aboutsummaryrefslogtreecommitdiffstats
path: root/test/CodeGen/AArch64/arm64-vext.ll
diff options
context:
space:
mode:
Diffstat (limited to 'test/CodeGen/AArch64/arm64-vext.ll')
-rw-r--r--test/CodeGen/AArch64/arm64-vext.ll176
1 files changed, 88 insertions, 88 deletions
diff --git a/test/CodeGen/AArch64/arm64-vext.ll b/test/CodeGen/AArch64/arm64-vext.ll
index 2240dfd..fa57eeb 100644
--- a/test/CodeGen/AArch64/arm64-vext.ll
+++ b/test/CodeGen/AArch64/arm64-vext.ll
@@ -6,12 +6,12 @@ define void @test_vext_s8() nounwind ssp {
%xS8x8 = alloca <8 x i8>, align 8
%__a = alloca <8 x i8>, align 8
%__b = alloca <8 x i8>, align 8
- %tmp = load <8 x i8>* %xS8x8, align 8
+ %tmp = load <8 x i8>, <8 x i8>* %xS8x8, align 8
store <8 x i8> %tmp, <8 x i8>* %__a, align 8
- %tmp1 = load <8 x i8>* %xS8x8, align 8
+ %tmp1 = load <8 x i8>, <8 x i8>* %xS8x8, align 8
store <8 x i8> %tmp1, <8 x i8>* %__b, align 8
- %tmp2 = load <8 x i8>* %__a, align 8
- %tmp3 = load <8 x i8>* %__b, align 8
+ %tmp2 = load <8 x i8>, <8 x i8>* %__a, align 8
+ %tmp3 = load <8 x i8>, <8 x i8>* %__b, align 8
%vext = shufflevector <8 x i8> %tmp2, <8 x i8> %tmp3, <8 x i32> <i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8>
store <8 x i8> %vext, <8 x i8>* %xS8x8, align 8
ret void
@@ -23,12 +23,12 @@ define void @test_vext_u8() nounwind ssp {
%xU8x8 = alloca <8 x i8>, align 8
%__a = alloca <8 x i8>, align 8
%__b = alloca <8 x i8>, align 8
- %tmp = load <8 x i8>* %xU8x8, align 8
+ %tmp = load <8 x i8>, <8 x i8>* %xU8x8, align 8
store <8 x i8> %tmp, <8 x i8>* %__a, align 8
- %tmp1 = load <8 x i8>* %xU8x8, align 8
+ %tmp1 = load <8 x i8>, <8 x i8>* %xU8x8, align 8
store <8 x i8> %tmp1, <8 x i8>* %__b, align 8
- %tmp2 = load <8 x i8>* %__a, align 8
- %tmp3 = load <8 x i8>* %__b, align 8
+ %tmp2 = load <8 x i8>, <8 x i8>* %__a, align 8
+ %tmp3 = load <8 x i8>, <8 x i8>* %__b, align 8
%vext = shufflevector <8 x i8> %tmp2, <8 x i8> %tmp3, <8 x i32> <i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9>
store <8 x i8> %vext, <8 x i8>* %xU8x8, align 8
ret void
@@ -40,12 +40,12 @@ define void @test_vext_p8() nounwind ssp {
%xP8x8 = alloca <8 x i8>, align 8
%__a = alloca <8 x i8>, align 8
%__b = alloca <8 x i8>, align 8
- %tmp = load <8 x i8>* %xP8x8, align 8
+ %tmp = load <8 x i8>, <8 x i8>* %xP8x8, align 8
store <8 x i8> %tmp, <8 x i8>* %__a, align 8
- %tmp1 = load <8 x i8>* %xP8x8, align 8
+ %tmp1 = load <8 x i8>, <8 x i8>* %xP8x8, align 8
store <8 x i8> %tmp1, <8 x i8>* %__b, align 8
- %tmp2 = load <8 x i8>* %__a, align 8
- %tmp3 = load <8 x i8>* %__b, align 8
+ %tmp2 = load <8 x i8>, <8 x i8>* %__a, align 8
+ %tmp3 = load <8 x i8>, <8 x i8>* %__b, align 8
