[SLP] Add detection of shuffled/perfect matching of tree entries.

SLP supports perfect diamond matching for the vectorized tree entries
but do not support it for gathered entries and does not support
non-perfect (shuffled) matching with 1 or 2 tree entries. Patch adds
support for this matching to improve cost of the vectorized tree.

Reviewed By: RKSimon

Differential Revision: https://reviews.llvm.org/D100495

3 files changed, 168 insertions, 128 deletions

diff --git a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
index 8d022623e40d..df06e9cbfada 100644
--- a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
+++ b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
@@ -1542,6 +1542,14 @@ private:
   getGatherCost(FixedVectorType *Ty,
                 const DenseSet<unsigned> &ShuffledIndices) const;
 
+  /// Checks if the gathered \p VL can be represented as shuffle(s) of previous
+  /// tree entries.
+  /// \returns ShuffleKind, if gathered values can be represented as shuffles of
+  /// previous tree entries. \p Mask is filled with the shuffle mask.
+  Optional<TargetTransformInfo::ShuffleKind>
+  isGatherShuffledEntry(const TreeEntry *TE, SmallVectorImpl<int> &Mask,
+                        SmallVectorImpl<const TreeEntry *> &Entries);
+
   /// \returns the scalarization cost for this list of values. Assuming that
   /// this subtree gets vectorized, we may need to extract the values from the
   /// roots. This method calculates the cost of extracting the values.
@@ -2540,6 +2548,17 @@ void BoUpSLP::buildTree(ArrayRef<Value *> Roots,
   buildTree(Roots, ExternallyUsedValues, UserIgnoreLst);
 }
 
+static int findLaneForValue(ArrayRef<Value *> Scalars,
+                            ArrayRef<int> ReuseShuffleIndices, Value *V) {
+  unsigned FoundLane = std::distance(Scalars.begin(), find(Scalars, V));
+  assert(FoundLane < Scalars.size() && "Couldn't find extract lane");
+  if (!ReuseShuffleIndices.empty()) {
+    FoundLane = std::distance(ReuseShuffleIndices.begin(),
+                              find(ReuseShuffleIndices, FoundLane));
+  }
+  return FoundLane;
+}
+
 void BoUpSLP::buildTree(ArrayRef<Value *> Roots,
                         ExtraValueToDebugLocsMap &ExternallyUsedValues,
                         ArrayRef<Value *> UserIgnoreLst) {
@@ -2560,12 +2579,8 @@ void BoUpSLP::buildTree(ArrayRef<Value *> Roots,
     // For each lane:
     for (int Lane = 0, LE = Entry->Scalars.size(); Lane != LE; ++Lane) {
       Value *Scalar = Entry->Scalars[Lane];
-      int FoundLane = Lane;
-      if (!Entry->ReuseShuffleIndices.empty()) {
-        FoundLane =
-            std::distance(Entry->ReuseShuffleIndices.begin(),
-                          llvm::find(Entry->ReuseShuffleIndices, FoundLane));
-      }
+      int FoundLane =
+          findLaneForValue(Entry->Scalars, Entry->ReuseShuffleIndices, Scalar);
 
       // Check if the scalar is externally used as an extra arg.
