1 files changed, 35 insertions, 0 deletions
diff --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp
index 159ce60af45..4331cb9c231 100644
--- a/llvm/lib/Target/X86/X86ISelLowering.cpp
+++ b/llvm/lib/Target/X86/X86ISelLowering.cpp
@@ -40179,6 +40179,41 @@ static SDValue combineStore(SDNode *N, SelectionDAG &DAG,
                              MVT::v16i8, St->getMemOperand());
   }
 
+  // Look for a truncating store to a less than 128 bit vector that has been
+  // truncated from an any_extend_inreg from a 128 bit vector with the same
+  // element size. We can use a 64/32/16-bit extractelement and store that.
+  // Disabling this when widening legalization is in effect since the trunc
+  // store would have been unlikely to be created in that case. Only doing this
+  // when truncstore is legal since it would otherwise be decomposed below and
+  // then combined away.
+  if (St->isTruncatingStore() && TLI.isTruncStoreLegal(VT, StVT) &&
+      StoredVal.getOpcode() == ISD::ANY_EXTEND_VECTOR_INREG &&
+      StoredVal.getValueType().is128BitVector() &&
+      !ExperimentalVectorWideningLegalization) {
+    EVT OrigVT = StoredVal.getOperand(0).getValueType();
+    if (OrigVT.is128BitVector() &&
+        OrigVT.getVectorElementType() == StVT.getVectorElementType()) {
+      unsigned StoreSize = StVT.getSizeInBits();
+      assert((128 % StoreSize == 0) && "Unexpected store size!");
+      MVT IntVT = MVT::getIntegerVT(StoreSize);
+      MVT CastVT = MVT::getVectorVT(IntVT, 128 / StoreSize);
+      StoredVal = DAG.getBitcast(CastVT, StoredVal.getOperand(0));
+      // Use extract_store for the 64-bit case to support 32-bit targets.
+      if (IntVT == MVT::i64) {
+        SDVTList Tys = DAG.getVTList(MVT::Other);
+        SDValue Ops[] = {St->getChain(), StoredVal, St->getBasePtr()};
+        return DAG.getMemIntrinsicNode(X86ISD::VEXTRACT_STORE, dl, Tys, Ops,
+                                       IntVT, St->getMemOperand());
+      }
+
+      // Otherwise just use an extract and store.
+      StoredVal = DAG.getNode(ISD::EXTRACT_VECTOR_ELT, dl, IntVT, StoredVal,
+                              DAG.getIntPtrConstant(0, dl));
+      return DAG.getStore(St->getChain(), dl, StoredVal, St->getBasePtr(),
+                          St->getMemOperand());
+    }
+  }
+
   // Optimize trunc store (of multiple scalars) to shuffle and store.
   // First, pack all of the elements in one place. Next, store to memory
   // in fewer chunks.