%vext = shufflevector <8 x i8> %tmp2, <8 x i8> %tmp3, <8 x i32> <i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10>
store <8 x i8> %vext, <8 x i8>* %xP8x8, align 8
ret void
@@ -57,13 +57,13 @@ define void @test_vext_s16() nounwind ssp {
%xS16x4 = alloca <4 x i16>, align 8
%__a = alloca <4 x i16>, align 8
%__b = alloca <4 x i16>, align 8
- %tmp = load <4 x i16>* %xS16x4, align 8
+ %tmp = load <4 x i16>, <4 x i16>* %xS16x4, align 8
store <4 x i16> %tmp, <4 x i16>* %__a, align 8
- %tmp1 = load <4 x i16>* %xS16x4, align 8
+ %tmp1 = load <4 x i16>, <4 x i16>* %xS16x4, align 8
store <4 x i16> %tmp1, <4 x i16>* %__b, align 8
- %tmp2 = load <4 x i16>* %__a, align 8
+ %tmp2 = load <4 x i16>, <4 x i16>* %__a, align 8
%tmp3 = bitcast <4 x i16> %tmp2 to <8 x i8>
- %tmp4 = load <4 x i16>* %__b, align 8
+ %tmp4 = load <4 x i16>, <4 x i16>* %__b, align 8
%tmp5 = bitcast <4 x i16> %tmp4 to <8 x i8>
%tmp6 = bitcast <8 x i8> %tmp3 to <4 x i16>
%tmp7 = bitcast <8 x i8> %tmp5 to <4 x i16>
@@ -78,13 +78,13 @@ define void @test_vext_u16() nounwind ssp {
%xU16x4 = alloca <4 x i16>, align 8
%__a = alloca <4 x i16>, align 8
%__b = alloca <4 x i16>, align 8
- %tmp = load <4 x i16>* %xU16x4, align 8
+ %tmp = load <4 x i16>, <4 x i16>* %xU16x4, align 8
store <4 x i16> %tmp, <4 x i16>* %__a, align 8
- %tmp1 = load <4 x i16>* %xU16x4, align 8
+ %tmp1 = load <4 x i16>, <4 x i16>* %xU16x4, align 8
store <4 x i16> %tmp1, <4 x i16>* %__b, align 8
- %tmp2 = load <4 x i16>* %__a, align 8
+ %tmp2 = load <4 x i16>, <4 x i16>* %__a, align 8
%tmp3 = bitcast <4 x i16> %tmp2 to <8 x i8>
- %tmp4 = load <4 x i16>* %__b, align 8
+ %tmp4 = load <4 x i16>, <4 x i16>* %__b, align 8
%tmp5 = bitcast <4 x i16> %tmp4 to <8 x i8>
%tmp6 = bitcast <8 x i8> %tmp3 to <4 x i16>
%tmp7 = bitcast <8 x i8> %tmp5 to <4 x i16>
@@ -99,13 +99,13 @@ define void @test_vext_p16() nounwind ssp {
%xP16x4 = alloca <4 x i16>, align 8
%__a = alloca <4 x i16>, align 8
%__b = alloca <4 x i16>, align 8
- %tmp = load <4 x i16>* %xP16x4, align 8
+ %tmp = load <4 x i16>, <4 x i16>* %xP16x4, align 8
store <4 x i16> %tmp, <4 x i16>* %__a, align 8
- %tmp1 = load <4 x i16>* %xP16x4, align 8
+ %tmp1 = load <4 x i16>, <4 x i16>* %xP16x4, align 8
store <4 x i16> %tmp1, <4 x i16>* %__b, align 8
- %tmp2 = load <4 x i16>* %__a, align 8
+ %tmp2 = load <4 x i16>, <4 x i16>* %__a, align 8
%tmp3 = bitcast <4 x i16> %tmp2 to <8 x i8>
- %tmp4 = load <4 x i16>* %__b, align 8
+ %tmp4 = load <4 x i16>, <4 x i16>* %__b, align 8
%tmp5 = bitcast <4 x i16> %tmp4 to <8 x i8>
%tmp6 = bitcast <8 x i8> %tmp3 to <4 x i16>
%tmp7 = bitcast <8 x i8> %tmp5 to <4 x i16>
@@ -120,13 +120,13 @@ define void @test_vext_s32() nounwind ssp {
