All target-parallel-based constructs can be run in SPMD mode from now
on. Even if num_threads clauses or if clauses are used, such constructs
can be executed in SPMD mode.
llvm-svn: 358595
Combined constructs with parallel and if clauses without modifiers may
be executed in SPMD mode since if the condition is true for the target
region, it is also true for parallel region and the threads must be run
in parallel.
llvm-svn: 358503
mode.
After the previous patch with the more correct handling of the number of
threads in parallel regions, the parallel regions with num_threads
clauses can be executed in SPMD mode.
llvm-svn: 358445
regions.
Added more complex analysis for number of teams and number of threads in
the target regions, also merged related common code between CGOpenMPRuntime
and CGOpenMPRuntimeNVPTX classes.
llvm-svn: 358126
Added special processing of the memory management directives/clauses for
NVPTX target. For private locals, omp_default_mem_alloc and
omp_thread_mem_alloc result in allocation in local memory.
omp_const_mem_alloc allocates const memory, omp_teams_mem_alloc
allocates shared memory, and omp_cgroup_mem_alloc and
omp_large_cap_mem_alloc allocate global memory.
llvm-svn: 357923
For the global variables the allocate directive must specify only the
predefined allocator. This allocator must be translated into the correct
form of the address space for the targets that support different address
spaces.
llvm-svn: 356702
Added initial codegen for the local variables with the #pragma omp
allocate directive. Instead of allocating the variables on the stack,
__kmpc_alloc|__kmpc_free functions are used for memory (de-)allocation.
llvm-svn: 356472
'_openmp_teams_reductions_buffer_$_.
nvlink does not handle weak linkage correctly, same symbols with the
different sizes are reported as erroneous though the largest size must
be chosen instead. Patch fixes this problem by using Internal linkage
instead of the Common.
llvm-svn: 356072
memory.
If the variable with the constant non-scalar type is firstprivatized in
the target region, the local copy is created with the data copying.
Instead, we allocate the copy in the constant memory and avoid extra
copying in the outlined target regions. This global copy is used in the
target regions without loss of the performance.
llvm-svn: 355418
A faster way to reduce the values in teams reductions was found, the
codegen is updated to use this faster algorithm and new runtime functions.
llvm-svn: 354479
The various EltSize, Offset, DataLayout, and StructLayout arguments
are all computable from the Address's element type and the DataLayout
which the CGBuilder already has access to.
After having previously asserted that the computed values are the same
as those passed in, now remove the redundant arguments from
CGBuilder's Create*GEP functions.
Differential Revision: https://reviews.llvm.org/D57767
llvm-svn: 353629
Emit{Nounwind,}RuntimeCall{,OrInvoke} have been modified to take a
FunctionCallee as an argument, and CreateRuntimeFunction has been
modified to return a FunctionCallee. All callers have been updated.
Additionally, CreateBuiltinFunction is removed, as it was redundant
with CreateRuntimeFunction after some previous changes.
Differential Revision: https://reviews.llvm.org/D57668
llvm-svn: 353184
This patch implements parsing and sema for "omp declare mapper"
directive. User defined mapper, i.e., declare mapper directive, is a new
feature in OpenMP 5.0. It is introduced to extend existing map clauses
for the purpose of simplifying the copy of complex data structures
between host and device (i.e., deep copy). An example is shown below:
struct S { int len; int *d; };
#pragma omp declare mapper(struct S s) map(s, s.d[0:s.len]) // Memory region that d points to is also mapped using this mapper.
Contributed-by: Lingda Li <lildmh@gmail.com>
Differential Revision: https://reviews.llvm.org/D56326
llvm-svn: 352906
to reflect the new license.
We understand that people may be surprised that we're moving the header
entirely to discuss the new license. We checked this carefully with the
Foundation's lawyer and we believe this is the correct approach.
Essentially, all code in the project is now made available by the LLVM
project under our new license, so you will see that the license headers
include that license only. Some of our contributors have contributed
code under our old license, and accordingly, we have retained a copy of
our old license notice in the top-level files in each project and
repository.
llvm-svn: 351636
Each we create the target regions with the teams distribute inner
region, we can better estimate number of the teams required to execute
the target region. Function __kmpc_push_target_tripcount() is used for
purpose, which accepts device_id and the number of the iterations,
performed by the associated loop.
llvm-svn: 350571
nvvm_barrier0.
Use runtime functions instead of the direct call to the nvvm intrinsics.
