Pointers of certain GPUs in AMDGCN target in private address space is 32 bit but pointers in other address spaces are 64 bit. size_t type should be defined as 64 bit for these GPUs so that it could hold pointers in all address spaces. Also fixed issues in pointer arithmetic codegen by using pointer specific intptr type.
Differential Revision: https://reviews.llvm.org/D23361
llvm-svn: 279121
This reverts commit r279003 as it breaks some of our buildbots (e.g.
clang-cmake-aarch64-quick, clang-x86_64-linux-selfhost-modules).
The error is in OpenMP/teams_distribute_simd_ast_print.cpp:
clang: /home/buildslave/buildslave/clang-cmake-aarch64-quick/llvm/include/llvm/ADT/DenseMap.h:527:
bool llvm::DenseMapBase<DerivedT, KeyT, ValueT, KeyInfoT, BucketT>::LookupBucketFor(const LookupKeyT&, const BucketT*&) const
[with LookupKeyT = clang::Stmt*; DerivedT = llvm::DenseMap<clang::Stmt*, long unsigned int>;
KeyT = clang::Stmt*; ValueT = long unsigned int;
KeyInfoT = llvm::DenseMapInfo<clang::Stmt*>;
BucketT = llvm::detail::DenseMapPair<clang::Stmt*, long unsigned int>]:
Assertion `!KeyInfoT::isEqual(Val, EmptyKey) && !KeyInfoT::isEqual(Val, TombstoneKey) &&
"Empty/Tombstone value shouldn't be inserted into map!"' failed.
llvm-svn: 279045
This patch is to implement sema and parsing for 'teams distribute simd’ pragma.
This patch is originated by Carlo Bertolli.
Differential Revision: https://reviews.llvm.org/D23528
llvm-svn: 279003
The previous condition would erroneously mark all CXXRecordDecls
that didn't have any fields as being defined in a clang module.
This patch fixes the condition to only apply to explicit template
instantiations.
<rdar://problem/27771823>
llvm-svn: 278952
This affects functions with the C++11 [[ noreturn ]] and C11 _Noreturn
specifiers.
Patch by Victor Leschuk!
https://reviews.llvm.org/D23168
llvm-svn: 278942
Use BB.getNextNode(), which returns nullptr on end(), instead of
&*BB.getIterator(), which is UB on end().
CodeGenFunction::createBasicBlock expects nullptr in this case already.
llvm-svn: 278898
With -debug-info-kind=limited, we omit debug info for dynamic classes that live in other TUs. This reduces duplicate type information. When statically linked, the type information comes together. But if your binary has a class derived from a base in a DLL, the base class info is not available to the debugger.
The decision is made in shouldOmitDefinition (CGDebugInfo.cpp). Per a suggestion from rnk, I've tweaked the decision so that we do include definitions for classes marked as DLL imports. This should be a relatively small number of classes, so we don't pay a large price for duplication of the type info, yet it should cover most cases on Windows.
Essentially this makes debug info for DLLs independent, but we still assume that all TUs within the same DLL will be consistently built with (or without) debug info and the debugger will be able to search across the debug info within that scope to resolve any declarations into definitions, etc.
llvm-svn: 278861
Summary:
This patch lets you create diagnostics that are emitted if and only if a
particular FunctionDecl is codegen'ed.
This is necessary for CUDA, where some constructs -- e.g. calls from
host+device functions to host functions when compiling for device -- are
allowed to appear in semantically-correct programs, but only if they're
never codegen'ed.
Reviewers: rnk
Subscribers: cfe-commits, tra
Differential Revision: https://reviews.llvm.org/D23241
llvm-svn: 278735
We processed unnamed bitfields after our logic for non-vector field
elements in records larger than 128 bits. The vector logic would
determine that the bit-field disqualifies the record from occupying a
register despite the unnamed bit-field not participating in the record
size nor its alignment.
N.B. This behavior matches GCC and ICC.
llvm-svn: 278656
An __m512 vector type wrapped in a structure should be passed in a
vector register.
Our prior implementation was based on a draft version of the psABI.
This fixes PR28975.
N.B. The update to the ABI was made here:
https://github.com/hjl-tools/x86-psABI/commit/30f9c9
llvm-svn: 278655
This matches the way nvcc encapsulates GPU binaries into host object file.
