320924278d
* initial commit Signed-off-by: raver119@gmail.com <raver119@gmail.com> * another initial commit Signed-off-by: raver119@gmail.com <raver119@gmail.com> * another initial commit Signed-off-by: raver119@gmail.com <raver119@gmail.com> * one more initial commit Signed-off-by: raver119@gmail.com <raver119@gmail.com> * next step Signed-off-by: raver119@gmail.com <raver119@gmail.com> * next step Signed-off-by: raver119@gmail.com <raver119@gmail.com> * next step Signed-off-by: raver119@gmail.com <raver119@gmail.com> * next step Signed-off-by: raver119@gmail.com <raver119@gmail.com> * Refactored buffer() and shapeInfo() methods usage with NDArray class. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopt Graph class methods to use const shapes. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopt choose op to use constant shapes. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopt where op shape method to use constant shapes. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopt lstsq op to use constant empty shapes. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopt matrix_diag_part op shape routine to use constant shapes. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopt determinant ops to use constant shapes. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopt mean_pairwssqerr_loss ops to use constant shapes. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopt ops shape methods. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopt shape methods for loss ops. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopt log_loss op shape method. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopt shape methods for ops. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopt dilation2d ops shape methods. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopted deconv2d ops shape methods. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopted dynamicRNN op shape method. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopted shape methods for ops. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopted shape methods for lstm layer ops. Signed-off-by: shugeo <sgazeos@gmail.com> * few updates Signed-off-by: raver119@gmail.com <raver119@gmail.com> * first cuda tweak Signed-off-by: raver119@gmail.com <raver119@gmail.com> * Adopt constant shapes for sconv2d ops. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopt constant shapes for gru ops. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopt constant shapes with shape methods for segment ops and so on. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopted constant shapes with unsorted_segment_* ops. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopted constant shapes with gamma op shape method. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopted shape methods of reduce_stddev ops. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopted shape methods for reduce_* ops. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopt shape method for squeeze op. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopt strided_slice shape method. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored concat op shape method to adopt constant shapes. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopted shape method for mirror_pad op. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopted split op shape method. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopted tile ops shape methods. Signed-off-by: shugeo <sgazeos@gmail.com> * Added const cast for mkldnn routines handles. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored logSoftMaxForVector_ routine to conform with proper data and shape pointer casts. Signed-off-by: shugeo <sgazeos@gmail.com> * Cosmetic changes to proper usage of constant pointers. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored a couple shape comparators for strides and addBias helpers to proper use data pointers with inplace option. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored depthToSpace helpers. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored histogram helpers. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored im2col helpers. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored gather and gatherND helpers. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed buffer usage on percentile helper. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed gather shape with helpers and range buffer usage. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed buffer usage with space to depth helpers. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed buffer usage and constant shapes. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed buffer usage with LUP decomposition> Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored onehot_ helper. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored pad and prefix to use constant shapes. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactoed softmax helpers. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed space to batch helpers to use buffers properly. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed stack and split helpers. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed buffer usage with sparse to dense helpers. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed buffer usage with mindistance_ helpers. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed buffer usage with tile helper. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed constant shape usage. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed constant shape usage with legacy pairwise bool ops. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored a couple of methods to adopt constant shape usage. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed broadcasting with constant shape." Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed const usage with inplace reverse and constant shapes with legacy reduction. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored legacy ops with const shapes. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored sort to adopt constant shapes. Signed-off-by: shugeo <sgazeos@gmail.com> * Corrected sort for constant shape usage. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed constant shape usage with special methods. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored Context to conform with constant shape usage. Signed-off-by: shugeo <sgazeos@gmail.com> * CUDA broadcasting headers Signed-off-by: raver119@gmail.com <raver119@gmail.com> * pairwise/indexreduce/random headers Signed-off-by: raver119@gmail.com <raver119@gmail.com> * Refactored native ops to adopt constant shapes. Signed-off-by: shugeo <sgazeos@gmail.com> * legacy reduce3/scalar headers Signed-off-by: raver119@gmail.com <raver119@gmail.com> * Corrected pullRow signature and tests. Signed-off-by: shugeo <sgazeos@gmail.com> * Corrected routines to proper use of constant shapes. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored tests to use constant shapes properly. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored legacy ops tests to use constant shapes properly. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored buffer usage with NDArray tests. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed native ops tests. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed special concat routine. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed buffer usage with test. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed buffer usage with a test. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored TAD.h and tests. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored calcStrides* routines to use constant shapes. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed miscelaneous errors with constant shapes. Signed-off-by: shugeo <sgazeos@gmail.com> * NativeOps const changes Signed-off-by: raver119@gmail.com <raver119@gmail.com> * Corrected definitions for declared functions. Signed-off-by: shugeo <sgazeos@gmail.com> * NativeOps const changes Signed-off-by: raver119@gmail.com <raver119@gmail.com> * few more const changes Signed-off-by: raver119@gmail.com <raver119@gmail.com> * Fixed const shapes with shape routines. Signed-off-by: shugeo <sgazeos@gmail.com> * few more const changes Signed-off-by: raver119@gmail.com <raver119@gmail.com> * Fixed shape method for broadcastable case. Signed-off-by: shugeo <sgazeos@gmail.com> * few more const changes Signed-off-by: raver119@gmail.com <raver119@gmail.com> * xw_plus_b BP shape fn restored Signed-off-by: raver119@gmail.com <raver119@gmail.com> * Fixed signatures with broadcasting. Signed-off-by: shugeo <sgazeos@gmail.com> * Repaired backprops shape methods for a set of operations. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored broadcast bool for cuda. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored methods for 3 args with const qualifier. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed a couple of kernel signatures for broadcasting. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed kernels signatures for const buffers and shapes. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored pairwise methods to persistent buffers and shapes usage. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopt const to buffers and shapes with kernels. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopt const to buffers and shapes with scalar kernels. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored indexreduce kernels signatures to use const buffers and shapes. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored pairwise kernels to adopt cons shapes and buffers. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored pairwise bool kernels to adopt cons shapes and buffers. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored random special ops to conform with const shapes and buffers. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored native ops to conform with const shapes and buffers under cuda platform. Signed-off-by: shugeo <sgazeos@gmail.com> * Cosmetical changes only. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed const shapes and buffers error. Signed-off-by: shugeo <sgazeos@gmail.com> * Corrected start pos routine. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored methods to conform with const shapes and buffers. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored helpers to use proper methods instead. Signed-off-by: shugeo <sgazeos@gmail.com> * bunch of changes Signed-off-by: raver119@gmail.com <raver119@gmail.com> * next bunch of changes Signed-off-by: raver119@gmail.com <raver119@gmail.com> * next bunch of changes Signed-off-by: raver119@gmail.com <raver119@gmail.com> * Fixed execScalar declaration. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed execScalar declaration. Signed-off-by: shugeo <sgazeos@gmail.com> * Corrected const shape cases with sort and so on. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed const shapes for sort. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored kernel declarations to adopt const shapes. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed kernels declarations to adopt const shapes. Signed-off-by: shugeo <sgazeos@gmail.com> * Corrected kernel declarations to adopt const shapes and buffers. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed kernels declarations to adopt const shapes. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed segment helpers kernels declarations and so on to adopt const shapes. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed const shape usage with segment and solve helpers. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed kernel declaration with adjustWeight helper. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed cuda implementations for constant shape helpers. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopted const shape usage with kernels. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopted top_k kernels to use const shapes and buffers. Signed-off-by: shugeo <sgazeos@gmail.com> * Corrected kernels declarations to adopt const shapes with helpers. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored NDArray definitions to adopt const shapes and buffers. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed const shapes with image suppression helpers. Signed-off-by: shugeo <sgazeos@gmail.com> * Slight improvement with buffers. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored buffer usage. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored buffer usage with tests. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed const shape usage with definitions. Signed-off-by: shugeo <sgazeos@gmail.com> * minor updates on cpu side Signed-off-by: raver119@gmail.com <raver119@gmail.com> * Refactored const shape usage with ConstantDescritor and native ops with cuda platform. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored tear and tile kernels to adopt with const shapes. Signed-off-by: shugeo <sgazeos@gmail.com> * softmax_loop fix Signed-off-by: raver119 <raver119@gmail.com> * update missing signature Signed-off-by: raver119@gmail.com <raver119@gmail.com> * softmax again Signed-off-by: raver119@gmail.com <raver119@gmail.com> * few more missing consts Signed-off-by: raver119 <raver119@gmail.com> * new methods updated Signed-off-by: raver119@gmail.com <raver119@gmail.com> Co-authored-by: shugeo <sgazeos@gmail.com>
680 lines
33 KiB
C++
680 lines
33 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
|
|
******************************************************************************/
|
|
|
|
//
|
|
// Created by agibsonccc on 1/28/16.
