[PATCH] D34844: [AMDGPU] Always use rcp + mul with fast math

[Matt Arsenault via Phabricator via llvm-commits]

arsenm added inline comments.


================
Comment at: lib/Target/AMDGPU/SIISelLowering.cpp:3780
     SDNodeFlags NewFlags;
     NewFlags.setUnsafeAlgebra(true);
     SDValue Recip = DAG.getNode(AMDGPUISD::RCP, SL, VT, RHS);
----------------
This is a possible source of errors now that less-strict flags can now trigger this


https://reviews.llvm.org/D34844