3c4e959e21
* 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>
1003 lines
44 KiB
C++
1003 lines
44 KiB
C++
/*******************************************************************************
|
|
* 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
|
|
******************************************************************************/
|
|
|
|
|
|
#include <vector>
|
|
#include <pointercast.h>
|
|
#include "NativeOpExecutioner.h"
|
|
#include <types/types.h>
|
|
|
|
#include <pairwise_bool.h>
|
|
#include <broadcasting_bool.h>
|
|
#include <scalar_bool.h>
|
|
|
|
#include <loops/transform_float.h>
|
|
#include <loops/transform_bool.h>
|
|
#include <loops/transform_any.h>
|
|
#include <loops/transform_same.h>
|
|
#include <loops/transform_strict.h>
|
|
|
|
#include <loops/reduce_float.h>
|
|
#include <loops/reduce_same.h>
|
|
#include <loops/reduce_bool.h>
|
|
#include <loops/reduce_long.h>
|
|
|
|
#include <loops/broadcasting.h>
|
|
#include <loops/indexreduce.h>
|
|
#include <loops/pairwise_transform.h>
|
|
#include <loops/reduce_float.h>
|
|
#include <loops/reduce3.h>
|
|
#include <loops/summarystatsreduce.h>
|
|
#include <loops/transform_same.h>
|
|
#include <loops/scalar.h>
|
|
#include <loops/random.h>
|
|
#include <pointercast.h>
|
|
#include <exceptions/datatype_exception.h>
|
|
|
|
|
|
#ifdef _OPENMP
|
|
|
|
#include <omp.h>
|
|
|
|
#endif
|
|
|
|
|
|
|
|
|
|
////////////////////////////////////////////////////////////////////////
|
|
/**
|
|
*
|
|
* @param opNum
|
|
* @param hX
|
|
* @param hXShapeInfo
|
|
* @param extraParams
|
|
* @param hZ
|
|
* @param hZShapeInfo
|
|
*/
|
|
void NativeOpExecutioner::execIndexReduceScalar(nd4j::LaunchContext *lc, int opNum,
|
|
void *hX, Nd4jLong *hXShapeInfo,
|
|
void *dX, Nd4jLong *dXShapeInfo,
|
|
void *extraParams,
|
|
void *hZ, Nd4jLong *hZShapeInfo,
|
|
void *dZ, Nd4jLong *dZShapeInfo) {
|
|
|
|
#ifdef _OPENMP
|
|
omp_set_nested(1);
|
|
#endif
|
|
|
|
auto xType = nd4j::ArrayOptions::dataType(hXShapeInfo);
|
|
auto hz = reinterpret_cast<Nd4jLong*>(hZ);
|
|
|
|
BUILD_SINGLE_SELECTOR(xType, hz[0] = functions::indexreduce::IndexReduce, ::execScalar(opNum,hX,hXShapeInfo,extraParams), LIBND4J_TYPES);
|
|
}
|
|
|
|
////////////////////////////////////////////////////////////////////////
|
|
/**
|
|
*
|
|
* @param opNum
|
|
* @param hX
|
|
* @param hXShapeInfo
|
|
* @param extraParams
|
|
* @param hZ
|
|
* @param hZShapeInfo
|
|
* @param dimension
|
|
* @param dimensionLength
|
|
*/
|
|
|
|
void NativeOpExecutioner::execIndexReduce(nd4j::LaunchContext *lc,
|
|
int opNum,
|
|
void *hX, Nd4jLong *hXShapeInfo,
|
|
void *dX, Nd4jLong *dXShapeInfo,
|
|
void *extraParams,
|
|
void *hZ, Nd4jLong *hZShapeInfo,
|
|
void *dZ, Nd4jLong *dZShapeInfo,
|
|
int *dimension, int dimensionLength,
|
|
Nd4jLong *tadShapeInfo, Nd4jLong *tadOffsets) {
|
|
#ifdef _OPENMP
|
|
omp_set_nested(1);
|
|
#endif
|
|
|
|
auto xType = nd4j::ArrayOptions::dataType(hXShapeInfo);
|
|
Nd4jLong* hz = reinterpret_cast<Nd4jLong*>(hZ);
|
|
|
|
BUILD_SINGLE_SELECTOR(xType, functions::indexreduce::IndexReduce, ::exec(opNum, hX, hXShapeInfo, extraParams, hz, hZShapeInfo, dimension, dimensionLength, tadShapeInfo, tadOffsets), LIBND4J_TYPES);
|
|
// BUILD_SINGLE_SELECTOR(xType, functions::indexreduce::IndexReduce, ::exec(opNum, hX, hXShapeInfo, dX, dXShapeInfo, extraParams, hZ, hZShapeInfo, dZ, dZShapeInfo, dimension, dimensionLength, tadShapeInfo, tadOffsets), LIBND4J_TYPES);
|
|
}
|
|
|
|
////////////////////////////////////////////////////////////////////////
|
|
/**
|
|
*
|
|
* @param opNum
|
|
* @param hX
|
|
* @param hXShapeInfo
|
|
* @param hY
|
|
* @param hYShapeInfo
|
|
* @param hZ
|
|
* @param hZShapeInfo
|
|
* @param dimension
|
|
* @param dimensionLength
|
|
*/
|
|
|
|
void NativeOpExecutioner::execBroadcast(nd4j::LaunchContext *lc,
|
|
int opNum,
|
|
void *hX, Nd4jLong *hXShapeInfo,
|
|
void *dX, Nd4jLong *dXShapeInfo,
|
|
void *hY, Nd4jLong *hYShapeInfo,
|
|
void *dY, Nd4jLong *dYShapeInfo,
|
|
void *hZ, Nd4jLong *hZShapeInfo,
|
|
void *dZ, Nd4jLong *dZShapeInfo,
|
|
int *dimension, int dimensionLength,
|
|
Nd4jLong *tadOnlyShapeInfo, Nd4jLong *tadOffsets,
|
|
Nd4jLong *tadOnlyShapeInfoZ,Nd4jLong *tadOffsetsZ) {
|
|
|
|
#ifdef _OPENMP
|
|
omp_set_nested(1);
|
|
#endif
|
|
|
|
auto xType = nd4j::ArrayOptions::dataType(hXShapeInfo);
|
|
auto yType = nd4j::ArrayOptions::dataType(hYShapeInfo);
|
|
auto zType = nd4j::ArrayOptions::dataType(hZShapeInfo);
|
|
|
|
#ifdef __ND4J_EXPERIMENTAL__
|
|
BUILD_PAIRWISE_SELECTOR(xType, yType, zType, functions::broadcast::Broadcast, ::exec(opNum, hX, hXShapeInfo, hY, hYShapeInfo, hZ, hZShapeInfo, dimension, dimensionLength, tadOnlyShapeInfo, tadOffsets, tadOnlyShapeInfoZ, tadOffsetsZ), LIBND4J_TYPES, LIBND4J_TYPES);
