diff --git a/llvm/lib/Target/ARM/ARMScheduleA8.td b/llvm/lib/Target/ARM/ARMScheduleA8.td
index 7573182434c6..32d9d66837b3 100644
--- a/llvm/lib/Target/ARM/ARMScheduleA8.td
+++ b/llvm/lib/Target/ARM/ARMScheduleA8.td
@@ -331,6 +331,28 @@ def CortexA8Itineraries : ProcessorItineraries<
   InstrItinData<IIC_fpSQRT64, [InstrStage<1, [A8_Pipe0, A8_Pipe1]>,
                                InstrStage<29, [A8_NPipe], 0>,
                                InstrStage<29, [A8_NLSPipe]>], [29, 1]>,
+
+  //
+  // Integer to Single-precision Move
+  InstrItinData<IIC_fpMOVIS,  [InstrStage<1, [A8_Pipe0, A8_Pipe1]>,
+                               InstrStage<1, [A8_NPipe]>],
+                              [2, 1]>,
+  //
+  // Integer to Double-precision Move
+  InstrItinData<IIC_fpMOVID,  [InstrStage<1, [A8_Pipe0, A8_Pipe1]>,
+                               InstrStage<1, [A8_NPipe]>],
+                              [2, 1, 1]>,
+  //
+  // Single-precision to Integer Move
+  InstrItinData<IIC_fpMOVSI,  [InstrStage<1, [A8_Pipe0, A8_Pipe1]>,
+                               InstrStage<1, [A8_NPipe]>],
+                              [20, 1]>,
+  //
+  // Double-precision to Integer Move
+  InstrItinData<IIC_fpMOVDI,  [InstrStage<1, [A8_Pipe0, A8_Pipe1]>,
+                               InstrStage<1, [A8_NPipe]>],
+                              [20, 20, 1]>,
+
   //
   // Single-precision FP Load
   InstrItinData<IIC_fpLoad32, [InstrStage<1, [A8_Pipe0, A8_Pipe1]>,
diff --git a/llvm/lib/Target/ARM/ARMScheduleA9.td b/llvm/lib/Target/ARM/ARMScheduleA9.td
index c22367716c30..548bc7cd6030 100644
--- a/llvm/lib/Target/ARM/ARMScheduleA9.td
+++ b/llvm/lib/Target/ARM/ARMScheduleA9.td
@@ -641,7 +641,7 @@ def CortexA9Itineraries : ProcessorItineraries<
                                InstrStage<1, [A9_DRegsVFP], 0, Required>,
                                InstrStage<2, [A9_DRegsN],   0, Reserved>,
                                InstrStage<1, [A9_NPipe]>],
-                              [1, 1]>,
+                              [2, 1]>,
   //
   // Double-precision to Integer Move
   InstrItinData<IIC_fpMOVDI,  [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
@@ -649,7 +649,7 @@ def CortexA9Itineraries : ProcessorItineraries<
                                InstrStage<1, [A9_DRegsVFP], 0, Required>,
                                InstrStage<2, [A9_DRegsN],   0, Reserved>,
                                InstrStage<1, [A9_NPipe]>],
-                              [1, 1, 1]>,
+                              [2, 1, 1]>,
   //
   // Single-precision FP Load
   InstrItinData<IIC_fpLoad32, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
@@ -1430,7 +1430,7 @@ def CortexA9Itineraries : ProcessorItineraries<
                                InstrStage<1, [A9_DRegsN],   0, Required>,
                                InstrStage<3, [A9_DRegsVFP], 0, Reserved>,
                                InstrStage<1, [A9_NPipe]>],
-                              [2, 1]>,
+                              [1, 1]>,
   //
   // Integer to Double-precision Move
   InstrItinData<IIC_VMOVID ,  [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
@@ -1438,7 +1438,7 @@ def CortexA9Itineraries : ProcessorItineraries<
                                InstrStage<1, [A9_DRegsN],   0, Required>,
                                InstrStage<3, [A9_DRegsVFP], 0, Reserved>,
                                InstrStage<1, [A9_NPipe]>],
-                              [2, 1, 1]>,
+                              [1, 1, 1]>,
   //
   // Single-precision to Integer Move
   InstrItinData<IIC_VMOVSI ,  [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
diff --git a/llvm/lib/Target/ARM/ARMScheduleV6.td b/llvm/lib/Target/ARM/ARMScheduleV6.td
index b845130e3701..e4e9c13bd935 100644
--- a/llvm/lib/Target/ARM/ARMScheduleV6.td
+++ b/llvm/lib/Target/ARM/ARMScheduleV6.td
@@ -247,6 +247,18 @@ def ARMV6Itineraries : ProcessorItineraries<
   // Double-precision FP SQRT
   InstrItinData<IIC_fpSQRT64 , [InstrStage<29, [V6_Pipe]>], [34, 2, 2]>,
   //
+  // Integer to Single-precision Move
+  InstrItinData<IIC_fpMOVIS,  [InstrStage<1, [V6_Pipe]>], [10, 1]>,
+  //
+  // Integer to Double-precision Move
+  InstrItinData<IIC_fpMOVID,  [InstrStage<1, [V6_Pipe]>], [10, 1, 1]>,
+  //
+  // Single-precision to Integer Move
+  InstrItinData<IIC_fpMOVSI,  [InstrStage<1, [V6_Pipe]>], [10, 1]>,
+  //
+  // Double-precision to Integer Move
+  InstrItinData<IIC_fpMOVDI,  [InstrStage<1, [V6_Pipe]>], [10, 10, 1]>,
+  //
   // Single-precision FP Load
   InstrItinData<IIC_fpLoad32 , [InstrStage<1, [V6_Pipe]>], [5, 2, 2]>,
   //
diff --git a/llvm/test/CodeGen/ARM/fmscs.ll b/llvm/test/CodeGen/ARM/fmscs.ll
index 103ce334519b..19359a1ae6bc 100644
--- a/llvm/test/CodeGen/ARM/fmscs.ll
+++ b/llvm/test/CodeGen/ARM/fmscs.ll
@@ -19,6 +19,6 @@ entry:
 ; NFP0: 	vnmls.f32	s2, s1, s0
 
 ; CORTEXA8: test:
-; CORTEXA8: 	vnmls.f32	s2, s1, s0
+; CORTEXA8: 	vnmls.f32	s1, s2, s0
 ; CORTEXA9: test:
 ; CORTEXA9: 	vnmls.f32	s0, s1, s2
diff --git a/llvm/test/CodeGen/ARM/reg_sequence.ll b/llvm/test/CodeGen/ARM/reg_sequence.ll
index 1a95897c26cf..390955472ec0 100644
--- a/llvm/test/CodeGen/ARM/reg_sequence.ll
+++ b/llvm/test/CodeGen/ARM/reg_sequence.ll
@@ -75,7 +75,8 @@ define <8 x i8> @t3(i8* %A, i8* %B) nounwind {
 ; CHECK:        t3:
 ; CHECK:        vld3.8
 ; CHECK:        vmul.i8
-; CHECK-NOT:    vmov
+; CHECK:        vmov r
+; CHECK-NOT:    vmov d
 ; CHECK:        vst3.8
   %tmp1 = call %struct.__neon_int8x8x3_t @llvm.arm.neon.vld3.v8i8(i8* %A, i32 1) ; <%struct.__neon_int8x8x3_t> [#uses=2]
   %tmp2 = extractvalue %struct.__neon_int8x8x3_t %tmp1, 0 ; <<8 x i8>> [#uses=1]