2019-06-06 14:21:15 +02:00
|
|
|
/*******************************************************************************
|
|
|
|
* 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
|
|
|
|
// @author Yurii Shyrma (iuriish@yahoo.com)
|
|
|
|
//
|
|
|
|
|
|
|
|
#ifndef DEV_TESTS_DATABUFFER_H
|
|
|
|
#define DEV_TESTS_DATABUFFER_H
|
|
|
|
|
|
|
|
#include <cstring>
|
|
|
|
#include <op_boilerplate.h>
|
|
|
|
#include <dll.h>
|
|
|
|
#include <pointercast.h>
|
|
|
|
#include <array/DataType.h>
|
|
|
|
#include <memory/Workspace.h>
|
|
|
|
#include <execution/LaunchContext.h>
|
|
|
|
|
|
|
|
namespace nd4j {
|
|
|
|
|
|
|
|
class ND4J_EXPORT DataBuffer {
|
|
|
|
|
|
|
|
private:
|
|
|
|
|
|
|
|
void* _primaryBuffer;
|
|
|
|
void* _specialBuffer;
|
|
|
|
size_t _lenInBytes;
|
|
|
|
DataType _dataType;
|
|
|
|
memory::Workspace* _workspace;
|
|
|
|
bool _isOwnerPrimary;
|
|
|
|
bool _isOwnerSpecial;
|
|
|
|
|
|
|
|
#ifdef __CUDABLAS__
|
|
|
|
mutable std::atomic<Nd4jLong> _counter;
|
|
|
|
mutable std::atomic<Nd4jLong> _writePrimary;
|
|
|
|
mutable std::atomic<Nd4jLong> _writeSpecial;
|
|
|
|
mutable std::atomic<Nd4jLong> _readPrimary;
|
|
|
|
mutable std::atomic<Nd4jLong> _readSpecial;
|
|
|
|
#endif
|
|
|
|
|
|
|
|
void setCountersToZero();
|
|
|
|
void copyCounters(const DataBuffer& other);
|
|
|
|
void deleteSpecial();
|
|
|
|
FORCEINLINE void deletePrimary();
|
|
|
|
FORCEINLINE void deleteBuffers();
|
|
|
|
FORCEINLINE void setAllocFlags(const bool isOwnerPrimary, const bool isOwnerSpecial = false);
|
|
|
|
void allocateBuffers(const bool allocBoth = false);
|
|
|
|
void setSpecial(void* special, const bool isOwnerSpecial);
|
|
|
|
void copyBufferFromHost(const void* hostBuffer, size_t sizeToCopyinBytes = 0, const Nd4jLong offsetThis = 0, const Nd4jLong offsetHostBuffer = 0);
|
|
|
|
|
|
|
|
|
|
|
|
public:
|
|
|
|
|
|
|
|
FORCEINLINE DataBuffer(void* primary, void* special,
|
|
|
|
const size_t lenInBytes, const DataType dataType,
|
|
|
|
const bool isOwnerPrimary = false, const bool isOwnerSpecial = false,
|
|
|
|
memory::Workspace* workspace = nullptr);
|
|
|
|
|
|
|
|
FORCEINLINE DataBuffer(void* primary,
|
|
|
|
const size_t lenInBytes, const DataType dataType,
|
|
|
|
const bool isOwnerPrimary = false,
|
|
|
|
memory::Workspace* workspace = nullptr);
|
|
|
|
|
|
|
|
FORCEINLINE DataBuffer(const void* hostBuffer, // copies data from hostBuffer to own memory buffer
|
|
|
|
const DataType dataType, const size_t lenInBytes,
|
|
|
|
memory::Workspace* workspace = nullptr);
|
|
|
|
|
|
|
|
FORCEINLINE DataBuffer(const size_t lenInBytes, const DataType dataType, memory::Workspace* workspace = nullptr, const bool allocBoth = false);
|
|
|
|
|
|
|
|
FORCEINLINE DataBuffer(const DataBuffer& other);
|
|
|
|
FORCEINLINE DataBuffer(DataBuffer&& other);
|
|
|
|
FORCEINLINE explicit DataBuffer();
|
|
|
|
FORCEINLINE ~DataBuffer();
|
|
|
|
|
|
|
|
FORCEINLINE DataBuffer& operator=(const DataBuffer& other);
|
|
|
|
FORCEINLINE DataBuffer& operator=(DataBuffer&& other) noexcept;
|
|
|
|
|
|
|
|
FORCEINLINE DataType getDataType();
|
|
|
|
FORCEINLINE size_t getLenInBytes() const;
|
|
|
|
|
|
|
|
FORCEINLINE void* primary();
|
|
|
|
FORCEINLINE void* special();
|
|
|
|
|
|
|
|
FORCEINLINE void allocatePrimary();
|
|
|
|
void allocateSpecial();
|
|
|
|
|
|
|
|
void writePrimary() const;
|
|
|
|
void writeSpecial() const;
|
|
|
|
void readPrimary() const;
|
|
|
|
void readSpecial() const;
|
|
|
|
bool isPrimaryActual() const;
|
|
|
|
bool isSpecialActual() const;
|
|
|
|
|
|
|
|
template <typename T> FORCEINLINE T* primaryAsT();
|
|
|
|
template <typename T> FORCEINLINE T* specialAsT();
|
|
|
|
|
|
|
|
void syncToPrimary(const LaunchContext* context, const bool forceSync = false);
|
|
|
|
void syncToSpecial(const bool forceSync = false);
|
|
|
|
|
|
|
|
void setToZeroBuffers(const bool both = false);
|
|
|
|
|
|
|
|
void copyBufferFrom(const DataBuffer& other, size_t sizeToCopyinBytes = 0, const Nd4jLong offsetThis = 0, const Nd4jLong offsetOther = 0);
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
///// IMLEMENTATION OF INLINE METHODS /////
|
|
|
|
|
|
|
|
|
|
|
|
////////////////////////////////////////////////////////////////////////
|
|
|
|
// default constructor
|
|
|
|
DataBuffer::DataBuffer() {
|
|
|
|
|
|
|
|
_primaryBuffer = nullptr;
|
|
|
|
_specialBuffer = nullptr;
|
|
|
|
_lenInBytes = 0;
|
|
|
|
_dataType = INT8;
|
|
|
|
_workspace = nullptr;
|
|
|
|
_isOwnerPrimary = false;
|
|
|
|
_isOwnerSpecial = false;
|
|
|
|
|
|
|
|
setCountersToZero();
|
|
|
|
}
|
|
|
|
|
|
|
|
////////////////////////////////////////////////////////////////////////