|
|
#else
|
|
BUILD_SINGLE_SELECTOR_THRICE(xType, functions::broadcast::Broadcast, ::exec(opNum, hX, hXShapeInfo, hY, hYShapeInfo, hZ, hZShapeInfo, dimension, dimensionLength, tadOnlyShapeInfo, tadOffsets, tadOnlyShapeInfoZ, tadOffsetsZ), LIBND4J_TYPES);
|
|
#endif
|
|
}
|
|
|
|
void NativeOpExecutioner::execInverseBroadcast(nd4j::LaunchContext *lc,
|
|
int opNum,
|
|
void *hX, Nd4jLong *hXShapeInfo,
|
|
void *dX, Nd4jLong *dXShapeInfo,
|
|
void *hY, Nd4jLong *hYShapeInfo,
|
|
void *dY, Nd4jLong *dYShapeInfo,
|
|
void *hZ, Nd4jLong *hZShapeInfo,
|
|
void *dZ, Nd4jLong *dZShapeInfo,
|
|
int *dimension, int dimensionLength,
|
|
Nd4jLong *tadOnlyShapeInfo, Nd4jLong *tadOffsets,
|
|
Nd4jLong *tadOnlyShapeInfoZ,Nd4jLong *tadOffsetsZ) {
|
|
auto xType = nd4j::ArrayOptions::dataType(hXShapeInfo);
|
|
auto yType = nd4j::ArrayOptions::dataType(hYShapeInfo);
|
|
auto zType = nd4j::ArrayOptions::dataType(hZShapeInfo);
|
|
|
|
#ifdef _OPENMP
|
|
omp_set_nested(1);
|
|
#endif
|
|
|
|
if (!nd4j::Environment::getInstance()->isExperimentalBuild())
|
|
if ((yType != xType && yType != nd4j::DataType::BOOL) || xType != zType)
|
|
throw nd4j::datatype_exception::build("NativeOps::execBroadcast both operands must have same data type", xType, yType);
|
|
|
|
#ifdef __ND4J_EXPERIMENTAL__
|
|
BUILD_PAIRWISE_SELECTOR(xType, yType, zType, functions::broadcast::Broadcast, ::execInverse(opNum, hX, hXShapeInfo, hY, hYShapeInfo, hZ, hZShapeInfo, dimension, dimensionLength, tadOnlyShapeInfo, tadOffsets, tadOnlyShapeInfoZ, tadOffsetsZ), LIBND4J_TYPES, LIBND4J_TYPES);
|
|
#else
|
|
BUILD_SINGLE_SELECTOR_THRICE(xType, functions::broadcast::Broadcast, ::execInverse(opNum, hX, hXShapeInfo, hY, hYShapeInfo, hZ, hZShapeInfo, dimension, dimensionLength, tadOnlyShapeInfo, tadOffsets, tadOnlyShapeInfoZ, tadOffsetsZ), LIBND4J_TYPES);
|
|
#endif
|
|
|
|
}
|
|
|
|
|
|
////////////////////////////////////////////////////////////////////////
|
|
void NativeOpExecutioner::execBroadcastBool(nd4j::LaunchContext *lc,
|
|
int opNum,
|
|
void *hX, Nd4jLong *hXShapeInfo,
|
|
void *dX, Nd4jLong *dXShapeInfo,
|
|
void *hY, Nd4jLong *hYShapeInfo,
|
|
void *dY, Nd4jLong *dYShapeInfo,
|
|
void *hZ, Nd4jLong *hZShapeInfo,
|
|
void *dZ, Nd4jLong *dZShapeInfo,
|
|
int *dimension, int dimensionLength,
|
|
Nd4jLong *tadOnlyShapeInfo, Nd4jLong *tadOffsets,
|
|
Nd4jLong *tadOnlyShapeInfoZ,Nd4jLong *tadOffsetsZ) {
|
|
#ifdef _OPENMP
|
|
omp_set_nested(1);
|
|
#endif
|
|
|
|
auto xType = nd4j::ArrayOptions::dataType(hXShapeInfo);
|
|
auto yType = nd4j::ArrayOptions::dataType(hYShapeInfo);
|
|
auto zType = nd4j::ArrayOptions::dataType(hZShapeInfo);
|
|
|
|
BUILD_DOUBLE_SELECTOR(xType, zType, functions::broadcast::BroadcastBool, ::exec(opNum, hX, hXShapeInfo, hY, hYShapeInfo, hZ, hZShapeInfo, dimension, dimensionLength, tadOnlyShapeInfo, tadOffsets, tadOnlyShapeInfoZ, tadOffsetsZ), LIBND4J_TYPES, BOOL_TYPES);
|
|
}
|
|
|
|
void NativeOpExecutioner::execInverseBroadcastBool(nd4j::LaunchContext *lc,
|
|
int opNum,
|
|
void *hX, Nd4jLong *hXShapeInfo,
|
|
void *dX, Nd4jLong *dXShapeInfo,
|
|
void *hY, Nd4jLong *hYShapeInfo,
|
|
void *dY, Nd4jLong *dYShapeInfo,
|
|
void *hZ, Nd4jLong *hZShapeInfo,
|
|
void *dZ, Nd4jLong *dZShapeInfo,
|
|
int *dimension, int dimensionLength,
|
|
Nd4jLong *tadOnlyShapeInfo, Nd4jLong *tadOffsets,
|
|
Nd4jLong *tadOnlyShapeInfoZ,Nd4jLong *tadOffsetsZ) {
|
|
|
|
#ifdef _OPENMP
|
|
omp_set_nested(1);
|
|
#endif
|
|
|
|
auto xType = nd4j::ArrayOptions::dataType(hXShapeInfo);
|
|
auto yType = nd4j::ArrayOptions::dataType(hYShapeInfo);
|
|
auto zType = nd4j::ArrayOptions::dataType(hZShapeInfo);
|
|
|
|
if (!nd4j::Environment::getInstance()->isExperimentalBuild())
|
|
if (yType != xType || nd4j::DataType::BOOL != zType)
|
|
throw nd4j::datatype_exception::build("NativeOps::execInverseBroadcastBool both operands must have same data type", xType, yType);
|
|
|
|
BUILD_DOUBLE_SELECTOR(xType, zType, functions::broadcast::BroadcastBool, ::execInverse(opNum, hX, hXShapeInfo, hY, hYShapeInfo, hZ, hZShapeInfo, dimension, dimensionLength, tadOnlyShapeInfo, tadOffsets, tadOnlyShapeInfoZ, tadOffsetsZ), LIBND4J_TYPES, BOOL_TYPES);
|
|
}
|
|
|
|
////////////////////////////////////////////////////////////////////////
|
|
/**
|
|
*
|
|
* @param opNum
|
|
* @param hX
|
|
* @param xStride
|
|
* @param hY
|
|
* @param yStride
|
|
* @param hZ
|
|
* @param resultStride
|
|
* @param extraParams
|
|
* @param n
|
|
*/
|
|
void NativeOpExecutioner::execPairwiseTransform(nd4j::LaunchContext *lc,
|
|
int opNum,
|
|
void *hX, Nd4jLong *hXShapeInfo,
|
|
void *dX, Nd4jLong *dXShapeInfo,
|
|
void *hY, Nd4jLong *hYShapeInfo,
|
|
void *dY, Nd4jLong *dYShapeInfo,
|
|
void *hZ, Nd4jLong *hZShapeInfo,
|
|