It allows to prevent some dangerous LLVM optimizations, that breaks the
code for the NVPTX target.
llvm-svn: 350328
buffer.
Seems to me, nvlink has a bug with the proper support of the weakly
linked symbols. It does not allow to define several shared memory buffer
with the different sizes even with the weak linkage. Instead we always
use 128 bytes buffer to prevent nvlink from the error message emission.
llvm-svn: 349540
Inlined runtime with the current implementation of the interwarp copy
function leads to the undefined behavior because of the not quite
correct implementation of the barriers. Start using generic
__kmpc_barier function instead of the custom made barriers.
llvm-svn: 349192
If the array section is based on pointer and this sections is mapped in
target region + then it is used in the inner parallel region, it also
must be globalized as the pointer itself is passed by value, not by
reference.
llvm-svn: 348492
Critical regions in NVPTX are the constructs, which, generally speaking,
are not supported by the NVPTX target. Instead we're using special
technique to handle the critical regions. Currently they are supported
only within the loop and all the threads in the loop must execute the
same critical region.
Inside of this special regions the regions still must be emitted as
critical, to avoid possible data races between the teams +
synchronization must use __kmpc_barrier functions.
llvm-svn: 348272
__kmpc_barrier runtime functions must be marked as convergent to prevent
some dangerous optimizations. Also, for NVPTX target all barriers must
be emitted as simple barriers.
llvm-svn: 348271
Summary: This patch adds a new runtime for the SPMD deinit kernel function which replaces the previous function. The new function takes as argument the flag which signals whether the runtime is required or not. This enables the compiler to optimize out the part of the deinit function which are not needed.
Reviewers: ABataev, caomhin
Reviewed By: ABataev
Subscribers: jholewinski, guansong, cfe-commits
Differential Revision: https://reviews.llvm.org/D54970
llvm-svn: 347915
modes.
If the region is inside target|teams|distribute region, we can emit the
locations with the correct info for execution mode and runtime mode.
Patch adds this ability to the NVPTX codegen to help the optimizer to
produce better code.
llvm-svn: 347583
For the NVPTX target default locations should be emitted as constants +
additional info must be emitted in the reserved_2 field of the ident_t
structure. The 1st bit controls the execution mode and the 2nd bit
controls use of the lightweight runtime. The combination of the bits for
Non-SPMD mode + lightweight runtime represents special undefined mode,
used outside of the target regions for orphaned directives or functions.
Should allow and additional optimization inside of the target regions.
llvm-svn: 347425
reductions.
Fixed previously committed code for the reduction support in
teams/parallel constructs taking into account new design of the NVPTX
support in the compiler. Teams reduction are not fully functional yet,
it is going to be fixed in the following patches.
llvm-svn: 347081
If the statements between target|teams|distribute directives does not
require execution in master thread, like constant expressions, null
statements, simple declarations, etc., such construct can be xecuted in
SPMD mode.
llvm-svn: 346551
target|teams|distribute variables.
If the total size of the variables, declared in target|teams|distribute
regions, is less than the maximal size of shared memory available, the
buffer is allocated in the shared memory.
llvm-svn: 346507
Coalesced memory access requires use of the new function
`__kmpc_data_sharing_coalesced_push_stack` instead of the
`__kmpc_data_sharing_push_stack`.
llvm-svn: 345991
target/teams/distribute regions.
Target/teams/distribute regions exist for all the time the kernel is
executed. Thus, if the variable is declared in their context and then
escape it, we can allocate global memory statically instead of
allocating it dynamically.
Patch captures all the globalized variables in target/teams/distribute
contexts, merges them into the records, one per each target region.
Those records are then joined into the union, one per compilation unit
(to save the global memory). Those units are organized into
2 x dimensional arrays, where the first dimension is
the number of blocks per SM and the second one is the number of SMs.
Runtime functions manage this global memory space between the executing
teams.
llvm-svn: 345978
Added support for mapping of lambdas in the target regions. It scans all
the captures by reference in the lambda, implicitly maps those variables
in the target region and then later reinstate the addresses of
references in lambda to the correct addresses of the captured|privatized
variables.
llvm-svn: 345609
Summary: This patch adds a new code generation path for bound sharing directives containing distribute parallel for. The new code generation scheme applies to chunked schedules on distribute and parallel for directives. The scheme simplifies the code that is being generated by eliminating the need for an outer for loop over chunks for both distribute and parallel for directives. In the case of distribute it applies to any sized chunk while in the parallel for case it only applies when chunk size is 1.
