This new builtin template allows for incredibly fast instantiations of
templates like std::integer_sequence.
Performance numbers follow:
My work station has 64 GB of ram + 20 Xeon Cores at 2.8 GHz.
__make_integer_seq<std::integer_sequence, int, 90000> takes 0.25
seconds.
std::make_integer_sequence<int, 90000> takes unbound time, it is still
running. Clang is consuming gigabytes of memory.
Differential Revision: http://reviews.llvm.org/D13786
llvm-svn: 252036
This sets the mostly expected Darwin default ABI options for these two
platforms. Active changes from these defaults for watchOS are in a later patch.
llvm-svn: 251708
This relands r250831 after some fixes to shrink the ParentMap overall
with one addtional tweak: nodes with pointer identity (e.g. Decl* and
friends) can be store more efficiently so I put them in a separate map.
All other nodes (so far only TypeLoc and NNSLoc) go in a different map
keyed on DynTypedNode. This further uglifies the code but significantly
reduces memory overhead.
Overall this change still make ParentMap significantly larger but it's
nowhere as bad as before. I see about 25 MB over baseline (pre-r251008)
on X86ISelLowering.cpp. If this becomes an issue we could consider
splitting the maps further as DynTypedNode is still larger (32 bytes)
than a single TypeLoc (16 bytes) but I didn't want to introduce even
more complexity now.
Differential Revision: http://reviews.llvm.org/D14011
llvm-svn: 251101
Previously, __weak was silently accepted and ignored in MRC mode.
That makes this a potentially source-breaking change that we have to
roll out cautiously. Accordingly, for the time being, actual support
for __weak references in MRC is experimental, and the compiler will
reject attempts to actually form such references. The intent is to
eventually enable the feature by default in all non-GC modes.
(It is, of course, incompatible with ObjC GC's interpretation of
__weak.)
If you like, you can enable this feature with
-Xclang -fobjc-weak
but like any -Xclang option, this option may be removed at any point,
e.g. if/when it is eventually enabled by default.
This patch also enables the use of the ARC __unsafe_unretained qualifier
in MRC. Unlike __weak, this is being enabled immediately. Since
variables are essentially __unsafe_unretained by default in MRC,
the only practical uses are (1) communication and (2) changing the
default behavior of by-value block capture.
As an implementation matter, this means that the ObjC ownership
qualifiers may appear in any ObjC language mode, and so this patch
removes a number of checks for getLangOpts().ObjCAutoRefCount
that were guarding the processing of these qualifiers. I don't
expect this to be a significant drain on performance; it may even
be faster to just check for these qualifiers directly on a type
(since it's probably in a register anyway) than to do N dependent
loads to grab the LangOptions.
rdar://9674298
llvm-svn: 251041
These are by far the most common types to be parents in the AST so it makes
sense to optimize for them. Put them directly into the value of the map.
This currently saves 32 bytes per parent in the map and a pointer
indirection at the cost of some additional complexity in the code.
Sadly this means we cannot return an ArrayRef from getParents anymore, add
a proxy class that can own a single DynTypedNode and otherwise behaves
exactly the same as ArrayRef.
For example on a random large file (X86ISelLowering.cpp) this reduces the
size of the parent map by 24 MB.
Differential Revision: http://reviews.llvm.org/D13976
llvm-svn: 251008
Putting DynTypedNode in the ParentMap bloats its memory foot print.
Before the void* key had 8 bytes, now we're at 40 bytes per key which
can mean multiple gigabytes increase for large ASTs and this count
doesn't even include all the added TypeLoc nodes. Revert until I come
up with a better data structure.
This reverts commit r250831.
llvm-svn: 250889
Firstly this changes the type of parent map to be keyed on DynTypedNode to
simplify the following changes. This comes with a DenseMapInfo for
DynTypedNode, which is a bit incomplete still and will probably only work
for parentmap right now.
Then the RecursiveASTVisitor in ASTContext is updated and finally
ASTMatchers hasParent and hasAncestor learn about the new functionality.
Now ParentMap is only missing TemplateArgumentLocs and CXXCtorInitializers.
Differential Revision: http://reviews.llvm.org/D13897
llvm-svn: 250831
Summary: It breaks the build for the ASTMatchers
Subscribers: klimek, cfe-commits
Differential Revision: http://reviews.llvm.org/D13893
llvm-svn: 250827
Out-of-line definitions of static data members which have an inline
initializer must get GVA_DiscardableODR linkage instead of
GVA_StrongExternal linkage.
MSVC 2013's behavior is different with respect to this and would cause
link errors if one TU provided a definition while another did not.
MSVC 2015 fixed this bug, making this OK. Note that the 2015 behavior
is always compatible with 2013: it never produces a strong definition.
This essentially reverts r237787.
llvm-svn: 250757
No ABI for C++ currently makes it possible to implement the standard
100% perfectly. We wrongly hid some of our compatible behavior behind
-fms-compatibility instead of tying it to the compiler ABI.
llvm-svn: 249656
Objective-C ARC lifetime qualifiers are dropped when canonicalizing
function types. Perform the same adjustment before comparing the
deduced result types of lambdas. Fixes rdar://problem/22344904.
llvm-svn: 249065
Adjust __global__ functions with DiscardableODR linkage to use
StrongODR linkage instead, so they are visible externally.
Differential Revision: http://reviews.llvm.org/D13067
llvm-svn: 248400
* adds -aux-triple option to specify target triple
* propagates aux target info to AST context and Preprocessor
* pulls in target specific preprocessor macros.
* pulls in target-specific builtins from aux target.
* sets appropriate host or device attribute on builtins.
Differential Revision: http://reviews.llvm.org/D12917
llvm-svn: 248299
Summary:
This change adds support for `__builtin_ms_va_list`, a GCC extension for
variadic `ms_abi` functions. The existing `__builtin_va_list` support is
inadequate for this because `va_list` is defined differently in the Win64
ABI vs. the System V/AMD64 ABI.
