[SLP] Vectorize the index computations of getelementptr instructions.

This patch seeds the SLP vectorizer with getelementptr indices. The primary
motivation in doing so is to vectorize gather-like idioms beginning with
consecutive loads (e.g., g[a[0] - b[0]] + g[a[1] - b[1]] + ...). While these
cases could be vectorized with a top-down phase, seeding the existing bottom-up
phase with the index computations avoids the complexity, compile-time, and
phase ordering issues associated with a full top-down pass. Only bundles of
single-index getelementptrs with non-constant differences are considered for
vectorization.

Differential Revision: http://reviews.llvm.org/D14829

llvm-svn: 257800

llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp

@@ -412,6 +412,13 @@ public:
     return NumLoadsWantToChangeOrder > NumLoadsWantToKeepOrder;
   }
 
+  /// \return The vector element size in bits to use when vectorizing the
+  /// expression tree ending at \p V. If V is a store, the size is the width of
+  /// the stored value. Otherwise, the size is the width of the largest loaded
+  /// value reaching V. This method is used by the vectorizer to calculate
+  /// vectorization factors.
+  unsigned getVectorElementSize(Value *V);
+
 private:
   struct TreeEntry;
 
@@ -3139,10 +3146,73 @@ void BoUpSLP::scheduleBlock(BlockScheduling *BS) {
   BS->ScheduleStart = nullptr;
 }
 
+unsigned BoUpSLP::getVectorElementSize(Value *V) {
+  auto &DL = F->getParent()->getDataLayout();
+
+  // If V is a store, just return the width of the stored value without
+  // traversing the expression tree. This is the common case.
+  if (auto *Store = dyn_cast<StoreInst>(V))
+    return DL.getTypeSizeInBits(Store->getValueOperand()->getType());
+
+  // If V is not a store, we can traverse the expression tree to find loads
+  // that feed it. The type of the loaded value may indicate a more suitable
+  // width than V's type. We want to base the vector element size on the width
+  // of memory operations where possible.
+  SmallVector<Instruction *, 16> Worklist;
+  SmallPtrSet<Instruction *, 16> Visited;
+  if (auto *I = dyn_cast<Instruction>(V))
+    Worklist.push_back(I);
+
+  // Traverse the expression tree in bottom-up order looking for loads. If we
+  // encounter an instruciton we don't yet handle, we give up.
+  auto MaxWidth = 0u;
+  auto FoundUnknownInst = false;
+  while (!Worklist.empty() && !FoundUnknownInst) {
+    auto *I = Worklist.pop_back_val();
+    Visited.insert(I);
+
+    // We should only be looking at scalar instructions here. If the current
+    // instruction has a vector type, give up.
+    auto *Ty = I->getType();
+    if (isa<VectorType>(Ty))
+      FoundUnknownInst = true;
+
+    // If the current instruction is a load, update MaxWidth to reflect the
+    // width of the loaded value.
+    else if (isa<LoadInst>(I))
+      MaxWidth = std::max(MaxWidth, (unsigned)DL.getTypeSizeInBits(Ty));
+
+    // Otherwise, we need to visit the operands of the instruction. We only
+    // handle the interesting cases from buildTree here. If an operand is an
+    // instruction we haven't yet visited, we add it to the worklist.
+    else if (isa<PHINode>(I) || isa<CastInst>(I) || isa<GetElementPtrInst>(I) ||
+             isa<CmpInst>(I) || isa<SelectInst>(I) || isa<BinaryOperator>(I)) {
+      for (Use &U : I->operands())
+        if (auto *J = dyn_cast<Instruction>(U.get()))
+          if (!Visited.count(J))
+            Worklist.push_back(J);
+    }
+
+    // If we don't yet handle the instruction, give up.
+    else
+      FoundUnknownInst = true;
+  }
+
+  // If we didn't encounter a memory access in the expression tree, or if we
+  // gave up for some reason, just return the width of V.
+  if (!MaxWidth || FoundUnknownInst)
+    return DL.getTypeSizeInBits(V->getType());
+
+  // Otherwise, return the maximum width we found.
+  return MaxWidth;
+}
+
 /// The SLPVectorizer Pass.
 struct SLPVectorizer : public FunctionPass {
   typedef SmallVector<StoreInst *, 8> StoreList;
   typedef MapVector<Value *, StoreList> StoreListMap;
+  typedef SmallVector<WeakVH, 8> WeakVHList;
+  typedef MapVector<Value *, WeakVHList> WeakVHListMap;
 
   /// Pass identification, replacement for typeid
   static char ID;
@@ -3172,7 +3242,8 @@ struct SLPVectorizer : public FunctionPass {
     DT = &getAnalysis<DominatorTreeWrapperPass>().getDomTree();
     AC = &getAnalysis<AssumptionCacheTracker>().getAssumptionCache(F);
 
-    StoreRefs.clear();
+    Stores.clear();
+    GEPs.clear();
     bool Changed = false;
 
