029b84e2b7
* RL4J: Add generic update rule (#502) Signed-off-by: Alexandre Boulanger <aboulang2002@yahoo.com> * Shyrma reduce (#481) * - start working on improving of cpu legacy code for reduce ops Signed-off-by: Yurii <iuriish@yahoo.com> * - further work on improving legacy loops Signed-off-by: Yurii <iuriish@yahoo.com> * - still working on improving reduce ops Signed-off-by: Yurii <iuriish@yahoo.com> * - further work on improving reduce ops Signed-off-by: Yurii <iuriish@yahoo.com> * - testing speed run of new reduce op Signed-off-by: Yurii <iuriish@yahoo.com> * - working on improvement of default loop for reduce op Signed-off-by: Yurii <iuriish@yahoo.com> * - update signatures of stuff which calls reduce ops Signed-off-by: Yurii <iuriish@yahoo.com> * - make corrections in cuda reduce kernels Signed-off-by: Yurii <iuriish@yahoo.com> * - change loop for default case in broadcast legacy ops Signed-off-by: Yurii <iuriish@yahoo.com> * - comment some shape stuff Signed-off-by: Yurii <iuriish@yahoo.com> * - comment unnecessary prints in RNGtests Signed-off-by: Yurii <iuriish@yahoo.com> * - finish to resolve conflicts after master has been merged Signed-off-by: Yurii <iuriish@yahoo.com> * - get rid of some compilation mistakes of cuda stuff Signed-off-by: Yurii <iuriish@yahoo.com> * - minor changes Signed-off-by: Yurii <iuriish@yahoo.com> * - further search for bug causing crash on java test Signed-off-by: Yurii <iuriish@yahoo.com> * - add scalar case in reduce_ ... exec stuff Signed-off-by: Yurii <iuriish@yahoo.com> * - minor corrections in NAtiveOps.cu Signed-off-by: Yurii <iuriish@yahoo.com> * - add switch to scalar case execReduceXD functions Signed-off-by: Yurii <iuriish@yahoo.com> * - add support for vectors old shape in ConstantShapeHelper::createShapeInfoWithNoUnitiesForReduce Signed-off-by: Yurii <iuriish@yahoo.com> * - correct cuda mirrorPad Signed-off-by: Yurii <iuriish@yahoo.com> * - add support for vectors old shape in cuda createShapeInfoWithNoUnitiesForReduce Signed-off-by: Yurii <iuriish@yahoo.com> Co-authored-by: raver119 <raver119@gmail.com> * Add support for CUDA 11.0 (#492) * Add support for CUDA 11.0 * libnd4j tweaks for CUDA 11 Signed-off-by: raver119@gmail.com <raver119@gmail.com> * bindings update, again? Signed-off-by: raver119@gmail.com <raver119@gmail.com> * * Update versions of JavaCPP Presets for FFmpeg, OpenBLAS, and NumPy * update API to match CUDA 8 Signed-off-by: raver119@gmail.com <raver119@gmail.com> * * Update version of JavaCPP Presets for CPython * C++ updated for cuDNN 8.0 Signed-off-by: raver119@gmail.com <raver119@gmail.com> * one more test Signed-off-by: raver119@gmail.com <raver119@gmail.com> * one more test Signed-off-by: raver119@gmail.com <raver119@gmail.com> * one more test Signed-off-by: raver119@gmail.com <raver119@gmail.com> * 128-bit alignment for workspaces Signed-off-by: raver119@gmail.com <raver119@gmail.com> * change seed in 1 test Signed-off-by: raver119@gmail.com <raver119@gmail.com> * Fix dependecy duplication in python4j-parent pom * Fix group id for in python4j-numpy * few tests tweaked Signed-off-by: raver119@gmail.com <raver119@gmail.com> * Remove macosx-x86_64-gpu from nd4j-tests-tensorflow * few minor tweaks for IndexReduce Signed-off-by: raver119@gmail.com <raver119@gmail.com> * one test removed Signed-off-by: raver119@gmail.com <raver119@gmail.com> Co-authored-by: raver119@gmail.com <raver119@gmail.com> Co-authored-by: Serhii Shepel <9946053+sshepel@users.noreply.github.com> * RL4J: Add SyncTrainer and AgentLearnerBuilder for a few algorithms (#504) Signed-off-by: Alexandre Boulanger <aboulang2002@yahoo.com> Co-authored-by: Alexandre Boulanger <44292157+aboulang2002@users.noreply.github.com> Co-authored-by: Yurii Shyrma <iuriish@yahoo.com> Co-authored-by: raver119 <raver119@gmail.com> Co-authored-by: Serhii Shepel <9946053+sshepel@users.noreply.github.com>
