'declare target'.
All the functions, referenced in implicit|explicit target regions must
be emitted during code emission for the device.
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@341093 91177308-0d34-0410-b5e6-96231b3b80d8
Added options -f[no-]openmp-cuda-force-full-runtime to [not] force use
of the full runtime for OpenMP offloading to CUDA devices.
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@341073 91177308-0d34-0410-b5e6-96231b3b80d8
If the target construct can be executed in SPMD mode + it is a loop
based directive with static scheduling, we can use lightweight runtime
support.
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@340953 91177308-0d34-0410-b5e6-96231b3b80d8
The attribute marked as inheritable since OpenMP 5.0 supports it +
additional fixes to support new functionality.
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@339704 91177308-0d34-0410-b5e6-96231b3b80d8
The first argument for the parallel outlined functions, called as
serialized parallel regions, should be a pointer to the global thread id
that always is 0.
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@337957 91177308-0d34-0410-b5e6-96231b3b80d8
Summary: In the SPMD case, we need to initialize the data sharing and globalization infrastructure. This covers the case when an SPMD region calls a function in a different compilation unit.
Reviewers: ABataev, carlo.bertolli, caomhin
Reviewed By: ABataev
Subscribers: Hahnfeld, jholewinski, guansong, cfe-commits
Differential Revision: https://reviews.llvm.org/D49188
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@337015 91177308-0d34-0410-b5e6-96231b3b80d8
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.
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@336567 91177308-0d34-0410-b5e6-96231b3b80d8
Patch tries to make better analysis of the variables that should be
globalized. From now, instead of all parallel directives it will check
only distribute parallel .. directives and check only for
firstprivte/lastprivate variables if they must be globalized.
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@335632 91177308-0d34-0410-b5e6-96231b3b80d8
If the shuffle is required for the reduced structures/big data type,
current code may cause compiler crash because of the loading of the
aggregate values. Patch fixes this problem.
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@335377 91177308-0d34-0410-b5e6-96231b3b80d8
parallel region.
If the current construct requires sharing of the local variable in the
inner parallel region, this variable must be globalized to avoid
runtime crash.
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@335285 91177308-0d34-0410-b5e6-96231b3b80d8
If orphaned parallel region is found, the next code must be emitted:
```
if(__kmpc_is_spmd_exec_mode() || __kmpc_parallel_level(loc, gtid))
Serialized execution.
else if (IsMasterThread())
Prepare and signal worker.
else
Outined function call.
```
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@333301 91177308-0d34-0410-b5e6-96231b3b80d8
If the orphaned directive is executed in SPMD mode, we need to emit the
check for the SPMD mode and run the orphaned parallel directive in
sequential mode.
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@332467 91177308-0d34-0410-b5e6-96231b3b80d8
In generic data-sharing mode we do not need to globalize
variables/parameters of reference/pointer types. They already are placed
in the global memory.
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@332380 91177308-0d34-0410-b5e6-96231b3b80d8
distribute simd directives.
Directives `target simd` and `target teams distribute simd` must be
executed in non-SPMD mode.
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@332129 91177308-0d34-0410-b5e6-96231b3b80d8
Added initial support for L2 parallelism in SPMD mode. Note, though,
that the orphaned parallel directives are not currently supported in
SPMD mode.
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@332016 91177308-0d34-0410-b5e6-96231b3b80d8
This is similar to the LLVM change https://reviews.llvm.org/D46290.
We've been running doxygen with the autobrief option for a couple of
years now. This makes the \brief markers into our comments
redundant. Since they are a visual distraction and we don't want to
encourage more \brief markers in new code either, this patch removes
them all.
Patch produced by
for i in $(git grep -l '\@brief'); do perl -pi -e 's/\@brief //g' $i & done
for i in $(git grep -l '\\brief'); do perl -pi -e 's/\\brief //g' $i & done
Differential Revision: https://reviews.llvm.org/D46320
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@331834 91177308-0d34-0410-b5e6-96231b3b80d8
Added initial codegen for level 2, 3 etc. parallelism. Currently, all
the second, the third etc. parallel regions will run sequentially.
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@331642 91177308-0d34-0410-b5e6-96231b3b80d8
Some symbols are not allowed to be used as names on some targets. Patch
ries to unify the emission of the names of LLVM globals so they could be
used on different targets.
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@331358 91177308-0d34-0410-b5e6-96231b3b80d8
NVPTX target.
When generating the wrapper function for the offloading region, we need
to call the outlined function and cast the arguments correctly to follow
the ABI. Usually, variables captured by value are casted to `uintptr_t`
type. But this should not performed for the variables with pointer type.
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@330620 91177308-0d34-0410-b5e6-96231b3b80d8
Added NUW flags for all the add|mul|sub operations + replaced sdiv by udiv
as we operate on unsigned values only (addresses, converted to integers)
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@329411 91177308-0d34-0410-b5e6-96231b3b80d8
variables.