%xS32x2 = alloca <2 x i32>, align 8
%__a = alloca <2 x i32>, align 8
%__b = alloca <2 x i32>, align 8
- %tmp = load <2 x i32>* %xS32x2, align 8
+ %tmp = load <2 x i32>, <2 x i32>* %xS32x2, align 8
store <2 x i32> %tmp, <2 x i32>* %__a, align 8
- %tmp1 = load <2 x i32>* %xS32x2, align 8
+ %tmp1 = load <2 x i32>, <2 x i32>* %xS32x2, align 8
store <2 x i32> %tmp1, <2 x i32>* %__b, align 8
- %tmp2 = load <2 x i32>* %__a, align 8
+ %tmp2 = load <2 x i32>, <2 x i32>* %__a, align 8
%tmp3 = bitcast <2 x i32> %tmp2 to <8 x i8>
- %tmp4 = load <2 x i32>* %__b, align 8
+ %tmp4 = load <2 x i32>, <2 x i32>* %__b, align 8
%tmp5 = bitcast <2 x i32> %tmp4 to <8 x i8>
%tmp6 = bitcast <8 x i8> %tmp3 to <2 x i32>
%tmp7 = bitcast <8 x i8> %tmp5 to <2 x i32>
@@ -141,13 +141,13 @@ define void @test_vext_u32() nounwind ssp {
%xU32x2 = alloca <2 x i32>, align 8
%__a = alloca <2 x i32>, align 8
%__b = alloca <2 x i32>, align 8
- %tmp = load <2 x i32>* %xU32x2, align 8
+ %tmp = load <2 x i32>, <2 x i32>* %xU32x2, align 8
store <2 x i32> %tmp, <2 x i32>* %__a, align 8
- %tmp1 = load <2 x i32>* %xU32x2, align 8
+ %tmp1 = load <2 x i32>, <2 x i32>* %xU32x2, align 8
store <2 x i32> %tmp1, <2 x i32>* %__b, align 8
- %tmp2 = load <2 x i32>* %__a, align 8
+ %tmp2 = load <2 x i32>, <2 x i32>* %__a, align 8
%tmp3 = bitcast <2 x i32> %tmp2 to <8 x i8>
- %tmp4 = load <2 x i32>* %__b, align 8
+ %tmp4 = load <2 x i32>, <2 x i32>* %__b, align 8
%tmp5 = bitcast <2 x i32> %tmp4 to <8 x i8>
%tmp6 = bitcast <8 x i8> %tmp3 to <2 x i32>
%tmp7 = bitcast <8 x i8> %tmp5 to <2 x i32>
@@ -162,13 +162,13 @@ define void @test_vext_f32() nounwind ssp {
%xF32x2 = alloca <2 x float>, align 8
%__a = alloca <2 x float>, align 8
%__b = alloca <2 x float>, align 8
- %tmp = load <2 x float>* %xF32x2, align 8
+ %tmp = load <2 x float>, <2 x float>* %xF32x2, align 8
store <2 x float> %tmp, <2 x float>* %__a, align 8
- %tmp1 = load <2 x float>* %xF32x2, align 8
+ %tmp1 = load <2 x float>, <2 x float>* %xF32x2, align 8
store <2 x float> %tmp1, <2 x float>* %__b, align 8
- %tmp2 = load <2 x float>* %__a, align 8
+ %tmp2 = load <2 x float>, <2 x float>* %__a, align 8
%tmp3 = bitcast <2 x float> %tmp2 to <8 x i8>
- %tmp4 = load <2 x float>* %__b, align 8
+ %tmp4 = load <2 x float>, <2 x float>* %__b, align 8
%tmp5 = bitcast <2 x float> %tmp4 to <8 x i8>
%tmp6 = bitcast <8 x i8> %tmp3 to <2 x float>
%tmp7 = bitcast <8 x i8> %tmp5 to <2 x float>
@@ -184,13 +184,13 @@ define void @test_vext_s64() nounwind ssp {
%xS64x1 = alloca <1 x i64>, align 8
%__a = alloca <1 x i64>, align 8
%__b = alloca <1 x i64>, align 8
- %tmp = load <1 x i64>* %xS64x1, align 8