Depends on D1622.
Reviewers: rsmith, rnk, rjmccall
CC: cfe-commits
Differential Revision: http://reviews.llvm.org/D1623
llvm-svn: 247941
This implements basic support for compiling (though not yet assembling
or linking) for a WebAssembly target. Note that ABI details are not yet
finalized, and may change.
Differential Revision: http://reviews.llvm.org/D12002
llvm-svn: 246814
A class without a name for linkage purposes gets a name along the lines
of <unnamed-type-foo> where foo is either the name of a declarator which
defined it (like a variable or field) or a
typedef-name (like a typedef or alias-declaration).
We handled the declarator case correctly but it would fall down during
template instantiation if the declarator didn't share the tag's type.
We failed to handle the typedef-name case at all.
Instead, keep track of the association between the two and keep it up to
date in the face of template instantiation.
llvm-svn: 246469
Adds parsing/sema analysis/serialization/deserialization for array sections in OpenMP constructs (introduced in OpenMP 4.0).
Currently it is allowed to use array sections only in OpenMP clauses that accepts list of expressions.
Differential Revision: http://reviews.llvm.org/D10732
llvm-svn: 245937
We risk iterator invalidation issues if we use a DenseMap to hold the
backing storage for an APValue. Instead, BumpPtrAllocate them and
use APValue * as our DenseMap value.
Also, don't assume that MaterializedGlobalTemporaryMap won't regrow
between when we initially perform a lookup and later on when we actually
try to insert into it.
This fixes PR24289.
Differential Revision: http://reviews.llvm.org/D11629
llvm-svn: 244989
chain and fix the cases where it fires.
* Handle the __va_list_tag as a predefined decl. Previously we failed to merge
sometimes it because it's not visible to name lookup. (In passing, remove
redundant __va_list_tag typedefs that we were creating for some ABIs. These
didn't affect the mangling or representation of the type.)
* For Decls derived from Redeclarable that are not in fact redeclarable
(implicit params, function params, ObjC type parameters), remove them from
the list of expected redeclarable decls.
llvm-svn: 243259
We treated DependentSizedArrayTypes with the same element type but
differing size expressions as equivalently canonical. This would lead
to bizarre behavior during template instantiation.
This fixes PR24212.
llvm-svn: 243093
Normally, explicit specializations are treated like strong external
definitions. However, MSVC treats explicit specializations of static
data members as weak. MSVC 2013's <regex> implementation has such an
explicit specialization which leads to clang emitting a strong
definition in each translation unit which includes it. Tweak clang's
linkage calculation to give such entities GVA_StrongODR linkage instead.
This fixes PR24165.
llvm-svn: 242592
Introduce co- and contra-variance for Objective-C type parameters,
which allows us to express that (for example) an NSArray is covariant
in its type parameter. This means that NSArray<NSMutableString *> * is
a subtype of NSArray<NSString *> *, which is expected of the immutable
Foundation collections.
Type parameters can be annotated with __covariant or __contravariant
to make them co- or contra-variant, respectively. This feature can be
detected by __has_feature(objc_generics_variance). Implements
rdar://problem/20217490.
llvm-svn: 241549
The __kindof type qualifier can be applied to Objective-C object
(pointer) types to indicate id-like behavior, which includes implicit
"downcasting" of __kindof types to subclasses and id-like message-send
behavior. __kindof types provide better type bounds for substitutions
into unspecified generic types, which preserves more type information.
llvm-svn: 241548
The Objective-C common-type computation had a few problems that
required a significant rework, including:
- Quadradic behavior when finding the common base type; now it's
linear.
- Keeping around type arguments when computing the common type
between a specialized and an unspecialized type
- Introducing redundant protocol qualifiers.
Part of rdar://problem/6294649. Also fixes rdar://problem/19572837 by
addressing a longstanding bug in
ASTContext::CollectInheritedProtocols().
llvm-svn: 241544
When messaging a method that was defined in an Objective-C class (or
category or extension thereof) that has type parameters, substitute
the type arguments for those type parameters. Similarly, substitute
into property accesses, instance variables, and other references.
This includes general infrastructure for substituting the type
arguments associated with an ObjCObject(Pointer)Type into a type
referenced within a particular context, handling all of the
substitutions required to deal with (e.g.) inheritance involving
parameterized classes. In cases where no type arguments are available
(e.g., because we're messaging via some unspecialized type, id, etc.),
we substitute in the type bounds for the type parameters instead.
Example:
@interface NSSet<T : id<NSCopying>> : NSObject <NSCopying>
- (T)firstObject;
@end
void f(NSSet<NSString *> *stringSet, NSSet *anySet) {
[stringSet firstObject]; // produces NSString*
[anySet firstObject]; // produces id<NSCopying> (the bound)
}
When substituting for the type parameters given an unspecialized
context (i.e., no specific type arguments were given), substituting
the type bounds unconditionally produces type signatures that are too
strong compared to the pre-generics signatures. Instead, use the
following rule:
- In covariant positions, such as method return types, replace type
parameters with “id” or “Class” (the latter only when the type
parameter bound is “Class” or qualified class, e.g,
“Class<NSCopying>”)
- In other positions (e.g., parameter types), replace type
parameters with their type bounds.
- When a specialized Objective-C object or object pointer type
contains a type parameter in its type arguments (e.g.,
NSArray<T>*, but not NSArray<NSString *> *), replace the entire
object/object pointer type with its unspecialized version (e.g.,
NSArray *).
llvm-svn: 241543
Objective-C type arguments can be provided in angle brackets following
an Objective-C interface type. Syntactically, this is the same
position as one would provide protocol qualifiers (e.g.,
id<NSCopying>), so parse both together and let Sema sort out the
ambiguous cases. This applies both when parsing types and when parsing
the superclass of an Objective-C class, which can now be a specialized
type (e.g., NSMutableArray<T> inherits from NSArray<T>).
