[llvm] [AArch64] Spare N2I roundtrip when splatting float comparison (PR #141806)

[David Green via llvm-commits]

================
@@ -25455,6 +25477,28 @@ static SDValue performDUPCombine(SDNode *N,
   }
 
   if (N->getOpcode() == AArch64ISD::DUP) {
+    // If the instruction is known to produce a scalar in SIMD registers, we can
+    // can duplicate it across the vector lanes using DUPLANE instead of moving
----------------
davemgreen wrote:

can can -> can

https://github.com/llvm/llvm-project/pull/141806