Skip to content

[ConstantFolding] Canonicalize constexpr GEPs to i8 #89872

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
May 20, 2024
Merged

[ConstantFolding] Canonicalize constexpr GEPs to i8 #89872

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
9ca8f47
[ConstantFolding] Canonicalize constexpr GEPs to i8
nikic Apr 24, 2024
10ed97d
fix profile tests
nikic Apr 26, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions clang/test/CodeGen/RISCV/riscv-inline-asm.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -49,9 +49,9 @@ extern int var, arr[2][2];
struct Pair { int a, b; } pair;

// CHECK-LABEL: test_s(
// CHECK: call void asm sideeffect "// $0 $1 $2", "s,s,s"(ptr nonnull @var, ptr nonnull getelementptr inbounds ([2 x [2 x i32]], ptr @arr, {{.*}}), ptr nonnull @test_s)
// CHECK: call void asm sideeffect "// $0", "s"(ptr nonnull getelementptr inbounds (%struct.Pair, ptr @pair, {{.*}}))
// CHECK: call void asm sideeffect "// $0 $1 $2", "S,S,S"(ptr nonnull @var, ptr nonnull getelementptr inbounds ([2 x [2 x i32]], ptr @arr, {{.*}}), ptr nonnull @test_s)
// CHECK: call void asm sideeffect "// $0 $1 $2", "s,s,s"(ptr nonnull @var, ptr nonnull getelementptr inbounds (i8, ptr @arr, {{.*}}), ptr nonnull @test_s)
// CHECK: call void asm sideeffect "// $0", "s"(ptr nonnull getelementptr inbounds (i8, ptr @pair, {{.*}}))
// CHECK: call void asm sideeffect "// $0 $1 $2", "S,S,S"(ptr nonnull @var, ptr nonnull getelementptr inbounds (i8, ptr @arr, {{.*}}), ptr nonnull @test_s)
void test_s(void) {
asm("// %0 %1 %2" :: "s"(&var), "s"(&arr[1][1]), "s"(test_s));
asm("// %0" :: "s"(&pair.b));
Expand Down
12 changes: 6 additions & 6 deletions clang/test/CodeGen/attr-counted-by.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1098,7 +1098,7 @@ int test12_a, test12_b;
// SANITIZE-WITH-ATTR-NEXT: tail call void @__ubsan_handle_out_of_bounds_abort(ptr nonnull @[[GLOB20:[0-9]+]], i64 0) #[[ATTR10]], !nosanitize [[META2]]
// SANITIZE-WITH-ATTR-NEXT: unreachable, !nosanitize [[META2]]
// SANITIZE-WITH-ATTR: handler.type_mismatch6:
// SANITIZE-WITH-ATTR-NEXT: tail call void @__ubsan_handle_type_mismatch_v1_abort(ptr nonnull @[[GLOB21:[0-9]+]], i64 ptrtoint (ptr getelementptr inbounds ([[STRUCT_ANON_5:%.*]], ptr @test12_foo, i64 1, i32 0, i32 0, i32 0) to i64)) #[[ATTR10]], !nosanitize [[META2]]
// SANITIZE-WITH-ATTR-NEXT: tail call void @__ubsan_handle_type_mismatch_v1_abort(ptr nonnull @[[GLOB21:[0-9]+]], i64 ptrtoint (ptr getelementptr inbounds (i8, ptr @test12_foo, i64 4) to i64)) #[[ATTR10]], !nosanitize [[META2]]
// SANITIZE-WITH-ATTR-NEXT: unreachable, !nosanitize [[META2]]
//
// NO-SANITIZE-WITH-ATTR-LABEL: define dso_local noundef i32 @test12(
Expand All @@ -1111,7 +1111,7 @@ int test12_a, test12_b;
// NO-SANITIZE-WITH-ATTR-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [6 x i32], ptr [[BAZ]], i64 0, i64 [[IDXPROM]]
// NO-SANITIZE-WITH-ATTR-NEXT: [[TMP0:%.*]] = load i32, ptr [[ARRAYIDX]], align 4, !tbaa [[TBAA2]]
// NO-SANITIZE-WITH-ATTR-NEXT: store i32 [[TMP0]], ptr @test12_b, align 4, !tbaa [[TBAA2]]
// NO-SANITIZE-WITH-ATTR-NEXT: [[TMP1:%.*]] = load i32, ptr getelementptr inbounds ([[STRUCT_ANON_5:%.*]], ptr @test12_foo, i64 1, i32 0, i32 0, i32 0), align 4, !tbaa [[TBAA2]]
// NO-SANITIZE-WITH-ATTR-NEXT: [[TMP1:%.*]] = load i32, ptr getelementptr inbounds (i8, ptr @test12_foo, i64 4), align 4, !tbaa [[TBAA2]]
// NO-SANITIZE-WITH-ATTR-NEXT: store i32 [[TMP1]], ptr @test12_a, align 4, !tbaa [[TBAA2]]
// NO-SANITIZE-WITH-ATTR-NEXT: br label [[FOR_COND:%.*]]
// NO-SANITIZE-WITH-ATTR: for.cond:
Expand Down Expand Up @@ -1140,7 +1140,7 @@ int test12_a, test12_b;
// SANITIZE-WITHOUT-ATTR-NEXT: tail call void @__ubsan_handle_out_of_bounds_abort(ptr nonnull @[[GLOB4:[0-9]+]], i64 0) #[[ATTR8]], !nosanitize [[META9]]
