cavis/libnd4j/include/helpers/impl/ShapeBuilders.cpp
Samuel Audet 029b84e2b7
Development updates (#9053)
* 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>
2020-07-26 21:59:27 +09:00

165 lines
6.6 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
//
#include <helpers/ShapeBuilders.h>
namespace sd {
Nd4jLong* ShapeBuilders::createScalarShapeInfo(const sd::DataType dataType, sd::memory::Workspace* workspace) {
Nd4jLong *newShape;
ALLOCATE(newShape, workspace, shape::shapeInfoLength(0), Nd4jLong);
newShape[0] = 0;
newShape[1] = 0;
newShape[2] = 1;
newShape[3] = 99;
sd::ArrayOptions::setDataType(newShape, dataType);
return newShape;
}
Nd4jLong* ShapeBuilders::createVectorShapeInfo(const sd::DataType dataType, const Nd4jLong length, sd::memory::Workspace* workspace) {
Nd4jLong *newShape;
ALLOCATE(newShape, workspace, shape::shapeInfoLength(1), Nd4jLong);
newShape[0] = 1;
newShape[1] = length;
newShape[2] = 1;
newShape[3] = 0;
newShape[4] = 1;
newShape[5] = 99;
sd::ArrayOptions::setDataType(newShape, dataType);
return newShape;
}
////////////////////////////////////////////////////////////////////////////////
Nd4jLong* ShapeBuilders::createShapeInfo(const sd::DataType dataType, const char order, int rank, const Nd4jLong* shapeOnly, memory::Workspace* workspace) {
Nd4jLong* shapeInfo = nullptr;
if(rank == 0) { // scalar case
shapeInfo = ShapeBuilders::createScalarShapeInfo(dataType, workspace);
}
else {
ALLOCATE(shapeInfo, workspace, shape::shapeInfoLength(rank), Nd4jLong);
shapeInfo[0] = rank;
bool isEmpty = false;
for(int i = 0; i < rank; ++i) {
shapeInfo[i + 1] = shapeOnly[i];
if (shapeOnly[i] == 0)
isEmpty = true;
}
if (!isEmpty) {
shape::updateStrides(shapeInfo, order);
}
else {
shapeInfo[shape::shapeInfoLength(rank) - 1] = order;
memset(shape::stride(shapeInfo), 0, rank * sizeof(Nd4jLong));
ArrayOptions::setPropertyBit(shapeInfo, ARRAY_EMPTY);
}
sd::ArrayOptions::setDataType(shapeInfo, dataType);
}
return shapeInfo;
}
Nd4jLong* ShapeBuilders::emptyShapeInfo(const sd::DataType dataType, memory::Workspace* workspace) {
auto shapeInfo = createScalarShapeInfo(dataType, workspace);
ArrayOptions::setPropertyBit(shapeInfo, ARRAY_EMPTY);
return shapeInfo;
}
Nd4jLong* ShapeBuilders::emptyShapeInfo(const sd::DataType dataType, const char order, const std::vector<Nd4jLong> &shape, memory::Workspace* workspace) {
auto shapeInfo = createShapeInfo(dataType, order, shape, workspace);
memset(shape::stride(shapeInfo), 0, shape.size() * sizeof(Nd4jLong));
ArrayOptions::setPropertyBit(shapeInfo, ARRAY_EMPTY);
return shapeInfo;
}
////////////////////////////////////////////////////////////////////////////////
Nd4jLong* ShapeBuilders::createShapeInfo(const sd::DataType dataType, const char order, const std::vector<Nd4jLong>& shapeOnly, memory::Workspace* workspace) {
return ShapeBuilders::createShapeInfo(dataType, order, shapeOnly.size(), shapeOnly.data(), workspace);
}
////////////////////////////////////////////////////////////////////////////////
Nd4jLong* ShapeBuilders::createShapeInfo(const sd::DataType dataType, const char order, const std::initializer_list<Nd4jLong>& shapeOnly, memory::Workspace* workspace) {
return ShapeBuilders::createShapeInfo(dataType, order, std::vector<Nd4jLong>(shapeOnly), workspace);
}
////////////////////////////////////////////////////////////////////////////////
Nd4jLong* ShapeBuilders::copyShapeInfo(const Nd4jLong* inShapeInfo, const bool copyStrides, memory::Workspace* workspace) {
Nd4jLong *outShapeInfo = nullptr;
ALLOCATE(outShapeInfo, workspace, shape::shapeInfoLength(inShapeInfo), Nd4jLong);
memcpy(outShapeInfo, inShapeInfo, shape::shapeInfoByteLength(inShapeInfo));
if(!copyStrides)
shape::updateStrides(outShapeInfo, shape::order(outShapeInfo));
return outShapeInfo;
}
////////////////////////////////////////////////////////////////////////////////
Nd4jLong* ShapeBuilders::copyShapeInfoAndType(const Nd4jLong* inShapeInfo, const DataType dtype, const bool copyStrides, memory::Workspace* workspace) {
Nd4jLong* outShapeInfo = ShapeBuilders::copyShapeInfo(inShapeInfo, copyStrides, workspace);
ArrayOptions::setDataType(outShapeInfo, dtype);
return outShapeInfo;
}
////////////////////////////////////////////////////////////////////////////////
Nd4jLong* ShapeBuilders::copyShapeInfoAndType(const Nd4jLong* inShapeInfo, const Nd4jLong* shapeInfoToGetTypeFrom, const bool copyStrides, memory::Workspace* workspace) {
return ShapeBuilders::copyShapeInfoAndType(inShapeInfo, ArrayOptions::dataType(shapeInfoToGetTypeFrom), copyStrides, workspace);
}
////////////////////////////////////////////////////////////////////////////////
Nd4jLong* ShapeBuilders::createSubArrShapeInfo(const Nd4jLong* inShapeInfo, const int* dims, const int dimsSize, memory::Workspace* workspace) {
Nd4jLong *subArrShapeInfo = nullptr;
ALLOCATE(subArrShapeInfo, workspace, shape::shapeInfoLength(dimsSize), Nd4jLong);
subArrShapeInfo[0] = dimsSize; // rank
sd::ArrayOptions::copyDataType(subArrShapeInfo, inShapeInfo); // type
subArrShapeInfo[2*dimsSize + 3] = shape::order(inShapeInfo); // order
Nd4jLong* shape = shape::shapeOf(subArrShapeInfo);
Nd4jLong* strides = shape::stride(subArrShapeInfo);
for(int i = 0; i < dimsSize; ++i) {
shape[i] = shape::sizeAt(inShapeInfo, dims[i]);
strides[i] = shape::strideAt(inShapeInfo, dims[i]);
}
shape::checkStridesEwsAndOrder(subArrShapeInfo);
return subArrShapeInfo;
}
}