Convert more NEON tests to use FileCheck.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@83507 91177308-0d34-0410-b5e6-96231b3b80d8

6 files changed, 114 insertions, 35 deletions

diff --git a/test/CodeGen/ARM/vmov.ll b/test/CodeGen/ARM/vmov.ll
index c4cb204..f43266c 100644
--- a/test/CodeGen/ARM/vmov.ll
+++ b/test/CodeGen/ARM/vmov.ll
@@ -1,101 +1,135 @@
-; RUN: llc < %s -march=arm -mattr=+neon > %t
-; RUN: grep vmov.i8 %t | count 2
-; RUN: grep vmov.i16 %t | count 4
-; RUN: grep vmov.i32 %t | count 12
-; RUN: grep vmov.i64 %t | count 2
-; Note: function names do not include "vmov" to allow simple grep for opcodes
+; RUN: llc < %s -march=arm -mattr=+neon | FileCheck %s
 
 define <8 x i8> @v_movi8() nounwind {
+;CHECK: v_movi8:
+;CHECK: vmov.i8
 	ret <8 x i8> < i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8 >
 }
 
 define <4 x i16> @v_movi16a() nounwind {
+;CHECK: v_movi16a:
+;CHECK: vmov.i16
 	ret <4 x i16> < i16 16, i16 16, i16 16, i16 16 >
 }
 
 ; 0x1000 = 4096
 define <4 x i16> @v_movi16b() nounwind {
+;CHECK: v_movi16b:
+;CHECK: vmov.i16
 	ret <4 x i16> < i16 4096, i16 4096, i16 4096, i16 4096 >
 }
 
 define <2 x i32> @v_movi32a() nounwind {
+;CHECK: v_movi32a:
+;CHECK: vmov.i32
 	ret <2 x i32> < i32 32, i32 32 >
 }
 
 ; 0x2000 = 8192
 define <2 x i32> @v_movi32b() nounwind {
+;CHECK: v_movi32b:
+;CHECK: vmov.i32
 	ret <2 x i32> < i32 8192, i32 8192 >
 }
 
 ; 0x200000 = 2097152
 define <2 x i32> @v_movi32c() nounwind {
+;CHECK: v_movi32c:
+;CHECK: vmov.i32
 	ret <2 x i32> < i32 2097152, i32 2097152 >
 }
 
 ; 0x20000000 = 536870912
 define <2 x i32> @v_movi32d() nounwind {
+;CHECK: v_movi32d:
+;CHECK: vmov.i32
 	ret <2 x i32> < i32 536870912, i32 536870912 >
 }
 
 ; 0x20ff = 8447
 define <2 x i32> @v_movi32e() nounwind {
+;CHECK: v_movi32e:
+;CHECK: vmov.i32
 	ret <2 x i32> < i32 8447, i32 8447 >
 }
 
 ; 0x20ffff = 2162687
 define <2 x i32> @v_movi32f() nounwind {
+;CHECK: v_movi32f:
+;CHECK: vmov.i32
 	ret <2 x i32> < i32 2162687, i32 2162687 >
 }
 
 ; 0xff0000ff0000ffff = 18374687574888349695
 define <1 x i64> @v_movi64() nounwind {
+;CHECK: v_movi64:
+;CHECK: vmov.i64
 	ret <1 x i64> < i64 18374687574888349695 >
 }
 
 define <16 x i8> @v_movQi8() nounwind {
+;CHECK: v_movQi8:
+;CHECK: vmov.i8
 	ret <16 x i8> < i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8 >
 }
 
 define <8 x i16> @v_movQi16a() nounwind {
+;CHECK: v_movQi16a:
+;CHECK: vmov.i16
 	ret <8 x i16> < i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16 >
 }
 
 ; 0x1000 = 4096
 define <8 x i16> @v_movQi16b() nounwind {
+;CHECK: v_movQi16b:
+;CHECK: vmov.i16
 	ret <8 x i16> < i16 4096, i16 4096, i16 4096, i16 4096, i16 4096, i16 4096, i16 4096, i16 4096 >
 }
 
 define <4 x i32> @v_movQi32a() nounwind {
+;CHECK: v_movQi32a:
+;CHECK: vmov.i32
 	ret <4 x i32> < i32 32, i32 32, i32 32, i32 32 >
 }
 
