[libc][libm][GPU] Populating 'libmgpu.a' for math on the GPU

This commit populates `libmgpu.a` with wrappers for the following built-ins
- modf, modff
- nearbyint, nearbyintf
- remainder, remainderf
- remquo, remquof
- rint, rintf
- scalbn, scalbnf
- sqrt, sqrtf
- tan, tanf
- tanh, tanhf
- trunc, truncf
and wrappers the following vendor implementations
- nextafter, nextafterf
- sincos, sincosf
- sinh, sinhf
- sinf
- tan, tanf
- tanh, tanhf

Reviewed By: jhuber6

Differential Revision: https://reviews.llvm.org/D153395