diff --git a/llvm/test/CodeGen/ARM/vmax.ll b/llvm/test/CodeGen/ARM/vmax.ll
index 85ff31033ca4..007ac568aac6 100644
--- a/llvm/test/CodeGen/ARM/vmax.ll
+++ b/llvm/test/CodeGen/ARM/vmax.ll
@@ -1,13 +1,8 @@
-; RUN: llc < %s -march=arm -mattr=+neon > %t
-; RUN: grep {vmax\\.s8} %t | count 2
-; RUN: grep {vmax\\.s16} %t | count 2
-; RUN: grep {vmax\\.s32} %t | count 2
-; RUN: grep {vmax\\.u8} %t | count 2
-; RUN: grep {vmax\\.u16} %t | count 2
-; RUN: grep {vmax\\.u32} %t | count 2
-; RUN: grep {vmax\\.f32} %t | count 2
+; RUN: llc < %s -march=arm -mattr=+neon | FileCheck %s
 
 define <8 x i8> @vmaxs8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
+;CHECK: vmaxs8:
+;CHECK: vmax.s8
 	%tmp1 = load <8 x i8>* %A
 	%tmp2 = load <8 x i8>* %B
 	%tmp3 = call <8 x i8> @llvm.arm.neon.vmaxs.v8i8(<8 x i8> %tmp1, <8 x i8> %tmp2)
@@ -15,6 +10,8 @@ define <8 x i8> @vmaxs8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
 }
 
 define <4 x i16> @vmaxs16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
+;CHECK: vmaxs16:
+;CHECK: vmax.s16
 	%tmp1 = load <4 x i16>* %A
 	%tmp2 = load <4 x i16>* %B
 	%tmp3 = call <4 x i16> @llvm.arm.neon.vmaxs.v4i16(<4 x i16> %tmp1, <4 x i16> %tmp2)
@@ -22,6 +19,8 @@ define <4 x i16> @vmaxs16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
 }
 
 define <2 x i32> @vmaxs32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
+;CHECK: vmaxs32:
+;CHECK: vmax.s32
 	%tmp1 = load <2 x i32>* %A
 	%tmp2 = load <2 x i32>* %B
 	%tmp3 = call <2 x i32> @llvm.arm.neon.vmaxs.v2i32(<2 x i32> %tmp1, <2 x i32> %tmp2)
@@ -29,6 +28,8 @@ define <2 x i32> @vmaxs32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
 }
 
 define <8 x i8> @vmaxu8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
+;CHECK: vmaxu8:
+;CHECK: vmax.u8
 	%tmp1 = load <8 x i8>* %A
 	%tmp2 = load <8 x i8>* %B
 	%tmp3 = call <8 x i8> @llvm.arm.neon.vmaxu.v8i8(<8 x i8> %tmp1, <8 x i8> %tmp2)
@@ -36,6 +37,8 @@ define <8 x i8> @vmaxu8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
 }
 
 define <4 x i16> @vmaxu16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
+;CHECK: vmaxu16:
+;CHECK: vmax.u16
 	%tmp1 = load <4 x i16>* %A
 	%tmp2 = load <4 x i16>* %B
 	%tmp3 = call <4 x i16> @llvm.arm.neon.vmaxu.v4i16(<4 x i16> %tmp1, <4 x i16> %tmp2)
@@ -43,6 +46,8 @@ define <4 x i16> @vmaxu16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
 }
 
 define <2 x i32> @vmaxu32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
+;CHECK: vmaxu32:
+;CHECK: vmax.u32
 	%tmp1 = load <2 x i32>* %A
 	%tmp2 = load <2 x i32>* %B
 	%tmp3 = call <2 x i32> @llvm.arm.neon.vmaxu.v2i32(<2 x i32> %tmp1, <2 x i32> %tmp2)
@@ -50,6 +55,8 @@ define <2 x i32> @vmaxu32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
 }
 
 define <2 x float> @vmaxf32(<2 x float>* %A, <2 x float>* %B) nounwind {
+;CHECK: vmaxf32:
+;CHECK: vmax.f32
 	%tmp1 = load <2 x float>* %A
 	%tmp2 = load <2 x float>* %B
 	%tmp3 = call <2 x float> @llvm.arm.neon.vmaxs.v2f32(<2 x float> %tmp1, <2 x float> %tmp2)
@@ -57,6 +64,8 @@ define <2 x float> @vmaxf32(<2 x float>* %A, <2 x float>* %B) nounwind {
 }
 