       auto ExtI = ExternallyUsedValues.find(Scalar);
@@ -3560,7 +3575,27 @@ InstructionCost BoUpSLP::getEntryCost(TreeEntry *E) {
         return ReuseShuffleCost + Cost;
       }
     }
-    return ReuseShuffleCost + getGatherCost(VL);
+    InstructionCost GatherCost = 0;
+    SmallVector<int> Mask;
+    SmallVector<const TreeEntry *> Entries;
+    Optional<TargetTransformInfo::ShuffleKind> Shuffle =
+        isGatherShuffledEntry(E, Mask, Entries);
+    if (Shuffle.hasValue()) {
+      if (ShuffleVectorInst::isIdentityMask(Mask)) {
+        LLVM_DEBUG(
+            dbgs()
+            << "SLP: perfect diamond match for gather bundle that starts with "
+            << *VL.front() << ".\n");
+      } else {
+        LLVM_DEBUG(dbgs() << "SLP: shuffled " << Entries.size()
+                          << " entries for bundle that starts with "
+                          << *VL.front() << ".\n");
+        GatherCost = TTI->getShuffleCost(*Shuffle, VecTy, Mask);
+      }
+    } else {
+      GatherCost = getGatherCost(VL);
+    }
+    return ReuseShuffleCost + GatherCost;
   }
   assert((E->State == TreeEntry::Vectorize ||
           E->State == TreeEntry::ScatterVectorize) &&
@@ -4216,6 +4251,76 @@ InstructionCost BoUpSLP::getTreeCost() {
   return Cost;
 }
 
+Optional<TargetTransformInfo::ShuffleKind>
+BoUpSLP::isGatherShuffledEntry(const TreeEntry *TE, SmallVectorImpl<int> &Mask,
+                               SmallVectorImpl<const TreeEntry *> &Entries) {
+  auto *VLIt = find_if(VectorizableTree,
+                       [TE](const std::unique_ptr<TreeEntry> &EntryPtr) {
+                         return EntryPtr.get() == TE;
+                       });
+  assert(VLIt != VectorizableTree.end() &&
+         "Gathered values should be in the tree.");
+  Mask.assign(TE->Scalars.size(), UndefMaskElem);
+  Entries.clear();
+  DenseMap<const TreeEntry *, int> Used;
+  int NumShuffles = 0;
+  for (int I = 0, E = TE->Scalars.size(); I < E; ++I) {
+    Value *V = TE->Scalars[I];
+    const TreeEntry *VTE = getTreeEntry(V);
+    if (!VTE) {
+      // Check if it is used in one of the gathered entries.
+      const auto *It =
+          find_if(make_range(VectorizableTree.begin(), VLIt),
+                  [V](const std::unique_ptr<TreeEntry> &EntryPtr) {
+                    return EntryPtr->State == TreeEntry::NeedToGather &&
+                           is_contained(EntryPtr->Scalars, V);
+                  });
+      if (It != VLIt)
+        VTE = It->get();
+    }
+    if (VTE) {
+      auto Res = Used.try_emplace(VTE, NumShuffles);
+      if (Res.second) {
+        Entries.push_back(VTE);
+        ++NumShuffles;
+        if (NumShuffles > 2)
+          return None;
+        if (NumShuffles == 2) {
+          unsigned FirstSz = Entries.front()->Scalars.size();
+          if (!Entries.front()->ReuseShuffleIndices.empty())
+            FirstSz = Entries.front()->ReuseShuffleIndices.size();
+          unsigned SecondSz = Entries.back()->Scalars.size();
+          if (!Entries.back()->ReuseShuffleIndices.empty())
+            SecondSz = Entries.back()->ReuseShuffleIndices.size();
+          if (FirstSz != SecondSz)
+            return None;
+        }
+      }
+      int FoundLane =
+          findLaneForValue(VTE->Scalars, VTE->ReuseShuffleIndices, V);
+      unsigned Sz = VTE->Scalars.size();
+      if (!VTE->ReuseShuffleIndices.empty())
+        Sz = VTE->ReuseShuffleIndices.size();
+      Mask[I] = Res.first->second * Sz + FoundLane;
+      continue;
+    }
+    return None;
+  }
+  if (NumShuffles == 1) {
+    if (ShuffleVectorInst::isReverseMask(Mask))
+      return TargetTransformInfo::SK_Reverse;
+    return TargetTransformInfo::SK_PermuteSingleSrc;
+  }
+  if (NumShuffles == 2) {
+    if (ShuffleVectorInst::isSelectMask(Mask))
+      return TargetTransformInfo::SK_Select;
+    if (ShuffleVectorInst::isTransposeMask(Mask))
+      return TargetTransformInfo::SK_Transpose;
+    return TargetTransformInfo::SK_PermuteTwoSrc;
+  }
+  return None;
+}
+
 InstructionCost
 BoUpSLP::getGatherCost(FixedVectorType *Ty,
                        const DenseSet<unsigned> &ShuffledIndices) const {
@@ -4346,13 +4451,8 @@ Value *BoUpSLP::gather(ArrayRef<Value *> VL) {
     // Add to our 'need-to-extract' list.
     if (TreeEntry *Entry = getTreeEntry(Val)) {
       // Find which lane we need to extract.