 ; 0x2000 = 8192
 define <4 x i32> @v_movQi32b() nounwind {
+;CHECK: v_movQi32b:
+;CHECK: vmov.i32
 	ret <4 x i32> < i32 8192, i32 8192, i32 8192, i32 8192 >
 }
 
 ; 0x200000 = 2097152
 define <4 x i32> @v_movQi32c() nounwind {
+;CHECK: v_movQi32c:
+;CHECK: vmov.i32
 	ret <4 x i32> < i32 2097152, i32 2097152, i32 2097152, i32 2097152 >
 }
 
 ; 0x20000000 = 536870912
 define <4 x i32> @v_movQi32d() nounwind {
+;CHECK: v_movQi32d:
+;CHECK: vmov.i32
 	ret <4 x i32> < i32 536870912, i32 536870912, i32 536870912, i32 536870912 >
 }
 
 ; 0x20ff = 8447
 define <4 x i32> @v_movQi32e() nounwind {
+;CHECK: v_movQi32e:
+;CHECK: vmov.i32
 	ret <4 x i32> < i32 8447, i32 8447, i32 8447, i32 8447 >
 }
 
 ; 0x20ffff = 2162687
 define <4 x i32> @v_movQi32f() nounwind {
+;CHECK: v_movQi32f:
+;CHECK: vmov.i32
 	ret <4 x i32> < i32 2162687, i32 2162687, i32 2162687, i32 2162687 >
 }
 
 ; 0xff0000ff0000ffff = 18374687574888349695
 define <2 x i64> @v_movQi64() nounwind {
+;CHECK: v_movQi64:
+;CHECK: vmov.i64
 	ret <2 x i64> < i64 18374687574888349695, i64 18374687574888349695 >
 }
-
diff --git a/test/CodeGen/ARM/vmovl.ll b/test/CodeGen/ARM/vmovl.ll
index 4757680..beb1613 100644
--- a/test/CodeGen/ARM/vmovl.ll
+++ b/test/CodeGen/ARM/vmovl.ll
@@ -1,42 +1,48 @@
-; RUN: llc < %s -march=arm -mattr=+neon > %t
-; RUN: grep {vmovl\\.s8} %t | count 1
-; RUN: grep {vmovl\\.s16} %t | count 1
-; RUN: grep {vmovl\\.s32} %t | count 1
-; RUN: grep {vmovl\\.u8} %t | count 1
-; RUN: grep {vmovl\\.u16} %t | count 1
-; RUN: grep {vmovl\\.u32} %t | count 1
+; RUN: llc < %s -march=arm -mattr=+neon | FileCheck %s
 
 define <8 x i16> @vmovls8(<8 x i8>* %A) nounwind {
+;CHECK: vmovls8:
+;CHECK: vmovl.s8
 	%tmp1 = load <8 x i8>* %A
 	%tmp2 = call <8 x i16> @llvm.arm.neon.vmovls.v8i16(<8 x i8> %tmp1)
 	ret <8 x i16> %tmp2
 }
 
 define <4 x i32> @vmovls16(<4 x i16>* %A) nounwind {
+;CHECK: vmovls16:
+;CHECK: vmovl.s16
 	%tmp1 = load <4 x i16>* %A
 	%tmp2 = call <4 x i32> @llvm.arm.neon.vmovls.v4i32(<4 x i16> %tmp1)
 	ret <4 x i32> %tmp2
 }
 
 define <2 x i64> @vmovls32(<2 x i32>* %A) nounwind {
+;CHECK: vmovls32:
+;CHECK: vmovl.s32
 	%tmp1 = load <2 x i32>* %A
 	%tmp2 = call <2 x i64> @llvm.arm.neon.vmovls.v2i64(<2 x i32> %tmp1)
 	ret <2 x i64> %tmp2
 }
 
