2 files changed, 47 insertions, 14 deletions

diff --git a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
index ad60b8244f1..01ca2884d03 100644
--- a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -11072,8 +11072,7 @@ bool DAGCombiner::MergeConsecutiveStores(StoreSDNode* St) {
   if (ElementSizeBytes * 8 != MemVT.getSizeInBits())
     return false;
 
-  // Don't merge vectors into wider inputs.
-  if (MemVT.isVector() || !MemVT.isSimple())
+  if (!MemVT.isSimple())
     return false;
 
   // Perform an early exit check. Do not bother looking at stored values that
@@ -11082,9 +11081,16 @@ bool DAGCombiner::MergeConsecutiveStores(StoreSDNode* St) {
   bool IsLoadSrc = isa<LoadSDNode>(StoredVal);
   bool IsConstantSrc = isa<ConstantSDNode>(StoredVal) ||
                        isa<ConstantFPSDNode>(StoredVal);
-  bool IsExtractVecEltSrc = (StoredVal.getOpcode() == ISD::EXTRACT_VECTOR_ELT);
+  bool IsExtractVecSrc = (StoredVal.getOpcode() == ISD::EXTRACT_VECTOR_ELT ||
+                          StoredVal.getOpcode() == ISD::EXTRACT_SUBVECTOR);
 
-  if (!IsConstantSrc && !IsLoadSrc && !IsExtractVecEltSrc)
+  if (!IsConstantSrc && !IsLoadSrc && !IsExtractVecSrc)
+    return false;
+
+  // Don't merge vectors into wider vectors if the source data comes from loads.
+  // TODO: This restriction can be lifted by using logic similar to the
+  // ExtractVecSrc case.
+  if (MemVT.isVector() && IsLoadSrc)
     return false;
 
   // Only look at ends of store sequences.
@@ -11217,29 +11223,36 @@ bool DAGCombiner::MergeConsecutiveStores(StoreSDNode* St) {
 
   // When extracting multiple vector elements, try to store them
   // in one vector store rather than a sequence of scalar stores.
-  if (IsExtractVecEltSrc) {
-    unsigned NumElem = 0;
+  if (IsExtractVecSrc) {
+    unsigned NumStoresToMerge = 0;
+    bool IsVec = MemVT.isVector();
     for (unsigned i = 0; i < LastConsecutiveStore + 1; ++i) {
       StoreSDNode *St  = cast<StoreSDNode>(StoreNodes[i].MemNode);
-      SDValue StoredVal = St->getValue();
+      unsigned StoreValOpcode = St->getValue().getOpcode();
       // This restriction could be loosened.
       // Bail out if any stored values are not elements extracted from a vector.
       // It should be possible to handle mixed sources, but load sources need
       // more careful handling (see the block of code below that handles
       // consecutive loads).
-      if (StoredVal.getOpcode() != ISD::EXTRACT_VECTOR_ELT)
+      if (StoreValOpcode != ISD::EXTRACT_VECTOR_ELT &&
+          StoreValOpcode != ISD::EXTRACT_SUBVECTOR)
         return false;
 
       // Find a legal type for the vector store.
-      EVT Ty = EVT::getVectorVT(Context, MemVT, i+1);
+      unsigned Elts = i + 1;
+      if (IsVec) {
+        // When merging vector stores, get the total number of elements.
+        Elts *= MemVT.getVectorNumElements();
+      }
+      EVT Ty = EVT::getVectorVT(*DAG.getContext(), MemVT.getScalarType(), Elts);
       bool IsFast;
       if (TLI.isTypeLegal(Ty) &&
           TLI.allowsMemoryAccess(Context, DL, Ty, FirstStoreAS,
                                  FirstStoreAlign, &IsFast) && IsFast)
-        NumElem = i + 1;
+        NumStoresToMerge = i + 1;
     }
 
-    return MergeStoresOfConstantsOrVecElts(StoreNodes, MemVT, NumElem,
+    return MergeStoresOfConstantsOrVecElts(StoreNodes, MemVT, NumStoresToMerge,
                                            false, true);
   }
 
diff --git a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
index cba7c5b5502..f27c3266138 100644
--- a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
+++ b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
@@ -796,9 +796,25 @@ bool AArch64TargetLowering::allowsMisalignedMemoryAccesses(EVT VT,
                                                            bool *Fast) const {
   if (Subtarget->requiresStrictAlign())
     return false;
-  // FIXME: True for Cyclone, but not necessary others.
-  if (Fast)
-    *Fast = true;
+
+  // FIXME: This is mostly true for Cyclone, but not necessarily others.
+  if (Fast) {
+    // FIXME: Define an attribute for slow unaligned accesses instead of
+    // relying on the CPU type as a proxy.
+    // On Cyclone, unaligned 128-bit stores are slow.
+    *Fast = !Subtarget->isCyclone() || VT.getStoreSize() != 16 ||
+            // See comments in performSTORECombine() for more details about
+            // these conditions.
+
+            // Code that uses clang vector extensions can mark that it
+            // wants unaligned accesses to be treated as fast by
+            // underspecifying alignment to be 1 or 2.
+            Align <= 2 ||
+
+            // Disregard v2i64. Memcpy lowering produces those and splitting
+            // them regresses performance on micro-benchmarks and olden/bh.
+            VT == MVT::v2i64;
+  }
   return true;
 }
 
@@ -8435,6 +8451,10 @@ static SDValue performSTORECombine(SDNode *N,
   if (S->isVolatile())
     return SDValue();
 
+  // FIXME: The logic for deciding if an unaligned store should be split should
+  // be included in TLI.allowsMisalignedMemoryAccesses(), and there should be
+  // a call to that function here.
+
   // Cyclone has bad performance on unaligned 16B stores when crossing line and
   // page boundaries. We want to split such stores.
   if (!Subtarget->isCyclone())