-      unsigned FoundLane = std::distance(Entry->Scalars.begin(),
-                                         find(Entry->Scalars, Val));
-      assert(FoundLane < Entry->Scalars.size() && "Couldn't find extract lane");
-      if (!Entry->ReuseShuffleIndices.empty()) {
-        FoundLane = std::distance(Entry->ReuseShuffleIndices.begin(),
-                                  find(Entry->ReuseShuffleIndices, FoundLane));
-      }
+      int FoundLane =
+          findLaneForValue(Entry->Scalars, Entry->ReuseShuffleIndices, Val);
       ExternalUses.push_back(ExternalUser(Val, InsElt, FoundLane));
     }
   }
@@ -4499,7 +4599,19 @@ Value *BoUpSLP::vectorizeTree(TreeEntry *E) {
   bool NeedToShuffleReuses = !E->ReuseShuffleIndices.empty();
   if (E->State == TreeEntry::NeedToGather) {
     setInsertPointAfterBundle(E);
-    Value *Vec = gather(E->Scalars);
+    Value *Vec;
+    SmallVector<int> Mask;
+    SmallVector<const TreeEntry *> Entries;
+    Optional<TargetTransformInfo::ShuffleKind> Shuffle =
+        isGatherShuffledEntry(E, Mask, Entries);
+    if (Shuffle.hasValue()) {
+      assert((Entries.size() == 1 || Entries.size() == 2) &&
+             "Expected shuffle of 1 or 2 entries.");
+      Vec = Builder.CreateShuffleVector(Entries.front()->VectorizedValue,
+                                        Entries.back()->VectorizedValue, Mask);
+    } else {
+      Vec = gather(E->Scalars);
+    }
     if (NeedToShuffleReuses) {
       ShuffleBuilder.addMask(E->ReuseShuffleIndices);
       Vec = ShuffleBuilder.finalize(Vec);
diff --git a/llvm/test/Transforms/SLPVectorizer/AArch64/gather-cost.ll b/llvm/test/Transforms/SLPVectorizer/AArch64/gather-cost.ll
index 57db62ace206..31c63d31f4df 100644
--- a/llvm/test/Transforms/SLPVectorizer/AArch64/gather-cost.ll
+++ b/llvm/test/Transforms/SLPVectorizer/AArch64/gather-cost.ll
@@ -10,7 +10,7 @@ target triple = "aarch64--linux-gnu"
 ; REMARK-LABEL: Function: gather_multiple_use
 ; REMARK:       Args:
 ; REMARK-NEXT:    - String: 'Vectorized horizontal reduction with cost '
-; REMARK-NEXT:    - Cost: '-7'
+; REMARK-NEXT:    - Cost: '-16'
 ;
 ; REMARK-NOT: Function: gather_load
 
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/matched-shuffled-entries.ll b/llvm/test/Transforms/SLPVectorizer/X86/matched-shuffled-entries.ll
index 1a4cbb16b9a9..c57f83ecb186 100644
--- a/llvm/test/Transforms/SLPVectorizer/X86/matched-shuffled-entries.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/matched-shuffled-entries.ll
