Split ARM and AArch64 emutls.ll test

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

diff --git a/test/CodeGen/ARM/vhadd.ll b/test/CodeGen/ARM/vhadd.ll
index 9c2ed579c98e6d8c6fd486cf77fab40ff29b8586..01e239d5c73a1214ac6c2d68ebbe1187e5fe7a7d 100644 (file)
--- a/test/CodeGen/ARM/vhadd.ll
+++ b/test/CodeGen/ARM/vhadd.ll
@@ -1,10 +1,10 @@
-; RUN: llc < %s -march=arm -mattr=+neon | FileCheck %s
+; RUN: llc -mtriple=arm-eabi -mattr=+neon %s -o - | FileCheck %s
 
 define <8 x i8> @vhadds8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
 ;CHECK-LABEL: vhadds8:
 ;CHECK: vhadd.s8
-       %tmp1 = load <8 x i8>* %A
-       %tmp2 = load <8 x i8>* %B
+       %tmp1 = load <8 x i8>, <8 x i8>* %A
+       %tmp2 = load <8 x i8>, <8 x i8>* %B
        %tmp3 = call <8 x i8> @llvm.arm.neon.vhadds.v8i8(<8 x i8> %tmp1, <8 x i8> %tmp2)
        ret <8 x i8> %tmp3
 }
@@ -12,8 +12,8 @@ define <8 x i8> @vhadds8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
 define <4 x i16> @vhadds16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
 ;CHECK-LABEL: vhadds16:
 ;CHECK: vhadd.s16
-       %tmp1 = load <4 x i16>* %A
-       %tmp2 = load <4 x i16>* %B
+       %tmp1 = load <4 x i16>, <4 x i16>* %A
+       %tmp2 = load <4 x i16>, <4 x i16>* %B
        %tmp3 = call <4 x i16> @llvm.arm.neon.vhadds.v4i16(<4 x i16> %tmp1, <4 x i16> %tmp2)
        ret <4 x i16> %tmp3
 }
@@ -21,8 +21,8 @@ define <4 x i16> @vhadds16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
 define <2 x i32> @vhadds32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
 ;CHECK-LABEL: vhadds32:
 ;CHECK: vhadd.s32
-       %tmp1 = load <2 x i32>* %A
-       %tmp2 = load <2 x i32>* %B
+       %tmp1 = load <2 x i32>, <2 x i32>* %A
+       %tmp2 = load <2 x i32>, <2 x i32>* %B
        %tmp3 = call <2 x i32> @llvm.arm.neon.vhadds.v2i32(<2 x i32> %tmp1, <2 x i32> %tmp2)
        ret <2 x i32> %tmp3
 }
@@ -30,8 +30,8 @@ define <2 x i32> @vhadds32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
 define <8 x i8> @vhaddu8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
 ;CHECK-LABEL: vhaddu8:
 ;CHECK: vhadd.u8
-       %tmp1 = load <8 x i8>* %A
-       %tmp2 = load <8 x i8>* %B
+       %tmp1 = load <8 x i8>, <8 x i8>* %A
+       %tmp2 = load <8 x i8>, <8 x i8>* %B
        %tmp3 = call <8 x i8> @llvm.arm.neon.vhaddu.v8i8(<8 x i8> %tmp1, <8 x i8> %tmp2)
        ret <8 x i8> %tmp3
 }
@@ -39,8 +39,8 @@ define <8 x i8> @vhaddu8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
 define <4 x i16> @vhaddu16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
 ;CHECK-LABEL: vhaddu16:
 ;CHECK: vhadd.u16
-       %tmp1 = load <4 x i16>* %A
-       %tmp2 = load <4 x i16>* %B
+       %tmp1 = load <4 x i16>, <4 x i16>* %A
+       %tmp2 = load <4 x i16>, <4 x i16>* %B
        %tmp3 = call <4 x i16> @llvm.arm.neon.vhaddu.v4i16(<4 x i16> %tmp1, <4 x i16> %tmp2)
        ret <4 x i16> %tmp3
 }
@@ -48,8 +48,8 @@ define <4 x i16> @vhaddu16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
 define <2 x i32> @vhaddu32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
 ;CHECK-LABEL: vhaddu32:
