Index: llvm/trunk/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
===================================================================
--- llvm/trunk/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ llvm/trunk/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -10196,7 +10196,8 @@
   // value.
   // TODO: Handle store large -> read small portion.
   // TODO: Handle TRUNCSTORE/LOADEXT
-  if (ISD::isNormalLoad(N) && !LD->isVolatile()) {
+  if (OptLevel != CodeGenOpt::None &&
+      ISD::isNormalLoad(N) && !LD->isVolatile()) {
     if (ISD::isNON_TRUNCStore(Chain.getNode())) {
       StoreSDNode *PrevST = cast<StoreSDNode>(Chain);
       if (PrevST->getBasePtr() == Ptr &&
Index: llvm/trunk/test/CodeGen/ARM/alloc-no-stack-realign.ll
===================================================================
--- llvm/trunk/test/CodeGen/ARM/alloc-no-stack-realign.ll
+++ llvm/trunk/test/CodeGen/ARM/alloc-no-stack-realign.ll
@@ -21,8 +21,9 @@
 ; NO-REALIGN: vst1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R2]]:128]
 ; NO-REALIGN: add r[[R2:[0-9]+]], r[[R1]], #32
 ; NO-REALIGN: vst1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R2]]:128]
-; NO-REALIGN: vst1.32 {{{d[0-9]+, d[0-9]+}}}, [r[[R1]]:128]!
-; NO-REALIGN: vst1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R1]]:128]
+; NO-REALIGN: mov	r[[R3:[0-9]+]], r[[R1]]
+; NO-REALIGN: vst1.32 {{{d[0-9]+, d[0-9]+}}}, [r[[R3]]:128]!
+; NO-REALIGN: vst1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R3]]:128]
 
 ; NO-REALIGN: add r[[R2:[0-9]+]], r[[R0:0]], #48
 ; NO-REALIGN: vst1.64 {{{d[0-9]+, d[0-9]+}}}, [r[[R2]]:128]
Index: llvm/trunk/test/CodeGen/ARM/dag-combine-ldst.ll
===================================================================
--- llvm/trunk/test/CodeGen/ARM/dag-combine-ldst.ll
+++ llvm/trunk/test/CodeGen/ARM/dag-combine-ldst.ll
@@ -0,0 +1,41 @@
+; RUN: llc < %s -mtriple=arm-eabi -mattr=+v4t -O0 | FileCheck %s -check-prefix=CHECK -check-prefix=CHECK_O0
+; RUN: llc < %s -mtriple=arm-eabi -mattr=+v4t -O1 | FileCheck %s -check-prefix=CHECK -check-prefix=CHECK_O1
+
+; In /O0, the addition must not be eliminated. This happens when the load
+; and store are folded by the DAGCombiner. In /O1 and above, the optimization
+; must be executed.
+
+; CHECK-LABEL:   {{^}}main
+; CHECK:         mov [[TMP:r[0-9]+]], #0
+; CHECK-NEXT:    str [[TMP]], [sp, #4]
+; CHECK-NEXT:    str [[TMP]], [sp]
+; CHECK_O0:      ldr [[TMP:r[0-9]+]], [sp]
+; CHECK_O0-NEXT: add [[TMP]], [[TMP]], #2
+; CHECK_O1-NOT:  ldr [[TMP:r[0-9]+]], [sp]
+; CHECK_O1-NOT:  add [[TMP]], [[TMP]], #2
+
+define i32 @main() {
+bb:
+  %tmp = alloca i32, align 4
+  %tmp1 = alloca i32, align 4
+  store i32 0, i32* %tmp, align 4
+  store i32 0, i32* %tmp1, align 4
+  %tmp2 = load i32, i32* %tmp1, align 4
+  %tmp3 = add nsw i32 %tmp2, 2
+  store i32 %tmp3, i32* %tmp1, align 4
+  %tmp4 = load i32, i32* %tmp1, align 4
+  %tmp5 = icmp eq i32 %tmp4, 2
+  br i1 %tmp5, label %bb6, label %bb7
+
+bb6:                                              ; preds = %bb
+  store i32 0, i32* %tmp, align 4
+  br label %bb8
+
+bb7:                                              ; preds = %bb
+  store i32 5, i32* %tmp, align 4
+  br label %bb8
+
+bb8:                                              ; preds = %bb7, %bb6
+  %tmp9 = load i32, i32* %tmp, align 4
+  ret i32 %tmp9
+}
Index: llvm/trunk/test/CodeGen/SystemZ/swift-return.ll
===================================================================
--- llvm/trunk/test/CodeGen/SystemZ/swift-return.ll
+++ llvm/trunk/test/CodeGen/SystemZ/swift-return.ll
@@ -49,10 +49,9 @@
 ; CHECK: a %r2, 172(%r15)
 ; CHECK: a %r2, 176(%r15)
 ; CHECK-O0-LABEL: test2:
-; CHECK-O0: la %[[REG1:r[0-9]+]], 168(%r15)
 ; CHECK-O0: st %r2, [[SPILL1:[0-9]+]](%r15)
-; CHECK-O0: lgr %r2, %[[REG1]]
 ; CHECK-O0: l %r3, [[SPILL1]](%r15)
+; CHECK-O0: la %r2, 168(%r15)
 ; CHECK-O0: brasl %r14, gen2
 ; CHECK-O0-DAG: l %r{{.*}}, 184(%r15)
 ; CHECK-O0-DAG: l %r{{.*}}, 180(%r15)
Index: llvm/trunk/test/CodeGen/X86/inline-asm-tied.ll
===================================================================
--- llvm/trunk/test/CodeGen/X86/inline-asm-tied.ll
+++ llvm/trunk/test/CodeGen/X86/inline-asm-tied.ll
@@ -1,8 +1,9 @@
 ; RUN: llc < %s -mtriple=i386-apple-darwin9 -O0 -optimize-regalloc -regalloc=basic -no-integrated-as | FileCheck %s
 ; rdar://6992609
 