@@ -4,124 +4,52 @@
 define i32 @bar() local_unnamed_addr {
 ; CHECK-LABEL: @bar(
 ; CHECK-NEXT:  entry:
-; CHECK-NEXT:    [[ADD103:%.*]] = add nsw i32 undef, undef
-; CHECK-NEXT:    [[SUB104:%.*]] = sub nsw i32 undef, undef
-; CHECK-NEXT:    [[ADD105:%.*]] = add nsw i32 undef, undef
-; CHECK-NEXT:    [[SUB106:%.*]] = sub nsw i32 undef, undef
-; CHECK-NEXT:    [[SHR_I:%.*]] = lshr i32 [[ADD103]], 15
-; CHECK-NEXT:    [[AND_I:%.*]] = and i32 [[SHR_I]], 65537
-; CHECK-NEXT:    [[MUL_I:%.*]] = mul nuw i32 [[AND_I]], 65535
-; CHECK-NEXT:    [[ADD_I:%.*]] = add i32 [[MUL_I]], [[ADD103]]
-; CHECK-NEXT:    [[XOR_I:%.*]] = xor i32 [[ADD_I]], [[MUL_I]]
-; CHECK-NEXT:    [[SHR_I64:%.*]] = lshr i32 [[ADD105]], 15
-; CHECK-NEXT:    [[AND_I65:%.*]] = and i32 [[SHR_I64]], 65537
-; CHECK-NEXT:    [[MUL_I66:%.*]] = mul nuw i32 [[AND_I65]], 65535
-; CHECK-NEXT:    [[ADD_I67:%.*]] = add i32 [[MUL_I66]], [[ADD105]]
-; CHECK-NEXT:    [[XOR_I68:%.*]] = xor i32 [[ADD_I67]], [[MUL_I66]]
-; CHECK-NEXT:    [[SHR_I69:%.*]] = lshr i32 [[SUB104]], 15
-; CHECK-NEXT:    [[AND_I70:%.*]] = and i32 [[SHR_I69]], 65537
-; CHECK-NEXT:    [[MUL_I71:%.*]] = mul nuw i32 [[AND_I70]], 65535
-; CHECK-NEXT:    [[ADD_I72:%.*]] = add i32 [[MUL_I71]], [[SUB104]]
-; CHECK-NEXT:    [[XOR_I73:%.*]] = xor i32 [[ADD_I72]], [[MUL_I71]]
-; CHECK-NEXT:    [[SHR_I74:%.*]] = lshr i32 [[SUB106]], 15
-; CHECK-NEXT:    [[AND_I75:%.*]] = and i32 [[SHR_I74]], 65537
-; CHECK-NEXT:    [[MUL_I76:%.*]] = mul nuw i32 [[AND_I75]], 65535
-; CHECK-NEXT:    [[ADD_I77:%.*]] = add i32 [[MUL_I76]], [[SUB106]]
-; CHECK-NEXT:    [[XOR_I78:%.*]] = xor i32 [[ADD_I77]], [[MUL_I76]]
-; CHECK-NEXT:    [[ADD110:%.*]] = add i32 [[XOR_I68]], [[XOR_I]]
-; CHECK-NEXT:    [[ADD112:%.*]] = add i32 [[ADD110]], [[XOR_I73]]
-; CHECK-NEXT:    [[ADD113:%.*]] = add i32 [[ADD112]], [[XOR_I78]]
 ; CHECK-NEXT:    [[ADD78_1:%.*]] = add nsw i32 undef, undef
 ; CHECK-NEXT:    [[SUB86_1:%.*]] = sub nsw i32 undef, undef
 ; CHECK-NEXT:    [[ADD94_1:%.*]] = add nsw i32 undef, undef
 ; CHECK-NEXT:    [[SUB102_1:%.*]] = sub nsw i32 undef, undef
-; CHECK-NEXT:    [[ADD103_1:%.*]] = add nsw i32 [[ADD94_1]], [[ADD78_1]]
-; CHECK-NEXT:    [[SUB104_1:%.*]] = sub nsw i32 [[ADD78_1]], [[ADD94_1]]
-; CHECK-NEXT:    [[ADD105_1:%.*]] = add nsw i32 [[SUB102_1]], [[SUB86_1]]
-; CHECK-NEXT:    [[SUB106_1:%.*]] = sub nsw i32 [[SUB86_1]], [[SUB102_1]]