 define <8 x i16> @vmovlu8(<8 x i8>* %A) nounwind {
+;CHECK: vmovlu8:
+;CHECK: vmovl.u8
 	%tmp1 = load <8 x i8>* %A
 	%tmp2 = call <8 x i16> @llvm.arm.neon.vmovlu.v8i16(<8 x i8> %tmp1)
 	ret <8 x i16> %tmp2
 }
 
 define <4 x i32> @vmovlu16(<4 x i16>* %A) nounwind {
+;CHECK: vmovlu16:
+;CHECK: vmovl.u16
 	%tmp1 = load <4 x i16>* %A
 	%tmp2 = call <4 x i32> @llvm.arm.neon.vmovlu.v4i32(<4 x i16> %tmp1)
 	ret <4 x i32> %tmp2
 }
 
 define <2 x i64> @vmovlu32(<2 x i32>* %A) nounwind {
+;CHECK: vmovlu32:
+;CHECK: vmovl.u32
 	%tmp1 = load <2 x i32>* %A
 	%tmp2 = call <2 x i64> @llvm.arm.neon.vmovlu.v2i64(<2 x i32> %tmp1)
 	ret <2 x i64> %tmp2
diff --git a/test/CodeGen/ARM/vmovn.ll b/test/CodeGen/ARM/vmovn.ll
index 173bb52..7bf049f 100644
--- a/test/CodeGen/ARM/vmovn.ll
+++ b/test/CodeGen/ARM/vmovn.ll
@@ -1,21 +1,24 @@
-; RUN: llc < %s -march=arm -mattr=+neon > %t
-; RUN: grep {vmovn\\.i16} %t | count 1
-; RUN: grep {vmovn\\.i32} %t | count 1
-; RUN: grep {vmovn\\.i64} %t | count 1
+; RUN: llc < %s -march=arm -mattr=+neon | FileCheck %s
 
 define <8 x i8> @vmovni16(<8 x i16>* %A) nounwind {
+;CHECK: vmovni16:
+;CHECK: vmovn.i16
 	%tmp1 = load <8 x i16>* %A
 	%tmp2 = call <8 x i8> @llvm.arm.neon.vmovn.v8i8(<8 x i16> %tmp1)
 	ret <8 x i8> %tmp2
 }
 
 define <4 x i16> @vmovni32(<4 x i32>* %A) nounwind {
+;CHECK: vmovni32:
+;CHECK: vmovn.i32
 	%tmp1 = load <4 x i32>* %A
 	%tmp2 = call <4 x i16> @llvm.arm.neon.vmovn.v4i16(<4 x i32> %tmp1)
 	ret <4 x i16> %tmp2
 }
 
 define <2 x i32> @vmovni64(<2 x i64>* %A) nounwind {
+;CHECK: vmovni64:
+;CHECK: vmovn.i64
 	%tmp1 = load <2 x i64>* %A
 	%tmp2 = call <2 x i32> @llvm.arm.neon.vmovn.v2i32(<2 x i64> %tmp1)
 	ret <2 x i32> %tmp2
diff --git a/test/CodeGen/ARM/vmul.ll b/test/CodeGen/ARM/vmul.ll
index 38abcca..83ec55e 100644
--- a/test/CodeGen/ARM/vmul.ll
+++ b/test/CodeGen/ARM/vmul.ll
@@ -1,11 +1,8 @@
-; RUN: llc < %s -march=arm -mattr=+neon > %t
-; RUN: grep {vmul\\.i8} %t | count 2
-; RUN: grep {vmul\\.i16} %t | count 2
-; RUN: grep {vmul\\.i32} %t | count 2
-; RUN: grep {vmul\\.f32} %t | count 2
-; RUN: grep {vmul\\.p8} %t | count 2
+; RUN: llc < %s -march=arm -mattr=+neon | FileCheck %s
 
 define <8 x i8> @vmuli8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
+;CHECK: vmuli8:
+;CHECK: vmul.i8
 	%tmp1 = load <8 x i8>* %A
 	%tmp2 = load <8 x i8>* %B
 	%tmp3 = mul <8 x i8> %tmp1, %tmp2
@@ -13,6 +10,8 @@ define <8 x i8> @vmuli8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
 }
 
