cavis/libnd4j/include/loops/transform_same.h
raver119 6de00bf75f
[WIP] Weekly update of repo (#8390)
* [WIP] Fix compilation after nd4j changes (#37)

* Fix compilation.

* Some tests fixed

* Disable tests temporarily.

* Restored test

* Tests restored.

* Test restored.

* [WIP] perf tests (#40)

* special maxpool test

Signed-off-by: raver119 <raver119@gmail.com>

* special maxpool test

Signed-off-by: raver119 <raver119@gmail.com>

* Shyrma bnorm bp (#41)

Batchnorm backprop mkldnn

* Add SameDiff memory reuse memory manager (array cache) (#39)

* Attention op comments

Signed-off-by: AlexDBlack <blacka101@gmail.com>

* ArrayCacheMemoryMgr - first pass

Signed-off-by: AlexDBlack <blacka101@gmail.com>

* Tweak array cache for use with SameDiff identity arrays

Signed-off-by: AlexDBlack <blacka101@gmail.com>

* ArrayCacheMemoryMgr javadoc and properly get max memory

Signed-off-by: AlexDBlack <blacka101@gmail.com>

* LRU cache policy + add tests

Signed-off-by: AlexDBlack <blacka101@gmail.com>

* Fixes

Signed-off-by: AlexDBlack <blacka101@gmail.com>

* Resize arrays internally if required for ArrayCacheMemoryMgr

Signed-off-by: AlexDBlack <blacka101@gmail.com>

* Test improvement

Signed-off-by: AlexDBlack <blacka101@gmail.com>

* Small polish

Signed-off-by: AlexDBlack <blacka101@gmail.com>

* SameDiff op runtime benchmarking listener (#42)

Signed-off-by: AlexDBlack <blacka101@gmail.com>

* INLINE_LOOPS for windows

Signed-off-by: raver119 <raver119@gmail.com>

* [WIP] ThreadPool (#8)

This PR removes OpenMP use in 95% of cases
2019-11-13 17:15:18 +03:00

90 lines
2.7 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
******************************************************************************/
/*
* transform.h
*
* Created on: Dec 28, 2015
* @author: agibsonccc
* @author: raver119@gmail.com
*/
#ifndef TRANSFORM_SAME_H_
#define TRANSFORM_SAME_H_
#include <vector>
#include <templatemath.h>
#include <ops/ops.h>
#ifdef _OPENMP
#include <omp.h>
#endif
#include <OmpLaunchHelper.h>
#include <dll.h>
//#include <loops/reduce.h>
//#include <loops/scalar.h>
//#include <loops/indexreduce.h>
//#include <loops/broadcasting.h>
#ifdef __CUDACC__
#include <cuda.h>
#include <cuda_runtime.h>
#endif
#include "legacy_ops.h"
namespace functions {
namespace transform {
template<typename X>
class TransformSame {
public:
#ifdef __CUDACC__
template<typename OpType>
static __device__ void transformCuda(
void *dy,
Nd4jLong *shapeInfo,
void *params,
void *result,
Nd4jLong *resultShapeInfo,
int *allocationPointer,
void *reductionPointer,
Nd4jLong *tadShapeInfo,
Nd4jLong *tadOffsets);
template <typename OpType>
static _CUDA_H void intermediateShaped(dim3 launchDims, cudaStream_t *stream, void *x, Nd4jLong *xShape, int xRank, void *extraParams, void *z, Nd4jLong *zShape, int zRank, int *allocationPointer, void *reductionPointer, Nd4jLong *tadShapeInfo, Nd4jLong *tadOffsets);
static _CUDA_H void executeTransformShaped(dim3 launchDims, cudaStream_t *stream, int opNum, void *x, Nd4jLong *xShape, int xRank, void *extraParams, void *z, Nd4jLong *zShape, int zRank, int *allocationPointer, void *reductionPointer, Nd4jLong *tadShapeInfo, Nd4jLong *tadOffsets);
#else
static void exec(int opNum, void *dx, Nd4jLong *xShapeInfo, void *result, Nd4jLong *resultShapeInfo, void *extraParams, uint64_t threadId, uint64_t numThreads);
template<typename OpType>
static ND4J_EXPORT void exec(void *dx, Nd4jLong *xShapeInfo, void *result, Nd4jLong *resultShapeInfo, void *extraParams, uint64_t threadId, uint64_t numThreads);
#endif
};
}
}
#endif /* TRANSFORM_H_ */