|
|
//
|
|
|
|
#ifndef NATIVEOPERATIONS_NATIVEOPEXCUTIONER_H
|
|
#define NATIVEOPERATIONS_NATIVEOPEXCUTIONER_H
|
|
|
|
|
|
#include <types/types.h>
|
|
#include <system/dll.h>
|
|
#include <ops/specials.h>
|
|
#include <ops/specials_sparse.h>
|
|
#include <execution/LaunchContext.h>
|
|
#include <array/ArrayOptions.h>
|
|
|
|
/**
|
|
* Native op executioner:
|
|
*
|
|
*/
|
|
|
|
class ND4J_EXPORT NativeOpExecutioner {
|
|
public:
|
|
/**
|
|
*
|
|
* @param opNum
|
|
* @param x
|
|
* @param xShapeInfo
|
|
* @param extraParams
|
|
* @param result
|
|
* @param resultShapeInfo
|
|
*/
|
|
static void execIndexReduceScalar(sd::LaunchContext *lc,
|
|
int opNum,
|
|
const void *hX, const Nd4jLong *hXShapeInfo,
|
|
const void *dX, const Nd4jLong *dXShapeInfo,
|
|
void *extraParams,
|
|
void *hZ, const Nd4jLong *hZShapeInfo,
|
|
void *dZ, const 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(sd::LaunchContext *lc,
|
|
int opNum,
|
|
const void *hX, const Nd4jLong *hXShapeInfo,
|
|
const void *dX, const Nd4jLong *dXShapeInfo,
|
|
void *extraParamsVals,
|
|
const void *hY, const Nd4jLong *hYShapeInfo,
|
|
const void *dY, const Nd4jLong *dYShapeInfo,
|
|
void *hZ, const Nd4jLong *hZShapeInfo,
|
|
void *dZ, const Nd4jLong *dZShapeInfo);
|
|
|
|
|
|
/**
|
|
*
|
|
* @param opNum
|
|
* @param x
|
|
* @param xShapeInfo
|
|
* @param extraParamsVals
|
|
* @param y
|
|
* @param yShapeInfo
|
|
* @param result
|
|
* @param resultShapeInfo
|
|
*/
|
|
static void execReduce3(sd::LaunchContext *lc,
|
|
int opNum,
|
|
const void *hX, const Nd4jLong *hXShapeInfo,
|
|
const void *dX, const Nd4jLong *dXShapeInfo,
|
|
void *extraParamsVals,
|
|
const void *hY, const Nd4jLong *hYShapeInfo,
|
|
const void *dY, const Nd4jLong *dYShapeInfo,
|
|
void *hZ, const Nd4jLong *hZShapeInfo,
|
|
void *dZ, const 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(sd::LaunchContext *lc,
|
|
int opNum,
|
|
const void *hX, const Nd4jLong *hXShapeInfo,
|
|
const void *dX, const Nd4jLong *dXShapeInfo,
|
|
void *extraParamsVals,
|
|
const void *hY, const Nd4jLong *hYShapeInfo,
|
|
const void *dY, const Nd4jLong *dYShapeInfo,
|
|
void *hZ, const Nd4jLong *hZShapeInfo,
|
|
void *dZ, const Nd4jLong *dZShapeInfo,
|
|
int *dimension, int dimensionLength,
|
|
const Nd4jLong *xTadOnlyShapeInfo, const Nd4jLong *xTadOffsets,
|
|
const Nd4jLong *yTadOnlyShapeInfo, const Nd4jLong *yTadOffsets);
|
|
|
|
static void execReduce3All(sd::LaunchContext *lc,
|
|
int opNum,
|
|
const void *hX, const Nd4jLong *hXShapeInfo,
|
|
const void *dX, const Nd4jLong *dXShapeInfo,
|
|
void *extraParamsVals,
|
|
const void *hY, const Nd4jLong *hYShapeInfo,
|
|
const void *dY, const Nd4jLong *dYShapeInfo,
|
|
void *hZ, const Nd4jLong *hZShapeInfo,
|
|
void *dZ, const Nd4jLong *dZShapeInfo,
|
|
int *dimension, int dimensionLength,
|
|
const Nd4jLong *xTadShapeInfo, const Nd4jLong *xOffsets,
|
|
const Nd4jLong *yTadShapeInfo, const Nd4jLong *yOffsets);
|
|
|
|
/**
|
|
*
|
|
* @param opNum
|
|
* @param x
|
|
* @param xShapeInfo
|
|
* @param extraParams
|
|
* @param result
|
|
* @param resultShapeInfoBuffer
|
|
* @param dimension
|
|
* @param dimensionLength
|
|
*/
|
|
static void execIndexReduce(sd::LaunchContext *lc,
|
|
int opNum,
|
|
const void *hX, const Nd4jLong *hXShapeInfo,
|
|
const void *dX, const Nd4jLong *dXShapeInfo,
|
|
void *extraParams,
|
|
void *hZ, const Nd4jLong *hZShapeInfo,
|
|
void *dZ, const Nd4jLong *dZShapeInfo,
|
|
int *dimension, int dimensionLength,
|
|
const Nd4jLong *tadShapeInfo, const Nd4jLong *tadOffsets);
|
|
|
|
/**
|
|
*
|
|
* @param opNum
|
|
* @param x
|
|
* @param xStride
|
|
* @param result
|
|
* @param resultStride
|
|
* @param scalar
|
|
* @param extraParams
|
|