-; CHECK-NEXT:    [[SHR_I_1:%.*]] = lshr i32 [[ADD103_1]], 15
-; CHECK-NEXT:    [[AND_I_1:%.*]] = and i32 [[SHR_I_1]], 65537
-; CHECK-NEXT:    [[MUL_I_1:%.*]] = mul nuw i32 [[AND_I_1]], 65535
-; CHECK-NEXT:    [[ADD_I_1:%.*]] = add i32 [[MUL_I_1]], [[ADD103_1]]
-; CHECK-NEXT:    [[XOR_I_1:%.*]] = xor i32 [[ADD_I_1]], [[MUL_I_1]]
-; CHECK-NEXT:    [[SHR_I64_1:%.*]] = lshr i32 [[ADD105_1]], 15
-; CHECK-NEXT:    [[AND_I65_1:%.*]] = and i32 [[SHR_I64_1]], 65537
-; CHECK-NEXT:    [[MUL_I66_1:%.*]] = mul nuw i32 [[AND_I65_1]], 65535
-; CHECK-NEXT:    [[ADD_I67_1:%.*]] = add i32 [[MUL_I66_1]], [[ADD105_1]]
-; CHECK-NEXT:    [[XOR_I68_1:%.*]] = xor i32 [[ADD_I67_1]], [[MUL_I66_1]]
-; CHECK-NEXT:    [[SHR_I69_1:%.*]] = lshr i32 [[SUB104_1]], 15
-; CHECK-NEXT:    [[AND_I70_1:%.*]] = and i32 [[SHR_I69_1]], 65537
-; CHECK-NEXT:    [[MUL_I71_1:%.*]] = mul nuw i32 [[AND_I70_1]], 65535
-; CHECK-NEXT:    [[ADD_I72_1:%.*]] = add i32 [[MUL_I71_1]], [[SUB104_1]]
-; CHECK-NEXT:    [[XOR_I73_1:%.*]] = xor i32 [[ADD_I72_1]], [[MUL_I71_1]]
-; CHECK-NEXT:    [[SHR_I74_1:%.*]] = lshr i32 [[SUB106_1]], 15
-; CHECK-NEXT:    [[AND_I75_1:%.*]] = and i32 [[SHR_I74_1]], 65537
-; CHECK-NEXT:    [[MUL_I76_1:%.*]] = mul nuw i32 [[AND_I75_1]], 65535
-; CHECK-NEXT:    [[ADD_I77_1:%.*]] = add i32 [[MUL_I76_1]], [[SUB106_1]]
-; CHECK-NEXT:    [[XOR_I78_1:%.*]] = xor i32 [[ADD_I77_1]], [[MUL_I76_1]]
-; CHECK-NEXT:    [[ADD108_1:%.*]] = add i32 [[XOR_I68_1]], [[ADD113]]
-; CHECK-NEXT:    [[ADD110_1:%.*]] = add i32 [[ADD108_1]], [[XOR_I_1]]
-; CHECK-NEXT:    [[ADD112_1:%.*]] = add i32 [[ADD110_1]], [[XOR_I73_1]]
-; CHECK-NEXT:    [[ADD113_1:%.*]] = add i32 [[ADD112_1]], [[XOR_I78_1]]
 ; CHECK-NEXT:    [[ADD78_2:%.*]] = add nsw i32 undef, undef
-; CHECK-NEXT:    [[ADD103_2:%.*]] = add nsw i32 undef, [[ADD78_2]]
-; CHECK-NEXT:    [[SUB104_2:%.*]] = sub nsw i32 [[ADD78_2]], undef
-; CHECK-NEXT:    [[ADD105_2:%.*]] = add nsw i32 undef, undef
-; CHECK-NEXT:    [[SUB106_2:%.*]] = sub nsw i32 undef, undef
-; CHECK-NEXT:    [[SHR_I_2:%.*]] = lshr i32 [[ADD103_2]], 15
-; CHECK-NEXT:    [[AND_I_2:%.*]] = and i32 [[SHR_I_2]], 65537
-; CHECK-NEXT:    [[MUL_I_2:%.*]] = mul nuw i32 [[AND_I_2]], 65535
-; CHECK-NEXT:    [[ADD_I_2:%.*]] = add i32 [[MUL_I_2]], [[ADD103_2]]
-; CHECK-NEXT:    [[XOR_I_2:%.*]] = xor i32 [[ADD_I_2]], [[MUL_I_2]]
-; CHECK-NEXT:    [[SHR_I64_2:%.*]] = lshr i32 [[ADD105_2]], 15
