[llvm] [LLVM][CodeGen][SVE] Add isel for bfloat unordered reductions. (PR #143540)

[Matt Arsenault via llvm-commits]

================
@@ -688,6 +683,22 @@ void VectorLegalizer::PromoteSTRICT(SDNode *Node,
   Results.push_back(Round.getValue(1));
 }
 
+void VectorLegalizer::PromoteVECREDUCE(SDNode *Node,
----------------
arsenm wrote:

Doesn't clearly indicate this is the for FP operations 

https://github.com/llvm/llvm-project/pull/143540