Use CHECK-NEXT to make sure we're only getting one copy of each shuffle

instruction.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@79702 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/test/CodeGen/ARM/vtrn.ll b/test/CodeGen/ARM/vtrn.ll
index 96dfb3ede4805c4d2480adf09f8ab4bce7c46211..3310efc5999fe96b6c9e6c1c23b6d6dd324ebcdd 100644 (file)
--- a/test/CodeGen/ARM/vtrn.ll
+++ b/test/CodeGen/ARM/vtrn.ll
@@ -13,6 +13,7 @@
 define <8 x i8> @vtrni8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
 ;CHECK: vtrni8:
 ;CHECK: vtrn.8
+;CHECK-NEXT: vadd.i8
        %tmp1 = load <8 x i8>* %A
        %tmp2 = load <8 x i8>* %B
        %tmp3 = shufflevector <8 x i8> %tmp1, <8 x i8> %tmp2, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
@@ -24,6 +25,7 @@ define <8 x i8> @vtrni8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
 define <4 x i16> @vtrni16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
 ;CHECK: vtrni16:
 ;CHECK: vtrn.16
+;CHECK-NEXT: vadd.i16
        %tmp1 = load <4 x i16>* %A
        %tmp2 = load <4 x i16>* %B
        %tmp3 = shufflevector <4 x i16> %tmp1, <4 x i16> %tmp2, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
@@ -35,6 +37,7 @@ define <4 x i16> @vtrni16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
 define <2 x i32> @vtrni32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
 ;CHECK: vtrni32:
 ;CHECK: vtrn.32
+;CHECK-NEXT: vadd.i32
        %tmp1 = load <2 x i32>* %A
        %tmp2 = load <2 x i32>* %B
        %tmp3 = shufflevector <2 x i32> %tmp1, <2 x i32> %tmp2, <2 x i32> <i32 0, i32 2>
@@ -46,6 +49,7 @@ define <2 x i32> @vtrni32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
 define <2 x float> @vtrnf(<2 x float>* %A, <2 x float>* %B) nounwind {
 ;CHECK: vtrnf:
 ;CHECK: vtrn.32
+;CHECK-NEXT: vadd.f32
        %tmp1 = load <2 x float>* %A
        %tmp2 = load <2 x float>* %B
        %tmp3 = shufflevector <2 x float> %tmp1, <2 x float> %tmp2, <2 x i32> <i32 0, i32 2>
@@ -57,6 +61,7 @@ define <2 x float> @vtrnf(<2 x float>* %A, <2 x float>* %B) nounwind {
 define <16 x i8> @vtrnQi8(<16 x i8>* %A, <16 x i8>* %B) nounwind {
 ;CHECK: vtrnQi8:
 ;CHECK: vtrn.8
+;CHECK-NEXT: vadd.i8
        %tmp1 = load <16 x i8>* %A
        %tmp2 = load <16 x i8>* %B
        %tmp3 = shufflevector <16 x i8> %tmp1, <16 x i8> %tmp2, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
@@ -68,6 +73,7 @@ define <16 x i8> @vtrnQi8(<16 x i8>* %A, <16 x i8>* %B) nounwind {
 define <8 x i16> @vtrnQi16(<8 x i16>* %A, <8 x i16>* %B) nounwind {
 ;CHECK: vtrnQi16:
 ;CHECK: vtrn.16
+;CHECK-NEXT: vadd.i16
        %tmp1 = load <8 x i16>* %A
        %tmp2 = load <8 x i16>* %B
        %tmp3 = shufflevector <8 x i16> %tmp1, <8 x i16> %tmp2, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
@@ -79,6 +85,7 @@ define <8 x i16> @vtrnQi16(<8 x i16>* %A, <8 x i16>* %B) nounwind {
 define <4 x i32> @vtrnQi32(<4 x i32>* %A, <4 x i32>* %B) nounwind {
 ;CHECK: vtrnQi32:
 ;CHECK: vtrn.32
+;CHECK-NEXT: vadd.i32