void *dZ, Nd4jLong *dZShapeInfo,
|
|
void *extraParams) {
|
|
#ifdef _OPENMP
|
|
omp_set_nested(1);
|
|
#endif
|
|
|
|
auto xType = nd4j::ArrayOptions::dataType(hXShapeInfo);
|
|
auto yType = nd4j::ArrayOptions::dataType(hYShapeInfo);
|
|
auto zType = nd4j::ArrayOptions::dataType(hZShapeInfo);
|
|
|
|
#ifdef __ND4J_EXPERIMENTAL__
|
|
BUILD_PAIRWISE_SELECTOR(xType, yType, zType, functions::pairwise_transforms::PairWiseTransform, ::exec(opNum, hX, hXShapeInfo, hY, hYShapeInfo, hZ, hZShapeInfo, extraParams), LIBND4J_TYPES, LIBND4J_TYPES);
|
|
#else
|
|
BUILD_SINGLE_SELECTOR_THRICE(xType, functions::pairwise_transforms::PairWiseTransform, ::exec(opNum, hX, hXShapeInfo, hY, hYShapeInfo, hZ, hZShapeInfo, extraParams), LIBND4J_TYPES);
|
|
#endif
|
|
}
|
|
|
|
////////////////////////////////////////////////////////////////////////
|
|
void NativeOpExecutioner::execPairwiseBoolTransform(nd4j::LaunchContext *lc,
|
|
int opNum,
|
|
void *hX, Nd4jLong *hXShapeInfo,
|
|
void *dX, Nd4jLong *dXShapeInfo,
|
|
void *hY, Nd4jLong *hYShapeInfo,
|
|
void *dY, Nd4jLong *dYShapeInfo,
|
|
void *hZ, Nd4jLong *hZShapeInfo,
|
|
void *dZ, Nd4jLong *dZShapeInfo,
|
|
void *extraParams) {
|
|
#ifdef _OPENMP
|
|
omp_set_nested(1);
|
|
#endif
|
|
|
|
auto xType = nd4j::ArrayOptions::dataType(hXShapeInfo);
|
|
auto yType = nd4j::ArrayOptions::dataType(hYShapeInfo);
|
|
auto zType = nd4j::ArrayOptions::dataType(hZShapeInfo);
|
|
|
|
BUILD_DOUBLE_SELECTOR(xType, zType, functions::pairwise_transforms::PairWiseBoolTransform, ::exec(opNum, hX, hXShapeInfo, hY, hYShapeInfo, hZ, hZShapeInfo, extraParams), LIBND4J_TYPES, BOOL_TYPES);
|
|
}
|
|
|
|
////////////////////////////////////////////////////////////////////////
|
|
/**
|
|
*
|
|
* @param opNum
|
|
* @param hX
|
|
* @param hXShapeInfo
|
|
* @param extraParams
|
|
* @param hZ
|
|
* @param hZShapeInfo
|
|
*/
|
|
void NativeOpExecutioner::execReduceFloat(nd4j::LaunchContext *lc,
|
|
int opNum,
|
|
void *hX, Nd4jLong *hXShapeInfo,
|
|
void *dX, Nd4jLong *dXShapeInfo,
|
|
void *extraParams,
|
|
void *hZ, Nd4jLong *hZShapeInfo,
|
|
void *dZ, Nd4jLong *dZShapeInfo,
|
|
int *dimension, int dimensionLength,
|
|
Nd4jLong *tadShapeInfo, Nd4jLong *tadOffsets) {
|
|
|
|
#ifdef _OPENMP
|
|
omp_set_nested(1);
|
|
#endif
|
|
|
|
auto xType = nd4j::ArrayOptions::dataType(hXShapeInfo);
|
|
auto zType = nd4j::ArrayOptions::dataType(hZShapeInfo);
|
|
|
|
BUILD_DOUBLE_SELECTOR(xType, zType, functions::reduce::ReduceFloatFunction, ::exec(opNum, hX, hXShapeInfo, extraParams, hZ, hZShapeInfo, dimension, dimensionLength, tadShapeInfo, tadOffsets), LIBND4J_TYPES, FLOAT_TYPES);
|
|
}
|
|
|
|
////////////////////////////////////////////////////////////////////////
|
|
void NativeOpExecutioner::execReduceSame(nd4j::LaunchContext *lc,
|
|
int opNum,
|
|
void *hX, Nd4jLong *hXShapeInfo,
|
|
void *dX, Nd4jLong *dXShapeInfo,
|
|
void *extraParams,
|
|
void *hZ, Nd4jLong *hZShapeInfo,
|
|
void *dZ, Nd4jLong *dZShapeInfo,
|
|
int *dimension, int dimensionLength,
|
|
Nd4jLong *tadShapeInfo, Nd4jLong *tadOffsets) {
|
|
#ifdef _OPENMP
|
|
omp_set_nested(1);
|
|
#endif
|
|
|
|
auto xType = nd4j::ArrayOptions::dataType(hXShapeInfo);
|
|
auto zType = nd4j::ArrayOptions::dataType(hZShapeInfo);
|
|
|
|
BUILD_SINGLE_SELECTOR(xType, functions::reduce::ReduceSameFunction, ::exec(opNum, hX, hXShapeInfo, extraParams, hZ, hZShapeInfo, dimension, dimensionLength, tadShapeInfo, tadOffsets), LIBND4J_TYPES);
|
|
}
|
|
|
|
////////////////////////////////////////////////////////////////////////
|
|
void NativeOpExecutioner::execReduceBool(nd4j::LaunchContext *lc,
|
|
int opNum,
|
|
void *hX, Nd4jLong *hXShapeInfo,
|
|
void *dX, Nd4jLong *dXShapeInfo,
|
|
void *extraParams,
|
|
void *hZ, Nd4jLong *hZShapeInfo,
|
|
void *dZ, Nd4jLong *dZShapeInfo,
|
|
int *dimension, int dimensionLength,
|
|
Nd4jLong *tadShapeInfo, Nd4jLong *tadOffsets) {
|
|
#ifdef _OPENMP
|
|
omp_set_nested(1);
|
|
#endif
|
|
|
|
auto xType = nd4j::ArrayOptions::dataType(hXShapeInfo);
|
|
auto zType = nd4j::ArrayOptions::dataType(hZShapeInfo);
|
|
|
|
BUILD_DOUBLE_SELECTOR(xType, zType, functions::reduce::ReduceBoolFunction, ::exec(opNum, hX, hXShapeInfo, extraParams, hZ, hZShapeInfo, dimension, dimensionLength, tadShapeInfo, tadOffsets), LIBND4J_TYPES, BOOL_TYPES);
|
|
}
|
|
|
|
////////////////////////////////////////////////////////////////////////
|
|
void NativeOpExecutioner::execReduceLong(nd4j::LaunchContext *lc,
|
|
int opNum,
|
|
void *hX, Nd4jLong *hXShapeInfo,
|
|
void *dX, Nd4jLong *dXShapeInfo,
|
|
void *extraParams,
|
|
void *hZ, Nd4jLong *hZShapeInfo,
|
|
void *dZ, Nd4jLong *dZShapeInfo,
|
|
int *dimension, int dimensionLength,
|
|
Nd4jLong *tadShapeInfo, Nd4jLong *tadOffsets) {
|
|
#ifdef _OPENMP
|
|
omp_set_nested(1);