// SANITIZE-WITHOUT-ATTR-NEXT: unreachable, !nosanitize [[META9]]
// SANITIZE-WITHOUT-ATTR: handler.type_mismatch6:
// SANITIZE-WITHOUT-ATTR-NEXT: tail call void @__ubsan_handle_type_mismatch_v1_abort(ptr nonnull @[[GLOB5:[0-9]+]], i64 ptrtoint (ptr getelementptr inbounds ([[STRUCT_ANON_5:%.*]], ptr @test12_foo, i64 1, i32 0, i32 0, i32 0) to i64)) #[[ATTR8]], !nosanitize [[META9]]
// SANITIZE-WITHOUT-ATTR-NEXT: tail call void @__ubsan_handle_type_mismatch_v1_abort(ptr nonnull @[[GLOB5:[0-9]+]], i64 ptrtoint (ptr getelementptr inbounds (i8, ptr @test12_foo, i64 4) to i64)) #[[ATTR8]], !nosanitize [[META9]]
// SANITIZE-WITHOUT-ATTR-NEXT: unreachable, !nosanitize [[META9]]
//
// NO-SANITIZE-WITHOUT-ATTR-LABEL: define dso_local noundef i32 @test12(
Expand All @@ -1153,7 +1153,7 @@ int test12_a, test12_b;
// NO-SANITIZE-WITHOUT-ATTR-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [6 x i32], ptr [[BAZ]], i64 0, i64 [[IDXPROM]]
// NO-SANITIZE-WITHOUT-ATTR-NEXT: [[TMP0:%.*]] = load i32, ptr [[ARRAYIDX]], align 4, !tbaa [[TBAA2]]
// NO-SANITIZE-WITHOUT-ATTR-NEXT: store i32 [[TMP0]], ptr @test12_b, align 4, !tbaa [[TBAA2]]
// NO-SANITIZE-WITHOUT-ATTR-NEXT: [[TMP1:%.*]] = load i32, ptr getelementptr inbounds ([[STRUCT_ANON_5:%.*]], ptr @test12_foo, i64 1, i32 0, i32 0, i32 0), align 4, !tbaa [[TBAA2]]
// NO-SANITIZE-WITHOUT-ATTR-NEXT: [[TMP1:%.*]] = load i32, ptr getelementptr inbounds (i8, ptr @test12_foo, i64 4), align 4, !tbaa [[TBAA2]]
// NO-SANITIZE-WITHOUT-ATTR-NEXT: store i32 [[TMP1]], ptr @test12_a, align 4, !tbaa [[TBAA2]]
// NO-SANITIZE-WITHOUT-ATTR-NEXT: br label [[FOR_COND:%.*]]
// NO-SANITIZE-WITHOUT-ATTR: for.cond:
Expand Down Expand Up @@ -1315,7 +1315,7 @@ int test14(int idx) {
// NO-SANITIZE-WITH-ATTR-SAME: i32 noundef [[IDX:%.*]]) local_unnamed_addr #[[ATTR4]] {
// NO-SANITIZE-WITH-ATTR-NEXT: entry:
// NO-SANITIZE-WITH-ATTR-NEXT: [[IDXPROM:%.*]] = sext i32 [[IDX]] to i64
// NO-SANITIZE-WITH-ATTR-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [0 x i32], ptr getelementptr inbounds ([[STRUCT_ANON_8:%.*]], ptr @__const.test15.foo, i64 1, i32 0), i64 0, i64 [[IDXPROM]]
// NO-SANITIZE-WITH-ATTR-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [0 x i32], ptr getelementptr inbounds (i8, ptr @__const.test15.foo, i64 8), i64 0, i64 [[IDXPROM]]
// NO-SANITIZE-WITH-ATTR-NEXT: [[TMP0:%.*]] = load i32, ptr [[ARRAYIDX]], align 4, !tbaa [[TBAA2]]
// NO-SANITIZE-WITH-ATTR-NEXT: ret i32 [[TMP0]]
//
Expand All @@ -1336,7 +1336,7 @@ int test14(int idx) {
// NO-SANITIZE-WITHOUT-ATTR-SAME: i32 noundef [[IDX:%.*]]) local_unnamed_addr #[[ATTR1]] {
// NO-SANITIZE-WITHOUT-ATTR-NEXT: entry:
// NO-SANITIZE-WITHOUT-ATTR-NEXT: [[IDXPROM:%.*]] = sext i32 [[IDX]] to i64
// NO-SANITIZE-WITHOUT-ATTR-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [0 x i32], ptr getelementptr inbounds ([[STRUCT_ANON_8:%.*]], ptr @__const.test15.foo, i64 1, i32 0), i64 0, i64 [[IDXPROM]]
// NO-SANITIZE-WITHOUT-ATTR-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [0 x i32], ptr getelementptr inbounds (i8, ptr @__const.test15.foo, i64 8), i64 0, i64 [[IDXPROM]]
// NO-SANITIZE-WITHOUT-ATTR-NEXT: [[TMP0:%.*]] = load i32, ptr [[ARRAYIDX]], align 4, !tbaa [[TBAA2]]
// NO-SANITIZE-WITHOUT-ATTR-NEXT: ret i32 [[TMP0]]
//
Expand Down
4 changes: 2 additions & 2 deletions clang/test/CodeGenCXX/atomicinit.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -86,7 +86,7 @@ namespace PR18097 {
};
// CHECK-LABEL: define {{.*}} @__cxx_global_var_init
// CHECK: call void @_ZN7PR180977dynamic1XC1Ei(ptr {{[^,]*}} @_ZN7PR180977dynamic1yE, i32 noundef 4)
// CHECK: store i32 5, ptr getelementptr inbounds ({{.*}}, ptr @_ZN7PR180977dynamic1yE, i32 0, i32 1)
// CHECK: store i32 5, ptr getelementptr inbounds (i8, ptr @_ZN7PR180977dynamic1yE, i32 4)
Y y = { X(4), 5 };
}