 ;CHECK: vhadd.u32
-       %tmp1 = load <2 x i32>* %A
-       %tmp2 = load <2 x i32>* %B
+       %tmp1 = load <2 x i32>, <2 x i32>* %A
+       %tmp2 = load <2 x i32>, <2 x i32>* %B
        %tmp3 = call <2 x i32> @llvm.arm.neon.vhaddu.v2i32(<2 x i32> %tmp1, <2 x i32> %tmp2)
        ret <2 x i32> %tmp3
 }
@@ -57,8 +57,8 @@ define <2 x i32> @vhaddu32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
 define <16 x i8> @vhaddQs8(<16 x i8>* %A, <16 x i8>* %B) nounwind {
 ;CHECK-LABEL: vhaddQs8:
 ;CHECK: vhadd.s8
-       %tmp1 = load <16 x i8>* %A
-       %tmp2 = load <16 x i8>* %B
+       %tmp1 = load <16 x i8>, <16 x i8>* %A
+       %tmp2 = load <16 x i8>, <16 x i8>* %B
        %tmp3 = call <16 x i8> @llvm.arm.neon.vhadds.v16i8(<16 x i8> %tmp1, <16 x i8> %tmp2)
        ret <16 x i8> %tmp3
 }
@@ -66,8 +66,8 @@ define <16 x i8> @vhaddQs8(<16 x i8>* %A, <16 x i8>* %B) nounwind {
 define <8 x i16> @vhaddQs16(<8 x i16>* %A, <8 x i16>* %B) nounwind {
 ;CHECK-LABEL: vhaddQs16:
 ;CHECK: vhadd.s16
-       %tmp1 = load <8 x i16>* %A
-       %tmp2 = load <8 x i16>* %B
+       %tmp1 = load <8 x i16>, <8 x i16>* %A
+       %tmp2 = load <8 x i16>, <8 x i16>* %B
        %tmp3 = call <8 x i16> @llvm.arm.neon.vhadds.v8i16(<8 x i16> %tmp1, <8 x i16> %tmp2)
        ret <8 x i16> %tmp3
 }
@@ -75,8 +75,8 @@ define <8 x i16> @vhaddQs16(<8 x i16>* %A, <8 x i16>* %B) nounwind {
 define <4 x i32> @vhaddQs32(<4 x i32>* %A, <4 x i32>* %B) nounwind {
 ;CHECK-LABEL: vhaddQs32:
 ;CHECK: vhadd.s32
-       %tmp1 = load <4 x i32>* %A
-       %tmp2 = load <4 x i32>* %B
+       %tmp1 = load <4 x i32>, <4 x i32>* %A
+       %tmp2 = load <4 x i32>, <4 x i32>* %B
        %tmp3 = call <4 x i32> @llvm.arm.neon.vhadds.v4i32(<4 x i32> %tmp1, <4 x i32> %tmp2)
        ret <4 x i32> %tmp3
 }
@@ -84,8 +84,8 @@ define <4 x i32> @vhaddQs32(<4 x i32>* %A, <4 x i32>* %B) nounwind {
 define <16 x i8> @vhaddQu8(<16 x i8>* %A, <16 x i8>* %B) nounwind {
 ;CHECK-LABEL: vhaddQu8:
 ;CHECK: vhadd.u8
-       %tmp1 = load <16 x i8>* %A
-       %tmp2 = load <16 x i8>* %B
+       %tmp1 = load <16 x i8>, <16 x i8>* %A
+       %tmp2 = load <16 x i8>, <16 x i8>* %B
        %tmp3 = call <16 x i8> @llvm.arm.neon.vhaddu.v16i8(<16 x i8> %tmp1, <16 x i8> %tmp2)
        ret <16 x i8> %tmp3
 }
@@ -93,8 +93,8 @@ define <16 x i8> @vhaddQu8(<16 x i8>* %A, <16 x i8>* %B) nounwind {
 define <8 x i16> @vhaddQu16(<8 x i16>* %A, <8 x i16>* %B) nounwind {
 ;CHECK-LABEL: vhaddQu16:
 ;CHECK: vhadd.u16
-       %tmp1 = load <8 x i16>* %A
-       %tmp2 = load <8 x i16>* %B
+       %tmp1 = load <8 x i16>, <8 x i16>* %A
+       %tmp2 = load <8 x i16>, <8 x i16>* %B
        %tmp3 = call <8 x i16> @llvm.arm.neon.vhaddu.v8i16(<8 x i16> %tmp1, <8 x i16> %tmp2)
        ret <8 x i16> %tmp3
 }
@@ -102,8 +102,8 @@ define <8 x i16> @vhaddQu16(<8 x i16>* %A, <8 x i16>* %B) nounwind {
 define <4 x i32> @vhaddQu32(<4 x i32>* %A, <4 x i32>* %B) nounwind {
 ;CHECK-LABEL: vhaddQu32:
 ;CHECK: vhadd.u32
-       %tmp1 = load <4 x i32>* %A
-       %tmp2 = load <4 x i32>* %B
+       %tmp1 = load <4 x i32>, <4 x i32>* %A
+       %tmp2 = load <4 x i32>, <4 x i32>* %B
