cavis/libnd4j/include/openmp_pragmas.h

139 lines
7.0 KiB
C
Raw Normal View History

2019-06-06 14:21:15 +02:00
/*******************************************************************************
* Copyright (c) 2015-2018 Skymind, Inc.
*
* This program and the accompanying materials are made available under the
* terms of the Apache License, Version 2.0 which is available at
* https://www.apache.org/licenses/LICENSE-2.0.
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS, WITHOUT
* WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the
* License for the specific language governing permissions and limitations
* under the License.
*
* SPDX-License-Identifier: Apache-2.0
******************************************************************************/
//
// @author raver119@gmail.com
//
#ifndef DEV_TESTS_OPENMP_PRAGMAS_H
#define DEV_TESTS_OPENMP_PRAGMAS_H
#if defined(_MSC_VER)
#define OMP_STRINGIFY(args) #args
2019-06-06 14:21:15 +02:00
#define OMP_IF(args)
#define OMP_SCHEDULE(args)
#define OMP_MAXT
#define OMP_SUMT
#define OMP_REDUCTION(args)
#define PRAGMA_OMP_ATOMIC
#define PRAGMA_OMP_ATOMIC_ARGS(args)
2019-06-06 14:21:15 +02:00
#define PRAGMA_OMP_CRITICAL
#define PRAGMA_OMP_SIMD __pragma(omp simd)
2019-06-06 14:21:15 +02:00
#define PRAGMA_OMP_SIMD_ARGS(args)
#define PRAGMA_OMP_SIMD_SUM(args)
#define PRAGMA_OMP_SIMD_MAX(args)
#define PRAGMA_OMP_PARALLEL
#define PRAGMA_OMP_PARALLEL_REDUCTION(args)
#define PRAGMA_OMP_PARALLEL_ARGS(args)
#define PRAGMA_OMP_PARALLEL_THREADS(args)
[WIP] More of CUDA (#95) * initial commit Signed-off-by: raver119 <raver119@gmail.com> * Implementation of hashcode cuda helper. Working edition. * Fixed parallel test input arangements. * Fixed tests for hashcode op. * Fixed shape calculation for image:crop_and_resize op and test. * NativeOps tests. Initial test suite. * Added tests for indexReduce methods. * Added test on execBroadcast with NDArray as dimensions. * Added test on execBroadcastBool with NDArray as dimensions. * Added tests on execPairwiseTransform and execPairwiseTransofrmBool. * Added tests for execReduce with scalar results. * Added reduce tests for non-empty dims array. * Added tests for reduce3. * Added tests for execScalar. * Added tests for execSummaryStats. * - provide cpu/cuda code for batch_to_space - testing it Signed-off-by: Yurii <yurii@skymind.io> * - remove old test for batch_to_space (had wrong format and numbers were not checked) Signed-off-by: Yurii <yurii@skymind.io> * Fixed complilation errors with test. * Added test for execTransformFloat. * Added test for execTransformSame. * Added test for execTransformBool. * Added test for execTransformStrict. * Added tests for execScalar/execScalarBool with TADs. * Added test for flatten. * - provide cpu/cuda code for space_to_Batch operaion Signed-off-by: Yurii <yurii@skymind.io> * Added test for concat. * comment unnecessary stuff in s_t_b Signed-off-by: Yurii <yurii@skymind.io> * Added test for specialConcat. * Added tests for memcpy/set routines. * Fixed pullRow cuda test. * Added pullRow test. * Added average test. * - correct typo in NDArray::applyPairwiseTransform(nd4j::pairwise::BoolOps op...) Signed-off-by: Yurii <yurii@skymind.io> * - debugging and fixing cuda tests in JavaInteropTests file Signed-off-by: Yurii <yurii@skymind.io> * - correct some tests Signed-off-by: Yurii <yurii@skymind.io> * Added test for shuffle. * Fixed ops declarations. * Restored omp and added shuffle test. * Added convertTypes test. * Added tests for execRandom. Eliminated usage of RandomBuffer with NativeOps. * Added sort tests. * Added tests for execCustomOp. * - further debuging and fixing tests terminated with