cavis/libnd4j/include/ops/declarable/generic/linalg/triu.cpp

116 lines
3.8 KiB
C++
Raw Normal View History

2021-02-01 13:31:45 +01:00
/* ******************************************************************************
*
2019-06-06 14:21:15 +02:00
*
* 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.
*
2021-02-01 13:31:45 +01:00
* See the NOTICE file distributed with this work for additional
* information regarding copyright ownership.
2019-06-06 14:21:15 +02:00
* 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 Yurii Shyrma (iuriish@yahoo.com), created on 31.03.2018
//
#include <ops/declarable/CustomOperations.h>
#include<ops/declarable/helpers/transforms.h>
namespace sd {
2019-06-06 14:21:15 +02:00
namespace ops {
//////////////////////////////////////////////////////////////////////////
CUSTOM_OP_IMPL(triu, 1, 1, false, 0, 0) {
auto input = INPUT_VARIABLE(0);
auto output = OUTPUT_VARIABLE(0);
REQUIRE_TRUE(input->rankOf() > 0, 0, "TRIU OP: the rank of input array must be > 0, but got %i instead !", input->rankOf());
const int diag = block.getIArguments()->size() > 0 ? INT_ARG(0) : 0;
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 20:35:39 +01:00
BUILD_SINGLE_SELECTOR(input->dataType(), input->fillAsTriangular, (0, diag, 0, *output, 'l' ), LIBND4J_TYPES);
2019-06-06 14:21:15 +02:00
return Status::OK();
}
DECLARE_TYPES(triu) {
getOpDescriptor()->setAllowedInputTypes(0, {ALL_FLOATS})
->setAllowedOutputTypes(0, {ALL_FLOATS});
}
DECLARE_SHAPE_FN(triu) {
auto inShapeInfo = inputShape->at(0);
REQUIRE_TRUE(inShapeInfo[0] > 0, 0, "TRIU OP: the rank of input array must be > 0, but got %i instead !", inShapeInfo[0]);
int rank = (inShapeInfo[0] == 1) ? 2 : inShapeInfo[0];
Nd4jLong *outShapeInfo = nullptr;
ALLOCATE(outShapeInfo, block.getWorkspace(), shape::shapeInfoLength(rank), Nd4jLong);
memcpy(outShapeInfo, inShapeInfo, (1 + rank) * sizeof(Nd4jLong)); // copy rank and dimensions values only
if(inShapeInfo[0] == 1) {
outShapeInfo[0] = rank;
outShapeInfo[1] = inShapeInfo[1];
outShapeInfo[2] = inShapeInfo[1];
}
ShapeUtils::updateStridesAndType(outShapeInfo, inShapeInfo, shape::order(inShapeInfo));
return SHAPELIST(CONSTANT(outShapeInfo));
}
//////////////////////////////////////////////////////////////////////////
CUSTOM_OP_IMPL(triu_bp, 2, 1, false, 0, 0) {
auto input = INPUT_VARIABLE(0);
auto gradO = INPUT_VARIABLE(1); // dLoss/dO
auto gradI = OUTPUT_VARIABLE(0); // dLoss/dI
REQUIRE_TRUE(input->rankOf() > 0, 0, "TRIU_BP OP: the rank of input array must be > 0, but got %i instead !", input->rankOf());
const int diag = block.getIArguments()->size() > 0 ? INT_ARG(0) : 0;
helpers::triuBP(block.launchContext(), *input, *gradO, *gradI, diag);
return Status::OK();
}
DECLARE_TYPES(triu_bp) {
getOpDescriptor()->setAllowedInputTypes(0, {ALL_FLOATS})
->setAllowedInputTypes(1, {ALL_FLOATS})
->setAllowedOutputTypes(0, {ALL_FLOATS});
}
DECLARE_SHAPE_FN(triu_bp) {
auto gradOShapeInfo = inputShape->at(1);
int rank = gradOShapeInfo[0];
Nd4jLong* outShapeInfo = nullptr;
ALLOCATE(outShapeInfo, block.getWorkspace(), shape::shapeInfoLength(rank), Nd4jLong);
memcpy(outShapeInfo, gradOShapeInfo, (1 + rank) * sizeof(Nd4jLong)); // copy rank and dimensions values only
auto in = inputShape->at(0);
ShapeUtils::updateStridesAndType(outShapeInfo, in, shape::order(in));
return SHAPELIST(CONSTANT(outShapeInfo));
}
}
}