pmattione-nvidia]

Is this a duplicate?

• I confirmed there appear to be no duplicate issues for this request and that I agree to the Code of Conduct

Area

libcu++

Is your feature request related to a problem? Please describe.

In template code, I need to take the absolute value of a signed integer, but I cannot use cuda::std::abs() as one of the integer types I need to use is __int128_t. Since cuda::std::abs() doesn't support __int128_t, I have to roll my own version instead.

Describe the solution you'd like

I would like there to be an overload for cuda::std::abs() that takes an __int128_t as an input.

Describe alternatives you've considered

No response

Additional context

No response