+ %tmp = load <1 x i64>, <1 x i64>* %xS64x1, align 8
store <1 x i64> %tmp, <1 x i64>* %__a, align 8
- %tmp1 = load <1 x i64>* %xS64x1, align 8
+ %tmp1 = load <1 x i64>, <1 x i64>* %xS64x1, align 8
store <1 x i64> %tmp1, <1 x i64>* %__b, align 8
- %tmp2 = load <1 x i64>* %__a, align 8
+ %tmp2 = load <1 x i64>, <1 x i64>* %__a, align 8
%tmp3 = bitcast <1 x i64> %tmp2 to <8 x i8>
- %tmp4 = load <1 x i64>* %__b, align 8
+ %tmp4 = load <1 x i64>, <1 x i64>* %__b, align 8
%tmp5 = bitcast <1 x i64> %tmp4 to <8 x i8>
%tmp6 = bitcast <8 x i8> %tmp3 to <1 x i64>
%tmp7 = bitcast <8 x i8> %tmp5 to <1 x i64>
@@ -206,13 +206,13 @@ define void @test_vext_u64() nounwind ssp {
%xU64x1 = alloca <1 x i64>, align 8
%__a = alloca <1 x i64>, align 8
%__b = alloca <1 x i64>, align 8
- %tmp = load <1 x i64>* %xU64x1, align 8
+ %tmp = load <1 x i64>, <1 x i64>* %xU64x1, align 8
store <1 x i64> %tmp, <1 x i64>* %__a, align 8
- %tmp1 = load <1 x i64>* %xU64x1, align 8
+ %tmp1 = load <1 x i64>, <1 x i64>* %xU64x1, align 8
store <1 x i64> %tmp1, <1 x i64>* %__b, align 8
- %tmp2 = load <1 x i64>* %__a, align 8
+ %tmp2 = load <1 x i64>, <1 x i64>* %__a, align 8
%tmp3 = bitcast <1 x i64> %tmp2 to <8 x i8>
- %tmp4 = load <1 x i64>* %__b, align 8
+ %tmp4 = load <1 x i64>, <1 x i64>* %__b, align 8
%tmp5 = bitcast <1 x i64> %tmp4 to <8 x i8>
%tmp6 = bitcast <8 x i8> %tmp3 to <1 x i64>
%tmp7 = bitcast <8 x i8> %tmp5 to <1 x i64>
@@ -227,12 +227,12 @@ define void @test_vextq_s8() nounwind ssp {
%xS8x16 = alloca <16 x i8>, align 16
%__a = alloca <16 x i8>, align 16
%__b = alloca <16 x i8>, align 16
- %tmp = load <16 x i8>* %xS8x16, align 16
+ %tmp = load <16 x i8>, <16 x i8>* %xS8x16, align 16
store <16 x i8> %tmp, <16 x i8>* %__a, align 16
- %tmp1 = load <16 x i8>* %xS8x16, align 16
+ %tmp1 = load <16 x i8>, <16 x i8>* %xS8x16, align 16
store <16 x i8> %tmp1, <16 x i8>* %__b, align 16
- %tmp2 = load <16 x i8>* %__a, align 16
- %tmp3 = load <16 x i8>* %__b, align 16
+ %tmp2 = load <16 x i8>, <16 x i8>* %__a, align 16
+ %tmp3 = load <16 x i8>, <16 x i8>* %__b, align 16
%vext = shufflevector <16 x i8> %tmp2, <16 x i8> %tmp3, <16 x i32> <i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19>
store <16 x i8> %vext, <16 x i8>* %xS8x16, align 16
ret void
@@ -244,12 +244,12 @@ define void @test_vextq_u8() nounwind ssp {
%xU8x16 = alloca <16 x i8>, align 16
%__a = alloca <16 x i8>, align 16
%__b = alloca <16 x i8>, align 16
- %tmp = load <16 x i8>* %xU8x16, align 16
+ %tmp = load <16 x i8>, <16 x i8>* %xU8x16, align 16
store <16 x i8> %tmp, <16 x i8>* %__a, align 16
- %tmp1 = load <16 x i8>* %xU8x16, align 16
+ %tmp1 = load <16 x i8>, <16 x i8>* %xU8x16, align 16
