78934c17ad
* - profiling of stack and unstack ops Signed-off-by: Yurii <iuriish@yahoo.com> * - fix bug in cpu concat op Signed-off-by: Yurii <iuriish@yahoo.com> * - correction of cuda stack and unstack Signed-off-by: Yurii <iuriish@yahoo.com> * - change shape.h method which operates with unity dimensions strides Signed-off-by: Yurii <iuriish@yahoo.com> * - rearrange stack tests Signed-off-by: Yurii <iuriish@yahoo.com> * - correct evaluation of smallest stride for moving through contiguous axis Signed-off-by: Yurii <iuriish@yahoo.com> * - forgot to update signature of function strideOverContigAxis in cuda concat and split ops Signed-off-by: Yurii <iuriish@yahoo.com> * - remove ShapeUtils::shapeAsString method applied before input arrays validations Signed-off-by: Yurii <iuriish@yahoo.com> * - further removing of ShapeUtils::shapeAsString Signed-off-by: Yurii <iuriish@yahoo.com> * - take sub-array shapeIndo/offset calculation out of NDArray class - add possibility of contiguous memory copy in execTransformAny op if opNum == assign Signed-off-by: Yurii <iuriish@yahoo.com> * - correct test_empty_scatter_2 in EmptyTests.cpp Signed-off-by: Yurii <iuriish@yahoo.com> * - profiling of slice op Signed-off-by: Yurii <iuriish@yahoo.com> * - get rid of contiguous memcpy for some cases in concat and split ops Signed-off-by: Yurii <iuriish@yahoo.com> * - forgot to declare oid nd4j::SpecialMethods<T>::splitCpuGeneric Signed-off-by: Yurii <iuriish@yahoo.com> * - correct typo in calculation of threads in cuda split op Signed-off-by: Yurii <iuriish@yahoo.com> * - forgot to correct another set of threads variables in split cuda ops Signed-off-by: Yurii <iuriish@yahoo.com> * - further conflicts resolving Signed-off-by: Yurii <iuriish@yahoo.com> Co-authored-by: raver119 <raver119@gmail.com>
88 lines
3.5 KiB
C++
88 lines
3.5 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 raver119 on 24.04.17.
|
|
//
|
|
|
|
#ifndef LIBND4J_SPECIALS_H
|
|
#define LIBND4J_SPECIALS_H
|
|
|
|
|
|
#ifdef __CUDACC__
|
|
#define ELEMENT_THRESHOLD 8192
|
|
#define TAD_THRESHOLD 2
|
|
#endif
|
|
|
|
#include <system/pointercast.h>
|
|
#include <vector>
|
|
|
|
namespace sd {
|
|
class NDArray;
|
|
|
|
//FIXME: get rid of this redefinition
|
|
typedef union
|
|
{
|
|
float f_;
|
|
int i_;
|
|
} FloatBits2;
|
|
|
|
|
|
class ND4J_EXPORT SpecialTypeConverter {
|
|
public:
|
|
template<typename S, typename T>
|
|
static void convertGeneric(Nd4jPointer * extras, void *dx, Nd4jLong N, void *dz);
|
|
};
|
|
|
|
template <typename T>
|
|
class ND4J_EXPORT SpecialMethods {
|
|
public:
|
|
static void concatCpuGeneric(const std::vector<const NDArray*>& inArrs, NDArray& output, const int axis);
|
|
static void concatCpuGeneric(int dimension, int numArrays, Nd4jPointer *data, Nd4jPointer *inputShapeInfo, void *result, Nd4jLong *resultShapeInfo);
|
|
static void splitCpuGeneric(const NDArray& input, const std::vector<NDArray*>& outArrs, const int axis);
|
|
static void accumulateGeneric(void **x, void *z, Nd4jLong *zShapeInfo, int n, const Nd4jLong length);
|
|
static void averageGeneric(void **x, void *z, Nd4jLong *zShapeInfo, int n, const Nd4jLong length, bool propagate);
|
|
|
|
static Nd4jLong getPosition(Nd4jLong *xShapeInfo, Nd4jLong index);
|
|
static void quickSort_parallel_internal(T* array, Nd4jLong *xShapeInfo, int left, int right, int cutoff, bool descending);
|
|
static void quickSort_parallel(void* array, Nd4jLong *xShapeInfo, Nd4jLong lenArray, int numThreads, bool descending);
|
|
|
|
static int nextPowerOf2(int number);
|
|
static int lastPowerOf2(int number);
|
|
|
|
static void sortGeneric(void *x, Nd4jLong *xShapeInfo, bool descending);
|
|
static void sortTadGeneric(void *x, Nd4jLong *xShapeInfo, int *dimension, int dimensionLength, Nd4jLong *tadShapeInfo, Nd4jLong *tadOffsets, bool descending);
|
|
|
|
static void decodeBitmapGeneric(void *dx, Nd4jLong N, void *dz, Nd4jLong *zShapeInfo);
|
|
static Nd4jLong encodeBitmapGeneric(void *dx, Nd4jLong *zShapeInfo, Nd4jLong N, int *dz, float threshold);
|
|
|
|
};
|
|
|
|
template <typename X, typename Y>
|
|
class ND4J_EXPORT DoubleMethods{
|
|
public:
|
|
static void sortByKey(void *vx, Nd4jLong *xShapeInfo, void *vy, Nd4jLong *yShapeInfo, bool descending);
|
|
static void sortByValue(void *vx, Nd4jLong *xShapeInfo, void *vy, Nd4jLong *yShapeInfo, bool descending);
|
|
|
|
|
|
static void sortTadByKey(void *vx, Nd4jLong *xShapeInfo, void *vy, Nd4jLong *yShapeInfo, int *dimension, int dimensionLength, bool descending);
|
|
static void sortTadByValue(void *vx, Nd4jLong *xShapeInfo, void *vy, Nd4jLong *yShapeInfo, int *dimension, int dimensionLength, bool descending);
|
|
};
|
|
}
|
|
|
|
|
|
#endif //LIBND4J_SPECIALS_H
|