Expand All @@ -110,7 +110,7 @@ namespace PR18097 {
// CHECK-LABEL: define {{.*}} @__cxx_global_var_init
// CHECK: tail call void @llvm.memcpy.p0.p0.i32(ptr{{.*}} @_ZN7PR180978constant2y2E, ptr{{.*}} @_ZN7PR180978constantL1xE, i32 3, i1 false)
// CHECK: %0 = load i32, ptr @_ZN7PR180978constant1zE
// CHECK: store i32 %0, ptr getelementptr inbounds (%"struct.PR18097::constant::Y", ptr @_ZN7PR180978constant2y2E, i32 0, i32 1)
// CHECK: store i32 %0, ptr getelementptr inbounds (i8, ptr @_ZN7PR180978constant2y2E, i32 4)
int z;
constexpr X x{1};
Y y2 = { x, z };
Expand Down
4 changes: 2 additions & 2 deletions clang/test/CodeGenCXX/auto-var-init.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1346,7 +1346,7 @@ TEST_UNINIT(base, base);
// PATTERN-O0: call void @llvm.memcpy{{.*}} @__const.test_base_uninit.uninit{{.+}}), !annotation [[AUTO_INIT]]
// ZERO-LABEL: @test_base_uninit()
// ZERO-O0: call void @llvm.memset{{.*}}, i8 0,{{.+}}), !annotation [[AUTO_INIT]]
// ZERO-O1: store ptr getelementptr inbounds inrange(-16, 16) ({ [4 x ptr] }, ptr @_ZTV4base, i64 0, i32 0, i64 2), {{.*}}, align 8
// ZERO-O1: store ptr getelementptr inbounds inrange(-16, 16) (i8, ptr @_ZTV4base, i64 16), {{.*}}, align 8
// ZERO-O1-NOT: !annotation

