[clang] 8beaba1 - [Clang][AArch64] Capturing proper pointer alignment for Neon vld1 intrinsicts
Lucas Prates via cfe-commits
cfe-commits at lists.llvm.org
Wed Jun 3 03:39:36 PDT 2020
Author: Lucas Prates
Date: 2020-06-03T11:39:27+01:00
New Revision: 8beaba13b8a61697008854b82ed3b45377af9d9d
URL: https://github.com/llvm/llvm-project/commit/8beaba13b8a61697008854b82ed3b45377af9d9d
DIFF: https://github.com/llvm/llvm-project/commit/8beaba13b8a61697008854b82ed3b45377af9d9d.diff
LOG: [Clang][AArch64] Capturing proper pointer alignment for Neon vld1 intrinsicts
Summary:
During CodeGen for AArch64 Neon intrinsics, Clang was incorrectly
assuming all the pointers from which loads were being generated for vld1
intrinsics were aligned according to the intrinsics result type, causing
alignment faults on the code generated by the backend.
This patch updates vld1 intrinsics' CodeGen to properly capture the
correct load alignment based on the type of the pointer provided as
input for the intrinsic.
Reviewers: t.p.northover, ostannard, pcc, efriedma
Reviewed By: ostannard, efriedma
Subscribers: echristo, plotfi, nickdesaulniers, efriedma, kristof.beyls, danielkiss, cfe-commits
Tags: #clang
Differential Revision: https://reviews.llvm.org/D79721
Added:
Modified:
clang/lib/CodeGen/CGBuiltin.cpp
clang/test/CodeGen/aarch64-neon-intrinsics.c
Removed:
################################################################################
diff --git a/clang/lib/CodeGen/CGBuiltin.cpp b/clang/lib/CodeGen/CGBuiltin.cpp
index cf8c8a1669d7..13c24a5d2686 100644
--- a/clang/lib/CodeGen/CGBuiltin.cpp
+++ b/clang/lib/CodeGen/CGBuiltin.cpp
@@ -8636,7 +8636,27 @@ Value *CodeGenFunction::EmitAArch64BuiltinExpr(unsigned BuiltinID,
assert(Error == ASTContext::GE_None && "Should not codegen an error");
llvm::SmallVector<Value*, 4> Ops;
+ Address PtrOp0 = Address::invalid();
for (unsigned i = 0, e = E->getNumArgs() - 1; i != e; i++) {
+ if (i == 0) {
+ switch (BuiltinID) {
+ case NEON::BI__builtin_neon_vld1_v:
+ case NEON::BI__builtin_neon_vld1q_v:
+ case NEON::BI__builtin_neon_vld1_dup_v:
+ case NEON::BI__builtin_neon_vld1q_dup_v:
+ case NEON::BI__builtin_neon_vld1_lane_v:
+ case NEON::BI__builtin_neon_vld1q_lane_v:
+ case NEON::BI__builtin_neon_vst1_v:
+ case NEON::BI__builtin_neon_vst1q_v:
+ case NEON::BI__builtin_neon_vst1_lane_v:
+ case NEON::BI__builtin_neon_vst1q_lane_v:
+ // Get the alignment for the argument in addition to the value;
+ // we'll use it later.