|
|
|
|
// copy constructor
|
|
|
|
DataBuffer::DataBuffer(const DataBuffer &other) {
|
|
|
|
|
|
|
|
throw std::runtime_error("DataBuffer copy constructor: we don't expect using of this constructor!");
|
|
|
|
|
|
|
|
_lenInBytes = other._lenInBytes;
|
|
|
|
_dataType = other._dataType;
|
|
|
|
_workspace = other._workspace;
|
|
|
|
|
|
|
|
_primaryBuffer = nullptr;
|
|
|
|
_specialBuffer = nullptr;
|
|
|
|
|
|
|
|
setCountersToZero();
|
|
|
|
|
|
|
|
allocateBuffers();
|
|
|
|
copyBufferFrom(other);
|
|
|
|
}
|
|
|
|
|
|
|
|
////////////////////////////////////////////////////////////////////////
|
|
|
|
DataBuffer::DataBuffer(void* primary, void* special,
|
|
|
|
const size_t lenInBytes, const DataType dataType,
|
|
|
|
const bool isOwnerPrimary, const bool isOwnerSpecial,
|
|
|
|
memory::Workspace* workspace) {
|
|
|
|
|
|
|
|
if (primary == nullptr && special == nullptr)
|
|
|
|
throw std::runtime_error("DataBuffer constructor: can't be initialized with both nullptr buffers !");
|
|
|
|
|
|
|
|
_primaryBuffer = primary;
|
|
|
|
_specialBuffer = special;
|
|
|
|
_lenInBytes = lenInBytes;
|
|
|
|
_dataType = dataType;
|
|
|
|
_workspace = workspace;
|
|
|
|
_isOwnerPrimary = isOwnerPrimary;
|
|
|
|
_isOwnerSpecial = isOwnerSpecial;
|
|
|
|
|
|
|
|
setCountersToZero();
|
|
|
|
|
|
|
|
if(primary != nullptr)
|
|
|
|
readPrimary();
|
|
|
|
if(special != nullptr)
|
|
|
|
readSpecial();
|
|
|
|
}
|
|
|
|
|
|
|
|
////////////////////////////////////////////////////////////////////////
|
|
|
|
DataBuffer::DataBuffer(void* primary, const size_t lenInBytes, const DataType dataType, const bool isOwnerPrimary, memory::Workspace* workspace):
|
|
|
|
DataBuffer(primary, nullptr, lenInBytes, dataType, isOwnerPrimary, false, workspace) {
|
|
|
|
|
|
|
|
syncToSpecial(true);
|
|
|
|
}
|
|
|
|
|
|
|
|
////////////////////////////////////////////////////////////////////////
|
|
|
|
// copies data from hostBuffer to own memory buffer
|
|
|
|
DataBuffer::DataBuffer(const void* hostBuffer, const DataType dataType, const size_t lenInBytes, memory::Workspace* workspace) {
|
|
|
|
|
|
|
|
if (hostBuffer == nullptr)
|
|
|
|
throw std::runtime_error("DataBuffer constructor: can't be initialized with nullptr host buffer !");
|
|
|
|
if (lenInBytes == 0)
|
|
|
|
throw std::runtime_error("DataBuffer constructor: can't be initialized with zero length !");
|
|
|
|
|
|
|
|
_primaryBuffer = nullptr;
|
|
|
|
_specialBuffer = nullptr;
|
|
|
|
_lenInBytes = lenInBytes;
|
|
|
|
_dataType = dataType;
|
|
|
|
_workspace = workspace;
|
|
|
|
|
|
|
|
setCountersToZero();
|
|
|
|
|
|
|
|
allocateBuffers();
|
|
|
|
|
|
|
|
copyBufferFromHost(hostBuffer, lenInBytes);
|
|
|
|
}
|
|
|
|
|
|
|
|
////////////////////////////////////////////////////////////////////////
|
|
|
|
DataBuffer::DataBuffer(const size_t lenInBytes, const DataType dataType, memory::Workspace* workspace, const bool allocBoth) {
|
|
|
|
|
|
|
|
_dataType = dataType;
|
|
|
|
_workspace = workspace;
|
|
|
|
_lenInBytes = lenInBytes;
|
|
|
|
|
|
|
|
_primaryBuffer = nullptr;
|
|
|
|
_specialBuffer = nullptr;
|
|
|
|
|
|
|
|
setCountersToZero();
|
|
|
|
|
|
|
|
if(!lenInBytes == 0) {
|
|
|
|
allocateBuffers(allocBoth);
|
|
|
|
writeSpecial();
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
////////////////////////////////////////////////////////////////////////
|
|
|
|
// move constructor
|
|
|
|
DataBuffer::DataBuffer(DataBuffer&& other) {
|
|
|
|
|
|
|
|
_primaryBuffer = other._primaryBuffer;
|
|
|
|
_specialBuffer = other._specialBuffer;
|
|
|
|
_lenInBytes = other._lenInBytes;
|
|
|
|
_dataType = other._dataType;
|
|
|
|
_workspace = other._workspace;
|
|
|
|
_isOwnerPrimary = other._isOwnerPrimary;
|
|
|
|
_isOwnerSpecial = other._isOwnerSpecial;
|
|
|
|
|
|
|
|
copyCounters(other);
|
|
|
|
|
|
|
|
other._primaryBuffer = other._specialBuffer = nullptr;
|
|
|
|
other.setAllocFlags(false, false);
|
|
|
|
other._lenInBytes = 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
////////////////////////////////////////////////////////////////////////
|
|
|
|
// assignment operator
|
|
|
|
DataBuffer& DataBuffer::operator=(const DataBuffer& other) {
|
|
|
|
|
|
|
|
if (this == &other)
|
|
|
|
return *this;
|
|
|
|
|
|
|
|
deleteBuffers();
|
|
|
|
|
|
|
|
_lenInBytes = other._lenInBytes;
|
|
|
|
_dataType = other._dataType;
|
|
|
|
_workspace = other._workspace;
|
|
|
|
|
|
|
|
allocateBuffers();
|
|
|
|
copyBufferFrom(other);
|
Merge master to upstream (#7945)
* Shugeo strided slice zeros (#14)
* Modified strided_slice op to properly work with empty-like shapes.
* Fixed test for reduce_mean with empty-like input.
