Make use of previously generated stores in SelectionDAGLegalize::ExpandExtractFromVectorThroughStack

When expanding EXTRACT_VECTOR_ELT and EXTRACT_SUBVECTOR using
SelectionDAGLegalize::ExpandExtractFromVectorThroughStack, we store the entire
vector and then load the piece we want. This is fine in isolation, but
generating a new store (and corresponding stack slot) for each extraction ends
up producing code of poor quality. When we scalarize a vector operation (using
SelectionDAG::UnrollVectorOp for example) we generate one EXTRACT_VECTOR_ELT
for each element in the vector. This used to generate one stored copy of the
vector for each element in the vector. Now we search the uses of the vector for
a suitable store before generating a new one, which results in much more
efficient scalarization code.

llvm-svn: 205153

llvm/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp

@@ -1394,10 +1394,39 @@ SDValue SelectionDAGLegalize::ExpandExtractFromVectorThroughStack(SDValue Op) {
   SDValue Vec = Op.getOperand(0);
   SDValue Idx = Op.getOperand(1);
   SDLoc dl(Op);
-  // Store the value to a temporary stack slot, then LOAD the returned part.
-  SDValue StackPtr = DAG.CreateStackTemporary(Vec.getValueType());
-  SDValue Ch = DAG.getStore(DAG.getEntryNode(), dl, Vec, StackPtr,
-                            MachinePointerInfo(), false, false, 0);
+
+  // Before we generate a new store to a temporary stack slot, see if there is
+  // already one that we can use. There often is because when we scalarize
+  // vector operations (using SelectionDAG::UnrollVectorOp for example) a whole
+  // series of EXTRACT_VECTOR_ELT nodes are generated, one for each element in
+  // the vector. If all are expanded here, we don't want one store per vector
+  // element.
+  SDValue StackPtr, Ch;
+  for (SDNode::use_iterator UI = Vec.getNode()->use_begin(),
+       UE = Vec.getNode()->use_end(); UI != UE; ++UI) {
+    SDNode *User = *UI;
+    if (StoreSDNode *ST = dyn_cast<StoreSDNode>(User)) {
+      if (ST->isIndexed() || ST->isTruncatingStore() ||
+          ST->getValue() != Vec)
+        continue;
+
+      // Make sure that nothing else could have stored into the destination of
+      // this store.
+      if (!ST->getChain().reachesChainWithoutSideEffects(DAG.getEntryNode()))
+        continue;
+
+      StackPtr = ST->getBasePtr();
+      Ch = SDValue(ST, 0);
+      break;
+    }
+  }
+
+  if (!Ch.getNode()) {
+    // Store the value to a temporary stack slot, then LOAD the returned part.
+    StackPtr = DAG.CreateStackTemporary(Vec.getValueType());
+    Ch = DAG.getStore(DAG.getEntryNode(), dl, Vec, StackPtr,
+                      MachinePointerInfo(), false, false, 0);
+  }
 
   // Add the offset to the index.
   unsigned EltSize =

llvm/test/CodeGen/PowerPC/vsx.ll

@@ -281,6 +281,12 @@ define <2 x i64> @test26(<2 x i64> %a, <2 x i64> %b) {
   ret <2 x i64> %v
 
 ; CHECK-LABEL: @test26
+
+; Make sure we use only two stores (one for each operand).
+; CHECK: stxvd2x 35,
+; CHECK: stxvd2x 34,
+; CHECK-NOT: stxvd2x
+
 ; FIXME: The code quality here is not good; just make sure we do something for now.
 ; CHECK: add
 ; CHECK: add