function parameter packs.
This makes our handling of non-trailing function parameter packs
consistent between the case of deduction at the top level in a function
call and other cases where deduction encounters a non-trailing function
parameter pack.
Instead of treating a non-trailing pack and all later parameters as
being non-deduced, we treat a non-trailing pack as exactly matching
any explicitly-specified template arguments (or being an empty pack
if there are no such arguments). This corresponds to the "never deduced"
rule in [temp.deduct.call]p1, but generalized to all deduction contexts.
Non-trailing template argument packs still result in the entire
template argument list being treated as non-deduced, as specified in
[temp.deduct.type]p9.
llvm-svn: 336962
This diagnostic triggers when -fsanitize=object-size is explicitly
specified but will be a no-op (i.e, at -O0).
This diagnostic should not fail a -Werror build because it's just an
explanatory note to the user. It's not always actionable.
For example, a user may not be able to simply disable object-size,
because they want it enabled in optimized builds.
rdar://42128447
llvm-svn: 336937
types.
We previously tried to use the "parameter is a reference" logic here,
but that doesn't work because it gets P and A backwards. Instead, add
a separate implementation of the "deduced A can be less qualified than
A" rule.
This also exposes that we incorrectly stripped cv-qualifiers from the
referent of A if it was a reference. However, if we don't do that, we
get the wrong results when P is a reference. In an attempt to match
what sanity dictates and what other implementations are doing, we now
remove cv-qualifiers from A and P unless both are reference types. I've
brought this up on the core reflector too, to try to get the standard
fixed.
llvm-svn: 336867
string, choose the strictest one instead of the last.
Also fix an undefined behavior. Move the pointer update to a later point to
avoid adding StringRef::npos to the pointer.
rdar://problem/40706280
llvm-svn: 336863
with another in template argument deduction.
We happened to typically get away with getting this wrong, because the
cases where we'd produce a bogus deduction were caught by the final
"deduced A is compatible with A" check.
llvm-svn: 336852
Code in `CodeGenModule::SetFunctionAttributes()` could set an empty
attribute `implicit-section-name` on a function that is affected by
`#pragma clang text="section"`. This is incorrect because the attribute
should contain a valid section name. If the function additionally also
used `__attribute__((section("section")))` then this could result in
emitting the function in a section with an empty name.
The patch fixes the issue by removing the problematic code that sets
empty `implicit-section-name` from
`CodeGenModule::SetFunctionAttributes()` because it is sufficient to set
this attribute only from a similar code in `setNonAliasAttributes()`
when the function is emitted.
Differential Revision: https://reviews.llvm.org/D48916
llvm-svn: 336842
Previously, the checker only tracked one raw pointer symbol for each
container object. But member functions returning a pointer to the
object's inner buffer may be called on the object several times. These
pointer symbols are now collected in a set inside the program state map
and thus all of them is checked for use-after-free problems.
Differential Revision: https://reviews.llvm.org/D49057
llvm-svn: 336835
Summary:
A forward-declared coroutine_traits should trip an error; we need
a complete type.
Unfortunately, in debug mode only, we trip an assert when attempting
to provide the fully qualified type for the error message.
If you try to compile a program with a forward-declared
coroutine_traits in debug mode, clang will crash.
I've included a test for the behavior and removed the q modifier
on the error message. This prevents the crash in debug mode and
does not change the behavior for the error message on a
forward-declaration of a coroutine_traits type.
Test Plan:
I've included a test for the forward-declaration.
Patch by Tanoy Sinha!
Reviewers: modocache, GorNishanov
Reviewed By: modocache
Subscribers: cfe-commits
Differential Revision: https://reviews.llvm.org/D49099
llvm-svn: 336748
This allows more qualification conversions, eg. conversion from
'int *(*)[]' -> 'const int *const (*)[]'
is now permitted, along with all the consequences of that: more types
are similar, more cases are permitted by const_cast, and conversely,
fewer "casting away constness" cases are permitted by reinterpret_cast.
llvm-svn: 336745
The "casts away constness" check doesn't care at all how the different
layers of the source and destination type were formed: for example, if
the source is a pointer and the destination is a pointer-to-member, the
types are still decomposed and their pointee qualifications are still
checked.