* [WIP] Last merge (#15)
* correct logsoftmax looss (#2)
* Small SameDiff listener fix (#4)
* Various fixes (#6)
* #7839 Fix for asXMatrix and tests
* #7866 EmbeddingSequenceLayer dtype fix + test
* #7856 SameDiff save/load stream methods
* #7859 RegressionEvaluation rank 4 fix + tests + axis configuration
* EvaluationBinary 3d/4d
* More evaluation 3d/4d tests
* #7847 Evaluation empty checks
* Small test ifx
* #7848 Fix median edge case
* Improve DL4J samediff layer tests
* [WIP] FastText wrapper implemented (#8)
* FastText implemented
* Some fixes
* Fix shapes for wordsNearest
* Validation of input vectors
* Fixes
* Fixed test
* Thread tagged
* Some tweaks
* setContextClassLoader for DeallocatorServiceThread
* Numpy format tests (#1)
* Various fixes (#11)
* #7852 SameDiff gather fix
* #7892 SameDiff placeholder to constant conversion
* #7890 validate input rank for MLN/CG init methods
* Fix broken permute shape calculation
* Permute and gather fixes
* Tests
* #7850 LogSumExp fix + test
* Handful of test fixes
* Empty arrays with non-scalar shapes (#10)
* minor rearrangements for lambdas
* empty tensors with non-scalar shapes
* numpy empty tensors with non-scalar shapes
* few more empty tweaks
* Small fixes
* conv3d signature update
* micro fix in batchnorm mkldnn
* Import fixes
* Fix
* MKL-DNN update
* Small fill fix
* fill with empty input + test
* Fixes
* Small error improvement
* Fix
* one special test
* couple of fixes for lstm
* Rewrite TFGraphMapper.getNDArrayFromTensor to be maintainable and less error prone
* Fixes
* FP16
* Unsigned
* BFloat16
* Fill op - empty tweaks
* - couple of fixes for empty arrays construction
- stack updated
* strided slice fix
* one transform test
* provide method for reducing shapeInfo in case of input array is empty
* Fixed reduceAlongDimensions to use empty input properly.
* couple of broadcast tests
* couple of tests broadcast tests + tweak to make them pass
* add check of non-empty to methods producing sub-arrays
* Fixed reshapeC with zeros in shape.
* complete empty check in reduce_... legacy ops
* Concat and cumsum/prod
* Tweak to empty shape inference on import
* add empty check to the rest of reduce legacy ops
* one more test
* correct typo in evalReduceShapeInfoEmpty
* Added tests for reduce_* ops to tests with zero shapes.
* few more tests for empty reductions
* Fixed strided_slice op with empty case and tests.
* one more empty reduction test
* Fixed strided_slice test.
* add empty check to NDArray::reshapei
* infOrMax
* empty min/max with infinity tests
* made unstack working correctly with empty arrays
* few IndexReduce tests + tweaks for empty shapes
* add test for empty concat
* few tests fixed
* Validation fix for reductions on empty shapes
* Reverse fix
* Reduction shape calc fixes
* SameDiff.generateOutputVariable: don't use shape function to determine number of outputs
* Range fix
* - NDArray constructor updated for scalars/empty arrays
- few tests fixed
* More fixes
* Empty creator fixes
* concat fix
* concat fix
* TF import tests: allow 'both all NaN' and 'both all inf' to pass
* Slice, zero fraction, and reshape fixes
* transpose, gather
* Zero fraction
* scalar cast fix
* Empty reduction axis support
* few more tests fixed
* Fixed input checks conforming with TF for concat op and tests.
* few tests fixed
* matmul scalar shape fix
* Fixed checkout for data type and scalarity with concat to allow non-empty scalars with vector concats.
* broadcast bool fix
* few more tests
* few more tests
* correct evalReduceShapeInfoEmpty
* argmax/argmin + tests
* one more empty edge case + one more test
* argmax/argmin/realdiv_bp tweaks
* empty reshape test + fix
* Helper fixes
* Small fixes
* Gather test fix
* Gather test fix
* Small fixes
* reduce scalar zero values
* scalar mean workaround
* Remove debug code
* along dim mean workaround
* one more test
* - equalsTo() tweak for empty arrays
- one more test
* broadcast tweaks
* [WIP] Fixing outstanding issues for NLP (#9)
* Avoid using not-inited objects
* Test fixed.
* Redundant method avoided for models like FastText
* KMeans++ implementation
* KMeans++ implementation
* Disable parallel execution
* KMeans++
* Tests
* Dev branch merge (#16)
* SameDiff: convertDataType and gradient check util improvements (#12)
* GradCheck util improvements
* StopGradient constructor + test
* SameDiff: Add datatype conversion
* Javadoc and add DataType.isNumerical()
* Small fix
* Fix SameDiff TF import test cases intermediate naming (workaround for bad default)
* TFGraphTestAllHelper: check intermediates in execution order
* Add missing debug listener
* [WIP] lstmBlock fix + other changes (#13)
- fixes lstmBlock issue
- changes NDArray method reshape(), permute(), transpose() by making them return instance instead of pointer
- CheckNumerics op
- fixes for ReduceBool IsInfOrNan & IsFinite
* Small test fix
* CheckNumerics op wrapper
* Fix some issues on master (#17)
* Fix DataVec test issue
* Fix issue with dl4j SameDiff output layer
* Dtype fix for lambda layers
* #7912 BertIterator dtype fix (use float32 not global default)
* [WIP] Next set of CUDA stuff (#7)
New CUDA implementations and improvements
* bad file
* Dev branch master merge (#23)
* SameDiff: convertDataType and gradient check util improvements (#12)
* GradCheck util improvements
* StopGradient constructor + test
* SameDiff: Add datatype conversion
* Javadoc and add DataType.isNumerical()
* Small fix
* Fix SameDiff TF import test cases intermediate naming (workaround for bad default)
* TFGraphTestAllHelper: check intermediates in execution order
* Add missing debug listener
* [WIP] lstmBlock fix + other changes (#13)
- fixes lstmBlock issue
- changes NDArray method reshape(), permute(), transpose() by making them return instance instead of pointer
- CheckNumerics op
- fixes for ReduceBool IsInfOrNan & IsFinite
* Small test fix
* CheckNumerics op wrapper
* Compatibility of deserialization (#18)
Signed-off-by: Alexander Stoyakin <alexander.stoyakin@gmail.com>
* SameDiff: add activation gradient checking support for debugging (#19)
* SameDiff gradient checker: first pass on activation gradient checks
* Fixes + tests for activation gradient checking
* Javadoc
* [WIP] Some nd4j data type corrections (#20)
* Adjust data type
* Set correct Data type.
* Size of proper data type.
