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
60 lines
1.8 KiB
C++
60 lines
1.8 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 GS (sgazeos@gmail.com), created on 10/1/2018
|
|
//
|
|
|
|
|
|
#include<ops/declarable/helpers/cross.h>
|
|
#include <helpers/ShapeUtils.h>
|
|
#include <ops/declarable/CustomOperations.h>
|
|
|
|
namespace nd4j {
|
|
namespace ops {
|
|
namespace helpers {
|
|
|
|
void crossBatched(nd4j::LaunchContext * context, NDArray *a, NDArray *b, NDArray *o) {
|
|
auto _a = a->reshape(a->ordering(), {-1, 3});
|
|
auto _b = b->reshape(b->ordering(), {-1, 3});
|
|
auto _o = o->reshape(o->ordering(), {-1, 3});
|
|
|
|
auto tadsA = _a.allTensorsAlongDimension({1});
|
|
auto tadsB = _b.allTensorsAlongDimension({1});
|
|
auto tadsO = _o.allTensorsAlongDimension({1});
|
|
|
|
int tads = tadsA->size();
|
|
|
|
auto func = PRAGMA_THREADS_FOR {
|
|
for (auto e = start; e < stop; e += increment) {
|
|
auto a_ = tadsA->at(e);
|
|
auto b_ = tadsB->at(e);
|
|
auto o_ = tadsO->at(e);
|
|
|
|
helpers::cross(context, a_, b_, o_);
|
|
}
|
|
};
|
|
|
|
samediff::Threads::parallel_tad(func, 0, tads);
|
|
|
|
delete tadsA;
|
|
delete tadsB;
|
|
delete tadsO;
|
|
}
|
|
|
|
}
|
|
}
|
|
} |