TEST_BRACES(base, base);
Expand All @@ -1367,7 +1367,7 @@ TEST_UNINIT(derived, derived);
// ZERO-LABEL: @test_derived_uninit()
// ZERO-O0: call void @llvm.memset{{.*}}, i8 0, {{.+}}), !annotation [[AUTO_INIT]]
// ZERO-O1: store i64 0, {{.*}} align 8, !annotation [[AUTO_INIT]]
// ZERO-O1: store ptr getelementptr inbounds inrange(-16, 16) ({ [4 x ptr] }, ptr @_ZTV7derived, i64 0, i32 0, i64 2), {{.*}} align 8
// ZERO-O1: store ptr getelementptr inbounds inrange(-16, 16) (i8, ptr @_ZTV7derived, i64 16), {{.*}} align 8

TEST_BRACES(derived, derived);
// CHECK-LABEL: @test_derived_braces()
Expand Down
4 changes: 2 additions & 2 deletions clang/test/Profile/c-unreachable-after-switch.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,11 +5,11 @@
// CHECK-LABEL: @foo()
// CHECK: store {{.*}} @[[C]]
void foo(void) {
// CHECK: store {{.*}} @[[C]], i64 0, i64 2
// CHECK: store {{.*}} @[[C]], i64 16)
switch (0) {
default:
return;
}
// We shouldn't emit the unreachable counter. This used to crash in GlobalDCE.
// CHECK-NOT: store {{.*}} @[[C]], i64 0, i64 1}
// CHECK-NOT: store {{.*}} @[[C]], i64 8)
}
20 changes: 10 additions & 10 deletions compiler-rt/test/profile/Linux/counter_promo_for.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,29 +19,29 @@ __attribute__((noinline)) void bar(int i) { g += i; }