crash Signed-off-by: Yurii <yurii@skymind.io> * Added tests for calculateOutputShapes. * Addded Benchmarks test. * Commented benchmark tests. * change assertion Signed-off-by: raver119 <raver119@gmail.com> * Added tests for apply_sgd op. Added cpu helper for that op. * Implement cuda helper for aplly_sgd op. Fixed tests for NativeOps. * Added test for assign broadcastable. * Added tests for assign_bp op. * Added tests for axpy op. * - assign/execScalar/execTransformAny signature change - minor test fix Signed-off-by: raver119 <raver119@gmail.com> * Fixed axpy op. * meh Signed-off-by: raver119 <raver119@gmail.com> * - fix tests for nativeOps::concat Signed-off-by: Yurii <yurii@skymind.io> * sequential transform/scalar Signed-off-by: raver119 <raver119@gmail.com> * allow nested parallelism Signed-off-by: raver119 <raver119@gmail.com> * assign_bp leak fix Signed-off-by: raver119 <raver119@gmail.com> * block setRNG fix Signed-off-by: raver119 <raver119@gmail.com> * enable parallelism by default Signed-off-by: raver119 <raver119@gmail.com> * enable nested parallelism by default Signed-off-by: raver119 <raver119@gmail.com> * Added cuda implementation for row_count helper. * Added implementation for tnse gains op helper. * - take into account possible situations when input arrays are empty in reduce_ cuda stuff Signed-off-by: Yurii <yurii@skymind.io> * Implemented tsne/edge_forces op cuda-based helper. Parallelized cpu-based helper for edge_forces. * Added kernel for tsne/symmetrized op heleper. * Implementation of tsne/symmetrized op cuda helper. Working edition. * Eliminated waste printfs. * Added test for broadcastgradientargs op. * host-only fallback for empty reduce float Signed-off-by: raver119 <raver119@gmail.com> * - some tests fixes Signed-off-by: Yurii <yurii@skymind.io> * - correct the rest of reduce_ stuff Signed-off-by: Yurii <yurii@skymind.io> * - further correction of reduce_ stuff Signed-off-by: Yurii <yurii@skymind.io> * Added test for Cbow op. Also added cuda implementation for cbow helpers. * - improve code of stack operation for scalar case Signed-off-by: Yurii <yurii@skymind.io> * - provide cuda kernel for gatherND operation Signed-off-by: Yurii <yurii@skymind.io> * Implementation of cbow helpers with cuda kernels. * minor tests tweaks Signed-off-by: raver119 <raver119@gmail.com> * minor tests tweaks Signed-off-by: raver119 <raver119@gmail.com> * - further correction of cuda stuff Signed-off-by: Yurii <yurii@skymind.io> * Implementatation of cbow op helper with cuda kernels. Working edition. * Skip random testing for cudablas case. * lstmBlockCell context fix Signed-off-by: raver119 <raver119@gmail.com> * Added tests for ELU and ELU_BP ops. * Added tests for eq_scalar, gt_scalar, gte_scalar and lte_scalar ops. * Added tests for neq_scalar. * Added test for noop. * - further work on clipbynorm_bp Signed-off-by: Yurii <yurii@skymind.io> * - get rid of concat op call, use instead direct concat helper call Signed-off-by: Yurii <yurii@skymind.io> * lstmBlockCell context fix Signed-off-by: raver119 <raver119@gmail.com> * Added tests for lrelu and lrelu_bp. * Added tests for selu and selu_bp. * Fixed lrelu derivative helpers. * - some corrections in lstm Signed-off-by: Yurii <yurii@skymind.io> * operator * result shape fix Signed-off-by: raver119 <raver119@gmail.com> * - correct typo in lstmCell Signed-off-by: Yurii <yurii@skymind.io> * few tests fixed Signed-off-by: raver119 <raver119@gmail.com> * CUDA inverse broadcast bool fix Signed-off-by: raver119 <raver119@gmail.com> * disable MMAP test for CUDA Signed-off-by: raver119 <raver119@gmail.com> * BooleanOp syncToDevice Signed-off-by: