25b3cd9b80
* one more CI test Signed-off-by: raver119 <raver119@gmail.com> * export additional symbols Signed-off-by: raver119 <raver119@gmail.com> * few more tweaks Signed-off-by: raver119 <raver119@gmail.com> * one more tweak for linux Signed-off-by: raver119 <raver119@gmail.com> * fix dtype in few tests Signed-off-by: raver119 <raver119@gmail.com> * missing sync and memset in couple of tests Signed-off-by: raver119 <raver119@gmail.com> * copy step for libnd4j cuda Signed-off-by: raver119 <raver119@gmail.com> * no-op on empty for adjust hue/contrast/saturation Signed-off-by: raver119 <raver119@gmail.com> * CUDA_VERBOSE Off Signed-off-by: raver119 <raver119@gmail.com> * BroadcastBool fix + few tests Signed-off-by: raver119 <raver119@gmail.com> * trigger jenkins Signed-off-by: raver119 <raver119@gmail.com> * trigger jenkins Signed-off-by: raver119 <raver119@gmail.com> * - ignore couple of warnings - remove redundant compiler options Signed-off-by: raver119 <raver119@gmail.com>
71 lines
2.2 KiB
C++
71 lines
2.2 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, created on 6/30/2018
|
|
// @author Yurii Shyrma (iuriish@yahoo.com)
|
|
//
|
|
|
|
#ifndef LIBND4J_OMPLAUNCHHELPER_H
|
|
#define LIBND4J_OMPLAUNCHHELPER_H
|
|
|
|
#include <vector>
|
|
#include <pointercast.h>
|
|
#include <op_boilerplate.h>
|
|
|
|
namespace nd4j {
|
|
|
|
class ND4J_EXPORT OmpLaunchHelper {
|
|
|
|
public:
|
|
|
|
OmpLaunchHelper() = delete;
|
|
|
|
OmpLaunchHelper(const Nd4jLong N, float desiredNumThreads = -1);
|
|
|
|
FORCEINLINE Nd4jLong getThreadOffset(const int threadNum);
|
|
FORCEINLINE Nd4jLong getItersPerThread(const int threadNum);
|
|
|
|
static Nd4jLong betterSpan(Nd4jLong N);
|
|
static Nd4jLong betterSpan(Nd4jLong N, Nd4jLong numThreads);
|
|
|
|
static int betterThreads(Nd4jLong N);
|
|
static int betterThreads(Nd4jLong N, int maxThreads);
|
|
|
|
static int tadThreads(Nd4jLong tadLength, Nd4jLong numTads);
|
|
|
|
int _numThreads;
|
|
unsigned int _itersPerThread;
|
|
unsigned int _remainder;
|
|
};
|
|
|
|
////////////////////////////////////////////////////////////////////////////////
|
|
FORCEINLINE Nd4jLong OmpLaunchHelper::getThreadOffset(const int threadNum) {
|
|
|
|
return threadNum * _itersPerThread;
|
|
}
|
|
|
|
////////////////////////////////////////////////////////////////////////////////
|
|
FORCEINLINE Nd4jLong OmpLaunchHelper::getItersPerThread(const int threadNum) {
|
|
|
|
return (threadNum == _numThreads - 1) ? _itersPerThread + _remainder : _itersPerThread; // last thread may contain bigger number of iterations
|
|
}
|
|
|
|
}
|
|
|
|
|
|
#endif //LIBND4J_OMPLAUNCHHELPER_H
|