+ PtrOp0 = EmitPointerWithAlignment(E->getArg(0));
+ Ops.push_back(PtrOp0.getPointer());
+ continue;
+ }
+ }
if ((ICEArguments & (1 << i)) == 0) {
Ops.push_back(EmitScalarExpr(E->getArg(i)));
} else {
@@ -10337,24 +10357,20 @@ Value *CodeGenFunction::EmitAArch64BuiltinExpr(unsigned BuiltinID,
case NEON::BI__builtin_neon_vld1_v:
case NEON::BI__builtin_neon_vld1q_v: {
Ops[0] = Builder.CreateBitCast(Ops[0], llvm::PointerType::getUnqual(VTy));
- auto Alignment = CharUnits::fromQuantity(
- BuiltinID == NEON::BI__builtin_neon_vld1_v ? 8 : 16);
- return Builder.CreateAlignedLoad(VTy, Ops[0], Alignment);
+ return Builder.CreateAlignedLoad(VTy, Ops[0], PtrOp0.getAlignment());
}
case NEON::BI__builtin_neon_vst1_v:
case NEON::BI__builtin_neon_vst1q_v:
Ops[0] = Builder.CreateBitCast(Ops[0], llvm::PointerType::getUnqual(VTy));
Ops[1] = Builder.CreateBitCast(Ops[1], VTy);
- return Builder.CreateDefaultAlignedStore(Ops[1], Ops[0]);
+ return Builder.CreateAlignedStore(Ops[1], Ops[0], PtrOp0.getAlignment());
case NEON::BI__builtin_neon_vld1_lane_v:
case NEON::BI__builtin_neon_vld1q_lane_v: {
Ops[1] = Builder.CreateBitCast(Ops[1], Ty);
Ty = llvm::PointerType::getUnqual(VTy->getElementType());
Ops[0] = Builder.CreateBitCast(Ops[0], Ty);
- auto Alignment = CharUnits::fromQuantity(
- BuiltinID == NEON::BI__builtin_neon_vld1_lane_v ? 8 : 16);
- Ops[0] =
- Builder.CreateAlignedLoad(VTy->getElementType(), Ops[0], Alignment);
+ Ops[0] = Builder.CreateAlignedLoad(VTy->getElementType(), Ops[0],
+ PtrOp0.getAlignment());
return Builder.CreateInsertElement(Ops[1], Ops[0], Ops[2], "vld1_lane");
}
case NEON::BI__builtin_neon_vld1_dup_v:
@@ -10362,10 +10378,8 @@ Value *CodeGenFunction::EmitAArch64BuiltinExpr(unsigned BuiltinID,
Value *V = UndefValue::get(Ty);
Ty = llvm::PointerType::getUnqual(VTy->getElementType());
Ops[0] = Builder.CreateBitCast(Ops[0], Ty);
- auto Alignment = CharUnits::fromQuantity(
- BuiltinID == NEON::BI__builtin_neon_vld1_dup_v ? 8 : 16);
- Ops[0] =
- Builder.CreateAlignedLoad(VTy->getElementType(), Ops[0], Alignment);
+ Ops[0] = Builder.CreateAlignedLoad(VTy->getElementType(), Ops[0],
+ PtrOp0.getAlignment());
llvm::Constant *CI = ConstantInt::get(Int32Ty, 0);
Ops[0] = Builder.CreateInsertElement(V, Ops[0], CI);
return EmitNeonSplat(Ops[0], CI);
@@ -10375,8 +10389,8 @@ Value *CodeGenFunction::EmitAArch64BuiltinExpr(unsigned BuiltinID,
Ops[1] = Builder.CreateBitCast(Ops[1], Ty);
Ops[1] = Builder.CreateExtractElement(Ops[1], Ops[2]);
Ty = llvm::PointerType::getUnqual(Ops[1]->getType());
- return Builder.CreateDefaultAlignedStore(Ops[1],
