diff --git a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
index 494db0493dacab..e098e0d2f5f5a8 100644
--- a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
+++ b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
@@ -835,11 +835,11 @@ static InstructionsState getSameOpcode(ArrayRef<Value *> VL,
         auto *CallBase = cast<CallInst>(IBase);
         if (Call->getCalledFunction() != CallBase->getCalledFunction())
           return InstructionsState(VL[BaseIndex], nullptr, nullptr);
-        if (Call->hasOperandBundles() &&
+        if (Call->hasOperandBundles() && (!CallBase->hasOperandBundles() ||
             !std::equal(Call->op_begin() + Call->getBundleOperandsStartIndex(),
                         Call->op_begin() + Call->getBundleOperandsEndIndex(),
                         CallBase->op_begin() +
-                            CallBase->getBundleOperandsStartIndex()))
+                            CallBase->getBundleOperandsStartIndex())))
           return InstructionsState(VL[BaseIndex], nullptr, nullptr);
         Intrinsic::ID ID = getVectorIntrinsicIDForCall(Call, &TLI);
         if (ID != BaseID)
diff --git a/llvm/test/Transforms/SLPVectorizer/AArch64/uselistorder.ll b/llvm/test/Transforms/SLPVectorizer/AArch64/uselistorder.ll
new file mode 100644
index 00000000000000..3a68a37c9f82ca
--- /dev/null
+++ b/llvm/test/Transforms/SLPVectorizer/AArch64/uselistorder.ll
@@ -0,0 +1,43 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt < %s -passes=slp-vectorizer -S -pass-remarks-missed=slp-vectorizer 2>&1 | FileCheck %s
+
+target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
+target triple = "aarch64-unknown-linux-gnu"
+
+; This test has UB but the crash in #95016 only happens with it
+define void @uselistorder_test() {
+; CHECK-LABEL: @uselistorder_test(
+; CHECK-NEXT:    [[TMP1:%.*]] = insertelement <2 x double> poison, double 0.000000e+00, i32 0
+; CHECK-NEXT:    [[TMP2:%.*]] = insertelement <2 x double> [[TMP1]], double 0.000000e+00, i32 1
+; CHECK-NEXT:    [[TMP3:%.*]] = fadd <2 x double> [[TMP2]], zeroinitializer
+; CHECK-NEXT:    [[TMP4:%.*]] = fmul <2 x double> zeroinitializer, [[TMP3]]
+; CHECK-NEXT:    [[TMP5:%.*]] = fmul <2 x double> [[TMP4]], zeroinitializer
+; CHECK-NEXT:    [[TMP6:%.*]] = select <2 x i1> zeroinitializer, <2 x double> zeroinitializer, <2 x double> [[TMP5]]
+; CHECK-NEXT:    [[TMP7:%.*]] = fmul <2 x double> [[TMP6]], zeroinitializer
+; CHECK-NEXT:    [[TMP8:%.*]] = fadd <2 x double> [[TMP7]], zeroinitializer
+; CHECK-NEXT:    store <2 x double> [[TMP8]], ptr null, align 8
+; CHECK-NEXT:    ret void
+;
+  %max1 = call double @llvm.maximum.f64(double 0.000000e+00, double 0.000000e+00) [ "a_list"(ptr null) ]
+  %add1 = fadd double %max1, 0.000000e+00
+  %mul1 = fmul double 0.000000e+00, %add1
+  %mul2 = fmul double %mul1, 0.000000e+00
+  %sel1 = select i1 false, double 0.000000e+00, double %mul2
+  %max2 = call double @llvm.maximum.f64(double 0.000000e+00, double 0.000000e+00)
+  %add2 = fadd double %max2, 0.000000e+00
+  %mul3 = fmul double 0.000000e+00, %add2
+  %mul4 = fmul double %mul3, 0.000000e+00
+  %sel2 = select i1 false, double 0.000000e+00, double %mul4
+  %mul5 = fmul double %sel2, 0.000000e+00
+  %add3 = fadd double 0.000000e+00, %mul5
+  %gep1 = getelementptr { double, [1 x [2 x double]] }, ptr null, i64 0, i32 1
+  store double %add3, ptr %gep1, align 8
+  %mul6 = fmul double %sel1, 0.000000e+00
+  %add4 = fadd double %mul6, 0.000000e+00
+  store double %add4, ptr null, align 8
+  ret void
+}
+
+declare double @llvm.maximum.f64(double, double) #0
+
+attributes #0 = { nocallback nofree nosync nounwind speculatable willreturn memory(none) }