Added emission of the offloading data sections for the variables within
declare target regions + fixes emission of the declare target variables
marked as declare target not within the declare target region.
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@328888 91177308-0d34-0410-b5e6-96231b3b80d8
Summary: The workers also need to initialize the global stack. The call to the initialization function needs to happen after the kernel_init() function is called by the master. This ensures that the per-team data structures of the runtime have been initialized.
Reviewers: ABataev, grokos, carlo.bertolli, caomhin
Reviewed By: ABataev
Subscribers: jholewinski, guansong, cfe-commits
Differential Revision: https://reviews.llvm.org/D44749
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@328219 91177308-0d34-0410-b5e6-96231b3b80d8
constructs in generic mode.
Fixed codegen for distribute parallel combined constructs. We have to
pass and read the shared lower and upper bound from the distribute
region in the inner parallel region. Patch is for generic mode.
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@327990 91177308-0d34-0410-b5e6-96231b3b80d8
If the generic codegen is enabled and private copy of the original
variable escapes the declaration context, this private copy should be
globalized just like it was the original variable.
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@327985 91177308-0d34-0410-b5e6-96231b3b80d8
We emitted fake thread id for the outined function in NVPTX codegen.
Patch adds emission of the real thread id.
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@327867 91177308-0d34-0410-b5e6-96231b3b80d8
The compiler complained about
../tools/clang/lib/CodeGen/CGOpenMPRuntimeNVPTX.cpp:184:15: error: unused variable 'CSI' [-Werror,-Wunused-variable]
if (auto *CSI = CGF.CapturedStmtInfo) {
^
1 error generated.
I don't know this code but it seems like an easy fix so I push it anyway
to get rid of the warning.
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@327694 91177308-0d34-0410-b5e6-96231b3b80d8
If the variable is captured by value and the corresponding parameter in
the outlined function escapes its declaration context, this parameter
must be globalized. To globalize it we need to get the address of the
original parameter, load the value, store it to the global address and
use this global address instead of the original.
Patch improves globalization for parallel|teams regions + functions in
declare target regions.
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@327654 91177308-0d34-0410-b5e6-96231b3b80d8
Summary: Remove this scheme for now since it will be covered by another more generic scheme using global memory. This code will be worked into an optimization for the generic data sharing scheme. Removing this completely and then adding it via future patches will make all future data sharing patches cleaner.
Reviewers: ABataev, carlo.bertolli, caomhin
Reviewed By: ABataev
Subscribers: jholewinski, guansong, cfe-commits
Differential Revision: https://reviews.llvm.org/D43625
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@326948 91177308-0d34-0410-b5e6-96231b3b80d8
Summary:
This patch enables debugging of C99 VLA types by generating more precise
LLVM Debug metadata, using the extended DISubrange 'count' field that
takes a DIVariable.
This should implement:
Bug 30553: Debug info generated for arrays is not what GDB expects (not as good as GCC's)
https://bugs.llvm.org/show_bug.cgi?id=30553
Reviewers: echristo, aprantl, dexonsmith, clayborg, pcc, kristof.beyls, dblaikie
Reviewed By: aprantl
Subscribers: jholewinski, schweitz, davide, fhahn, JDevlieghere, cfe-commits
Differential Revision: https://reviews.llvm.org/D41698
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@323952 91177308-0d34-0410-b5e6-96231b3b80d8
Removed more empty SourceLocations() from the OpenMP code and replaced
with the correct locations for better debug info emission.
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@323232 91177308-0d34-0410-b5e6-96231b3b80d8
getAssociatedStmt() returns the outermost captured statement for the
OpenMP directive. It may return incorrect region in case of combined
constructs. Reworked the code to reduce the number of calls of
getAssociatedStmt() and used getInnermostCapturedStmt() and
getCapturedStmt() functions instead.
In case of firstprivate variables it may lead to an extra allocas
generation for private copies even if the variable is passed by value
into outlined function and could be used directly as private copy.
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@322393 91177308-0d34-0410-b5e6-96231b3b80d8
If the reduction required shuffle in the NVPTX codegen, we may need to
cast the reduced value to the integer type. This casting was implemented
incorrectly and may cause compiler crash. Patch fixes this problem.
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@321818 91177308-0d34-0410-b5e6-96231b3b80d8
Most of the generated functions for the OpenMP were generated with
disabled debug info. Patch fixes this for better user experience.
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@321816 91177308-0d34-0410-b5e6-96231b3b80d8
Summary:
The backend should only emit data sharing code for the cases where it is needed.
A new function attribute is used by Clang to enable data sharing only for the cases where OpenMP semantics require it and there are variables that need to be shared.
Reviewers: hfinkel, Hahnfeld, ABataev, carlo.bertolli, caomhin
Reviewed By: ABataev
Subscribers: cfe-commits, jholewinski
Differential Revision: https://reviews.llvm.org/D41123
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@320527 91177308-0d34-0410-b5e6-96231b3b80d8
Alexey Bataev