6de00bf75f
* [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
70 lines
2.5 KiB
C++
70 lines
2.5 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 GS <sgazeos@gmail.com> on 3/21/2018.
|
|
//
|
|
|
|
#include "ResultSet.h"
|
|
#include <ops/declarable/helpers/matrix_diag_part.h>
|
|
#include <Status.h>
|
|
#include <execution/Threads.h>
|
|
|
|
namespace nd4j {
|
|
namespace ops {
|
|
namespace helpers {
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
// Returns a batched matrix tensor with new batched diagonal values.
|
|
// for detailed explanations please take a look on web page: https://www.tensorflow.org/api_docs/python/tf/matrix_set_diag
|
|
template <typename T>
|
|
int _matrixDiagPart(const NDArray* input, NDArray* output) {
|
|
|
|
auto listOut = output->allTensorsAlongDimension({output->rankOf() - 1});
|
|
auto listDiag = input->allTensorsAlongDimension({input->rankOf() - 2, input->rankOf() - 1});
|
|
|
|
if (listOut->size() != listDiag->size()) {
|
|
nd4j_printf("matrix_diag_part: Input matrix has wrong shape.", "");
|
|
return ND4J_STATUS_VALIDATION;
|
|
}
|
|
int lastDimension = nd4j::math::nd4j_min(input->sizeAt(-2), input->sizeAt(-1));
|
|
// TODO: tune this properlys
|
|
int lO = listOut->size();
|
|
|
|
auto func = PRAGMA_THREADS_FOR {
|
|
for (auto i = start; i < stop; i += increment)
|
|
for (int j = 0; j < lastDimension; ++j)
|
|
listOut->at(i)->p(j, listDiag->at(i)->e<T>(j, j));
|
|
};
|
|
|
|
samediff::Threads::parallel_tad(func, 0, lO);
|
|
|
|
delete listOut;
|
|
delete listDiag;
|
|
|
|
return Status::OK();
|
|
}
|
|
|
|
int matrixDiagPart(nd4j::LaunchContext * context, const NDArray* input, NDArray* output) {
|
|
BUILD_SINGLE_SELECTOR(input->dataType(), return _matrixDiagPart, (input, output), LIBND4J_TYPES);
|
|
}
|
|
|
|
BUILD_SINGLE_TEMPLATE(template int _matrixDiagPart, (const NDArray* input, NDArray* output), LIBND4J_TYPES);
|
|
|
|
}
|
|
}
|
|
} |