* fix averaged cpu load (#22)
* SameDiff ops, TF import and fixes (#24)
* CheckNumerics tests + fixes + misc fixes
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Fake quant
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Fixes
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* FakeQuantWithMinMaxArgs
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* CheckNumerics fix
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Fix libnd4j ALL_INTS and ALL_FLOATS declaration (uint and bfloat types)
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Small fix
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Javadoc
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Exception tweak
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* fix
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Fix for out of scope stack allocated var use
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Ignores
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Ignore for known failing test (already logged issue)
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Merge upstream to fork (#25)
* Add thousand-separator commas to TotalParams (#7915)
* Add thousand-separator commas to TotalParams
The number of parameters can be quite large, and it would help the reading of the summary printout to have the TotalParams column & values at the bottom have thousand-separator-commas in them.
* Add thousand-separator commas to MultiLayerNetwork
Corresponding change to MultiLayerNetwork
Signed-off-by: Jxtps Jxtps <jxtps435@gmail.com>
* Update contributing and issue/PR templates (#7934)
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Fix link to AdaDelta paper (#7942)
Fix link to AdaDelta paper hosted on matthewzeiler.com
Signed-off-by: Jxtps
* Fixes, and ignores for known/logged failing issues (#7943)
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* SameDiff + DL4J/SameDiff: Multiple fixes (#28)
* #7919 HDF5 attribute buffer length fix
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #7909 Arbiter constructor exception ux improvements
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #7925 RNN output layer length checks
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #7939 Add listener for validating inputs are not incorrectly modified
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #7939 Integrate NonInplaceValidationListener into tests
* #7844 DL4J SameDiff fixes for variable minibatch size
* DL4J SameDiff fixes - ensure gradient for input placeholder is available
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Tweaks to ExternalErrorsFunction - use placeholders, make more robust
* Another fix
* More fixes
* More SameDiff/DL4J fixes
* Scope out scalar array creation in BaseScalarOp
* Remove debug code
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* [WIP] Final dev branch merge (#29)
* SameDiff: convertDataType and gradient check util improvements (#12)
* GradCheck util improvements
* StopGradient constructor + test
* SameDiff: Add datatype conversion
* Javadoc and add DataType.isNumerical()
* Small fix
* Fix SameDiff TF import test cases intermediate naming (workaround for bad default)
* TFGraphTestAllHelper: check intermediates in execution order
* Add missing debug listener
* [WIP] lstmBlock fix + other changes (#13)
- fixes lstmBlock issue
- changes NDArray method reshape(), permute(), transpose() by making them return instance instead of pointer
- CheckNumerics op
- fixes for ReduceBool IsInfOrNan & IsFinite
* Small test fix
* CheckNumerics op wrapper
* Compatibility of deserialization (#18)
Signed-off-by: Alexander Stoyakin <alexander.stoyakin@gmail.com>
* SameDiff: add activation gradient checking support for debugging (#19)
* SameDiff gradient checker: first pass on activation gradient checks
* Fixes + tests for activation gradient checking
* Javadoc
* [WIP] Some nd4j data type corrections (#20)
* Adjust data type
* Set correct Data type.
* Size of proper data type.
* fix averaged cpu load (#22)
* [WIP] Multiple dataset iterators (#27)
* Splitting dataset into arbitrary number
* Fixes
* Multiple split of iterator
* Test
* Test
* Some fixes
* signature change
* one more tweak
Signed-off-by: raver119 <raver119@gmail.com>
* one more test for sequential use of DataSetIteratorSplitter
Signed-off-by: raver119 <raver119@gmail.com>
* Fixes
* Fixes
* one more test for Alexander
Signed-off-by: raver119 <raver119@gmail.com>
* Some fixes
* Some fixes
* one more test for Alexander
Signed-off-by: raver119 <raver119@gmail.com>
* minor test fix
Signed-off-by: raver119 <raver119@gmail.com>
* Some fixes
* Some fixes
* couple of assertions tweaked
Signed-off-by: raver119 <raver119@gmail.com>
* MDS splitter test :/
Signed-off-by: raver119 <raver119@gmail.com>
* Minor refactoring
* Multi dataset
* Some fixes
* More tests
* Small number of test fixes/improvements (failures on CI) (#31)
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* [WIP] More CUDA stuff (#26)
* initial commit
Signed-off-by: raver119 <raver119@gmail.com>
* LRN BP CUDA
Signed-off-by: raver119 <raver119@gmail.com>
* less memory
Signed-off-by: raver119 <raver119@gmail.com>
* Fixed bug with crop_and_resize op helper.
* get rid of unnecessary index-calculation dunction
Signed-off-by: Yurii <yurii@skymind.io>
* Fixed sort with nth_element cuda-based helper.
* Refactored nth_element.
* Refactored nth_element op and tests.
* Modified usage of dim array with sortTad routine.
* Refactored main routine of helper for non_max_image_suppression op.
* non_max_image_suppression op helper with cuda kernel implementation. Initial revision.
* fix vol2col cuda kernel
* meh
Signed-off-by: raver119 <raver119@gmail.com>
* topK concept
Signed-off-by: raver119 <raver119@gmail.com>
* unsorted topK with scanWitdh of 1
Signed-off-by: raver119 <raver119@gmail.com>
* correct vol2col tests
* sorted/unsorted topK
Signed-off-by: raver119 <raver119@gmail.com>
* implementation and fixing col2im/col2vol
* Corrected usage flags with input/output with reverse op.
* dup is const now
Signed-off-by: raver119 <raver119@gmail.com>
* percentile op
Signed-off-by: raver119 <raver119@gmail.com>
* group tests for mapool2d
Signed-off-by: Yurii <yurii@skymind.io>
* special test for george
Signed-off-by: raver119 <raver119@gmail.com>
* less threads for sortTad
Signed-off-by: raver119 <raver119@gmail.com>
* provide conv2d for cuda
Signed-off-by: Yurii <yurii@skymind.io>
* remove auther in sort tad kernel code
Signed-off-by: Yurii <yurii@skymind.io>
* provide depthwise_conv2d for cuda
Signed-off-by: Yurii <yurii@skymind.io>
* - max_pooling_with_argmax
- null check for special use
Signed-off-by: raver119 <raver119@gmail.com>
* dts cuda
Signed-off-by: raver119 <raver119@gmail.com>
* provide sconv2d for cuda
Signed-off-by: Yurii <yurii@skymind.io>
* std cuda
Signed-off-by: raver119 <raver119@gmail.com>
* Refactored non_max_suppression op to conform TF implementation.
* Improved suppression helper.