* @param n
|
|
*/
|
|
static void execScalar(sd::LaunchContext *lc,
|
|
int opNum,
|
|
const void *hX, const Nd4jLong *hXShapeInfo,
|
|
const void *dX, const Nd4jLong *dXShapeInfo,
|
|
void *hZ, const Nd4jLong *hZShapeInfo,
|
|
void *dZ, const Nd4jLong *dZShapeInfo,
|
|
const void *hScalar, const Nd4jLong *hSscalarShapeInfo,
|
|
const void *dScalar, const Nd4jLong *dSscalarShapeInfo,
|
|
void *extraParams,
|
|
bool allowParallelism = true);
|
|
|
|
static void execScalarBool(sd::LaunchContext *lc,
|
|
int opNum,
|
|
const void *hX, const Nd4jLong *hXShapeInfo,
|
|
const void *dX, const Nd4jLong *dXShapeInfo,
|
|
void *hZ, const Nd4jLong *hZShapeInfo,
|
|
void *dZ, const Nd4jLong *dZShapeInfo,
|
|
const void *hScalar, const Nd4jLong *hSscalarShapeInfo,
|
|
const void *dScalar, const Nd4jLong *dSscalarShapeInfo,
|
|
void *extraParams,
|
|
bool allowParallelism = true);
|
|
|
|
static void execScalarInt(sd::LaunchContext *lc,
|
|
int opNum,
|
|
const void *hX, const Nd4jLong *hXShapeInfo,
|
|
const void *dX, const Nd4jLong *dXShapeInfo,
|
|
void *hZ, const Nd4jLong *hZShapeInfo,
|
|
void *dZ, const Nd4jLong *dZShapeInfo,
|
|
const void *hScalar, const Nd4jLong *hSscalarShapeInfo,
|
|
const void *dScalar, const Nd4jLong *dSscalarShapeInfo,
|
|
void *extraParams,
|
|
bool allowParallelism = true);
|
|
|
|
static void execScalar(sd::LaunchContext *lc,
|
|
int opNum,
|
|
void const* hX, Nd4jLong const* hXShapeInfo,
|
|
void const* dX, Nd4jLong const* dXShapeInfo,
|
|
void *extraParams,
|
|
void *hZ, Nd4jLong const* hZShapeInfo,
|
|
void *dZ, Nd4jLong const* dZShapeInfo,
|
|
void const* hScalars, Nd4jLong const* hScalarShapeInfo,
|
|
void const* dScalars, Nd4jLong const* dScalarShapeInfo,
|
|
int *dimension, int dimensionLength,
|
|
Nd4jLong const* tadShapeInfo, Nd4jLong const* tadOffsets,
|
|
Nd4jLong const* tadShapeInfoZ, Nd4jLong const* tadOffsetsZ);
|
|
|
|
static void execScalarBool(sd::LaunchContext *lc,
|
|
int opNum,
|
|
const void *hX, const Nd4jLong *hXShapeInfo,
|
|
const void *dX, const Nd4jLong *dXShapeInfo,
|
|
void *extraParams,
|
|
void *hZ, const Nd4jLong *hZShapeInfo,
|
|
void *dZ, const Nd4jLong *dZShapeInfo,
|
|
const void *hScalars, const Nd4jLong *hScalarShapeInfo,
|
|
const void *dScalars, const Nd4jLong *dScalarShapeInfo,
|
|
int *dimension, int dimensionLength,
|
|
const Nd4jLong *tadShapeInfo, const Nd4jLong *tadOffsets,
|
|
const Nd4jLong *tadShapeInfoZ, const Nd4jLong *tadOffsetsZ);
|
|
|
|
static void execScalarInt(sd::LaunchContext *lc,
|
|
int opNum,
|
|
const void *hX, const Nd4jLong *hXShapeInfo,
|
|
const void *dX, const Nd4jLong *dXShapeInfo,
|
|
void *extraParams,
|
|
void *hZ, const Nd4jLong *hZShapeInfo,
|
|
void *dZ, const Nd4jLong *dZShapeInfo,
|
|
const void *hScalars, const Nd4jLong *hScalarShapeInfo,
|
|
const void *dScalars, const Nd4jLong *dScalarShapeInfo,
|
|
int *dimension, int dimensionLength,
|
|
const Nd4jLong *tadShapeInfo, const Nd4jLong *tadOffsets,
|
|
const Nd4jLong *tadShapeInfoZ, const Nd4jLong *tadOffsetsZ);
|
|
|
|
|
|
/**
|
|
*
|
|
* @param opNum
|
|
* @param x
|
|
* @param xShapeInfo
|
|
* @param y
|
|
* @param yShapeInfo
|
|
* @param result
|
|
* @param resultShapeInfo
|
|
* @param dimension
|
|
* @param dimensionLength
|
|
*/
|
|
static void execBroadcast(sd::LaunchContext *lc,
|
|
int opNum,
|
|
const void *hX, const Nd4jLong *hXShapeInfo,
|
|
const void *dX, const Nd4jLong *dXShapeInfo,
|
|
const void *hY, const Nd4jLong *hYShapeInfo,
|
|
const void *dY, const Nd4jLong *dYShapeInfo,
|
|
void *hZ, const Nd4jLong *hZShapeInfo,
|
|
void *dZ, const Nd4jLong *dZShapeInfo,
|
|
int *dimension, int dimensionLength,
|
|
const Nd4jLong *tadOnlyShapeInfo, const Nd4jLong *tadOffsets,
|
|
