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
57 lines
1.9 KiB
C++
57 lines
1.9 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 27.08.2018
|
|
//
|
|
|
|
|
|
#include <ops/declarable/helpers/range.h>
|
|
#include <execution/Threads.h>
|
|
|
|
namespace nd4j {
|
|
namespace ops {
|
|
namespace helpers {
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
// be careful: outVector must have c-order and ews = 1 !!!
|
|
template <typename T>
|
|
static void _range(const NDArray& start, const NDArray& delta, NDArray& outVector) {
|
|
|
|
const Nd4jLong len = outVector.lengthOf();
|
|
|
|
auto buff = reinterpret_cast<T *>(outVector.getBuffer());
|
|
auto s = start.e<T>(0);
|
|
auto d = delta.e<T>(0);
|
|
|
|
auto func = PRAGMA_THREADS_FOR {
|
|
for (auto i = start; i < stop; i += increment)
|
|
buff[i] = s + i * d;
|
|
};
|
|
samediff::Threads::parallel_for(func, 0, len);
|
|
}
|
|
|
|
void range(nd4j::LaunchContext * context, const NDArray& start, const NDArray& delta, NDArray& outVector) {
|
|
BUILD_SINGLE_SELECTOR(outVector.dataType(), _range, (start, delta, outVector), LIBND4J_TYPES);
|
|
}
|
|
|
|
BUILD_SINGLE_TEMPLATE(template void _range, (const NDArray& start, const NDArray& delta, NDArray& outVector), LIBND4J_TYPES);
|
|
|
|
|
|
}
|
|
}
|
|
} |