Now cuobjdump can deal with clang-compiled object files.
Differential Revision: https://reviews.llvm.org/D23429
llvm-svn: 278549
Summary:
This changes clang to use the llvm::lto::thinBackend function instead of
its own less comprehensive ThinLTO backend implementation.
Patch by Peter Collingbourne
Reviewers: tejohnson, mehdi_amini
Subscribers: cfe-commits, mehdi_amini
Differential Revision: https://reviews.llvm.org/D21545
llvm-svn: 278541
constraints were added to _mm256_broadcast_{pd,ps} intel intrinsics.
The spec for these intrinics is ... pretty much silent on alignment.
This is especially frustrating considering the amount of discussion of
alignment in the load and store instrinsics. So I was forced to rely on
the specification for the VBROADCASTF128 instruction.
That instruction's spec is *also* completely silent on alignment.
Fortunately, when it comes to the instruction's spec, silence is enough.
There is no #GP fault option for an underaligned address so this
instruction, and by inference the intrinsic, can read any alignment.
As it happens, the old code worked exactly this way and in fact we have
plenty of code that hands pointers with less than 16-byte alignment to
these intrinsics. This code broke pretty spectacularly with this commit.
Fortunately, the fix is super simple! Change a 16 to a 1, and ta da!
Anyways, a lot of debugging for a really boring fix. =]
llvm-svn: 278202
Let the driver pass the option to frontend. Do not set precision metadata for division instructions when this option is set. Set function attribute "correctly-rounded-divide-sqrt-fp-math" based on this option.
Differential Revision: https://reviews.llvm.org/D22940
llvm-svn: 278155
Summary:
Based on a patch by Michael Mueller.
This attribute specifies that a function can be hooked or patched. This
mechanism was originally devised by Microsoft for hotpatching their
binaries (which they're constantly updating to stay ahead of crackers,
script kiddies, and other ne'er-do-wells on the Internet), but it's now
commonly abused by Windows programs that want to hook API functions. It
is for this reason that this attribute was added to GCC--hence the name,
`ms_hook_prologue`.
Depends on D19908.
Reviewers: rnk, aaron.ballman
Subscribers: cfe-commits
Differential Revision: https://reviews.llvm.org/D19909
llvm-svn: 278050
This patch (with the corresponding ARM backend patch) adds support for
some new relocation models:
* Read-only position independence (ROPI): Code and read-only data is accessed
PC-relative. The offsets between all code and RO data sections are known at
static link time.
* Read-write position independence (RWPI): Read-write data is accessed relative
to a static base register. The offsets between all writeable data sections
are known at static link time.
These two modes are independent (they specify how different objects
should be addressed), so they can be used individually or together.
These modes are intended for bare-metal systems or systems with small
real-time operating systems. They are designed to avoid the need for a
dynamic linker, the only initialisation required is setting the static
base register to an appropriate value for RWPI code.
There is one C construct not currently supported by these modes: global
variables initialised to the address of another global variable or
function, where that address is not known at static-link time. There are
a few possible ways to solve this:
* Disallow this, and require the user to write their own initialisation
function if they need variables like this.
* Emit dynamic initialisers for these variables in the compiler, called from
the .init_array section (as is currently done for C++ dynamic initialisers).
We have a patch to do this, described in my original RFC email
(http://lists.llvm.org/pipermail/llvm-dev/2015-December/093022.html), but the
feedback from that RFC thread was that this is not something that belongs in
clang.
* Use a small dynamic loader to fix up these variables, by adding the
difference between the load and execution address of the relevant section.
This would require linker co-operation to generate a table of addresses that
need fixing up.
Differential Revision: https://reviews.llvm.org/D23196
llvm-svn: 278016
For now just disregard the using declaration in this case. Suboptimal,
but wiring up the ability to have declarations of functions that are
separate from their definition (we currently only do that for member
functions) and have differing return types (we don't have any support
for that) is more work than seems reasonable to at least fix this crash.
llvm-svn: 277852
Summary:
In order to re-define OpenCL built-in functions
'to_{private,local,global}' in OpenCL run-time library LLVM names must
be different from the clang built-in function names.
