diff --git a/lib/Target/ARM/ARMFrameInfo.cpp b/lib/Target/ARM/ARMFrameInfo.cpp
index bddc7987b17..cbc06160d3d 100644
--- a/lib/Target/ARM/ARMFrameInfo.cpp
+++ b/lib/Target/ARM/ARMFrameInfo.cpp
@@ -592,7 +592,7 @@ void ARMFrameInfo::emitPopInst(MachineBasicBlock &MBB,
       unsigned Reg = CSI[i-1].getReg();
       if (!(Func)(Reg, STI.isTargetDarwin())) continue;
 
-      if (Reg == ARM::LR && !isVarArg) {
+      if (Reg == ARM::LR && !isVarArg && STI.hasV5TOps()) {
         Reg = ARM::PC;
         LdmOpc = AFI->isThumbFunction() ? ARM::t2LDMIA_RET : ARM::LDMIA_RET;
         // Fold the return instruction into the LDM.
diff --git a/lib/Target/ARM/ARMLoadStoreOptimizer.cpp b/lib/Target/ARM/ARMLoadStoreOptimizer.cpp
index a544029e5ab..f2d705f0ec5 100644
--- a/lib/Target/ARM/ARMLoadStoreOptimizer.cpp
+++ b/lib/Target/ARM/ARMLoadStoreOptimizer.cpp
@@ -1390,7 +1390,8 @@ bool ARMLoadStoreOpt::runOnMachineFunction(MachineFunction &Fn) {
        ++MFI) {
     MachineBasicBlock &MBB = *MFI;
     Modified |= LoadStoreMultipleOpti(MBB);
-    Modified |= MergeReturnIntoLDM(MBB);
+    if (TM.getSubtarget<ARMSubtarget>().hasV5TOps())
+      Modified |= MergeReturnIntoLDM(MBB);
   }
 
   delete RS;
diff --git a/test/CodeGen/ARM/2010-03-18-ldm-rtrn.ll b/test/CodeGen/ARM/2010-03-18-ldm-rtrn.ll
index 31525eff446..d9e1a1486a3 100644
--- a/test/CodeGen/ARM/2010-03-18-ldm-rtrn.ll
+++ b/test/CodeGen/ARM/2010-03-18-ldm-rtrn.ll
@@ -1,4 +1,4 @@
-; RUN: llc < %s -mtriple=armv4-unknown-eabi | FileCheck %s
+; RUN: llc < %s -mtriple=armv4-unknown-eabi | FileCheck %s -check-prefix=V4
 ; RUN: llc < %s -mtriple=armv5-unknown-eabi | FileCheck %s
 ; RUN: llc < %s -mtriple=armv6-unknown-eabi | FileCheck %s
 
@@ -7,6 +7,8 @@ entry:
   %0 = tail call i32 @foo(i32 %a) nounwind ; <i32> [#uses=1]
   %1 = add nsw i32 %0, 3                          ; <i32> [#uses=1]
 ; CHECK: ldmia	sp!, {r11, pc}
+; V4: pop
+; V4-NEXT: mov pc, lr
   ret i32 %1
 }
 
diff --git a/test/CodeGen/ARM/bx_fold.ll b/test/CodeGen/ARM/bx_fold.ll
index 0e3e070a818..09f1aae0a9f 100644
--- a/test/CodeGen/ARM/bx_fold.ll
+++ b/test/CodeGen/ARM/bx_fold.ll
@@ -1,5 +1,4 @@
-; RUN: llc < %s -march=arm
-; RUN: llc < %s -march=arm | not grep bx
+; RUN: llc < %s -mtriple=armv5t-apple-darwin | FileCheck %s
 
 define void @test(i32 %Ptr, i8* %L) {
 entry:
@@ -24,6 +23,8 @@ bb1:		; preds = %bb, %entry
 	br i1 %bothcond, label %bb, label %bb18
 
 bb18:		; preds = %bb1
+; CHECK-NOT: bx
+; CHECK: ldmia sp!
 	ret void
 }
 
diff --git a/test/CodeGen/ARM/ifcvt6.ll b/test/CodeGen/ARM/ifcvt6.ll
index e2c0ba398c6..5edf32fd1af 100644
--- a/test/CodeGen/ARM/ifcvt6.ll
+++ b/test/CodeGen/ARM/ifcvt6.ll
@@ -1,10 +1,9 @@
-; RUN: llc < %s -march=arm -mtriple=arm-apple-darwin | \
-; RUN:   grep cmpne | count 1
-; RUN: llc < %s -march=arm -mtriple=arm-apple-darwin | \
-; RUN:   grep ldmiahi | count 1
+; RUN: llc < %s -mtriple=armv7-apple-darwin | FileCheck %s
 
 define void @foo(i32 %X, i32 %Y) {
 entry:
+; CHECK: cmpne
+; CHECK: ldmiahi sp!
 	%tmp1 = icmp ult i32 %X, 4		; <i1> [#uses=1]
 	%tmp4 = icmp eq i32 %Y, 0		; <i1> [#uses=1]
 	%tmp7 = or i1 %tmp4, %tmp1		; <i1> [#uses=1]
diff --git a/test/CodeGen/ARM/ifcvt7.ll b/test/CodeGen/ARM/ifcvt7.ll
index eb97085ac00..62e13557cfd 100644
--- a/test/CodeGen/ARM/ifcvt7.ll
+++ b/test/CodeGen/ARM/ifcvt7.ll
@@ -1,14 +1,12 @@
-; RUN: llc < %s -march=arm -mtriple=arm-apple-darwin | \
-; RUN:   grep cmpeq | count 1
-; RUN: llc < %s -march=arm -mtriple=arm-apple-darwin | \
-; RUN:   grep moveq | count 1
-; RUN: llc < %s -march=arm -mtriple=arm-apple-darwin | \
-; RUN:   grep ldmiaeq | count 1
+; RUN: llc < %s -mtriple=armv7-apple-darwin | FileCheck %s
 ; FIXME: Need post-ifcvt branch folding to get rid of the extra br at end of BB1.
 