|
|
#endif
|
|
|
|
auto xType = nd4j::ArrayOptions::dataType(hXShapeInfo);
|
|
auto zType = nd4j::ArrayOptions::dataType(hZShapeInfo);
|
|
|
|
BUILD_DOUBLE_SELECTOR(xType, zType, functions::reduce::ReduceLongFunction, ::exec(opNum, hX, hXShapeInfo, extraParams, hZ, hZShapeInfo, dimension, dimensionLength, tadShapeInfo, tadOffsets), LIBND4J_TYPES, LONG_TYPES);
|
|
}
|
|
|
|
////////////////////////////////////////////////////////////////////////
|
|
/**
|
|
*
|
|
* @param opNum
|
|
* @param hX
|
|
* @param hXShapeInfo
|
|
* @param extraParams
|
|
* @return
|
|
*/
|
|
void NativeOpExecutioner::execReduceFloatScalar(nd4j::LaunchContext *lc,
|
|
int opNum,
|
|
void *hX, Nd4jLong *hXShapeInfo,
|
|
void *dX, Nd4jLong *dXShapeInfo,
|
|
void *extraParams,
|
|
void *hZ, Nd4jLong *hZShapeInfo,
|
|
void *dZ, Nd4jLong *dZShapeInfo) {
|
|
#ifdef _OPENMP
|
|
omp_set_nested(1);
|
|
#endif
|
|
|
|
auto xType = nd4j::ArrayOptions::dataType(hXShapeInfo);
|
|
auto zType = nd4j::ArrayOptions::dataType(hZShapeInfo);
|
|
|
|
BUILD_DOUBLE_SELECTOR(xType, zType, functions::reduce::ReduceFloatFunction, ::execScalar(opNum, hX, hXShapeInfo, extraParams, hZ, hZShapeInfo), LIBND4J_TYPES, FLOAT_TYPES);
|
|
}
|
|
|
|
////////////////////////////////////////////////////////////////////////
|
|
void NativeOpExecutioner::execReduceSameScalar(nd4j::LaunchContext *lc,
|
|
int opNum,
|
|
void *hX, Nd4jLong *hXShapeInfo,
|
|
void *dX, Nd4jLong *dXShapeInfo,
|
|
void *extraParams,
|
|
void *hZ, Nd4jLong *hZShapeInfo,
|
|
void *dZ, Nd4jLong *dZShapeInfo) {
|
|
#ifdef _OPENMP
|
|
omp_set_nested(1);
|
|
#endif
|
|
|
|
auto xType = nd4j::ArrayOptions::dataType(hXShapeInfo);
|
|
|
|
BUILD_SINGLE_SELECTOR(xType, functions::reduce::ReduceSameFunction, ::execScalar(opNum, hX, hXShapeInfo, extraParams, hZ, hZShapeInfo), LIBND4J_TYPES);
|
|
}
|
|
|
|
////////////////////////////////////////////////////////////////////////
|
|
void NativeOpExecutioner::execReduceBoolScalar(nd4j::LaunchContext *lc,
|
|
int opNum,
|
|
void *hX, Nd4jLong *hXShapeInfo,
|
|
void *dX, Nd4jLong *dXShapeInfo,
|
|
void *extraParams,
|
|
void *hZ, Nd4jLong *hZShapeInfo,
|
|
void *dZ, Nd4jLong *dZShapeInfo) {
|
|
|
|
#ifdef _OPENMP
|
|
omp_set_nested(1);
|
|
#endif
|
|
|
|
auto xType = nd4j::ArrayOptions::dataType(hXShapeInfo);
|
|
auto zType = nd4j::ArrayOptions::dataType(hZShapeInfo);
|
|
|
|
BUILD_DOUBLE_SELECTOR(xType, zType, functions::reduce::ReduceBoolFunction, ::execScalar(opNum, hX, hXShapeInfo, extraParams, hZ, hZShapeInfo), LIBND4J_TYPES, BOOL_TYPES);
|
|
}
|
|
|
|
////////////////////////////////////////////////////////////////////////
|
|
void NativeOpExecutioner::execReduceLongScalar(nd4j::LaunchContext *lc,
|
|
int opNum,
|
|
void *hX, Nd4jLong *hXShapeInfo,
|
|
void *dX, Nd4jLong *dXShapeInfo,
|
|
void *extraParams,
|
|
void *hZ, Nd4jLong *hZShapeInfo,
|
|
void *dZ, Nd4jLong *dZShapeInfo) {
|
|
#ifdef _OPENMP
|
|
omp_set_nested(1);
|
|
#endif
|
|
|
|
auto xType = nd4j::ArrayOptions::dataType(hXShapeInfo);
|
|
auto zType = nd4j::ArrayOptions::dataType(hZShapeInfo);
|
|
|
|
BUILD_DOUBLE_SELECTOR(xType, zType, functions::reduce::ReduceLongFunction, ::execScalar(opNum, hX, hXShapeInfo, extraParams, hZ, hZShapeInfo), LIBND4J_TYPES, LONG_TYPES);
|
|
}
|
|
|
|
|
|
////////////////////////////////////////////////////////////////////////
|
|
/**
|
|
*
|
|
* @param opNum
|
|
* @param hX
|
|
* @param hXShapeInfo
|
|
* @param extraParamsVals
|
|
* @param hY
|
|
* @param hYShapeInfo
|
|
* @param hZ
|
|
* @param hZShapeInfo
|
|
* @param dimension
|
|
* @param dimensionLength
|
|
*/
|
|
void NativeOpExecutioner::execReduce3Scalar(nd4j::LaunchContext *lc,
|
|
int opNum,
|
|
void *hX, Nd4jLong *hXShapeInfo,
|
|
void *dX, Nd4jLong *dXShapeInfo,
|
|
void *extraParamsVals,
|
|
void *hY, Nd4jLong *hYShapeInfo,
|
|
void *dY, Nd4jLong *dYShapeInfo,
|
|
void *hZ, Nd4jLong *hZShapeInfo,
|
|
void *dZ, Nd4jLong *dZShapeInfo) {
|
|
#ifdef _OPENMP
|
|
omp_set_nested(1);
|
|
#endif
|
|
|
|
auto xType = nd4j::ArrayOptions::dataType(hXShapeInfo);
|
|
auto zType = nd4j::ArrayOptions::dataType(hZShapeInfo);
|
|
|
|
|
|
BUILD_DOUBLE_SELECTOR(xType, zType, functions::reduce3::Reduce3, ::execScalar(opNum, hX, hXShapeInfo, extraParamsVals, hY, hYShapeInfo, hZ, hZShapeInfo), LIBND4J_TYPES, FLOAT_TYPES);
|
|
}
|
|
|
|
////////////////////////////////////////////////////////////////////////
|
|
/**
|
|
*
|
|
* @param opNum
|
|
* @param hX
|
|
* @param hXShapeInfo
|
|
* @param extraParamsVals
|
|
* @param hY
|
|
* @param hYShapeInfo
|
|
* @param hZ
|
|
* @param hZShapeInfo
|
|
*/
|
|
void NativeOpExecutioner::execReduce3(nd4j::LaunchContext *lc,
|
|
int opNum,
|
|
void *hX, Nd4jLong *hXShapeInfo,
|
|
void *dX, Nd4jLong *dXShapeInfo,
|
|