store <16 x i8> %tmp1, <16 x i8>* %__b, align 16
- %tmp2 = load <16 x i8>* %__a, align 16
- %tmp3 = load <16 x i8>* %__b, align 16
+ %tmp2 = load <16 x i8>, <16 x i8>* %__a, align 16
+ %tmp3 = load <16 x i8>, <16 x i8>* %__b, align 16
%vext = shufflevector <16 x i8> %tmp2, <16 x i8> %tmp3, <16 x i32> <i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20>
store <16 x i8> %vext, <16 x i8>* %xU8x16, align 16
ret void
@@ -261,12 +261,12 @@ define void @test_vextq_p8() nounwind ssp {
%xP8x16 = alloca <16 x i8>, align 16
%__a = alloca <16 x i8>, align 16
%__b = alloca <16 x i8>, align 16
- %tmp = load <16 x i8>* %xP8x16, align 16
+ %tmp = load <16 x i8>, <16 x i8>* %xP8x16, align 16
store <16 x i8> %tmp, <16 x i8>* %__a, align 16
- %tmp1 = load <16 x i8>* %xP8x16, align 16
+ %tmp1 = load <16 x i8>, <16 x i8>* %xP8x16, align 16
store <16 x i8> %tmp1, <16 x i8>* %__b, align 16
- %tmp2 = load <16 x i8>* %__a, align 16
- %tmp3 = load <16 x i8>* %__b, align 16
+ %tmp2 = load <16 x i8>, <16 x i8>* %__a, align 16
+ %tmp3 = load <16 x i8>, <16 x i8>* %__b, align 16
%vext = shufflevector <16 x i8> %tmp2, <16 x i8> %tmp3, <16 x i32> <i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21>
store <16 x i8> %vext, <16 x i8>* %xP8x16, align 16
ret void
@@ -278,13 +278,13 @@ define void @test_vextq_s16() nounwind ssp {
%xS16x8 = alloca <8 x i16>, align 16
%__a = alloca <8 x i16>, align 16
%__b = alloca <8 x i16>, align 16
- %tmp = load <8 x i16>* %xS16x8, align 16
+ %tmp = load <8 x i16>, <8 x i16>* %xS16x8, align 16
store <8 x i16> %tmp, <8 x i16>* %__a, align 16
- %tmp1 = load <8 x i16>* %xS16x8, align 16
+ %tmp1 = load <8 x i16>, <8 x i16>* %xS16x8, align 16
store <8 x i16> %tmp1, <8 x i16>* %__b, align 16
- %tmp2 = load <8 x i16>* %__a, align 16
+ %tmp2 = load <8 x i16>, <8 x i16>* %__a, align 16
%tmp3 = bitcast <8 x i16> %tmp2 to <16 x i8>
- %tmp4 = load <8 x i16>* %__b, align 16
+ %tmp4 = load <8 x i16>, <8 x i16>* %__b, align 16
%tmp5 = bitcast <8 x i16> %tmp4 to <16 x i8>
%tmp6 = bitcast <16 x i8> %tmp3 to <8 x i16>
%tmp7 = bitcast <16 x i8> %tmp5 to <8 x i16>
@@ -299,13 +299,13 @@ define void @test_vextq_u16() nounwind ssp {
%xU16x8 = alloca <8 x i16>, align 16
%__a = alloca <8 x i16>, align 16
%__b = alloca <8 x i16>, align 16
- %tmp = load <8 x i16>* %xU16x8, align 16
+ %tmp = load <8 x i16>, <8 x i16>* %xU16x8, align 16
store <8 x i16> %tmp, <8 x i16>* %__a, align 16
- %tmp1 = load <8 x i16>* %xU16x8, align 16
+ %tmp1 = load <8 x i16>, <8 x i16>* %xU16x8, align 16
store <8 x i16> %tmp1, <8 x i16>* %__b, align 16
- %tmp2 = load <8 x i16>* %__a, align 16
+ %tmp2 = load <8 x i16>, <8 x i16>* %__a, align 16