Check Objective-C type arguments against the type parameters of the
corresponding class. Verify the length of the type argument list and
that each type argument satisfies the corresponding bound.
Specializations of parameterized Objective-C classes are represented
in the type system as distinct types. Both specialized types (e.g.,
NSArray<NSString *> *) and unspecialized types (NSArray *) are
represented, separately.
llvm-svn: 241542
Produce type parameter declarations for Objective-C type parameters,
and attach lists of type parameters to Objective-C classes,
categories, forward declarations, and extensions as
appropriate. Perform semantic analysis of type bounds for type
parameters, both in isolation and across classes/categories/extensions
to ensure consistency.
Also handle (de-)serialization of Objective-C type parameter lists,
along with sundry other things one must do to add a new declaration to
Clang.
Note that Objective-C type parameters are typedef name declarations,
like typedefs and C++11 type aliases, in support of type erasure.
Part of rdar://problem/6294649.
llvm-svn: 241541
Virtual inheritance member pointers are always relative to the vbindex,
even when the member pointer doesn't point into a virtual base. This is
corrected by adjusting the non-virtual offset backwards from the vbptr
back to the top of the most derived class. While we performed this
adjustment when manifesting member pointers as constants or when
performing conversions, we didn't perform the adjustment when mangling
them.
llvm-svn: 240453
While the rest of the Objective-C metadata seems to honor
objc_runtime_name, the encoding strings produced by, e.g., @encode and
property meta, were not. Fixes rdar://problem/21408305.
llvm-svn: 239852
There are 3 cases of defining static const member:
initialized inside the class, not defined outside the class.
initialized inside the class, defined outside the class.
not initialized inside the class, defined outside the class.
Revision r213304 was supposed to fix the linkage problem of case (1), but mistakenly it made case (2) behave the same.
As a result, out-of-line definition of static data member is not handled correctly.
Proposed patch distinguishes between cases (1) and (2) and allows to properly emit static const members under –fms-compatibility option.
This fixes http://llvm.org/PR21164.
Differential Revision: http://reviews.llvm.org/D9850
llvm-svn: 237787
With this change, enabling -fmodules-local-submodule-visibility results in name
visibility rules being applied to submodules of the current module in addition
to imported modules (that is, names no longer "leak" between submodules of the
same top-level module). This also makes it much safer to textually include a
non-modular library into a module: each submodule that textually includes that
library will get its own "copy" of that library, and so the library becomes
visible no matter which including submodule you import.
llvm-svn: 237473
The GCC construct __attribute__((aligned)) is defined to set alignment
to "the default alignment for the target architecture" according to
the GCC documentation:
The default alignment is sufficient for all scalar types, but may not be
enough for all vector types on a target that supports vector operations.
The default alignment is fixed for a particular target ABI.
clang currently hard-coded an alignment of 16 bytes for that construct,
which is correct on some platforms (including X86), but wrong on others
(including SystemZ). Since this value is ABI-relevant, it is important
to get correct for compatibility purposes.
This patch adds a new TargetInfo member "DefaultAlignForAttributeAligned"
that targets can set to the appropriate default __attribute__((aligned))
value.
Note that I'm deliberately *not* using the existing "SuitableAlign"
value, which is used to set the pre-defined macro __BIGGEST_ALIGNMENT__,
since those two values may not be the same on all platforms. In fact,
on X86, __attribute__((aligned)) always uses 16-byte alignment, while
__BIGGEST_ALIGNMENT__ may be larger if AVX-2 or AVX-512 are supported.
(This is actually not yet correctly implemented in clang either.)
The patch provides a value for DefaultAlignForAttributeAligned only for
SystemZ, and leaves the default for all other targets at 16, which means
no visible change in behavior on all other targets. (The value is still
wrong for some other targets, but I'd prefer to leave it to the target
maintainers for those platforms to fix.)
llvm-svn: 235397
SystemZ prefers to align all global variables to two bytes, which is
implemented by setting the TargetInfo member MinGlobalAlign.
However, for compatibility with existing compilers this should *not*
change the ABI alignment value as retrieved via __alignof__, which
it currently does.
This patch fixes the issue by having ASTContext::getDeclAlign ignore
the MinGlobalAlign setting in the ForAlignof case.
Since SystemZ is the only platform setting MinGlobalAlign, this should
cause no change for any other target.
llvm-svn: 235395
It was documented as 8 and operator new[] defaults to 8, but the normal
operator new was never updated and happily wasted bytes on every other
allocation.
We still have to allocate all Types with 16 byte alignment, update the
allocation calls for Types that were missing explicit alignment.
llvm-svn: 233922
for a DeclContext, and fix propagation of exception specifications along
redeclaration chains.
This reverts r232905, r232907, and r232907, which reverted r232793, r232853,
and r232853.
One additional change is present here to resolve issues with LLDB: distinguish
between whether lexical decls missing from the lookup table are local or are
provided by the external AST source, and still look in the external source if
that's where they came from.
llvm-svn: 232928
When we need to build the lookup table for a DeclContext, we used to pull in
all lexical declarations for the context; instead, just build a lookup table
for the local lexical declarations. We previously didn't guarantee that the
imported declarations would be in the returned map, but in some cases we'd
happen to put them all in there regardless. Now we're even lazier about this.
This unnecessary work was papering over some other bugs:
- LookupVisibleDecls would use the DC for name lookups in the TU in C, and
this was not guaranteed to find all imported names (generally, the DC for
the TU in C is not a reliable place to perform lookups). We now use an
identifier-based lookup mechanism for this.
