This adds support for the align_value attribute. This attribute is supported by
Intel's compiler (versions 14.0+), and several of my HPC users have requested
support in Clang. It specifies an alignment assumption on the values to which a
pointer points, and is used by numerical libraries to encourage efficient
generation of vector code.
Of course, we already have an aligned attribute that can specify enhanced
alignment for a type, so why is this additional attribute important? The
problem is that if you want to specify that an input array of T is, say,
64-byte aligned, you could try this:
typedef double aligned_double attribute((aligned(64)));
void foo(aligned_double *P) {
double x = P[0]; // This is fine.
double y = P[1]; // What alignment did those doubles have again?
}
the access here to P[1] causes problems. P was specified as a pointer to type
aligned_double, and any object of type aligned_double must be 64-byte aligned.
But if P[0] is 64-byte aligned, then P[1] cannot be, and this access causes
undefined behavior. Getting round this problem requires a lot of awkward
casting and hand-unrolling of loops, all of which is bad.
With the align_value attribute, we can accomplish what we'd like in a well
defined way:
typedef double *aligned_double_ptr attribute((align_value(64)));
void foo(aligned_double_ptr P) {
double x = P[0]; // This is fine.
double y = P[1]; // This is fine too.
}
This attribute does not create a new type (and so it not part of the type
system), and so will only "propagate" through templates, auto, etc. by
optimizer deduction after inlining. This seems consistent with Intel's
implementation (thanks to Alexey for confirming the various Intel-compiler
behaviors).
As a final note, I would have chosen to call this aligned_value, not
align_value, for better naming consistency with the aligned attribute, but I
think it would be more useful to users to adopt Intel's name.
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@218910
91177308-0d34-0410-b5e6-
96231b3b80d8
let Documentation = [Undocumented];
}
+def AlignValue : Attr {
+ let Spellings = [
+ // Unfortunately, this is semantically an assertion, not a
+ // directive (something else must ensure the alignment), so
+ // aligned_value is a probably a better name. We might want
+ // to add an aligned_value spelling in the future (and a
+ // corresponding C++ attribute), but this can be done later
+ // once we decide if we also want them to have
+ // slightly-different semantics than Intel's align_value.
+ GNU<"align_value">
+ // Intel's compiler on Windows also supports:
+ // , Declspec<"align_value">
+ ];
+ let Args = [ExprArgument<"Alignment">];
+ let Subjects = SubjectList<[Var, TypedefName], WarnDiag,
+ "ExpectedVariableOrTypedef">;
+ let Documentation = [AlignValueDocs];
+}
+
def AlignMac68k : InheritableAttr {
// This attribute has no spellings as it is only ever created implicitly.
let Spellings = [];
}];
}
+def AlignValueDocs : Documentation {
+ let Category = DocCatType;
+ let Content = [{
+The align_value attribute can be added to the typedef of a pointer type or the
+declaration of a variable of pointer or reference type. It specifies that the
+pointer will point to, or the reference will bind to, only objects with at
+least the provided alignment. This alignment value must be some positive power
+of 2.
+
+ .. code-block:: c
+
+ typedef double * aligned_double_ptr __attribute__((align_value(64)));
+ void foo(double & x __attribute__((align_value(128)),
+ aligned_double_ptr y) { ... }
+
+If the pointer value does not have the specified alignment at runtime, the
+behavior of the program is undefined.
+ }];
+}
+
def MSInheritanceDocs : Documentation {
let Category = DocCatType;
let Heading = "__single_inhertiance, __multiple_inheritance, __virtual_inheritance";
"Neon vector size must be 64 or 128 bits">;
def err_attribute_unsupported : Error<
"%0 attribute is not supported for this target">;
+// The err_*_attribute_argument_not_int are seperate because they're used by
+// VerifyIntegerConstantExpression.