 	%struct.quad_struct = type { i32, i32, %struct.quad_struct*, %struct.quad_struct*, %struct.quad_struct*, %struct.quad_struct*, %struct.quad_struct* }
 
 define fastcc i32 @CountTree(%struct.quad_struct* %tree) {
+; CHECK: cmpeq
+; CHECK: moveq
+; CHECK: ldmiaeq sp!
 entry:
 	br label %tailrecurse
 
diff --git a/test/CodeGen/ARM/ifcvt8.ll b/test/CodeGen/ARM/ifcvt8.ll
index 1e39060e69f..5fdfc4ea680 100644
--- a/test/CodeGen/ARM/ifcvt8.ll
+++ b/test/CodeGen/ARM/ifcvt8.ll
@@ -1,11 +1,11 @@
-; RUN: llc < %s -march=arm -mtriple=arm-apple-darwin | \
-; RUN:   grep ldmiane | count 1
+; RUN: llc < %s -mtriple=armv7-apple-darwin | FileCheck %s
 
 	%struct.SString = type { i8*, i32, i32 }
 
 declare void @abort()
 
 define fastcc void @t(%struct.SString* %word, i8 signext  %c) {
+; CHECK: ldmiane sp!
 entry:
 	%tmp1 = icmp eq %struct.SString* %word, null		; <i1> [#uses=1]
 	br i1 %tmp1, label %cond_true, label %cond_false
diff --git a/test/CodeGen/ARM/ldm.ll b/test/CodeGen/ARM/ldm.ll
index 78201a6b341..2f1b85ebbb0 100644
--- a/test/CodeGen/ARM/ldm.ll
+++ b/test/CodeGen/ARM/ldm.ll
@@ -1,10 +1,13 @@
-; RUN: llc < %s -mtriple=arm-apple-darwin | FileCheck %s
+; RUN: llc < %s -mtriple=armv7-apple-darwin | FileCheck %s
+; RUN: llc < %s -mtriple=armv4t-apple-darwin | FileCheck %s -check-prefix=V4T
 
 @X = external global [0 x i32]          ; <[0 x i32]*> [#uses=5]
 
 define i32 @t1() {
 ; CHECK: t1:
 ; CHECK: ldmia
+; V4T: t1:
+; V4T: ldmia
         %tmp = load i32* getelementptr ([0 x i32]* @X, i32 0, i32 0)            ; <i32> [#uses=1]
         %tmp3 = load i32* getelementptr ([0 x i32]* @X, i32 0, i32 1)           ; <i32> [#uses=1]
         %tmp4 = tail call i32 @f1( i32 %tmp, i32 %tmp3 )                ; <i32> [#uses=1]
@@ -14,6 +17,8 @@ define i32 @t1() {
 define i32 @t2() {
 ; CHECK: t2:
 ; CHECK: ldmia
+; V4T: t2:
+; V4T: ldmia
         %tmp = load i32* getelementptr ([0 x i32]* @X, i32 0, i32 2)            ; <i32> [#uses=1]
         %tmp3 = load i32* getelementptr ([0 x i32]* @X, i32 0, i32 3)           ; <i32> [#uses=1]
         %tmp5 = load i32* getelementptr ([0 x i32]* @X, i32 0, i32 4)           ; <i32> [#uses=1]
@@ -25,6 +30,10 @@ define i32 @t3() {
 ; CHECK: t3:
 ; CHECK: ldmib
 ; CHECK: ldmia sp!
+; V4T: t3:
+; V4T: ldmib
+; V4T: pop
+; V4T-NEXT: bx lr
         %tmp = load i32* getelementptr ([0 x i32]* @X, i32 0, i32 1)            ; <i32> [#uses=1]
         %tmp3 = load i32* getelementptr ([0 x i32]* @X, i32 0, i32 2)           ; <i32> [#uses=1]
         %tmp5 = load i32* getelementptr ([0 x i32]* @X, i32 0, i32 3)           ; <i32> [#uses=1]
diff --git a/test/CodeGen/ARM/lsr-code-insertion.ll b/test/CodeGen/ARM/lsr-code-insertion.ll
index b8c543b1bd1..1bbb96deeef 100644
--- a/test/CodeGen/ARM/lsr-code-insertion.ll
+++ b/test/CodeGen/ARM/lsr-code-insertion.ll
@@ -1,4 +1,4 @@
-; RUN: llc < %s -stats |& grep {38.*Number of machine instrs printed}
+; RUN: llc < %s -stats |& grep {39.*Number of machine instrs printed}
 ; RUN: llc < %s -stats |& not grep {.*Number of re-materialization}
 ; This test really wants to check that the resultant "cond_true" block only 
 ; has a single store in it, and that cond_true55 only has code to materialize