* RL4J: Add generic update rule (#502) Signed-off-by: Alexandre Boulanger <aboulang2002@yahoo.com> * Shyrma reduce (#481) * - start working on improving of cpu legacy code for reduce ops Signed-off-by: Yurii <iuriish@yahoo.com> * - further work on improving legacy loops Signed-off-by: Yurii <iuriish@yahoo.com> * - still working on improving reduce ops Signed-off-by: Yurii <iuriish@yahoo.com> * - further work on improving reduce ops Signed-off-by: Yurii <iuriish@yahoo.com> * - testing speed run of new reduce op Signed-off-by: Yurii <iuriish@yahoo.com> * - working on improvement of default loop for reduce op Signed-off-by: Yurii <iuriish@yahoo.com> * - update signatures of stuff which calls reduce ops Signed-off-by: Yurii <iuriish@yahoo.com> * - make corrections in cuda reduce kernels Signed-off-by: Yurii <iuriish@yahoo.com> * - change loop for default case in broadcast legacy ops Signed-off-by: Yurii <iuriish@yahoo.com> * - comment some shape stuff Signed-off-by: Yurii <iuriish@yahoo.com> * - comment unnecessary prints in RNGtests Signed-off-by: Yurii <iuriish@yahoo.com> * - finish to resolve conflicts after master has been merged Signed-off-by: Yurii <iuriish@yahoo.com> * - get rid of some compilation mistakes of cuda stuff Signed-off-by: Yurii <iuriish@yahoo.com> * - minor changes Signed-off-by: Yurii <iuriish@yahoo.com> * - further search for bug causing crash on java test Signed-off-by: Yurii <iuriish@yahoo.com> * - add scalar case in reduce_ ... exec stuff Signed-off-by: Yurii <iuriish@yahoo.com> * - minor corrections in NAtiveOps.cu Signed-off-by: Yurii <iuriish@yahoo.com> * - add switch to scalar case execReduceXD functions Signed-off-by: Yurii <iuriish@yahoo.com> * - add support for vectors old shape in ConstantShapeHelper::createShapeInfoWithNoUnitiesForReduce Signed-off-by: Yurii <iuriish@yahoo.com> * - correct cuda mirrorPad Signed-off-by: Yurii <iuriish@yahoo.com> * - add support for vectors old shape in cuda createShapeInfoWithNoUnitiesForReduce Signed-off-by: Yurii <iuriish@yahoo.com> Co-authored-by: raver119 <raver119@gmail.com> * Add support for CUDA 11.0 (#492) * Add support for CUDA 11.0 * libnd4j tweaks for CUDA 11 Signed-off-by: raver119@gmail.com <raver119@gmail.com> * bindings update, again? Signed-off-by: raver119@gmail.com <raver119@gmail.com> * * Update versions of JavaCPP Presets for FFmpeg, OpenBLAS, and NumPy * update API to match CUDA 8 Signed-off-by: raver119@gmail.com <raver119@gmail.com> * * Update version of JavaCPP Presets for CPython * C++ updated for cuDNN 8.0 Signed-off-by: raver119@gmail.com <raver119@gmail.com> * one more test Signed-off-by: raver119@gmail.com <raver119@gmail.com> * one more test Signed-off-by: raver119@gmail.com <raver119@gmail.com> * one more test Signed-off-by: raver119@gmail.com <raver119@gmail.com> * 128-bit alignment for workspaces Signed-off-by: raver119@gmail.com <raver119@gmail.com> * change seed in 1 test Signed-off-by: raver119@gmail.com <raver119@gmail.com> * Fix dependecy duplication in python4j-parent pom * Fix group id for in python4j-numpy * few tests tweaked Signed-off-by: raver119@gmail.com <raver119@gmail.com> * Remove macosx-x86_64-gpu from nd4j-tests-tensorflow * few minor tweaks for IndexReduce Signed-off-by: raver119@gmail.com <raver119@gmail.com> * one test removed Signed-off-by: raver119@gmail.com <raver119@gmail.com> Co-authored-by: raver119@gmail.com <raver119@gmail.com> Co-authored-by: Serhii Shepel <9946053+sshepel@users.noreply.github.com> * RL4J: Add SyncTrainer and AgentLearnerBuilder for a few algorithms (#504) Signed-off-by: Alexandre Boulanger <aboulang2002@yahoo.com> Co-authored-by: Alexandre Boulanger <44292157+aboulang2002@users.noreply.github.com> Co-authored-by: Yurii Shyrma <iuriish@yahoo.com> Co-authored-by: raver119 <raver119@gmail.com> Co-authored-by: Serhii Shepel <9946053+sshepel@users.noreply.github.com>