- We didn't actually load in the list of eagerly-deserialized declarations
when importing a module (so external definitions in a module wouldn't be
emitted by users of those modules unless they happened to be deserialized
by the user of the module).
llvm-svn: 232793
We assumed that the most recent declaration of an inline function would
also be inline. However, a more recent declaration can come from a
friend declaration in a class template that is instantiated at the
definition of the function.
llvm-svn: 232786
std::make_exception_ptr calls std::__GetExceptionInfo in order to figure
out how to properly copy the exception object.
Differential Revision: http://reviews.llvm.org/D8280
llvm-svn: 232188
This adds support for copy-constructor closures. These are generated
when the C++ runtime has to call a copy-constructor with a particular
calling convention or with default arguments substituted in to the call.
Because the runtime has no mechanism to call the function with a
different calling convention or know-how to evaluate the default
arguments at run-time, we create a thunk which will do all the
appropriate work and package it in a way the runtime can use.
Differential Revision: http://reviews.llvm.org/D8225
llvm-svn: 231952
of extern "C" declarations. This is simpler and vastly more efficient for
modules builds (we no longer need to load *all* extern "C" declarations to
determine if we have a redeclaration).
No functionality change intended.
llvm-svn: 231538
Find all unambiguous public classes of the exception object's class type
and reference all of their copy constructors. Yes, this is not
conforming but it is necessary in order to implement their ABI. This is
because the copy constructor is actually referenced by the metadata
describing which catch handlers are eligible to handle the exception
object.
N.B. This doesn't yet handle the copy constructor closure case yet,
that work is ongoing.
Differential Revision: http://reviews.llvm.org/D8101
llvm-svn: 231499
Summary:
Allow user to provide multiple blacklists by passing several
-fsanitize-blacklist= options. These options now don't override
default blacklist from Clang resource directory, which is always
applied (which fixes PR22431).
-fno-sanitize-blacklist option now disables all blacklists that
were specified earlier in the command line (including the default
one).
This change depends on http://reviews.llvm.org/D7367.
Test Plan: regression test suite
Reviewers: timurrrr
Subscribers: cfe-commits, kcc, pcc
Differential Revision: http://reviews.llvm.org/D7368
llvm-svn: 228156
We didn't consider any alignment attributes on an EnumDecl when
calculating alignment.
While we are here, ignore alignment specifications on typedef types if
one is used as the underlying type. Otherwise, weird things happen:
enum Y : int;
Y y;
typedef int __attribute__((aligned(64))) u;
enum Y : u {};
What is the alignment of 'Y'? It would be more consistent with the
overall design of enums with fixed underlying types to consider the
underlying type's UnqualifiedDesugaredType.
This fixes PR22279.
llvm-svn: 226653
The test was fixed after a discussion with the revision author: the check
pattern was made more flexible as the "%call" part is not what we actually want
to check strictly there.
The original patch description:
===
Introduce SPIR calling conventions.
This implements Section 3.7 from the SPIR 1.2 spec:
SPIR kernels should use "spir_kernel" calling convention.
Non-kernel functions use "spir_func" calling convention. All
other calling conventions are disallowed.
The patch works only for OpenCL source. Any other uses will need
to ensure that kernels are assigned the spir_kernel calling
convention correctly.
===
llvm-svn: 226561
This implements Section 3.7 from the SPIR 1.2 spec:
SPIR kernels should use "spir_kernel" calling convention.
Non-kernel functions use "spir_func" calling convention. All
other calling conventions are disallowed.
The patch works only for OpenCL source. Any other uses will need
to ensure that kernels are assigned the spir_kernel calling
convention correctly.
llvm-svn: 226548
Types composed with certain implicit record types would have their RTTI
marked as hidden because the implicit record type didn't have any
visibility.
This manifests itself as triggering false positives from tools like
clang's -fsantize=function feature. The RTTI for a function type's
return type wouldn't match if the return type was an implicit record
type.
Patch by Stephan Bergmann!
llvm-svn: 226148
Also add a few asserts for this. The existing code assumes this in a bunch
of places already (see e.g. the assert at the top of ParseTypedefDecl(), and
there are many unchecked calls on the result of GetTypeForDeclarator()), and
from looking through the code this should always be true from what I can tell.
This allows removing ASTContext::getNullTypeSourceInfo() too as that's now
unused.
No behavior change intended.
llvm-svn: 225125
To support it in the frontend, the following has been added:
- generic address space type attribute;
- documentation for the OpenCL address space attributes;
- parsing of __generic(generic) keyword;
- test code for the parser and diagnostics.
llvm-svn: 222831
For all threadprivate variables which have constructor/destructor emit call to void __kmpc_threadprivate_register(ident_t * <Current Location>, void *<Original Global Addr>, kmpc_ctor <Constructor>, kmpc_cctor NULL, kmpc_dtor <Destructor>);
In expressions all references to such variables are replaced by calls to void *__kmpc_threadprivate_cached(ident_t *<Current Location>, kmp_int32 <Current Thread Id>, void *<Original Global Addr>, size_t <Size of Data>, void ***<Pointer to autogenerated cache – array of private copies of threadprivate variable>);
Test test/OpenMP/threadprivate_codegen.cpp checks that codegen is correct. Also it checks that codegen is correct after serialization/deserialization and one of passes verifies debug info.
Differential Revision: http://reviews.llvm.org/D4002
llvm-svn: 221663
Get rid of ugly SanitizerOptions class thrust into LangOptions:
* Make SanitizeAddressFieldPadding a regular language option,
and rely on default behavior to initialize/reset it.
* Make SanitizerBlacklistFile a regular member LangOptions.
* Introduce the helper class "SanitizerSet" to represent the
set of enabled sanitizers and make it a member of LangOptions.
It is exactly the entity we want to cache and modify in CodeGenFunction,
for instance. We'd also be able to reuse SanitizerSet in
CodeGenOptions for storing the set of recoverable sanitizers,
and in the Driver to represent the set of sanitizers
turned on/off by the commandline flags.
