[llvm] [InstCombine] Transform high latency, dependent FSQRT/FDIV into FMUL (PR #87474)

[Matt Arsenault via llvm-commits]

================
@@ -1796,6 +1879,35 @@ static Instruction *foldFDivSqrtDivisor(BinaryOperator &I,
   return BinaryOperator::CreateFMulFMF(Op0, NewSqrt, &I);
 }
 
+static Value *convertFSqrtDivIntoFMul(CallInst *CI, Instruction *X,
+                                      const SmallVectorImpl<Instruction *> &R1,
+                                      const SmallVectorImpl<Instruction *> &R2,
----------------
arsenm wrote:

const vector ref -> ArrayRef 

https://github.com/llvm/llvm-project/pull/87474