 define <16 x i8> @vmaxQs8(<16 x i8>* %A, <16 x i8>* %B) nounwind {
+;CHECK: vmaxQs8:
+;CHECK: vmax.s8
 	%tmp1 = load <16 x i8>* %A
 	%tmp2 = load <16 x i8>* %B
 	%tmp3 = call <16 x i8> @llvm.arm.neon.vmaxs.v16i8(<16 x i8> %tmp1, <16 x i8> %tmp2)
@@ -64,6 +73,8 @@ define <16 x i8> @vmaxQs8(<16 x i8>* %A, <16 x i8>* %B) nounwind {
 }
 
 define <8 x i16> @vmaxQs16(<8 x i16>* %A, <8 x i16>* %B) nounwind {
+;CHECK: vmaxQs16:
+;CHECK: vmax.s16
 	%tmp1 = load <8 x i16>* %A
 	%tmp2 = load <8 x i16>* %B
 	%tmp3 = call <8 x i16> @llvm.arm.neon.vmaxs.v8i16(<8 x i16> %tmp1, <8 x i16> %tmp2)
@@ -71,6 +82,8 @@ define <8 x i16> @vmaxQs16(<8 x i16>* %A, <8 x i16>* %B) nounwind {
 }
 
 define <4 x i32> @vmaxQs32(<4 x i32>* %A, <4 x i32>* %B) nounwind {
+;CHECK: vmaxQs32:
+;CHECK: vmax.s32
 	%tmp1 = load <4 x i32>* %A
 	%tmp2 = load <4 x i32>* %B
 	%tmp3 = call <4 x i32> @llvm.arm.neon.vmaxs.v4i32(<4 x i32> %tmp1, <4 x i32> %tmp2)
@@ -78,6 +91,8 @@ define <4 x i32> @vmaxQs32(<4 x i32>* %A, <4 x i32>* %B) nounwind {
 }
 
 define <16 x i8> @vmaxQu8(<16 x i8>* %A, <16 x i8>* %B) nounwind {
+;CHECK: vmaxQu8:
+;CHECK: vmax.u8
 	%tmp1 = load <16 x i8>* %A
 	%tmp2 = load <16 x i8>* %B
 	%tmp3 = call <16 x i8> @llvm.arm.neon.vmaxu.v16i8(<16 x i8> %tmp1, <16 x i8> %tmp2)
@@ -85,6 +100,8 @@ define <16 x i8> @vmaxQu8(<16 x i8>* %A, <16 x i8>* %B) nounwind {
 }
 
 define <8 x i16> @vmaxQu16(<8 x i16>* %A, <8 x i16>* %B) nounwind {
+;CHECK: vmaxQu16:
+;CHECK: vmax.u16
 	%tmp1 = load <8 x i16>* %A
 	%tmp2 = load <8 x i16>* %B
 	%tmp3 = call <8 x i16> @llvm.arm.neon.vmaxu.v8i16(<8 x i16> %tmp1, <8 x i16> %tmp2)
@@ -92,6 +109,8 @@ define <8 x i16> @vmaxQu16(<8 x i16>* %A, <8 x i16>* %B) nounwind {
 }
 
 define <4 x i32> @vmaxQu32(<4 x i32>* %A, <4 x i32>* %B) nounwind {
+;CHECK: vmaxQu32:
+;CHECK: vmax.u32
 	%tmp1 = load <4 x i32>* %A
 	%tmp2 = load <4 x i32>* %B
 	%tmp3 = call <4 x i32> @llvm.arm.neon.vmaxu.v4i32(<4 x i32> %tmp1, <4 x i32> %tmp2)
@@ -99,6 +118,8 @@ define <4 x i32> @vmaxQu32(<4 x i32>* %A, <4 x i32>* %B) nounwind {
 }
 