No functionality change.
llvm-svn: 221653
Plumb through the full QualType of the TemplateArgument::Declaration, as
it's insufficient to only know whether the type is a reference or
pointer (that was necessary for mangling, but insufficient for debug
info). This shouldn't increase the size of TemplateArgument as
TemplateArgument::Integer is still longer by another 32 bits.
Several bits of code were testing that the reference-ness of the
parameters matched, but this seemed to be insufficient (various other
features of the type could've mismatched and wouldn't've been caught)
and unnecessary, at least insofar as removing those tests didn't cause
anything to fail.
(Richard - perchaps you can hypothesize why any of these checks might
need to test reference-ness of the parameters (& explain why
reference-ness is part of the mangling - I would've figured that for the
reference-ness to be different, a prior template argument would have to
be different). I'd be happy to add them in/beef them up and add test
cases if there's a reason for them)
llvm-svn: 219900
Soon we'll need to have access to blacklist before the CodeGen
phase (see http://reviews.llvm.org/D5687), so parse and construct
the blacklist earlier.
llvm-svn: 219857
We build a NestedNameSpecifier that records the CXXRecordDecl in which
__super appeared. Name lookup is performed in all base classes of the
recorded CXXRecordDecl. Use of __super is allowed only inside class and
member function scope.
llvm-svn: 218484
we were failing to find that bit-field when performing integer promotions. This
brings us closer to following the standard, and closer to GCC.
In C, this change is technically a regression: we get bit-field promotions
completely wrong in C, promoting cases that are categorically not bit-field
designators. This change makes us do so slightly more consistently, though.
llvm-svn: 218428
FunctionProtoType::ExtProtoInfo. Most of the users of these fields don't care
about the other ExtProtoInfo bits and just want to talk about the exception
specification.
llvm-svn: 214450
Iterator invalidation issues already force us to do one lookup and one
insert.
Don't use the particular bit-pattern of the 'Align' field to determine
whether or not we have already inserted into the TypeInfo DenseMap;
instead ask for an iterator to the TypeInfo entry.
llvm-svn: 214293
The MS ABI has a notion of 'required alignment' for fields; this
alignment supercedes pragma pack directives.
MSVC takes into account alignment attributes on typedefs when
determining whether or not a field has a certain required alignment.
Do the same in clang by tracking whether or not we saw such an attribute
when calculating the type's bitwidth and alignment.
This fixes PR20418.
Reviewers: rnk
Differential Revision: http://reviews.llvm.org/D4714
llvm-svn: 214274
This makes us emit dllexported in-class initialized static data members (which
are treated as definitions in MSVC), even when they're not referenced.
It also makes their special linkage reflected in the GVA linkage instead of
getting massaged in CodeGen.
Differential Revision: http://reviews.llvm.org/D4563
llvm-svn: 213304
Summary:
Do not store duplicate parents when memoization data is available.
This does not solve the duplication problem, but ameliorates it.
Reviewers: klimek
Subscribers: klimek, cfe-commits
Differential Revision: http://reviews.llvm.org/D4124
llvm-svn: 210902
The backing store of thread local variables is internal for OS X and all
accesses must go through the thread wrapper.
However, individual TUs may have inlined through the thread wrapper.
To fix this, give the thread wrapper functions WeakAnyLinkage. This
prevents them from getting inlined into call-sites.
This fixes PR19989.
llvm-svn: 210632
expression of array-of-unknown-bound type, don't try to complete the array
bound, and return the alignment of the element type rather than 1.
llvm-svn: 210608
MSVC delays parsing of default arguments until instantiation. If the
default argument is never used, it is never parsed. We don't model
this.
Instead, if lookup of a type name fails in a template argument context,
we form a DependentNameType, which will be looked up at instantiation
time.
This fixes errors about 'CControlWinTraits' in atlwin.h.
Reviewers: rsmith
Differential Revision: http://reviews.llvm.org/D3995
llvm-svn: 210382
On test files I ran this on, memory consumption overall went down from
2.5G to 2G, without performance regressions.
I also investigated making DynTypedNode by itself smaller (by pulling
out pointers for everything that doesn't fit in 8 bytes). This led to
another 200-300MB saved, but also introduced a significant regression in
performance due to the memory management overhead.
llvm-svn: 209297
ensure that querying the first declaration for its most recent declaration
checks for redeclarations from the imported module.
This works as follows:
* The 'most recent' pointer on a canonical declaration grows a pointer to the
external AST source and a generation number (space- and time-optimized for
the case where there is no external source).
* Each time the 'most recent' pointer is queried, if it has an external source,
we check whether it's up to date, and update it if not.
* The ancillary data stored on the canonical declaration is allocated lazily
to avoid filling it in for declarations that end up being non-canonical.
We'll still perform a redundant (ASTContext) allocation if someone asks for
the most recent declaration from a decl before setPreviousDecl is called,
but such cases are probably all bugs, and are now easy to find.
Some finessing is still in order here -- in particular, we use a very general
mechanism for handling the DefinitionData pointer on CXXRecordData, and a more
targeted approach would be more compact.
Also, the MayHaveOutOfDateDef mechanism should now be expunged, since it was
addressing only a corner of the full problem space here. That's not covered
by this patch.
Early performance benchmarks show that this makes no measurable difference to
Clang performance without modules enabled (and fixes a major correctness issue
with modules enabled). I'll revert if a full performance comparison shows any
problems.
llvm-svn: 209046
GetGVALinkageForFunction handles TSK_ExplicitInstantiationDeclaration
twice, remove the redundant code trying to handle it again.
While we are here, update the reference we make to the standard. It
seems like another paragraph was added causing this text to get
renumbered.
llvm-svn: 208850
Having various possible states of initialization following construction doesn't
add value here.
Also remove the unused size_reserve parameter.
llvm-svn: 207897
Summary:
A reference temporary should inherit the linkage of the variable it
initializes. Otherwise, we may hit cases where a reference temporary
wouldn't have the same value in all translation units.
