aboutsummaryrefslogtreecommitdiffstats
path: root/test/CodeGen/ARM/vldlane.ll
diff options
context:
space:
mode:
authorPirama Arumuga Nainar <pirama@google.com>2015-04-10 21:22:52 +0000
committerGerrit Code Review <noreply-gerritcodereview@google.com>2015-04-10 21:23:04 +0000
commit31195f0bdca6ee2a5e72d07edf13e1d81206d949 (patch)
tree1b2c9792582e12f5af0b1512e3094425f0dc0df9 /test/CodeGen/ARM/vldlane.ll
parentc75239e6119d0f9a74c57099d91cbc9bde56bf33 (diff)
parent4c5e43da7792f75567b693105cc53e3f1992ad98 (diff)
downloadexternal_llvm-31195f0bdca6ee2a5e72d07edf13e1d81206d949.zip
external_llvm-31195f0bdca6ee2a5e72d07edf13e1d81206d949.tar.gz
external_llvm-31195f0bdca6ee2a5e72d07edf13e1d81206d949.tar.bz2
Merge "Update aosp/master llvm for rebase to r233350"
Diffstat (limited to 'test/CodeGen/ARM/vldlane.ll')
-rw-r--r--test/CodeGen/ARM/vldlane.ll96
1 files changed, 48 insertions, 48 deletions
diff --git a/test/CodeGen/ARM/vldlane.ll b/test/CodeGen/ARM/vldlane.ll
index c7d69ff..ac2be7f 100644
--- a/test/CodeGen/ARM/vldlane.ll
+++ b/test/CodeGen/ARM/vldlane.ll
@@ -7,8 +7,8 @@ define <8 x i8> @vld1lanei8(i8* %A, <8 x i8>* %B) nounwind {
;CHECK-LABEL: vld1lanei8:
;Check the (default) alignment value.
;CHECK: vld1.8 {d16[3]}, [r0]
- %tmp1 = load <8 x i8>* %B
- %tmp2 = load i8* %A, align 8
+ %tmp1 = load <8 x i8>, <8 x i8>* %B
+ %tmp2 = load i8, i8* %A, align 8
%tmp3 = insertelement <8 x i8> %tmp1, i8 %tmp2, i32 3
ret <8 x i8> %tmp3
}
@@ -17,8 +17,8 @@ define <4 x i16> @vld1lanei16(i16* %A, <4 x i16>* %B) nounwind {
;CHECK-LABEL: vld1lanei16:
;Check the alignment value. Max for this instruction is 16 bits:
;CHECK: vld1.16 {d16[2]}, [r0:16]
- %tmp1 = load <4 x i16>* %B
- %tmp2 = load i16* %A, align 8
+ %tmp1 = load <4 x i16>, <4 x i16>* %B
+ %tmp2 = load i16, i16* %A, align 8
%tmp3 = insertelement <4 x i16> %tmp1, i16 %tmp2, i32 2
ret <4 x i16> %tmp3
}
@@ -27,8 +27,8 @@ define <2 x i32> @vld1lanei32(i32* %A, <2 x i32>* %B) nounwind {
;CHECK-LABEL: vld1lanei32:
;Check the alignment value. Max for this instruction is 32 bits:
;CHECK: vld1.32 {d16[1]}, [r0:32]
- %tmp1 = load <2 x i32>* %B
- %tmp2 = load i32* %A, align 8
+ %tmp1 = load <2 x i32>, <2 x i32>* %B
+ %tmp2 = load i32, i32* %A, align 8
%tmp3 = insertelement <2 x i32> %tmp1, i32 %tmp2, i32 1
ret <2 x i32> %tmp3
}
@@ -37,8 +37,8 @@ define <2 x i32> @vld1lanei32a32(i32* %A, <2 x i32>* %B) nounwind {
;CHECK-LABEL: vld1lanei32a32:
;Check the alignment value. Legal values are none or :32.