 define <4 x float> @vmaxQf32(<4 x float>* %A, <4 x float>* %B) nounwind {
+;CHECK: vmaxQf32:
+;CHECK: vmax.f32
 	%tmp1 = load <4 x float>* %A
 	%tmp2 = load <4 x float>* %B
 	%tmp3 = call <4 x float> @llvm.arm.neon.vmaxs.v4f32(<4 x float> %tmp1, <4 x float> %tmp2)
diff --git a/llvm/test/CodeGen/ARM/vmin.ll b/llvm/test/CodeGen/ARM/vmin.ll
index ecde35ae447c..65ed82b3859c 100644
--- a/llvm/test/CodeGen/ARM/vmin.ll
+++ b/llvm/test/CodeGen/ARM/vmin.ll
@@ -1,13 +1,8 @@
-; RUN: llc < %s -march=arm -mattr=+neon > %t
-; RUN: grep {vmin\\.s8} %t | count 2
-; RUN: grep {vmin\\.s16} %t | count 2
-; RUN: grep {vmin\\.s32} %t | count 2
-; RUN: grep {vmin\\.u8} %t | count 2
-; RUN: grep {vmin\\.u16} %t | count 2
-; RUN: grep {vmin\\.u32} %t | count 2
-; RUN: grep {vmin\\.f32} %t | count 2
+; RUN: llc < %s -march=arm -mattr=+neon | FileCheck %s
 
 define <8 x i8> @vmins8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
+;CHECK: vmins8:
+;CHECK: vmin.s8
 	%tmp1 = load <8 x i8>* %A
 	%tmp2 = load <8 x i8>* %B
 	%tmp3 = call <8 x i8> @llvm.arm.neon.vmins.v8i8(<8 x i8> %tmp1, <8 x i8> %tmp2)
@@ -15,6 +10,8 @@ define <8 x i8> @vmins8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
 }
 
 define <4 x i16> @vmins16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
+;CHECK: vmins16:
+;CHECK: vmin.s16
 	%tmp1 = load <4 x i16>* %A
 	%tmp2 = load <4 x i16>* %B
 	%tmp3 = call <4 x i16> @llvm.arm.neon.vmins.v4i16(<4 x i16> %tmp1, <4 x i16> %tmp2)
@@ -22,6 +19,8 @@ define <4 x i16> @vmins16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
 }
 
 define <2 x i32> @vmins32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
+;CHECK: vmins32:
+;CHECK: vmin.s32
 	%tmp1 = load <2 x i32>* %A
 	%tmp2 = load <2 x i32>* %B
 	%tmp3 = call <2 x i32> @llvm.arm.neon.vmins.v2i32(<2 x i32> %tmp1, <2 x i32> %tmp2)
@@ -29,6 +28,8 @@ define <2 x i32> @vmins32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
 }
 
 define <8 x i8> @vminu8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
+;CHECK: vminu8:
+;CHECK: vmin.u8
 	%tmp1 = load <8 x i8>* %A
 	%tmp2 = load <8 x i8>* %B
 	%tmp3 = call <8 x i8> @llvm.arm.neon.vminu.v8i8(<8 x i8> %tmp1, <8 x i8> %tmp2)
@@ -36,6 +37,8 @@ define <8 x i8> @vminu8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
 }
 
 define <4 x i16> @vminu16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
+;CHECK: vminu16:
+;CHECK: vmin.u16
 	%tmp1 = load <4 x i16>* %A
 	%tmp2 = load <4 x i16>* %B
 	%tmp3 = call <4 x i16> @llvm.arm.neon.vminu.v4i16(<4 x i16> %tmp1, <4 x i16> %tmp2)
@@ -43,6 +46,8 @@ define <4 x i16> @vminu16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
 }
 
 define <2 x i32> @vminu32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
+;CHECK: vminu32:
+;CHECK: vmin.u32
 	%tmp1 = load <2 x i32>* %A
 	%tmp2 = load <2 x i32>* %B
 	%tmp3 = call <2 x i32> @llvm.arm.neon.vminu.v2i32(<2 x i32> %tmp1, <2 x i32> %tmp2)
@@ -50,6 +55,8 @@ define <2 x i32> @vminu32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
 }
 
 define <2 x float> @vminf32(<2 x float>* %A, <2 x float>* %B) nounwind {
+;CHECK: vminf32:
+;CHECK: vmin.f32
 	%tmp1 = load <2 x float>* %A
 	%tmp2 = load <2 x float>* %B
 	%tmp3 = call <2 x float> @llvm.arm.neon.vmins.v2f32(<2 x float> %tmp1, <2 x float> %tmp2)
@@ -57,6 +64,8 @@ define <2 x float> @vminf32(<2 x float>* %A, <2 x float>* %B) nounwind {
 }
 