raver119 <raver119@gmail.com> * meh Signed-off-by: raver119 <raver119@gmail.com> * additional data types for im2col/col2im Signed-off-by: raver119 <raver119@gmail.com> * Added test for firas_sparse op. * one more RandomBuffer test excluded Signed-off-by: raver119 <raver119@gmail.com> * Added tests for flatten op. * Added test for Floor op. * bunch of tests fixed Signed-off-by: raver119 <raver119@gmail.com> * mmulDot tests fixed Signed-off-by: raver119 <raver119@gmail.com> * more tests fixed Signed-off-by: raver119 <raver119@gmail.com> * Implemented floordiv_bp op and tests. * Fixed scalar case with cuda implementation for bds. * - work on cuda kernel for clip_by_norm backprop op is completed Signed-off-by: Yurii <yurii@skymind.io> * Eliminate cbow crach. * more tests fixed Signed-off-by: raver119 <raver119@gmail.com> * more tests fixed Signed-off-by: raver119 <raver119@gmail.com> * Eliminated abortion with batched nlp test. * more tests fixed Signed-off-by: raver119 <raver119@gmail.com> * Fixed shared flag initializing. * disabled bunch of cpu workspaces tests Signed-off-by: raver119 <raver119@gmail.com> * scalar operators fix: missing registerSpecialUse call Signed-off-by: raver119 <raver119@gmail.com> * Fixed logdet for cuda and tests. * - correct clipBynorm_bp Signed-off-by: Yurii <yurii@skymind.io> * Fixed crop_and_resize shape datatype. * - correct some mmul tests Signed-off-by: Yurii <yurii@skymind.io>
2019-08-02 19:01:03 +02:00
#define PRAGMA_OMP_PARALLEL_THREADS_IF(threads, condition)
2019-06-06 14:21:15 +02:00
#define PRAGMA_OMP_PARALLEL_FOR
#define PRAGMA_OMP_PARALLEL_FOR_ARGS(args)
#define PRAGMA_OMP_PARALLEL_FOR_IF(args)
#define PRAGMA_OMP_PARALLEL_FOR_COLLAPSE(loops)
#define PRAGMA_OMP_PARALLEL_FOR_REDUCTION(args)
#define PRAGMA_OMP_PARALLEL_FOR_THREADS(args)
#define PRAGMA_OMP_PARALLEL_FOR_SIMD
#define PRAGMA_OMP_PARALLEL_FOR_SIMD_ARGS(args)
#define PRAGMA_OMP_PARALLEL_FOR_SIMD_COLLAPSE(loops)
#define PRAGMA_OMP_PARALLEL_FOR_SIMD_REDUCTION(args)
#define PRAGMA_OMP_PARALLEL_FOR_SIMD_THREADS(args)
#define PRAGMA_OMP_PARALLEL_FOR_SIMD_THREADS_COLLAPSE(threads, loops)
#define PRAGMA_OMP_PARALLEL_SECTIONS
#define PRAGMA_OMP_SECTION
#define PRAGMA_OMP_SINGLE
#define PRAGMA_OMP_SINGLE_ARGS(args)
#define PRAGMA_OMP_TASK
2019-06-06 14:21:15 +02:00
#else
2019-06-06 14:21:15 +02:00
#define OMP_STRINGIFY(args) #args
#define OMP_IF(args) if(args)
#define OMP_SCHEDULE(args) schedule(args)
#define OMP_MAXT maxT
#define OMP_SUMT sumT
#define OMP_REDUCTION(args) reduction(args)
#define PRAGMA_OMP_ATOMIC _Pragma(OMP_STRINGIFY(omp atomic))
#define PRAGMA_OMP_ATOMIC_ARGS(args) _Pragma(OMP_STRINGIFY(omp atomic args))
2019-06-06 14:21:15 +02:00
#define PRAGMA_OMP_CRITICAL _Pragma(OMP_STRINGIFY(omp critical))
#define PRAGMA_OMP_SIMD _Pragma(OMP_STRINGIFY(omp simd))
#define PRAGMA_OMP_SIMD_ARGS(args) _Pragma(OMP_STRINGIFY(omp simd args))
#define PRAGMA_OMP_SIMD_SUM(args) _Pragma(OMP_STRINGIFY(omp simd reduction(sumT:args)))
#define PRAGMA_OMP_SIMD_MAX(args) _Pragma(OMP_STRINGIFY(omp simd reduction(maxTF:args)))
#define PRAGMA_OMP_PARALLEL _Pragma(OMP_STRINGIFY(omp parallel default(shared)))
#define PRAGMA_OMP_PARALLEL_REDUCTION(args) _Pragma(OMP_STRINGIFY(omp parallel reduction(args) default(shared)))
#define PRAGMA_OMP_PARALLEL_ARGS(args) _Pragma(OMP_STRINGIFY(omp parallel args default(shared)))
#define PRAGMA_OMP_PARALLEL_THREADS(args) _Pragma(OMP_STRINGIFY(omp parallel num_threads(args) if(args > 1) default(shared)))