This rule is bizarre and somewhat ridiculous, so as an extension we
accept code making use of such reinterpret_casts with a warning outside
of SFINAE contexts.
llvm-svn: 336738
The member init list for the sole constructor for CodeGenFunction
has gotten out of hand, so this patch moves the non-parameter-dependent
initializations into the member value inits.
llvm-svn: 336726
Summary:
Make sure that loop metadata only is put on the backedge
when expanding a do-while loop.
Previously we added the loop metadata also on the branch
in the pre-header. That could confuse optimization passes
and result in the loop metadata being associated with the
wrong loop.
Fixes https://bugs.llvm.org/show_bug.cgi?id=38011
Committing on behalf of deepak2427 (Deepak Panickal)
Reviewers: #clang, ABataev, hfinkel, aaron.ballman, bjope
Reviewed By: bjope
Subscribers: bjope, rsmith, shenhan, zzheng, xbolva00, lebedev.ri, cfe-commits
Tags: #clang
Differential Revision: https://reviews.llvm.org/D48721
llvm-svn: 336717
Use getTriple.isMIPS64() to detect 64-bit MIPS ABIs in
FreeBSD::getSupportedSanitizers() instead of getTriple.isMIPS32().
Reviewed By: atanasyan
Differential Revision: https://reviews.llvm.org/D49143
llvm-svn: 336710
is useful to omit the debug compilation dir when compiling assembly
files with -g. Part of PR38050.
Patch by Siddhartha Bagaria!
Differential Revision: https://reviews.llvm.org/D48989
llvm-svn: 336685
Summary:
Reproducer and errors:
https://bugs.llvm.org/show_bug.cgi?id=37878
lookupModule was falling back to loadSubdirectoryModuleMaps when it couldn't
find ModuleName in (proper) search paths. This was causing iteration over all
files in the search path subdirectories for example "/usr/include/foobar" in
bugzilla case.
Users don't expect Clang to load modulemaps in subdirectories implicitly, and
also the disk access is not cheap.
if (AllowExtraModuleMapSearch) true with ObjC with @import ModuleName.
Reviewers: rsmith, aprantl, bruno
Subscribers: cfe-commits, teemperor, v.g.vassilev
Differential Revision: https://reviews.llvm.org/D48367
llvm-svn: 336660
In this setup, skip adding all the default windows import libraries,
if linking to windowsapp (which replaces them, when targeting the
windows store/UWP api subset).
With GCC, the same is achieved by using a custom spec file, but
since clang doesn't use spec files, we have to allow other means of
overriding what default libraries to use (without going all the
way to using -nostdlib, which would exclude everything). The same
approach, in detecting certain user specified libraries and omitting
others from the defaults, was already used in SVN r314138.
Differential Revision: https://reviews.llvm.org/D49059
llvm-svn: 336655
Since SVN r314138, we check if the user has specified any particular
alternative msvcrt/ucrt version, and skip the default -lmsvcrt
in those cases.
In addition to the existing names checked, we should also treat
a plain -lucrt in the same way, mingw-w64 has now added a separate
import library named libucrt.a, in addition to libucrtbase.a.
Differential Revision: https://reviews.llvm.org/D49054
llvm-svn: 336654
This patch lowers the _mm[256|512]_cvtepi{64|32|16}_epi{32|16|8} intrinsics to
native IR in cases where the result's length is less than 128 bits.
The resulting IR for 256-bit inputs is folded into VPMOV instructions, while for
128-bit inputs the vpshufb (or, in the 64-to-32-bit case, vinsertps)
instructions are generated instead
Differential Revision: https://reviews.llvm.org/D48712
llvm-svn: 336643
The rounding mode is checked in CGBuiltin.cpp to generate the correct intrinsic call.
Making this switch switchs the masking to use the i8 bitcast to <8 x i1> and extract i1 version of the IR for the mask. Previously we ended up with a scalar 'and' plus an icmp.
llvm-svn: 336637
BindingDecls have null type until their initializer is processed, so we can't
assume that a correction candidate has non-null type.
rdar://41559582
llvm-svn: 336634
Functions that are a sub-Decl of a record were hashed differently than other
functions. This change keeps the AddFunctionDecl function and the hash of
records now calls this function. In addition, AddFunctionDecl has an option
to perform a hash as if the body was absent, which is required for some
checks after loading modules. Additional logic prevents multiple error
message from being printed.
llvm-svn: 336632
Privacy annotations shouldn't have to appear in the first
comma-delimited string in order to be recognized. Also, they should be
ignored if they are preceded or followed by non-whitespace characters.
rdar://problem/40706280
llvm-svn: 336629
This will convert the i8 mask argument to <8 x i1> and extract an i1 and then emit a select instruction. This replaces the '(__U & 1)" and ternary operator used in some of intrinsics. The old sequence was lowered to a scalar and and compare. The new sequence uses an i1 vector that will interoperate better with other mask intrinsics.