;CHECK: vld1.32 {d16[1]}, [r0:32]
- %tmp1 = load <2 x i32>* %B
- %tmp2 = load i32* %A, align 4
+ %tmp1 = load <2 x i32>, <2 x i32>* %B
+ %tmp2 = load i32, i32* %A, align 4
%tmp3 = insertelement <2 x i32> %tmp1, i32 %tmp2, i32 1
ret <2 x i32> %tmp3
}
@@ -46,8 +46,8 @@ define <2 x i32> @vld1lanei32a32(i32* %A, <2 x i32>* %B) nounwind {
define <2 x float> @vld1lanef(float* %A, <2 x float>* %B) nounwind {
;CHECK-LABEL: vld1lanef:
;CHECK: vld1.32 {d16[1]}, [r0:32]
- %tmp1 = load <2 x float>* %B
- %tmp2 = load float* %A, align 4
+ %tmp1 = load <2 x float>, <2 x float>* %B
+ %tmp2 = load float, float* %A, align 4
%tmp3 = insertelement <2 x float> %tmp1, float %tmp2, i32 1
ret <2 x float> %tmp3
}
@@ -55,8 +55,8 @@ define <2 x float> @vld1lanef(float* %A, <2 x float>* %B) nounwind {
define <16 x i8> @vld1laneQi8(i8* %A, <16 x i8>* %B) nounwind {
;CHECK-LABEL: vld1laneQi8:
;CHECK: vld1.8 {d17[1]}, [r0]
- %tmp1 = load <16 x i8>* %B
- %tmp2 = load i8* %A, align 8
+ %tmp1 = load <16 x i8>, <16 x i8>* %B
+ %tmp2 = load i8, i8* %A, align 8
%tmp3 = insertelement <16 x i8> %tmp1, i8 %tmp2, i32 9
ret <16 x i8> %tmp3
}
@@ -64,8 +64,8 @@ define <16 x i8> @vld1laneQi8(i8* %A, <16 x i8>* %B) nounwind {
define <8 x i16> @vld1laneQi16(i16* %A, <8 x i16>* %B) nounwind {
;CHECK-LABEL: vld1laneQi16:
;CHECK: vld1.16 {d17[1]}, [r0:16]
- %tmp1 = load <8 x i16>* %B
- %tmp2 = load i16* %A, align 8
+ %tmp1 = load <8 x i16>, <8 x i16>* %B
+ %tmp2 = load i16, i16* %A, align 8
%tmp3 = insertelement <8 x i16> %tmp1, i16 %tmp2, i32 5
ret <8 x i16> %tmp3
}
@@ -73,8 +73,8 @@ define <8 x i16> @vld1laneQi16(i16* %A, <8 x i16>* %B) nounwind {
define <4 x i32> @vld1laneQi32(i32* %A, <4 x i32>* %B) nounwind {
;CHECK-LABEL: vld1laneQi32:
;CHECK: vld1.32 {d17[1]}, [r0:32]
- %tmp1 = load <4 x i32>* %B
- %tmp2 = load i32* %A, align 8
+ %tmp1 = load <4 x i32>, <4 x i32>* %B
+ %tmp2 = load i32, i32* %A, align 8
%tmp3 = insertelement <4 x i32> %tmp1, i32 %tmp2, i32 3
ret <4 x i32> %tmp3
}
@@ -82,8 +82,8 @@ define <4 x i32> @vld1laneQi32(i32* %A, <4 x i32>* %B) nounwind {
define <4 x float> @vld1laneQf(float* %A, <4 x float>* %B) nounwind {
;CHECK-LABEL: vld1laneQf:
;CHECK: vld1.32 {d16[0]}, [r0:32]
- %tmp1 = load <4 x float>* %B
- %tmp2 = load float* %A
+ %tmp1 = load <4 x float>, <4 x float>* %B
+ %tmp2 = load float, float* %A
%tmp3 = insertelement <4 x float> %tmp1, float %tmp2, i32 0
ret <4 x float> %tmp3
}
@@ -101,7 +101,7 @@ define <8 x i8> @vld2lanei8(i8* %A, <8 x i8>* %B) nounwind {
;CHECK-LABEL: vld2lanei8:
;Check the alignment value. Max for this instruction is 16 bits:
;CHECK: vld2.8 {d16[1], d17[1]}, [r0:16]
- %tmp1 = load <8 x i8>* %B
+ %tmp1 = load <8 x i8>, <8 x i8>* %B
