cavis/libnd4j/blas/NativeOpExecutioner.h

609 lines
26 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
******************************************************************************/
//
// Created by agibsonccc on 1/28/16.
//
#ifndef NATIVEOPERATIONS_NATIVEOPEXCUTIONER_H
#define NATIVEOPERATIONS_NATIVEOPEXCUTIONER_H
#include <types/types.h>
#include <dll.h>
#include <loops/aggregates.h>
#include <ops/specials.h>
#include <ops/specials_sparse.h>
#include <execution/LaunchContext.h>
/**
* Native op executioner:
*
*/
class ND4J_EXPORT NativeOpExecutioner {
public:
/**
*
* @param opNum
* @param x
* @param xShapeInfo
* @param extraParams
* @param result
* @param resultShapeInfo
*/
static void execIndexReduceScalar(nd4j::LaunchContext *lc,
int opNum,
void *hX, Nd4jLong *hXShapeInfo,
void *dX, Nd4jLong *dXShapeInfo,
void *extraParams,
void *hZ, Nd4jLong *hZShapeInfo,
void *dZ, Nd4jLong *dZShapeInfo);
/**
*
* @param opNum
* @param x
* @param xShapeInfo
* @param extraParamsVals
* @param y
* @param yShapeInfo
* @param result
* @param resultShapeInfoBuffer
* @param dimension
* @param dimensionLength
*/
static void 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);
/**
*
* @param opNum
* @param x
* @param xShapeInfo
* @param extraParamsVals
* @param y
* @param yShapeInfo
* @param result
* @param resultShapeInfo
*/
static void 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);
/**
*
* @param opNum
* @param x
* @param xShapeInfo
* @param extraParamsVals
* @param y
* @param yShapeInfo
* @param result
* @param resultShapeInfoBuffer
* @param dimension
* @param dimensionLength
*/
static void 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);
static void 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);
/**
*
* @param opNum
* @param x
* @param xShapeInfo
* @param extraParams
* @param result
* @param resultShapeInfoBuffer
* @param dimension
* @param dimensionLength
*/
static void 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);
/**
*
* @param opNum
* @param x
* @param xStride
* @param result
* @param resultStride
* @param scalar
* @param extraParams
* @param n
*/
static void 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 *hSscalarShapeInfo,
void *dScalar, Nd4jLong *dSscalarShapeInfo,
[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
void *extraParams, bool allowParallelism = true);
2019-06-06 14:21:15 +02:00
static void 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,
[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
void *extraParams, bool allowParallelism = true);
2019-06-06 14:21:15 +02:00
static void 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);
static void 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);
/**
*
* @param opNum
* @param x
* @param xShapeInfo
* @param y
* @param yShapeInfo
* @param result
* @param resultShapeInfo
* @param dimension
* @param dimensionLength
*/
static void 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);
static void execInverseBroadcast(nd4j::LaunchContext *lc,
int opNum,
void *x, Nd4jLong *xShapeInfo,
void *dX, Nd4jLong *dXShapeInfo,
void *y, Nd4jLong *yShapeInfo,
void *dY, Nd4jLong *dYShapeInfo,
void *result, Nd4jLong *resultShapeInfo,
void *dZ, Nd4jLong *dZShapeInfo,
int *dimension, int dimensionLength,
Nd4jLong *tadOnlyShapeInfo, Nd4jLong *tadOffsets,
Nd4jLong *tadOnlyShapeInfoZ, Nd4jLong *tadOffsetsZ);
static void 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);
static void execInverseBroadcastBool(nd4j::LaunchContext *lc,
int opNum,
void *x, Nd4jLong *xShapeInfo,
void *dX, Nd4jLong *dXShapeInfo,
void *y, Nd4jLong *yShapeInfo,
void *dY, Nd4jLong *dYShapeInfo,
void *result, Nd4jLong *resultShapeInfo,
void *dZ, Nd4jLong *dZShapeInfo,
int *dimension, int dimensionLength,
Nd4jLong *tadOnlyShapeInfo, Nd4jLong *tadOffsets,
Nd4jLong *tadOnlyShapeInfoZ, Nd4jLong *tadOffsetsZ);
/**
*
* @param opNum
* @param dx
* @param xStride
* @param y
* @param yStride
* @param result
* @param resultStride
* @param extraParams
* @param n
*/
static void 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);
static void 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);
/**
*
* @param opNum
* @param dx
* @param xStride
* @param result
* @param resultStride
* @param extraParams
* @param n
*/
static void 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);
static void execTransformAny(nd4j::LaunchContext *lc,
int opNum,
void *hX, Nd4jLong *hXShapeInfo,
void *dX, Nd4jLong *dXShapeInfo,
void *hZ, Nd4jLong *hZShapeInfo,
void *dZ, Nd4jLong *dZShapeInfo,
void *extraParams,
[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
Nd4jLong *tadShapeInfo, Nd4jLong *tadOffsets, bool allowParallelism = true);
2019-06-06 14:21:15 +02:00
static void 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);
static void 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);