Reviewers: rsmith
Subscribers: cfe-commits
Differential Revision: http://reviews.llvm.org/D3515
llvm-svn: 207451
When instantiating an array that has an alignment attribute on it, we
were looking through the array type and only considering the element
type for the resulting alignment. We need to make sure we take the
array's requirements into account too.
llvm-svn: 206317
Summary:
MSVC always emits inline functions marked with the extern storage class
specifier. The result is something similar to the opposite of
__attribute__((gnu_inline)).
This extension is also available in C.
This fixes PR19264.
Reviewers: rnk, rsmith
CC: cfe-commits
Differential Revision: http://llvm-reviews.chandlerc.com/D3207
llvm-svn: 205485
This adds Clang support for the ARM64 backend. There are definitely
still some rough edges, so please bring up any issues you see with
this patch.
As with the LLVM commit though, we think it'll be more useful for
merging with AArch64 from within the tree.
llvm-svn: 205100
correctly order comments in SourceManager::isBeforeInTranslationUnit() order
Unfortunately, this is not as simple as it was implemented previously, and
actually requires doing a merge sort.
llvm-svn: 204936
Summary:
The MSVC ABI appears to mangle the lexical scope into the names of
statics. Specifically, a counter is incremented whenever a scope is
entered where things can be declared in such a way that an ambiguity can
arise. For example, a class scope inside of a class scope doesn't do
anything interesting because the nested class cannot collide with
another nested class.
There are problems with this scheme:
- It is unreliable. The counter is only incremented when a previously
never encountered scope is entered. There are cases where this will
cause ambiguity amongst declarations that have the same name where one
was introduced in a deep scope while the other was introduced right
after in the previous lexical scope.
- It is wasteful. Statements like: {{{{{{{ static int foo = a; }}}}}}}
will make the mangling of "foo" larger than it need be because the
scope counter has been incremented many times.
Because of these problems, and practical implementation concerns. We
choose not to implement this scheme if the local static or local type
isn't visible. The mangling of these declarations will look very
similar but the numbering will make far more sense, this scheme is
lifted from the Itanium ABI implementation.
Reviewers: rsmith, doug.gregor, rnk, eli.friedman, cdavis5x
Reviewed By: rnk
CC: cfe-commits
Differential Revision: http://llvm-reviews.chandlerc.com/D2953
llvm-svn: 202951
With r197755 we started reading the contents of buffer file entries, but the
buffers may point to ASTReader blobs that have been disposed.
Fix this by having the CompilerInstance object keep a reference to the ASTReader
as well as having the ASTContext keep reference to the ExternalASTSource.
This was very difficult to construct a test case for.
rdar://16149782
llvm-svn: 202346
When calculating the preferred alignment of a type, consider if a alignment
attribute came from a typedef declaration. If one did, do not naturally align
the type.
Patch by Stephan Tolksdorf, with a little tweaking and an additional testcase by me.
llvm-svn: 202088
Most 64-bit targets define int64_t as long int, and AArch64 should
make same definition to follow LP64 model. In GNU tool chain, int64_t
is defined as long int for 64-bit target. So to get consistent with GNU,
it's better Changing int64_t from 'long long int' to 'long int',
otherwise clang will get different name mangling suffix compared with g++.
llvm-svn: 202004
Member pointers are mangled as they would be represented at runtime.
They can be a single integer literal, single decl, or a tuple with some
more numbers tossed in. With Clang today, most of those numbers will be
zero because we reject pointers to members of virtual bases.
This change required moving VTableContextBase ownership from
CodeGenVTables to ASTContext, because mangling now depends on vtable
layout.
I also hoisted the inheritance model helpers up to be inline static
methods of MSInheritanceAttr. This makes the AST code that deals with
member pointers much more readable.
MSVC doesn't appear to have stable manglings of null member pointers:
- Null data memptrs in function templates have a mangling collision with
the first field of a non-polymorphic single inheritance class.
- The mangling of null data memptrs changes if you add casts.
- Large null function memptrs in class templates crash MSVC.
Clang uses the class template mangling for null data memptrs and the
function template mangling for null function memptrs to deal with this.
Reviewers: majnemer
Differential Revision: http://llvm-reviews.chandlerc.com/D2695
llvm-svn: 200857
A return type is the declared or deduced part of the function type specified in
the declaration.
A result type is the (potentially adjusted) type of the value of an expression
that calls the function.
Rule of thumb:
* Declarations have return types and parameters.
* Expressions have result types and arguments.
llvm-svn: 200082
not using backing ivar warning, ignore when
property is not being synthesized (user declared its
implementation @dynamic). // rdar://1583425
llvm-svn: 199820
Fix a perennial source of confusion in the clang type system: Declarations and
function prototypes have parameters to which arguments are supplied, so calling
these 'arguments' was a stretch even in C mode, let alone C++ where default
arguments, templates and overloading make the distinction important to get
right.
Readability win across the board, especially in the casting, ADL and
overloading implementations which make a lot more sense at a glance now.
Will keep an eye on the builders and update dependent projects shortly.
No functional change.
llvm-svn: 199686
There's been long-standing confusion over the role of these two options. This
commit makes the necessary changes to differentiate them clearly, following up
from r198936.
MicrosoftExt (aka. fms-extensions):
Enable largely unobjectionable Microsoft language extensions to ease
portability. This mode, also supported by gcc, is used for building software
like FreeBSD and Linux kernel extensions that share code with Windows drivers.
MSVCCompat (aka. -fms-compatibility, formerly MicrosoftMode):
Turn on a special mode supporting 'heinous' extensions for drop-in
compatibility with the Microsoft Visual C++ product. Standards-compilant C and
C++ code isn't guaranteed to work in this mode. Implies MicrosoftExt.
