// 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.
+
+ // Caches for hasPredecessorHelper
+ SmallPtrSet<const SDNode *, 32> Visited;
+ SmallVector<const SDNode *, 16> Worklist;
+
SDValue StackPtr, Ch;
for (SDNode::use_iterator UI = Vec.getNode()->use_begin(),
UE = Vec.getNode()->use_end(); UI != UE; ++UI) {
if (!ST->getChain().reachesChainWithoutSideEffects(DAG.getEntryNode()))
continue;
+ // If the index is dependent on the store we will introduce a cycle when
+ // creating the load (the load uses the index, and by replacing the chain
+ // we will make the index dependent on the load).
+ if (Idx.getNode()->hasPredecessorHelper(ST, Visited, Worklist))
+ continue;
+
StackPtr = ST->getBasePtr();
Ch = SDValue(ST, 0);
break;
--- /dev/null
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown | FileCheck %s
+
+; When the extractelement is converted to a load the store can be re-used.
+; This will, however, introduce a cycle into the selection DAG (the load
+; of the extractelement index is dependent on the store, and so after the
+; conversion it becomes dependent on the new load, which is dependent on
+; the index). Make sure we skip the store, and conservatively instead
+; use a store to the stack.
+
+define float @foo(i32* %i, <4 x float>* %v) {
+; CHECK-LABEL: foo:
+; CHECK: movaps %xmm0, -[[OFFSET:[0-9]+]](%rsp)
+; CHECK: movss -[[OFFSET]](%rsp,{{.*}}), %xmm0 {{.*}}
+; CHECK-NEXT: retq
+ %1 = load <4 x float>, <4 x float>* %v, align 16
+ %mul = fmul <4 x float> %1, %1
+ store <4 x float> %mul, <4 x float>* %v, align 16
+ %2 = load i32, i32* %i, align 4
+ %vecext = extractelement <4 x float> %mul, i32 %2
+ ret float %vecext
+}