129 lines
5.3 KiB
C++
Executable File
129 lines
5.3 KiB
C++
Executable File
/*******************************************************************************
|
|
* 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
|
|
******************************************************************************/
|
|
|
|
/*
|
|
*
|
|
* Created on: Dec 28, 2015
|
|
* Author: agibsonccc
|
|
*/
|
|
|
|
#ifndef INDEXREDUCE_H_
|
|
#define INDEXREDUCE_H_
|
|
#include <helpers/shape.h>
|
|
#ifdef _OPENMP
|
|
#include <omp.h>
|
|
#endif
|
|
#include <system/dll.h>
|
|
#include <ops/ops.h>
|
|
#include <system/op_boilerplate.h>
|
|
#include <helpers/OmpLaunchHelper.h>
|
|
#include <helpers/DebugHelper.h>
|
|
|
|
#ifdef __CUDACC__
|
|
#include <cuda.h>
|
|
#include <cuda_runtime.h>
|
|
#endif
|
|
|
|
|
|
#include <helpers/TAD.h>
|
|
|
|
|
|
#include "system/pairwise_util.h"
|
|
|
|
#include "legacy_ops.h"
|
|
|
|
namespace functions {
|
|
namespace indexreduce {
|
|
|
|
template<typename X, typename Z>
|
|
class IndexReduce {
|
|
public:
|
|
#ifdef __CUDABLAS__
|
|
|
|
static __device__ void transform(int opNum,
|
|
const void *x, const Nd4jLong *xShapeInfo,
|
|
void *extraParams,
|
|
void *result, const Nd4jLong *resultShapeInfo,
|
|
int *dimension,int dimensionLength,
|
|
int postProcessOrNot,
|
|
int *allocationBuffer, void *reductionBuffer,
|
|
const Nd4jLong *tadShapeInfo, const Nd4jLong *tadOffset);
|
|
|
|
template<typename OpType>
|
|
static __device__ void aggregatePartials(IndexValue<X> *sPartialsRef, Nd4jLong tid, Nd4jLong numElements, void *extraParams);
|
|
|
|
|
|
template<typename OpType>
|
|
static __device__ void transform(const void *dx, const Nd4jLong *xShapeInfo,
|
|
void *extraParams,
|
|
void *result, const Nd4jLong *resultShapeInfo,
|
|
int *dimension, int dimensionLength,
|
|
int postProcessOrNot,
|
|
int *allocationBuffer, void *reductionBuffer,
|
|
const Nd4jLong *tadOnlyShapeInfo, const Nd4jLong *tadOffsets);
|
|
|
|
|
|
static _CUDA_H void executeIndexReduceScalar(dim3 launchDims, cudaStream_t *stream,
|
|
int op,
|
|
const void *dx, const Nd4jLong *xShapeInfo,
|
|
int xRank,
|
|
void *extraParams,
|
|
void *result, const Nd4jLong *resultShapeInfo,
|
|
int zRank,
|
|
int *dimension, int dimensionLength,
|
|
int postProcessOrNot,
|
|
int *allocationBuffer, void *reductionBuffer,
|
|
const Nd4jLong *tadOnlyShapeInfo, const Nd4jLong *tadOffsets);
|
|
|
|
static _CUDA_H void executeIndexReduce(dim3 launchDims, cudaStream_t *stream,
|
|
int op,
|
|
const void *dx, const Nd4jLong *xShapeInfo,
|
|
int xRank,
|
|
void *extraParams,
|
|
void *result, const Nd4jLong *resultShapeInfo,
|
|
int zRank,
|
|
int *dimension, int dimensionLength,
|
|
int postProcessOrNot,
|
|
int *allocationBuffer, void *reductionBuffer,
|
|
const Nd4jLong *tadOnlyShapeInfo, const Nd4jLong *tadOffsets);
|
|
#else
|
|
|
|
static Nd4jLong execScalar(int opNum, const void *x, const Nd4jLong *xShapeInfo, void *extraParams);
|
|
|
|
static void exec(int opNum,
|
|
const void *x, const Nd4jLong *xShapeInfo,
|
|
void *extraParams,
|
|
void *result, const Nd4jLong *resultShapeInfoBuffer,
|
|
int *dimension, int dimensionLength,
|
|
const Nd4jLong *tadShapeInfo, const Nd4jLong *tadOffset);
|
|
|
|
template<typename OpType>
|
|
static _CUDA_H Nd4jLong execScalar(const void *x, const Nd4jLong *xShapeInfo, void *extraParams);
|
|
|
|
template<typename OpType>
|
|
static _CUDA_H void exec(const void *x, const Nd4jLong *xShapeInfo,
|
|
void *extraParams,
|
|
void *result, const Nd4jLong *resultShapeInfoBuffer,
|
|
int *dimension, int dimensionLength,
|
|
const Nd4jLong *tadShapeInfo, const Nd4jLong *tadOffset);
|
|
#endif
|
|
};
|
|
}
|
|
}
|
|
|
|
#endif /* INDEXREDUCE_H_ */
|
|
|