4 files changed, 54 insertions, 18 deletions
diff --git a/test/CodeGen/ARM/vdup.ll b/test/CodeGen/ARM/vdup.ll
index a545f6c..e99fac1 100644
--- a/test/CodeGen/ARM/vdup.ll
+++ b/test/CodeGen/ARM/vdup.ll
@@ -162,24 +162,6 @@ 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:
-;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
-}
-
-define <4 x float> @v_shuffledupQfloat2(float* %A) nounwind {
-;CHECK: v_shuffledupQfloat2:
-;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
-}
-
 define <8 x i8> @vduplane8(<8 x i8>* %A) nounwind {
 ;CHECK: vduplane8:
 ;CHECK: vdup.8
diff --git a/test/CodeGen/ARM/vlddup.ll b/test/CodeGen/ARM/vlddup.ll
index bb07ce2..033febb 100644
--- a/test/CodeGen/ARM/vlddup.ll
+++ b/test/CodeGen/ARM/vlddup.ll
@@ -30,6 +30,15 @@ define <2 x i32> @vld1dupi32(i32* %A) nounwind {
         ret <2 x i32> %tmp3
 }
 
+define <2 x float> @vld1dupf(float* %A) nounwind {
+;CHECK: vld1dupf:
+;CHECK: vld1.32 {d16[]}, [r0]
+	%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
+}
+
 define <16 x i8> @vld1dupQi8(i8* %A) nounwind {
 ;CHECK: vld1dupQi8:
 ;Check the (default) alignment value.
@@ -40,6 +49,15 @@ define <16 x i8> @vld1dupQi8(i8* %A) nounwind {
         ret <16 x i8> %tmp3
 }
 
+define <4 x float> @vld1dupQf(float* %A) nounwind {
+;CHECK: vld1dupQf:
+;CHECK: vld1.32 {d16[], d17[]}, [r0]
+        %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
+}
+
 %struct.__neon_int8x8x2_t = type { <8 x i8>, <8 x i8> }
 %struct.__neon_int4x16x2_t = type { <4 x i16>, <4 x i16> }
 %struct.__neon_int2x32x2_t = type { <2 x i32>, <2 x i32> }
diff --git a/test/CodeGen/ARM/vldlane.ll b/test/CodeGen/ARM/vldlane.ll
index 09b68a6..fe2a0dc 100644
--- a/test/CodeGen/ARM/vldlane.ll
+++ b/test/CodeGen/ARM/vldlane.ll
@@ -30,6 +30,15 @@ define <2 x i32> @vld1lanei32(i32* %A, <2 x i32>* %B) nounwind {
         ret <2 x i32> %tmp3
 }
 
+define <2 x float> @vld1lanef(float* %A, <2 x float>* %B) nounwind {
+;CHECK: vld1lanef:
+;CHECK: vld1.32 {d16[1]}, [r0]
+	%tmp1 = load <2 x float>* %B
+	%tmp2 = load float* %A, align 4
+	%tmp3 = insertelement <2 x float> %tmp1, float %tmp2, i32 1
+	ret <2 x float> %tmp3
+}
+
 define <16 x i8> @vld1laneQi8(i8* %A, <16 x i8>* %B) nounwind {
 ;CHECK: vld1laneQi8:
 ;CHECK: vld1.8 {d17[1]}, [r0]
@@ -57,6 +66,15 @@ define <4 x i32> @vld1laneQi32(i32* %A, <4 x i32>* %B) nounwind {
 	ret <4 x i32> %tmp3
 }
 
+define <4 x float> @vld1laneQf(float* %A, <4 x float>* %B) nounwind {
+;CHECK: vld1laneQf:
+;CHECK: vld1.32 {d16[0]}, [r0]
+	%tmp1 = load <4 x float>* %B
+	%tmp2 = load float* %A
+	%tmp3 = insertelement <4 x float> %tmp1, float %tmp2, i32 0
+	ret <4 x float> %tmp3
+}
+
 %struct.__neon_int8x8x2_t = type { <8 x i8>,  <8 x i8> }
 %struct.__neon_int16x4x2_t = type { <4 x i16>, <4 x i16> }
 %struct.__neon_int32x2x2_t = type { <2 x i32>, <2 x i32> }
diff --git a/test/CodeGen/ARM/vstlane.ll b/test/CodeGen/ARM/vstlane.ll
index c5387e0..9aa8d59 100644
--- a/test/CodeGen/ARM/vstlane.ll
+++ b/test/CodeGen/ARM/vstlane.ll
@@ -30,6 +30,15 @@ define void @vst1lanei32(i32* %A, <2 x i32>* %B) nounwind {
 	ret void
 }
 
+define void @vst1lanef(float* %A, <2 x float>* %B) nounwind {
+;CHECK: vst1lanef:
+;CHECK: vst1.32 {d16[1]}, [r0]
+	%tmp1 = load <2 x float>* %B
+        %tmp2 = extractelement <2 x float> %tmp1, i32 1
+        store float %tmp2, float* %A
+	ret void
+}
+
 define void @vst1laneQi8(i8* %A, <16 x i8>* %B) nounwind {
 ;CHECK: vst1laneQi8:
 ;CHECK: vst1.8 {d17[1]}, [r0]
@@ -57,6 +66,15 @@ define void @vst1laneQi32(i32* %A, <4 x i32>* %B) nounwind {
 	ret void
 }
 
+define void @vst1laneQf(float* %A, <4 x float>* %B) nounwind {
+;CHECK: vst1laneQf:
+;CHECK: vst1.32 {d17[1]}, [r0]
+	%tmp1 = load <4 x float>* %B
+        %tmp2 = extractelement <4 x float> %tmp1, i32 3
+        store float %tmp2, float* %A
+	ret void
+}
+
 define void @vst2lanei8(i8* %A, <8 x i8>* %B) nounwind {
 ;CHECK: vst2lanei8:
 ;Check the alignment value.  Max for this instruction is 16 bits: