Yurii Shyrma 5d9b2a16e5 Shyrma temp (#131)
* - specifying template instantiation for certain types in float16 and bloat16

Signed-off-by: Yurii <iuriish@yahoo.com>

* - polishing bfloat16 and float16 member functions template specialization

Signed-off-by: Yurii <iuriish@yahoo.com>

* - rewrite and overload array +-*/ scalar and scalar +-*/ arr in NDAray class

Signed-off-by: Yurii <iuriish@yahoo.com>

* - make corrections which have to do with and rvalue lvalue conversions

Signed-off-by: Yurii <iuriish@yahoo.com>

* - provide move semantic in NDArray operators array +-/* array

Signed-off-by: Yurii <iuriish@yahoo.com>

* float16/bfloat16 tweaks

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

* one more tweak

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

* - make float16 and bfloat16 to compile successfully on cuda

Signed-off-by: Yurii <iuriish@yahoo.com>

* - do not use resources of view-like arrays when move semantics is applied

Signed-off-by: Yurii <iuriish@yahoo.com>

* - get rid of pointers in signatures NDArray methods 1

Signed-off-by: Yurii <iuriish@yahoo.com>

* - correction of signature of NDArray::dup method

Signed-off-by: Yurii <iuriish@yahoo.com>

* - correction of signature of NDArray::reduceAlongDimension method

Signed-off-by: Yurii <iuriish@yahoo.com>

* - signature correction of NDArray::applyIndexReduce and applyTrueBroadcast methods

Signed-off-by: Yurii <iuriish@yahoo.com>

* - signature correction of NDArray::applyReduce3 and varianceAlongDimension methods

Signed-off-by: Yurii <iuriish@yahoo.com>

* - signature correction of NDArray::tensorsAlongDimension and diagonal methods

Signed-off-by: Yurii <iuriish@yahoo.com>

* - signature correction of NDArray::allTensorsAlongDimension

Signed-off-by: Yurii <iuriish@yahoo.com>

* - signature correction of NDArray::reduceAlongDimension 2

Signed-off-by: Yurii <iuriish@yahoo.com>

* - signature correction of NDArray::applyTransform 2

Signed-off-by: Yurii <iuriish@yahoo.com>

* - signature correction of NDArray::applyPairwiseTransform 2

Signed-off-by: Yurii <iuriish@yahoo.com>

* - signature correction of NDArray::applyBroadcast 2

Signed-off-by: Yurii <iuriish@yahoo.com>

* - signature correction of NDArray::applyTrueBroadcast 2

Signed-off-by: Yurii <iuriish@yahoo.com>

* - signature correction of NDArray::applyScalar and applyScalarArr

Signed-off-by: Yurii <iuriish@yahoo.com>

* - signature correction of NDArray::lambda methods

Signed-off-by: Yurii <iuriish@yahoo.com>

* - signature correction of NDArray::reduce3 methods 2

Signed-off-by: Yurii <iuriish@yahoo.com>

* - signature correction of following NDArray methods: add/sub/mul/div row/column and fillAsTriangular

Signed-off-by: Yurii <iuriish@yahoo.com>

* - signature correction of NDArray::tileToShape methods

Signed-off-by: Yurii <iuriish@yahoo.com>

* - signature correction of NDArray::isShapeSameStrict method

Signed-off-by: Yurii <iuriish@yahoo.com>

* minor corrections in tests

Signed-off-by: Yurii <iuriish@yahoo.com>

* - replace reduce op in batchnorm mkldnn

Signed-off-by: Yurii <iuriish@yahoo.com>

* - add explicit templates instantiations for operator+(NDArray&&. const scalar)

Signed-off-by: Yurii <iuriish@yahoo.com>

* - corrections of casts in float16/bfloat16

Signed-off-by: Yurii <iuriish@yahoo.com>

* - provide move semantics in following NDArray methods: transform, applyTrueBroadcast, transpose, reshape, permute

Signed-off-by: Yurii <iuriish@yahoo.com>

* - get rid of input array A duplicate in svd cuda op

Signed-off-by: Yurii <iuriish@yahoo.com>

* - avoid available bug in svd cuda API

Signed-off-by: Yurii <iuriish@yahoo.com>

* - add temporary global memory buffer in svd cuda when calcUV = false and  m != n

Signed-off-by: Yurii <iuriish@yahoo.com>

* - remove test with blfoat16 type for betainC

Signed-off-by: Yurii <iuriish@yahoo.com>

* - resolve conflicts after master has been merged in

Signed-off-by: Yurii <iuriish@yahoo.com>

* - changed type of affected input array in fused_batch_norm

Signed-off-by: Yurii <iuriish@yahoo.com>

* - add several explicit type castings

Signed-off-by: Yurii <iuriish@yahoo.com>

* - add ND4J_EXPORT to operators

Signed-off-by: Yurii <iuriish@yahoo.com>

* - add explicit template types in instantiations of template arithm operators of NDArray class

Signed-off-by: Yurii <iuriish@yahoo.com>

* - one more test fix

Signed-off-by: Yurii <iuriish@yahoo.com>

Co-authored-by: raver119 <raver119@gmail.com>
2019-12-20 22:35:39 +03:00

74 lines
3.3 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 George A. Shulinok <sgazeos@gmail.com>
//
#include <ops/declarable/helpers/matrix_band.h>
namespace nd4j {
namespace ops {
namespace helpers {
template <typename T>
void matrixBandPart_(NDArray* input, NDArray* output, Nd4jLong lowerBand, Nd4jLong upperBand) {
// TO DO: retrieve all 2D submatricies with last dimensions and process them with given bands
Nd4jLong M = input->sizeAt(-2);
Nd4jLong N = input->sizeAt(-1);
Nd4jLong lastDim = input->rankOf() - 1;
Nd4jLong preLastDim = input->rankOf() - 2;
ResultSet listOut = output->allTensorsAlongDimension({(int)preLastDim, (int)lastDim});
ResultSet listDiag = input->allTensorsAlongDimension({(int)preLastDim, (int)lastDim});
for (Nd4jLong e = 0; e < listOut.size(); ++e) {
NDArray* inputMatrix = listDiag.at(e);
NDArray* outputMatrix = listOut.at(e);
if (outputMatrix != inputMatrix) // if not inplace
outputMatrix->assign(inputMatrix);
if (lowerBand >= 0) {
for (Nd4jLong row = 0; row < inputMatrix->rows(); ++row) {
for (Nd4jLong col = 0; col < row; ++col) {
if ((row - col) > lowerBand)
outputMatrix->p(row, col, 0.);
// else
// (*outputMatrix)(row, col) = (*inputMatrix)(row, col);
}
// in_band(m, n) = (num_lower < 0 || (m-n) <= num_lower)) && (num_upper < 0 || (n-m) <= num_upper).
}
}
if (upperBand >= 0) {
for (Nd4jLong col = 0; col < inputMatrix->columns(); ++col) {
for (Nd4jLong row = 0; row < col; ++row) {
if ((col - row) > upperBand)
outputMatrix->p(row, col, 0.);
// else
// (*outputMatrix)(row, col) = (*inputMatrix)(row, col);
}
// in_band(m, n) = (num_lower < 0 || (m-n) <= num_lower)) && (num_upper < 0 || (n-m) <= num_upper).
}
}
}
}
void matrixBandPart(nd4j::LaunchContext * context, NDArray* input, NDArray* output, Nd4jLong lowerBand, Nd4jLong upperBand) {
BUILD_SINGLE_SELECTOR(input->dataType(), matrixBandPart_, (input, output, lowerBand, upperBand), FLOAT_TYPES);
}
BUILD_SINGLE_TEMPLATE(template void matrixBandPart_, (NDArray* input, NDArray* output, Nd4jLong lowerBand, Nd4jLong upperBand), FLOAT_TYPES);
}
}
}