        %tmp3 = call <4 x i32> @llvm.arm.neon.vhaddu.v4i32(<4 x i32> %tmp1, <4 x i32> %tmp2)
        ret <4 x i32> %tmp3
 }
@@ -127,8 +127,8 @@ declare <4 x i32> @llvm.arm.neon.vhaddu.v4i32(<4 x i32>, <4 x i32>) nounwind rea
 define <8 x i8> @vrhadds8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
 ;CHECK-LABEL: vrhadds8:
 ;CHECK: vrhadd.s8
-       %tmp1 = load <8 x i8>* %A
-       %tmp2 = load <8 x i8>* %B
+       %tmp1 = load <8 x i8>, <8 x i8>* %A
+       %tmp2 = load <8 x i8>, <8 x i8>* %B
        %tmp3 = call <8 x i8> @llvm.arm.neon.vrhadds.v8i8(<8 x i8> %tmp1, <8 x i8> %tmp2)
        ret <8 x i8> %tmp3
 }
@@ -136,8 +136,8 @@ define <8 x i8> @vrhadds8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
 define <4 x i16> @vrhadds16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
 ;CHECK-LABEL: vrhadds16:
 ;CHECK: vrhadd.s16
-       %tmp1 = load <4 x i16>* %A
-       %tmp2 = load <4 x i16>* %B
+       %tmp1 = load <4 x i16>, <4 x i16>* %A
+       %tmp2 = load <4 x i16>, <4 x i16>* %B
        %tmp3 = call <4 x i16> @llvm.arm.neon.vrhadds.v4i16(<4 x i16> %tmp1, <4 x i16> %tmp2)
        ret <4 x i16> %tmp3
 }
@@ -145,8 +145,8 @@ define <4 x i16> @vrhadds16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
 define <2 x i32> @vrhadds32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
 ;CHECK-LABEL: vrhadds32:
 ;CHECK: vrhadd.s32
-       %tmp1 = load <2 x i32>* %A
-       %tmp2 = load <2 x i32>* %B
+       %tmp1 = load <2 x i32>, <2 x i32>* %A
+       %tmp2 = load <2 x i32>, <2 x i32>* %B
        %tmp3 = call <2 x i32> @llvm.arm.neon.vrhadds.v2i32(<2 x i32> %tmp1, <2 x i32> %tmp2)
        ret <2 x i32> %tmp3
 }
@@ -154,8 +154,8 @@ define <2 x i32> @vrhadds32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
 define <8 x i8> @vrhaddu8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
 ;CHECK-LABEL: vrhaddu8:
 ;CHECK: vrhadd.u8
-       %tmp1 = load <8 x i8>* %A
-       %tmp2 = load <8 x i8>* %B
+       %tmp1 = load <8 x i8>, <8 x i8>* %A
+       %tmp2 = load <8 x i8>, <8 x i8>* %B
        %tmp3 = call <8 x i8> @llvm.arm.neon.vrhaddu.v8i8(<8 x i8> %tmp1, <8 x i8> %tmp2)
        ret <8 x i8> %tmp3
 }
@@ -163,8 +163,8 @@ define <8 x i8> @vrhaddu8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
 define <4 x i16> @vrhaddu16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
 ;CHECK-LABEL: vrhaddu16:
 ;CHECK: vrhadd.u16
-       %tmp1 = load <4 x i16>* %A
-       %tmp2 = load <4 x i16>* %B
+       %tmp1 = load <4 x i16>, <4 x i16>* %A
+       %tmp2 = load <4 x i16>, <4 x i16>* %B
        %tmp3 = call <4 x i16> @llvm.arm.neon.vrhaddu.v4i16(<4 x i16> %tmp1, <4 x i16> %tmp2)
        ret <4 x i16> %tmp3
 }
@@ -172,8 +172,8 @@ define <4 x i16> @vrhaddu16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
 define <2 x i32> @vrhaddu32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
 ;CHECK-LABEL: vrhaddu32:
 ;CHECK: vrhadd.u32
-       %tmp1 = load <2 x i32>* %A
-       %tmp2 = load <2 x i32>* %B
+       %tmp1 = load <2 x i32>, <2 x i32>* %A
+       %tmp2 = load <2 x i32>, <2 x i32>* %B
