* - 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>
87 lines
3.7 KiB
C++
87 lines
3.7 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 raver119 on 16.10.2017.
|
|
//
|
|
|
|
#include <ops/declarable/LegacyScalarBoolOp.h>
|
|
#include <NDArrayFactory.h>
|
|
#include <Status.h>
|
|
|
|
|
|
namespace nd4j {
|
|
namespace ops {
|
|
LegacyScalarBoolOp::LegacyScalarBoolOp() : LegacyOp::LegacyOp(1) {
|
|
// no-op
|
|
}
|
|
|
|
LegacyScalarBoolOp::LegacyScalarBoolOp(int opNum) : LegacyOp::LegacyOp(1, opNum){
|
|
// no-op
|
|
}
|
|
|
|
LegacyOp* LegacyScalarBoolOp::clone() {
|
|
return new LegacyScalarBoolOp(this->_opNum, *this->_scalar);
|
|
}
|
|
|
|
LegacyScalarBoolOp::LegacyScalarBoolOp(int opNum, NDArray &scalar) : LegacyOp::LegacyOp(1, opNum){
|
|
_scalar = new NDArray(scalar.dup(scalar.ordering()));
|
|
}
|
|
|
|
ShapeList *LegacyScalarBoolOp::calculateOutputShape(ShapeList *inputShape, nd4j::graph::Context &block) {
|
|
auto inShape = inputShape->at(0);
|
|
|
|
Nd4jLong *newShape;
|
|
COPY_SHAPE(inShape, newShape);
|
|
|
|
return SHAPELIST(CONSTANT(newShape));
|
|
}
|
|
|
|
Nd4jStatus LegacyScalarBoolOp::validateAndExecute(Context &block) {
|
|
auto x = INPUT_VARIABLE(0);
|
|
auto z = OUTPUT_VARIABLE(0);
|
|
|
|
int opNum = block.opNum() < 0 ? this->_opNum : block.opNum();
|
|
|
|
ExtraArguments extras(*block.getTArguments());
|
|
PointersManager manager(block.launchContext(), "LegacyScalarBoolOp");
|
|
|
|
if (block.width() > 1) {
|
|
auto y = INPUT_VARIABLE(1);
|
|
|
|
NDArray::prepareSpecialUse({z}, {x, y});
|
|
|
|
NativeOpExecutioner::execScalarBool(block.launchContext(), opNum, x->getBuffer(), x->getShapeInfo(), x->specialBuffer(), x->specialShapeInfo(), z->getBuffer(), z->getShapeInfo(), z->specialBuffer(), z->specialShapeInfo(), y->buffer(), y->shapeInfo(), y->specialBuffer(), y->specialShapeInfo(), extras.argumentsAsT(x->dataType()));
|
|
} else if (block.getTArguments()->size() > 0) {
|
|
auto y = NDArrayFactory::create(T_ARG(0), block.launchContext());
|
|
|
|
NDArray::prepareSpecialUse({z}, {x, &y});
|
|
|
|
NativeOpExecutioner::execScalarBool(block.launchContext(), opNum, x->getBuffer(), x->getShapeInfo(), x->specialBuffer(), x->specialShapeInfo(),z->getBuffer(), z->getShapeInfo(),z->specialBuffer(), z->specialShapeInfo(), y.buffer(), y.shapeInfo(), y.specialBuffer(), y.specialShapeInfo(), extras.argumentsAsT(x->dataType(), 1));
|
|
|
|
manager.synchronize();
|
|
} else {
|
|
NDArray::prepareSpecialUse({z}, {x, _scalar});
|
|
|
|
NativeOpExecutioner::execScalarBool(block.launchContext(), opNum, x->getBuffer(), x->getShapeInfo(), x->specialBuffer(), x->specialShapeInfo(),z->getBuffer(), z->getShapeInfo(),z->specialBuffer(), z->specialShapeInfo(), _scalar->buffer(), _scalar->shapeInfo(), _scalar->specialBuffer(), _scalar->specialShapeInfo(), extras.argumentsAsT(x->dataType()));
|
|
}
|
|
manager.synchronize();
|
|
STORE_RESULT(*z);
|
|
|
|
return Status::OK();
|
|
}
|
|
}
|
|
} |