Reviewers: ABataev, caomhin
Reviewed By: ABataev
Subscribers: jholewinski, guansong, cfe-commits
Differential Revision: https://reviews.llvm.org/D53448
llvm-svn: 345509
Summary: This patch enables the choosing of the default schedule for parallel for loops even in non-SPMD cases.
Reviewers: ABataev, caomhin
Reviewed By: ABataev
Subscribers: jholewinski, guansong, cfe-commits
Differential Revision: https://reviews.llvm.org/D53443
llvm-svn: 345507
if the function has globalized variables and called in context of
target/teams/distribute regions, it does not need to globalize 32
copies of the same variables for memory coalescing, it is enough to
have just one copy, because there is parallel region.
Patch does this by adding call for `__kmpc_parallel_level` function and
checking its return value. If the code sees that the parallel level is
0, then only one variable is allocated, not 32.
llvm-svn: 344356
target/teams/distribute regions.
Previously introduced globalization scheme that uses memory coalescing
scheme may increase memory usage fr the variables that are devlared in
target/teams/distribute contexts. We don't need 32 copies of such
variables, just 1. Patch reduces memory use in this case.
llvm-svn: 344273
Added support for memory coalescing for better performance for
globalized variables. From now on all the globalized variables are
represented as arrays of 32 elements and each thread accesses these
elements using `tid & 31` as index.
llvm-svn: 344049
Fixed emission of the __kmpc_global_thread_num() so that it is not
messed up with alloca instructions anymore. Plus, fixes emission of the
__kmpc_global_thread_num() functions in the target outlined regions so
that they are not called before runtime is initialized.
llvm-svn: 343856
Worker threads fork off to the compiler generated worker function
directly after entering the kernel function. Hence, there is no
need to check whether the current thread is the master if we are
outside of a parallel region (neither SPMD nor parallel_level > 0).
Differential Revision: https://reviews.llvm.org/D52732
llvm-svn: 343618
lightweight runtime.
The datasharing flag must be set to `1` when executing SPMD-mode compatible directive with reduction|lastprivate clauses.
llvm-svn: 343492
Summary: Set default schedule for parallel for loops to schedule(static, 1) when using SPMD mode on the NVPTX device offloading toolchain to ensure coalescing.
Reviewers: ABataev, Hahnfeld, caomhin
Reviewed By: ABataev
Subscribers: jholewinski, guansong, cfe-commits
Differential Revision: https://reviews.llvm.org/D52629
llvm-svn: 343260
Summary: For the OpenMP NVPTX toolchain choose a default distribute schedule that ensures coalescing on the GPU when in SPMD mode. This significantly increases the performance of offloaded target code and reduces the number of registers used on the GPU side.
Reviewers: ABataev, caomhin, Hahnfeld
Reviewed By: ABataev, Hahnfeld
Subscribers: Hahnfeld, jholewinski, guansong, cfe-commits
Differential Revision: https://reviews.llvm.org/D52434
llvm-svn: 343253
Add support for OMP5.0 requires directive and unified_address clause.
Patches to follow will include support for additional clauses.
Differential Revision: https://reviews.llvm.org/D52359
llvm-svn: 343063
'declare target'.
All the functions, referenced in implicit|explicit target regions must
be emitted during code emission for the device.
llvm-svn: 341093
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.
llvm-svn: 340953
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.
llvm-svn: 337957
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
llvm-svn: 337015
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
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.
llvm-svn: 335632
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.
llvm-svn: 335377
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.
llvm-svn: 335285
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.
```
llvm-svn: 333301
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.
llvm-svn: 332467
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.
llvm-svn: 332380
Added initial support for L2 parallelism in SPMD mode. Note, though,
that the orphaned parallel directives are not currently supported in
SPMD mode.
llvm-svn: 332016
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
llvm-svn: 331834
Added initial codegen for level 2, 3 etc. parallelism. Currently, all
the second, the third etc. parallel regions will run sequentially.
llvm-svn: 331642
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.
llvm-svn: 331358
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.
llvm-svn: 330620
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)
llvm-svn: 329411
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.
llvm-svn: 328888
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
llvm-svn: 328219
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.
llvm-svn: 327990
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.
llvm-svn: 327985
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.
llvm-svn: 327694
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.
llvm-svn: 327654
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
llvm-svn: 326948
Differential Revision: https://reviews.llvm.org/D43852
This patch extends the SPMD implementation to all target constructs and guards this implementation under a new flag.
llvm-svn: 326368
Alexey Bataev