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

via llvm-commits llvm-commits at lists.llvm.org
Wed May 6 13:54:40 PDT 2026


================

----------------
carlobertolli wrote:

done

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


More information about the llvm-commits mailing list