-; CHECK-NEXT:    [[AND_I65_2:%.*]] = and i32 [[SHR_I64_2]], 65537
-; CHECK-NEXT:    [[MUL_I66_2:%.*]] = mul nuw i32 [[AND_I65_2]], 65535
-; CHECK-NEXT:    [[ADD_I67_2:%.*]] = add i32 [[MUL_I66_2]], [[ADD105_2]]
-; CHECK-NEXT:    [[XOR_I68_2:%.*]] = xor i32 [[ADD_I67_2]], [[MUL_I66_2]]
-; CHECK-NEXT:    [[SHR_I69_2:%.*]] = lshr i32 [[SUB104_2]], 15
-; CHECK-NEXT:    [[AND_I70_2:%.*]] = and i32 [[SHR_I69_2]], 65537
-; CHECK-NEXT:    [[MUL_I71_2:%.*]] = mul nuw i32 [[AND_I70_2]], 65535
-; CHECK-NEXT:    [[ADD_I72_2:%.*]] = add i32 [[MUL_I71_2]], [[SUB104_2]]
-; CHECK-NEXT:    [[XOR_I73_2:%.*]] = xor i32 [[ADD_I72_2]], [[MUL_I71_2]]
-; CHECK-NEXT:    [[SHR_I74_2:%.*]] = lshr i32 [[SUB106_2]], 15
-; CHECK-NEXT:    [[AND_I75_2:%.*]] = and i32 [[SHR_I74_2]], 65537
-; CHECK-NEXT:    [[MUL_I76_2:%.*]] = mul nuw i32 [[AND_I75_2]], 65535
-; CHECK-NEXT:    [[ADD_I77_2:%.*]] = add i32 [[MUL_I76_2]], [[SUB106_2]]
-; CHECK-NEXT:    [[XOR_I78_2:%.*]] = xor i32 [[ADD_I77_2]], [[MUL_I76_2]]
-; CHECK-NEXT:    [[ADD108_2:%.*]] = add i32 [[XOR_I68_2]], [[ADD113_1]]
-; CHECK-NEXT:    [[ADD110_2:%.*]] = add i32 [[ADD108_2]], [[XOR_I_2]]
-; CHECK-NEXT:    [[ADD112_2:%.*]] = add i32 [[ADD110_2]], [[XOR_I73_2]]
-; CHECK-NEXT:    [[ADD113_2:%.*]] = add i32 [[ADD112_2]], [[XOR_I78_2]]
 ; CHECK-NEXT:    [[SUB102_3:%.*]] = sub nsw i32 undef, undef
-; CHECK-NEXT:    [[ADD103_3:%.*]] = add nsw i32 undef, undef
-; CHECK-NEXT:    [[SUB104_3:%.*]] = sub nsw i32 undef, undef
-; CHECK-NEXT:    [[ADD105_3:%.*]] = add nsw i32 [[SUB102_3]], undef
-; CHECK-NEXT:    [[SUB106_3:%.*]] = sub nsw i32 undef, [[SUB102_3]]
-; CHECK-NEXT:    [[SHR_I_3:%.*]] = lshr i32 [[ADD103_3]], 15
-; CHECK-NEXT:    [[AND_I_3:%.*]] = and i32 [[SHR_I_3]], 65537
-; CHECK-NEXT:    [[MUL_I_3:%.*]] = mul nuw i32 [[AND_I_3]], 65535
-; CHECK-NEXT:    [[ADD_I_3:%.*]] = add i32 [[MUL_I_3]], [[ADD103_3]]
-; CHECK-NEXT:    [[XOR_I_3:%.*]] = xor i32 [[ADD_I_3]], [[MUL_I_3]]
-; CHECK-NEXT:    [[SHR_I64_3:%.*]] = lshr i32 [[ADD105_3]], 15
-; CHECK-NEXT:    [[AND_I65_3:%.*]] = and i32 [[SHR_I64_3]], 65537
-; CHECK-NEXT:    [[MUL_I66_3:%.*]] = mul nuw i32 [[AND_I65_3]], 65535
-; CHECK-NEXT:    [[ADD_I67_3:%.*]] = add i32 [[MUL_I66_3]], [[ADD105_3]]
-; CHECK-NEXT:    [[XOR_I68_3:%.*]] = xor i32 [[ADD_I67_3]], [[MUL_I66_3]]
-; CHECK-NEXT:    [[SHR_I69_3:%.*]] = lshr i32 [[SUB104_3]], 15
-; CHECK-NEXT:    [[AND_I70_3:%.*]] = and i32 [[SHR_I69_3]], 65537