- Builder.CreateBitCast(Ops[0], Ty));
+ return Builder.CreateAlignedStore(Ops[1], Builder.CreateBitCast(Ops[0], Ty),
+ PtrOp0.getAlignment());
case NEON::BI__builtin_neon_vld2_v:
case NEON::BI__builtin_neon_vld2q_v: {
llvm::Type *PTy = llvm::PointerType::getUnqual(VTy);
diff --git a/clang/test/CodeGen/aarch64-neon-intrinsics.c b/clang/test/CodeGen/aarch64-neon-intrinsics.c
index 7744b4f4a159..fbf3c2c5b63e 100644
--- a/clang/test/CodeGen/aarch64-neon-intrinsics.c
+++ b/clang/test/CodeGen/aarch64-neon-intrinsics.c
@@ -8956,7 +8956,7 @@ float64_t test_vrsqrted_f64(float64_t a) {
// CHECK-LABEL: @test_vld1q_u8(
// CHECK: [[TMP0:%.*]] = bitcast i8* %a to <16 x i8>*
-// CHECK: [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* [[TMP0]]
+// CHECK: [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* [[TMP0]], align 1
// CHECK: ret <16 x i8> [[TMP1]]
uint8x16_t test_vld1q_u8(uint8_t const *a) {
return vld1q_u8(a);
@@ -8965,7 +8965,7 @@ uint8x16_t test_vld1q_u8(uint8_t const *a) {
// CHECK-LABEL: @test_vld1q_u16(
// CHECK: [[TMP0:%.*]] = bitcast i16* %a to i8*
// CHECK: [[TMP1:%.*]] = bitcast i8* [[TMP0]] to <8 x i16>*
-// CHECK: [[TMP2:%.*]] = load <8 x i16>, <8 x i16>* [[TMP1]]
+// CHECK: [[TMP2:%.*]] = load <8 x i16>, <8 x i16>* [[TMP1]], align 2
// CHECK: ret <8 x i16> [[TMP2]]
uint16x8_t test_vld1q_u16(uint16_t const *a) {
return vld1q_u16(a);
@@ -8974,7 +8974,7 @@ uint16x8_t test_vld1q_u16(uint16_t const *a) {
// CHECK-LABEL: @test_vld1q_u32(
// CHECK: [[TMP0:%.*]] = bitcast i32* %a to i8*
// CHECK: [[TMP1:%.*]] = bitcast i8* [[TMP0]] to <4 x i32>*
-// CHECK: [[TMP2:%.*]] = load <4 x i32>, <4 x i32>* [[TMP1]]
+// CHECK: [[TMP2:%.*]] = load <4 x i32>, <4 x i32>* [[TMP1]], align 4
// CHECK: ret <4 x i32> [[TMP2]]
uint32x4_t test_vld1q_u32(uint32_t const *a) {
return vld1q_u32(a);
@@ -8983,7 +8983,7 @@ uint32x4_t test_vld1q_u32(uint32_t const *a) {
// CHECK-LABEL: @test_vld1q_u64(
// CHECK: [[TMP0:%.*]] = bitcast i64* %a to i8*
// CHECK: [[TMP1:%.*]] = bitcast i8* [[TMP0]] to <2 x i64>*
-// CHECK: [[TMP2:%.*]] = load <2 x i64>, <2 x i64>* [[TMP1]]
+// CHECK: [[TMP2:%.*]] = load <2 x i64>, <2 x i64>* [[TMP1]], align 8
// CHECK: ret <2 x i64> [[TMP2]]
uint64x2_t test_vld1q_u64(uint64_t const *a) {
return vld1q_u64(a);
@@ -8991,7 +8991,7 @@ uint64x2_t test_vld1q_u64(uint64_t const *a) {
// CHECK-LABEL: @test_vld1q_s8(
// CHECK: [[TMP0:%.*]] = bitcast i8* %a to <16 x i8>*
-// CHECK: [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* [[TMP0]]
+// CHECK: [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* [[TMP0]], align 1