__attribute__((noinline)) void foo(int n, int N) {
// PROMO-LABEL: @foo
// PROMO: load{{.*}}@__profc_foo{{.*}} 3){{.*}}
// PROMO: load{{.*}}@__profc_foo{{.*}} 24){{.*}}
// PROMO-NEXT: add
// PROMO-NEXT: store{{.*}}@__profc_foo{{.*}} 3){{.*}}
// PROMO-NEXT: store{{.*}}@__profc_foo{{.*}} 24){{.*}}
// PROMO: load{{.*}}@__profc_foo, align
// PROMO-NEXT: add
// PROMO-NEXT: store{{.*}}@__profc_foo, align
// PROMO-NEXT: load{{.*}}@__profc_foo{{.*}} 1){{.*}}
// PROMO-NEXT: load{{.*}}@__profc_foo{{.*}} 8){{.*}}
// PROMO-NEXT: add
// PROMO-NEXT: store{{.*}}@__profc_foo{{.*}} 1){{.*}}
// PROMO: load{{.*}}@__profc_foo{{.*}} 2){{.*}}
// PROMO-NEXT: store{{.*}}@__profc_foo{{.*}} 8){{.*}}
// PROMO: load{{.*}}@__profc_foo{{.*}} 16){{.*}}
// PROMO-NEXT: add
// PROMO-NEXT: store{{.*}}@__profc_foo{{.*}} 2){{.*}}
// PROMO-NEXT: store{{.*}}@__profc_foo{{.*}} 16){{.*}}
//
// NOPROMO-LABEL: @foo
// NOPROMO: load{{.*}}@__profc_foo, align
// NOPROMO-NEXT: add
// NOPROMO-NEXT: store{{.*}}@__profc_foo, align
// NOPROMO: load{{.*}}@__profc_foo{{.*}} 1){{.*}}
// NOPROMO: load{{.*}}@__profc_foo{{.*}} 8){{.*}}
// NOPROMO-NEXT: add
// NOPROMO-NEXT: store{{.*}}@__profc_foo{{.*}} 1){{.*}}
// NOPROMO: load{{.*}}@__profc_foo{{.*}} 2){{.*}}
// NOPROMO-NEXT: store{{.*}}@__profc_foo{{.*}} 8){{.*}}
// NOPROMO: load{{.*}}@__profc_foo{{.*}} 16){{.*}}
// NOPROMO-NEXT: add
// NOPROMO-NEXT: store{{.*}}@__profc_foo{{.*}} 2){{.*}}
// NOPROMO-NEXT: store{{.*}}@__profc_foo{{.*}} 16){{.*}}
int i;
for (i = 0; i < N; i++) {
if (i < n + 1)
Expand Down
16 changes: 8 additions & 8 deletions compiler-rt/test/profile/Linux/counter_promo_while.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,23 +20,23 @@ __attribute__((noinline)) void foo(int n, int N) {
// PROMO: load{{.*}}@__profc_foo, align
// PROMO-NEXT: add
// PROMO-NEXT: store{{.*}}@__profc_foo, align
// PROMO-NEXT: load{{.*}}@__profc_foo{{.*}} 1){{.*}}
// PROMO-NEXT: load{{.*}}@__profc_foo{{.*}} 8){{.*}}
// PROMO-NEXT: add
// PROMO-NEXT: store{{.*}}@__profc_foo{{.*}} 1){{.*}}
// PROMO-NEXT: load{{.*}}@__profc_foo{{.*}} 2){{.*}}
// PROMO-NEXT: store{{.*}}@__profc_foo{{.*}} 8){{.*}}
// PROMO-NEXT: load{{.*}}@__profc_foo{{.*}} 16){{.*}}
// PROMO-NEXT: add
// PROMO-NEXT: store{{.*}}@__profc_foo{{.*}} 2){{.*}}
// PROMO-NEXT: store{{.*}}@__profc_foo{{.*}} 16){{.*}}
//
// NOPROMO-LABEL: @foo
// NOPROMO: load{{.*}}@__profc_foo, align
// NOPROMO-NEXT: add
// NOPROMO-NEXT: store{{.*}}@__profc_foo, align
// NOPROMO: load{{.*}}@__profc_foo{{.*}} 1){{.*}}
// NOPROMO: load{{.*}}@__profc_foo{{.*}} 8){{.*}}
// NOPROMO-NEXT: add
// NOPROMO-NEXT: store{{.*}}@__profc_foo{{.*}} 1){{.*}}
// NOPROMO: load{{.*}}@__profc_foo{{.*}} 2){{.*}}
// NOPROMO-NEXT: store{{.*}}@__profc_foo{{.*}} 8){{.*}}
// NOPROMO: load{{.*}}@__profc_foo{{.*}} 16){{.*}}
// NOPROMO-NEXT: add
// NOPROMO-NEXT: store{{.*}}@__profc_foo{{.*}} 2){{.*}}
// NOPROMO-NEXT: store{{.*}}@__profc_foo{{.*}} 16){{.*}}
int i = 0;
while (i < N) {
if (i < n + 1)
Expand Down
46 changes: 10 additions & 36 deletions llvm/lib/Analysis/ConstantFolding.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -869,7 +869,6 @@ Constant *SymbolicallyEvaluateGEP(const GEPOperator *GEP,
bool InBounds = GEP->isInBounds();

Type *SrcElemTy = GEP->getSourceElementType();
Type *ResElemTy = GEP->getResultElementType();
Type *ResTy = GEP->getType();
if (!SrcElemTy->isSized() || isa<ScalableVectorType>(SrcElemTy))
return nullptr;
Expand Down Expand Up @@ -944,43 +943,18 @@ Constant *SymbolicallyEvaluateGEP(const GEPOperator *GEP,
return ConstantExpr::getIntToPtr(C, ResTy);
}

// Otherwise form a regular getelementptr. Recompute the indices so that
// we eliminate over-indexing of the notional static type array bounds.
// This makes it easy to determine if the getelementptr is "inbounds".