 define <4 x i16> @vmuli16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
+;CHECK: vmuli16:
+;CHECK: vmul.i16
 	%tmp1 = load <4 x i16>* %A
 	%tmp2 = load <4 x i16>* %B
 	%tmp3 = mul <4 x i16> %tmp1, %tmp2
@@ -20,6 +19,8 @@ define <4 x i16> @vmuli16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
 }
 
 define <2 x i32> @vmuli32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
+;CHECK: vmuli32:
+;CHECK: vmul.i32
 	%tmp1 = load <2 x i32>* %A
 	%tmp2 = load <2 x i32>* %B
 	%tmp3 = mul <2 x i32> %tmp1, %tmp2
@@ -27,6 +28,8 @@ define <2 x i32> @vmuli32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
 }
 
 define <2 x float> @vmulf32(<2 x float>* %A, <2 x float>* %B) nounwind {
+;CHECK: vmulf32:
+;CHECK: vmul.f32
 	%tmp1 = load <2 x float>* %A
 	%tmp2 = load <2 x float>* %B
 	%tmp3 = mul <2 x float> %tmp1, %tmp2
@@ -34,6 +37,8 @@ define <2 x float> @vmulf32(<2 x float>* %A, <2 x float>* %B) nounwind {
 }
 
 define <8 x i8> @vmulp8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
+;CHECK: vmulp8:
+;CHECK: vmul.p8
 	%tmp1 = load <8 x i8>* %A
 	%tmp2 = load <8 x i8>* %B
 	%tmp3 = call <8 x i8> @llvm.arm.neon.vmulp.v8i8(<8 x i8> %tmp1, <8 x i8> %tmp2)
@@ -41,6 +46,8 @@ define <8 x i8> @vmulp8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
 }
 
 define <16 x i8> @vmulQi8(<16 x i8>* %A, <16 x i8>* %B) nounwind {
+;CHECK: vmulQi8:
+;CHECK: vmul.i8
 	%tmp1 = load <16 x i8>* %A
 	%tmp2 = load <16 x i8>* %B
 	%tmp3 = mul <16 x i8> %tmp1, %tmp2
@@ -48,6 +55,8 @@ define <16 x i8> @vmulQi8(<16 x i8>* %A, <16 x i8>* %B) nounwind {
 }
 
 define <8 x i16> @vmulQi16(<8 x i16>* %A, <8 x i16>* %B) nounwind {
+;CHECK: vmulQi16:
+;CHECK: vmul.i16
 	%tmp1 = load <8 x i16>* %A
 	%tmp2 = load <8 x i16>* %B
 	%tmp3 = mul <8 x i16> %tmp1, %tmp2
@@ -55,6 +64,8 @@ define <8 x i16> @vmulQi16(<8 x i16>* %A, <8 x i16>* %B) nounwind {
 }
 
 define <4 x i32> @vmulQi32(<4 x i32>* %A, <4 x i32>* %B) nounwind {
+;CHECK: vmulQi32:
+;CHECK: vmul.i32
 	%tmp1 = load <4 x i32>* %A
 	%tmp2 = load <4 x i32>* %B
 	%tmp3 = mul <4 x i32> %tmp1, %tmp2
@@ -62,6 +73,8 @@ define <4 x i32> @vmulQi32(<4 x i32>* %A, <4 x i32>* %B) nounwind {
 }
 
 define <4 x float> @vmulQf32(<4 x float>* %A, <4 x float>* %B) nounwind {
+;CHECK: vmulQf32:
+;CHECK: vmul.f32
 	%tmp1 = load <4 x float>* %A
 	%tmp2 = load <4 x float>* %B
 	%tmp3 = mul <4 x float> %tmp1, %tmp2
@@ -69,6 +82,8 @@ define <4 x float> @vmulQf32(<4 x float>* %A, <4 x float>* %B) nounwind {
 }
 