Reviewers: yaxunl, Anastasia
Subscribers: cfe-commits
Differential Revision: https://reviews.llvm.org/D23120
llvm-svn: 277743
The size of image type is reported incorrectly as size of a pointer to address space 0, which causes error when casting image type to pointers by __builtin_astype.
The fix is to get image address space from TargetInfo then report the size accordingly.
Differential Revision: https://reviews.llvm.org/D22927
llvm-svn: 277647
Use the calling convention of the wrapper directly to set the calling convention
to ensure that the calling convention matches. Incorrectly setting the calling
convention results in the code path being entirely nullified as InstCombine +
SimplifyCFG will prune the mismatched CC calls.
llvm-svn: 277390
It seems the compiler was getting confused by the in-class initializers
in local struct MapInfo, so moving those to a default constructor
instead.
llvm-svn: 277256
The previous change was insufficient to mark the content as read-write as the
structure itself was marked constant. Adjust this and add tests to ensure that
the section is marked appropriately as being read-write.
llvm-svn: 277200
Currently Clang use int32 to represent sampler_t, which have been a source of issue for some backends, because in some backends sampler_t cannot be represented by int32. They have to depend on kernel argument metadata and use IPA to find the sampler arguments and global variables and transform them to target specific sampler type.
This patch uses opaque pointer type opencl.sampler_t* for sampler_t. For each use of file-scope sampler variable, it generates a function call of __translate_sampler_initializer. For each initialization of function-scope sampler variable, it generates a function call of __translate_sampler_initializer.
Each builtin library can implement its own __translate_sampler_initializer(). Since the real sampler type tends to be architecture dependent, allowing it to be initialized by a library function simplifies backend design. A typical implementation of __translate_sampler_initializer could be a table lookup of real sampler literal values. Since its argument is always a literal, the returned pointer is known at compile time and easily optimized to finally become some literal values directly put into image read instructions.
This patch is partially based on Alexey Sotkin's work in Khronos Clang (3d4eec6162).
Differential Revision: https://reviews.llvm.org/D21567
llvm-svn: 277024
Summary: This patch adds support for the is_device_ptr clause. It expands SEMA to use the mappable expression logic that can only be tested with code generation in place and check conflicts with other data sharing related clauses using the mappable expressions infrastructure.
Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev
Subscribers: caomhin, cfe-commits
Differential Revision: https://reviews.llvm.org/D22788
llvm-svn: 276978
Summary: This patch adds support for the use_device_ptr clause. It includes changes in SEMA that could not be tested without codegen, namely, the use of the first private logic and mappable expressions support.
Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev
Subscribers: caomhin, cfe-commits
Differential Revision: https://reviews.llvm.org/D22691
llvm-svn: 276977
Summary: This patch add support to map pointers through references in class members. Although a reference does not have storage that a user can access, it still has to be mapped in order to get the deep copy right and the dereferencing code work properly.
Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev
Subscribers: caomhin, cfe-commits
Differential Revision: https://reviews.llvm.org/D22787
llvm-svn: 276934
Summary:
This patch fixes a bug in the map of array sections whose base is a reference to a pointer. The existing mapping support was not prepared to deal with it, causing the compiler to crash.
Mapping a reference to a pointer enjoys the same characteristics of a regular pointer, i.e., it is passed by value. Therefore, the reference has to be materialized in the target region.
Reviewers: hfinkel, carlo.bertolli, kkwli0, ABataev
Subscribers: caomhin, cfe-commits
Differential Revision: https://reviews.llvm.org/D22690
llvm-svn: 276933
Summary:
Before this patch, we computed the offsets in memory of args passed to
GPU kernel functions by throwing all of the args into an LLVM struct.
clang emits packed llvm structs basically whenever it feels like it, and
packed structs have alignment 1. So we cannot rely on the llvm type's
alignment matching the C++ type's alignment.
This patch fixes our codegen so we always respect the clang types'
alignments.
Reviewers: rnk
Subscribers: cfe-commits, tra
Differential Revision: https://reviews.llvm.org/D22879
llvm-svn: 276927
Summary:
Previously this crashed inside EmitThisParam(). There should be no
prelude for naked functions, so just skip the whole thing.
Reviewers: majnemer
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D22715
llvm-svn: 276925
Justin Bogner