 define <16 x i8> @vminQs8(<16 x i8>* %A, <16 x i8>* %B) nounwind {
+;CHECK: vminQs8:
+;CHECK: vmin.s8
 	%tmp1 = load <16 x i8>* %A
 	%tmp2 = load <16 x i8>* %B
 	%tmp3 = call <16 x i8> @llvm.arm.neon.vmins.v16i8(<16 x i8> %tmp1, <16 x i8> %tmp2)
@@ -64,6 +73,8 @@ define <16 x i8> @vminQs8(<16 x i8>* %A, <16 x i8>* %B) nounwind {
 }
 
 define <8 x i16> @vminQs16(<8 x i16>* %A, <8 x i16>* %B) nounwind {
+;CHECK: vminQs16:
+;CHECK: vmin.s16
 	%tmp1 = load <8 x i16>* %A
 	%tmp2 = load <8 x i16>* %B
 	%tmp3 = call <8 x i16> @llvm.arm.neon.vmins.v8i16(<8 x i16> %tmp1, <8 x i16> %tmp2)
@@ -71,6 +82,8 @@ define <8 x i16> @vminQs16(<8 x i16>* %A, <8 x i16>* %B) nounwind {
 }
 
 define <4 x i32> @vminQs32(<4 x i32>* %A, <4 x i32>* %B) nounwind {
+;CHECK: vminQs32:
+;CHECK: vmin.s32
 	%tmp1 = load <4 x i32>* %A
 	%tmp2 = load <4 x i32>* %B
 	%tmp3 = call <4 x i32> @llvm.arm.neon.vmins.v4i32(<4 x i32> %tmp1, <4 x i32> %tmp2)
@@ -78,6 +91,8 @@ define <4 x i32> @vminQs32(<4 x i32>* %A, <4 x i32>* %B) nounwind {
 }
 
 define <16 x i8> @vminQu8(<16 x i8>* %A, <16 x i8>* %B) nounwind {
+;CHECK: vminQu8:
+;CHECK: vmin.u8
 	%tmp1 = load <16 x i8>* %A
 	%tmp2 = load <16 x i8>* %B
 	%tmp3 = call <16 x i8> @llvm.arm.neon.vminu.v16i8(<16 x i8> %tmp1, <16 x i8> %tmp2)
@@ -85,6 +100,8 @@ define <16 x i8> @vminQu8(<16 x i8>* %A, <16 x i8>* %B) nounwind {
 }
 
 define <8 x i16> @vminQu16(<8 x i16>* %A, <8 x i16>* %B) nounwind {
+;CHECK: vminQu16:
+;CHECK: vmin.u16
 	%tmp1 = load <8 x i16>* %A
 	%tmp2 = load <8 x i16>* %B
 	%tmp3 = call <8 x i16> @llvm.arm.neon.vminu.v8i16(<8 x i16> %tmp1, <8 x i16> %tmp2)
@@ -92,6 +109,8 @@ define <8 x i16> @vminQu16(<8 x i16>* %A, <8 x i16>* %B) nounwind {
 }
 
 define <4 x i32> @vminQu32(<4 x i32>* %A, <4 x i32>* %B) nounwind {
+;CHECK: vminQu32:
+;CHECK: vmin.u32
 	%tmp1 = load <4 x i32>* %A
 	%tmp2 = load <4 x i32>* %B
 	%tmp3 = call <4 x i32> @llvm.arm.neon.vminu.v4i32(<4 x i32> %tmp1, <4 x i32> %tmp2)
@@ -99,6 +118,8 @@ define <4 x i32> @vminQu32(<4 x i32>* %A, <4 x i32>* %B) nounwind {
 }
 
 define <4 x float> @vminQf32(<4 x float>* %A, <4 x float>* %B) nounwind {
+;CHECK: vminQf32:
+;CHECK: vmin.f32
 	%tmp1 = load <4 x float>* %A
 	%tmp2 = load <4 x float>* %B
 	%tmp3 = call <4 x float> @llvm.arm.neon.vmins.v4f32(<4 x float> %tmp1, <4 x float> %tmp2)
diff --git a/llvm/test/CodeGen/ARM/vmla.ll b/llvm/test/CodeGen/ARM/vmla.ll
index 3103d7f30b8d..58ac6b057cf4 100644
--- a/llvm/test/CodeGen/ARM/vmla.ll
+++ b/llvm/test/CodeGen/ARM/vmla.ll
@@ -1,10 +1,8 @@
-; RUN: llc < %s -march=arm -mattr=+neon > %t
-; RUN: grep {vmla\\.i8} %t | count 2
-; RUN: grep {vmla\\.i16} %t | count 2
-; RUN: grep {vmla\\.i32} %t | count 2
-; RUN: grep {vmla\\.f32} %t | count 2
+; RUN: llc < %s -march=arm -mattr=+neon | FileCheck %s
 