%tmp2 = call %struct.__neon_int8x8x2_t @llvm.arm.neon.vld2lane.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, i32 1, i32 4)
%tmp3 = extractvalue %struct.__neon_int8x8x2_t %tmp2, 0
%tmp4 = extractvalue %struct.__neon_int8x8x2_t %tmp2, 1
@@ -114,7 +114,7 @@ define <4 x i16> @vld2lanei16(i16* %A, <4 x i16>* %B) nounwind {
;Check the alignment value. Max for this instruction is 32 bits:
;CHECK: vld2.16 {d16[1], d17[1]}, [r0:32]
%tmp0 = bitcast i16* %A to i8*
- %tmp1 = load <4 x i16>* %B
+ %tmp1 = load <4 x i16>, <4 x i16>* %B
%tmp2 = call %struct.__neon_int16x4x2_t @llvm.arm.neon.vld2lane.v4i16(i8* %tmp0, <4 x i16> %tmp1, <4 x i16> %tmp1, i32 1, i32 8)
%tmp3 = extractvalue %struct.__neon_int16x4x2_t %tmp2, 0
%tmp4 = extractvalue %struct.__neon_int16x4x2_t %tmp2, 1
@@ -126,7 +126,7 @@ define <2 x i32> @vld2lanei32(i32* %A, <2 x i32>* %B) nounwind {
;CHECK-LABEL: vld2lanei32:
;CHECK: vld2.32
%tmp0 = bitcast i32* %A to i8*
- %tmp1 = load <2 x i32>* %B
+ %tmp1 = load <2 x i32>, <2 x i32>* %B
%tmp2 = call %struct.__neon_int32x2x2_t @llvm.arm.neon.vld2lane.v2i32(i8* %tmp0, <2 x i32> %tmp1, <2 x i32> %tmp1, i32 1, i32 1)
%tmp3 = extractvalue %struct.__neon_int32x2x2_t %tmp2, 0
%tmp4 = extractvalue %struct.__neon_int32x2x2_t %tmp2, 1
@@ -138,14 +138,14 @@ define <2 x i32> @vld2lanei32(i32* %A, <2 x i32>* %B) nounwind {
define <2 x i32> @vld2lanei32_update(i32** %ptr, <2 x i32>* %B) nounwind {
;CHECK-LABEL: vld2lanei32_update:
;CHECK: vld2.32 {d16[1], d17[1]}, [{{r[0-9]+}}]!
- %A = load i32** %ptr
+ %A = load i32*, i32** %ptr
%tmp0 = bitcast i32* %A to i8*
- %tmp1 = load <2 x i32>* %B
+ %tmp1 = load <2 x i32>, <2 x i32>* %B
%tmp2 = call %struct.__neon_int32x2x2_t @llvm.arm.neon.vld2lane.v2i32(i8* %tmp0, <2 x i32> %tmp1, <2 x i32> %tmp1, i32 1, i32 1)
%tmp3 = extractvalue %struct.__neon_int32x2x2_t %tmp2, 0
%tmp4 = extractvalue %struct.__neon_int32x2x2_t %tmp2, 1
%tmp5 = add <2 x i32> %tmp3, %tmp4
- %tmp6 = getelementptr i32* %A, i32 2
+ %tmp6 = getelementptr i32, i32* %A, i32 2
store i32* %tmp6, i32** %ptr
ret <2 x i32> %tmp5
}
@@ -154,7 +154,7 @@ define <2 x float> @vld2lanef(float* %A, <2 x float>* %B) nounwind {
;CHECK-LABEL: vld2lanef:
;CHECK: vld2.32
%tmp0 = bitcast float* %A to i8*
- %tmp1 = load <2 x float>* %B
+ %tmp1 = load <2 x float>, <2 x float>* %B
%tmp2 = call %struct.__neon_float32x2x2_t @llvm.arm.neon.vld2lane.v2f32(i8* %tmp0, <2 x float> %tmp1, <2 x float> %tmp1, i32 1, i32 1)
%tmp3 = extractvalue %struct.__neon_float32x2x2_t %tmp2, 0
%tmp4 = extractvalue %struct.__neon_float32x2x2_t %tmp2, 1
@@ -167,7 +167,7 @@ define <8 x i16> @vld2laneQi16(i16* %A, <8 x i16>* %B) nounwind {
;Check the (default) alignment.