// CHECK: ret <16 x i8> [[TMP1]]
int8x16_t test_vld1q_s8(int8_t const *a) {
return vld1q_s8(a);
@@ -9000,7 +9000,7 @@ int8x16_t test_vld1q_s8(int8_t const *a) {
// CHECK-LABEL: @test_vld1q_s16(
// CHECK: [[TMP0:%.*]] = bitcast i16* %a to i8*
// CHECK: [[TMP1:%.*]] = bitcast i8* [[TMP0]] to <8 x i16>*
-// CHECK: [[TMP2:%.*]] = load <8 x i16>, <8 x i16>* [[TMP1]]
+// CHECK: [[TMP2:%.*]] = load <8 x i16>, <8 x i16>* [[TMP1]], align 2
// CHECK: ret <8 x i16> [[TMP2]]
int16x8_t test_vld1q_s16(int16_t const *a) {
return vld1q_s16(a);
@@ -9009,7 +9009,7 @@ int16x8_t test_vld1q_s16(int16_t const *a) {
// CHECK-LABEL: @test_vld1q_s32(
// CHECK: [[TMP0:%.*]] = bitcast i32* %a to i8*
// CHECK: [[TMP1:%.*]] = bitcast i8* [[TMP0]] to <4 x i32>*
-// CHECK: [[TMP2:%.*]] = load <4 x i32>, <4 x i32>* [[TMP1]]
+// CHECK: [[TMP2:%.*]] = load <4 x i32>, <4 x i32>* [[TMP1]], align 4
// CHECK: ret <4 x i32> [[TMP2]]
int32x4_t test_vld1q_s32(int32_t const *a) {
return vld1q_s32(a);
@@ -9018,7 +9018,7 @@ int32x4_t test_vld1q_s32(int32_t const *a) {
// CHECK-LABEL: @test_vld1q_s64(
// CHECK: [[TMP0:%.*]] = bitcast i64* %a to i8*
// CHECK: [[TMP1:%.*]] = bitcast i8* [[TMP0]] to <2 x i64>*
-// CHECK: [[TMP2:%.*]] = load <2 x i64>, <2 x i64>* [[TMP1]]
+// CHECK: [[TMP2:%.*]] = load <2 x i64>, <2 x i64>* [[TMP1]], align 8
// CHECK: ret <2 x i64> [[TMP2]]
int64x2_t test_vld1q_s64(int64_t const *a) {
return vld1q_s64(a);
@@ -9027,7 +9027,7 @@ int64x2_t test_vld1q_s64(int64_t const *a) {
// CHECK-LABEL: @test_vld1q_f16(
// CHECK: [[TMP0:%.*]] = bitcast half* %a to i8*
// CHECK: [[TMP1:%.*]] = bitcast i8* [[TMP0]] to <8 x half>*
-// CHECK: [[TMP2:%.*]] = load <8 x half>, <8 x half>* [[TMP1]]
+// CHECK: [[TMP2:%.*]] = load <8 x half>, <8 x half>* [[TMP1]], align 2
// CHECK: ret <8 x half> [[TMP2]]
float16x8_t test_vld1q_f16(float16_t const *a) {
return vld1q_f16(a);
@@ -9036,7 +9036,7 @@ float16x8_t test_vld1q_f16(float16_t const *a) {
// CHECK-LABEL: @test_vld1q_f32(
// CHECK: [[TMP0:%.*]] = bitcast float* %a to i8*
// CHECK: [[TMP1:%.*]] = bitcast i8* [[TMP0]] to <4 x float>*
-// CHECK: [[TMP2:%.*]] = load <4 x float>, <4 x float>* [[TMP1]]
+// CHECK: [[TMP2:%.*]] = load <4 x float>, <4 x float>* [[TMP1]], align 4
// CHECK: ret <4 x float> [[TMP2]]
float32x4_t test_vld1q_f32(float32_t const *a) {
return vld1q_f32(a);
@@ -9045,7 +9045,7 @@ float32x4_t test_vld1q_f32(float32_t const *a) {
// CHECK-LABEL: @test_vld1q_f64(
// CHECK: [[TMP0:%.*]] = bitcast double* %a to i8*
// CHECK: [[TMP1:%.*]] = bitcast i8* [[TMP0]] to <2 x double>*
-// CHECK: [[TMP2:%.*]] = load <2 x double>, <2 x double>* [[TMP1]]