     // If the target claims to have no vector registers don't attempt
@@ -3206,15 +3277,24 @@ struct SLPVectorizer : public FunctionPass {
 
     // Scan the blocks in the function in post order.
     for (auto BB : post_order(&F.getEntryBlock())) {
+      collectSeedInstructions(BB);
+
       // Vectorize trees that end at stores.
-      if (unsigned count = collectStores(BB, R)) {
+      if (NumStores > 0) {
-        (void)count;
+        DEBUG(dbgs() << "SLP: Found " << NumStores << " stores.\n");
-        DEBUG(dbgs() << "SLP: Found " << count << " stores to vectorize.\n");
         Changed |= vectorizeStoreChains(R);
       }
 
       // Vectorize trees that end at reductions.
       Changed |= vectorizeChainsInBlock(BB, R);
+
+      // Vectorize the index computations of getelementptr instructions. This
+      // is primarily intended to catch gather-like idioms ending at
+      // non-consecutive loads.
+      if (NumGEPs > 0) {
+        DEBUG(dbgs() << "SLP: Found " << NumGEPs << " GEPs.\n");
+        Changed |= vectorizeGEPIndices(BB, R);
+      }
     }
 
     if (Changed) {
@@ -3241,12 +3321,14 @@ struct SLPVectorizer : public FunctionPass {
   }
 
 private:
-
+  /// \brief Collect store and getelementptr instructions and organize them
-  /// \brief Collect memory references and sort them according to their base
+  /// according to the underlying object of their pointer operands. We sort the
-  /// object. We sort the stores to their base objects to reduce the cost of the
+  /// instructions by their underlying objects to reduce the cost of
-  /// quadratic search on the stores. TODO: We can further reduce this cost
+  /// consecutive access queries.
-  /// if we flush the chain creation every time we run into a memory barrier.
+  ///
-  unsigned collectStores(BasicBlock *BB, BoUpSLP &R);
+  /// TODO: We can further reduce this cost if we flush the chain creation
+  ///       every time we run into a memory barrier.
+  void collectSeedInstructions(BasicBlock *BB);
 
   /// \brief Try to vectorize a chain that starts at two arithmetic instrs.
   bool tryToVectorizePair(Value *A, Value *B, BoUpSLP &R);
@@ -3262,9 +3344,13 @@ private:
   /// \brief Try to vectorize a chain that may start at the operands of \V;
   bool tryToVectorize(BinaryOperator *V, BoUpSLP &R);
 
-  /// \brief Vectorize the stores that were collected in StoreRefs.
+  /// \brief Vectorize the store instructions collected in Stores.
   bool vectorizeStoreChains(BoUpSLP &R);
 
+  /// \brief Vectorize the index computations of the getelementptr instructions
+  /// collected in GEPs.
+  bool vectorizeGEPIndices(BasicBlock *BB, BoUpSLP &R);
+
   /// \brief Scan the basic block and look for patterns that are likely to start
   /// a vectorization chain.
   bool vectorizeChainsInBlock(BasicBlock *BB, BoUpSLP &R);
@@ -3274,8 +3360,19 @@ private:
 
   bool vectorizeStores(ArrayRef<StoreInst *> Stores, int costThreshold,
                        BoUpSLP &R);
-private:
+
-  StoreListMap StoreRefs;
+  /// The store instructions in a basic block organized by base pointer.
+  StoreListMap Stores;
+
+  /// The getelementptr instructions in a basic block organized by base pointer.
+  WeakVHListMap GEPs;
+
+  /// The number of store instructions in a basic block.
+  unsigned NumStores;
+
+  /// The number of getelementptr instructions in a basic block.
+  unsigned NumGEPs;
+
   unsigned MaxVecRegSize; // This is set by TTI or overridden by cl::opt.
 };
 
@@ -3296,9 +3393,7 @@ bool SLPVectorizer::vectorizeStoreChain(ArrayRef<Value *> Chain,
   unsigned ChainLen = Chain.size();
   DEBUG(dbgs() << "SLP: Analyzing a store chain of length " << ChainLen
         << "\n");
-  Type *StoreTy = cast<StoreInst>(Chain[0])->getValueOperand()->getType();
+  unsigned Sz = R.getVectorElementSize(Chain[0]);
-  auto &DL = cast<StoreInst>(Chain[0])->getModule()->getDataLayout();
-  unsigned Sz = DL.getTypeSizeInBits(StoreTy);
   unsigned VF = VecRegSize / Sz;
 
   if (!isPowerOf2_32(Sz) || VF < 2)
@@ -3409,33 +3504,43 @@ bool SLPVectorizer::vectorizeStores(ArrayRef<StoreInst *> Stores,
   return Changed;
 }
 
