65 lines
2.9 KiB
Plaintext
65 lines
2.9 KiB
Plaintext
/* ******************************************************************************
|
|
*
|
|
*
|
|
* 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.
|
|
*
|
|
* See the NOTICE file distributed with this work for additional
|
|
* information regarding copyright ownership.
|
|
* 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
|
|
//
|
|
//
|
|
#ifndef LIBND4J_GRID_H
|
|
#define LIBND4J_GRID_H
|
|
|
|
#include <ops/ops.h>
|
|
#include <types/float16.h>
|
|
#include <cuda.h>
|
|
#include <cuda_runtime_api.h>
|
|
#include <cuda_runtime.h>
|
|
#include <cuda_device_runtime_api.h>
|
|
|
|
namespace functions {
|
|
namespace grid {
|
|
template <typename T>
|
|
class GRIDShaped {
|
|
public:
|
|
static void execMetaPredicateShaped(cudaStream_t * stream,
|
|
Nd4jPointer *extras,
|
|
const int opTypeA,
|
|
const int opNumA,
|
|
const int opTypeB,
|
|
const int opNumB,
|
|
Nd4jLong N,
|
|
void *dx,
|
|
Nd4jLong *xShapeInfo,
|
|
void *dy,
|
|
Nd4jLong *yShapeInfo,
|
|
void *dz,
|
|
Nd4jLong *zShapeInfo,
|
|
void *extraA,
|
|
void *extraB,
|
|
double scalarA,
|
|
double scalarB);
|
|
|
|
template<typename OpType>
|
|
static __device__ void transformCuda(void *dx, Nd4jLong *xShapeBuffer, void *y, Nd4jLong *yShapeBuffer, void *result, Nd4jLong *resultShapeBuffer, void *extraParams, int *allocationPointer, UnifiedSharedMemory *manager, Nd4jLong *tadOnlyShapeInfo);
|
|
|
|
static __device__ void transformCuda(int opTypeA, int opNumA, int opTypeB, int opNumB, void *dx, Nd4jLong *xShapeBuffer, void *y, Nd4jLong *yShapeBuffer, void *result, Nd4jLong *resultShapeBuffer, void *extraParams, int *allocationPointer, UnifiedSharedMemory *manager, Nd4jLong *tadOnlyShapeInfo);
|
|
};
|
|
}
|
|
}
|
|
|
|
#endif //LIBND4J_GRID_H
|