void *extraParamsVals,
|
|
void *hY, Nd4jLong *hYShapeInfo,
|
|
void *dY, Nd4jLong *dYShapeInfo,
|
|
void *hZ, Nd4jLong *hZShapeInfo,
|
|
void *dZ, Nd4jLong *dZShapeInfo) {
|
|
#ifdef _OPENMP
|
|
omp_set_nested(1);
|
|
#endif
|
|
|
|
auto xType = nd4j::ArrayOptions::dataType(hXShapeInfo);
|
|
auto zType = nd4j::ArrayOptions::dataType(hZShapeInfo);
|
|
|
|
BUILD_DOUBLE_SELECTOR(xType, zType, functions::reduce3::Reduce3, ::exec(opNum, hX, hXShapeInfo, extraParamsVals, hY, hYShapeInfo, hZ, hZShapeInfo, nullptr, 1), LIBND4J_TYPES, FLOAT_TYPES);
|
|
|
|
}
|
|
|
|
////////////////////////////////////////////////////////////////////////
|
|
void NativeOpExecutioner::execReduce3(nd4j::LaunchContext *lc,
|
|
int opNum,
|
|
void *hX, Nd4jLong *hXShapeInfo,
|
|
void *dX, Nd4jLong *dXShapeInfo,
|
|
void *extraParamsVals,
|
|
void *hY, Nd4jLong *hYShapeInfo,
|
|
void *dY, Nd4jLong *dYShapeInfo,
|
|
void *hZ, Nd4jLong *hZShapeInfo,
|
|
void *dZ, Nd4jLong *dZShapeInfo,
|
|
int *dimension, int dimensionLength,
|
|
Nd4jLong *xTadOnlyShapeInfo, Nd4jLong *xTadOffsets,
|
|
Nd4jLong *yTadOnlyShapeInfo, Nd4jLong *yTadOffsets) {
|
|
#ifdef _OPENMP
|
|
omp_set_nested(1);
|
|
#endif
|
|
|
|
auto xType = nd4j::ArrayOptions::dataType(hXShapeInfo);
|
|
auto zType = nd4j::ArrayOptions::dataType(hZShapeInfo);
|
|
|
|
BUILD_DOUBLE_SELECTOR(xType, zType, functions::reduce3::Reduce3, ::exec(opNum, hX, hXShapeInfo, extraParamsVals, hY, hYShapeInfo, hZ, hZShapeInfo, dimension, dimensionLength), LIBND4J_TYPES, FLOAT_TYPES);
|
|
}
|
|
|
|
|
|
////////////////////////////////////////////////////////////////////////
|
|
void NativeOpExecutioner::execReduce3All(nd4j::LaunchContext *lc,
|
|
int opNum,
|
|
void *hX, Nd4jLong *hXShapeInfo,
|
|
void *dX, Nd4jLong *dXShapeInfo,
|
|
void *extraParamsVals,
|
|
void *hY, Nd4jLong *hYShapeInfo,
|
|
void *dY, Nd4jLong *dYShapeInfo,
|
|
void *hZ, Nd4jLong *hZShapeInfo,
|
|
void *dZ, Nd4jLong *dZShapeInfo,
|
|
int *dimension, int dimensionLength,
|
|
Nd4jLong *xTadShapeInfo, Nd4jLong *xOffsets,
|
|
Nd4jLong *yTadShapeInfo, Nd4jLong *yOffsets) {
|
|
#ifdef _OPENMP
|
|
omp_set_nested(1);
|
|
#endif
|
|
|
|
auto xType = nd4j::ArrayOptions::dataType(hXShapeInfo);
|
|
auto zType = nd4j::ArrayOptions::dataType(hZShapeInfo);
|
|
|
|
BUILD_DOUBLE_SELECTOR(xType, zType, functions::reduce3::Reduce3, ::execAll(opNum, hX, hXShapeInfo, extraParamsVals, hY, hYShapeInfo, hZ, hZShapeInfo, dimension, dimensionLength, xTadShapeInfo, xOffsets, yTadShapeInfo, yOffsets), LIBND4J_TYPES, FLOAT_TYPES);
|
|
// BUILD_DOUBLE_SELECTOR(xType, zType, functions::reduce3::Reduce3, ::execAll(opNum, hX, hXShapeInfo, dX, dXShapeInfo, extraParamsVals, hY, hYShapeInfo, dY, dYShapeInfo, hZ, hZShapeInfo, dZ, dZShapeInfo, dimension, dimensionLength, xTadShapeInfo, xOffsets, yTadShapeInfo, yOffsets), LIBND4J_TYPES, FLOAT_TYPES);
|
|
}
|
|
|
|
////////////////////////////////////////////////////////////////////////
|
|
void NativeOpExecutioner::execReduce3TAD(nd4j::LaunchContext *lc,
|
|
int opNum,
|
|
void *hX, Nd4jLong *hXShapeInfo,
|
|
void *dX, Nd4jLong *dXShapeInfo,
|
|
void *extraParamsVals,
|
|
void *hY, Nd4jLong *hYShapeInfo,
|
|
void *dY, Nd4jLong *dYShapeInfo,
|
|
void *hZ, Nd4jLong *hZShapeInfo,
|
|
void *dZ, Nd4jLong *dZShapeInfo,
|
|
int *dimension, int dimensionLength,
|
|
Nd4jLong *tadShapeInfo, Nd4jLong *tadOffsets,
|
|
Nd4jLong *yTadShapeInfo, Nd4jLong *yTadOffsets) {
|
|
|
|
#ifdef _OPENMP
|
|
omp_set_nested(1);
|
|
#endif
|
|
|
|
auto xType = nd4j::ArrayOptions::dataType(hXShapeInfo);
|
|
auto zType = nd4j::ArrayOptions::dataType(hZShapeInfo);
|
|
|
|
BUILD_DOUBLE_SELECTOR(xType, zType, functions::reduce3::Reduce3, ::exec(opNum, hX, hXShapeInfo, extraParamsVals, hY, hYShapeInfo, hZ, hZShapeInfo, dimension, dimensionLength, tadShapeInfo, tadOffsets), LIBND4J_TYPES, FLOAT_TYPES);
|
|
// BUILD_DOUBLE_SELECTOR(xType, zType, functions::reduce3::Reduce3, ::exec(opNum, hX, hXShapeInfo, dX, dXShapeInfo, extraParamsVals, hY, hYShapeInfo, dY, dYShapeInfo, hZ, hZShapeInfo, dZ, dZShapeInfo, dimension, dimensionLength, tadShapeInfo, tadOffsets), LIBND4J_TYPES, FLOAT_TYPES);
|
|
}
|
|
|
|
|
|
////////////////////////////////////////////////////////////////////////
|
|
/**
|
|
*
|
|
* @param opNum
|
|
* @param hX
|
|
* @param xStride
|
|
* @param hZ
|
|
* @param resultStride
|
|
* @param scalar
|
|
* @param extraParams
|
|
* @param n
|
|
*/
|
|
void NativeOpExecutioner::execScalar(nd4j::LaunchContext *lc,
|
|
int opNum,
|
|
void *hX, Nd4jLong *hXShapeInfo,
|
|
void *dX, Nd4jLong *dXShapeInfo,
|
|
void *hZ, Nd4jLong *hZShapeInfo,
|
|
void *dZ, Nd4jLong *dZShapeInfo,
|
|
void *hScalar, Nd4jLong *hScalarShapeInfo,
|
|
void *dScalar, Nd4jLong *dScalarShapeInfo,
|
|
void *extraParams, bool allowParallelism) {