* provide pooling3d for cuda
Signed-off-by: Yurii <yurii@skymind.io>
* minor lstm rearrangements
Signed-off-by: raver119 <raver119@gmail.com>
* more of minor lstm rearrangements
Signed-off-by: raver119 <raver119@gmail.com>
* (bi)dynamic_rnn
Signed-off-by: raver119 <raver119@gmail.com>
* templates init order
Signed-off-by: raver119 <raver119@gmail.com>
* Refactored non_max_suppression op.
* Added cuda kernel for non_max_suppression.
* CPU sort by key/value
Signed-off-by: raver119 <raver119@gmail.com>
* CPU sort TAD by key/value
Signed-off-by: raver119 <raver119@gmail.com>
* CPU sort TAD by key/value tests
Signed-off-by: raver119 <raver119@gmail.com>
* Eliminate compiler error with cuda implementation.
* - repaired gradCheck in cuda
- provide conv2d_bp for cuda
Signed-off-by: Yurii <yurii@skymind.io>
* missed signature
Signed-off-by: raver119 <raver119@gmail.com>
* provide depthwise_conv2d_bp for cuda
Signed-off-by: Yurii <yurii@skymind.io>
* Implementation of lup helper with cuda kernel. Initial commit.
* further work on backprops for convolutions
Signed-off-by: Yurii <yurii@skymind.io>
* CUDA linear sort by key/val
Signed-off-by: raver119 <raver119@gmail.com>
* CUDA tad sort by key/val
Signed-off-by: raver119 <raver119@gmail.com>
* start providing of backprop for pooling2d/3d
Signed-off-by: Yurii <yurii@skymind.io>
* Added atomicAdd for bool datatype.
* dynamic partition concept
Signed-off-by: raver119 <raver119@gmail.com>
* dynamic partition concept
Signed-off-by: raver119 <raver119@gmail.com>
* dynamic partition scalar CUDA
Signed-off-by: raver119 <raver119@gmail.com>
* important comment
Signed-off-by: raver119 <raver119@gmail.com>
* fix pooling2d/3d backprop helpers
Signed-off-by: Yurii <yurii@skymind.io>
* Added non-linear test with dynamic_partition.
* Improved test for dynamic_partition.
* dynamic_partition TAD concept
Signed-off-by: raver119 <raver119@gmail.com>
* - dynamic_partition TAD CUDA impl
- dynamic_partition TAD CPU fix
Signed-off-by: raver119 <raver119@gmail.com>
* - rewrite cpu code for usampling2d/3d
- write cuda code for usampling2d/3d
Signed-off-by: Yurii <yurii@skymind.io>
* dynamic_stitch CUDA vector case
Signed-off-by: raver119 <raver119@gmail.com>
* dynamic_stitch CUDA TAD case concept
Signed-off-by: raver119 <raver119@gmail.com>
* dynamic_stitch CUDA TAD case impl
Signed-off-by: raver119 <raver119@gmail.com>
* Added tests for dynamic_stitch 3D-4D cases.
* minor tests tweaks
Signed-off-by: raver119 <raver119@gmail.com>
* Fixed type check for dynamic stitch.
* min/max bp
Signed-off-by: raver119 <raver119@gmail.com>
* rewrite code for upsampling2d/3d cpu
Signed-off-by: Yurii <yurii@skymind.io>
* reduce min/max/norm_max bp
Signed-off-by: raver119 <raver119@gmail.com>
* lup implementation. Additional enhancements.
* provide code for upsamling2d/3d backprop
Signed-off-by: Yurii <yurii@skymind.io>
* weightedCrossEntropyWithLogits
Signed-off-by: raver119 <raver119@gmail.com>
* Fixed template math atomicMul for 64bit ints.
* Refactored dynamic_partition_bp op.
* inverseBroadcast fix
Signed-off-by: raver119 <raver119@gmail.com>
* DynamicPartitionBP test datatype fixed.
* - nd4j_atomicMul Windows fix
- cpu/NDArrayLambda.hpp excluded from CUDA
Signed-off-by: raver119 <raver119@gmail.com>
2019-06-27 17:37:04 +02:00
|
|
|
|
|
|
|
return *this;
|
2019-06-06 14:21:15 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
////////////////////////////////////////////////////////////////////////
|
|
|
|
// move assignment operator
|
|
|
|
DataBuffer& DataBuffer::operator=(DataBuffer&& other) noexcept {
|
|
|
|
|
|
|
|
if (this == &other)
|
|
|
|
return *this;
|
|
|
|
|
|
|
|
deleteBuffers();
|
|
|
|
|
|
|
|
_primaryBuffer = other._primaryBuffer;
|
|
|
|
_specialBuffer = other._specialBuffer;
|
|
|
|
_lenInBytes = other._lenInBytes;
|
|
|
|
_dataType = other._dataType;
|
|
|
|
_workspace = other._workspace;
|
|
|
|
_isOwnerPrimary = other._isOwnerPrimary;
|
|
|
|
_isOwnerSpecial = other._isOwnerSpecial;
|
|
|
|
|
|
|
|
copyCounters(other);
|
|
|
|
|
|
|
|
other._primaryBuffer = other._specialBuffer = nullptr;
|
|
|
|
other.setAllocFlags(false, false);
|
|
|
|
other._lenInBytes = 0;
|
Merge master to upstream (#7945)
* Shugeo strided slice zeros (#14)
* Modified strided_slice op to properly work with empty-like shapes.
* Fixed test for reduce_mean with empty-like input.
* [WIP] Last merge (#15)
* correct logsoftmax looss (#2)
* Small SameDiff listener fix (#4)
* Various fixes (#6)
* #7839 Fix for asXMatrix and tests
* #7866 EmbeddingSequenceLayer dtype fix + test
* #7856 SameDiff save/load stream methods
* #7859 RegressionEvaluation rank 4 fix + tests + axis configuration
* EvaluationBinary 3d/4d
* More evaluation 3d/4d tests
* #7847 Evaluation empty checks
* Small test ifx
* #7848 Fix median edge case
* Improve DL4J samediff layer tests
* [WIP] FastText wrapper implemented (#8)
* FastText implemented
* Some fixes
* Fix shapes for wordsNearest
* Validation of input vectors
* Fixes
* Fixed test
* Thread tagged
* Some tweaks
* setContextClassLoader for DeallocatorServiceThread
* Numpy format tests (#1)
* Various fixes (#11)
* #7852 SameDiff gather fix
* #7892 SameDiff placeholder to constant conversion
* #7890 validate input rank for MLN/CG init methods
* Fix broken permute shape calculation
* Permute and gather fixes
* Tests
* #7850 LogSumExp fix + test
* Handful of test fixes
* Empty arrays with non-scalar shapes (#10)
* minor rearrangements for lambdas
* empty tensors with non-scalar shapes
* numpy empty tensors with non-scalar shapes
* few more empty tweaks
* Small fixes
* conv3d signature update
* micro fix in batchnorm mkldnn
* Import fixes
* Fix
* MKL-DNN update
* Small fill fix
* fill with empty input + test
* Fixes
* Small error improvement
* Fix
* one special test
* couple of fixes for lstm
* Rewrite TFGraphMapper.getNDArrayFromTensor to be maintainable and less error prone
* Fixes
* FP16
* Unsigned
* BFloat16
* Fill op - empty tweaks
* - couple of fixes for empty arrays construction
- stack updated
* strided slice fix
* one transform test
* provide method for reducing shapeInfo in case of input array is empty
* Fixed reduceAlongDimensions to use empty input properly.
