[SLP]Fix PR95925: extract vectorized index of the potential buildvector sequence.

If the vectorized scalar is not the insert value in the buildvector
sequence but the index, it should be always extracted.

Author: alexey-bataev

llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp

@@ -10269,7 +10269,8 @@ InstructionCost BoUpSLP::getTreeCost(ArrayRef<Value *> VectorizedVals) {
 
     // If found user is an insertelement, do not calculate extract cost but try
     // to detect it as a final shuffled/identity match.
-    if (auto *VU = dyn_cast_or_null<InsertElementInst>(EU.User)) {
+    if (auto *VU = dyn_cast_or_null<InsertElementInst>(EU.User);
+        VU && VU->getOperand(1) == EU.Scalar) {
       if (auto *FTy = dyn_cast<FixedVectorType>(VU->getType())) {
         if (!UsedInserts.insert(VU).second)
           continue;
@@ -13768,7 +13769,8 @@ Value *BoUpSLP::vectorizeTree(
       continue;
     }
 
-    if (auto *VU = dyn_cast<InsertElementInst>(User)) {
+    if (auto *VU = dyn_cast<InsertElementInst>(User);
+        VU && VU && VU->getOperand(1) == Scalar) {
       // Skip if the scalar is another vector op or Vec is not an instruction.
       if (!Scalar->getType()->isVectorTy() && isa<Instruction>(Vec)) {
         if (auto *FTy = dyn_cast<FixedVectorType>(User->getType())) {

llvm/test/Transforms/SLPVectorizer/X86/insertelement-uses-vectorized-index.ll

@@ -0,0 +1,42 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
+; RUN: opt -S --passes=slp-vectorizer -slp-threshold=-10 < %s -mtriple=x86_64-pc-windows-msvc19.39.33523 | FileCheck %s
+
+define void @test(ptr %0) {
+; CHECK-LABEL: define void @test(
+; CHECK-SAME: ptr [[TMP0:%.*]]) {
+; CHECK-NEXT:  [[ENTRY:.*:]]
+; CHECK-NEXT:    [[TMP1:%.*]] = insertelement <2 x ptr> <ptr null, ptr poison>, ptr [[TMP0]], i32 1
+; CHECK-NEXT:    [[TMP2:%.*]] = ptrtoint <2 x ptr> [[TMP1]] to <2 x i64>
+; CHECK-NEXT:    [[TMP3:%.*]] = trunc <2 x i64> [[TMP2]] to <2 x i32>
+; CHECK-NEXT:    switch i32 0, label %[[NEWFUNCROOT994:.*]] [
+; CHECK-NEXT:      i32 1, label %[[NEWFUNCROOT994]]
+; CHECK-NEXT:      i32 0, label %[[NEWFUNCROOT584:.*]]
+; CHECK-NEXT:    ]
+; CHECK:       [[NEWFUNCROOT584]]:
+; CHECK-NEXT:    [[TMP4:%.*]] = shufflevector <2 x i32> [[TMP3]], <2 x i32> poison, <4 x i32> <i32 0, i32 1, i32 poison, i32 poison>
+; CHECK-NEXT:    ret void
+; CHECK:       [[NEWFUNCROOT994]]:
+; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <2 x i32> [[TMP3]], i32 1
+; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <2 x i64> [[TMP2]], i32 0
+; CHECK-NEXT:    [[TMP7:%.*]] = insertelement <4 x i32> zeroinitializer, i32 [[TMP5]], i64 [[TMP6]]
+; CHECK-NEXT:    ret void
+;
+entry:
+  %1 = ptrtoint ptr %0 to i64
+  %2 = trunc i64 %1 to i32
+  %3 = ptrtoint ptr null to i64
+  %4 = trunc i64 %3 to i32
+  switch i32 0, label %newFuncRoot994 [
+  i32 1, label %newFuncRoot994
+  i32 0, label %newFuncRoot584
+  ]
+
+newFuncRoot584:
+  %5 = insertelement <4 x i32> poison, i32 %4, i64 0
+  %6 = insertelement <4 x i32> %5, i32 %2, i64 1
+  ret void
+
+newFuncRoot994:
+  %7 = insertelement <4 x i32> zeroinitializer, i32 %2, i64 %3
+  ret void
+}