// For GEPs of GlobalValues, use the value type, otherwise use an i8 GEP.
if (auto *GV = dyn_cast<GlobalValue>(Ptr))
SrcElemTy = GV->getValueType();
else
SrcElemTy = Type::getInt8Ty(Ptr->getContext());

if (!SrcElemTy->isSized())
return nullptr;

Type *ElemTy = SrcElemTy;
SmallVector<APInt> Indices = DL.getGEPIndicesForOffset(ElemTy, Offset);
if (Offset != 0)
return nullptr;

// Try to add additional zero indices to reach the desired result element
// type.
// TODO: Should we avoid extra zero indices if ResElemTy can't be reached and
// we'll have to insert a bitcast anyway?
while (ElemTy != ResElemTy) {
Type *NextTy = GetElementPtrInst::getTypeAtIndex(ElemTy, (uint64_t)0);
if (!NextTy)
break;

Indices.push_back(APInt::getZero(isa<StructType>(ElemTy) ? 32 : BitWidth));
ElemTy = NextTy;
// Try to infer inbounds for GEPs of globals.
if (!InBounds && Offset.isNonNegative()) {
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

is there a test for the case where !Offset.isNonNegative()?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

https://github.com/llvm/llvm-project/blob/main/llvm/test/Transforms/GlobalOpt/large-element-size.ll gets an incorrect inbounds without the check.

bool CanBeNull, CanBeFreed;
uint64_t DerefBytes =
Ptr->getPointerDereferenceableBytes(DL, CanBeNull, CanBeFreed);
InBounds = DerefBytes != 0 && !CanBeNull && Offset.sle(DerefBytes);
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I've added this inference in this patch, because we lose out on this inference in the DataLayout-independent constant folding:

llvm-project/llvm/lib/IR/ConstantFold.cpp

Lines 1717 to 1724 in 88b6186

// If all indices are known integers and normalized, we can do a simple
// check for the "inbounds" property.
if (!Unknown && !InBounds)
if (auto *GV = dyn_cast<GlobalVariable>(C))
if (!GV->hasExternalWeakLinkage() && GV->getValueType() == PointeeTy &&
isInBoundsIndices(Idxs))
return ConstantExpr::getGetElementPtr(PointeeTy, C, Idxs,
/*InBounds=*/true, InRange);
As such, we need a (more powerful version of) this inference in the DataLayout-aware constant folding code.

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

can we remove the other constant folding?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I don't think we'd want to remove it at this point as it's still used in some key places like initial IR construction in clang -- longer term, I'd like to get rid of the two separate constant folding implementations altogether.

}

SmallVector<Constant *, 32> NewIdxs;
for (const APInt &Index : Indices)
NewIdxs.push_back(ConstantInt::get(
Type::getIntNTy(Ptr->getContext(), Index.getBitWidth()), Index));

return ConstantExpr::getGetElementPtr(SrcElemTy, Ptr, NewIdxs, InBounds,
// Otherwise canonicalize this to a single ptradd.
LLVMContext &Ctx = Ptr->getContext();
return ConstantExpr::getGetElementPtr(Type::getInt8Ty(Ctx), Ptr,
ConstantInt::get(Ctx, Offset), InBounds,
InRange);
}

Expand Down
14 changes: 7 additions & 7 deletions llvm/test/Other/constant-fold-gep.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -106,10 +106,10 @@