;CHECK: vld2.16 {d17[1], d19[1]}, [{{r[0-9]+}}]
%tmp0 = bitcast i16* %A to i8*
- %tmp1 = load <8 x i16>* %B
+ %tmp1 = load <8 x i16>, <8 x i16>* %B
%tmp2 = call %struct.__neon_int16x8x2_t @llvm.arm.neon.vld2lane.v8i16(i8* %tmp0, <8 x i16> %tmp1, <8 x i16> %tmp1, i32 5, i32 1)
%tmp3 = extractvalue %struct.__neon_int16x8x2_t %tmp2, 0
%tmp4 = extractvalue %struct.__neon_int16x8x2_t %tmp2, 1
@@ -180,7 +180,7 @@ define <4 x i32> @vld2laneQi32(i32* %A, <4 x i32>* %B) nounwind {
;Check the alignment value. Max for this instruction is 64 bits:
;CHECK: vld2.32 {d17[0], d19[0]}, [{{r[0-9]+}}:64]
%tmp0 = bitcast i32* %A to i8*
- %tmp1 = load <4 x i32>* %B
+ %tmp1 = load <4 x i32>, <4 x i32>* %B
%tmp2 = call %struct.__neon_int32x4x2_t @llvm.arm.neon.vld2lane.v4i32(i8* %tmp0, <4 x i32> %tmp1, <4 x i32> %tmp1, i32 2, i32 16)
%tmp3 = extractvalue %struct.__neon_int32x4x2_t %tmp2, 0
%tmp4 = extractvalue %struct.__neon_int32x4x2_t %tmp2, 1
@@ -192,7 +192,7 @@ define <4 x float> @vld2laneQf(float* %A, <4 x float>* %B) nounwind {
;CHECK-LABEL: vld2laneQf:
;CHECK: vld2.32
%tmp0 = bitcast float* %A to i8*
- %tmp1 = load <4 x float>* %B
+ %tmp1 = load <4 x float>, <4 x float>* %B
%tmp2 = call %struct.__neon_float32x4x2_t @llvm.arm.neon.vld2lane.v4f32(i8* %tmp0, <4 x float> %tmp1, <4 x float> %tmp1, i32 1, i32 1)
%tmp3 = extractvalue %struct.__neon_float32x4x2_t %tmp2, 0
%tmp4 = extractvalue %struct.__neon_float32x4x2_t %tmp2, 1
@@ -221,7 +221,7 @@ declare %struct.__neon_float32x4x2_t @llvm.arm.neon.vld2lane.v4f32(i8*, <4 x flo
define <8 x i8> @vld3lanei8(i8* %A, <8 x i8>* %B) nounwind {
;CHECK-LABEL: vld3lanei8:
;CHECK: vld3.8
- %tmp1 = load <8 x i8>* %B
+ %tmp1 = load <8 x i8>, <8 x i8>* %B
%tmp2 = call %struct.__neon_int8x8x3_t @llvm.arm.neon.vld3lane.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, i32 1, i32 1)
%tmp3 = extractvalue %struct.__neon_int8x8x3_t %tmp2, 0
%tmp4 = extractvalue %struct.__neon_int8x8x3_t %tmp2, 1
@@ -236,7 +236,7 @@ define <4 x i16> @vld3lanei16(i16* %A, <4 x i16>* %B) nounwind {
;Check the (default) alignment value. VLD3 does not support alignment.