[WIP] More of CUDA (#95) * initial commit Signed-off-by: raver119 <raver119@gmail.com> * Implementation of hashcode cuda helper. Working edition. * Fixed parallel test input arangements. * Fixed tests for hashcode op. * Fixed shape calculation for image:crop_and_resize op and test. * NativeOps tests. Initial test suite. * Added tests for indexReduce methods. * Added test on execBroadcast with NDArray as dimensions. * Added test on execBroadcastBool with NDArray as dimensions. * Added tests on execPairwiseTransform and execPairwiseTransofrmBool. * Added tests for execReduce with scalar results. * Added reduce tests for non-empty dims array. * Added tests for reduce3. * Added tests for execScalar. * Added tests for execSummaryStats. * - provide cpu/cuda code for batch_to_space - testing it Signed-off-by: Yurii <yurii@skymind.io> * - remove old test for batch_to_space (had wrong format and numbers were not checked) Signed-off-by: Yurii <yurii@skymind.io> * Fixed complilation errors with test. * Added test for execTransformFloat. * Added test for execTransformSame. * Added test for execTransformBool. * Added test for execTransformStrict. * Added tests for execScalar/execScalarBool with TADs. * Added test for flatten. * - provide cpu/cuda code for space_to_Batch operaion Signed-off-by: Yurii <yurii@skymind.io> * Added test for concat. * comment unnecessary stuff in s_t_b Signed-off-by: Yurii <yurii@skymind.io> * Added test for specialConcat. * Added tests for memcpy/set routines. * Fixed pullRow cuda test. * Added pullRow test. * Added average test. * - correct typo in NDArray::applyPairwiseTransform(nd4j::pairwise::BoolOps op...) Signed-off-by: Yurii <yurii@skymind.io> * - debugging and fixing cuda tests in JavaInteropTests file Signed-off-by: Yurii <yurii@skymind.io> * - correct some tests Signed-off-by: Yurii <yurii@skymind.io> * Added test for shuffle. * Fixed ops declarations. * Restored omp and added shuffle test. * Added convertTypes test. * Added tests for execRandom. Eliminated usage of RandomBuffer with NativeOps. * Added sort tests. * Added tests for execCustomOp. * - further debuging and fixing tests terminated with crash Signed-off-by: Yurii <yurii@skymind.io> * Added tests for calculateOutputShapes. * Addded Benchmarks test. * Commented benchmark tests. * change assertion Signed-off-by: raver119 <raver119@gmail.com> * Added tests for apply_sgd op. Added cpu helper for that op. * Implement cuda helper for aplly_sgd op. Fixed tests for NativeOps. * Added test for assign broadcastable. * Added tests for assign_bp op. * Added tests for axpy op. * - assign/execScalar/execTransformAny signature change - minor test fix Signed-off-by: raver119 <raver119@gmail.com> * Fixed axpy op. * meh Signed-off-by: raver119 <raver119@gmail.com> * - fix tests for nativeOps::concat Signed-off-by: Yurii <yurii@skymind.io> * sequential transform/scalar Signed-off-by: raver119 <raver119@gmail.com> * allow nested parallelism Signed-off-by: raver119 <raver119@gmail.com> * assign_bp leak fix Signed-off-by: raver119 <raver119@gmail.com> * block setRNG fix Signed-off-by: raver119 <raver119@gmail.com> * enable parallelism by default Signed-off-by: raver119 <raver119@gmail.com> * enable nested parallelism by default Signed-off-by: raver119 <raver119@gmail.com> * Added cuda implementation for row_count helper. * Added implementation for tnse gains op helper. * - take into account possible situations when input arrays are empty in reduce_ cuda stuff Signed-off-by: Yurii <yurii@skymind.io> * Implemented tsne/edge_forces op cuda-based helper. Parallelized cpu-based helper for edge_forces. * Added kernel for tsne/symmetrized op heleper. * Implementation of tsne/symmetrized op cuda helper. Working edition. * Eliminated waste printfs. * Added test for broadcastgradientargs op. * host-only fallback for empty reduce