 define <8 x i8> @vmlai8(<8 x i8>* %A, <8 x i8>* %B, <8 x i8> * %C) nounwind {
+;CHECK: vmlai8:
+;CHECK: vmla.i8
 	%tmp1 = load <8 x i8>* %A
 	%tmp2 = load <8 x i8>* %B
 	%tmp3 = load <8 x i8>* %C
@@ -14,6 +12,8 @@ define <8 x i8> @vmlai8(<8 x i8>* %A, <8 x i8>* %B, <8 x i8> * %C) nounwind {
 }
 
 define <4 x i16> @vmlai16(<4 x i16>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind {
+;CHECK: vmlai16:
+;CHECK: vmla.i16
 	%tmp1 = load <4 x i16>* %A
 	%tmp2 = load <4 x i16>* %B
 	%tmp3 = load <4 x i16>* %C
@@ -23,6 +23,8 @@ define <4 x i16> @vmlai16(<4 x i16>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind
 }
 
 define <2 x i32> @vmlai32(<2 x i32>* %A, <2 x i32>* %B, <2 x i32>* %C) nounwind {
+;CHECK: vmlai32:
+;CHECK: vmla.i32
 	%tmp1 = load <2 x i32>* %A
 	%tmp2 = load <2 x i32>* %B
 	%tmp3 = load <2 x i32>* %C
@@ -32,6 +34,8 @@ define <2 x i32> @vmlai32(<2 x i32>* %A, <2 x i32>* %B, <2 x i32>* %C) nounwind
 }
 
 define <2 x float> @vmlaf32(<2 x float>* %A, <2 x float>* %B, <2 x float>* %C) nounwind {
+;CHECK: vmlaf32:
+;CHECK: vmla.f32
 	%tmp1 = load <2 x float>* %A
 	%tmp2 = load <2 x float>* %B
 	%tmp3 = load <2 x float>* %C
@@ -41,6 +45,8 @@ define <2 x float> @vmlaf32(<2 x float>* %A, <2 x float>* %B, <2 x float>* %C) n
 }
 
 define <16 x i8> @vmlaQi8(<16 x i8>* %A, <16 x i8>* %B, <16 x i8> * %C) nounwind {
+;CHECK: vmlaQi8:
+;CHECK: vmla.i8
 	%tmp1 = load <16 x i8>* %A
 	%tmp2 = load <16 x i8>* %B
 	%tmp3 = load <16 x i8>* %C
@@ -50,6 +56,8 @@ define <16 x i8> @vmlaQi8(<16 x i8>* %A, <16 x i8>* %B, <16 x i8> * %C) nounwind
 }
 
 define <8 x i16> @vmlaQi16(<8 x i16>* %A, <8 x i16>* %B, <8 x i16>* %C) nounwind {
+;CHECK: vmlaQi16:
+;CHECK: vmla.i16
 	%tmp1 = load <8 x i16>* %A
 	%tmp2 = load <8 x i16>* %B
 	%tmp3 = load <8 x i16>* %C
@@ -59,6 +67,8 @@ define <8 x i16> @vmlaQi16(<8 x i16>* %A, <8 x i16>* %B, <8 x i16>* %C) nounwind
 }
 
 define <4 x i32> @vmlaQi32(<4 x i32>* %A, <4 x i32>* %B, <4 x i32>* %C) nounwind {
+;CHECK: vmlaQi32:
+;CHECK: vmla.i32
 	%tmp1 = load <4 x i32>* %A
 	%tmp2 = load <4 x i32>* %B
 	%tmp3 = load <4 x i32>* %C
@@ -68,6 +78,8 @@ define <4 x i32> @vmlaQi32(<4 x i32>* %A, <4 x i32>* %B, <4 x i32>* %C) nounwind
 }
 