-; CHECK-NEXT:    [[MUL_I71_3:%.*]] = mul nuw i32 [[AND_I70_3]], 65535
-; CHECK-NEXT:    [[ADD_I72_3:%.*]] = add i32 [[MUL_I71_3]], [[SUB104_3]]
-; CHECK-NEXT:    [[XOR_I73_3:%.*]] = xor i32 [[ADD_I72_3]], [[MUL_I71_3]]
-; CHECK-NEXT:    [[SHR_I74_3:%.*]] = lshr i32 [[SUB106_3]], 15
-; CHECK-NEXT:    [[AND_I75_3:%.*]] = and i32 [[SHR_I74_3]], 65537
-; CHECK-NEXT:    [[MUL_I76_3:%.*]] = mul nuw i32 [[AND_I75_3]], 65535
-; CHECK-NEXT:    [[ADD_I77_3:%.*]] = add i32 [[MUL_I76_3]], [[SUB106_3]]
-; CHECK-NEXT:    [[XOR_I78_3:%.*]] = xor i32 [[ADD_I77_3]], [[MUL_I76_3]]
-; CHECK-NEXT:    [[ADD108_3:%.*]] = add i32 [[XOR_I68_3]], [[ADD113_2]]
-; CHECK-NEXT:    [[ADD110_3:%.*]] = add i32 [[ADD108_3]], [[XOR_I_3]]
-; CHECK-NEXT:    [[ADD112_3:%.*]] = add i32 [[ADD110_3]], [[XOR_I73_3]]
-; CHECK-NEXT:    [[ADD113_3:%.*]] = add i32 [[ADD112_3]], [[XOR_I78_3]]
-; CHECK-NEXT:    [[SHR:%.*]] = lshr i32 [[ADD113_3]], 16
+; CHECK-NEXT:    [[TMP0:%.*]] = insertelement <16 x i32> poison, i32 [[SUB102_3]], i32 0
+; CHECK-NEXT:    [[TMP1:%.*]] = insertelement <16 x i32> [[TMP0]], i32 undef, i32 1
+; CHECK-NEXT:    [[TMP2:%.*]] = insertelement <16 x i32> [[TMP1]], i32 [[SUB102_1]], i32 2
+; CHECK-NEXT:    [[TMP3:%.*]] = insertelement <16 x i32> [[TMP2]], i32 undef, i32 3
+; CHECK-NEXT:    [[TMP4:%.*]] = insertelement <16 x i32> [[TMP3]], i32 undef, i32 4
+; CHECK-NEXT:    [[TMP5:%.*]] = insertelement <16 x i32> [[TMP4]], i32 undef, i32 5
+; CHECK-NEXT:    [[TMP6:%.*]] = insertelement <16 x i32> [[TMP5]], i32 undef, i32 6
+; CHECK-NEXT:    [[TMP7:%.*]] = insertelement <16 x i32> [[TMP6]], i32 [[ADD94_1]], i32 7
+; CHECK-NEXT:    [[TMP8:%.*]] = insertelement <16 x i32> [[TMP7]], i32 [[ADD78_1]], i32 8
+; CHECK-NEXT:    [[TMP9:%.*]] = insertelement <16 x i32> [[TMP8]], i32 [[SUB86_1]], i32 9
+; CHECK-NEXT:    [[TMP10:%.*]] = insertelement <16 x i32> [[TMP9]], i32 undef, i32 10
+; CHECK-NEXT:    [[TMP11:%.*]] = insertelement <16 x i32> [[TMP10]], i32 [[ADD78_2]], i32 11
+; CHECK-NEXT:    [[TMP12:%.*]] = insertelement <16 x i32> [[TMP11]], i32 undef, i32 12
+; CHECK-NEXT:    [[TMP13:%.*]] = insertelement <16 x i32> [[TMP12]], i32 undef, i32 13
+; CHECK-NEXT:    [[TMP14:%.*]] = insertelement <16 x i32> [[TMP13]], i32 undef, i32 14
+; CHECK-NEXT:    [[TMP15:%.*]] = insertelement <16 x i32> [[TMP14]], i32 undef, i32 15
+; CHECK-NEXT:    [[TMP16:%.*]] = insertelement <16 x i32> <i32 undef, i32 undef, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>, i32 [[SUB86_1]], i32 2
