Index: lib/CodeGen/SelectionDAG/DAGCombiner.cpp
===================================================================
--- lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -12556,9 +12556,6 @@
     LoadSDNode *Ld = dyn_cast<LoadSDNode>(St->getValue());
     if (!Ld) break;
 
-    // Loads must only have one use.
-    if (!Ld->hasNUsesOfValue(1, 0))
-      break;
 
     // The memory operands must not be volatile.
     if (Ld->isVolatile() || Ld->isIndexed())
@@ -12568,9 +12565,6 @@
     if (Ld->getExtensionType() != ISD::NON_EXTLOAD)
       break;
 
-    // The stored memory type must be the same.
-    if (Ld->getMemoryVT() != MemVT)
-      break;
 
     BaseIndexOffset LdPtr = BaseIndexOffset::match(Ld->getBasePtr(), DAG);
     // If this is not the first ptr that we check.
@@ -12703,8 +12697,24 @@
   // Transfer chain users from old loads to the new load.
   for (unsigned i = 0; i < NumElem; ++i) {
     LoadSDNode *Ld = cast<LoadSDNode>(LoadNodes[i].MemNode);
-    DAG.ReplaceAllUsesOfValueWith(SDValue(Ld, 1),
-                                  SDValue(NewLoad.getNode(), 1));
+    if (SDValue(Ld, 0).hasOneUse()) {
+      // Only the original store used value so just replace chain.
+      DAG.ReplaceAllUsesOfValueWith(SDValue(Ld, 1),
+                                    SDValue(NewLoad.getNode(), 1));
+    } else {
+      // Multiple uses exist. Keep the old load in line with the new load.
+      SDValue Token0 =
+          DAG.getNode(ISD::TokenFactor, SDLoc(Ld), MVT::Other, SDValue(Ld, 1),
+                      SDValue(NewLoad.getNode(), 1));
+      // Don't cleanup Ld yet. This changes Token0 first argument to itself.
+      CombineTo(Ld, SDValue(Ld, 0), Token0, false);
+      SDValue Token =
+          DAG.getNode(ISD::TokenFactor, SDLoc(Ld), MVT::Other, SDValue(Ld, 1),
+                      SDValue(NewLoad.getNode(), 1));
+      // Reset Token0's input from itself to Ld's output chain.
+      CombineTo(Token0.getNode(), Token);
+      AddToWorklist(Ld);
+    }
   }
 
   // Replace the all stores with the new store.
Index: test/CodeGen/X86/merge_store_duplicated_loads.ll
===================================================================
--- test/CodeGen/X86/merge_store_duplicated_loads.ll
+++ test/CodeGen/X86/merge_store_duplicated_loads.ll
@@ -1,18 +1,15 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc %s -mtriple=x86_64-unknown-linux-gnu -mcpu=corei7 -o - | FileCheck %s
 
-
+; PR32086
 target triple = "x86_64-unknown-linux-gnu"
 
 define void @merge_double(double* noalias nocapture %st, double* noalias nocapture readonly %ld) #0 {
 ; CHECK-LABEL: merge_double:
 ; CHECK:       # BB#0:
-; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
-; CHECK-NEXT:    movsd {{.*#+}} xmm1 = mem[0],zero
-; CHECK-NEXT:    movsd %xmm0, (%rdi)
-; CHECK-NEXT:    movsd %xmm1, 8(%rdi)
-; CHECK-NEXT:    movsd %xmm0, 16(%rdi)
-; CHECK-NEXT:    movsd %xmm1, 24(%rdi)
+; CHECK-NEXT:    movups (%rsi), %xmm0
+; CHECK-NEXT:    movups %xmm0, (%rdi)
+; CHECK-NEXT:    movups %xmm0, 16(%rdi)
 ; CHECK-NEXT:    retq
   %ld_idx1 = getelementptr inbounds double, double* %ld, i64 1
   %ld0 = load double, double* %ld, align 8, !tbaa !2
@@ -32,12 +29,9 @@
 define void @merge_loadstore_int(i64* noalias nocapture readonly %p, i64* noalias nocapture %q) local_unnamed_addr #0 {
 ; CHECK-LABEL: merge_loadstore_int:
 ; CHECK:       # BB#0: # %entry
-; CHECK-NEXT:    movq (%rdi), %rax
-; CHECK-NEXT:    movq 8(%rdi), %rcx
-; CHECK-NEXT:    movq %rax, (%rsi)
-; CHECK-NEXT:    movq %rcx, 8(%rsi)
-; CHECK-NEXT:    movq %rax, 16(%rsi)
-; CHECK-NEXT:    movq %rcx, 24(%rsi)
+; CHECK-NEXT:    movups (%rdi), %xmm0
+; CHECK-NEXT:    movups %xmm0, (%rsi)
+; CHECK-NEXT:    movups %xmm0, 16(%rsi)
 ; CHECK-NEXT:    retq
 entry:
   %0 = load i64, i64* %p, align 8, !tbaa !1
@@ -57,11 +51,9 @@
 ; CHECK-LABEL: merge_loadstore_int_with_extra_use:
 ; CHECK:       # BB#0: # %entry
 ; CHECK-NEXT:    movq (%rdi), %rax
-; CHECK-NEXT:    movq 8(%rdi), %rcx
-; CHECK-NEXT:    movq %rax, (%rsi)
-; CHECK-NEXT:    movq %rcx, 8(%rsi)
-; CHECK-NEXT:    movq %rax, 16(%rsi)
-; CHECK-NEXT:    movq %rcx, 24(%rsi)
+; CHECK-NEXT:    movups (%rdi), %xmm0
+; CHECK-NEXT:    movups %xmm0, (%rsi)
+; CHECK-NEXT:    movups %xmm0, 16(%rsi)
 ; CHECK-NEXT:    retq
 entry:
   %0 = load i64, i64* %p, align 8, !tbaa !1