def err_aligned_attribute_argument_not_int : Error<
"'aligned' attribute requires integer constant">;
+def err_align_value_attribute_argument_not_int : Error<
+ "'align_value' attribute requires integer constant">;
def err_alignas_attribute_wrong_decl_type : Error<
"%0 attribute cannot be applied to a %select{function parameter|"
"variable with 'register' storage class|'catch' variable|bit-field}1">;
def warn_attribute_return_pointers_refs_only : Warning<
"%0 attribute only applies to return values that are pointers or references">,
InGroup<IgnoredAttributes>;
+def warn_attribute_pointer_or_reference_only : Warning<
+ "%0 attribute only applies to a pointer or reference (%1 is invalid)">,
+ InGroup<IgnoredAttributes>;
def err_attribute_no_member_pointers : Error<
"%0 attribute cannot be used with pointers to members">;
def err_attribute_invalid_implicit_this_argument : Error<
"functions, methods and blocks|functions, methods, and classes|"
"functions, methods, and parameters|classes|variables|methods|"
"variables, functions and labels|fields and global variables|structs|"
- "variables, functions and tag types|thread-local variables|"
+ "variables and typedefs|thread-local variables|"
"variables and fields|variables, data members and tag types|"
"types and namespaces|Objective-C interfaces|methods and properties|"
"struct or union|struct, union or class|types|"
ExpectedVariableFunctionOrLabel,
ExpectedFieldOrGlobalVar,
ExpectedStruct,
- ExpectedVariableFunctionOrTag,
+ ExpectedVariableOrTypedef,
ExpectedTLSVar,
ExpectedVariableOrField,
ExpectedVariableFieldOrTag,
void AddAssumeAlignedAttr(SourceRange AttrRange, Decl *D, Expr *E, Expr *OE,
unsigned SpellingListIndex);
+ /// AddAlignValueAttr - Adds an align_value attribute to a particular
+ /// declaration.
+ void AddAlignValueAttr(SourceRange AttrRange, Decl *D, Expr *E,
+ unsigned SpellingListIndex);
+
// OpenMP directives and clauses.
private:
void *VarDataSharingAttributesStack;
AI->getArgNo() + 1,
llvm::Attribute::NonNull));
}
+
+ const auto *AVAttr = PVD->getAttr<AlignValueAttr>();
+ if (!AVAttr)
+ if (const auto *TOTy = dyn_cast<TypedefType>(OTy))
+ AVAttr = TOTy->getDecl()->getAttr<AlignValueAttr>();
+ if (AVAttr) {
+ llvm::Value *AlignmentValue =
+ EmitScalarExpr(AVAttr->getAlignment());
+ llvm::ConstantInt *AlignmentCI =
+ cast<llvm::ConstantInt>(AlignmentValue);
+ unsigned Alignment =
+ std::min((unsigned) AlignmentCI->getZExtValue(),
+ +llvm::Value::MaximumAlignment);
+
+ llvm::AttrBuilder Attrs;
+ Attrs.addAlignmentAttr(Alignment);
+ AI->addAttr(llvm::AttributeSet::get(getLLVMContext(),
+ AI->getArgNo() + 1, Attrs));
+ }
}
if (Arg->getType().isRestrictQualified())
Attr.getAttributeSpellingListIndex()));
}
+static void handleAlignValueAttr(Sema &S, Decl *D,
+ const AttributeList &Attr) {
+ S.AddAlignValueAttr(Attr.getRange(), D, Attr.getArgAsExpr(0),
+ Attr.getAttributeSpellingListIndex());
+}
+
+void Sema::AddAlignValueAttr(SourceRange AttrRange, Decl *D, Expr *E,
+ unsigned SpellingListIndex) {
+ AlignValueAttr TmpAttr(AttrRange, Context, E, SpellingListIndex);
+ SourceLocation AttrLoc = AttrRange.getBegin();
+
+ QualType T;
+ if (TypedefNameDecl *TD = dyn_cast<TypedefNameDecl>(D))
+ T = TD->getUnderlyingType();
+ else if (ValueDecl *VD = dyn_cast<ValueDecl>(D))
+ T = VD->getType();
+ else
+ llvm_unreachable("Unknown decl type for align_value");
+
+ if (!T->isDependentType() && !T->isAnyPointerType() &&
+ !T->isReferenceType() && !T->isMemberPointerType()) {
+ Diag(AttrLoc, diag::warn_attribute_pointer_or_reference_only)
+ << &TmpAttr /*TmpAttr.getName()*/ << T << D->getSourceRange();
+ return;
+ }
+
+ if (!E->isValueDependent()) {
+ llvm::APSInt Alignment(32);
+ ExprResult ICE
+ = VerifyIntegerConstantExpression(E, &Alignment,
+ diag::err_align_value_attribute_argument_not_int,
+ /*AllowFold*/ false);
+ if (ICE.isInvalid())
+ return;
+
+ if (!Alignment.isPowerOf2()) {
+ Diag(AttrLoc, diag::err_alignment_not_power_of_two)
+ << E->getSourceRange();
+ return;
+ }
+
+ D->addAttr(::new (Context)
+ AlignValueAttr(AttrRange, Context, ICE.get(),
+ SpellingListIndex));
+ return;
+ }
+
+ // Save dependent expressions in the AST to be instantiated.