* couple of broadcast tests
* couple of tests broadcast tests + tweak to make them pass
* add check of non-empty to methods producing sub-arrays
* Fixed reshapeC with zeros in shape.
* complete empty check in reduce_... legacy ops
* Concat and cumsum/prod
* Tweak to empty shape inference on import
* add empty check to the rest of reduce legacy ops
* one more test
* correct typo in evalReduceShapeInfoEmpty
* Added tests for reduce_* ops to tests with zero shapes.
* few more tests for empty reductions
* Fixed strided_slice op with empty case and tests.
* one more empty reduction test
* Fixed strided_slice test.
* add empty check to NDArray::reshapei
* infOrMax
* empty min/max with infinity tests
* made unstack working correctly with empty arrays
* few IndexReduce tests + tweaks for empty shapes
* add test for empty concat
* few tests fixed
* Validation fix for reductions on empty shapes
* Reverse fix
* Reduction shape calc fixes
* SameDiff.generateOutputVariable: don't use shape function to determine number of outputs
* Range fix
* - NDArray constructor updated for scalars/empty arrays
- few tests fixed
* More fixes
* Empty creator fixes
* concat fix
* concat fix
* TF import tests: allow 'both all NaN' and 'both all inf' to pass
* Slice, zero fraction, and reshape fixes
* transpose, gather
* Zero fraction
* scalar cast fix
* Empty reduction axis support
* few more tests fixed
* Fixed input checks conforming with TF for concat op and tests.
* few tests fixed
* matmul scalar shape fix
* Fixed checkout for data type and scalarity with concat to allow non-empty scalars with vector concats.
* broadcast bool fix
* few more tests
* few more tests
* correct evalReduceShapeInfoEmpty
* argmax/argmin + tests
* one more empty edge case + one more test
* argmax/argmin/realdiv_bp tweaks
* empty reshape test + fix
* Helper fixes
* Small fixes
* Gather test fix
* Gather test fix
* Small fixes
* reduce scalar zero values
* scalar mean workaround
* Remove debug code
* along dim mean workaround
* one more test
* - equalsTo() tweak for empty arrays
- one more test
* broadcast tweaks
* [WIP] Fixing outstanding issues for NLP (#9)
* Avoid using not-inited objects
* Test fixed.
* Redundant method avoided for models like FastText
* KMeans++ implementation
* KMeans++ implementation
* Disable parallel execution
* KMeans++
* Tests
* Dev branch merge (#16)
* SameDiff: convertDataType and gradient check util improvements (#12)
* GradCheck util improvements
* StopGradient constructor + test
* SameDiff: Add datatype conversion
* Javadoc and add DataType.isNumerical()
* Small fix
* Fix SameDiff TF import test cases intermediate naming (workaround for bad default)
* TFGraphTestAllHelper: check intermediates in execution order
* Add missing debug listener
* [WIP] lstmBlock fix + other changes (#13)
- fixes lstmBlock issue
- changes NDArray method reshape(), permute(), transpose() by making them return instance instead of pointer
- CheckNumerics op
- fixes for ReduceBool IsInfOrNan & IsFinite
* Small test fix
* CheckNumerics op wrapper
* Fix some issues on master (#17)
* Fix DataVec test issue
* Fix issue with dl4j SameDiff output layer
* Dtype fix for lambda layers
* #7912 BertIterator dtype fix (use float32 not global default)
* [WIP] Next set of CUDA stuff (#7)
New CUDA implementations and improvements
* bad file
* Dev branch master merge (#23)
* SameDiff: convertDataType and gradient check util improvements (#12)
* GradCheck util improvements
* StopGradient constructor + test
* SameDiff: Add datatype conversion
* Javadoc and add DataType.isNumerical()
* Small fix
* Fix SameDiff TF import test cases intermediate naming (workaround for bad default)
* TFGraphTestAllHelper: check intermediates in execution order
* Add missing debug listener
* [WIP] lstmBlock fix + other changes (#13)
- fixes lstmBlock issue
- changes NDArray method reshape(), permute(), transpose() by making them return instance instead of pointer
- CheckNumerics op
- fixes for ReduceBool IsInfOrNan & IsFinite
* Small test fix
* CheckNumerics op wrapper
* Compatibility of deserialization (#18)
Signed-off-by: Alexander Stoyakin <alexander.stoyakin@gmail.com>
* SameDiff: add activation gradient checking support for debugging (#19)
* SameDiff gradient checker: first pass on activation gradient checks
* Fixes + tests for activation gradient checking
* Javadoc
* [WIP] Some nd4j data type corrections (#20)
* Adjust data type
* Set correct Data type.
* Size of proper data type.
* fix averaged cpu load (#22)
* SameDiff ops, TF import and fixes (#24)
* CheckNumerics tests + fixes + misc fixes
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Fake quant
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Fixes
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* FakeQuantWithMinMaxArgs
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* CheckNumerics fix
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Fix libnd4j ALL_INTS and ALL_FLOATS declaration (uint and bfloat types)
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Small fix
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Javadoc
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Exception tweak
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* fix
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Fix for out of scope stack allocated var use
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Ignores
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Ignore for known failing test (already logged issue)
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Merge upstream to fork (#25)
* Add thousand-separator commas to TotalParams (#7915)
* Add thousand-separator commas to TotalParams
The number of parameters can be quite large, and it would help the reading of the summary printout to have the TotalParams column & values at the bottom have thousand-separator-commas in them.