+void SLPVectorizer::collectSeedInstructions(BasicBlock *BB) {
 
-unsigned SLPVectorizer::collectStores(BasicBlock *BB, BoUpSLP &R) {
+  // Initialize the collections. We will make a single pass over the block.
-  unsigned count = 0;
+  Stores.clear();
-  StoreRefs.clear();
+  GEPs.clear();
+  NumStores = NumGEPs = 0;
   const DataLayout &DL = BB->getModule()->getDataLayout();
+
+  // Visit the store and getelementptr instructions in BB and organize them in
+  // Stores and GEPs according to the underlying objects of their pointer
+  // operands.
   for (Instruction &I : *BB) {
-    StoreInst *SI = dyn_cast<StoreInst>(&I);
-    if (!SI)
-      continue;
 
-    // Don't touch volatile stores.
+    // Ignore store instructions that are volatile or have a pointer operand
-    if (!SI->isSimple())
+    // that doesn't point to a scalar type.
-      continue;
+    if (auto *SI = dyn_cast<StoreInst>(&I)) {
+      if (!SI->isSimple())
+        continue;
+      if (!isValidElementType(SI->getValueOperand()->getType()))
+        continue;
+      Stores[GetUnderlyingObject(SI->getPointerOperand(), DL)].push_back(SI);
+      ++NumStores;
+    }
 
-    // Check that the pointer points to scalars.
+    // Ignore getelementptr instructions that have more than one index, a
-    Type *Ty = SI->getValueOperand()->getType();
+    // constant index, or a pointer operand that doesn't point to a scalar
-    if (!isValidElementType(Ty))
+    // type.
-      continue;
+    else if (auto *GEP = dyn_cast<GetElementPtrInst>(&I)) {
-
+      auto Idx = GEP->idx_begin()->get();
-    // Find the base pointer.
+      if (GEP->getNumIndices() > 1 || isa<Constant>(Idx))
-    Value *Ptr = GetUnderlyingObject(SI->getPointerOperand(), DL);
+        continue;
-
+      if (!isValidElementType(Idx->getType()))
-    // Save the store locations.
+        continue;
-    StoreRefs[Ptr].push_back(SI);
+      GEPs[GetUnderlyingObject(GEP->getPointerOperand(), DL)].push_back(GEP);
-    count++;
+      ++NumGEPs;
+    }
   }
-  return count;
 }
 
 bool SLPVectorizer::tryToVectorizePair(Value *A, Value *B, BoUpSLP &R) {
@@ -3459,12 +3564,10 @@ bool SLPVectorizer::tryToVectorizeList(ArrayRef<Value *> VL, BoUpSLP &R,
     return false;
 
   unsigned Opcode0 = I0->getOpcode();
-  const DataLayout &DL = I0->getModule()->getDataLayout();
 
-  Type *Ty0 = I0->getType();
-  unsigned Sz = DL.getTypeSizeInBits(Ty0);
   // FIXME: Register size should be a parameter to this function, so we can
   // try different vectorization factors.
+  unsigned Sz = R.getVectorElementSize(I0);
   unsigned VF = MinVecRegSize / Sz;
 
   for (Value *V : VL) {
@@ -4183,10 +4286,83 @@ bool SLPVectorizer::vectorizeChainsInBlock(BasicBlock *BB, BoUpSLP &R) {
   return Changed;
 }
 