float Signed-off-by: raver119 <raver119@gmail.com> * - some tests fixes Signed-off-by: Yurii <yurii@skymind.io> * - correct the rest of reduce_ stuff Signed-off-by: Yurii <yurii@skymind.io> * - further correction of reduce_ stuff Signed-off-by: Yurii <yurii@skymind.io> * Added test for Cbow op. Also added cuda implementation for cbow helpers. * - improve code of stack operation for scalar case Signed-off-by: Yurii <yurii@skymind.io> * - provide cuda kernel for gatherND operation Signed-off-by: Yurii <yurii@skymind.io> * Implementation of cbow helpers with cuda kernels. * minor tests tweaks Signed-off-by: raver119 <raver119@gmail.com> * minor tests tweaks Signed-off-by: raver119 <raver119@gmail.com> * - further correction of cuda stuff Signed-off-by: Yurii <yurii@skymind.io> * Implementatation of cbow op helper with cuda kernels. Working edition. * Skip random testing for cudablas case. * lstmBlockCell context fix Signed-off-by: raver119 <raver119@gmail.com> * Added tests for ELU and ELU_BP ops. * Added tests for eq_scalar, gt_scalar, gte_scalar and lte_scalar ops. * Added tests for neq_scalar. * Added test for noop. * - further work on clipbynorm_bp Signed-off-by: Yurii <yurii@skymind.io> * - get rid of concat op call, use instead direct concat helper call Signed-off-by: Yurii <yurii@skymind.io> * lstmBlockCell context fix Signed-off-by: raver119 <raver119@gmail.com> * Added tests for lrelu and lrelu_bp. * Added tests for selu and selu_bp. * Fixed lrelu derivative helpers. * - some corrections in lstm Signed-off-by: Yurii <yurii@skymind.io> * operator * result shape fix Signed-off-by: raver119 <raver119@gmail.com> * - correct typo in lstmCell Signed-off-by: Yurii <yurii@skymind.io> * few tests fixed Signed-off-by: raver119 <raver119@gmail.com> * CUDA inverse broadcast bool fix Signed-off-by: raver119 <raver119@gmail.com> * disable MMAP test for CUDA Signed-off-by: raver119 <raver119@gmail.com> * BooleanOp syncToDevice Signed-off-by: raver119 <raver119@gmail.com> * meh Signed-off-by: raver119 <raver119@gmail.com> * additional data types for im2col/col2im Signed-off-by: raver119 <raver119@gmail.com> * Added test for firas_sparse op. * one more RandomBuffer test excluded Signed-off-by: raver119 <raver119@gmail.com> * Added tests for flatten op. * Added test for Floor op. * bunch of tests fixed Signed-off-by: raver119 <raver119@gmail.com> * mmulDot tests fixed Signed-off-by: raver119 <raver119@gmail.com> * more tests fixed Signed-off-by: raver119 <raver119@gmail.com> * Implemented floordiv_bp op and tests. * Fixed scalar case with cuda implementation for bds. * - work on cuda kernel for clip_by_norm backprop op is completed Signed-off-by: Yurii <yurii@skymind.io> * Eliminate cbow crach. * more tests fixed Signed-off-by: raver119 <raver119@gmail.com> * more tests fixed Signed-off-by: raver119 <raver119@gmail.com> * Eliminated abortion with batched nlp test. * more tests fixed Signed-off-by: raver119 <raver119@gmail.com> * Fixed shared flag initializing. * disabled bunch of cpu workspaces tests Signed-off-by: raver119 <raver119@gmail.com> * scalar operators fix: missing registerSpecialUse call Signed-off-by: raver119 <raver119@gmail.com> * Fixed logdet for cuda and tests. * - correct clipBynorm_bp Signed-off-by: Yurii <yurii@skymind.io> * Fixed crop_and_resize shape datatype. * - correct some mmul tests Signed-off-by: Yurii <yurii@skymind.io>
2019-08-02 19:01:03 +02:00
#define PRAGMA_OMP_PARALLEL_THREADS_IF(threads, condition) _Pragma(OMP_STRINGIFY(omp parallel num_threads(threads) if(condition) default(shared)))
2019-06-06 14:21:15 +02:00
#define PRAGMA_OMP_PARALLEL_FOR _Pragma(OMP_STRINGIFY(omp parallel for default(shared)))