+// CHECK: [[TMP2:%.*]] = load <2 x double>, <2 x double>* [[TMP1]], align 8
// CHECK: ret <2 x double> [[TMP2]]
float64x2_t test_vld1q_f64(float64_t const *a) {
return vld1q_f64(a);
@@ -9053,7 +9053,7 @@ float64x2_t test_vld1q_f64(float64_t const *a) {
// CHECK-LABEL: @test_vld1q_p8(
// CHECK: [[TMP0:%.*]] = bitcast i8* %a to <16 x i8>*
-// CHECK: [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* [[TMP0]]
+// CHECK: [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* [[TMP0]], align 1
// CHECK: ret <16 x i8> [[TMP1]]
poly8x16_t test_vld1q_p8(poly8_t const *a) {
return vld1q_p8(a);
@@ -9062,7 +9062,7 @@ poly8x16_t test_vld1q_p8(poly8_t const *a) {
// CHECK-LABEL: @test_vld1q_p16(
// CHECK: [[TMP0:%.*]] = bitcast i16* %a to i8*
// CHECK: [[TMP1:%.*]] = bitcast i8* [[TMP0]] to <8 x i16>*
-// CHECK: [[TMP2:%.*]] = load <8 x i16>, <8 x i16>* [[TMP1]]
+// CHECK: [[TMP2:%.*]] = load <8 x i16>, <8 x i16>* [[TMP1]], align 2
// CHECK: ret <8 x i16> [[TMP2]]
poly16x8_t test_vld1q_p16(poly16_t const *a) {
return vld1q_p16(a);
@@ -9070,7 +9070,7 @@ poly16x8_t test_vld1q_p16(poly16_t const *a) {
// CHECK-LABEL: @test_vld1_u8(
// CHECK: [[TMP0:%.*]] = bitcast i8* %a to <8 x i8>*
-// CHECK: [[TMP1:%.*]] = load <8 x i8>, <8 x i8>* [[TMP0]]
+// CHECK: [[TMP1:%.*]] = load <8 x i8>, <8 x i8>* [[TMP0]], align 1
// CHECK: ret <8 x i8> [[TMP1]]
uint8x8_t test_vld1_u8(uint8_t const *a) {
return vld1_u8(a);
@@ -9079,7 +9079,7 @@ uint8x8_t test_vld1_u8(uint8_t const *a) {
// CHECK-LABEL: @test_vld1_u16(
// CHECK: [[TMP0:%.*]] = bitcast i16* %a to i8*
// CHECK: [[TMP1:%.*]] = bitcast i8* [[TMP0]] to <4 x i16>*
-// CHECK: [[TMP2:%.*]] = load <4 x i16>, <4 x i16>* [[TMP1]]
+// CHECK: [[TMP2:%.*]] = load <4 x i16>, <4 x i16>* [[TMP1]], align 2
// CHECK: ret <4 x i16> [[TMP2]]
uint16x4_t test_vld1_u16(uint16_t const *a) {
return vld1_u16(a);
@@ -9088,7 +9088,7 @@ uint16x4_t test_vld1_u16(uint16_t const *a) {
// CHECK-LABEL: @test_vld1_u32(
// CHECK: [[TMP0:%.*]] = bitcast i32* %a to i8*
// CHECK: [[TMP1:%.*]] = bitcast i8* [[TMP0]] to <2 x i32>*
-// CHECK: [[TMP2:%.*]] = load <2 x i32>, <2 x i32>* [[TMP1]]
+// CHECK: [[TMP2:%.*]] = load <2 x i32>, <2 x i32>* [[TMP1]], align 4
// CHECK: ret <2 x i32> [[TMP2]]
uint32x2_t test_vld1_u32(uint32_t const *a) {
return vld1_u32(a);
@@ -9097,7 +9097,7 @@ uint32x2_t test_vld1_u32(uint32_t const *a) {
// CHECK-LABEL: @test_vld1_u64(
// CHECK: [[TMP0:%.*]] = bitcast i64* %a to i8*
// CHECK: [[TMP1:%.*]] = bitcast i8* [[TMP0]] to <1 x i64>*
-// CHECK: [[TMP2:%.*]] = load <1 x i64>, <1 x i64>* [[TMP1]]