+bool SLPVectorizer::vectorizeGEPIndices(BasicBlock *BB, BoUpSLP &R) {
+  auto Changed = false;
+  for (auto &Entry : GEPs) {
+    auto &GEPList = Entry.second;
+
+    // If the getelementptr list has fewer than two elements, there's nothing
+    // to do.
+    if (GEPList.size() < 2)
+      continue;
+
+    DEBUG(dbgs() << "SLP: Analyzing a getelementptr list of length "
+                 << GEPList.size() << ".\n");
+
+    // Initialize a set a candidate getelementptrs. Note that we use a
+    // SetVector here to preserve program order. If the index computations are
+    // vectorizable and begin with loads, we want to minimize the chance of
+    // having to reorder them later.
+    SetVector<Value *> Candidates(GEPList.begin(), GEPList.end());
+
+    // Some of the candidates may have already been vectorized after we
+    // initially collected them. If so, the WeakVHs will have nullified the
+    // values, so remove them from the set of candidates.
+    Candidates.remove(nullptr);
+
+    // Remove from the set of candidates all pairs of getelementptrs with
+    // constant differences. Such getelementptrs are likely not good candidates
+    // for vectorization in a bottom-up phase since one can be computed from
+    // the other.
+    for (int I = 0, E = GEPList.size(); I < E && Candidates.size() > 1; ++I) {
+      auto *GEP = SE->getSCEV(GEPList[I]);
+      for (int J = I + 1; J < E && Candidates.size() > 1; ++J)
+        if (isa<SCEVConstant>(SE->getMinusSCEV(GEP, SE->getSCEV(GEPList[J])))) {
+          Candidates.remove(GEPList[I]);
+          Candidates.remove(GEPList[J]);
+        }
+    }
+
+    // We break out of the above computation as soon as we know there are fewer
+    // than two candidates remaining.
+    if (Candidates.size() < 2)
+      continue;
+
+    // Add the single, non-constant index of each candidate to the bundle. We
+    // ensured the indices met these constraints when we originally collected
+    // the getelementptrs.
+    SmallVector<Value *, 16> Bundle(Candidates.size());
+    auto BundleIndex = 0u;
+    for (auto *V : Candidates) {
+      auto *GEP = cast<GetElementPtrInst>(V);
+      auto *GEPIdx = GEP->idx_begin()->get();
+      assert(GEP->getNumIndices() == 1 || !isa<Constant>(GEPIdx));
+      Bundle[BundleIndex++] = GEPIdx;
+    }
+
+    // Try and vectorize the indices. We are currently only interested in
+    // gather-like cases of the form:
+    //
+    // ... = g[a[0] - b[0]] + g[a[1] - b[1]] + ...
+    //
+    // where the loads of "a", the loads of "b", and the subtractions can be
+    // performed in parallel. It's likely that detecting this pattern in a
+    // bottom-up phase will be simpler and less costly than building a
+    // full-blown top-down phase beginning at the consecutive loads. We process
+    // the bundle in chunks of 16 (like we do for stores) to minimize
+    // compile-time.
+    for (unsigned BI = 0, BE = Bundle.size(); BI < BE; BI += 16) {
+      auto Len = std::min<unsigned>(BE - BI, 16);
+      Changed |= tryToVectorizeList(makeArrayRef(&Bundle[BI], Len), R);
+    }
+  }
+  return Changed;
+}
+
 bool SLPVectorizer::vectorizeStoreChains(BoUpSLP &R) {
   bool Changed = false;
   // Attempt to sort and vectorize each of the store-groups.
-  for (StoreListMap::iterator it = StoreRefs.begin(), e = StoreRefs.end();
+  for (StoreListMap::iterator it = Stores.begin(), e = Stores.end();
        it != e; ++it) {
     if (it->second.size() < 2)
       continue;

