[clang] [llvm] [AMDGPU] Use 1-iteration Newton-Raphson refinement for FP32 reciprocal. (PR #194716)

[Jay Foad via cfe-commits]

jayfoad wrote:

> > 1ULP for normals, 0 for everything else.
> 
> Isn't there some existing metadata or similar that specifies the max ULP error the user will tolerate? You could piggy back on that instead of inventing a new command line option to control this.

https://llvm.org/docs/LangRef.html#fpmath-metadata

https://github.com/llvm/llvm-project/pull/194716