const Nd4jLong *tadOnlyShapeInfoZ,const Nd4jLong *tadOffsetsZ);
|
|
|
|
static void execBroadcast(sd::LaunchContext* lc,
|
|
int opNum,
|
|
const void *hX, const Nd4jLong *hXShapeInfo,
|
|
const void *dX, const Nd4jLong *dXShapeInfo,
|
|
const void *hY, const Nd4jLong *hYShapeInfo,
|
|
const void *dY, const Nd4jLong *dYShapeInfo,
|
|
void *hZ, const Nd4jLong *hZShapeInfo,
|
|
void *dZ, const Nd4jLong *dZShapeInfo);
|
|
|
|
static void execInverseBroadcast(sd::LaunchContext *lc,
|
|
int opNum,
|
|
const void *x, const Nd4jLong *xShapeInfo,
|
|
const void *dX, const Nd4jLong *dXShapeInfo,
|
|
const void *y, const Nd4jLong *yShapeInfo,
|
|
const void *dY, const Nd4jLong *dYShapeInfo,
|
|
void *result, const Nd4jLong *resultShapeInfo,
|
|
void *dZ, const Nd4jLong *dZShapeInfo,
|
|
int *dimension, int dimensionLength,
|
|
const Nd4jLong *tadOnlyShapeInfo, const Nd4jLong *tadOffsets,
|
|
const Nd4jLong *tadOnlyShapeInfoZ, const Nd4jLong *tadOffsetsZ);
|
|
|
|
|
|
static void execBroadcastBool(sd::LaunchContext *lc,
|
|
int opNum,
|
|
const void *hX, const Nd4jLong *hXShapeInfo,
|
|
const void *dX, const Nd4jLong *dXShapeInfo,
|
|
const void *hY, const Nd4jLong *hYShapeInfo,
|
|
const void *dY, const Nd4jLong *dYShapeInfo,
|
|
void *hZ, const Nd4jLong *hZShapeInfo,
|
|
void *dZ, const Nd4jLong *dZShapeInfo,
|
|
void *extraParams,
|
|
int *dimension, int dimensionLength,
|
|
const Nd4jLong *tadOnlyShapeInfo, const Nd4jLong *tadOffsets,
|
|
const Nd4jLong *tadOnlyShapeInfoZ,const Nd4jLong *tadOffsetsZ);
|
|
|
|
static void execBroadcastBool(sd::LaunchContext* lc,
|
|
int opNum,
|
|
const void *hX, const Nd4jLong *hXShapeInfo,
|
|
const void *dX, const Nd4jLong *dXShapeInfo,
|
|
const void *hY, const Nd4jLong *hYShapeInfo,
|
|
const void *dY, const Nd4jLong *dYShapeInfo,
|
|
void *hZ, const Nd4jLong *hZShapeInfo,
|
|
void *dZ, const Nd4jLong *dZShapeInfo,
|
|
void *extraParams);
|
|
|
|
static void execInverseBroadcastBool(sd::LaunchContext *lc,
|
|
int opNum,
|
|
const void *x, const Nd4jLong *xShapeInfo,
|
|
const void *dX, const Nd4jLong *dXShapeInfo,
|
|
const void *y, const Nd4jLong *yShapeInfo,
|
|
const void *dY, const Nd4jLong *dYShapeInfo,
|
|
void *result, const Nd4jLong *resultShapeInfo,
|
|
void *dZ, const Nd4jLong *dZShapeInfo,
|
|
void *extraParams,
|
|
int *dimension, int dimensionLength,
|
|
const Nd4jLong *tadOnlyShapeInfo, const Nd4jLong *tadOffsets,
|
|
const Nd4jLong *tadOnlyShapeInfoZ, const Nd4jLong *tadOffsetsZ);
|
|
|
|
static void execBroadcastInt(sd::LaunchContext *lc,
|
|
int opNum,
|
|
const void *hX, const Nd4jLong *hXShapeInfo,
|
|
const void *dX, const Nd4jLong *dXShapeInfo,
|
|
const void *hY, const Nd4jLong *hYShapeInfo,
|
|
const void *dY, const Nd4jLong *dYShapeInfo,
|
|
void *hZ, const Nd4jLong *hZShapeInfo,
|
|
void *dZ, const Nd4jLong *dZShapeInfo,
|
|
int *dimension, int dimensionLength,
|
|
const Nd4jLong *tadOnlyShapeInfo, const Nd4jLong *tadOffsets,
|
|
const Nd4jLong *tadOnlyShapeInfoZ,const Nd4jLong *tadOffsetsZ);
|
|
|
|
static void execBroadcastInt(sd::LaunchContext* lc,
|
|
int opNum,
|
|
const void *hX, const Nd4jLong *hXShapeInfo,
|
|
const void *dX, const Nd4jLong *dXShapeInfo,
|
|
const void *hY, const Nd4jLong *hYShapeInfo,
|
|
const void *dY, const Nd4jLong *dYShapeInfo,
|
|
void *hZ, const Nd4jLong *hZShapeInfo,
|
|
void *dZ, const Nd4jLong *dZShapeInfo);
|
|
|
|
static void execInverseBroadcastInt(sd::LaunchContext *lc,
|
|
int opNum,
|
|
const void *x, const Nd4jLong *xShapeInfo,
|
|
const void *dX, const Nd4jLong *dXShapeInfo,
|
|
const void *y, const Nd4jLong *yShapeInfo,
|
|
const void *dY, const Nd4jLong *dYShapeInfo,
|
|
void *result, const Nd4jLong *resultShapeInfo,
|
|