+// CHECK: [[TMP2:%.*]] = load <1 x i64>, <1 x i64>* [[TMP1]], align 8
// CHECK: ret <1 x i64> [[TMP2]]
uint64x1_t test_vld1_u64(uint64_t const *a) {
return vld1_u64(a);
@@ -9105,7 +9105,7 @@ uint64x1_t test_vld1_u64(uint64_t const *a) {
// CHECK-LABEL: @test_vld1_s8(
// CHECK: [[TMP0:%.*]] = bitcast i8* %a to <8 x i8>*
-// CHECK: [[TMP1:%.*]] = load <8 x i8>, <8 x i8>* [[TMP0]]
+// CHECK: [[TMP1:%.*]] = load <8 x i8>, <8 x i8>* [[TMP0]], align 1
// CHECK: ret <8 x i8> [[TMP1]]
int8x8_t test_vld1_s8(int8_t const *a) {
return vld1_s8(a);
@@ -9114,7 +9114,7 @@ int8x8_t test_vld1_s8(int8_t const *a) {
// CHECK-LABEL: @test_vld1_s16(
// CHECK: [[TMP0:%.*]] = bitcast i16* %a to i8*
// CHECK: [[TMP1:%.*]] = bitcast i8* [[TMP0]] to <4 x i16>*
-// CHECK: [[TMP2:%.*]] = load <4 x i16>, <4 x i16>* [[TMP1]]
+// CHECK: [[TMP2:%.*]] = load <4 x i16>, <4 x i16>* [[TMP1]], align 2
// CHECK: ret <4 x i16> [[TMP2]]
int16x4_t test_vld1_s16(int16_t const *a) {
return vld1_s16(a);
@@ -9123,7 +9123,7 @@ int16x4_t test_vld1_s16(int16_t const *a) {
// CHECK-LABEL: @test_vld1_s32(
// CHECK: [[TMP0:%.*]] = bitcast i32* %a to i8*
// CHECK: [[TMP1:%.*]] = bitcast i8* [[TMP0]] to <2 x i32>*
-// CHECK: [[TMP2:%.*]] = load <2 x i32>, <2 x i32>* [[TMP1]]
+// CHECK: [[TMP2:%.*]] = load <2 x i32>, <2 x i32>* [[TMP1]], align 4
// CHECK: ret <2 x i32> [[TMP2]]
int32x2_t test_vld1_s32(int32_t const *a) {
return vld1_s32(a);
@@ -9132,7 +9132,7 @@ int32x2_t test_vld1_s32(int32_t const *a) {
// CHECK-LABEL: @test_vld1_s64(
// CHECK: [[TMP0:%.*]] = bitcast i64* %a to i8*
// CHECK: [[TMP1:%.*]] = bitcast i8* [[TMP0]] to <1 x i64>*
-// CHECK: [[TMP2:%.*]] = load <1 x i64>, <1 x i64>* [[TMP1]]
+// CHECK: [[TMP2:%.*]] = load <1 x i64>, <1 x i64>* [[TMP1]], align 8
// CHECK: ret <1 x i64> [[TMP2]]
int64x1_t test_vld1_s64(int64_t const *a) {
return vld1_s64(a);
@@ -9141,7 +9141,7 @@ int64x1_t test_vld1_s64(int64_t const *a) {
// CHECK-LABEL: @test_vld1_f16(
// CHECK: [[TMP0:%.*]] = bitcast half* %a to i8*
// CHECK: [[TMP1:%.*]] = bitcast i8* [[TMP0]] to <4 x half>*
-// CHECK: [[TMP2:%.*]] = load <4 x half>, <4 x half>* [[TMP1]]
+// CHECK: [[TMP2:%.*]] = load <4 x half>, <4 x half>* [[TMP1]], align 2
// CHECK: ret <4 x half> [[TMP2]]
float16x4_t test_vld1_f16(float16_t const *a) {
return vld1_f16(a);
@@ -9150,7 +9150,7 @@ float16x4_t test_vld1_f16(float16_t const *a) {
// CHECK-LABEL: @test_vld1_f32(
// CHECK: [[TMP0:%.*]] = bitcast float* %a to i8*
// CHECK: [[TMP1:%.*]] = bitcast i8* [[TMP0]] to <2 x float>*
-// CHECK: [[TMP2:%.*]] = load <2 x float>, <2 x float>* [[TMP1]]