 define <4 x float> @vmlaQf32(<4 x float>* %A, <4 x float>* %B, <4 x float>* %C) nounwind {
+;CHECK: vmlaQf32:
+;CHECK: vmla.f32
 	%tmp1 = load <4 x float>* %A
 	%tmp2 = load <4 x float>* %B
 	%tmp3 = load <4 x float>* %C
diff --git a/llvm/test/CodeGen/ARM/vmlal.ll b/llvm/test/CodeGen/ARM/vmlal.ll
index 08c4d88c77c3..6e1897148939 100644
--- a/llvm/test/CodeGen/ARM/vmlal.ll
+++ b/llvm/test/CodeGen/ARM/vmlal.ll
@@ -1,12 +1,8 @@
-; RUN: llc < %s -march=arm -mattr=+neon > %t
-; RUN: grep {vmlal\\.s8} %t | count 1
-; RUN: grep {vmlal\\.s16} %t | count 1
-; RUN: grep {vmlal\\.s32} %t | count 1
-; RUN: grep {vmlal\\.u8} %t | count 1
-; RUN: grep {vmlal\\.u16} %t | count 1
-; RUN: grep {vmlal\\.u32} %t | count 1
+; RUN: llc < %s -march=arm -mattr=+neon | FileCheck %s
 
 define <8 x i16> @vmlals8(<8 x i16>* %A, <8 x i8>* %B, <8 x i8>* %C) nounwind {
+;CHECK: vmlals8:
+;CHECK: vmlal.s8
 	%tmp1 = load <8 x i16>* %A
 	%tmp2 = load <8 x i8>* %B
 	%tmp3 = load <8 x i8>* %C
@@ -15,6 +11,8 @@ define <8 x i16> @vmlals8(<8 x i16>* %A, <8 x i8>* %B, <8 x i8>* %C) nounwind {
 }
 
 define <4 x i32> @vmlals16(<4 x i32>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind {
+;CHECK: vmlals16:
+;CHECK: vmlal.s16
 	%tmp1 = load <4 x i32>* %A
 	%tmp2 = load <4 x i16>* %B
 	%tmp3 = load <4 x i16>* %C
@@ -23,6 +21,8 @@ define <4 x i32> @vmlals16(<4 x i32>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind
 }
 
 define <2 x i64> @vmlals32(<2 x i64>* %A, <2 x i32>* %B, <2 x i32>* %C) nounwind {
+;CHECK: vmlals32:
+;CHECK: vmlal.s32
 	%tmp1 = load <2 x i64>* %A
 	%tmp2 = load <2 x i32>* %B
 	%tmp3 = load <2 x i32>* %C
@@ -31,6 +31,8 @@ define <2 x i64> @vmlals32(<2 x i64>* %A, <2 x i32>* %B, <2 x i32>* %C) nounwind
 }
 
 define <8 x i16> @vmlalu8(<8 x i16>* %A, <8 x i8>* %B, <8 x i8>* %C) nounwind {
+;CHECK: vmlalu8:
+;CHECK: vmlal.u8
 	%tmp1 = load <8 x i16>* %A
 	%tmp2 = load <8 x i8>* %B
 	%tmp3 = load <8 x i8>* %C
@@ -39,6 +41,8 @@ define <8 x i16> @vmlalu8(<8 x i16>* %A, <8 x i8>* %B, <8 x i8>* %C) nounwind {
 }
 
 define <4 x i32> @vmlalu16(<4 x i32>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind {
+;CHECK: vmlalu16:
+;CHECK: vmlal.u16
 	%tmp1 = load <4 x i32>* %A
 	%tmp2 = load <4 x i16>* %B
 	%tmp3 = load <4 x i16>* %C
@@ -47,6 +51,8 @@ define <4 x i32> @vmlalu16(<4 x i32>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind
 }
 