;CHECK: vld3.16 {d{{.*}}[1], d{{.*}}[1], d{{.*}}[1]}, [{{r[0-9]+}}]
%tmp0 = bitcast i16* %A to i8*
- %tmp1 = load <4 x i16>* %B
+ %tmp1 = load <4 x i16>, <4 x i16>* %B
%tmp2 = call %struct.__neon_int16x4x3_t @llvm.arm.neon.vld3lane.v4i16(i8* %tmp0, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1, i32 1, i32 8)
%tmp3 = extractvalue %struct.__neon_int16x4x3_t %tmp2, 0
%tmp4 = extractvalue %struct.__neon_int16x4x3_t %tmp2, 1
@@ -250,7 +250,7 @@ define <2 x i32> @vld3lanei32(i32* %A, <2 x i32>* %B) nounwind {
;CHECK-LABEL: vld3lanei32:
;CHECK: vld3.32
%tmp0 = bitcast i32* %A to i8*
- %tmp1 = load <2 x i32>* %B
+ %tmp1 = load <2 x i32>, <2 x i32>* %B
%tmp2 = call %struct.__neon_int32x2x3_t @llvm.arm.neon.vld3lane.v2i32(i8* %tmp0, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, i32 1, i32 1)
%tmp3 = extractvalue %struct.__neon_int32x2x3_t %tmp2, 0
%tmp4 = extractvalue %struct.__neon_int32x2x3_t %tmp2, 1
@@ -264,7 +264,7 @@ define <2 x float> @vld3lanef(float* %A, <2 x float>* %B) nounwind {
;CHECK-LABEL: vld3lanef:
;CHECK: vld3.32
%tmp0 = bitcast float* %A to i8*
- %tmp1 = load <2 x float>* %B
+ %tmp1 = load <2 x float>, <2 x float>* %B
%tmp2 = call %struct.__neon_float32x2x3_t @llvm.arm.neon.vld3lane.v2f32(i8* %tmp0, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1, i32 1, i32 1)
%tmp3 = extractvalue %struct.__neon_float32x2x3_t %tmp2, 0
%tmp4 = extractvalue %struct.__neon_float32x2x3_t %tmp2, 1
@@ -279,7 +279,7 @@ define <8 x i16> @vld3laneQi16(i16* %A, <8 x i16>* %B) nounwind {
;Check the (default) alignment value. VLD3 does not support alignment.
;CHECK: vld3.16 {d{{.*}}[1], d{{.*}}[1], d{{.*}}[1]}, [{{r[0-9]+}}]
%tmp0 = bitcast i16* %A to i8*
- %tmp1 = load <8 x i16>* %B
+ %tmp1 = load <8 x i16>, <8 x i16>* %B
%tmp2 = call %struct.__neon_int16x8x3_t @llvm.arm.neon.vld3lane.v8i16(i8* %tmp0, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1, i32 1, i32 8)
%tmp3 = extractvalue %struct.__neon_int16x8x3_t %tmp2, 0
%tmp4 = extractvalue %struct.__neon_int16x8x3_t %tmp2, 1
@@ -293,16 +293,16 @@ define <8 x i16> @vld3laneQi16(i16* %A, <8 x i16>* %B) nounwind {
define <8 x i16> @vld3laneQi16_update(i16** %ptr, <8 x i16>* %B, i32 %inc) nounwind {
;CHECK-LABEL: vld3laneQi16_update:
;CHECK: vld3.16 {d{{.*}}[1], d{{.*}}[1], d{{.*}}[1]}, [{{r[0-9]+}}], {{r[0-9]+}}
- %A = load i16** %ptr
+ %A = load i16*, i16** %ptr
%tmp0 = bitcast i16* %A to i8*
- %tmp1 = load <8 x i16>* %B
+ %tmp1 = load <8 x i16>, <8 x i16>* %B
%tmp2 = call %struct.__neon_int16x8x3_t @llvm.arm.neon.vld3lane.v8i16(i8* %tmp0, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1, i32 1, i32 8)
%tmp3 = extractvalue %struct.__neon_int16x8x3_t %tmp2, 0
%tmp4 = extractvalue %struct.__neon_int16x8x3_t %tmp2, 1
%tmp5 = extractvalue %struct.__neon_int16x8x3_t %tmp2, 2
%tmp6 = add <8 x i16> %tmp3, %tmp4
%tmp7 = add <8 x i16> %tmp5, %tmp6
- %tmp8 = getelementptr i16* %A, i32 %inc
+ %tmp8 = getelementptr i16, i16* %A, i32 %inc
store i16* %tmp8, i16** %ptr
ret <8 x i16> %tmp7
}
@@ -311,7 +311,7 @@ define <4 x i32> @vld3laneQi32(i32* %A, <4 x i32>* %B) nounwind {