+// CHECK: [[TMP2:%.*]] = load <2 x float>, <2 x float>* [[TMP1]], align 4
// CHECK: ret <2 x float> [[TMP2]]
float32x2_t test_vld1_f32(float32_t const *a) {
return vld1_f32(a);
@@ -9159,7 +9159,7 @@ float32x2_t test_vld1_f32(float32_t const *a) {
// CHECK-LABEL: @test_vld1_f64(
// CHECK: [[TMP0:%.*]] = bitcast double* %a to i8*
// CHECK: [[TMP1:%.*]] = bitcast i8* [[TMP0]] to <1 x double>*
-// CHECK: [[TMP2:%.*]] = load <1 x double>, <1 x double>* [[TMP1]]
+// CHECK: [[TMP2:%.*]] = load <1 x double>, <1 x double>* [[TMP1]], align 8
// CHECK: ret <1 x double> [[TMP2]]
float64x1_t test_vld1_f64(float64_t const *a) {
return vld1_f64(a);
@@ -9167,7 +9167,7 @@ float64x1_t test_vld1_f64(float64_t const *a) {
// CHECK-LABEL: @test_vld1_p8(
// CHECK: [[TMP0:%.*]] = bitcast i8* %a to <8 x i8>*
-// CHECK: [[TMP1:%.*]] = load <8 x i8>, <8 x i8>* [[TMP0]]
+// CHECK: [[TMP1:%.*]] = load <8 x i8>, <8 x i8>* [[TMP0]], align 1
// CHECK: ret <8 x i8> [[TMP1]]
poly8x8_t test_vld1_p8(poly8_t const *a) {
return vld1_p8(a);
@@ -9176,12 +9176,116 @@ poly8x8_t test_vld1_p8(poly8_t const *a) {
// CHECK-LABEL: @test_vld1_p16(
// CHECK: [[TMP0:%.*]] = bitcast i16* %a to i8*
// CHECK: [[TMP1:%.*]] = bitcast i8* [[TMP0]] to <4 x i16>*
-// CHECK: [[TMP2:%.*]] = load <4 x i16>, <4 x i16>* [[TMP1]]
+// CHECK: [[TMP2:%.*]] = load <4 x i16>, <4 x i16>* [[TMP1]], align 2
// CHECK: ret <4 x i16> [[TMP2]]
poly16x4_t test_vld1_p16(poly16_t const *a) {
return vld1_p16(a);
}
+// CHECK-LABEL: @test_vld1_u8_void(
+// CHECK: [[TMP0:%.*]] = bitcast i8* %a to <8 x i8>*
+// CHECK: [[TMP1:%.*]] = load <8 x i8>, <8 x i8>* [[TMP0]], align 1
+// CHECK: ret <8 x i8> [[TMP1]]
+uint8x8_t test_vld1_u8_void(void *a) {
+ return vld1_u8(a);
+}
+
+// CHECK-LABEL: @test_vld1_u16_void(
+// CHECK: [[TMP0:%.*]] = bitcast i8* %a to <4 x i16>*
+// CHECK: [[TMP1:%.*]] = load <4 x i16>, <4 x i16>* [[TMP0]], align 1
+// CHECK: ret <4 x i16> [[TMP1]]
+uint16x4_t test_vld1_u16_void(void *a) {
+ return vld1_u16(a);
+}
+
+// CHECK-LABEL: @test_vld1_u32_void(
+// CHECK: [[TMP0:%.*]] = bitcast i8* %a to <2 x i32>*
+// CHECK: [[TMP1:%.*]] = load <2 x i32>, <2 x i32>* [[TMP0]], align 1
+// CHECK: ret <2 x i32> [[TMP1]]
+uint32x2_t test_vld1_u32_void(void *a) {
+ return vld1_u32(a);
+}
+
+// CHECK-LABEL: @test_vld1_u64_void(
+// CHECK: [[TMP0:%.*]] = bitcast i8* %a to <1 x i64>*
+// CHECK: [[TMP1:%.*]] = load <1 x i64>, <1 x i64>* [[TMP0]], align 1
+// CHECK: ret <1 x i64> [[TMP1]]
+uint64x1_t test_vld1_u64_void(void *a) {
+ return vld1_u64(a);
+}
+
+// CHECK-LABEL: @test_vld1_s8_void(
