[clang] [AArch64] Change the coercion type of structs with pointer members. (PR #135064)
David Green via cfe-commits
cfe-commits at lists.llvm.org
Wed Apr 9 11:21:37 PDT 2025
https://github.com/davemgreen created https://github.com/llvm/llvm-project/pull/135064
The aim here is to avoid a ptrtoint->inttoptr round-trip through the function
argument whilst keeping the calling convention the same. Given a struct which
is <= 128bits in size, which can only contain either 1 or 2 pointers, we
convert to a ptr or [2 x ptr] as opposed to the old coercion that uses i64 or
[2 x i64]. This helps alias analysis produce more accurate results.
>From 6825a7d7cbc68f595a4243ce86f7c35b9b2b3c6e Mon Sep 17 00:00:00 2001
From: David Green <david.green at arm.com>
Date: Wed, 9 Apr 2025 11:18:25 +0100
Subject: [PATCH 1/2] [AArch64] Add a test case for the coerced arguments. NFC
---
.../AArch64/struct-coerce-using-ptr.cpp | 94 +++++++++++++++++++
1 file changed, 94 insertions(+)
create mode 100644 clang/test/CodeGen/AArch64/struct-coerce-using-ptr.cpp
diff --git a/clang/test/CodeGen/AArch64/struct-coerce-using-ptr.cpp b/clang/test/CodeGen/AArch64/struct-coerce-using-ptr.cpp
new file mode 100644
index 0000000000000..295a5158f7e97
--- /dev/null
+++ b/clang/test/CodeGen/AArch64/struct-coerce-using-ptr.cpp
@@ -0,0 +1,94 @@
+// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --version 5
+// RUN: %clang_cc1 -triple aarch64-none-elf -fcxx-exceptions -fexceptions -emit-llvm -o - %s | FileCheck %s
+
+struct Sp {
+ int *x;
+};
+// CHECK-LABEL: define dso_local void @_Z2Tp2Sp(
+// CHECK-SAME: i64 [[S_COERCE:%.*]]) #[[ATTR0:[0-9]+]] {
+// CHECK-NEXT: [[ENTRY:.*:]]
+// CHECK-NEXT: [[S:%.*]] = alloca [[STRUCT_SP:%.*]], align 8
+// CHECK-NEXT: [[COERCE_DIVE:%.*]] = getelementptr inbounds nuw [[STRUCT_SP]], ptr [[S]], i32 0, i32 0
+// CHECK-NEXT: [[COERCE_VAL_IP:%.*]] = inttoptr i64 [[S_COERCE]] to ptr
+// CHECK-NEXT: store ptr [[COERCE_VAL_IP]], ptr [[COERCE_DIVE]], align 8
+// CHECK-NEXT: [[X:%.*]] = getelementptr inbounds nuw [[STRUCT_SP]], ptr [[S]], i32 0, i32 0
+// CHECK-NEXT: [[TMP0:%.*]] = load ptr, ptr [[X]], align 8
+// CHECK-NEXT: store i32 1, ptr [[TMP0]], align 4
+// CHECK-NEXT: ret void
+//
+void Tp(Sp s) { *s.x = 1; }
+
+struct Spp {
+ int *x, *y;
+};
+// CHECK-LABEL: define dso_local void @_Z3Tpp3Spp(
+// CHECK-SAME: [2 x i64] [[S_COERCE:%.*]]) #[[ATTR0]] {
+// CHECK-NEXT: [[ENTRY:.*:]]
+// CHECK-NEXT: [[S:%.*]] = alloca [[STRUCT_SPP:%.*]], align 8
+// CHECK-NEXT: store [2 x i64] [[S_COERCE]], ptr [[S]], align 8
+// CHECK-NEXT: [[X:%.*]] = getelementptr inbounds nuw [[STRUCT_SPP]], ptr [[S]], i32 0, i32 0
+// CHECK-NEXT: [[TMP0:%.*]] = load ptr, ptr [[X]], align 8