Note that full -fms-compatibility mode is currently enabled by default on the
Windows target, which may need tuning to serve as a reasonable default.
See cfe-commits for the full discourse, thread 'r198497 - Move MS predefined
type_info out of InitializePredefinedMacros'
No change in behaviour.
llvm-svn: 199209
__builtin_va_list and friends have been showing up where they shouldn't for way
to long, making unwanted appearences in -ast-print, tooling and source level
visitors and even the hello world tutorial on the clang website.
This commit factors down the implicit typedef and record creation facilities to
ensure they're marked implicit.
Also fixes a unit test that was testing incorrect behaviour, and removes old
hacks in the DeclPrinter that tried to skip implicit declarations manually.
llvm-svn: 197336
Summary:
In general, this type node can be used to represent any type adjustment
that occurs implicitly without losing type sugar. The immediate use of
this is to adjust the calling conventions of member function pointer
types without breaking template instantiation.
Fixes PR17996.
Reviewers: rsmith
Differential Revision: http://llvm-reviews.chandlerc.com/D2332
llvm-svn: 196451
The xcore llvm backend does not handle 8 byte alignment viz:
"%BadAlignment = alloca i64, align 8"
So getPreferredTypeAlign() must never overalign.
llvm-svn: 194462
Differential Revision: http://llvm-reviews.chandlerc.com/D2090
Clang was "improperly" over-aligning arrays with sizes are not a multiple of
their alignment.
This behavior was removed in microsoft 32 bit mode.
In addition, after examination of ASTContext::getTypeInfoImpl, a redundant code block in
MicrosoftRecordLayoutBuilder::getAdjustedFieldInfo was deleted.
llvm-svn: 193898
address spaces which is both (1) a "semantic" concept and
(2) possibly a hardware level restriction. It is desirable to
be able to discard/merge the LLVM-level address spaces on arguments for which
there is no difference to the current backend while keeping
track of the semantic address spaces in a funciton prototype. To do this
enable addition of the address space into the name-mangling process. Add
some tests to document this behaviour against inadvertent changes.
Patch by Michele Scandale!
llvm-svn: 190684
Static locals requiring initialization are not thread safe on Windows.
Unfortunately, it's possible to create static locals that are actually
externally visible with inline functions and templates. As a result, we
have to implement an initialization guard scheme that is compatible with
TUs built by MSVC, which makes thread safety prohibitively difficult.
MSVC's scheme is that every function that requires a guard gets an i32
bitfield. Each static local is assigned a bit that indicates if it has
been initialized, up to 32 bits, at which point a new bitfield is
created. MSVC rejects inline functions with more than 32 static locals,
and the externally visible mangling (?_B) only allows for one guard
variable per function.
On Eli's recommendation, I used MangleNumberingContext to track which
bit each static corresponds to.
Implements PR16888.
Reviewers: rjmccall, eli.friedman
Differential Revision: http://llvm-reviews.chandlerc.com/D1416
llvm-svn: 190427
getRealTypeByWidth and getIntTypeByWidth
for ASTContext names are almost same(invokes new methods from TargetInfo):
getIntTypeForBitwidth and getRealTypeForBitwidth.
As first commit for PR16752 fix: 'mode' attribute for unusual targets doesn't work properly
Description:
Troubles could be happened due to some assumptions in handleModeAttr function (see SemaDeclAttr.cpp).
For example, it assumes that 32 bit integer is 'int', while it could be 16 bit only.
Instead of asking target: 'which type do you want to use for int32_t ?' it just hardcodes general opinion. That doesn't looks pretty correct.
Please consider the next solution:
1. In Basic/TargetInfo add getIntTypeByWidth and getRealTypeByWidth virtual methods. By default current behaviour could be implemented here.
2. Fix handleModeAttr according to new methods in TargetInfo.
This approach is implemented in the patch attached to this post.
Fixes:
1st Commit (Current): Add new methods for TargetInfo:
getRealTypeByWidth and getIntTypeByWidth
for ASTContext names are almost same(invokes new methods from TargetInfo):
getIntTypeForBitwidth and getRealTypeForBitwidth
2nd Commit (Next): Fix SemaDeclAttr, handleModeAttr function.
llvm-svn: 190044
Summary:
Makes functions with implicit calling convention compatible with
function types with a matching explicit calling convention. This fixes
things like calls to qsort(), which has an explicit __cdecl attribute on
the comparator in Windows headers.
Clang will now infer the calling convention from the declarator. There
are two cases when the CC must be adjusted during redeclaration:
1. When defining a non-inline static method.
2. When redeclaring a function with an implicit or mismatched
convention.
Fixes PR13457, and allows clang to compile CommandLine.cpp for the
Microsoft C++ ABI.
Excellent test cases provided by Alexander Zinenko!
Reviewers: rsmith
Differential Revision: http://llvm-reviews.chandlerc.com/D1231
llvm-svn: 189412
Specifically, the following features are not included in this commit:
- any sort of capturing within generic lambdas
- nested lambdas
- conversion operator for captureless lambdas
- ensuring all visitors are generic lambda aware
As an example of what compiles:
template <class F1, class F2>
struct overload : F1, F2 {
using F1::operator();
using F2::operator();
overload(F1 f1, F2 f2) : F1(f1), F2(f2) { }
};
auto Recursive = [](auto Self, auto h, auto ... rest) {
return 1 + Self(Self, rest...);
};
auto Base = [](auto Self, auto h) {
return 1;
};
overload<decltype(Base), decltype(Recursive)> O(Base, Recursive);
int num_params = O(O, 5, 3, "abc", 3.14, 'a');
Please see attached tests for more examples.
Some implementation notes:
- Add a new Declarator context => LambdaExprParameterContext to
clang::Declarator to allow the use of 'auto' in declaring generic
lambda parameters
- Augment AutoType's constructor (similar to how variadic
template-type-parameters ala TemplateTypeParmDecl are implemented) to
accept an IsParameterPack to encode a generic lambda parameter pack.