void *dZ, const Nd4jLong *dZShapeInfo,
|
|
int *dimension, int dimensionLength,
|
|
const Nd4jLong *tadOnlyShapeInfo, const Nd4jLong *tadOffsets,
|
|
const Nd4jLong *tadOnlyShapeInfoZ, const Nd4jLong *tadOffsetsZ);
|
|
|
|
/**
|
|
*
|
|
* @param opNum
|
|
* @param dx
|
|
* @param xStride
|
|
* @param y
|
|
* @param yStride
|
|
* @param result
|
|
* @param resultStride
|
|
* @param extraParams
|
|
* @param n
|
|
*/
|
|
static void execPairwiseTransform(sd::LaunchContext *lc,
|
|
int opNum,
|
|
const void *hX, const Nd4jLong *hXShapeInfo,
|
|
const void *dX, const Nd4jLong *dXShapeInfo,
|
|
const void *hY, const Nd4jLong *hYShapeInfo,
|
|
const void *dY, const Nd4jLong *dYShapeInfo,
|
|
void *hZ, const Nd4jLong *hZShapeInfo,
|
|
void *dZ, const Nd4jLong *dZShapeInfo,
|
|
void *extraParams);
|
|
|
|
static void execPairwiseBoolTransform(sd::LaunchContext *lc,
|
|
int opNum,
|
|
const void *hX, const Nd4jLong *hXShapeInfo,
|
|
const void *dX, const Nd4jLong *dXShapeInfo,
|
|
const void *hY, const Nd4jLong *hYShapeInfo,
|
|
const void *dY, const Nd4jLong *dYShapeInfo,
|
|
void *hZ, const Nd4jLong *hZShapeInfo,
|
|
void *dZ, const Nd4jLong *dZShapeInfo,
|
|
void *extraParams);
|
|
|
|
static void execPairwiseIntTransform(sd::LaunchContext *lc,
|
|
int opNum,
|
|
const void *hX, const Nd4jLong *hXShapeInfo,
|
|
const void *dX, const Nd4jLong *dXShapeInfo,
|
|
const void *hY, const Nd4jLong *hYShapeInfo,
|
|
const void *dY, const Nd4jLong *dYShapeInfo,
|
|
void *hZ, const Nd4jLong *hZShapeInfo,
|
|
void *dZ, const Nd4jLong *dZShapeInfo,
|
|
void *extraParams);
|
|
|
|
/**
|
|
*
|
|
* @param opNum
|
|
* @param dx
|
|
* @param xStride
|
|
* @param result
|
|
* @param resultStride
|
|
* @param extraParams
|
|
* @param n
|
|
*/
|
|
static void execTransformFloat(sd::LaunchContext *lc,
|
|
int opNum,
|
|
const void *hX, const Nd4jLong *hXShapeInfo,
|
|
const void *dX, const Nd4jLong *dXShapeInfo,
|
|
void *hZ, const Nd4jLong *hZShapeInfo,
|
|
void *dZ, const Nd4jLong *dZShapeInfo,
|
|
void *extraParams,
|
|
const Nd4jLong *tadShapeInfo, const Nd4jLong *tadOffsets);
|
|
|
|
static void execTransformAny(sd::LaunchContext *lc,
|
|
int opNum,
|
|
const void *hX, const Nd4jLong *hXShapeInfo,
|
|
const void *dX, const Nd4jLong *dXShapeInfo,
|
|
void *hZ, const Nd4jLong *hZShapeInfo,
|
|
void *dZ, const Nd4jLong *dZShapeInfo,
|
|
void *extraParams,
|
|
const Nd4jLong *tadShapeInfo, const Nd4jLong *tadOffsets,
|
|
bool allowParallelism = true);
|
|
|
|
static void execTransformStrict(sd::LaunchContext *lc,
|
|
int opNum,
|
|
const void *hX, const Nd4jLong *hXShapeInfo,
|
|
const void *dX, const Nd4jLong *dXShapeInfo,
|
|
void *hZ, const Nd4jLong *hZShapeInfo,
|
|
void *dZ, const Nd4jLong *dZShapeInfo,
|
|
void *extraParams,
|
|
const Nd4jLong *tadShapeInfo, const Nd4jLong *tadOffsets);
|
|
|
|
static void execTransformSame(sd::LaunchContext *lc,
|
|
int opNum,
|
|
const void *hX, const Nd4jLong *hXShapeInfo,
|
|
const void *dX, const Nd4jLong *dXShapeInfo,
|
|
void *hZ, const Nd4jLong *hZShapeInfo,
|
|
void *dZ, const Nd4jLong *dZShapeInfo,
|
|
void *extraParams,
|
|
const Nd4jLong *tadShapeInfo, const Nd4jLong *tadOffsets);
|
|
|
|
static void execTransformBool(sd::LaunchContext *lc,
|
|
int opNum,
|
|
const void *hX, const Nd4jLong *hXShapeInfo,
|
|
const void *dX, const Nd4jLong *dXShapeInfo,
|
|
void *hZ, const Nd4jLong *hZShapeInfo,
|
|
void *dZ, const Nd4jLong *dZShapeInfo,
|
|
void *extraParams,
|
|
const Nd4jLong *tadShapeInfo, const Nd4jLong *tadOffsets);
|
|
/**
|
|
*
|
|
* @param opNum
|
|
* @param x
|
|
* @param xShapeInfo
|
|
* @param extraParams
|
|
* @param result
|
|
* @param resultShapeInfo
|
|
*/
|
|
static void execReduceFloat(sd::LaunchContext *lc,