|
|
#ifdef _OPENMP
|
|
omp_set_nested(1);
|
|
#endif
|
|
|
|
auto xType = nd4j::ArrayOptions::dataType(hXShapeInfo);
|
|
auto yType = nd4j::ArrayOptions::dataType(hScalarShapeInfo);
|
|
auto zType = nd4j::ArrayOptions::dataType(hZShapeInfo);
|
|
|
|
#ifdef __ND4J_EXPERIMENTAL__
|
|
BUILD_PAIRWISE_SELECTOR(xType, yType, zType, functions::scalar::ScalarTransform, ::transform(opNum, hX, hXShapeInfo, hZ, hZShapeInfo, hScalar, extraParams), LIBND4J_TYPES, LIBND4J_TYPES);
|
|
#else
|
|
if (xType != yType || xType != zType)
|
|
throw nd4j::datatype_exception::build("NativeOpExecutioner::execScalar", zType, xType, yType);
|
|
|
|
BUILD_SINGLE_SELECTOR_THRICE(xType, functions::scalar::ScalarTransform, ::transform(opNum, hX, hXShapeInfo, hZ, hZShapeInfo, hScalar, extraParams, allowParallelism), LIBND4J_TYPES);
|
|
#endif
|
|
}
|
|
|
|
////////////////////////////////////////////////////////////////////////
|
|
void NativeOpExecutioner::execScalar(nd4j::LaunchContext *lc,
|
|
int opNum,
|
|
void *hX, Nd4jLong *hXShapeInfo,
|
|
void *dX, Nd4jLong *dXShapeInfo,
|
|
void *extraParams,
|
|
void *hZ, Nd4jLong *hZShapeInfo,
|
|
void *dZ, Nd4jLong *dZShapeInfo,
|
|
void *hScalars, Nd4jLong *hScalarShapeInfo,
|
|
void *dScalars, Nd4jLong *dScalarShapeInfo,
|
|
int *dimension, int dimensionLength,
|
|
Nd4jLong *tadShapeInfo, Nd4jLong *tadOffsets,
|
|
Nd4jLong *tadShapeInfoZ, Nd4jLong *tadOffsetsZ) {
|
|
#ifdef _OPENMP
|
|
omp_set_nested(1);
|
|
#endif
|
|
|
|
auto xType = nd4j::ArrayOptions::dataType(hXShapeInfo);
|
|
auto yType = nd4j::ArrayOptions::dataType(hScalarShapeInfo);
|
|
auto zType = nd4j::ArrayOptions::dataType(hZShapeInfo);
|
|
|
|
#ifdef __ND4J_EXPERIMENTAL__
|
|
BUILD_PAIRWISE_SELECTOR(xType, yType, zType, functions::scalar::ScalarTransform, ::transform(opNum, hX, hXShapeInfo, extraParams, hZ, hZShapeInfo, hScalars, dimension, dimensionLength, tadShapeInfo, tadOffsets, tadShapeInfoZ, tadOffsetsZ), LIBND4J_TYPES, LIBND4J_TYPES);
|
|
#else
|
|
if (xType != yType || xType != zType)
|
|
throw nd4j::datatype_exception::build("NativeOpExecutioner::execScalar", zType, xType, yType);
|
|
|
|
BUILD_SINGLE_SELECTOR_THRICE(xType, functions::scalar::ScalarTransform, ::transform(opNum, hX, hXShapeInfo, extraParams, hZ, hZShapeInfo, hScalars, dimension, dimensionLength, tadShapeInfo, tadOffsets, tadShapeInfoZ, tadOffsetsZ), LIBND4J_TYPES);
|
|
#endif
|
|
}
|
|
|
|
////////////////////////////////////////////////////////////////////////
|
|
void NativeOpExecutioner::execScalarBool(nd4j::LaunchContext *lc,
|
|
int opNum,
|
|
void *hX, Nd4jLong *hXShapeInfo,
|
|
void *dX, Nd4jLong *dXShapeInfo,
|
|
void *hZ, Nd4jLong *hZShapeInfo,
|
|
void *dZ, Nd4jLong *dZShapeInfo,
|
|
void *hScalar, Nd4jLong *hSscalarShapeInfo,
|
|
void *dScalar, Nd4jLong *dSscalarShapeInfo,
|
|
void *extraParams, bool allowParallelism) {
|
|
|
|
#ifdef _OPENMP
|
|
omp_set_nested(1);
|
|
#endif
|
|
|
|
auto xType = nd4j::ArrayOptions::dataType(hXShapeInfo);
|
|
auto yType = nd4j::ArrayOptions::dataType(hSscalarShapeInfo);
|
|
auto zType = nd4j::ArrayOptions::dataType(hZShapeInfo);
|
|
|
|
if (xType != yType)
|
|
throw nd4j::datatype_exception::build("NativeOpExecutioner::execScalarBool", xType, yType);
|
|
|
|
if (zType != nd4j::DataType::BOOL)
|
|
throw nd4j::datatype_exception::build("NativeOpExecutioner::execScalarBool", nd4j::DataType::BOOL, zType);
|
|
|
|
BUILD_DOUBLE_SELECTOR(xType, zType, functions::scalar::ScalarBoolTransform, ::transform(opNum, hX, hXShapeInfo, hZ, hZShapeInfo, hScalar, extraParams), LIBND4J_TYPES, BOOL_TYPES);
|
|
}
|
|
|
|
////////////////////////////////////////////////////////////////////////
|
|
void NativeOpExecutioner::execScalarBool(nd4j::LaunchContext *lc,
|
|
int opNum,
|
|
void *hX, Nd4jLong *hXShapeInfo,
|
|
void *dX, Nd4jLong *dXShapeInfo,
|
|
void *extraParams,
|
|
void *hZ, Nd4jLong *hZShapeInfo,
|
|
void *dZ, Nd4jLong *dZShapeInfo,
|
|
void *hScalars, Nd4jLong *hScalarShapeInfo,
|
|
void *dScalars, Nd4jLong *dScalarShapeInfo,
|
|
int *dimension, int dimensionLength,
|
|
Nd4jLong *tadShapeInfo, Nd4jLong *tadOffsets,
|
|
Nd4jLong *tadShapeInfoZ, Nd4jLong *tadOffsetsZ) {
|
|
#ifdef _OPENMP
|
|
omp_set_nested(1);
|
|
#endif
|
|
|
|
auto xType = nd4j::ArrayOptions::dataType(hXShapeInfo);
|
|
auto yType = nd4j::ArrayOptions::dataType(hScalarShapeInfo);
|
|
auto zType = nd4j::ArrayOptions::dataType(hZShapeInfo);
|
|
|
|
if (xType != yType)
|
|
throw nd4j::datatype_exception::build("NativeOpExecutioner::execScalarBool", xType, yType);
|
|
|
|
if (zType != nd4j::DataType::BOOL)
|
|
throw nd4j::datatype_exception::build("NativeOpExecutioner::execScalarBool", nd4j::DataType::BOOL, zType);
|
|
|
|