- Add various helpers to CXXRecordDecl to facilitate identifying
and querying a closure class
- LambdaScopeInfo (which maintains the current lambda's Sema state)
was augmented to house the current depth of the template being
parsed (id est the Parser calls Sema::RecordParsingTemplateParameterDepth)
so that Sema::ActOnLambdaAutoParameter may use it to create the
appropriate list of corresponding TemplateTypeParmDecl for each
auto parameter identified within the generic lambda (also stored
within the current LambdaScopeInfo). Additionally,
a TemplateParameterList data-member was added to hold the invented
TemplateParameterList AST node which will be much more useful
once we teach TreeTransform how to transform generic lambdas.
- SemaLambda.h was added to hold some common lambda utility
functions (this file is likely to grow ...)
- Teach Sema::ActOnStartOfFunctionDef to check whether it
is being called to instantiate a generic lambda's call
operator, and if so, push an appropriately prepared
LambdaScopeInfo object on the stack.
- Teach Sema::ActOnStartOfLambdaDefinition to set the
return type of a lambda without a trailing return type
to 'auto' in C++1y mode, and teach the return type
deduction machinery in SemaStmt.cpp to process either
C++11 and C++14 lambda's correctly depending on the flag.
- various tests were added - but much more will be needed.
A greatful thanks to all reviewers including Eli Friedman,
James Dennett and the ever illuminating Richard Smith. And
yet I am certain that I have allowed unidentified bugs to creep in;
bugs, that I will do my best to slay, once identified!
Thanks!
llvm-svn: 188977
Add support for half (a.k.a. __fp16) in builtin descriptions.
The second argument to BUILTIN() now accepts 'h' to represent half.
Patch by Daniel Sanders
llvm-svn: 188464
We were exposing the extra alignment given to large arrays. The new behavior
matches gcc, which is a good thing since this is a gcc extension.
Thanks to Joerg Sonnenberger for noticing it.
While at it, centralize the method description in the .h file.
llvm-svn: 187999
Before this patch we would align
long long int big[1024];
to 4 bytes on 32 bit systems. The problem is that we were only looking
at the element type when getLargeArrayMinWidth returned non zero.
llvm-svn: 187897
via a macro, try using declaration's starting location.
This is improvement over not having a valid location and
dropping comment altogether. // rdar://14348912
llvm-svn: 187085
Compute mangling numbers for externally visible local variables and tags.
Change the mangler to consistently use discriminators where necessary.
Tweak the scheme we use to number decls which are not externally visible
to avoid unnecessary discriminators in common cases now that we request
them more consistently.
Fixes <rdar://problem/14204721>.
llvm-svn: 185986
Blocks, like lambdas, can be written in contexts which are required to be
treated as the same under ODR. Unlike lambdas, it isn't possible to actually
take the address of a block, so the mangling of the block itself doesn't
matter. However, objects like static variables inside a block do need to
be mangled in a consistent way.
There are basically three components here. One, block literals need a
consistent numbering. Two, objects/types inside a block literal need
to be mangled using it. Three, objects/types inside a block literal need
to have their linkage computed correctly.
llvm-svn: 185372
The old implementation of ms_struct in RecordLayoutBuilder was a
complete mess: it depended on complicated conditionals which didn't
really reflect the underlying logic, and placed a burden on users of
the resulting RecordLayout. This commit rips out almost all of the
old code, and replaces it with simple checks in
RecordLayoutBuilder::LayoutBitField.
This commit also fixes <rdar://problem/14252115>, a bug where class
inheritance would cause us to lay out bitfields incorrectly.
llvm-svn: 185018
When the decl that we're getting alignment for is a FieldDecl, and the field's
parent record is invalid, skip the actual field alignment calculation (and
return 1-byte alignment in the general case).
Also, assert in in getASTRecordLayout that the decl is valid. This was
inspired by PR16292; see also r184581 and r184751.
llvm-svn: 184883
The goal of this sugar node is to be able to look at an arbitrary
FunctionType and tell if any of the parameters were decayed from an
array or function type. Ultimately this is necessary to implement
Microsoft's C++ name mangling scheme, which mangles decayed arrays
differently from normal pointers.
Reviewers: rsmith
Differential Revision: http://llvm-reviews.chandlerc.com/D1014
llvm-svn: 184763
The untemplated implementation of getParents() doesn't need to be in a
header file.
RecursiveASTVisitor.h is full of repeated macro expansion. Moving this
include to ASTContext.cpp speeds up compilation of
LambdaMangleContext.cpp, a small C++ file with few includes, from 3.7s
to 2.8s for me locally. I haven't measured a full build, but it can't
hurt.
I had to fix a few static analyzer files that were depending on
transitive includes of C++ AST headers.
Reviewers: rsmith, klimek
Differential Revision: http://llvm-reviews.chandlerc.com/D982
llvm-svn: 184075
This helps preserve the type-as-written in the AST, which we need for
MSVC mangling. In particular, we need to preserve the types of array
parameters in function pointer types.
The essence of this change is:
- QualType ArgTy = Param->getType();
+ QualType ArgTy = Param->getTypeSourceInfo()->getType();
... followed by the adjustment in ActOnFunctionDeclarator().
Differential Revision: http://llvm-reviews.chandlerc.com/D883
llvm-svn: 183614
handle temporaries which have been lifetime-extended to static storage duration
within constant expressions. This correctly handles nested lifetime extension
(through reference members of aggregates in aggregate initializers) but
non-constant-expression emission hasn't yet been updated to do the same.
llvm-svn: 183283
This patch ensures that APValues are deallocated with the ASTContext by
registering a deallocation function for APValues to the ASTContext.
Original version of the patch by James Dennett.
llvm-svn: 183101
David Majnemer