%tmp3 = bitcast <8 x i16> %tmp2 to <16 x i8>
- %tmp4 = load <8 x i16>* %__b, align 16
+ %tmp4 = load <8 x i16>, <8 x i16>* %__b, align 16
%tmp5 = bitcast <8 x i16> %tmp4 to <16 x i8>
%tmp6 = bitcast <16 x i8> %tmp3 to <8 x i16>
%tmp7 = bitcast <16 x i8> %tmp5 to <8 x i16>
@@ -320,13 +320,13 @@ define void @test_vextq_p16() nounwind ssp {
%xP16x8 = alloca <8 x i16>, align 16
%__a = alloca <8 x i16>, align 16
%__b = alloca <8 x i16>, align 16
- %tmp = load <8 x i16>* %xP16x8, align 16
+ %tmp = load <8 x i16>, <8 x i16>* %xP16x8, align 16
store <8 x i16> %tmp, <8 x i16>* %__a, align 16
- %tmp1 = load <8 x i16>* %xP16x8, align 16
+ %tmp1 = load <8 x i16>, <8 x i16>* %xP16x8, align 16
store <8 x i16> %tmp1, <8 x i16>* %__b, align 16
- %tmp2 = load <8 x i16>* %__a, align 16
+ %tmp2 = load <8 x i16>, <8 x i16>* %__a, align 16
%tmp3 = bitcast <8 x i16> %tmp2 to <16 x i8>
- %tmp4 = load <8 x i16>* %__b, align 16
+ %tmp4 = load <8 x i16>, <8 x i16>* %__b, align 16
%tmp5 = bitcast <8 x i16> %tmp4 to <16 x i8>
%tmp6 = bitcast <16 x i8> %tmp3 to <8 x i16>
%tmp7 = bitcast <16 x i8> %tmp5 to <8 x i16>
@@ -341,13 +341,13 @@ define void @test_vextq_s32() nounwind ssp {
%xS32x4 = alloca <4 x i32>, align 16
%__a = alloca <4 x i32>, align 16
%__b = alloca <4 x i32>, align 16
- %tmp = load <4 x i32>* %xS32x4, align 16
+ %tmp = load <4 x i32>, <4 x i32>* %xS32x4, align 16
store <4 x i32> %tmp, <4 x i32>* %__a, align 16
- %tmp1 = load <4 x i32>* %xS32x4, align 16
+ %tmp1 = load <4 x i32>, <4 x i32>* %xS32x4, align 16
store <4 x i32> %tmp1, <4 x i32>* %__b, align 16
- %tmp2 = load <4 x i32>* %__a, align 16
+ %tmp2 = load <4 x i32>, <4 x i32>* %__a, align 16
%tmp3 = bitcast <4 x i32> %tmp2 to <16 x i8>
- %tmp4 = load <4 x i32>* %__b, align 16
+ %tmp4 = load <4 x i32>, <4 x i32>* %__b, align 16
%tmp5 = bitcast <4 x i32> %tmp4 to <16 x i8>
%tmp6 = bitcast <16 x i8> %tmp3 to <4 x i32>
%tmp7 = bitcast <16 x i8> %tmp5 to <4 x i32>
@@ -362,13 +362,13 @@ define void @test_vextq_u32() nounwind ssp {
%xU32x4 = alloca <4 x i32>, align 16
%__a = alloca <4 x i32>, align 16
%__b = alloca <4 x i32>, align 16
- %tmp = load <4 x i32>* %xU32x4, align 16
+ %tmp = load <4 x i32>, <4 x i32>* %xU32x4, align 16
store <4 x i32> %tmp, <4 x i32>* %__a, align 16
- %tmp1 = load <4 x i32>* %xU32x4, align 16
+ %tmp1 = load <4 x i32>, <4 x i32>* %xU32x4, align 16
store <4 x i32> %tmp1, <4 x i32>* %__b, align 16
- %tmp2 = load <4 x i32>* %__a, align 16
+ %tmp2 = load <4 x i32>, <4 x i32>* %__a, align 16
%tmp3 = bitcast <4 x i32> %tmp2 to <16 x i8>
- %tmp4 = load <4 x i32>* %__b, align 16
+ %tmp4 = load <4 x i32>, <4 x i32>* %__b, align 16
