The ARM disassembler did not handle the alignment correctly for VLD*DUP* instructions

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

diff --git a/test/CodeGen/ARM/vdup.ll b/test/CodeGen/ARM/vdup.ll
index 0d0087b973343cb92464dbb053db911001447642..e99fac1f1e67a7eb92e61cabf153b92f6bd83be6 100644 (file)
--- a/test/CodeGen/ARM/vdup.ll
+++ b/test/CodeGen/ARM/vdup.ll
@@ -1,7 +1,4 @@
-; RUN: llvm-as < %s | llc -march=arm -mattr=+neon | FileCheck %s
-; RUN: grep vdup.8 %t | count 4
-; RUN: grep vdup.16 %t | count 4
-; RUN: grep vdup.32 %t | count 10
+; RUN: llc < %s -march=arm -mattr=+neon | FileCheck %s
 
 define <8 x i8> @v_dup8(i8 %A) nounwind {
 ;CHECK: v_dup8:
@@ -165,20 +162,102 @@ define <4 x float> @v_shuffledupQfloat(float %A) nounwind {
        ret <4 x float> %tmp2
 }
 
-define <2 x float> @v_shuffledupfloat2(float* %A) nounwind {
-;CHECK: v_shuffledupfloat2:
+define <8 x i8> @vduplane8(<8 x i8>* %A) nounwind {
+;CHECK: vduplane8:
+;CHECK: vdup.8
+       %tmp1 = load <8 x i8>* %A
+       %tmp2 = shufflevector <8 x i8> %tmp1, <8 x i8> undef, <8 x i32> < i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1 >
+       ret <8 x i8> %tmp2
+}
+
+define <4 x i16> @vduplane16(<4 x i16>* %A) nounwind {
+;CHECK: vduplane16:
+;CHECK: vdup.16
+       %tmp1 = load <4 x i16>* %A
+       %tmp2 = shufflevector <4 x i16> %tmp1, <4 x i16> undef, <4 x i32> < i32 1, i32 1, i32 1, i32 1 >
+       ret <4 x i16> %tmp2
+}
+
+define <2 x i32> @vduplane32(<2 x i32>* %A) nounwind {
+;CHECK: vduplane32:
+;CHECK: vdup.32
+       %tmp1 = load <2 x i32>* %A
+       %tmp2 = shufflevector <2 x i32> %tmp1, <2 x i32> undef, <2 x i32> < i32 1, i32 1 >
+       ret <2 x i32> %tmp2
+}
+
+define <2 x float> @vduplanefloat(<2 x float>* %A) nounwind {
+;CHECK: vduplanefloat:
+;CHECK: vdup.32
+       %tmp1 = load <2 x float>* %A
+       %tmp2 = shufflevector <2 x float> %tmp1, <2 x float> undef, <2 x i32> < i32 1, i32 1 >
+       ret <2 x float> %tmp2
+}
+
+define <16 x i8> @vduplaneQ8(<8 x i8>* %A) nounwind {
+;CHECK: vduplaneQ8:
+;CHECK: vdup.8
+       %tmp1 = load <8 x i8>* %A
+       %tmp2 = shufflevector <8 x i8> %tmp1, <8 x i8> undef, <16 x i32> < i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1 >
+       ret <16 x i8> %tmp2
+}
+
+define <8 x i16> @vduplaneQ16(<4 x i16>* %A) nounwind {
+;CHECK: vduplaneQ16:
+;CHECK: vdup.16
+       %tmp1 = load <4 x i16>* %A
+       %tmp2 = shufflevector <4 x i16> %tmp1, <4 x i16> undef, <8 x i32> < i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1 >
+       ret <8 x i16> %tmp2
+}
+
+define <4 x i32> @vduplaneQ32(<2 x i32>* %A) nounwind {
+;CHECK: vduplaneQ32:
 ;CHECK: vdup.32
-       %tmp0 = load float* %A
-        %tmp1 = insertelement <2 x float> undef, float %tmp0, i32 0
-        %tmp2 = shufflevector <2 x float> %tmp1, <2 x float> undef, <2 x i32> zeroinitializer
-        ret <2 x float> %tmp2
+       %tmp1 = load <2 x i32>* %A
+       %tmp2 = shufflevector <2 x i32> %tmp1, <2 x i32> undef, <4 x i32> < i32 1, i32 1, i32 1, i32 1 >
+       ret <4 x i32> %tmp2
 }
 
-define <4 x float> @v_shuffledupQfloat2(float* %A) nounwind {
-;CHECK: v_shuffledupQfloat2:
+define <4 x float> @vduplaneQfloat(<2 x float>* %A) nounwind {
+;CHECK: vduplaneQfloat:
 ;CHECK: vdup.32
-        %tmp0 = load float* %A
-        %tmp1 = insertelement <4 x float> undef, float %tmp0, i32 0
-        %tmp2 = shufflevector <4 x float> %tmp1, <4 x float> undef, <4 x i32> zeroinitializer
-        ret <4 x float> %tmp2
+       %tmp1 = load <2 x float>* %A
+       %tmp2 = shufflevector <2 x float> %tmp1, <2 x float> undef, <4 x i32> < i32 1, i32 1, i32 1, i32 1 >
+       ret <4 x float> %tmp2
+}
+
+define <2 x i64> @foo(<2 x i64> %arg0_int64x1_t) nounwind readnone {
+entry:
+  %0 = shufflevector <2 x i64> %arg0_int64x1_t, <2 x i64> undef, <2 x i32> <i32 1, i32 1>
+  ret <2 x i64> %0
+}
+
+define <2 x i64> @bar(<2 x i64> %arg0_int64x1_t) nounwind readnone {
+entry:
+  %0 = shufflevector <2 x i64> %arg0_int64x1_t, <2 x i64> undef, <2 x i32> <i32 0, i32 0>
+  ret <2 x i64> %0
+}
+
+define <2 x double> @baz(<2 x double> %arg0_int64x1_t) nounwind readnone {
+entry:
+  %0 = shufflevector <2 x double> %arg0_int64x1_t, <2 x double> undef, <2 x i32> <i32 1, i32 1>
+  ret <2 x double> %0
+}
+
+define <2 x double> @qux(<2 x double> %arg0_int64x1_t) nounwind readnone {
+entry:
+  %0 = shufflevector <2 x double> %arg0_int64x1_t, <2 x double> undef, <2 x i32> <i32 0, i32 0>
+  ret <2 x double> %0
+}
+
+; Radar 7373643
+;CHECK: redundantVdup:
+;CHECK: vmov.i8
+;CHECK-NOT: vdup.8
+;CHECK: vstr.64
+define void @redundantVdup(<8 x i8>* %ptr) nounwind {
+  %1 = insertelement <8 x i8> undef, i8 -128, i32 0
+  %2 = shufflevector <8 x i8> %1, <8 x i8> undef, <8 x i32> zeroinitializer
+  store <8 x i8> %2, <8 x i8>* %ptr, align 8
+  ret void
 }