cavis/libnd4j/include/helpers/impl/CudaLaunchHelper.cpp

44 lines
1.5 KiB
C++
Raw Normal View History

2021-02-01 13:31:45 +01:00
/* ******************************************************************************
*
2019-06-06 14:21:15 +02:00
*
* 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.
*
2021-02-01 13:31:45 +01:00
* See the NOTICE file distributed with this work for additional
* information regarding copyright ownership.
2019-06-06 14:21:15 +02:00
* 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
******************************************************************************/
//
// Created by raver on 4/5/2018.
//
#include <helpers/CudaLaunchHelper.h>
#include <math/templatemath.h>
2019-06-06 14:21:15 +02:00
namespace sd {
2019-06-06 14:21:15 +02:00
Triple CudaLaunchHelper::getFlatLaunchParams(Nd4jLong length, int SM, int CORES, int SHARED_MEMORY) {
// TODO: to be implemented
Triple triple(1, 2, 3);
return triple;
}
int CudaLaunchHelper::getReductionBlocks(Nd4jLong xLength, int blockSize) {
int div = xLength / blockSize;
int can = sd::math::nd4j_max<int>(div, 1);
2019-06-06 14:21:15 +02:00
if (xLength % blockSize != 0 && xLength > blockSize)
can++;
// not more then 512 blocks
return sd::math::nd4j_min<int>(can, 512);
2019-06-06 14:21:15 +02:00
}
}