%tmp5 = bitcast <4 x i32> %tmp4 to <16 x i8>
%tmp6 = bitcast <16 x i8> %tmp3 to <4 x i32>
%tmp7 = bitcast <16 x i8> %tmp5 to <4 x i32>
@@ -383,13 +383,13 @@ define void @test_vextq_f32() nounwind ssp {
%xF32x4 = alloca <4 x float>, align 16
%__a = alloca <4 x float>, align 16
%__b = alloca <4 x float>, align 16
- %tmp = load <4 x float>* %xF32x4, align 16
+ %tmp = load <4 x float>, <4 x float>* %xF32x4, align 16
store <4 x float> %tmp, <4 x float>* %__a, align 16
- %tmp1 = load <4 x float>* %xF32x4, align 16
+ %tmp1 = load <4 x float>, <4 x float>* %xF32x4, align 16
store <4 x float> %tmp1, <4 x float>* %__b, align 16
- %tmp2 = load <4 x float>* %__a, align 16
+ %tmp2 = load <4 x float>, <4 x float>* %__a, align 16
%tmp3 = bitcast <4 x float> %tmp2 to <16 x i8>
- %tmp4 = load <4 x float>* %__b, align 16
+ %tmp4 = load <4 x float>, <4 x float>* %__b, align 16
%tmp5 = bitcast <4 x float> %tmp4 to <16 x i8>
%tmp6 = bitcast <16 x i8> %tmp3 to <4 x float>
%tmp7 = bitcast <16 x i8> %tmp5 to <4 x float>
@@ -404,13 +404,13 @@ define void @test_vextq_s64() nounwind ssp {
%xS64x2 = alloca <2 x i64>, align 16
%__a = alloca <2 x i64>, align 16
%__b = alloca <2 x i64>, align 16
- %tmp = load <2 x i64>* %xS64x2, align 16
+ %tmp = load <2 x i64>, <2 x i64>* %xS64x2, align 16
store <2 x i64> %tmp, <2 x i64>* %__a, align 16
- %tmp1 = load <2 x i64>* %xS64x2, align 16
+ %tmp1 = load <2 x i64>, <2 x i64>* %xS64x2, align 16
store <2 x i64> %tmp1, <2 x i64>* %__b, align 16
- %tmp2 = load <2 x i64>* %__a, align 16
+ %tmp2 = load <2 x i64>, <2 x i64>* %__a, align 16
%tmp3 = bitcast <2 x i64> %tmp2 to <16 x i8>
- %tmp4 = load <2 x i64>* %__b, align 16
+ %tmp4 = load <2 x i64>, <2 x i64>* %__b, align 16
%tmp5 = bitcast <2 x i64> %tmp4 to <16 x i8>
%tmp6 = bitcast <16 x i8> %tmp3 to <2 x i64>
%tmp7 = bitcast <16 x i8> %tmp5 to <2 x i64>
@@ -425,13 +425,13 @@ define void @test_vextq_u64() nounwind ssp {
%xU64x2 = alloca <2 x i64>, align 16
%__a = alloca <2 x i64>, align 16
%__b = alloca <2 x i64>, align 16
- %tmp = load <2 x i64>* %xU64x2, align 16
+ %tmp = load <2 x i64>, <2 x i64>* %xU64x2, align 16
store <2 x i64> %tmp, <2 x i64>* %__a, align 16
- %tmp1 = load <2 x i64>* %xU64x2, align 16
+ %tmp1 = load <2 x i64>, <2 x i64>* %xU64x2, align 16
store <2 x i64> %tmp1, <2 x i64>* %__b, align 16
- %tmp2 = load <2 x i64>* %__a, align 16
+ %tmp2 = load <2 x i64>, <2 x i64>* %__a, align 16
%tmp3 = bitcast <2 x i64> %tmp2 to <16 x i8>
- %tmp4 = load <2 x i64>* %__b, align 16
+ %tmp4 = load <2 x i64>, <2 x i64>* %__b, align 16
%tmp5 = bitcast <2 x i64> %tmp4 to <16 x i8>
%tmp6 = bitcast <16 x i8> %tmp3 to <2 x i64>
%tmp7 = bitcast <16 x i8> %tmp5 to <2 x i64>