* Add thousand-separator commas to MultiLayerNetwork
Corresponding change to MultiLayerNetwork
Signed-off-by: Jxtps Jxtps <jxtps435@gmail.com>
* Update contributing and issue/PR templates (#7934)
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Fix link to AdaDelta paper (#7942)
Fix link to AdaDelta paper hosted on matthewzeiler.com
Signed-off-by: Jxtps
* Fixes, and ignores for known/logged failing issues (#7943)
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* SameDiff + DL4J/SameDiff: Multiple fixes (#28)
* #7919 HDF5 attribute buffer length fix
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #7909 Arbiter constructor exception ux improvements
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #7925 RNN output layer length checks
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #7939 Add listener for validating inputs are not incorrectly modified
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #7939 Integrate NonInplaceValidationListener into tests
* #7844 DL4J SameDiff fixes for variable minibatch size
* DL4J SameDiff fixes - ensure gradient for input placeholder is available
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Tweaks to ExternalErrorsFunction - use placeholders, make more robust
* Another fix
* More fixes
* More SameDiff/DL4J fixes
* Scope out scalar array creation in BaseScalarOp
* Remove debug code
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* [WIP] Final dev branch merge (#29)
* SameDiff: convertDataType and gradient check util improvements (#12)
* GradCheck util improvements
* StopGradient constructor + test
* SameDiff: Add datatype conversion
* Javadoc and add DataType.isNumerical()
* Small fix
* Fix SameDiff TF import test cases intermediate naming (workaround for bad default)
* TFGraphTestAllHelper: check intermediates in execution order
* Add missing debug listener
* [WIP] lstmBlock fix + other changes (#13)
- fixes lstmBlock issue
- changes NDArray method reshape(), permute(), transpose() by making them return instance instead of pointer
- CheckNumerics op
- fixes for ReduceBool IsInfOrNan & IsFinite
* Small test fix
* CheckNumerics op wrapper
* Compatibility of deserialization (#18)
Signed-off-by: Alexander Stoyakin <alexander.stoyakin@gmail.com>
* SameDiff: add activation gradient checking support for debugging (#19)
* SameDiff gradient checker: first pass on activation gradient checks
* Fixes + tests for activation gradient checking
* Javadoc
* [WIP] Some nd4j data type corrections (#20)
* Adjust data type
* Set correct Data type.
* Size of proper data type.
* fix averaged cpu load (#22)
* [WIP] Multiple dataset iterators (#27)
* Splitting dataset into arbitrary number
* Fixes
* Multiple split of iterator
* Test
* Test
* Some fixes
* signature change
* one more tweak
Signed-off-by: raver119 <raver119@gmail.com>
* one more test for sequential use of DataSetIteratorSplitter
Signed-off-by: raver119 <raver119@gmail.com>
* Fixes
* Fixes
* one more test for Alexander
Signed-off-by: raver119 <raver119@gmail.com>
* Some fixes
* Some fixes
* one more test for Alexander
Signed-off-by: raver119 <raver119@gmail.com>
* minor test fix
Signed-off-by: raver119 <raver119@gmail.com>
* Some fixes
* Some fixes
* couple of assertions tweaked
Signed-off-by: raver119 <raver119@gmail.com>
* MDS splitter test :/
Signed-off-by: raver119 <raver119@gmail.com>
* Minor refactoring
* Multi dataset
* Some fixes
* More tests
* Small number of test fixes/improvements (failures on CI) (#31)
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* [WIP] More CUDA stuff (#26)
* initial commit
Signed-off-by: raver119 <raver119@gmail.com>
* LRN BP CUDA
Signed-off-by: raver119 <raver119@gmail.com>
* less memory
Signed-off-by: raver119 <raver119@gmail.com>
* Fixed bug with crop_and_resize op helper.
* get rid of unnecessary index-calculation dunction
Signed-off-by: Yurii <yurii@skymind.io>
* Fixed sort with nth_element cuda-based helper.
* Refactored nth_element.
* Refactored nth_element op and tests.
* Modified usage of dim array with sortTad routine.
* Refactored main routine of helper for non_max_image_suppression op.
* non_max_image_suppression op helper with cuda kernel implementation. Initial revision.
* fix vol2col cuda kernel
* meh
Signed-off-by: raver119 <raver119@gmail.com>
* topK concept
Signed-off-by: raver119 <raver119@gmail.com>
* unsorted topK with scanWitdh of 1
Signed-off-by: raver119 <raver119@gmail.com>
* correct vol2col tests
* sorted/unsorted topK
Signed-off-by: raver119 <raver119@gmail.com>
* implementation and fixing col2im/col2vol
* Corrected usage flags with input/output with reverse op.
* dup is const now
Signed-off-by: raver119 <raver119@gmail.com>
* percentile op
Signed-off-by: raver119 <raver119@gmail.com>
* group tests for mapool2d
Signed-off-by: Yurii <yurii@skymind.io>
* special test for george
Signed-off-by: raver119 <raver119@gmail.com>
* less threads for sortTad
Signed-off-by: raver119 <raver119@gmail.com>
* provide conv2d for cuda
Signed-off-by: Yurii <yurii@skymind.io>
* remove auther in sort tad kernel code
Signed-off-by: Yurii <yurii@skymind.io>
* provide depthwise_conv2d for cuda
Signed-off-by: Yurii <yurii@skymind.io>
* - max_pooling_with_argmax
- null check for special use
Signed-off-by: raver119 <raver119@gmail.com>
* dts cuda
Signed-off-by: raver119 <raver119@gmail.com>
* provide sconv2d for cuda
Signed-off-by: Yurii <yurii@skymind.io>
* std cuda
Signed-off-by: raver119 <raver119@gmail.com>
* Refactored non_max_suppression op to conform TF implementation.
* Improved suppression helper.
* provide pooling3d for cuda
Signed-off-by: Yurii <yurii@skymind.io>
* minor lstm rearrangements
Signed-off-by: raver119 <raver119@gmail.com>
* more of minor lstm rearrangements
Signed-off-by: raver119 <raver119@gmail.com>
* (bi)dynamic_rnn
Signed-off-by: raver119 <raver119@gmail.com>
* templates init order
Signed-off-by: raver119 <raver119@gmail.com>
* Refactored non_max_suppression op.
* Added cuda kernel for non_max_suppression.
* CPU sort by key/value
Signed-off-by: raver119 <raver119@gmail.com>
* CPU sort TAD by key/value
Signed-off-by: raver119 <raver119@gmail.com>
* CPU sort TAD by key/value tests
Signed-off-by: raver119 <raver119@gmail.com>
* Eliminate compiler error with cuda implementation.
