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
61 lines
2.1 KiB
C++
61 lines
2.1 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 raver119@gmail.com
|
|
//
|
|
|
|
#include <op_boilerplate.h>
|
|
#include <Loops.h>
|
|
#include <types/types.h>
|
|
#include <loops/transform_strict.h>
|
|
#include <loops/legacy_ops.h>
|
|
|
|
using namespace simdOps;
|
|
|
|
namespace functions {
|
|
namespace transform {
|
|
|
|
template <typename X>
|
|
void TransformStrict<X>::exec(
|
|
int opNum,
|
|
void *x,
|
|
Nd4jLong *xShapeInfo,
|
|
void *z,
|
|
Nd4jLong *zShapeInfo,
|
|
void *extraParams, uint64_t threadId, uint64_t numThreads) {
|
|
DISPATCH_BY_OPNUM_T(exec, PARAMS(x, xShapeInfo, z, zShapeInfo, extraParams, threadId, numThreads), TRANSFORM_STRICT_OPS);
|
|
}
|
|
|
|
template <typename X>
|
|
template<typename OpType>
|
|
void _CUDA_H TransformStrict<X>::exec(
|
|
void *vx,
|
|
Nd4jLong *xShapeInfo,
|
|
void *vz,
|
|
Nd4jLong *zShapeInfo,
|
|
void *vextraParams, uint64_t threadId, uint64_t numThreads) {
|
|
|
|
auto x = reinterpret_cast<X *>(vx);
|
|
auto z = reinterpret_cast<X *>(vz);
|
|
auto extraParams = reinterpret_cast<X *>(vextraParams);
|
|
|
|
nd4j::TransformLoops<X,X,X>::template loopTransform<OpType>(x, xShapeInfo, z, zShapeInfo, extraParams, threadId, numThreads);
|
|
}
|
|
|
|
BUILD_SINGLE_TEMPLATE(template class ND4J_EXPORT TransformStrict, , FLOAT_TYPES);
|
|
}
|
|
} |