99 lines
3.9 KiB
C++
99 lines
3.9 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
|
|
******************************************************************************/
|
|
|
|
//
|
|
// @author raver119@gmail.com
|
|
//
|
|
|
|
#ifndef DEV_TESTS_CONSTANTSHAPEHELPER_H
|
|
#define DEV_TESTS_CONSTANTSHAPEHELPER_H
|
|
|
|
#include <system/dll.h>
|
|
#include <system/pointercast.h>
|
|
#include <map>
|
|
#include <mutex>
|
|
#include <vector>
|
|
#include <array/ShapeDescriptor.h>
|
|
#include <array/ConstantShapeBuffer.h>
|
|
#include <memory/Workspace.h>
|
|
#include <system/op_boilerplate.h>
|
|
|
|
namespace sd {
|
|
|
|
class ND4J_EXPORT ConstantShapeHelper {
|
|
private:
|
|
std::mutex _mutex;
|
|
std::vector<MAP_IMPL<ShapeDescriptor, ConstantShapeBuffer>> _cache;
|
|
|
|
|
|
ConstantShapeHelper();
|
|
public:
|
|
~ConstantShapeHelper() = default;
|
|
|
|
static ConstantShapeHelper & getInstance();
|
|
|
|
|
|
ConstantShapeBuffer& bufferForShapeInfo(sd::DataType dataType, char order, const std::vector<Nd4jLong> &shape);
|
|
ConstantShapeBuffer& bufferForShapeInfo(const ShapeDescriptor &descriptor);
|
|
ConstantShapeBuffer& bufferForShapeInfo(const Nd4jLong *shapeInfo);
|
|
ConstantShapeBuffer& bufferForShapeInfo(sd::DataType dataType, char order, int rank, const Nd4jLong* shape);
|
|
ConstantShapeBuffer& createShapeInfoWithUnitiesForBroadcast(const Nd4jLong* maxShapeInfo, const Nd4jLong* minShapeInfo, sd::memory::Workspace* workspace = nullptr, const std::vector<int> &dimensions = {});
|
|
ConstantShapeBuffer& createShapeInfoWithNoUnitiesForReduce(const Nd4jLong* maxShapeInfo, const std::vector<int> &dimsWithUnities, sd::memory::Workspace* workspace = nullptr);
|
|
ConstantShapeBuffer& createSubArrShapeInfo(const Nd4jLong* inShapeInfo, const int* dims, const int dimsSize, sd::memory::Workspace* workspace = nullptr);
|
|
|
|
|
|
const Nd4jLong* emptyShapeInfo(sd::DataType dataType);
|
|
const Nd4jLong* scalarShapeInfo(sd::DataType dataType);
|
|
const Nd4jLong* vectorShapeInfo(Nd4jLong length, sd::DataType dataType);
|
|
const Nd4jLong* createShapeInfo(const ShapeDescriptor &descriptor);
|
|
const Nd4jLong* createShapeInfo(sd::DataType dataType, char order, const std::vector<Nd4jLong> &shape);
|
|
const Nd4jLong* createShapeInfo(sd::DataType dataType, char order, int rank, const Nd4jLong* shape);
|
|
const Nd4jLong* createShapeInfo(sd::DataType dataType, const Nd4jLong* shapeInfo);
|
|
|
|
const Nd4jLong* createFromExisting(Nd4jLong *shapeInfo, sd::memory::Workspace *workspace);
|
|
const Nd4jLong* createFromExisting(Nd4jLong *shapeInfo, bool destroyOriginal = true);
|
|
|
|
bool checkBufferExistenceForShapeInfo(ShapeDescriptor &descriptor);
|
|
|
|
|
|
/**
|
|
* This method returns number of cached TAD shapes/offsets on specific device
|
|
* @return
|
|
*/
|
|
FORCEINLINE int cachedEntriesForDevice(int deviceId) {
|
|
if (deviceId > _cache.size())
|
|
throw std::runtime_error("deviceId > number of actual devices");
|
|
|
|
return _cache[deviceId].size();
|
|
}
|
|
|
|
/**
|
|
* This method returns total number of cached TAD shapes/offsets on all devices
|
|
* @return
|
|
*/
|
|
FORCEINLINE int totalCachedEntries() {
|
|
int total = 0;
|
|
|
|
for (int e = 0; e < _cache.size(); e++)
|
|
total += _cache[e].size();
|
|
|
|
return total;
|
|
}
|
|
};
|
|
}
|
|
|
|
#endif //DEV_TESTS_CONSTANTSHAPEHELPER_H
|