;CHECK-LABEL: vld3laneQi32:
;CHECK: vld3.32
%tmp0 = bitcast i32* %A to i8*
- %tmp1 = load <4 x i32>* %B
+ %tmp1 = load <4 x i32>, <4 x i32>* %B
%tmp2 = call %struct.__neon_int32x4x3_t @llvm.arm.neon.vld3lane.v4i32(i8* %tmp0, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1, i32 3, i32 1)
%tmp3 = extractvalue %struct.__neon_int32x4x3_t %tmp2, 0
%tmp4 = extractvalue %struct.__neon_int32x4x3_t %tmp2, 1
@@ -325,7 +325,7 @@ define <4 x float> @vld3laneQf(float* %A, <4 x float>* %B) nounwind {
;CHECK-LABEL: vld3laneQf:
;CHECK: vld3.32
%tmp0 = bitcast float* %A to i8*
- %tmp1 = load <4 x float>* %B
+ %tmp1 = load <4 x float>, <4 x float>* %B
%tmp2 = call %struct.__neon_float32x4x3_t @llvm.arm.neon.vld3lane.v4f32(i8* %tmp0, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1, i32 1, i32 1)
%tmp3 = extractvalue %struct.__neon_float32x4x3_t %tmp2, 0
%tmp4 = extractvalue %struct.__neon_float32x4x3_t %tmp2, 1
@@ -357,7 +357,7 @@ define <8 x i8> @vld4lanei8(i8* %A, <8 x i8>* %B) nounwind {
;CHECK-LABEL: vld4lanei8:
;Check the alignment value. Max for this instruction is 32 bits:
;CHECK: vld4.8 {d{{.*}}[1], d{{.*}}[1], d{{.*}}[1], d{{.*}}[1]}, [{{r[0-9]+}}:32]
- %tmp1 = load <8 x i8>* %B
+ %tmp1 = load <8 x i8>, <8 x i8>* %B
%tmp2 = call %struct.__neon_int8x8x4_t @llvm.arm.neon.vld4lane.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, i32 1, i32 8)
%tmp3 = extractvalue %struct.__neon_int8x8x4_t %tmp2, 0
%tmp4 = extractvalue %struct.__neon_int8x8x4_t %tmp2, 1
@@ -373,8 +373,8 @@ define <8 x i8> @vld4lanei8(i8* %A, <8 x i8>* %B) nounwind {
define <8 x i8> @vld4lanei8_update(i8** %ptr, <8 x i8>* %B) nounwind {
;CHECK-LABEL: vld4lanei8_update:
;CHECK: vld4.8 {d16[1], d17[1], d18[1], d19[1]}, [{{r[0-9]+}}:32]!
- %A = load i8** %ptr
- %tmp1 = load <8 x i8>* %B
+ %A = load i8*, i8** %ptr
+ %tmp1 = load <8 x i8>, <8 x i8>* %B
%tmp2 = call %struct.__neon_int8x8x4_t @llvm.arm.neon.vld4lane.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, i32 1, i32 8)
%tmp3 = extractvalue %struct.__neon_int8x8x4_t %tmp2, 0
%tmp4 = extractvalue %struct.__neon_int8x8x4_t %tmp2, 1
@@ -383,7 +383,7 @@ define <8 x i8> @vld4lanei8_update(i8** %ptr, <8 x i8>* %B) nounwind {
%tmp7 = add <8 x i8> %tmp3, %tmp4
%tmp8 = add <8 x i8> %tmp5, %tmp6
%tmp9 = add <8 x i8> %tmp7, %tmp8
- %tmp10 = getelementptr i8* %A, i32 4
+ %tmp10 = getelementptr i8, i8* %A, i32 4
store i8* %tmp10, i8** %ptr
ret <8 x i8> %tmp9
}
@@ -394,7 +394,7 @@ define <4 x i16> @vld4lanei16(i16* %A, <4 x i16>* %B) nounwind {
;being loaded is ignored.
;CHECK: vld4.16 {d16[1], d17[1], d18[1], d19[1]}, [{{r[0-9]+}}]
%tmp0 = bitcast i16* %A to i8*
- %tmp1 = load <4 x i16>* %B
+ %tmp1 = load <4 x i16>, <4 x i16>* %B
%tmp2 = call %struct.__neon_int16x4x4_t @llvm.arm.neon.vld4lane.v4i16(i8* %tmp0, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1, i32 1, i32 4)
%tmp3 = extractvalue %struct.__neon_int16x4x4_t %tmp2, 0
%tmp4 = extractvalue %struct.__neon_int16x4x4_t %tmp2, 1
@@ -412,7 +412,7 @@ define <2 x i32> @vld4lanei32(i32* %A, <2 x i32>* %B) nounwind {
;it is smaller than the total size of the memory being loaded.