+// CHECK-NEXT: store i32 1, ptr [[TMP0]], align 4
+// CHECK-NEXT: ret void
+//
+void Tpp(Spp s) { *s.x = 1; }
+
+struct Sppp {
+ int *x, *y, *z;
+};
+// CHECK-LABEL: define dso_local void @_Z4Tppp4Sppp(
+// CHECK-SAME: ptr noundef [[S:%.*]]) #[[ATTR0]] {
+// CHECK-NEXT: [[ENTRY:.*:]]
+// CHECK-NEXT: [[S_INDIRECT_ADDR:%.*]] = alloca ptr, align 8
+// CHECK-NEXT: store ptr [[S]], ptr [[S_INDIRECT_ADDR]], align 8
+// CHECK-NEXT: [[X:%.*]] = getelementptr inbounds nuw [[STRUCT_SPPP:%.*]], ptr [[S]], i32 0, i32 0
+// CHECK-NEXT: [[TMP0:%.*]] = load ptr, ptr [[X]], align 8
+// CHECK-NEXT: store i32 1, ptr [[TMP0]], align 4
+// CHECK-NEXT: ret void
+//
+void Tppp(Sppp s) { *s.x = 1; }
+
+struct Spi {
+ int *x, y;
+};
+// CHECK-LABEL: define dso_local void @_Z3Tpi3Spi(
+// CHECK-SAME: [2 x i64] [[S_COERCE:%.*]]) #[[ATTR0]] {
+// CHECK-NEXT: [[ENTRY:.*:]]
+// CHECK-NEXT: [[S:%.*]] = alloca [[STRUCT_SPI:%.*]], align 8
+// CHECK-NEXT: store [2 x i64] [[S_COERCE]], ptr [[S]], align 8
+// CHECK-NEXT: [[X:%.*]] = getelementptr inbounds nuw [[STRUCT_SPI]], ptr [[S]], i32 0, i32 0
+// CHECK-NEXT: [[TMP0:%.*]] = load ptr, ptr [[X]], align 8
+// CHECK-NEXT: store i32 1, ptr [[TMP0]], align 4
+// CHECK-NEXT: ret void
+//
+void Tpi(Spi s) { *s.x = 1; }
+
+struct Srp {
+ int &x, *y;
+};
+// CHECK-LABEL: define dso_local void @_Z3Trp3Srp(
+// CHECK-SAME: [2 x i64] [[S_COERCE:%.*]]) #[[ATTR0]] {
+// CHECK-NEXT: [[ENTRY:.*:]]
+// CHECK-NEXT: [[S:%.*]] = alloca [[STRUCT_SRP:%.*]], align 8
+// CHECK-NEXT: store [2 x i64] [[S_COERCE]], ptr [[S]], align 8
+// CHECK-NEXT: [[X:%.*]] = getelementptr inbounds nuw [[STRUCT_SRP]], ptr [[S]], i32 0, i32 0
+// CHECK-NEXT: [[TMP0:%.*]] = load ptr, ptr [[X]], align 8
+// CHECK-NEXT: store i32 1, ptr [[TMP0]], align 4
+// CHECK-NEXT: ret void
+//
+void Trp(Srp s) { s.x = 1; }
+
+struct __attribute__((__packed__)) Spp_packed {
+ int *x, *y;
+};
+// CHECK-LABEL: define dso_local void @_Z10Tpp_packed10Spp_packed(
+// CHECK-SAME: [2 x i64] [[S_COERCE:%.*]]) #[[ATTR0]] {
+// CHECK-NEXT: [[ENTRY:.*:]]
+// CHECK-NEXT: [[S:%.*]] = alloca [[STRUCT_SPP_PACKED:%.*]], align 1
+// CHECK-NEXT: store [2 x i64] [[S_COERCE]], ptr [[S]], align 1
+// CHECK-NEXT: [[X:%.*]] = getelementptr inbounds nuw [[STRUCT_SPP_PACKED]], ptr [[S]], i32 0, i32 0
+// CHECK-NEXT: [[TMP0:%.*]] = load ptr, ptr [[X]], align 1
+// CHECK-NEXT: store i32 1, ptr [[TMP0]], align 4
+// CHECK-NEXT: ret void
+//
+void Tpp_packed(Spp_packed s) { *s.x = 1; }
>From c116767ca758e8e5fa5ecbe9d537d937cc7193fa Mon Sep 17 00:00:00 2001
From: David Green <david.green at arm.com>
Date: Wed, 9 Apr 2025 19:07:04 +0100
Subject: [PATCH 2/2] [AArch64] Change the coercion type of structs with
pointer members.
