[clang] [llvm] [clang-tools-extra] [SLP]Improve findReusedOrderedScalars and graph rotation. (PR #77529)

[Simon Pilgrim via cfe-commits]

================
@@ -3779,65 +3780,169 @@ static void reorderOrder(SmallVectorImpl<unsigned> &Order, ArrayRef<int> Mask,
 std::optional<BoUpSLP::OrdersType>
 BoUpSLP::findReusedOrderedScalars(const BoUpSLP::TreeEntry &TE) {
   assert(TE.State == TreeEntry::NeedToGather && "Expected gather node only.");
-  unsigned NumScalars = TE.Scalars.size();
+  // Try to find subvector extract/insert patterns and reorder only such
+  // patterns.
+  SmallVector<Value *> GatheredScalars(TE.Scalars.begin(), TE.Scalars.end());
+  Type *ScalarTy = GatheredScalars.front()->getType();
+  int NumScalars = GatheredScalars.size();
+  if (!isValidElementType(ScalarTy))
+    return std::nullopt;
+  auto *VecTy = FixedVectorType::get(ScalarTy, NumScalars);
+  int NumParts = TTI->getNumberOfParts(VecTy);
+  if (NumParts == 0 || NumParts >= NumScalars)
+    NumParts = 1;
+  SmallVector<int> ExtractMask;
+  SmallVector<int> Mask;
+  SmallVector<SmallVector<const TreeEntry *>> Entries;
+  SmallVector<std::optional<TargetTransformInfo::ShuffleKind>> ExtractShuffles =
+      tryToGatherExtractElements(GatheredScalars, ExtractMask, NumParts);
+  SmallVector<std::optional<TargetTransformInfo::ShuffleKind>> GatherShuffles =
+      isGatherShuffledEntry(&TE, GatheredScalars, Mask, Entries, NumParts,
+                            /*ForOrder=*/true);
+  // No shuffled operands - ignore.
+  if (GatherShuffles.empty() && ExtractShuffles.empty())
+    return std::nullopt;
   OrdersType CurrentOrder(NumScalars, NumScalars);
-  SmallVector<int> Positions;
-  SmallBitVector UsedPositions(NumScalars);
-  const TreeEntry *STE = nullptr;
-  // Try to find all gathered scalars that are gets vectorized in other
-  // vectorize node. Here we can have only one single tree vector node to
-  // correctly identify order of the gathered scalars.
-  for (unsigned I = 0; I < NumScalars; ++I) {
-    Value *V = TE.Scalars[I];
-    if (!isa<LoadInst, ExtractElementInst, ExtractValueInst>(V))
-      continue;
-    if (const auto *LocalSTE = getTreeEntry(V)) {
-      if (!STE)
-        STE = LocalSTE;
-      else if (STE != LocalSTE)
-        // Take the order only from the single vector node.
-        return std::nullopt;
-      unsigned Lane =
-          std::distance(STE->Scalars.begin(), find(STE->Scalars, V));
-      if (Lane >= NumScalars)
-        return std::nullopt;
-      if (CurrentOrder[Lane] != NumScalars) {
-        if (Lane != I)
+  if (GatherShuffles.size() == 1 &&
+      *GatherShuffles.front() == TTI::SK_PermuteSingleSrc &&
+      Entries.front().front()->isSame(TE.Scalars)) {
+    // Exclude nodes for strided geps from analysis, better to reorder them.
+    if (!TE.UserTreeIndices.empty() &&
+        TE.UserTreeIndices.front().UserTE->State ==
+            TreeEntry::PossibleStridedVectorize &&
+        Entries.front().front()->State == TreeEntry::NeedToGather)
+      return std::nullopt;
+    // Perfect match in the graph, will reuse the previously vectorized
+    // node. Cost is 0.
+    std::iota(CurrentOrder.begin(), CurrentOrder.end(), 0);
+    return CurrentOrder;
+  }
+  auto IsBroadcastMask = [](ArrayRef<int> Mask) {
+    int SingleElt = PoisonMaskElem;
+    return all_of(Mask, [&](int I) {
+      if (SingleElt == PoisonMaskElem && I != PoisonMaskElem)
+        SingleElt = I;
+      return I == PoisonMaskElem || I == SingleElt;
+    });
+  };
----------------
RKSimon wrote:

Don't we have this anywhere else that we can reuse?

https://github.com/llvm/llvm-project/pull/77529