|
|
int opNum,
|
|
const void *hX, const Nd4jLong *hXShapeInfo,
|
|
const void *dX, const Nd4jLong *dXShapeInfo,
|
|
void *extraParams,
|
|
void *hZ, const Nd4jLong *hZShapeInfo,
|
|
void *dZ, const Nd4jLong *dZShapeInfo,
|
|
int *dimension, int dimensionLength,
|
|
const Nd4jLong *tadShapeInfo, const Nd4jLong *tadOffsets);
|
|
|
|
static void execReduceSame(sd::LaunchContext *lc,
|
|
int opNum,
|
|
const void *hX, const Nd4jLong *hXShapeInfo,
|
|
const void *dX, const Nd4jLong *dXShapeInfo,
|
|
void *extraParams,
|
|
void *hZ, const Nd4jLong *hZShapeInfo,
|
|
void *dZ, const Nd4jLong *dZShapeInfo,
|
|
int *dimension, int dimensionLength,
|
|
const Nd4jLong *tadShapeInfo, const Nd4jLong *tadOffsets);
|
|
|
|
static void execReduceBool(sd::LaunchContext *lc,
|
|
int opNum,
|
|
const void *hX, const Nd4jLong *hXShapeInfo,
|
|
const void *dX, const Nd4jLong *dXShapeInfo,
|
|
void *extraParams,
|
|
void *hZ, const Nd4jLong *hZShapeInfo,
|
|
void *dZ, const Nd4jLong *dZShapeInfo,
|
|
int *dimension, int dimensionLength,
|
|
const Nd4jLong *tadShapeInfo, const Nd4jLong *tadOffsets);
|
|
|
|
static void execReduceLong(sd::LaunchContext *lc,
|
|
int opNum,
|
|
const void *hX, const Nd4jLong *hXShapeInfo,
|
|
const void *dX, const Nd4jLong *dXShapeInfo,
|
|
void *extraParams,
|
|
void *hZ, const Nd4jLong *hZShapeInfo,
|
|
void *dZ, const Nd4jLong *dZShapeInfo,
|
|
int *dimension, int dimensionLength,
|
|
const Nd4jLong *tadShapeInfo, const Nd4jLong *tadOffsets);
|
|
|
|
/**
|
|
*
|
|
* @param opNum
|
|
* @param x
|
|
* @param xShapeInfo
|
|
* @param extraParams
|
|
* @return
|
|
*/
|
|
static void execReduceFloatScalar(sd::LaunchContext *lc,
|
|
int opNum,
|
|
const void *hX, const Nd4jLong *hXShapeInfo,
|
|
const void *dX, const Nd4jLong *dXShapeInfo,
|
|
void *extraParams,
|
|
void *hZ, const Nd4jLong *hZShapeInfo,
|
|
void *dZ, const Nd4jLong *dZShapeInfo);
|
|
|
|
static void execReduceBoolScalar(sd::LaunchContext *lc,
|
|
int opNum,
|
|
const void *hX, const Nd4jLong *hXShapeInfo,
|
|
const void *dX, const Nd4jLong *dXShapeInfo,
|
|
void *extraParams,
|
|
void *hZ, const Nd4jLong *hZShapeInfo,
|
|
void *dZ, const Nd4jLong *dZShapeInfo);
|
|
|
|
static void execReduceSameScalar(sd::LaunchContext *lc,
|
|
int opNum,
|
|
const void *hX, const Nd4jLong *hXShapeInfo,
|
|
const void *dX, const Nd4jLong *dXShapeInfo,
|
|
void *extraParams,
|
|
void *hZ, const Nd4jLong *hZShapeInfo,
|
|
void *dZ, const Nd4jLong *dZShapeInfo);
|
|
|
|
static void execReduceLongScalar(sd::LaunchContext *lc,
|
|
int opNum,
|
|
const void *hX, const Nd4jLong *hXShapeInfo,
|
|
const void *dX, const Nd4jLong *dXShapeInfo,
|
|
void *extraParams,
|
|
void *hZ, const Nd4jLong *hZShapeInfo,
|
|
void *dZ, const Nd4jLong *dZShapeInfo);
|
|
|
|
static void execReduce3TAD(sd::LaunchContext *lc,
|
|
int opNum,
|
|
const void *hX, const Nd4jLong *hXShapeInfo,
|
|
const void *dX, const Nd4jLong *dXShapeInfo,
|
|
void *extraParamsVals,
|
|
const void *hY, const Nd4jLong *hYShapeInfo,
|
|
const void *dY, const Nd4jLong *dYShapeInfo,
|
|
void *hZ, const Nd4jLong *hZShapeInfo,
|
|
void *dZ, const Nd4jLong *dZShapeInfo,
|
|
int *dimension, int dimensionLength,
|
|
const Nd4jLong *tadShapeInfo, const Nd4jLong *tadOffsets,
|
|
const Nd4jLong *yTadShapeInfo, const Nd4jLong *yTadOffsets);
|
|
|
|
/**
|
|
*
|
|
* @param opNum
|
|
* @param x
|
|
* @param xShapeInfo
|
|
* @param extraParams
|
|
* @param result
|
|
* @param resultShapeInfoBuffer
|
|
* @param dimension
|
|
* @param dimensionLength
|
|
*/
|
|
static void execSummaryStats(sd::LaunchContext *lc,
|
|
int opNum,
|
|
const void *hX, const Nd4jLong *hXShapeInfo,
|
|
const void *dX, const Nd4jLong *dXShapeInfo,
|
|
void *extraParams,
