[flang-commits] [flang] [flang][AMDGPU] Convert math ops to AMD GPU library calls instead of libm calls (PR #99517)

[Krzysztof Drewniak via flang-commits]

https://github.com/krzysz00 commented:

@arsenm  Overall, is there a problem with using the OCML functions uniformly, even if they're trivial? That leaves the ability for them to become non-trivial in the future

https://github.com/llvm/llvm-project/pull/99517