static void 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);
/**
*
* @param opNum
* @param x
* @param xShapeInfo
* @param extraParams
* @param result
* @param resultShapeInfo
*/
static void 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);
static void 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);
static void 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);
static void 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);
/**
*
* @param opNum
* @param x
* @param xShapeInfo
* @param extraParams
* @return
*/
static void execReduceFloatScalar(nd4j::LaunchContext *lc,
int opNum,
void *hX, Nd4jLong *hXShapeInfo,
void *dX, Nd4jLong *dXShapeInfo,
void *extraParams,
void *hZ, Nd4jLong *hZShapeInfo,
void *dZ, Nd4jLong *dZShapeInfo);
static void execReduceBoolScalar(nd4j::LaunchContext *lc,
int opNum,
void *hX, Nd4jLong *hXShapeInfo,
void *dX, Nd4jLong *dXShapeInfo,
void *extraParams,
void *hZ, Nd4jLong *hZShapeInfo,
void *dZ, Nd4jLong *dZShapeInfo);
static void execReduceSameScalar(nd4j::LaunchContext *lc,
int opNum,
void *hX, Nd4jLong *hXShapeInfo,
void *dX, Nd4jLong *dXShapeInfo,
void *extraParams,
void *hZ, Nd4jLong *hZShapeInfo,
void *dZ, Nd4jLong *dZShapeInfo);
static void execReduceLongScalar(nd4j::LaunchContext *lc,
int opNum,
void *hX, Nd4jLong *hXShapeInfo,
void *dX, Nd4jLong *dXShapeInfo,
void *extraParams,
void *hZ, Nd4jLong *hZShapeInfo,
void *dZ, Nd4jLong *dZShapeInfo);
static void 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);
/**
*
* @param opNum
* @param x
* @param xShapeInfo
* @param extraParams
* @param result
* @param resultShapeInfoBuffer
* @param dimension
* @param dimensionLength
*/
static void 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);
/**
*
* @param opNum
* @param x
* @param xShapeInfo
* @param extraParams
* @param result
* @param resultShapeInfo
*/
static void 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);
/**
*
* @param opNum
* @param x
* @param xShapeInfo
* @param extraParams
* @param result
* @param resultShapeInfo
*/
static void 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);
static void execRandom(nd4j::LaunchContext *lc,
int opNum,
Nd4jPointer state,
void *hZ, Nd4jLong *hZShapeBuffer,
void *dZ, Nd4jLong *dZShapeBuffer,
void *extraArguments);
static void execRandom(nd4j::LaunchContext *lc,
int opNum,
Nd4jPointer state,
void *hX, Nd4jLong *hXShapeBuffer,
void *dX, Nd4jLong *dXShapeBuffer,
void *hZ, Nd4jLong *hZShapeBuffer,
void *dZ, Nd4jLong *dZShapeBuffer,
void *extraArguments);
static void execRandom(nd4j::LaunchContext *lc,
int opNum,
Nd4jPointer state,
void *hX, Nd4jLong *hXShapeBuffer,
void *dX, Nd4jLong *dXShapeBuffer,
void *hY, Nd4jLong *hYShapeBuffer,
void *dY, Nd4jLong *dYShapeBuffer,
void *hZ, Nd4jLong *hZShapeBuffer,
void *dZ, Nd4jLong *dZShapeBuffer,
void *extraArguments);
template <typename X>
static FORCEINLINE void execAggregate(nd4j::LaunchContext *lc,
int opNum,
void **varguments,
int numArguments,
Nd4jLong **shapeArguments,
int numShapeArguments,
int *indexArguments,
int numIndexArguments,
int **intArrays,
int numIntArrays,
void *vrealArguments,
int numRealArguments) {
auto arguments = reinterpret_cast<X **>(varguments);
auto realArguments = reinterpret_cast<X *>(vrealArguments);
functions::aggregate::AggregatedFunction<X>::exec(opNum, arguments, numArguments, shapeArguments, numShapeArguments, indexArguments, numIndexArguments, intArrays, numIntArrays, realArguments, numRealArguments);
}
inline static void execSort(void *x, Nd4jLong *xShapeInfo, bool descending) {
auto xType = nd4j::ArrayOptions::dataType(xShapeInfo);
BUILD_SINGLE_SELECTOR(xType, nd4j::SpecialMethods, ::sortGeneric(x, xShapeInfo, descending), LIBND4J_TYPES);
}
static void execSort(void *x, Nd4jLong *xShapeInfo, int *dimension, int dimensionLength, Nd4jLong *tadShapeInfo, Nd4jLong *tadOffsets, bool descending) {
auto xType = nd4j::ArrayOptions::dataType(xShapeInfo);
BUILD_SINGLE_SELECTOR(xType, nd4j::SpecialMethods, ::sortTadGeneric(x, xShapeInfo, dimension, dimensionLength, tadShapeInfo, tadOffsets, descending), LIBND4J_TYPES);
}
inline static void execSortCooIndices(Nd4jLong *indices, void *values, Nd4jLong length, int rank) {
nd4j::sparse::SparseUtils<Nd4jLong>::sortCooIndicesGeneric(indices, reinterpret_cast<Nd4jLong *>(values), length, rank);
}
inline static Nd4jLong encodeBitmap(void *dx, Nd4jLong *xShapeInfo, Nd4jLong N, int *dz, float threshold) {
auto xType = nd4j::ArrayOptions::dataType(xShapeInfo);
BUILD_SINGLE_SELECTOR(xType, return nd4j::SpecialMethods, ::encodeBitmapGeneric(dx, xShapeInfo, N, dz, threshold), FLOAT_TYPES);
}
inline static void decodeBitmap(void *dx, Nd4jLong N, void *dz, Nd4jLong *zShapeInfo) {
auto zType = nd4j::ArrayOptions::dataType(zShapeInfo);
BUILD_SINGLE_SELECTOR(zType, nd4j::SpecialMethods, ::decodeBitmapGeneric(dx, N, dz, zShapeInfo), FLOAT_TYPES);
}
};
#endif //NATIVEOPERATIONS_NATIVEOPEXCUTIONER_H