The aim here is to avoid a ptrtoint->inttoptr round-trip throught the function
argument whilst keeping the calling convention the same. Given a struct which
is <= 128bits in size, which can only contain either 1 or 2 pointers, we
convert to a ptr or [2 x ptr] as opposed to the old coercion that uses i64 or
[2 x i64].
---
clang/lib/CodeGen/Targets/AArch64.cpp | 18 ++++++++++++++++++
.../AArch64/struct-coerce-using-ptr.cpp | 17 ++++++++---------
clang/test/CodeGenCXX/trivial_abi.cpp | 13 +++++--------
3 files changed, 31 insertions(+), 17 deletions(-)
diff --git a/clang/lib/CodeGen/Targets/AArch64.cpp b/clang/lib/CodeGen/Targets/AArch64.cpp
index 073ca3cc82690..9dc5f824254eb 100644
--- a/clang/lib/CodeGen/Targets/AArch64.cpp
+++ b/clang/lib/CodeGen/Targets/AArch64.cpp
@@ -485,6 +485,24 @@ ABIArgInfo AArch64ABIInfo::classifyArgumentType(QualType Ty, bool IsVariadicFn,
}
Size = llvm::alignTo(Size, Alignment);
+ // If the Aggregate is made up of pointers, use an array of pointers for the
+ // coerced type. This prevents having to convert ptr2int->int2ptr through
+ // the call, allowing alias analysis to produce better code.
+ if (const RecordType *RT = Ty->getAs<RecordType>()) {
+ if (const RecordDecl *RD = RT->getDecl()) {
+ if (all_of(RD->fields(), [](FieldDecl *FD) {
+ return FD->getType()->isPointerOrReferenceType();
+ })) {
+ assert((Size == 64 || Size == 128) &&
+ "Expected a 64 or 128bit struct containing pointers");
+ llvm::Type *PtrTy = llvm::PointerType::getUnqual(getVMContext());
+ if (Size == 128)
+ PtrTy = llvm::ArrayType::get(PtrTy, 2);
+ return ABIArgInfo::getDirect(PtrTy);
+ }
+ }
+ }
+
// We use a pair of i64 for 16-byte aggregate with 8-byte alignment.
// For aggregates with 16-byte alignment, we use i128.
llvm::Type *BaseTy = llvm::Type::getIntNTy(getVMContext(), Alignment);
diff --git a/clang/test/CodeGen/AArch64/struct-coerce-using-ptr.cpp b/clang/test/CodeGen/AArch64/struct-coerce-using-ptr.cpp
index 295a5158f7e97..c2d68ae7ef6cd 100644
--- a/clang/test/CodeGen/AArch64/struct-coerce-using-ptr.cpp
+++ b/clang/test/CodeGen/AArch64/struct-coerce-using-ptr.cpp
@@ -5,12 +5,11 @@ struct Sp {
int *x;
};
// CHECK-LABEL: define dso_local void @_Z2Tp2Sp(
-// CHECK-SAME: i64 [[S_COERCE:%.*]]) #[[ATTR0:[0-9]+]] {
+// CHECK-SAME: ptr [[S_COERCE:%.*]]) #[[ATTR0:[0-9]+]] {
// CHECK-NEXT: [[ENTRY:.*:]]
// CHECK-NEXT: [[S:%.*]] = alloca [[STRUCT_SP:%.*]], align 8
// CHECK-NEXT: [[COERCE_DIVE:%.*]] = getelementptr inbounds nuw [[STRUCT_SP]], ptr [[S]], i32 0, i32 0
