[SLP]Reorder counters for same values, if the root node is reordered.

The counters for the repeated scalars are ordered in the natural order,
but the original scalars might be reordered during SLP graph reordering
and this order can be dropped. Need to use the scalars after the
reordering, not the original ones, to emit correct code for same value
counters.

llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp

@@ -1165,6 +1165,12 @@ class BoUpSLP {
            !VectorizableTree.front()->UserTreeIndices.empty();
   }
 
+  /// Return the scalars of the root node.
+  ArrayRef<Value *> getRootNodeScalars() const {
+    assert(!VectorizableTree.empty() && "No graph to get the first node from");
+    return VectorizableTree.front()->Scalars;
+  }
+
   /// Builds external uses of the vectorized scalars, i.e. the list of
   /// vectorized scalars to be extracted, their lanes and their scalar users. \p
   /// ExternallyUsedValues contains additional list of external uses to handle
@@ -13355,8 +13361,9 @@ class HorizontalReduction {
 
         // Emit code to correctly handle reused reduced values, if required.
         if (OptReusedScalars && !SameScaleFactor) {
-          VectorizedRoot = emitReusedOps(VectorizedRoot, Builder, VL,
-                                         SameValuesCounter, TrackedToOrig);
+          VectorizedRoot =
+              emitReusedOps(VectorizedRoot, Builder, V.getRootNodeScalars(),
+                            SameValuesCounter, TrackedToOrig);
         }
 
         Value *ReducedSubTree =

llvm/test/Transforms/SLPVectorizer/X86/same-scalars-reordered-in-reduction.ll

@@ -7,7 +7,7 @@ define i32 @test() {
 ; CHECK-NEXT:    [[SQ:%.*]] = alloca [64 x i32], i32 0, align 16
 ; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds [64 x i32], ptr [[SQ]], i64 0, i64 1
 ; CHECK-NEXT:    [[TMP1:%.*]] = load <4 x i32>, ptr [[TMP0]], align 4
-; CHECK-NEXT:    [[TMP2:%.*]] = mul <4 x i32> [[TMP1]], <i32 3, i32 2, i32 2, i32 1>
+; CHECK-NEXT:    [[TMP2:%.*]] = mul <4 x i32> [[TMP1]], <i32 2, i32 3, i32 2, i32 1>
 ; CHECK-NEXT:    [[TMP3:%.*]] = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> [[TMP2]])
 ; CHECK-NEXT:    ret i32 [[TMP3]]
 ;