diff --git a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
--- a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
+++ b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
@@ -3774,12 +3774,19 @@
   // Don't tail-fold for tight loops where we would be better off interleaving
   // with an unpredicated loop.
   unsigned NumInsns = 0;
+  unsigned NumComparisons = 0;
   for (BasicBlock *BB : TFI->LVL->getLoop()->blocks()) {
     NumInsns += BB->sizeWithoutDebug();
+    NumComparisons += count_if(
+        *BB, [](Instruction &I) { return isa<CmpInst, FCmpInst>(&I); });
   }
 
   // We expect 4 of these to be a IV PHI, IV add, IV compare and branch.
-  return NumInsns >= SVETailFoldInsnThreshold;
+  // If there is more than one comparison in the loop, increase the required
+  // number of instructions for predicated tail folding. This is because the
+  // throughput of comparison and `whileXX` instructions is only one, and
+  // insufficient computation between comparisons can slow down the code.
+  return NumInsns >= SVETailFoldInsnThreshold * NumComparisons;
 }
 
 InstructionCost