-// CHECK-NEXT: [[COERCE_VAL_IP:%.*]] = inttoptr i64 [[S_COERCE]] to ptr
-// CHECK-NEXT: store ptr [[COERCE_VAL_IP]], ptr [[COERCE_DIVE]], align 8
+// CHECK-NEXT: store ptr [[S_COERCE]], ptr [[COERCE_DIVE]], align 8
// CHECK-NEXT: [[X:%.*]] = getelementptr inbounds nuw [[STRUCT_SP]], ptr [[S]], i32 0, i32 0
// CHECK-NEXT: [[TMP0:%.*]] = load ptr, ptr [[X]], align 8
// CHECK-NEXT: store i32 1, ptr [[TMP0]], align 4
@@ -22,10 +21,10 @@ struct Spp {
int *x, *y;
};
// CHECK-LABEL: define dso_local void @_Z3Tpp3Spp(
-// CHECK-SAME: [2 x i64] [[S_COERCE:%.*]]) #[[ATTR0]] {
+// CHECK-SAME: [2 x ptr] [[S_COERCE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT: [[ENTRY:.*:]]
// CHECK-NEXT: [[S:%.*]] = alloca [[STRUCT_SPP:%.*]], align 8
-// CHECK-NEXT: store [2 x i64] [[S_COERCE]], ptr [[S]], align 8
+// CHECK-NEXT: store [2 x ptr] [[S_COERCE]], ptr [[S]], align 8
// CHECK-NEXT: [[X:%.*]] = getelementptr inbounds nuw [[STRUCT_SPP]], ptr [[S]], i32 0, i32 0
// CHECK-NEXT: [[TMP0:%.*]] = load ptr, ptr [[X]], align 8
// CHECK-NEXT: store i32 1, ptr [[TMP0]], align 4
@@ -67,10 +66,10 @@ struct Srp {
int &x, *y;
};
// CHECK-LABEL: define dso_local void @_Z3Trp3Srp(
-// CHECK-SAME: [2 x i64] [[S_COERCE:%.*]]) #[[ATTR0]] {
+// CHECK-SAME: [2 x ptr] [[S_COERCE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT: [[ENTRY:.*:]]
// CHECK-NEXT: [[S:%.*]] = alloca [[STRUCT_SRP:%.*]], align 8
-// CHECK-NEXT: store [2 x i64] [[S_COERCE]], ptr [[S]], align 8
+// CHECK-NEXT: store [2 x ptr] [[S_COERCE]], ptr [[S]], align 8
// CHECK-NEXT: [[X:%.*]] = getelementptr inbounds nuw [[STRUCT_SRP]], ptr [[S]], i32 0, i32 0
// CHECK-NEXT: [[TMP0:%.*]] = load ptr, ptr [[X]], align 8
// CHECK-NEXT: store i32 1, ptr [[TMP0]], align 4
@@ -82,10 +81,10 @@ struct __attribute__((__packed__)) Spp_packed {
int *x, *y;
};
// CHECK-LABEL: define dso_local void @_Z10Tpp_packed10Spp_packed(
-// CHECK-SAME: [2 x i64] [[S_COERCE:%.*]]) #[[ATTR0]] {
+// CHECK-SAME: [2 x ptr] [[S_COERCE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT: [[ENTRY:.*:]]
// CHECK-NEXT: [[S:%.*]] = alloca [[STRUCT_SPP_PACKED:%.*]], align 1
-// CHECK-NEXT: store [2 x i64] [[S_COERCE]], ptr [[S]], align 1
+// CHECK-NEXT: store [2 x ptr] [[S_COERCE]], ptr [[S]], align 1
// CHECK-NEXT: [[X:%.*]] = getelementptr inbounds nuw [[STRUCT_SPP_PACKED]], ptr [[S]], i32 0, i32 0
// CHECK-NEXT: [[TMP0:%.*]] = load ptr, ptr [[X]], align 1
// CHECK-NEXT: store i32 1, ptr [[TMP0]], align 4
diff --git a/clang/test/CodeGenCXX/trivial_abi.cpp b/clang/test/CodeGenCXX/trivial_abi.cpp