 define <16 x i8> @vmulQp8(<16 x i8>* %A, <16 x i8>* %B) nounwind {
+;CHECK: vmulQp8:
+;CHECK: vmul.p8
 	%tmp1 = load <16 x i8>* %A
 	%tmp2 = load <16 x i8>* %B
 	%tmp3 = call <16 x i8> @llvm.arm.neon.vmulp.v16i8(<16 x i8> %tmp1, <16 x i8> %tmp2)
diff --git a/test/CodeGen/ARM/vmull.ll b/test/CodeGen/ARM/vmull.ll
index c3bd141..56149da 100644
--- a/test/CodeGen/ARM/vmull.ll
+++ b/test/CodeGen/ARM/vmull.ll
@@ -1,13 +1,8 @@
-; RUN: llc < %s -march=arm -mattr=+neon > %t
-; RUN: grep {vmull\\.s8} %t | count 1
-; RUN: grep {vmull\\.s16} %t | count 1
-; RUN: grep {vmull\\.s32} %t | count 1
-; RUN: grep {vmull\\.u8} %t | count 1
-; RUN: grep {vmull\\.u16} %t | count 1
-; RUN: grep {vmull\\.u32} %t | count 1
-; RUN: grep {vmull\\.p8} %t | count 1
+; RUN: llc < %s -march=arm -mattr=+neon | FileCheck %s
 
 define <8 x i16> @vmulls8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
+;CHECK: vmulls8:
+;CHECK: vmull.s8
 	%tmp1 = load <8 x i8>* %A
 	%tmp2 = load <8 x i8>* %B
 	%tmp3 = call <8 x i16> @llvm.arm.neon.vmulls.v8i16(<8 x i8> %tmp1, <8 x i8> %tmp2)
@@ -15,6 +10,8 @@ define <8 x i16> @vmulls8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
 }
 
 define <4 x i32> @vmulls16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
+;CHECK: vmulls16:
+;CHECK: vmull.s16
 	%tmp1 = load <4 x i16>* %A
 	%tmp2 = load <4 x i16>* %B
 	%tmp3 = call <4 x i32> @llvm.arm.neon.vmulls.v4i32(<4 x i16> %tmp1, <4 x i16> %tmp2)
@@ -22,6 +19,8 @@ define <4 x i32> @vmulls16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
 }
 
 define <2 x i64> @vmulls32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
+;CHECK: vmulls32:
+;CHECK: vmull.s32
 	%tmp1 = load <2 x i32>* %A
 	%tmp2 = load <2 x i32>* %B
 	%tmp3 = call <2 x i64> @llvm.arm.neon.vmulls.v2i64(<2 x i32> %tmp1, <2 x i32> %tmp2)
@@ -29,6 +28,8 @@ define <2 x i64> @vmulls32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
 }
 
 define <8 x i16> @vmullu8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
+;CHECK: vmullu8:
+;CHECK: vmull.u8
 	%tmp1 = load <8 x i8>* %A
 	%tmp2 = load <8 x i8>* %B
 	%tmp3 = call <8 x i16> @llvm.arm.neon.vmullu.v8i16(<8 x i8> %tmp1, <8 x i8> %tmp2)
@@ -36,6 +37,8 @@ define <8 x i16> @vmullu8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
 }
 
 define <4 x i32> @vmullu16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
+;CHECK: vmullu16:
+;CHECK: vmull.u16
 	%tmp1 = load <4 x i16>* %A
 	%tmp2 = load <4 x i16>* %B
 	%tmp3 = call <4 x i32> @llvm.arm.neon.vmullu.v4i32(<4 x i16> %tmp1, <4 x i16> %tmp2)
@@ -43,6 +46,8 @@ define <4 x i32> @vmullu16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
 }
 
 define <2 x i64> @vmullu32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
+;CHECK: vmullu32:
+;CHECK: vmull.u32
 	%tmp1 = load <2 x i32>* %A
 	%tmp2 = load <2 x i32>* %B
 	%tmp3 = call <2 x i64> @llvm.arm.neon.vmullu.v2i64(<2 x i32> %tmp1, <2 x i32> %tmp2)
@@ -50,6 +55,8 @@ define <2 x i64> @vmullu32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
 }
 