+; CHECK-NEXT:    [[TMP17:%.*]] = insertelement <16 x i32> [[TMP16]], i32 undef, i32 3
+; CHECK-NEXT:    [[TMP18:%.*]] = insertelement <16 x i32> [[TMP17]], i32 undef, i32 4
+; CHECK-NEXT:    [[TMP19:%.*]] = insertelement <16 x i32> [[TMP18]], i32 undef, i32 5
+; CHECK-NEXT:    [[TMP20:%.*]] = insertelement <16 x i32> [[TMP19]], i32 undef, i32 6
+; CHECK-NEXT:    [[TMP21:%.*]] = insertelement <16 x i32> [[TMP20]], i32 [[ADD78_1]], i32 7
+; CHECK-NEXT:    [[TMP22:%.*]] = insertelement <16 x i32> [[TMP21]], i32 [[ADD94_1]], i32 8
+; CHECK-NEXT:    [[TMP23:%.*]] = insertelement <16 x i32> [[TMP22]], i32 [[SUB102_1]], i32 9
+; CHECK-NEXT:    [[TMP24:%.*]] = insertelement <16 x i32> [[TMP23]], i32 [[ADD78_2]], i32 10
+; CHECK-NEXT:    [[TMP25:%.*]] = insertelement <16 x i32> [[TMP24]], i32 undef, i32 11
+; CHECK-NEXT:    [[TMP26:%.*]] = insertelement <16 x i32> [[TMP25]], i32 undef, i32 12
+; CHECK-NEXT:    [[TMP27:%.*]] = insertelement <16 x i32> [[TMP26]], i32 undef, i32 13
+; CHECK-NEXT:    [[TMP28:%.*]] = insertelement <16 x i32> [[TMP27]], i32 undef, i32 14
+; CHECK-NEXT:    [[TMP29:%.*]] = insertelement <16 x i32> [[TMP28]], i32 [[SUB102_3]], i32 15
+; CHECK-NEXT:    [[TMP30:%.*]] = add nsw <16 x i32> [[TMP15]], [[TMP29]]
+; CHECK-NEXT:    [[TMP31:%.*]] = sub nsw <16 x i32> [[TMP15]], [[TMP29]]
+; CHECK-NEXT:    [[TMP32:%.*]] = shufflevector <16 x i32> [[TMP30]], <16 x i32> [[TMP31]], <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 21, i32 22, i32 7, i32 24, i32 25, i32 10, i32 27, i32 28, i32 13, i32 30, i32 31>
+; CHECK-NEXT:    [[TMP33:%.*]] = lshr <16 x i32> [[TMP32]], <i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15>
+; CHECK-NEXT:    [[TMP34:%.*]] = and <16 x i32> [[TMP33]], <i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537>
+; CHECK-NEXT:    [[TMP35:%.*]] = mul nuw <16 x i32> [[TMP34]], <i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535>
+; CHECK-NEXT:    [[TMP36:%.*]] = add <16 x i32> [[TMP35]], [[TMP32]]
+; CHECK-NEXT:    [[TMP37:%.*]] = xor <16 x i32> [[TMP36]], [[TMP35]]
+; CHECK-NEXT:    [[TMP38:%.*]] = call i32 @llvm.vector.reduce.add.v16i32(<16 x i32> [[TMP37]])
+; CHECK-NEXT:    [[SHR:%.*]] = lshr i32 [[TMP38]], 16
 ; CHECK-NEXT:    [[ADD119:%.*]] = add nuw nsw i32 undef, [[SHR]]
 ; CHECK-NEXT:    [[SHR120:%.*]] = lshr i32 [[ADD119]], 1
 ; CHECK-NEXT:    ret i32 [[SHR120]]