+ D->addAttr(::new (Context) AlignValueAttr(TmpAttr));
+ return;
+}
+
static void handleAlignedAttr(Sema &S, Decl *D, const AttributeList &Attr) {
// check the attribute arguments.
if (Attr.getNumArgs() > 1) {
case AttributeList::AT_Aligned:
handleAlignedAttr(S, D, Attr);
break;
+ case AttributeList::AT_AlignValue:
+ handleAlignValueAttr(S, D, Attr);
+ break;
case AttributeList::AT_AlwaysInline:
handleAlwaysInlineAttr(S, D, Attr);
break;
Aligned->getSpellingListIndex());
}
+static void instantiateDependentAlignValueAttr(
+ Sema &S, const MultiLevelTemplateArgumentList &TemplateArgs,
+ const AlignValueAttr *Aligned, Decl *New) {
+ // The alignment expression is a constant expression.
+ EnterExpressionEvaluationContext Unevaluated(S, Sema::ConstantEvaluated);
+ ExprResult Result = S.SubstExpr(Aligned->getAlignment(), TemplateArgs);
+ if (!Result.isInvalid())
+ S.AddAlignValueAttr(Aligned->getLocation(), New, Result.getAs<Expr>(),
+ Aligned->getSpellingListIndex());
+}
+
static void instantiateDependentEnableIfAttr(
Sema &S, const MultiLevelTemplateArgumentList &TemplateArgs,
const EnableIfAttr *A, const Decl *Tmpl, Decl *New) {
continue;
}
+ const AlignValueAttr *AlignValue = dyn_cast<AlignValueAttr>(TmplAttr);
+ if (AlignValue) {
+ instantiateDependentAlignValueAttr(*this, TemplateArgs, AlignValue, New);
+ continue;
+ }
+
const EnableIfAttr *EnableIf = dyn_cast<EnableIfAttr>(TmplAttr);
if (EnableIf && EnableIf->getCond()->isValueDependent()) {
instantiateDependentEnableIfAttr(*this, TemplateArgs, EnableIf, Tmpl,
--- /dev/null
+// RUN: %clang_cc1 -triple x86_64-unknown-unknown -emit-llvm -o - %s | FileCheck %s
+
+typedef double * __attribute__((align_value(64))) aligned_double;
+
+void foo(aligned_double x, double * y __attribute__((align_value(32))),
+ double & z __attribute__((align_value(128)))) { };
+// CHECK: define void @_Z3fooPdS_Rd(double* align 64 %x, double* align 32 %y, double* dereferenceable(8) align 128 %z)
+
--- /dev/null
+// RUN: %clang_cc1 -fsyntax-only -verify %s
+
+typedef double * __attribute__((align_value(64))) aligned_double;
+
+void foo(aligned_double x, double * y __attribute__((align_value(32)))) { };
+
+// expected-error@+1 {{requested alignment is not a power of 2}}
+typedef double * __attribute__((align_value(63))) aligned_double1;
+
+// expected-error@+1 {{requested alignment is not a power of 2}}
+typedef double * __attribute__((align_value(-2))) aligned_double2;
+
+// expected-error@+1 {{attribute takes one argument}}
+typedef double * __attribute__((align_value(63, 4))) aligned_double3;
+
+// expected-error@+1 {{attribute takes one argument}}
+typedef double * __attribute__((align_value())) aligned_double3a;
+
+// expected-error@+1 {{attribute takes one argument}}
+typedef double * __attribute__((align_value)) aligned_double3b;
+
+// expected-error@+1 {{'align_value' attribute requires integer constant}}
+typedef double * __attribute__((align_value(4.5))) aligned_double4;
+
+// expected-warning@+1 {{'align_value' attribute only applies to a pointer or reference ('int' is invalid)}}
+typedef int __attribute__((align_value(32))) aligned_int;
+
+typedef double * __attribute__((align_value(32*2))) aligned_double5;
+
+// expected-warning@+1 {{'align_value' attribute only applies to variables and typedefs}}
+void foo() __attribute__((align_value(32)));
+
--- /dev/null
+// RUN: %clang_cc1 -fsyntax-only -verify %s
+
+typedef double * __attribute__((align_value(64))) aligned_double;
+
+void foo(aligned_double x, double * y __attribute__((align_value(32))),
+ double & z __attribute__((align_value(128)))) { };
+
+template <typename T, int Q>
+struct x {
+ typedef T* aligned_int __attribute__((align_value(32+8*Q)));
+ aligned_int V;
+
+ void foo(aligned_int a, T &b __attribute__((align_value(sizeof(T)*4))));
+};
+
+x<float, 4> y;
+
+template <typename T, int Q>
+struct nope {
+ // expected-error@+1 {{requested alignment is not a power of 2}}
+ void foo(T &b __attribute__((align_value(sizeof(T)+1))));
+};
+
+// expected-note@+1 {{in instantiation of template class 'nope<long double, 4>' requested here}}
+nope<long double, 4> y2;
+
projects / clang / commitdiff