BUILD_DOUBLE_SELECTOR(xType, zType, functions::scalar::ScalarBoolTransform, ::transform(opNum, hX, hXShapeInfo, extraParams, hZ, hZShapeInfo, hScalars, dimension, dimensionLength, tadShapeInfo, tadOffsets, tadShapeInfoZ, tadOffsetsZ), LIBND4J_TYPES, BOOL_TYPES);
|
|
}
|
|
|
|
////////////////////////////////////////////////////////////////////////
|
|
/**
|
|
*
|
|
* @param opNum
|
|
* @param hX
|
|
* @param hXShapeInfo
|
|
* @param extraParams
|
|
* @param hZ
|
|
* @param hZShapeInfo
|
|
*/
|
|
void NativeOpExecutioner::execSummaryStats(nd4j::LaunchContext *lc,
|
|
int opNum,
|
|
void *hX, Nd4jLong *hXShapeInfo,
|
|
void *dX, Nd4jLong *dXShapeInfo,
|
|
void *extraParams,
|
|
void *hZ, Nd4jLong *hZShapeInfo,
|
|
void *dZ, Nd4jLong *dZShapeInfo,
|
|
bool biasCorrected) {
|
|
#ifdef _OPENMP
|
|
omp_set_nested(1);
|
|
#endif
|
|
|
|
auto xType = nd4j::ArrayOptions::dataType(hXShapeInfo);
|
|
auto zType = nd4j::ArrayOptions::dataType(hZShapeInfo);
|
|
|
|
BUILD_DOUBLE_SELECTOR(xType, zType, functions::summarystats::SummaryStatsReduce, ::exec(opNum, biasCorrected, hX, hXShapeInfo, extraParams, hZ, hZShapeInfo, nullptr, 1), LIBND4J_TYPES, FLOAT_TYPES);
|
|
}
|
|
|
|
////////////////////////////////////////////////////////////////////////
|
|
/**
|
|
*
|
|
* @param opNum
|
|
* @param hX
|
|
* @param hXShapeInfo
|
|
* @param extraParams
|
|
* @param hZ
|
|
* @param hZShapeInfo
|
|
*/
|
|
void NativeOpExecutioner::execSummaryStatsScalar(nd4j::LaunchContext *lc,
|
|
int opNum,
|
|
void *hX, Nd4jLong *hXShapeInfo,
|
|
void *dX, Nd4jLong *dXShapeInfo,
|
|
void *extraParams,
|
|
void *hZ, Nd4jLong *hZShapeInfo,
|
|
void *dZ, Nd4jLong *dZShapeInfo,
|
|
bool biasCorrected) {
|
|
#ifdef _OPENMP
|
|
omp_set_nested(1);
|
|
#endif
|
|
|
|
auto xType = nd4j::ArrayOptions::dataType(hXShapeInfo);
|
|
auto zType = nd4j::ArrayOptions::dataType(hZShapeInfo);
|
|
|
|
BUILD_DOUBLE_SELECTOR(xType, zType, functions::summarystats::SummaryStatsReduce, ::execScalar(opNum, biasCorrected, hX, hXShapeInfo, extraParams, hZ, hZShapeInfo), LIBND4J_TYPES, FLOAT_TYPES);
|
|
}
|
|
|
|
////////////////////////////////////////////////////////////////////////
|
|
/**
|
|
*
|
|
* @param opNum
|
|
* @param hX
|
|
* @param hXShapeInfo
|
|
* @param extraParams
|
|
* @param hZ
|
|
* @param hZShapeInfo
|
|
* @param dimension
|
|
* @param dimensionLength
|
|
*/
|
|
void NativeOpExecutioner::execSummaryStats(nd4j::LaunchContext *lc,
|
|
int opNum,
|
|
void *hX, Nd4jLong *hXShapeInfo,
|
|
void *dX, Nd4jLong *dXShapeInfo,
|
|
void *extraParams,
|
|
void *hZ, Nd4jLong *hZShapeInfo,
|
|
void *dZ, Nd4jLong *dZShapeInfo,
|
|
int *dimension, int dimensionLength,
|
|
Nd4jLong *tadShapeInfo, Nd4jLong *tadOffsets,
|
|
bool biasCorrected) {
|
|
#ifdef _OPENMP
|
|
omp_set_nested(1);
|
|
#endif
|
|
|
|
auto xType = nd4j::ArrayOptions::dataType(hXShapeInfo);
|
|
auto zType = nd4j::ArrayOptions::dataType(hZShapeInfo);
|
|
|
|
BUILD_DOUBLE_SELECTOR(xType, zType, functions::summarystats::SummaryStatsReduce, ::exec(opNum, biasCorrected, hX, hXShapeInfo, extraParams, hZ, hZShapeInfo, dimension, dimensionLength), LIBND4J_TYPES, FLOAT_TYPES);
|
|
}
|
|
|
|
|
|
////////////////////////////////////////////////////////////////////////
|
|
/**
|
|
*
|
|
* @param opNum
|
|
* @param hX
|
|
* @param xStride
|
|
* @param hZ
|
|
* @param resultStride
|
|
* @param extraParams
|
|
* @param n
|
|
*/
|
|
void NativeOpExecutioner::execTransformFloat(nd4j::LaunchContext *lc,
|
|
int opNum,
|
|
void *hX, Nd4jLong *hXShapeInfo,
|
|
void *dX, Nd4jLong *dXShapeInfo,
|
|
void *hZ, Nd4jLong *hZShapeInfo,
|
|
void *dZ, Nd4jLong *dZShapeInfo,
|
|
void *extraParams,
|
|
Nd4jLong *tadShapeInfo, Nd4jLong *tadOffsets) {
|
|
#ifdef _OPENMP
|
|
omp_set_nested(1);
|
|
#endif
|
|
|
|
auto xType = nd4j::ArrayOptions::dataType(hXShapeInfo);
|
|
auto zType = nd4j::ArrayOptions::dataType(hZShapeInfo);
|
|
|
|
BUILD_DOUBLE_SELECTOR(xType, zType, functions::transform::TransformFloat, ::exec(opNum, hX, hXShapeInfo, hZ, hZShapeInfo, extraParams, tadShapeInfo, tadOffsets), LIBND4J_TYPES, FLOAT_TYPES);
|
|
}
|
|
|
|
////////////////////////////////////////////////////////////////////////
|
|
void NativeOpExecutioner::execTransformBool(nd4j::LaunchContext *lc,
|
|
int opNum,
|
|
void *hX, Nd4jLong *hXShapeInfo,
|
|
void *dX, Nd4jLong *dXShapeInfo,
|
|
void *hZ, Nd4jLong *hZShapeInfo,
|
|
void *dZ, Nd4jLong *dZShapeInfo,
|
|
void *extraParams,
|
|
Nd4jLong *tadShapeInfo, Nd4jLong *tadOffsets) {
|
|
#ifdef _OPENMP
|
|
omp_set_nested(1);
|
|
#endif
|
|
|
|
auto xType = nd4j::ArrayOptions::dataType(hXShapeInfo);
|
|
auto zType = nd4j::ArrayOptions::dataType(hZShapeInfo);
|
|
|
|
BUILD_DOUBLE_SELECTOR(xType, zType, functions::transform::TransformBool, ::exec(opNum, hX, hXShapeInfo, hZ, hZShapeInfo, extraParams, tadShapeInfo, tadOffsets), LIBND4J_TYPES, BOOL_TYPES);