|
|
void *hZ, const Nd4jLong *hZShapeInfo,
|
|
void *dZ, const Nd4jLong *dZShapeInfo,
|
|
int *dimension, int dimensionLength,
|
|
const Nd4jLong *tadShapeInfo, const Nd4jLong *tadOffsets,
|
|
bool biasCorrected);
|
|
|
|
/**
|
|
*
|
|
* @param opNum
|
|
* @param x
|
|
* @param xShapeInfo
|
|
* @param extraParams
|
|
* @param result
|
|
* @param resultShapeInfo
|
|
*/
|
|
static void execSummaryStats(sd::LaunchContext *lc,
|
|
int opNum,
|
|
const void *hX, const Nd4jLong *hXShapeInfo,
|
|
const void *dX, const Nd4jLong *dXShapeInfo,
|
|
void *extraParams,
|
|
void *hZ, const Nd4jLong *hZShapeInfo,
|
|
void *dZ, const Nd4jLong *dZShapeInfo,
|
|
bool biasCorrected);
|
|
|
|
/**
|
|
*
|
|
* @param opNum
|
|
* @param x
|
|
* @param xShapeInfo
|
|
* @param extraParams
|
|
* @param result
|
|
* @param resultShapeInfo
|
|
*/
|
|
static void execSummaryStatsScalar(sd::LaunchContext *lc,
|
|
int opNum,
|
|
const void *hX, const Nd4jLong *hXShapeInfo,
|
|
const void *dX, const Nd4jLong *dXShapeInfo,
|
|
void *extraParams,
|
|
void *hZ, const Nd4jLong *hZShapeInfo,
|
|
void *dZ, const Nd4jLong *dZShapeInfo,
|
|
bool biasCorrected);
|
|
|
|
|
|
static void execRandom(sd::LaunchContext *lc,
|
|
int opNum,
|
|
Nd4jPointer state,
|
|
void *hZ, const Nd4jLong *hZShapeBuffer,
|
|
void *dZ, const Nd4jLong *dZShapeBuffer,
|
|
void *extraArguments);
|
|
|
|
static void execRandom(sd::LaunchContext *lc,
|
|
int opNum,
|
|
Nd4jPointer state,
|
|
const void *hX, const Nd4jLong *hXShapeBuffer,
|
|
const void *dX, const Nd4jLong *dXShapeBuffer,
|
|
void *hZ, const Nd4jLong *hZShapeBuffer,
|
|
void *dZ, const Nd4jLong *dZShapeBuffer,
|
|
void *extraArguments);
|
|
|
|
static void execRandom(sd::LaunchContext *lc,
|
|
int opNum,
|
|
Nd4jPointer state,
|
|
const void *hX, const Nd4jLong *hXShapeBuffer,
|
|
const void *dX, const Nd4jLong *dXShapeBuffer,
|
|
const void *hY, const Nd4jLong *hYShapeBuffer,
|
|
const void *dY, const Nd4jLong *dYShapeBuffer,
|
|
void *hZ, const Nd4jLong *hZShapeBuffer,
|
|
void *dZ, const Nd4jLong *dZShapeBuffer,
|
|
void *extraArguments);
|
|
|
|
|
|
|
|
inline static void execSort(void *x, const Nd4jLong *xShapeInfo, bool descending) {
|
|
auto xType = sd::ArrayOptions::dataType(xShapeInfo);
|
|
|
|
BUILD_SINGLE_SELECTOR(xType, sd::SpecialMethods, ::sortGeneric(x, xShapeInfo, descending), LIBND4J_TYPES);
|
|
}
|
|
|
|
static void execSort(void *x, const Nd4jLong *xShapeInfo, int *dimension, int dimensionLength, const Nd4jLong *tadShapeInfo, const Nd4jLong *tadOffsets, bool descending) {
|
|
auto xType = sd::ArrayOptions::dataType(xShapeInfo);
|
|
|
|
BUILD_SINGLE_SELECTOR(xType, sd::SpecialMethods, ::sortTadGeneric(x, xShapeInfo, dimension, dimensionLength, tadShapeInfo, tadOffsets, descending), LIBND4J_TYPES);
|
|
}
|
|
|
|
inline static void execSortCooIndices(Nd4jLong *indices, void *values, Nd4jLong length, int rank) {
|
|
sd::sparse::SparseUtils<Nd4jLong>::sortCooIndicesGeneric(indices, reinterpret_cast<Nd4jLong *>(values), length, rank);
|
|
}
|
|
|
|
|
|
inline static Nd4jLong encodeBitmap(void *dx, const Nd4jLong *xShapeInfo, Nd4jLong N, int *dz, float threshold) {
|
|
auto xType = sd::ArrayOptions::dataType(xShapeInfo);
|
|
|
|
BUILD_SINGLE_SELECTOR(xType, return sd::SpecialMethods, ::encodeBitmapGeneric(dx, xShapeInfo, N, dz, threshold), FLOAT_TYPES);
|
|
}
|
|
|
|
inline static void decodeBitmap(const void *dx, Nd4jLong N, void *dz, const Nd4jLong *zShapeInfo) {
|
|
auto zType = sd::ArrayOptions::dataType(zShapeInfo);
|
|
|
|
BUILD_SINGLE_SELECTOR(zType, sd::SpecialMethods, ::decodeBitmapGeneric(dx, N, dz, zShapeInfo), FLOAT_TYPES);
|
|
}
|
|
|
|
};
|
|
|
|
|
|
#endif //NATIVEOPERATIONS_NATIVEOPEXCUTIONER_H
|