llvm/test/Transforms/SLPVectorizer/AArch64/gather-reduce.ll

@@ -0,0 +1,258 @@
+; RUN: opt -S -slp-vectorizer -dce -instcombine < %s | FileCheck %s
+
+target datalayout = "e-m:e-i64:64-i128:128-n32:64-S128"
+target triple = "aarch64--linux-gnu"
+
+; These tests check that we vectorize the index calculations in the
+; gather-reduce pattern shown below. We check cases having i32 and i64
+; subtraction.
+;
+; int gather_reduce_8x16(short *a, short *b, short *g, int n) {
+;   int sum = 0;
+;   for (int i = 0; i < n ; ++i) {
+;     sum += g[*a++ - b[0]]; sum += g[*a++ - b[1]];
+;     sum += g[*a++ - b[2]]; sum += g[*a++ - b[3]];
+;     sum += g[*a++ - b[4]]; sum += g[*a++ - b[5]];
+;     sum += g[*a++ - b[6]]; sum += g[*a++ - b[7]];
+;   }
+;   return sum;
+; }
+
+; CHECK-LABEL: @gather_reduce_8x16_i32
+;
+; CHECK: [[L:%[a-zA-Z0-9.]+]] = load <8 x i16>
+; CHECK: zext <8 x i16> [[L]] to <8 x i32>
+; CHECK: [[S:%[a-zA-Z0-9.]+]] = sub nsw <8 x i32>
+; CHECK: [[X:%[a-zA-Z0-9.]+]] = extractelement <8 x i32> [[S]]
+; CHECK: sext i32 [[X]] to i64
+;
+define i32 @gather_reduce_8x16_i32(i16* nocapture readonly %a, i16* nocapture readonly %b, i16* nocapture readonly %g, i32 %n) {
+entry:
+  %cmp.99 = icmp sgt i32 %n, 0
+  br i1 %cmp.99, label %for.body.preheader, label %for.cond.cleanup
+
+for.body.preheader:
+  br label %for.body
+
+for.cond.cleanup.loopexit:
+  br label %for.cond.cleanup
+
+for.cond.cleanup:
+  %sum.0.lcssa = phi i32 [ 0, %entry ], [ %add66, %for.cond.cleanup.loopexit ]
+  ret i32 %sum.0.lcssa
+
+for.body:
+  %i.0103 = phi i32 [ %inc, %for.body ], [ 0, %for.body.preheader ]
+  %sum.0102 = phi i32 [ %add66, %for.body ], [ 0, %for.body.preheader ]
+  %a.addr.0101 = phi i16* [ %incdec.ptr58, %for.body ], [ %a, %for.body.preheader ]
+  %incdec.ptr = getelementptr inbounds i16, i16* %a.addr.0101, i64 1
+  %0 = load i16, i16* %a.addr.0101, align 2
+  %conv = zext i16 %0 to i32
+  %incdec.ptr1 = getelementptr inbounds i16, i16* %b, i64 1
+  %1 = load i16, i16* %b, align 2
+  %conv2 = zext i16 %1 to i32
+  %sub = sub nsw i32 %conv, %conv2
+  %arrayidx = getelementptr inbounds i16, i16* %g, i32 %sub
+  %2 = load i16, i16* %arrayidx, align 2
+  %conv3 = zext i16 %2 to i32
+  %add = add nsw i32 %conv3, %sum.0102
+  %incdec.ptr4 = getelementptr inbounds i16, i16* %a.addr.0101, i64 2
+  %3 = load i16, i16* %incdec.ptr, align 2
+  %conv5 = zext i16 %3 to i32
+  %incdec.ptr6 = getelementptr inbounds i16, i16* %b, i64 2
+  %4 = load i16, i16* %incdec.ptr1, align 2
+  %conv7 = zext i16 %4 to i32
+  %sub8 = sub nsw i32 %conv5, %conv7
+  %arrayidx10 = getelementptr inbounds i16, i16* %g, i32 %sub8
+  %5 = load i16, i16* %arrayidx10, align 2
+  %conv11 = zext i16 %5 to i32
+  %add12 = add nsw i32 %add, %conv11
+  %incdec.ptr13 = getelementptr inbounds i16, i16* %a.addr.0101, i64 3
+  %6 = load i16, i16* %incdec.ptr4, align 2
+  %conv14 = zext i16 %6 to i32
+  %incdec.ptr15 = getelementptr inbounds i16, i16* %b, i64 3
+  %7 = load i16, i16* %incdec.ptr6, align 2
+  %conv16 = zext i16 %7 to i32
+  %sub17 = sub nsw i32 %conv14, %conv16
+  %arrayidx19 = getelementptr inbounds i16, i16* %g, i32 %sub17
+  %8 = load i16, i16* %arrayidx19, align 2
+  %conv20 = zext i16 %8 to i32
+  %add21 = add nsw i32 %add12, %conv20
+  %incdec.ptr22 = getelementptr inbounds i16, i16* %a.addr.0101, i64 4
+  %9 = load i16, i16* %incdec.ptr13, align 2
+  %conv23 = zext i16 %9 to i32
+  %incdec.ptr24 = getelementptr inbounds i16, i16* %b, i64 4
+  %10 = load i16, i16* %incdec.ptr15, align 2
+  %conv25 = zext i16 %10 to i32
+  %sub26 = sub nsw i32 %conv23, %conv25
+  %arrayidx28 = getelementptr inbounds i16, i16* %g, i32 %sub26
+  %11 = load i16, i16* %arrayidx28, align 2
+  %conv29 = zext i16 %11 to i32