;CHECK: vld4.32 {d16[1], d17[1], d18[1], d19[1]}, [{{r[0-9]+}}:64]
%tmp0 = bitcast i32* %A to i8*
- %tmp1 = load <2 x i32>* %B
+ %tmp1 = load <2 x i32>, <2 x i32>* %B
%tmp2 = call %struct.__neon_int32x2x4_t @llvm.arm.neon.vld4lane.v2i32(i8* %tmp0, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, i32 1, i32 8)
%tmp3 = extractvalue %struct.__neon_int32x2x4_t %tmp2, 0
%tmp4 = extractvalue %struct.__neon_int32x2x4_t %tmp2, 1
@@ -428,7 +428,7 @@ define <2 x float> @vld4lanef(float* %A, <2 x float>* %B) nounwind {
;CHECK-LABEL: vld4lanef:
;CHECK: vld4.32
%tmp0 = bitcast float* %A to i8*
- %tmp1 = load <2 x float>* %B
+ %tmp1 = load <2 x float>, <2 x float>* %B
%tmp2 = call %struct.__neon_float32x2x4_t @llvm.arm.neon.vld4lane.v2f32(i8* %tmp0, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1, i32 1, i32 1)
%tmp3 = extractvalue %struct.__neon_float32x2x4_t %tmp2, 0
%tmp4 = extractvalue %struct.__neon_float32x2x4_t %tmp2, 1
@@ -445,7 +445,7 @@ define <8 x i16> @vld4laneQi16(i16* %A, <8 x i16>* %B) nounwind {
;Check the alignment value. Max for this instruction is 64 bits:
;CHECK: vld4.16 {d16[1], d18[1], d20[1], d22[1]}, [{{r[0-9]+}}:64]
%tmp0 = bitcast i16* %A to i8*
- %tmp1 = load <8 x i16>* %B
+ %tmp1 = load <8 x i16>, <8 x i16>* %B
%tmp2 = call %struct.__neon_int16x8x4_t @llvm.arm.neon.vld4lane.v8i16(i8* %tmp0, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1, i32 1, i32 16)
%tmp3 = extractvalue %struct.__neon_int16x8x4_t %tmp2, 0
%tmp4 = extractvalue %struct.__neon_int16x8x4_t %tmp2, 1
@@ -462,7 +462,7 @@ define <4 x i32> @vld4laneQi32(i32* %A, <4 x i32>* %B) nounwind {
;Check the (default) alignment.
;CHECK: vld4.32 {d17[0], d19[0], d21[0], d23[0]}, [{{r[0-9]+}}]
%tmp0 = bitcast i32* %A to i8*
- %tmp1 = load <4 x i32>* %B
+ %tmp1 = load <4 x i32>, <4 x i32>* %B
%tmp2 = call %struct.__neon_int32x4x4_t @llvm.arm.neon.vld4lane.v4i32(i8* %tmp0, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1, i32 2, i32 1)
%tmp3 = extractvalue %struct.__neon_int32x4x4_t %tmp2, 0
%tmp4 = extractvalue %struct.__neon_int32x4x4_t %tmp2, 1
@@ -478,7 +478,7 @@ define <4 x float> @vld4laneQf(float* %A, <4 x float>* %B) nounwind {
;CHECK-LABEL: vld4laneQf:
;CHECK: vld4.32
%tmp0 = bitcast float* %A to i8*
- %tmp1 = load <4 x float>* %B
+ %tmp1 = load <4 x float>, <4 x float>* %B
%tmp2 = call %struct.__neon_float32x4x4_t @llvm.arm.neon.vld4lane.v4f32(i8* %tmp0, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1, i32 1, i32 1)
%tmp3 = extractvalue %struct.__neon_float32x4x4_t %tmp2, 0
%tmp4 = extractvalue %struct.__neon_float32x4x4_t %tmp2, 1