        %tmp1 = load <4 x i32>* %A
        %tmp2 = load <4 x i32>* %B
        %tmp3 = shufflevector <4 x i32> %tmp1, <4 x i32> %tmp2, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
@@ -90,6 +97,7 @@ define <4 x i32> @vtrnQi32(<4 x i32>* %A, <4 x i32>* %B) nounwind {
 define <4 x float> @vtrnQf(<4 x float>* %A, <4 x float>* %B) nounwind {
 ;CHECK: vtrnQf:
 ;CHECK: vtrn.32
+;CHECK-NEXT: vadd.f32
        %tmp1 = load <4 x float>* %A
        %tmp2 = load <4 x float>* %B
        %tmp3 = shufflevector <4 x float> %tmp1, <4 x float> %tmp2, <4 x i32> <i32 0, i32 4, i32 2, i32 6>

diff --git a/test/CodeGen/ARM/vuzp.ll b/test/CodeGen/ARM/vuzp.ll
index 35beae36fb62d59a0793ca0b94b6e8336d00d2e8..e901e66be01dbe713196e56ef4a02d816963a9b7 100644 (file)
--- a/test/CodeGen/ARM/vuzp.ll
+++ b/test/CodeGen/ARM/vuzp.ll
@@ -13,6 +13,7 @@
 define <8 x i8> @vuzpi8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
 ;CHECK: vuzpi8:
 ;CHECK: vuzp.8
+;CHECK-NEXT: vadd.i8
        %tmp1 = load <8 x i8>* %A
        %tmp2 = load <8 x i8>* %B
        %tmp3 = shufflevector <8 x i8> %tmp1, <8 x i8> %tmp2, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14>
@@ -24,6 +25,7 @@ define <8 x i8> @vuzpi8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
 define <4 x i16> @vuzpi16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
 ;CHECK: vuzpi16:
 ;CHECK: vuzp.16
+;CHECK-NEXT: vadd.i16
        %tmp1 = load <4 x i16>* %A
        %tmp2 = load <4 x i16>* %B
        %tmp3 = shufflevector <4 x i16> %tmp1, <4 x i16> %tmp2, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
@@ -37,6 +39,7 @@ define <4 x i16> @vuzpi16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
 define <16 x i8> @vuzpQi8(<16 x i8>* %A, <16 x i8>* %B) nounwind {
 ;CHECK: vuzpQi8:
 ;CHECK: vuzp.8
+;CHECK-NEXT: vadd.i8
        %tmp1 = load <16 x i8>* %A
        %tmp2 = load <16 x i8>* %B
        %tmp3 = shufflevector <16 x i8> %tmp1, <16 x i8> %tmp2, <16 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14, i32 16, i32 18, i32 20, i32 22, i32 24, i32 26, i32 28, i32 30>
@@ -48,6 +51,7 @@ define <16 x i8> @vuzpQi8(<16 x i8>* %A, <16 x i8>* %B) nounwind {
 define <8 x i16> @vuzpQi16(<8 x i16>* %A, <8 x i16>* %B) nounwind {
 ;CHECK: vuzpQi16:
 ;CHECK: vuzp.16
+;CHECK-NEXT: vadd.i16
        %tmp1 = load <8 x i16>* %A
        %tmp2 = load <8 x i16>* %B
        %tmp3 = shufflevector <8 x i16> %tmp1, <8 x i16> %tmp2, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14>
@@ -59,6 +63,7 @@ define <8 x i16> @vuzpQi16(<8 x i16>* %A, <8 x i16>* %B) nounwind {
 define <4 x i32> @vuzpQi32(<4 x i32>* %A, <4 x i32>* %B) nounwind {
 ;CHECK: vuzpQi32:
 ;CHECK: vuzp.32
+;CHECK-NEXT: vadd.i32
        %tmp1 = load <4 x i32>* %A
        %tmp2 = load <4 x i32>* %B
        %tmp3 = shufflevector <4 x i32> %tmp1, <4 x i32> %tmp2, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
@@ -70,6 +75,7 @@ define <4 x i32> @vuzpQi32(<4 x i32>* %A, <4 x i32>* %B) nounwind {
