Index: llvm/trunk/lib/Target/X86/X86ISelDAGToDAG.cpp
===================================================================
--- llvm/trunk/lib/Target/X86/X86ISelDAGToDAG.cpp
+++ llvm/trunk/lib/Target/X86/X86ISelDAGToDAG.cpp
@@ -1513,12 +1513,15 @@
                                           SDValue &Scale, SDValue &Index,
                                           SDValue &Disp, SDValue &Segment,
                                           SDValue &PatternNodeWithChain) {
-  if (N.getOpcode() == ISD::SCALAR_TO_VECTOR) {
+  // Need to make sure that the SCALAR_TO_VECTOR and load are both only used
+  // once. Otherwise the load might get duplicated and the chain output of the
+  // duplicate load will not be observed by all dependencies.
+  if (N.getOpcode() == ISD::SCALAR_TO_VECTOR && N.getNode()->hasOneUse()) {
     PatternNodeWithChain = N.getOperand(0);
     if (ISD::isNON_EXTLoad(PatternNodeWithChain.getNode()) &&
         PatternNodeWithChain.hasOneUse() &&
-        IsProfitableToFold(N.getOperand(0), N.getNode(), Root) &&
-        IsLegalToFold(N.getOperand(0), N.getNode(), Root, OptLevel)) {
+        IsProfitableToFold(PatternNodeWithChain, N.getNode(), Root) &&
+        IsLegalToFold(PatternNodeWithChain, N.getNode(), Root, OptLevel)) {
       LoadSDNode *LD = cast<LoadSDNode>(PatternNodeWithChain);
       if (!selectAddr(LD, LD->getBasePtr(), Base, Scale, Index, Disp, Segment))
         return false;
Index: llvm/trunk/test/CodeGen/X86/vec_ss_load_fold.ll
===================================================================
--- llvm/trunk/test/CodeGen/X86/vec_ss_load_fold.ll
+++ llvm/trunk/test/CodeGen/X86/vec_ss_load_fold.ll
@@ -381,33 +381,37 @@
 ; X32-LABEL: double_fold:
 ; X32:       ## BB#0: ## %entry
 ; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
-; X32-NEXT:    movaps %xmm0, %xmm1
-; X32-NEXT:    minss (%eax), %xmm1
-; X32-NEXT:    maxss (%eax), %xmm0
-; X32-NEXT:    addps %xmm1, %xmm0
+; X32-NEXT:    movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
+; X32-NEXT:    movaps %xmm0, %xmm2
+; X32-NEXT:    minss %xmm1, %xmm2
+; X32-NEXT:    maxss %xmm1, %xmm0
+; X32-NEXT:    addps %xmm2, %xmm0
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: double_fold:
 ; X64:       ## BB#0: ## %entry
-; X64-NEXT:    movaps %xmm0, %xmm1
-; X64-NEXT:    minss (%rdi), %xmm1
-; X64-NEXT:    maxss (%rdi), %xmm0
-; X64-NEXT:    addps %xmm1, %xmm0
+; X64-NEXT:    movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
+; X64-NEXT:    movaps %xmm0, %xmm2
+; X64-NEXT:    minss %xmm1, %xmm2
+; X64-NEXT:    maxss %xmm1, %xmm0
+; X64-NEXT:    addps %xmm2, %xmm0
 ; X64-NEXT:    retq
 ;
 ; X32_AVX-LABEL: double_fold:
 ; X32_AVX:       ## BB#0: ## %entry
 ; X32_AVX-NEXT:    movl {{[0-9]+}}(%esp), %eax
-; X32_AVX-NEXT:    vminss (%eax), %xmm0, %xmm1
-; X32_AVX-NEXT:    vmaxss (%eax), %xmm0, %xmm0
-; X32_AVX-NEXT:    vaddps %xmm0, %xmm1, %xmm0
+; X32_AVX-NEXT:    vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
+; X32_AVX-NEXT:    vminss %xmm1, %xmm0, %xmm2
+; X32_AVX-NEXT:    vmaxss %xmm1, %xmm0, %xmm0
+; X32_AVX-NEXT:    vaddps %xmm0, %xmm2, %xmm0
 ; X32_AVX-NEXT:    retl
 ;
 ; X64_AVX-LABEL: double_fold:
 ; X64_AVX:       ## BB#0: ## %entry
-; X64_AVX-NEXT:    vminss (%rdi), %xmm0, %xmm1
-; X64_AVX-NEXT:    vmaxss (%rdi), %xmm0, %xmm0
-; X64_AVX-NEXT:    vaddps %xmm0, %xmm1, %xmm0
+; X64_AVX-NEXT:    vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
+; X64_AVX-NEXT:    vminss %xmm1, %xmm0, %xmm2
+; X64_AVX-NEXT:    vmaxss %xmm1, %xmm0, %xmm0
+; X64_AVX-NEXT:    vaddps %xmm0, %xmm2, %xmm0
 ; X64_AVX-NEXT:    retq
 entry:
   %0 = load float, float* %x, align 1