 define <2 x i64> @vmlalu32(<2 x i64>* %A, <2 x i32>* %B, <2 x i32>* %C) nounwind {
+;CHECK: vmlalu32:
+;CHECK: vmlal.u32
 	%tmp1 = load <2 x i64>* %A
 	%tmp2 = load <2 x i32>* %B
 	%tmp3 = load <2 x i32>* %C
diff --git a/llvm/test/CodeGen/ARM/vmls.ll b/llvm/test/CodeGen/ARM/vmls.ll
index d3996a3d091d..0dca6e33755a 100644
--- a/llvm/test/CodeGen/ARM/vmls.ll
+++ b/llvm/test/CodeGen/ARM/vmls.ll
@@ -1,10 +1,8 @@
-; RUN: llc < %s -march=arm -mattr=+neon > %t
-; RUN: grep {vmls\\.i8} %t | count 2
-; RUN: grep {vmls\\.i16} %t | count 2
-; RUN: grep {vmls\\.i32} %t | count 2
-; RUN: grep {vmls\\.f32} %t | count 2
+; RUN: llc < %s -march=arm -mattr=+neon | FileCheck %s
 
 define <8 x i8> @vmlsi8(<8 x i8>* %A, <8 x i8>* %B, <8 x i8> * %C) nounwind {
+;CHECK: vmlsi8:
+;CHECK: vmls.i8
 	%tmp1 = load <8 x i8>* %A
 	%tmp2 = load <8 x i8>* %B
 	%tmp3 = load <8 x i8>* %C
@@ -14,6 +12,8 @@ define <8 x i8> @vmlsi8(<8 x i8>* %A, <8 x i8>* %B, <8 x i8> * %C) nounwind {
 }
 
 define <4 x i16> @vmlsi16(<4 x i16>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind {
+;CHECK: vmlsi16:
+;CHECK: vmls.i16
 	%tmp1 = load <4 x i16>* %A
 	%tmp2 = load <4 x i16>* %B
 	%tmp3 = load <4 x i16>* %C
@@ -23,6 +23,8 @@ define <4 x i16> @vmlsi16(<4 x i16>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind
 }
 
 define <2 x i32> @vmlsi32(<2 x i32>* %A, <2 x i32>* %B, <2 x i32>* %C) nounwind {
+;CHECK: vmlsi32:
+;CHECK: vmls.i32
 	%tmp1 = load <2 x i32>* %A
 	%tmp2 = load <2 x i32>* %B
 	%tmp3 = load <2 x i32>* %C
@@ -32,6 +34,8 @@ define <2 x i32> @vmlsi32(<2 x i32>* %A, <2 x i32>* %B, <2 x i32>* %C) nounwind
 }
 
 define <2 x float> @vmlsf32(<2 x float>* %A, <2 x float>* %B, <2 x float>* %C) nounwind {
+;CHECK: vmlsf32:
+;CHECK: vmls.f32
 	%tmp1 = load <2 x float>* %A
 	%tmp2 = load <2 x float>* %B
 	%tmp3 = load <2 x float>* %C
@@ -41,6 +45,8 @@ define <2 x float> @vmlsf32(<2 x float>* %A, <2 x float>* %B, <2 x float>* %C) n
 }
 
 define <16 x i8> @vmlsQi8(<16 x i8>* %A, <16 x i8>* %B, <16 x i8> * %C) nounwind {
+;CHECK: vmlsQi8:
+;CHECK: vmls.i8
 	%tmp1 = load <16 x i8>* %A
 	%tmp2 = load <16 x i8>* %B
 	%tmp3 = load <16 x i8>* %C
@@ -50,6 +56,8 @@ define <16 x i8> @vmlsQi8(<16 x i8>* %A, <16 x i8>* %B, <16 x i8> * %C) nounwind
 }
 
 define <8 x i16> @vmlsQi16(<8 x i16>* %A, <8 x i16>* %B, <8 x i16>* %C) nounwind {
+;CHECK: vmlsQi16:
+;CHECK: vmls.i16
 	%tmp1 = load <8 x i16>* %A
 	%tmp2 = load <8 x i16>* %B
 	%tmp3 = load <8 x i16>* %C
@@ -59,6 +67,8 @@ define <8 x i16> @vmlsQi16(<8 x i16>* %A, <8 x i16>* %B, <8 x i16>* %C) nounwind
 }
 
 define <4 x i32> @vmlsQi32(<4 x i32>* %A, <4 x i32>* %B, <4 x i32>* %C) nounwind {
+;CHECK: vmlsQi32:
+;CHECK: vmls.i32
 	%tmp1 = load <4 x i32>* %A
 	%tmp2 = load <4 x i32>* %B
 	%tmp3 = load <4 x i32>* %C
@@ -68,6 +78,8 @@ define <4 x i32> @vmlsQi32(<4 x i32>* %A, <4 x i32>* %B, <4 x i32>* %C) nounwind
 }
 