This removes the need to handle div_ss/sd specially in CGBuiltin.cpp. A follow up patch will add the GCCBuiltin name back in llvm and remove the custom handling.
I made some adjustments to legacy move_ss/sd intrinsics which we reused here to do a simpler extract and insert instead of 2 extracts and two inserts or a shuffle.
llvm-svn: 336622
Summary:
New flag causes crash reports to be written in the specified directory
rather than the temp directory.
Patch by Chijioke Kamanu.
Reviewers: hans, inglorion, rnk
Reviewed By: hans
Subscribers: zturner, hiraditya, llvm-commits, cfe-commits
Differential Revision: https://reviews.llvm.org/D48601
llvm-svn: 336604
When the parsing of the functions happens inside of the declare target
region, we may erroneously mark local variables as declare target
thought they are not. This attribute can be applied only to global
variables.
llvm-svn: 336592
This is part of an ongoing attempt at making 512 bit vectors illegal in the X86 backend type legalizer due to CPU frequency penalties associated with wide vectors on Skylake Server CPUs. We want the loop vectorizer to be able to emit IR containing wide vectors as intermediate operations in vectorized code and allow these wide vectors to be legalized to 256 bits by the X86 backend even though we are targetting a CPU that supports 512 bit vectors. This is similar to what happens with an AVX2 CPU, the vectorizer can emit wide vectors and the backend will split them. We want this splitting behavior, but still be able to use new Skylake instructions that work on 256-bit vectors and support things like masking and gather/scatter.
Of course if the user uses explicit vector code in their source code we need to not split those operations. Especially if they have used any of the 512-bit vector intrinsics from immintrin.h. And we need to make it so that merely using the intrinsics produces the expected code in order to be backwards compatible.
To support this goal, this patch adds a new IR function attribute "min-legal-vector-width" that can indicate the need for a minimum vector width to be legal in the backend. We need to ensure this attribute is set to the largest vector width needed by any intrinsics from immintrin.h that the function uses. The inliner will be reponsible for merging this attribute when a function is inlined. We may also need a way to limit inlining in the future as well, but we can discuss that in the future.
To make things more complicated, there are two different ways intrinsics are implemented in immintrin.h. Either as an always_inline function containing calls to builtins(can be target specific or target independent) or vector extension code. Or as a macro wrapper around a taget specific builtin. I believe I've removed all cases where the macro was around a target independent builtin.
To support the always_inline function case this patch adds attribute((min_vector_width(128))) that can be used to tag these functions with their vector width. All x86 intrinsic functions that operate on vectors have been tagged with this attribute.
To support the macro case, all x86 specific builtins have also been tagged with the vector width that they require. Use of any builtin with this property will implicitly increase the min_vector_width of the function that calls it. I've done this as a new property in the attribute string for the builtin rather than basing it on the type string so that we can opt into it on a per builtin basis and avoid any impact to target independent builtins.
There will be future work to support vectors passed as function arguments and supporting inline assembly. And whatever else we can find that isn't covered by this patch.
Special thanks to Chandler who suggested this direction and reviewed a preview version of this patch. And thanks to Eric Christopher who has had many conversations with me about this issue.
Differential Revision: https://reviews.llvm.org/D48617
llvm-svn: 336583
Add a number of builtins for __float128 Round To Odd.
This is the Clang portion of the builtins work.
Differential Revision: https://reviews.llvm.org/D47548
llvm-svn: 336579
In generic data-sharing mode we are allowed to not globalize local
variables that escape their declaration context iff they are declared
inside of the parallel region. We can do this because L2 parallel
regions are executed sequentially and, thus, we do not need to put
shared local variables in the global memory.
llvm-svn: 336567
Kristof Umann