[mips] MIPS-IV is broadly the same as MIPS64 so duplicate all -mcpu=mips64 tests...

[oota-llvm.git] / test / CodeGen / ARM / vzip.ll

diff --git a/test/CodeGen/ARM/vzip.ll b/test/CodeGen/ARM/vzip.ll
index 5927ea613d5acc967cff5716328aa1ee1cf7b8e0..f74dc62599cffdd1470f5d9479b5afc29c7a1202 100644 (file)
--- a/test/CodeGen/ARM/vzip.ll
+++ b/test/CodeGen/ARM/vzip.ll
@@ -1,17 +1,7 @@
-; RUN: llvm-as < %s | llc -march=arm -mattr=+neon | FileCheck %s
-
-%struct.__builtin_neon_v8qi2 = type { <8 x i8>,  <8 x i8> }
-%struct.__builtin_neon_v4hi2 = type { <4 x i16>, <4 x i16> }
-%struct.__builtin_neon_v2si2 = type { <2 x i32>, <2 x i32> }
-%struct.__builtin_neon_v2sf2 = type { <2 x float>, <2 x float> }
-
-%struct.__builtin_neon_v16qi2 = type { <16 x i8>, <16 x i8> }
-%struct.__builtin_neon_v8hi2  = type { <8 x i16>, <8 x i16> }
-%struct.__builtin_neon_v4si2  = type { <4 x i32>, <4 x i32> }
-%struct.__builtin_neon_v4sf2  = type { <4 x float>, <4 x float> }
+; RUN: llc -mtriple=arm-eabi -mattr=+neon %s -o - | FileCheck %s
 
 define <8 x i8> @vzipi8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
-;CHECK: vzipi8:
+;CHECK-LABEL: vzipi8:
 ;CHECK: vzip.8
 ;CHECK-NEXT: vadd.i8
        %tmp1 = load <8 x i8>* %A
@@ -23,7 +13,7 @@ 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-LABEL: vzipi16:
 ;CHECK: vzip.16
 ;CHECK-NEXT: vadd.i16
        %tmp1 = load <4 x i16>* %A
@@ -37,7 +27,7 @@ define <4 x i16> @vzipi16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
 ; VZIP.32 is equivalent to VTRN.32 for 64-bit vectors.
 
 define <16 x i8> @vzipQi8(<16 x i8>* %A, <16 x i8>* %B) nounwind {
-;CHECK: vzipQi8:
+;CHECK-LABEL: vzipQi8:
 ;CHECK: vzip.8
 ;CHECK-NEXT: vadd.i8
        %tmp1 = load <16 x i8>* %A
@@ -49,7 +39,7 @@ 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-LABEL: vzipQi16:
 ;CHECK: vzip.16
 ;CHECK-NEXT: vadd.i16
        %tmp1 = load <8 x i16>* %A
@@ -61,7 +51,7 @@ 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-LABEL: vzipQi32:
 ;CHECK: vzip.32
 ;CHECK-NEXT: vadd.i32
        %tmp1 = load <4 x i32>* %A
@@ -73,13 +63,40 @@ 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-LABEL: 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>
        %tmp4 = shufflevector <4 x float> %tmp1, <4 x float> %tmp2, <4 x i32> <i32 2, i32 6, i32 3, i32 7>
-        %tmp5 = add <4 x float> %tmp3, %tmp4
+        %tmp5 = fadd <4 x float> %tmp3, %tmp4
        ret <4 x float> %tmp5
 }
+
+; Undef shuffle indices should not prevent matching to VZIP:
+
+define <8 x i8> @vzipi8_undef(<8 x i8>* %A, <8 x i8>* %B) nounwind {
+;CHECK-LABEL: vzipi8_undef:
+;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 undef, i32 1, i32 9, i32 undef, i32 10, i32 3, i32 11>
+       %tmp4 = shufflevector <8 x i8> %tmp1, <8 x i8> %tmp2, <8 x i32> <i32 4, i32 12, i32 5, i32 13, i32 6, i32 undef, i32 undef, i32 15>
+        %tmp5 = add <8 x i8> %tmp3, %tmp4
+       ret <8 x i8> %tmp5
+}
+
+define <16 x i8> @vzipQi8_undef(<16 x i8>* %A, <16 x i8>* %B) nounwind {
+;CHECK-LABEL: vzipQi8_undef:
+;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 undef, i32 undef, i32 undef, i32 3, i32 19, i32 4, i32 20, i32 5, i32 21, i32 6, i32 22, i32 7, i32 23>
+       %tmp4 = shufflevector <16 x i8> %tmp1, <16 x i8> %tmp2, <16 x i32> <i32 8, i32 24, i32 9, i32 undef, i32 10, i32 26, i32 11, i32 27, i32 12, i32 28, i32 13, i32 undef, i32 14, i32 30, i32 undef, i32 31>
+        %tmp5 = add <16 x i8> %tmp3, %tmp4
+       ret <16 x i8> %tmp5
+}
+