        %tmp3 = call <2 x i32> @llvm.arm.neon.vrhaddu.v2i32(<2 x i32> %tmp1, <2 x i32> %tmp2)
        ret <2 x i32> %tmp3
 }
@@ -181,8 +181,8 @@ define <2 x i32> @vrhaddu32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
 define <16 x i8> @vrhaddQs8(<16 x i8>* %A, <16 x i8>* %B) nounwind {
 ;CHECK-LABEL: vrhaddQs8:
 ;CHECK: vrhadd.s8
-       %tmp1 = load <16 x i8>* %A
-       %tmp2 = load <16 x i8>* %B
+       %tmp1 = load <16 x i8>, <16 x i8>* %A
+       %tmp2 = load <16 x i8>, <16 x i8>* %B
        %tmp3 = call <16 x i8> @llvm.arm.neon.vrhadds.v16i8(<16 x i8> %tmp1, <16 x i8> %tmp2)
        ret <16 x i8> %tmp3
 }
@@ -190,8 +190,8 @@ define <16 x i8> @vrhaddQs8(<16 x i8>* %A, <16 x i8>* %B) nounwind {
 define <8 x i16> @vrhaddQs16(<8 x i16>* %A, <8 x i16>* %B) nounwind {
 ;CHECK-LABEL: vrhaddQs16:
 ;CHECK: vrhadd.s16
-       %tmp1 = load <8 x i16>* %A
-       %tmp2 = load <8 x i16>* %B
+       %tmp1 = load <8 x i16>, <8 x i16>* %A
+       %tmp2 = load <8 x i16>, <8 x i16>* %B
        %tmp3 = call <8 x i16> @llvm.arm.neon.vrhadds.v8i16(<8 x i16> %tmp1, <8 x i16> %tmp2)
        ret <8 x i16> %tmp3
 }
@@ -199,8 +199,8 @@ define <8 x i16> @vrhaddQs16(<8 x i16>* %A, <8 x i16>* %B) nounwind {
 define <4 x i32> @vrhaddQs32(<4 x i32>* %A, <4 x i32>* %B) nounwind {
 ;CHECK-LABEL: vrhaddQs32:
 ;CHECK: vrhadd.s32
-       %tmp1 = load <4 x i32>* %A
-       %tmp2 = load <4 x i32>* %B
+       %tmp1 = load <4 x i32>, <4 x i32>* %A
+       %tmp2 = load <4 x i32>, <4 x i32>* %B
        %tmp3 = call <4 x i32> @llvm.arm.neon.vrhadds.v4i32(<4 x i32> %tmp1, <4 x i32> %tmp2)
        ret <4 x i32> %tmp3
 }
@@ -208,8 +208,8 @@ define <4 x i32> @vrhaddQs32(<4 x i32>* %A, <4 x i32>* %B) nounwind {
 define <16 x i8> @vrhaddQu8(<16 x i8>* %A, <16 x i8>* %B) nounwind {
 ;CHECK-LABEL: vrhaddQu8:
 ;CHECK: vrhadd.u8
-       %tmp1 = load <16 x i8>* %A
-       %tmp2 = load <16 x i8>* %B
+       %tmp1 = load <16 x i8>, <16 x i8>* %A
+       %tmp2 = load <16 x i8>, <16 x i8>* %B
        %tmp3 = call <16 x i8> @llvm.arm.neon.vrhaddu.v16i8(<16 x i8> %tmp1, <16 x i8> %tmp2)
        ret <16 x i8> %tmp3
 }
@@ -217,8 +217,8 @@ define <16 x i8> @vrhaddQu8(<16 x i8>* %A, <16 x i8>* %B) nounwind {
 define <8 x i16> @vrhaddQu16(<8 x i16>* %A, <8 x i16>* %B) nounwind {
 ;CHECK-LABEL: vrhaddQu16:
 ;CHECK: vrhadd.u16
-       %tmp1 = load <8 x i16>* %A
-       %tmp2 = load <8 x i16>* %B
+       %tmp1 = load <8 x i16>, <8 x i16>* %A
+       %tmp2 = load <8 x i16>, <8 x i16>* %B
        %tmp3 = call <8 x i16> @llvm.arm.neon.vrhaddu.v8i16(<8 x i16> %tmp1, <8 x i16> %tmp2)
        ret <8 x i16> %tmp3
 }
@@ -226,8 +226,8 @@ define <8 x i16> @vrhaddQu16(<8 x i16>* %A, <8 x i16>* %B) nounwind {
 define <4 x i32> @vrhaddQu32(<4 x i32>* %A, <4 x i32>* %B) nounwind {
 ;CHECK-LABEL: vrhaddQu32:
 ;CHECK: vrhadd.u32
-       %tmp1 = load <4 x i32>* %A
-       %tmp2 = load <4 x i32>* %B
+       %tmp1 = load <4 x i32>, <4 x i32>* %A
+       %tmp2 = load <4 x i32>, <4 x i32>* %B
        %tmp3 = call <4 x i32> @llvm.arm.neon.vrhaddu.v4i32(<4 x i32> %tmp1, <4 x i32> %tmp2)
        ret <4 x i32> %tmp3
 }