[SLP]Do not count extractelement costs in unreachable/landing pad blocks.

If the external user of the scalar to be extract is in
unreachable/landing pad block, we can skip counting their cost.

Reviewers: RKSimon

Reviewed By: RKSimon

Pull Request: #105667

Author: alexey-bataev

llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp

@@ -10768,17 +10768,21 @@ InstructionCost BoUpSLP::getTreeCost(ArrayRef<Value *> VectorizedVals) {
   std::optional<DenseMap<Value *, unsigned>> ValueToExtUses;
   DenseMap<const TreeEntry *, DenseSet<Value *>> ExtractsCount;
   for (ExternalUser &EU : ExternalUses) {
+    // Uses by ephemeral values are free (because the ephemeral value will be
+    // removed prior to code generation, and so the extraction will be
+    // removed as well) as well as uses in unreachable blocks or in landing pads
+    // (rarely executed).
+    if (EphValues.count(EU.User) ||
+        (EU.User &&
+         (!DT->isReachableFromEntry(cast<Instruction>(EU.User)->getParent()) ||
+          cast<Instruction>(EU.User)->getParent()->isLandingPad())))
+      continue;
+
     // We only add extract cost once for the same scalar.
     if (!isa_and_nonnull<InsertElementInst>(EU.User) &&
         !ExtractCostCalculated.insert(EU.Scalar).second)
       continue;
 
-    // Uses by ephemeral values are free (because the ephemeral value will be
-    // removed prior to code generation, and so the extraction will be
-    // removed as well).
-    if (EphValues.count(EU.User))
-      continue;
-
     // No extract cost for vector "scalar"
     if (isa<FixedVectorType>(EU.Scalar->getType()))
       continue;

llvm/test/Transforms/SLPVectorizer/X86/same-scalar-in-same-phi-extract.ll

@@ -5,7 +5,6 @@ define void @test(i32 %arg) {
 ; CHECK-LABEL: define void @test(
 ; CHECK-SAME: i32 [[ARG:%.*]]) {
 ; CHECK-NEXT:  bb:
-; CHECK-NEXT:    [[TMP2:%.*]] = zext i32 [[ARG]] to i64
 ; CHECK-NEXT:    [[TMP0:%.*]] = insertelement <2 x i32> <i32 poison, i32 0>, i32 [[ARG]], i32 0
 ; CHECK-NEXT:    br label [[BB2:%.*]]
 ; CHECK:       bb2:
@@ -15,6 +14,8 @@ define void @test(i32 %arg) {
 ; CHECK-NEXT:      i32 1, label [[BB4:%.*]]
 ; CHECK-NEXT:    ]
 ; CHECK:       bb3:
+; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <2 x i32> [[TMP0]], i32 0
+; CHECK-NEXT:    [[TMP2:%.*]] = zext i32 [[TMP1]] to i64
 ; CHECK-NEXT:    switch i32 0, label [[BB10]] [
 ; CHECK-NEXT:      i32 18, label [[BB7:%.*]]
 ; CHECK-NEXT:      i32 1, label [[BB7]]