#define PRAGMA_OMP_PARALLEL_FOR_REDUCTION(args) _Pragma(OMP_STRINGIFY(omp parallel for reduction(args) default(shared)))
#define PRAGMA_OMP_PARALLEL_FOR_ARGS(args) _Pragma(OMP_STRINGIFY(omp parallel for args default(shared)))
#define PRAGMA_OMP_PARALLEL_FOR_IF(args) _Pragma(OMP_STRINGIFY(omp parallel for if(args) default(shared)))
#define PRAGMA_OMP_PARALLEL_FOR_COLLAPSE(loops) _Pragma(OMP_STRINGIFY(omp parallel for default(shared) collapse(loops)))
#define PRAGMA_OMP_PARALLEL_FOR_THREADS(args) _Pragma(OMP_STRINGIFY(omp parallel for num_threads(args) if(args > 1) default(shared)))
#define PRAGMA_OMP_PARALLEL_FOR_SIMD _Pragma(OMP_STRINGIFY(omp parallel for simd default(shared)))
#define PRAGMA_OMP_PARALLEL_FOR_SIMD_ARGS(args) _Pragma(OMP_STRINGIFY(omp parallel for simd args default(shared)))
#define PRAGMA_OMP_PARALLEL_FOR_SIMD_THREADS_COLLAPSE(threads, loops) _Pragma(OMP_STRINGIFY(omp parallel for simd num_threads(threads) if(threads > 1) default(shared) collapse(loops)))
#define PRAGMA_OMP_PARALLEL_FOR_SIMD_COLLAPSE(loops) _Pragma(OMP_STRINGIFY(omp parallel for simd default(shared) collapse(loops)))
#define PRAGMA_OMP_PARALLEL_FOR_SIMD_REDUCTION(args) _Pragma(OMP_STRINGIFY(omp parallel for simd reduction(args) default(shared)))
#define PRAGMA_OMP_PARALLEL_FOR_SIMD_THREADS(args) _Pragma(OMP_STRINGIFY(omp parallel for simd num_threads(args) if(args > 1) default(shared)))
#define PRAGMA_OMP_PARALLEL_SECTIONS _Pragma(OMP_STRINGIFY(omp parallel sections))
#define PRAGMA_OMP_SECTION _Pragma(OMP_STRINGIFY(omp section))
#define PRAGMA_OMP_SINGLE _Pragma(OMP_STRINGIFY(omp single))
#define PRAGMA_OMP_SINGLE_ARGS(args) _Pragma(OMP_STRINGIFY(omp single args))
#define PRAGMA_OMP_TASK _Pragma(OMP_STRINGIFY(omp task))
2019-06-06 14:21:15 +02:00
#endif
// reductions
#define FUNC_RL std::function<int64_t(uint64_t, int64_t, int64_t, int64_t)>
#define FUNC_AL std::function<int64_t(int64_t, int64_t)>
// aggregation functions
#define FUNC_RD std::function<double(uint64_t, int64_t, int64_t, int64_t)>
#define FUNC_AD std::function<double(double, double)>
// parallel block
#define FUNC_DO std::function<void(uint64_t, uint64_t)>
// parallel_for block
#define FUNC_1D std::function<void(uint64_t, int64_t, int64_t, int64_t)>
#define FUNC_2D std::function<void(uint64_t, int64_t, int64_t, int64_t, int64_t, int64_t, int64_t)>
#define FUNC_3D std::function<void(uint64_t, int64_t, int64_t, int64_t, int64_t, int64_t, int64_t, int64_t, int64_t, int64_t)>
// aggregation lambda
#define LAMBDA_AL [&](int64_t _old, int64_t _new) -> int64_t
#define LAMBDA_AD [&](double _old, double _new) -> double
#define LAMBDA_SUML LAMBDA_AL {return _old + _new; }
#define LAMBDA_SUMD LAMBDA_AD {return _old + _new; }
// reduction lambda
#define PRAGMA_REDUCE_LONG [&] (uint64_t thread_id, int64_t start, int64_t stop, int64_t increment) mutable -> int64_t
#define PRAGMA_REDUCE_DOUBLE [&] (uint64_t thread_id, int64_t start, int64_t stop, int64_t increment) mutable -> double
// paralllel block lambda
#define PRAGMA_THREADS_DO [&](uint64_t thread_id, uint64_t numThreads) -> void
// paralllel_for lambdas
#define PRAGMA_THREADS_FOR [&](uint64_t thread_id, int64_t start, int64_t stop, int64_t increment) -> void
#define PRAGMA_THREADS_FOR_2D [&](uint64_t thread_id, int64_t start_x, int64_t stop_x, int64_t inc_x, int64_t start_y, int64_t stop_y, int64_t inc_y) -> void
#define PRAGMA_THREADS_FOR_3D [&](uint64_t thread_id, int64_t start_x, int64_t stop_x, int64_t inc_x, int64_t start_y, int64_t stop_y, int64_t inc_y, int64_t start_z, int64_t stop_z, int64_t inc_z) -> void
2019-06-06 14:21:15 +02:00
#endif //DEV_TESTS_OPENMP_PRAGMAS_H