[libclc] [libclc] Use __ocml_cos/sin/tan/exp*/lgamma/log*/fmax/fmin/sqrt for AMDGPU (PR #153328)

[Wenju He via cfe-commits]

wenju-he wrote:

> If you want to use these implementations, I'd rather merge the OCML content into libclc and migrate over to using it.

Tag @frasercrmck 
The amdgcn implementation probably needs improvement to use llvm elementwise builtin for e.g. half/float exp*

https://github.com/llvm/llvm-project/pull/153328