+  %add30 = add nsw i32 %add21, %conv29
+  %incdec.ptr31 = getelementptr inbounds i16, i16* %a.addr.0101, i64 5
+  %12 = load i16, i16* %incdec.ptr22, align 2
+  %conv32 = zext i16 %12 to i32
+  %incdec.ptr33 = getelementptr inbounds i16, i16* %b, i64 5
+  %13 = load i16, i16* %incdec.ptr24, align 2
+  %conv34 = zext i16 %13 to i32
+  %sub35 = sub nsw i32 %conv32, %conv34
+  %arrayidx37 = getelementptr inbounds i16, i16* %g, i32 %sub35
+  %14 = load i16, i16* %arrayidx37, align 2
+  %conv38 = zext i16 %14 to i32
+  %add39 = add nsw i32 %add30, %conv38
+  %incdec.ptr40 = getelementptr inbounds i16, i16* %a.addr.0101, i64 6
+  %15 = load i16, i16* %incdec.ptr31, align 2
+  %conv41 = zext i16 %15 to i32
+  %incdec.ptr42 = getelementptr inbounds i16, i16* %b, i64 6
+  %16 = load i16, i16* %incdec.ptr33, align 2
+  %conv43 = zext i16 %16 to i32
+  %sub44 = sub nsw i32 %conv41, %conv43
+  %arrayidx46 = getelementptr inbounds i16, i16* %g, i32 %sub44
+  %17 = load i16, i16* %arrayidx46, align 2
+  %conv47 = zext i16 %17 to i32
+  %add48 = add nsw i32 %add39, %conv47
+  %incdec.ptr49 = getelementptr inbounds i16, i16* %a.addr.0101, i64 7
+  %18 = load i16, i16* %incdec.ptr40, align 2
+  %conv50 = zext i16 %18 to i32
+  %incdec.ptr51 = getelementptr inbounds i16, i16* %b, i64 7
+  %19 = load i16, i16* %incdec.ptr42, align 2
+  %conv52 = zext i16 %19 to i32
+  %sub53 = sub nsw i32 %conv50, %conv52
+  %arrayidx55 = getelementptr inbounds i16, i16* %g, i32 %sub53
+  %20 = load i16, i16* %arrayidx55, align 2
+  %conv56 = zext i16 %20 to i32
+  %add57 = add nsw i32 %add48, %conv56
+  %incdec.ptr58 = getelementptr inbounds i16, i16* %a.addr.0101, i64 8
+  %21 = load i16, i16* %incdec.ptr49, align 2
+  %conv59 = zext i16 %21 to i32
+  %22 = load i16, i16* %incdec.ptr51, align 2
+  %conv61 = zext i16 %22 to i32
+  %sub62 = sub nsw i32 %conv59, %conv61
+  %arrayidx64 = getelementptr inbounds i16, i16* %g, i32 %sub62
+  %23 = load i16, i16* %arrayidx64, align 2
+  %conv65 = zext i16 %23 to i32
+  %add66 = add nsw i32 %add57, %conv65
+  %inc = add nuw nsw i32 %i.0103, 1
+  %exitcond = icmp eq i32 %inc, %n
+  br i1 %exitcond, label %for.cond.cleanup.loopexit, label %for.body
+}
+
+; CHECK-LABEL: @gather_reduce_8x16_i64
+;
+; CHECK-NOT: load <8 x i16>
+;
+; FIXME: We are currently unable to vectorize the case with i64 subtraction
+;        because the zero extensions are too expensive. The solution here is to
+;        convert the i64 subtractions to i32 subtractions during vectorization.
+;        This would then match the case above.
+;
+define i32 @gather_reduce_8x16_i64(i16* nocapture readonly %a, i16* nocapture readonly %b, i16* nocapture readonly %g, i32 %n) {
+entry:
+  %cmp.99 = icmp sgt i32 %n, 0
+  br i1 %cmp.99, label %for.body.preheader, label %for.cond.cleanup
+
+for.body.preheader:
+  br label %for.body
+
+for.cond.cleanup.loopexit:
+  br label %for.cond.cleanup
+
+for.cond.cleanup:
+  %sum.0.lcssa = phi i32 [ 0, %entry ], [ %add66, %for.cond.cleanup.loopexit ]
+  ret i32 %sum.0.lcssa
+
+for.body:
+  %i.0103 = phi i32 [ %inc, %for.body ], [ 0, %for.body.preheader ]
+  %sum.0102 = phi i32 [ %add66, %for.body ], [ 0, %for.body.preheader ]
+  %a.addr.0101 = phi i16* [ %incdec.ptr58, %for.body ], [ %a, %for.body.preheader ]
+  %incdec.ptr = getelementptr inbounds i16, i16* %a.addr.0101, i64 1
+  %0 = load i16, i16* %a.addr.0101, align 2
+  %conv = zext i16 %0 to i64
+  %incdec.ptr1 = getelementptr inbounds i16, i16* %b, i64 1
+  %1 = load i16, i16* %b, align 2
+  %conv2 = zext i16 %1 to i64
+  %sub = sub nsw i64 %conv, %conv2
+  %arrayidx = getelementptr inbounds i16, i16* %g, i64 %sub
+  %2 = load i16, i16* %arrayidx, align 2
+  %conv3 = zext i16 %2 to i32
