diff --git a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
index 4b3cc9e41bbd6..77362d610a0c8 100644
--- a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
+++ b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
@@ -5806,21 +5806,18 @@ void BoUpSLP::buildTree_rec(ArrayRef<Value *> VL, unsigned Depth,
   if (TreeEntry *E = getTreeEntry(S.OpValue)) {
     LLVM_DEBUG(dbgs() << "SLP: \tChecking bundle: " << *S.OpValue << ".\n");
     if (!E->isSame(VL)) {
-      if (!doesNotNeedToBeScheduled(S.OpValue)) {
-        LLVM_DEBUG(dbgs() << "SLP: Gathering due to partial overlap.\n");
-        if (TryToFindDuplicates(S))
-          newTreeEntry(VL, std::nullopt /*not vectorized*/, S, UserTreeIdx,
-                       ReuseShuffleIndicies);
-        return;
-      }
-    } else {
-      // Record the reuse of the tree node.  FIXME, currently this is only used
-      // to properly draw the graph rather than for the actual vectorization.
-      E->UserTreeIndices.push_back(UserTreeIdx);
-      LLVM_DEBUG(dbgs() << "SLP: Perfect diamond merge at " << *S.OpValue
-                        << ".\n");
+      LLVM_DEBUG(dbgs() << "SLP: Gathering due to partial overlap.\n");
+      if (TryToFindDuplicates(S))
+        newTreeEntry(VL, std::nullopt /*not vectorized*/, S, UserTreeIdx,
+                     ReuseShuffleIndicies);
       return;
     }
+    // Record the reuse of the tree node.  FIXME, currently this is only used to
+    // properly draw the graph rather than for the actual vectorization.
+    E->UserTreeIndices.push_back(UserTreeIdx);
+    LLVM_DEBUG(dbgs() << "SLP: Perfect diamond merge at " << *S.OpValue
+                      << ".\n");
+    return;
   }
 
   // Check that none of the instructions in the bundle are already in the tree.
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/multi-node-vectorized-insts.ll b/llvm/test/Transforms/SLPVectorizer/X86/multi-node-vectorized-insts.ll
index 3b54b0a058d0c..87292700317ea 100644
--- a/llvm/test/Transforms/SLPVectorizer/X86/multi-node-vectorized-insts.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/multi-node-vectorized-insts.ll
@@ -83,12 +83,13 @@ define void @test2(double %0) {
 ; CHECK-NEXT:    [[TMP3:%.*]] = shufflevector <2 x double> [[TMP2]], <2 x double> poison, <2 x i32> zeroinitializer
 ; CHECK-NEXT:    br label [[TMP4:%.*]]
 ; CHECK:       4:
-; CHECK-NEXT:    [[TMP5:%.*]] = fsub <2 x double> <double 3.000000e+00, double 2.000000e+00>, [[TMP3]]
-; CHECK-NEXT:    [[TMP6:%.*]] = fsub <2 x double> <double 3.000000e+00, double 1.000000e+00>, [[TMP3]]
+; CHECK-NEXT:    [[TMP5:%.*]] = fsub double 1.000000e+00, [[TMP0]]
+; CHECK-NEXT:    [[TMP6:%.*]] = fsub <2 x double> <double 3.000000e+00, double 2.000000e+00>, [[TMP3]]
 ; CHECK-NEXT:    br label [[DOTBACKEDGE:%.*]]
 ; CHECK:       .backedge:
-; CHECK-NEXT:    [[TMP7:%.*]] = fmul <2 x double> [[TMP5]], [[TMP6]]
-; CHECK-NEXT:    [[TMP8:%.*]] = fcmp olt <2 x double> [[TMP7]], zeroinitializer
+; CHECK-NEXT:    [[TMP7:%.*]] = insertelement <2 x double> [[TMP6]], double [[TMP5]], i32 1
+; CHECK-NEXT:    [[TMP8:%.*]] = fmul <2 x double> [[TMP6]], [[TMP7]]
+; CHECK-NEXT:    [[TMP9:%.*]] = fcmp olt <2 x double> [[TMP8]], zeroinitializer
 ; CHECK-NEXT:    br label [[TMP4]]
 ;
   br label %2