 define <8 x i16> @vmullp8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
+;CHECK: vmullp8:
+;CHECK: vmull.p8
 	%tmp1 = load <8 x i8>* %A
 	%tmp2 = load <8 x i8>* %B
 	%tmp3 = call <8 x i16> @llvm.arm.neon.vmullp.v8i16(<8 x i8> %tmp1, <8 x i8> %tmp2)
diff --git a/test/CodeGen/ARM/vmvn.ll b/test/CodeGen/ARM/vmvn.ll
index f71777b..d756b76 100644
--- a/test/CodeGen/ARM/vmvn.ll
+++ b/test/CodeGen/ARM/vmvn.ll
@@ -1,50 +1,64 @@
-; RUN: llc < %s -march=arm -mattr=+neon > %t
-; RUN: grep vmvn %t | count 8
-; Note: function names do not include "vmvn" to allow simple grep for opcodes
+; RUN: llc < %s -march=arm -mattr=+neon | FileCheck %s
 
 define <8 x i8> @v_mvni8(<8 x i8>* %A) nounwind {
+;CHECK: v_mvni8:
+;CHECK: vmvn
 	%tmp1 = load <8 x i8>* %A
 	%tmp2 = xor <8 x i8> %tmp1, < i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1 >
 	ret <8 x i8> %tmp2
 }
 
 define <4 x i16> @v_mvni16(<4 x i16>* %A) nounwind {
+;CHECK: v_mvni16:
+;CHECK: vmvn
 	%tmp1 = load <4 x i16>* %A
 	%tmp2 = xor <4 x i16> %tmp1, < i16 -1, i16 -1, i16 -1, i16 -1 >
 	ret <4 x i16> %tmp2
 }
 
 define <2 x i32> @v_mvni32(<2 x i32>* %A) nounwind {
+;CHECK: v_mvni32:
+;CHECK: vmvn
 	%tmp1 = load <2 x i32>* %A
 	%tmp2 = xor <2 x i32> %tmp1, < i32 -1, i32 -1 >
 	ret <2 x i32> %tmp2
 }
 
 define <1 x i64> @v_mvni64(<1 x i64>* %A) nounwind {
+;CHECK: v_mvni64:
+;CHECK: vmvn
 	%tmp1 = load <1 x i64>* %A
 	%tmp2 = xor <1 x i64> %tmp1, < i64 -1 >
 	ret <1 x i64> %tmp2
 }
 
 define <16 x i8> @v_mvnQi8(<16 x i8>* %A) nounwind {
+;CHECK: v_mvnQi8:
+;CHECK: vmvn
 	%tmp1 = load <16 x i8>* %A
 	%tmp2 = xor <16 x i8> %tmp1, < i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1 >
 	ret <16 x i8> %tmp2
 }
 
 define <8 x i16> @v_mvnQi16(<8 x i16>* %A) nounwind {
+;CHECK: v_mvnQi16:
+;CHECK: vmvn
 	%tmp1 = load <8 x i16>* %A
 	%tmp2 = xor <8 x i16> %tmp1, < i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1 >
 	ret <8 x i16> %tmp2
 }
 
 define <4 x i32> @v_mvnQi32(<4 x i32>* %A) nounwind {
+;CHECK: v_mvnQi32:
+;CHECK: vmvn
 	%tmp1 = load <4 x i32>* %A
 	%tmp2 = xor <4 x i32> %tmp1, < i32 -1, i32 -1, i32 -1, i32 -1 >
 	ret <4 x i32> %tmp2
 }
 
 define <2 x i64> @v_mvnQi64(<2 x i64>* %A) nounwind {
+;CHECK: v_mvnQi64:
+;CHECK: vmvn
 	%tmp1 = load <2 x i64>* %A
 	%tmp2 = xor <2 x i64> %tmp1, < i64 -1, i64 -1 >
 	ret <2 x i64> %tmp2