+  %add = add nsw i32 %conv3, %sum.0102
+  %incdec.ptr4 = getelementptr inbounds i16, i16* %a.addr.0101, i64 2
+  %3 = load i16, i16* %incdec.ptr, align 2
+  %conv5 = zext i16 %3 to i64
+  %incdec.ptr6 = getelementptr inbounds i16, i16* %b, i64 2
+  %4 = load i16, i16* %incdec.ptr1, align 2
+  %conv7 = zext i16 %4 to i64
+  %sub8 = sub nsw i64 %conv5, %conv7
+  %arrayidx10 = getelementptr inbounds i16, i16* %g, i64 %sub8
+  %5 = load i16, i16* %arrayidx10, align 2
+  %conv11 = zext i16 %5 to i32
+  %add12 = add nsw i32 %add, %conv11
+  %incdec.ptr13 = getelementptr inbounds i16, i16* %a.addr.0101, i64 3
+  %6 = load i16, i16* %incdec.ptr4, align 2
+  %conv14 = zext i16 %6 to i64
+  %incdec.ptr15 = getelementptr inbounds i16, i16* %b, i64 3
+  %7 = load i16, i16* %incdec.ptr6, align 2
+  %conv16 = zext i16 %7 to i64
+  %sub17 = sub nsw i64 %conv14, %conv16
+  %arrayidx19 = getelementptr inbounds i16, i16* %g, i64 %sub17
+  %8 = load i16, i16* %arrayidx19, align 2
+  %conv20 = zext i16 %8 to i32
+  %add21 = add nsw i32 %add12, %conv20
+  %incdec.ptr22 = getelementptr inbounds i16, i16* %a.addr.0101, i64 4
+  %9 = load i16, i16* %incdec.ptr13, align 2
+  %conv23 = zext i16 %9 to i64
+  %incdec.ptr24 = getelementptr inbounds i16, i16* %b, i64 4
+  %10 = load i16, i16* %incdec.ptr15, align 2
+  %conv25 = zext i16 %10 to i64
+  %sub26 = sub nsw i64 %conv23, %conv25
+  %arrayidx28 = getelementptr inbounds i16, i16* %g, i64 %sub26
+  %11 = load i16, i16* %arrayidx28, align 2
+  %conv29 = zext i16 %11 to i32
+  %add30 = add nsw i32 %add21, %conv29
+  %incdec.ptr31 = getelementptr inbounds i16, i16* %a.addr.0101, i64 5
+  %12 = load i16, i16* %incdec.ptr22, align 2
+  %conv32 = zext i16 %12 to i64
+  %incdec.ptr33 = getelementptr inbounds i16, i16* %b, i64 5
+  %13 = load i16, i16* %incdec.ptr24, align 2
+  %conv34 = zext i16 %13 to i64
+  %sub35 = sub nsw i64 %conv32, %conv34
+  %arrayidx37 = getelementptr inbounds i16, i16* %g, i64 %sub35
+  %14 = load i16, i16* %arrayidx37, align 2
+  %conv38 = zext i16 %14 to i32
+  %add39 = add nsw i32 %add30, %conv38
+  %incdec.ptr40 = getelementptr inbounds i16, i16* %a.addr.0101, i64 6
+  %15 = load i16, i16* %incdec.ptr31, align 2
+  %conv41 = zext i16 %15 to i64
+  %incdec.ptr42 = getelementptr inbounds i16, i16* %b, i64 6
+  %16 = load i16, i16* %incdec.ptr33, align 2
+  %conv43 = zext i16 %16 to i64
+  %sub44 = sub nsw i64 %conv41, %conv43
+  %arrayidx46 = getelementptr inbounds i16, i16* %g, i64 %sub44
+  %17 = load i16, i16* %arrayidx46, align 2
+  %conv47 = zext i16 %17 to i32
+  %add48 = add nsw i32 %add39, %conv47
+  %incdec.ptr49 = getelementptr inbounds i16, i16* %a.addr.0101, i64 7
+  %18 = load i16, i16* %incdec.ptr40, align 2
+  %conv50 = zext i16 %18 to i64
+  %incdec.ptr51 = getelementptr inbounds i16, i16* %b, i64 7
+  %19 = load i16, i16* %incdec.ptr42, align 2
+  %conv52 = zext i16 %19 to i64
+  %sub53 = sub nsw i64 %conv50, %conv52
+  %arrayidx55 = getelementptr inbounds i16, i16* %g, i64 %sub53
+  %20 = load i16, i16* %arrayidx55, align 2
+  %conv56 = zext i16 %20 to i32
+  %add57 = add nsw i32 %add48, %conv56
+  %incdec.ptr58 = getelementptr inbounds i16, i16* %a.addr.0101, i64 8
+  %21 = load i16, i16* %incdec.ptr49, align 2
+  %conv59 = zext i16 %21 to i64
+  %22 = load i16, i16* %incdec.ptr51, align 2
+  %conv61 = zext i16 %22 to i64
+  %sub62 = sub nsw i64 %conv59, %conv61
+  %arrayidx64 = getelementptr inbounds i16, i16* %g, i64 %sub62
+  %23 = load i16, i16* %arrayidx64, align 2
+  %conv65 = zext i16 %23 to i32
+  %add66 = add nsw i32 %add57, %conv65
+  %inc = add nuw nsw i32 %i.0103, 1
+  %exitcond = icmp eq i32 %inc, %n
+  br i1 %exitcond, label %for.cond.cleanup.loopexit, label %for.body
+}