; PLAIN: @Y = global ptr getelementptr inbounds ([3 x { i32, i32 }], ptr @ext, i64 2)
; PLAIN: @Z = global ptr getelementptr inbounds (i32, ptr getelementptr inbounds ([3 x { i32, i32 }], ptr @ext, i64 0, i64 1, i32 0), i64 1)
; OPT: @Y = local_unnamed_addr global ptr getelementptr inbounds ([3 x { i32, i32 }], ptr @ext, i64 2)
; OPT: @Z = local_unnamed_addr global ptr getelementptr inbounds ([3 x { i32, i32 }], ptr @ext, i64 0, i64 1, i32 1)
; TO: @Y = local_unnamed_addr global ptr getelementptr inbounds ([3 x { i32, i32 }], ptr @ext, i64 2)
; TO: @Z = local_unnamed_addr global ptr getelementptr inbounds ([3 x { i32, i32 }], ptr @ext, i64 0, i64 1, i32 1)
; OPT: @Y = local_unnamed_addr global ptr getelementptr inbounds (i8, ptr @ext, i64 48)
; OPT: @Z = local_unnamed_addr global ptr getelementptr inbounds (i8, ptr @ext, i64 12)
; TO: @Y = local_unnamed_addr global ptr getelementptr inbounds (i8, ptr @ext, i64 48)
; TO: @Z = local_unnamed_addr global ptr getelementptr inbounds (i8, ptr @ext, i64 12)

@ext = external global [3 x { i32, i32 }]
@Y = global ptr getelementptr inbounds ([3 x { i32, i32 }], ptr getelementptr inbounds ([3 x { i32, i32 }], ptr @ext, i64 1), i64 1)
Expand Down Expand Up @@ -433,10 +433,10 @@ define ptr @fO() nounwind {
; PLAIN: ret ptr %t
; PLAIN: }
; OPT: define ptr @fZ() local_unnamed_addr #0 {
; OPT: ret ptr getelementptr inbounds ([3 x { i32, i32 }], ptr @ext, i64 0, i64 1, i32 1)
; OPT: ret ptr getelementptr inbounds (i8, ptr @ext, i64 12)
; OPT: }
; TO: define ptr @fZ() local_unnamed_addr #0 {
; TO: ret ptr getelementptr inbounds ([3 x { i32, i32 }], ptr @ext, i64 0, i64 1, i32 1)
; TO: ret ptr getelementptr inbounds (i8, ptr @ext, i64 12)
; TO: }
; SCEV: Classifying expressions for: @fZ
; SCEV: %t = bitcast ptr getelementptr inbounds (i32, ptr getelementptr inbounds ([3 x { i32, i32 }], ptr @ext, i64 0, i64 1, i32 0), i64 1) to ptr
Expand Down Expand Up @@ -464,7 +464,7 @@ define ptr @same_addrspace() nounwind noinline {
; OPT: same_addrspace
%p = getelementptr inbounds i8, ptr @p0, i32 2
ret ptr %p
; OPT: ret ptr getelementptr inbounds ([4 x i8], ptr @p0, i64 0, i64 2)
; OPT: ret ptr getelementptr inbounds (i8, ptr @p0, i64 2)
}