+// CHECK: [[TMP0:%.*]] = bitcast i8* %a to <8 x i8>*
+// CHECK: [[TMP1:%.*]] = load <8 x i8>, <8 x i8>* [[TMP0]], align 1
+// CHECK: ret <8 x i8> [[TMP1]]
+int8x8_t test_vld1_s8_void(void *a) {
+ return vld1_s8(a);
+}
+
+// CHECK-LABEL: @test_vld1_s16_void(
+// CHECK: [[TMP0:%.*]] = bitcast i8* %a to <4 x i16>*
+// CHECK: [[TMP1:%.*]] = load <4 x i16>, <4 x i16>* [[TMP0]], align 1
+// CHECK: ret <4 x i16> [[TMP1]]
+int16x4_t test_vld1_s16_void(void *a) {
+ return vld1_s16(a);
+}
+
+// CHECK-LABEL: @test_vld1_s32_void(
+// CHECK: [[TMP0:%.*]] = bitcast i8* %a to <2 x i32>*
+// CHECK: [[TMP1:%.*]] = load <2 x i32>, <2 x i32>* [[TMP0]], align 1
+// CHECK: ret <2 x i32> [[TMP1]]
+int32x2_t test_vld1_s32_void(void *a) {
+ return vld1_s32(a);
+}
+
+// CHECK-LABEL: @test_vld1_s64_void(
+// CHECK: [[TMP0:%.*]] = bitcast i8* %a to <1 x i64>*
+// CHECK: [[TMP1:%.*]] = load <1 x i64>, <1 x i64>* [[TMP0]], align 1
+// CHECK: ret <1 x i64> [[TMP1]]
+int64x1_t test_vld1_s64_void(void *a) {
+ return vld1_s64(a);
+}
+
+// CHECK-LABEL: @test_vld1_f16_void(
+// CHECK: [[TMP0:%.*]] = bitcast i8* %a to <4 x half>*
+// CHECK: [[TMP1:%.*]] = load <4 x half>, <4 x half>* [[TMP0]], align 1
+// CHECK: ret <4 x half> [[TMP1]]
+float16x4_t test_vld1_f16_void(void *a) {
+ return vld1_f16(a);
+}
+
+// CHECK-LABEL: @test_vld1_f32_void(
+// CHECK: [[TMP0:%.*]] = bitcast i8* %a to <2 x float>*
+// CHECK: [[TMP1:%.*]] = load <2 x float>, <2 x float>* [[TMP0]], align 1
+// CHECK: ret <2 x float> [[TMP1]]
+float32x2_t test_vld1_f32_void(void *a) {
+ return vld1_f32(a);
+}
+
+// CHECK-LABEL: @test_vld1_f64_void(
+// CHECK: [[TMP0:%.*]] = bitcast i8* %a to <1 x double>*
+// CHECK: [[TMP1:%.*]] = load <1 x double>, <1 x double>* [[TMP0]], align 1
+// CHECK: ret <1 x double> [[TMP1]]
+float64x1_t test_vld1_f64_void(void *a) {
+ return vld1_f64(a);
+}
+
+// CHECK-LABEL: @test_vld1_p8_void(
+// CHECK: [[TMP0:%.*]] = bitcast i8* %a to <8 x i8>*
+// CHECK: [[TMP1:%.*]] = load <8 x i8>, <8 x i8>* [[TMP0]], align 1
+// CHECK: ret <8 x i8> [[TMP1]]
+poly8x8_t test_vld1_p8_void(void *a) {
+ return vld1_p8(a);
+}
+
+// CHECK-LABEL: @test_vld1_p16_void(
+// CHECK: [[TMP0:%.*]] = bitcast i8* %a to <4 x i16>*
+// CHECK: [[TMP1:%.*]] = load <4 x i16>, <4 x i16>* [[TMP0]], align 1
+// CHECK: ret <4 x i16> [[TMP1]]
+poly16x4_t test_vld1_p16_void(void *a) {
+ return vld1_p16(a);
+}
+
// CHECK-LABEL: @test_vld2q_u8(
// CHECK: [[RETVAL:%.*]] = alloca %struct.uint8x16x2_t, align 16
// CHECK: [[__RET:%.*]] = alloca %struct.uint8x16x2_t, align 16
More information about the cfe-commits
mailing list