Index: llvm/trunk/lib/Target/ARM/ARMLoadStoreOptimizer.cpp
===================================================================
--- llvm/trunk/lib/Target/ARM/ARMLoadStoreOptimizer.cpp
+++ llvm/trunk/lib/Target/ARM/ARMLoadStoreOptimizer.cpp
@@ -630,9 +630,10 @@
 
     unsigned NewBase;
     if (isi32Load(Opcode)) {
-      // If it is a load, then just use one of the destination register to
-      // use as the new base.
+      // If it is a load, then just use one of the destination registers
+      // as the new base. Will no longer be writeback in Thumb1.
       NewBase = Regs[NumRegs-1].first;
+      Writeback = false;
     } else {
       // Find a free register that we can use as scratch register.
       moveLiveRegsBefore(MBB, InsertBefore);
@@ -736,9 +737,12 @@
   MachineInstrBuilder MIB;
 
   if (Writeback) {
-    if (Opcode == ARM::tLDMIA)
+    assert(isThumb1 && "expected Writeback only inThumb1");
+    if (Opcode == ARM::tLDMIA) {
+      assert(!(ContainsReg(Regs, Base)) && "Thumb1 can't LDM ! with Base in Regs");
       // Update tLDMIA with writeback if necessary.
       Opcode = ARM::tLDMIA_UPD;
+    }
 
     MIB = BuildMI(MBB, InsertBefore, DL, TII->get(Opcode));
 
Index: llvm/trunk/test/CodeGen/ARM/thumb1-ldst-opt.ll
===================================================================
--- llvm/trunk/test/CodeGen/ARM/thumb1-ldst-opt.ll
+++ llvm/trunk/test/CodeGen/ARM/thumb1-ldst-opt.ll
@@ -0,0 +1,27 @@
+; RUN: llc -stop-after block-placement -o /dev/null %s | FileCheck %s
+
+target triple = "thumbv6m-none-none"
+
+define i32* @foo(i32* readonly %p0) {
+entry:
+  %add.ptr = getelementptr inbounds i32, i32* %p0, i32 10
+  %arrayidx = getelementptr inbounds i32, i32* %p0, i32 13
+  %0 = load i32, i32* %arrayidx, align 4
+  %arrayidx1 = getelementptr inbounds i32, i32* %p0, i32 12
+  %1 = load i32, i32* %arrayidx1, align 4
+  %add = add nsw i32 %1, %0
+  %arrayidx2 = getelementptr inbounds i32, i32* %p0, i32 11
+  %2 = load i32, i32* %arrayidx2, align 4
+  %add3 = add nsw i32 %add, %2
+  %3 = load i32, i32* %add.ptr, align 4
+  %add5 = add nsw i32 %add3, %3
+  tail call void @g(i32 %add5)
+  ret i32* %p0
+}
+
+declare void @g(i32)
+
+; CHECK-LABEL: name: foo
+; CHECK: [[BASE:%r[0-7]]], {{.*}} tADDi8
+; CHECK-NOT: [[BASE]] = tLDMIA_UPD {{.*}} [[BASE]]
+; CHECK: tLDMIA killed [[BASE]], {{.*}} def [[BASE]]