@gv1 = internal global i32 1
Expand Down
2 changes: 1 addition & 1 deletion llvm/test/Other/optimize-inrange-gep.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,7 +20,7 @@ define void @foo(ptr %p) {
;
; CHECK-LABEL: define void @foo(
; CHECK-SAME: ptr nocapture writeonly [[P:%.*]]) local_unnamed_addr #[[ATTR0:[0-9]+]] {
; CHECK-NEXT: store ptr getelementptr inbounds inrange(-24, 0) ({ [3 x ptr] }, ptr @vtable, i64 1, i32 0, i64 0), ptr [[P]], align 8
; CHECK-NEXT: store ptr getelementptr inbounds inrange(-24, 0) (i8, ptr @vtable, i64 24), ptr [[P]], align 8
; CHECK-NEXT: ret void
;
store ptr getelementptr inrange(-24, 0) ({ [3 x ptr], [3 x ptr] }, ptr @vtable, i32 0, i32 0, i32 3), ptr %p
Expand Down
6 changes: 3 additions & 3 deletions llvm/test/Transforms/FunctionSpecialization/function-specialization-constant-expression.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,13 +30,13 @@ define internal i64 @zoo(i1 %flag) {
; CHECK-NEXT: entry:
; CHECK-NEXT: br i1 [[FLAG:%.*]], label [[PLUS:%.*]], label [[MINUS:%.*]]
; CHECK: plus:
; CHECK-NEXT: [[TMP0:%.*]] = call i64 @func2.specialized.2(ptr getelementptr inbounds ([[STRUCT:%.*]], ptr @Global, i64 0, i32 3))
; CHECK-NEXT: [[TMP0:%.*]] = call i64 @func2.specialized.2(ptr getelementptr inbounds (i8, ptr @Global, i64 8))
; CHECK-NEXT: br label [[MERGE:%.*]]
; CHECK: minus:
; CHECK-NEXT: [[TMP1:%.*]] = call i64 @func2.specialized.1(ptr getelementptr inbounds ([[STRUCT]], ptr @Global, i64 0, i32 4))
; CHECK-NEXT: [[TMP1:%.*]] = call i64 @func2.specialized.1(ptr getelementptr inbounds (i8, ptr @Global, i64 16))
; CHECK-NEXT: br label [[MERGE]]
; CHECK: merge:
; CHECK-NEXT: [[TMP2:%.*]] = phi i64 [ ptrtoint (ptr getelementptr inbounds ([[STRUCT]], ptr @Global, i64 0, i32 3) to i64), [[PLUS]] ], [ ptrtoint (ptr getelementptr inbounds ([[STRUCT]], ptr @Global, i64 0, i32 4) to i64), [[MINUS]] ]
; CHECK-NEXT: [[TMP2:%.*]] = phi i64 [ ptrtoint (ptr getelementptr inbounds (i8, ptr @Global, i64 8) to i64), [[PLUS]] ], [ ptrtoint (ptr getelementptr inbounds (i8, ptr @Global, i64 16) to i64), [[MINUS]] ]
; CHECK-NEXT: ret i64 [[TMP2]]
;
entry:
Expand Down
2 changes: 1 addition & 1 deletion llvm/test/Transforms/GVN/PRE/load-pre-licm.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@ target triple = "i386-apple-darwin11.0.0"
define void @Bubble() nounwind noinline {
; CHECK-LABEL: @Bubble(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP7_PRE:%.*]] = load i32, ptr getelementptr inbounds ([5001 x i32], ptr @sortlist, i32 0, i32 1), align 4
; CHECK-NEXT: [[TMP7_PRE:%.*]] = load i32, ptr getelementptr inbounds (i8, ptr @sortlist, i32 4), align 4
; CHECK-NEXT: br label [[WHILE_BODY5:%.*]]
; CHECK: while.body5:
; CHECK-NEXT: [[TMP7:%.*]] = phi i32 [ [[TMP7_PRE]], [[ENTRY:%.*]] ], [ [[TMP71:%.*]], [[IF_END:%.*]] ]
Expand Down
4 changes: 2 additions & 2 deletions llvm/test/Transforms/GVN/PRE/phi-translate-2.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -63,8 +63,8 @@ define void @test2(i64 %i) {
; CHECK: if.then:
; CHECK-NEXT: [[CALL:%.*]] = tail call i64 (...) @goo()
; CHECK-NEXT: store i64 [[CALL]], ptr @g2, align 8
; CHECK-NEXT: [[T2_PRE:%.*]] = load i64, ptr getelementptr inbounds ([100 x i64], ptr @a, i64 0, i64 3), align 8
; CHECK-NEXT: [[T3_PRE:%.*]] = load i64, ptr getelementptr inbounds ([100 x i64], ptr @b, i64 0, i64 3), align 8
; CHECK-NEXT: [[T2_PRE:%.*]] = load i64, ptr getelementptr inbounds (i8, ptr @a, i64 24), align 8
; CHECK-NEXT: [[T3_PRE:%.*]] = load i64, ptr getelementptr inbounds (i8, ptr @b, i64 24), align 8
; CHECK-NEXT: [[DOTPRE:%.*]] = mul nsw i64 [[T3_PRE]], [[T2_PRE]]
; CHECK-NEXT: br label [[IF_END]]
; CHECK: if.end:
Expand Down
Loading
Loading