78934c17ad
* - profiling of stack and unstack ops Signed-off-by: Yurii <iuriish@yahoo.com> * - fix bug in cpu concat op Signed-off-by: Yurii <iuriish@yahoo.com> * - correction of cuda stack and unstack Signed-off-by: Yurii <iuriish@yahoo.com> * - change shape.h method which operates with unity dimensions strides Signed-off-by: Yurii <iuriish@yahoo.com> * - rearrange stack tests Signed-off-by: Yurii <iuriish@yahoo.com> * - correct evaluation of smallest stride for moving through contiguous axis Signed-off-by: Yurii <iuriish@yahoo.com> * - forgot to update signature of function strideOverContigAxis in cuda concat and split ops Signed-off-by: Yurii <iuriish@yahoo.com> * - remove ShapeUtils::shapeAsString method applied before input arrays validations Signed-off-by: Yurii <iuriish@yahoo.com> * - further removing of ShapeUtils::shapeAsString Signed-off-by: Yurii <iuriish@yahoo.com> * - take sub-array shapeIndo/offset calculation out of NDArray class - add possibility of contiguous memory copy in execTransformAny op if opNum == assign Signed-off-by: Yurii <iuriish@yahoo.com> * - correct test_empty_scatter_2 in EmptyTests.cpp Signed-off-by: Yurii <iuriish@yahoo.com> * - profiling of slice op Signed-off-by: Yurii <iuriish@yahoo.com> * - get rid of contiguous memcpy for some cases in concat and split ops Signed-off-by: Yurii <iuriish@yahoo.com> * - forgot to declare oid nd4j::SpecialMethods<T>::splitCpuGeneric Signed-off-by: Yurii <iuriish@yahoo.com> * - correct typo in calculation of threads in cuda split op Signed-off-by: Yurii <iuriish@yahoo.com> * - forgot to correct another set of threads variables in split cuda ops Signed-off-by: Yurii <iuriish@yahoo.com> * - further conflicts resolving Signed-off-by: Yurii <iuriish@yahoo.com> Co-authored-by: raver119 <raver119@gmail.com>
77 lines
2.3 KiB
C++
77 lines
2.3 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 Yurii Shyrma (iuriish@yahoo.com), created on 01.11.2017
|
|
//
|
|
|
|
#include <system/op_boilerplate.h>
|
|
#if NOT_EXCLUDED(OP_parallel_stack)
|
|
|
|
#include <ops/declarable/CustomOperations.h>
|
|
#include<ops/declarable/helpers/stack.h>
|
|
|
|
namespace sd {
|
|
namespace ops {
|
|
|
|
|
|
CUSTOM_OP_IMPL(parallel_stack, -1, 1, false, 0, 0) {
|
|
auto input = INPUT_VARIABLE(0);
|
|
auto output = OUTPUT_VARIABLE(0);
|
|
|
|
// check whether shapes of all input array are the same
|
|
for (int i = 0; i < (int) block.width() - 1; ++i)
|
|
REQUIRE_TRUE(shape::equalsSoft((INPUT_VARIABLE(i))->getShapeInfo(), (INPUT_VARIABLE(i+1))->getShapeInfo()), 0, "PARALLEL_STACK op: the shapes of all input arrays must be the same !");
|
|
|
|
std::vector<const NDArray*> inArrs(block.width());
|
|
for(int i = 0; i < block.width(); ++i)
|
|
inArrs[i] = INPUT_VARIABLE(i);
|
|
|
|
const int dim = 0;
|
|
helpers::stack(block.launchContext(), inArrs, *output, dim);
|
|
|
|
return Status::OK();
|
|
}
|
|
|
|
DECLARE_TYPES(parallel_stack) {
|
|
getOpDescriptor()
|
|
->setAllowedInputTypes(sd::DataType::ANY)
|
|
->setAllowedOutputTypes({ALL_FLOATS});
|
|
}
|
|
|
|
DECLARE_SHAPE_FN(parallel_stack) {
|
|
|
|
auto inShapeInfo = inputShape->at(0);
|
|
int rank = inShapeInfo[0];
|
|
|
|
Nd4jLong* outShapeInfo = nullptr;
|
|
ALLOCATE(outShapeInfo, block.getWorkspace(), shape::shapeInfoLength(rank+1), Nd4jLong);
|
|
|
|
outShapeInfo[0] = rank + 1;
|
|
outShapeInfo[1] = block.width();
|
|
for(int i = 1; i <= rank; ++i)
|
|
outShapeInfo[i+1] = inShapeInfo[i];
|
|
|
|
ShapeUtils::updateStridesAndType(outShapeInfo, inShapeInfo, shape::order(inShapeInfo));
|
|
|
|
return SHAPELIST(CONSTANT(outShapeInfo));
|
|
}
|
|
|
|
|
|
}
|
|
}
|
|
|
|
#endif |