 define <4 x float> @vmlsQf32(<4 x float>* %A, <4 x float>* %B, <4 x float>* %C) nounwind {
+;CHECK: vmlsQf32:
+;CHECK: vmls.f32
 	%tmp1 = load <4 x float>* %A
 	%tmp2 = load <4 x float>* %B
 	%tmp3 = load <4 x float>* %C
diff --git a/llvm/test/CodeGen/ARM/vmlsl.ll b/llvm/test/CodeGen/ARM/vmlsl.ll
index 253157d27a04..a2be79c958e0 100644
--- a/llvm/test/CodeGen/ARM/vmlsl.ll
+++ b/llvm/test/CodeGen/ARM/vmlsl.ll
@@ -1,12 +1,8 @@
-; RUN: llc < %s -march=arm -mattr=+neon > %t
-; RUN: grep {vmlsl\\.s8} %t | count 1
-; RUN: grep {vmlsl\\.s16} %t | count 1
-; RUN: grep {vmlsl\\.s32} %t | count 1
-; RUN: grep {vmlsl\\.u8} %t | count 1
-; RUN: grep {vmlsl\\.u16} %t | count 1
-; RUN: grep {vmlsl\\.u32} %t | count 1
+; RUN: llc < %s -march=arm -mattr=+neon | FileCheck %s
 
 define <8 x i16> @vmlsls8(<8 x i16>* %A, <8 x i8>* %B, <8 x i8>* %C) nounwind {
+;CHECK: vmlsls8:
+;CHECK: vmlsl.s8
 	%tmp1 = load <8 x i16>* %A
 	%tmp2 = load <8 x i8>* %B
 	%tmp3 = load <8 x i8>* %C
@@ -15,6 +11,8 @@ define <8 x i16> @vmlsls8(<8 x i16>* %A, <8 x i8>* %B, <8 x i8>* %C) nounwind {
 }
 
 define <4 x i32> @vmlsls16(<4 x i32>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind {
+;CHECK: vmlsls16:
+;CHECK: vmlsl.s16
 	%tmp1 = load <4 x i32>* %A
 	%tmp2 = load <4 x i16>* %B
 	%tmp3 = load <4 x i16>* %C
@@ -23,6 +21,8 @@ define <4 x i32> @vmlsls16(<4 x i32>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind
 }
 
 define <2 x i64> @vmlsls32(<2 x i64>* %A, <2 x i32>* %B, <2 x i32>* %C) nounwind {
+;CHECK: vmlsls32:
+;CHECK: vmlsl.s32
 	%tmp1 = load <2 x i64>* %A
 	%tmp2 = load <2 x i32>* %B
 	%tmp3 = load <2 x i32>* %C
@@ -31,6 +31,8 @@ define <2 x i64> @vmlsls32(<2 x i64>* %A, <2 x i32>* %B, <2 x i32>* %C) nounwind
 }
 
 define <8 x i16> @vmlslu8(<8 x i16>* %A, <8 x i8>* %B, <8 x i8>* %C) nounwind {
+;CHECK: vmlslu8:
+;CHECK: vmlsl.u8
 	%tmp1 = load <8 x i16>* %A
 	%tmp2 = load <8 x i8>* %B
 	%tmp3 = load <8 x i8>* %C
@@ -39,6 +41,8 @@ define <8 x i16> @vmlslu8(<8 x i16>* %A, <8 x i8>* %B, <8 x i8>* %C) nounwind {
 }
 
 define <4 x i32> @vmlslu16(<4 x i32>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind {
+;CHECK: vmlslu16:
+;CHECK: vmlsl.u16
 	%tmp1 = load <4 x i32>* %A
 	%tmp2 = load <4 x i16>* %B
 	%tmp3 = load <4 x i16>* %C
@@ -47,6 +51,8 @@ define <4 x i32> @vmlslu16(<4 x i32>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind
 }
 
 define <2 x i64> @vmlslu32(<2 x i64>* %A, <2 x i32>* %B, <2 x i32>* %C) nounwind {
+;CHECK: vmlslu32:
+;CHECK: vmlsl.u32
 	%tmp1 = load <2 x i64>* %A
 	%tmp2 = load <2 x i32>* %B
 	%tmp3 = load <2 x i32>* %C