|
|
}
|
|
|
|
////////////////////////////////////////////////////////////////////////
|
|
void NativeOpExecutioner::execTransformAny(nd4j::LaunchContext *lc,
|
|
int opNum,
|
|
void *hX, Nd4jLong *hXShapeInfo,
|
|
void *dX, Nd4jLong *dXShapeInfo,
|
|
void *hZ, Nd4jLong *hZShapeInfo,
|
|
void *dZ, Nd4jLong *dZShapeInfo,
|
|
void *extraParams,
|
|
Nd4jLong *tadShapeInfo, Nd4jLong *tadOffsets, bool allowParallelism) {
|
|
#ifdef _OPENMP
|
|
omp_set_nested(1);
|
|
#endif
|
|
|
|
auto xType = nd4j::ArrayOptions::dataType(hXShapeInfo);
|
|
auto zType = nd4j::ArrayOptions::dataType(hZShapeInfo);
|
|
|
|
BUILD_DOUBLE_SELECTOR(xType, zType, functions::transform::TransformAny, ::exec(opNum, hX, hXShapeInfo, hZ, hZShapeInfo, extraParams, tadShapeInfo, tadOffsets, allowParallelism), LIBND4J_TYPES, LIBND4J_TYPES);
|
|
}
|
|
|
|
////////////////////////////////////////////////////////////////////////
|
|
void NativeOpExecutioner::execTransformSame(nd4j::LaunchContext *lc,
|
|
int opNum,
|
|
void *hX, Nd4jLong *hXShapeInfo,
|
|
void *dX, Nd4jLong *dXShapeInfo,
|
|
void *hZ, Nd4jLong *hZShapeInfo,
|
|
void *dZ, Nd4jLong *dZShapeInfo,
|
|
void *extraParams,
|
|
Nd4jLong *tadShapeInfo, Nd4jLong *tadOffsets) {
|
|
#ifdef _OPENMP
|
|
omp_set_nested(1);
|
|
#endif
|
|
|
|
auto xType = nd4j::ArrayOptions::dataType(hXShapeInfo);
|
|
auto zType = nd4j::ArrayOptions::dataType(hZShapeInfo);
|
|
|
|
BUILD_SINGLE_SELECTOR(xType, functions::transform::TransformSame, ::exec(opNum, hX, hXShapeInfo, hZ, hZShapeInfo, extraParams, tadShapeInfo, tadOffsets), LIBND4J_TYPES);
|
|
}
|
|
|
|
////////////////////////////////////////////////////////////////////////
|
|
void NativeOpExecutioner::execTransformStrict(nd4j::LaunchContext *lc,
|
|
int opNum,
|
|
void *hX, Nd4jLong *hXShapeInfo,
|
|
void *dX, Nd4jLong *dXShapeInfo,
|
|
void *hZ, Nd4jLong *hZShapeInfo,
|
|
void *dZ, Nd4jLong *dZShapeInfo,
|
|
void *extraParams,
|
|
Nd4jLong *tadShapeInfo, Nd4jLong *tadOffsets) {
|
|
#ifdef _OPENMP
|
|
omp_set_nested(1);
|
|
#endif
|
|
|
|
auto xType = nd4j::ArrayOptions::dataType(hXShapeInfo);
|
|
auto zType = nd4j::ArrayOptions::dataType(hZShapeInfo);
|
|
|
|
BUILD_SINGLE_SELECTOR(xType, functions::transform::TransformStrict, ::exec(opNum, hX, hXShapeInfo, hZ, hZShapeInfo, extraParams, tadShapeInfo, tadOffsets), FLOAT_TYPES);
|
|
}
|
|
|
|
////////////////////////////////////////////////////////////////////////
|
|
void NativeOpExecutioner::execRandom(nd4j::LaunchContext *lc,
|
|
int opNum,
|
|
Nd4jPointer state,
|
|
void *hZ, Nd4jLong *hZShapeInfo,
|
|
void *dZ, Nd4jLong *dZShapeInfo,
|
|
void *extraArguments) {
|
|
#ifdef _OPENMP
|
|
omp_set_nested(1);
|
|
#endif
|
|
|
|
auto zType = nd4j::ArrayOptions::dataType(hZShapeInfo);
|
|
|
|
BUILD_SINGLE_SELECTOR(zType, functions::random::RandomFunction, ::execTransform(opNum, state, hZ, hZShapeInfo, extraArguments), FLOAT_TYPES);
|
|
|
|
auto rng = reinterpret_cast<nd4j::graph::RandomGenerator*>(state);
|
|
rng->rewindH(shape::length(hZShapeInfo));
|
|
}
|
|
|
|
////////////////////////////////////////////////////////////////////////
|
|
void NativeOpExecutioner::execRandom(nd4j::LaunchContext *lc,
|
|
int opNum,
|
|
Nd4jPointer state,
|
|
void *hX, Nd4jLong *hXShapeInfo,
|
|
void *dX, Nd4jLong *dXShapeInfo,
|
|
void *hZ, Nd4jLong *hZShapeInfo,
|
|
void *dZ, Nd4jLong *dZShapeInfo,
|
|
void *extraArguments) {
|
|
#ifdef _OPENMP
|
|
omp_set_nested(1);
|
|
#endif
|
|
|
|
auto zType = nd4j::ArrayOptions::dataType(hZShapeInfo);
|
|
|
|
BUILD_SINGLE_SELECTOR(zType, functions::random::RandomFunction, ::execTransform(opNum, state, hX, hXShapeInfo, hZ, hZShapeInfo, extraArguments), FLOAT_TYPES);
|
|
|
|
auto rng = reinterpret_cast<nd4j::graph::RandomGenerator*>(state);
|
|
rng->rewindH(shape::length(hZShapeInfo));
|
|
}
|
|
|
|
////////////////////////////////////////////////////////////////////////
|
|
void NativeOpExecutioner::execRandom(nd4j::LaunchContext *lc,
|
|
int opNum,
|
|
Nd4jPointer state,
|
|
void *hX, Nd4jLong *hXShapeInfo,
|
|
void *dX, Nd4jLong *dXShapeInfo,
|
|
void *hY, Nd4jLong *hYShapeInfo,
|
|
void *dY, Nd4jLong *dYShapeInfo,
|
|
void *hZ, Nd4jLong *hZShapeInfo,
|
|
void *dZ, Nd4jLong *dZShapeInfo,
|
|
void *extraArguments) {
|
|
#ifdef _OPENMP
|
|
omp_set_nested(1);
|
|
#endif
|
|
|
|
auto xType = nd4j::ArrayOptions::dataType(hZShapeInfo);
|
|
|
|
BUILD_SINGLE_SELECTOR(xType, functions::random::RandomFunction, ::execTransform(opNum, state, hX, hXShapeInfo, hY, hYShapeInfo, hZ, hZShapeInfo, extraArguments), FLOAT_TYPES);
|
|
|
|
auto rng = reinterpret_cast<nd4j::graph::RandomGenerator*>(state);
|
|
rng->rewindH(shape::length(hZShapeInfo));
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|