 define <4 x float> @vuzpQf(<4 x float>* %A, <4 x float>* %B) nounwind {
 ;CHECK: vuzpQf:
 ;CHECK: vuzp.32
+;CHECK-NEXT: vadd.f32
        %tmp1 = load <4 x float>* %A
        %tmp2 = load <4 x float>* %B
        %tmp3 = shufflevector <4 x float> %tmp1, <4 x float> %tmp2, <4 x i32> <i32 0, i32 2, i32 4, i32 6>

diff --git a/test/CodeGen/ARM/vzip.ll b/test/CodeGen/ARM/vzip.ll
index f8946558b4fc6d9901e19ce9cf2cc46843b76902..5927ea613d5acc967cff5716328aa1ee1cf7b8e0 100644 (file)
--- a/test/CodeGen/ARM/vzip.ll
+++ b/test/CodeGen/ARM/vzip.ll
@@ -13,6 +13,7 @@
 define <8 x i8> @vzipi8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
 ;CHECK: vzipi8:
 ;CHECK: vzip.8
+;CHECK-NEXT: vadd.i8
        %tmp1 = load <8 x i8>* %A
        %tmp2 = load <8 x i8>* %B
        %tmp3 = shufflevector <8 x i8> %tmp1, <8 x i8> %tmp2, <8 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11>
@@ -24,6 +25,7 @@ define <8 x i8> @vzipi8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
 define <4 x i16> @vzipi16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
 ;CHECK: vzipi16:
 ;CHECK: vzip.16
+;CHECK-NEXT: vadd.i16
        %tmp1 = load <4 x i16>* %A
        %tmp2 = load <4 x i16>* %B
        %tmp3 = shufflevector <4 x i16> %tmp1, <4 x i16> %tmp2, <4 x i32> <i32 0, i32 4, i32 1, i32 5>
@@ -37,6 +39,7 @@ define <4 x i16> @vzipi16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
 define <16 x i8> @vzipQi8(<16 x i8>* %A, <16 x i8>* %B) nounwind {
 ;CHECK: vzipQi8:
 ;CHECK: vzip.8
+;CHECK-NEXT: vadd.i8
        %tmp1 = load <16 x i8>* %A
        %tmp2 = load <16 x i8>* %B
        %tmp3 = shufflevector <16 x i8> %tmp1, <16 x i8> %tmp2, <16 x i32> <i32 0, i32 16, i32 1, i32 17, i32 2, i32 18, i32 3, i32 19, i32 4, i32 20, i32 5, i32 21, i32 6, i32 22, i32 7, i32 23>
@@ -48,6 +51,7 @@ define <16 x i8> @vzipQi8(<16 x i8>* %A, <16 x i8>* %B) nounwind {
 define <8 x i16> @vzipQi16(<8 x i16>* %A, <8 x i16>* %B) nounwind {
 ;CHECK: vzipQi16:
 ;CHECK: vzip.16
+;CHECK-NEXT: vadd.i16
        %tmp1 = load <8 x i16>* %A
        %tmp2 = load <8 x i16>* %B
        %tmp3 = shufflevector <8 x i16> %tmp1, <8 x i16> %tmp2, <8 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11>
@@ -59,6 +63,7 @@ define <8 x i16> @vzipQi16(<8 x i16>* %A, <8 x i16>* %B) nounwind {
 define <4 x i32> @vzipQi32(<4 x i32>* %A, <4 x i32>* %B) nounwind {
 ;CHECK: vzipQi32:
 ;CHECK: vzip.32
+;CHECK-NEXT: vadd.i32
        %tmp1 = load <4 x i32>* %A
        %tmp2 = load <4 x i32>* %B
        %tmp3 = shufflevector <4 x i32> %tmp1, <4 x i32> %tmp2, <4 x i32> <i32 0, i32 4, i32 1, i32 5>
@@ -70,6 +75,7 @@ define <4 x i32> @vzipQi32(<4 x i32>* %A, <4 x i32>* %B) nounwind {
 define <4 x float> @vzipQf(<4 x float>* %A, <4 x float>* %B) nounwind {
 ;CHECK: vzipQf:
 ;CHECK: vzip.32
+;CHECK-NEXT: vadd.f32
        %tmp1 = load <4 x float>* %A
        %tmp2 = load <4 x float>* %B
        %tmp3 = shufflevector <4 x float> %tmp1, <4 x float> %tmp2, <4 x i32> <i32 0, i32 4, i32 1, i32 5>