-; CHECK: movl [[EDX:%e..]], 4(%esp)
-; CHECK: movl [[EDX]], 4(%esp)
+; CHECK: movl %ecx, 4([[ESP:%e..]])
+; CHECK: movl 4([[ESP]]), [[EDX:%e..]]
+; CHECK: movl [[EDX]], 4([[ESP]])
 target triple = "i386-apple-darwin9.0"
 @llvm.used = appending global [1 x i8*] [i8* bitcast (i64 (i64)* @_OSSwapInt64 to i8*)], section "llvm.metadata"		; <[1 x i8*]*> [#uses=0]
 
Index: llvm/trunk/test/CodeGen/X86/pr30430.ll
===================================================================
--- llvm/trunk/test/CodeGen/X86/pr30430.ll
+++ llvm/trunk/test/CodeGen/X86/pr30430.ll
@@ -46,6 +46,7 @@
 ; CHECK-NEXT:    vmovss {{.*#+}} xmm5 = mem[0],zero,zero,zero
 ; CHECK-NEXT:    vmovss {{.*#+}} xmm6 = mem[0],zero,zero,zero
 ; CHECK-NEXT:    vmovss {{.*#+}} xmm7 = mem[0],zero,zero,zero
+; CHECK-NEXT:    vmovss {{.*#+}} xmm8 = mem[0],zero,zero,zero
 ; CHECK-NEXT:    vmovss {{.*#+}} xmm9 = mem[0],zero,zero,zero
 ; CHECK-NEXT:    vmovss {{.*#+}} xmm10 = mem[0],zero,zero,zero
 ; CHECK-NEXT:    vmovss {{.*#+}} xmm11 = mem[0],zero,zero,zero
@@ -53,7 +54,6 @@
 ; CHECK-NEXT:    vmovss {{.*#+}} xmm13 = mem[0],zero,zero,zero
 ; CHECK-NEXT:    vmovss {{.*#+}} xmm14 = mem[0],zero,zero,zero
 ; CHECK-NEXT:    vmovss {{.*#+}} xmm15 = mem[0],zero,zero,zero
-; CHECK-NEXT:    vmovss %xmm8, {{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    vmovss %xmm0, {{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    vmovss %xmm1, {{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    vmovss %xmm2, {{[0-9]+}}(%rsp)
@@ -62,6 +62,7 @@
 ; CHECK-NEXT:    vmovss %xmm5, {{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    vmovss %xmm6, {{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    vmovss %xmm7, {{[0-9]+}}(%rsp)
+; CHECK-NEXT:    vmovss %xmm8, {{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    vmovss %xmm9, {{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    vmovss %xmm10, {{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    vmovss %xmm11, {{[0-9]+}}(%rsp)
@@ -94,7 +95,8 @@
 ; CHECK-NEXT:    vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
 ; CHECK-NEXT:    vinsertps {{.*#+}} xmm0 = xmm0[0,1,2],xmm1[0]
 ; CHECK-NEXT:    vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
-; CHECK-NEXT:    vinsertps {{.*#+}} xmm1 = xmm15[0],xmm1[0],xmm15[2,3]
+; CHECK-NEXT:    vmovss {{.*#+}} xmm3 = mem[0],zero,zero,zero
+; CHECK-NEXT:    vinsertps {{.*#+}} xmm1 = xmm3[0],xmm1[0],xmm3[2,3]
 ; CHECK-NEXT:    vmovss {{.*#+}} xmm3 = mem[0],zero,zero,zero
 ; CHECK-NEXT:    vinsertps {{.*#+}} xmm1 = xmm1[0,1],xmm3[0],xmm1[3]
 ; CHECK-NEXT:    vmovss {{.*#+}} xmm3 = mem[0],zero,zero,zero