* - repaired gradCheck in cuda
- provide conv2d_bp for cuda
Signed-off-by: Yurii <yurii@skymind.io>
* missed signature
Signed-off-by: raver119 <raver119@gmail.com>
* provide depthwise_conv2d_bp for cuda
Signed-off-by: Yurii <yurii@skymind.io>
* Implementation of lup helper with cuda kernel. Initial commit.
* further work on backprops for convolutions
Signed-off-by: Yurii <yurii@skymind.io>
* CUDA linear sort by key/val
Signed-off-by: raver119 <raver119@gmail.com>
* CUDA tad sort by key/val
Signed-off-by: raver119 <raver119@gmail.com>
* start providing of backprop for pooling2d/3d
Signed-off-by: Yurii <yurii@skymind.io>
* Added atomicAdd for bool datatype.
* dynamic partition concept
Signed-off-by: raver119 <raver119@gmail.com>
* dynamic partition concept
Signed-off-by: raver119 <raver119@gmail.com>
* dynamic partition scalar CUDA
Signed-off-by: raver119 <raver119@gmail.com>
* important comment
Signed-off-by: raver119 <raver119@gmail.com>
* fix pooling2d/3d backprop helpers
Signed-off-by: Yurii <yurii@skymind.io>
* Added non-linear test with dynamic_partition.
* Improved test for dynamic_partition.
* dynamic_partition TAD concept
Signed-off-by: raver119 <raver119@gmail.com>
* - dynamic_partition TAD CUDA impl
- dynamic_partition TAD CPU fix
Signed-off-by: raver119 <raver119@gmail.com>
* - rewrite cpu code for usampling2d/3d
- write cuda code for usampling2d/3d
Signed-off-by: Yurii <yurii@skymind.io>
* dynamic_stitch CUDA vector case
Signed-off-by: raver119 <raver119@gmail.com>
* dynamic_stitch CUDA TAD case concept
Signed-off-by: raver119 <raver119@gmail.com>
* dynamic_stitch CUDA TAD case impl
Signed-off-by: raver119 <raver119@gmail.com>
* Added tests for dynamic_stitch 3D-4D cases.
* minor tests tweaks
Signed-off-by: raver119 <raver119@gmail.com>
* Fixed type check for dynamic stitch.
* min/max bp
Signed-off-by: raver119 <raver119@gmail.com>
* rewrite code for upsampling2d/3d cpu
Signed-off-by: Yurii <yurii@skymind.io>
* reduce min/max/norm_max bp
Signed-off-by: raver119 <raver119@gmail.com>
* lup implementation. Additional enhancements.
* provide code for upsamling2d/3d backprop
Signed-off-by: Yurii <yurii@skymind.io>
* weightedCrossEntropyWithLogits
Signed-off-by: raver119 <raver119@gmail.com>
* Fixed template math atomicMul for 64bit ints.
* Refactored dynamic_partition_bp op.
* inverseBroadcast fix
Signed-off-by: raver119 <raver119@gmail.com>
* DynamicPartitionBP test datatype fixed.
* - nd4j_atomicMul Windows fix
- cpu/NDArrayLambda.hpp excluded from CUDA
Signed-off-by: raver119 <raver119@gmail.com>
2019-06-27 17:37:04 +02:00
|
|
|
|
|
|
|
return *this;
|
2019-06-06 14:21:15 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
////////////////////////////////////////////////////////////////////////
|
|
|
|
void* DataBuffer::primary() {
|
|
|
|
return _primaryBuffer;
|
|
|
|
}
|
|
|
|
|
|
|
|
////////////////////////////////////////////////////////////////////////
|
|
|
|
void* DataBuffer::special() {
|
|
|
|
return _specialBuffer;
|
|
|
|
}
|
|
|
|
|
|
|
|
////////////////////////////////////////////////////////////////////////
|
|
|
|
DataType DataBuffer::getDataType() {
|
|
|
|
return _dataType;
|
|
|
|
}
|
|
|
|
|
|
|
|
////////////////////////////////////////////////////////////////////////
|
|
|
|
size_t DataBuffer::getLenInBytes() const {
|
|
|
|
return _lenInBytes;
|
|
|
|
}
|
|
|
|
|
|
|
|
////////////////////////////////////////////////////////////////////////
|
|
|
|
template <typename T>
|
|
|
|
T* DataBuffer::primaryAsT() {
|
|
|
|
return reinterpret_cast<T*>(_primaryBuffer);
|
|
|
|
}
|
|
|
|
|
|
|
|
////////////////////////////////////////////////////////////////////////
|
|
|
|
template <typename T>
|
|
|
|
T* DataBuffer::specialAsT() {
|
|
|
|
return reinterpret_cast<T*>(_specialBuffer);
|
|
|
|
}
|
|
|
|
|
|
|
|
////////////////////////////////////////////////////////////////////////
|
|
|
|
void DataBuffer::allocatePrimary() {
|
|
|
|
|
|
|
|
if (_primaryBuffer == nullptr && getLenInBytes() > 0) {
|
|
|
|
ALLOCATE(_primaryBuffer, _workspace, getLenInBytes(), int8_t);
|
|
|
|
_isOwnerPrimary = true;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
////////////////////////////////////////////////////////////////////////
|
|
|
|
void DataBuffer::setAllocFlags(const bool isOwnerPrimary, const bool isOwnerSpecial) {
|
|
|
|
|
|
|
|
_isOwnerPrimary = isOwnerPrimary;
|
|
|
|
_isOwnerSpecial = isOwnerSpecial;
|
|
|
|
}
|
|
|
|
|
|
|
|
////////////////////////////////////////////////////////////////////////
|
|
|
|
void DataBuffer::deletePrimary() {
|
|
|
|
|
|
|
|
if(_isOwnerPrimary && _primaryBuffer != nullptr && getLenInBytes() != 0) {
|
|
|
|
auto p = reinterpret_cast<int8_t*>(_primaryBuffer);
|
|
|
|
RELEASE(p, _workspace);
|
|
|
|
_primaryBuffer = nullptr;
|
|
|
|
_isOwnerPrimary = false;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
////////////////////////////////////////////////////////////////////////
|
|
|
|
void DataBuffer::deleteBuffers() {
|
|
|
|
|
|
|
|
deletePrimary();
|
|
|
|
deleteSpecial();
|
|
|
|
_lenInBytes = 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
////////////////////////////////////////////////////////////////////////
|
|
|
|
DataBuffer::~DataBuffer() {
|
|
|
|
|
|
|
|
deleteBuffers();
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
#endif //DEV_TESTS_DATABUFFER_H
|