index 90054dbf37ae3..b8cc0d1cc6528 100644
--- a/clang/test/CodeGenCXX/trivial_abi.cpp
+++ b/clang/test/CodeGenCXX/trivial_abi.cpp
@@ -68,11 +68,10 @@ struct D0 : B0, B1 {
Small D0::m0() { return {}; }
-// CHECK: define{{.*}} void @_Z14testParamSmall5Small(i64 %[[A_COERCE:.*]])
+// CHECK: define{{.*}} void @_Z14testParamSmall5Small(ptr %[[A_COERCE:.*]])
// CHECK: %[[A:.*]] = alloca %[[STRUCT_SMALL]], align 8
// CHECK: %[[COERCE_DIVE:.*]] = getelementptr inbounds nuw %[[STRUCT_SMALL]], ptr %[[A]], i32 0, i32 0
-// CHECK: %[[COERCE_VAL_IP:.*]] = inttoptr i64 %[[A_COERCE]] to ptr
-// CHECK: store ptr %[[COERCE_VAL_IP]], ptr %[[COERCE_DIVE]], align 8
+// CHECK: store ptr %[[A_COERCE]], ptr %[[COERCE_DIVE]], align 8
// CHECK: %[[CALL:.*]] = call noundef ptr @_ZN5SmallD1Ev(ptr {{[^,]*}} %[[A]])
// CHECK: ret void
// CHECK: }
@@ -101,8 +100,7 @@ Small testReturnSmall() {
// CHECK: %[[CALL1:.*]] = call noundef ptr @_ZN5SmallC1ERKS_(ptr {{[^,]*}} %[[AGG_TMP]], ptr noundef nonnull align 8 dereferenceable(8) %[[T]])
// CHECK: %[[COERCE_DIVE:.*]] = getelementptr inbounds nuw %[[STRUCT_SMALL]], ptr %[[AGG_TMP]], i32 0, i32 0
// CHECK: %[[V0:.*]] = load ptr, ptr %[[COERCE_DIVE]], align 8
-// CHECK: %[[COERCE_VAL_PI:.*]] = ptrtoint ptr %[[V0]] to i64
-// CHECK: call void @_Z14testParamSmall5Small(i64 %[[COERCE_VAL_PI]])
+// CHECK: call void @_Z14testParamSmall5Small(ptr %[[V0]])
// CHECK: %[[CALL2:.*]] = call noundef ptr @_ZN5SmallD1Ev(ptr {{[^,]*}} %[[T]])
// CHECK: ret void
// CHECK: }
@@ -120,8 +118,7 @@ void testCallSmall0() {
// CHECK: store ptr %[[COERCE_VAL_IP]], ptr %[[COERCE_DIVE]], align 8
// CHECK: %[[COERCE_DIVE1:.*]] = getelementptr inbounds nuw %[[STRUCT_SMALL]], ptr %[[AGG_TMP]], i32 0, i32 0
// CHECK: %[[V0:.*]] = load ptr, ptr %[[COERCE_DIVE1]], align 8
-// CHECK: %[[COERCE_VAL_PI:.*]] = ptrtoint ptr %[[V0]] to i64
-// CHECK: call void @_Z14testParamSmall5Small(i64 %[[COERCE_VAL_PI]])
+// CHECK: call void @_Z14testParamSmall5Small(ptr %[[V0]])
// CHECK: ret void
// CHECK: }
@@ -226,7 +223,7 @@ NonTrivial testReturnHasNonTrivial() {
// CHECK: call noundef ptr @_ZN5SmallC1Ev(ptr {{[^,]*}} %[[AGG_TMP]])
// CHECK: invoke noundef ptr @_ZN5SmallC1Ev(ptr {{[^,]*}} %[[AGG_TMP1]])
-// CHECK: call void @_Z20calleeExceptionSmall5SmallS_(i64 %{{.*}}, i64 %{{.*}})
+// CHECK: call void @_Z20calleeExceptionSmall5SmallS_(ptr %{{.*}}, ptr %{{.*}})
// CHECK-NEXT: ret void
// CHECK: landingpad { ptr, i32 }
More information about the cfe-commits
mailing list