llvm/test/Transforms/SLPVectorizer/AArch64/getelementptr.ll

@@ -0,0 +1,111 @@
+; RUN: opt -S -slp-vectorizer -slp-threshold=-18 -dce -instcombine < %s | FileCheck %s
+
+target datalayout = "e-m:e-i32:64-i128:128-n32:64-S128"
+target triple = "aarch64--linux-gnu"
+
+; These tests check that we remove from consideration pairs of seed
+; getelementptrs when they are known to have a constant difference. Such pairs
+; are likely not good candidates for vectorization since one can be computed
+; from the other. We use an unprofitable threshold to force vectorization.
+;
+; int getelementptr(int *g, int n, int w, int x, int y, int z) {
+;   int sum = 0;
+;   for (int i = 0; i < n ; ++i) {
+;     sum += g[2*i + w]; sum += g[2*i + x];
+;     sum += g[2*i + y]; sum += g[2*i + z];
+;   }
+;   return sum;
+; }
+;
+
+; CHECK-LABEL: @getelementptr_4x32
+;
+; CHECK: [[A:%[a-zA-Z0-9.]+]] = add nsw <4 x i32>
+; CHECK: [[X:%[a-zA-Z0-9.]+]] = extractelement <4 x i32> [[A]]
+; CHECK: sext i32 [[X]] to i64
+;
+define i32 @getelementptr_4x32(i32* nocapture readonly %g, i32 %n, i32 %x, i32 %y, i32 %z) {
+entry:
+  %cmp31 = icmp sgt i32 %n, 0
+  br i1 %cmp31, label %for.body.preheader, label %for.cond.cleanup
+
+for.body.preheader:
+  br label %for.body
+
+for.cond.cleanup.loopexit:
+  br label %for.cond.cleanup
+
+for.cond.cleanup:
+  %sum.0.lcssa = phi i32 [ 0, %entry ], [ %add16, %for.cond.cleanup.loopexit ]
+  ret i32 %sum.0.lcssa
+
+for.body:
+  %indvars.iv = phi i32 [ 0, %for.body.preheader ], [ %indvars.iv.next, %for.body ]
+  %sum.032 = phi i32 [ 0, %for.body.preheader ], [ %add16, %for.body ]
+  %t4 = shl nsw i32 %indvars.iv, 1
+  %t5 = add nsw i32 %t4, 0
+  %arrayidx = getelementptr inbounds i32, i32* %g, i32 %t5
+  %t6 = load i32, i32* %arrayidx, align 4
+  %add1 = add nsw i32 %t6, %sum.032
+  %t7 = add nsw i32 %t4, %x
+  %arrayidx5 = getelementptr inbounds i32, i32* %g, i32 %t7
+  %t8 = load i32, i32* %arrayidx5, align 4
+  %add6 = add nsw i32 %add1, %t8
+  %t9 = add nsw i32 %t4, %y
+  %arrayidx10 = getelementptr inbounds i32, i32* %g, i32 %t9
+  %t10 = load i32, i32* %arrayidx10, align 4
+  %add11 = add nsw i32 %add6, %t10
+  %t11 = add nsw i32 %t4, %z
+  %arrayidx15 = getelementptr inbounds i32, i32* %g, i32 %t11
+  %t12 = load i32, i32* %arrayidx15, align 4
+  %add16 = add nsw i32 %add11, %t12
+  %indvars.iv.next = add nuw nsw i32 %indvars.iv, 1
+  %exitcond = icmp eq i32 %indvars.iv.next , %n
+  br i1 %exitcond, label %for.cond.cleanup.loopexit, label %for.body
+}
+
+; CHECK-LABEL: @getelementptr_2x32
+;
+; CHECK: [[A:%[a-zA-Z0-9.]+]] = add nsw <2 x i32>
+; CHECK: [[X:%[a-zA-Z0-9.]+]] = extractelement <2 x i32> [[A]]
+; CHECK: sext i32 [[X]] to i64
+;
+define i32 @getelementptr_2x32(i32* nocapture readonly %g, i32 %n, i32 %x, i32 %y, i32 %z) {
+entry:
+  %cmp31 = icmp sgt i32 %n, 0
+  br i1 %cmp31, label %for.body.preheader, label %for.cond.cleanup
+
+for.body.preheader:
+  br label %for.body
+
+for.cond.cleanup.loopexit:
+  br label %for.cond.cleanup
+
+for.cond.cleanup:
+  %sum.0.lcssa = phi i32 [ 0, %entry ], [ %add16, %for.cond.cleanup.loopexit ]
+  ret i32 %sum.0.lcssa
+
+for.body:
+  %indvars.iv = phi i32 [ 0, %for.body.preheader ], [ %indvars.iv.next, %for.body ]
+  %sum.032 = phi i32 [ 0, %for.body.preheader ], [ %add16, %for.body ]
+  %t4 = shl nsw i32 %indvars.iv, 1
+  %t5 = add nsw i32 %t4, 0
+  %arrayidx = getelementptr inbounds i32, i32* %g, i32 %t5
+  %t6 = load i32, i32* %arrayidx, align 4
+  %add1 = add nsw i32 %t6, %sum.032
+  %t7 = add nsw i32 %t4, 1
+  %arrayidx5 = getelementptr inbounds i32, i32* %g, i32 %t7
+  %t8 = load i32, i32* %arrayidx5, align 4
+  %add6 = add nsw i32 %add1, %t8
+  %t9 = add nsw i32 %t4, %y
+  %arrayidx10 = getelementptr inbounds i32, i32* %g, i32 %t9
+  %t10 = load i32, i32* %arrayidx10, align 4
+  %add11 = add nsw i32 %add6, %t10
+  %t11 = add nsw i32 %t4, %z
+  %arrayidx15 = getelementptr inbounds i32, i32* %g, i32 %t11
+  %t12 = load i32, i32* %arrayidx15, align 4
+  %add16 = add nsw i32 %add11, %t12
+  %indvars.iv.next = add nuw nsw i32 %indvars.iv, 1
+  %exitcond = icmp eq i32 %indvars.iv.next , %n
+  br i1 %exitcond, label %for.cond.cleanup.loopexit, label %for.body
+}