cavis/libnd4j/include/execution/LaunchContext.h

114 lines
3.4 KiB
C
Raw Normal View History

2019-06-06 14:21:15 +02:00
/*******************************************************************************
* 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 by raver119 on 30.11.17.
//
#ifndef LIBND4J_CUDACONTEXT_H
#define LIBND4J_CUDACONTEXT_H
#ifdef __CUDABLAS__
#include <cuda.h>
#include <cuda_runtime_api.h>
#include <cuda_runtime.h>
#include <cuda_device_runtime_api.h>
#endif
#include <dll.h>
#include <memory>
#include <op_boilerplate.h>
#include <memory/Workspace.h>
#include <vector>
namespace nd4j {
class ND4J_EXPORT LaunchContext {
private:
static std::vector<std::shared_ptr<LaunchContext>> _contexts;
#ifdef __CUDABLAS__
#ifndef __JAVACPP_HACK__
void* _reductionPointer;
void* _scalarPointer;
int* _allocationPointer;
cudaStream_t *_cudaStream = nullptr;
cudaStream_t *_cudaSpecialStream = nullptr;
void *_cublasHandle = nullptr;
#endif // JCPP
bool _isAllocated = false;
#endif // CUDA
nd4j::memory::Workspace* _workspace = nullptr;
int _deviceID = 0;
public:
#ifdef __CUDABLAS__
#ifndef __JAVACPP_HACK__
LaunchContext(cudaStream_t* cudaStream, cudaStream_t& specialCudaStream, void* reductionPointer = nullptr, void* scalarPointer = nullptr, int* allocationPointer = nullptr);
FORCEINLINE void* getReductionPointer () const {return _reductionPointer;};
FORCEINLINE void* getScalarPointer() const {return _scalarPointer;};
FORCEINLINE int* getAllocationPointer() const {return _allocationPointer;};
FORCEINLINE void* getCublasHandle() const {return _cublasHandle;};
FORCEINLINE cudaStream_t* getCudaStream() const {return _cudaStream;};
FORCEINLINE cudaStream_t* getCudaSpecialStream() const {return _cudaSpecialStream;};
FORCEINLINE void setReductionPointer (void* reductionPointer) {_reductionPointer = reductionPointer;};
FORCEINLINE void setScalarPointer(void* scalarPointer) {_scalarPointer = scalarPointer;};
FORCEINLINE void setAllocationPointer(int* allocationPointer) {_allocationPointer = allocationPointer;};
FORCEINLINE void setCudaStream(cudaStream_t* cudaStream) {_cudaStream = cudaStream;};
FORCEINLINE void setCudaSpecialStream(cudaStream_t* cudaStream) {_cudaSpecialStream = cudaStream;};
[WIP] more CUDA stuff (#57) * initial commit Signed-off-by: raver119 <raver119@gmail.com> * Added gradcheck test for dynamic_partition_bp op. * - implementation of dilation op (cpu and cuda) Signed-off-by: Yurii <yurii@skymind.io> * Fixed broadcast_dynamic_shape 1D case and tests. * Fixed usage of default integer arguments. * Fixed dynamic_partition_bp op and tests. * Eliminated test with grad check for dynamic_partition_bp op. * start working on cuda svd - porting available corresponding api from cuSOLVER library Signed-off-by: Yurii <yurii@skymind.io> * provide prelu_bp Signed-off-by: Yurii <yurii@skymind.io> * - provide gruCell_bp (old version ??) Signed-off-by: Yurii <yurii@skymind.io> * - polishing cumsum_bp and cumprod_bp tests Signed-off-by: Yurii <yurii@skymind.io> * provide sparseSoftmaxCrossEntropyWithLogits and sparseSoftmaxCrossEntropyWithLogits_grad Signed-off-by: Yurii <yurii@skymind.io> * Fixed atomicMul with float input/output * implementation of cuda kernel for triu_bp operation Signed-off-by: Yurii <yurii@skymind.io> * Refactored lup helper to add parrallel computing. * cusolver libraries Signed-off-by: raver119 <raver119@gmail.com> * uncomment cuSolver APIs in svd.cu Signed-off-by: Yurii <yurii@skymind.io> * cusolver var Signed-off-by: raver119 <raver119@gmail.com> * - further work on cuSolver svd Signed-off-by: Yurii <yurii@skymind.io> * Implement usage of cuda solver to LUP decomposition. * - correct naames in lup functions Signed-off-by: Yurii <yurii@skymind.io> * correct svdQR cuda Signed-off-by: Yurii <yurii@skymind.io> * - provide transpositions of input matrices in case of c order in svdCudaQR Signed-off-by: Yurii <yurii@skymind.io> * Fixed implementation issues with LUP usign cuda solver. * Implementation of matrix_determinant helper with cuda kernels. Working revision. * Implemented log_matrix_determinant helper with cuda kernels. * - implementation of batched cuda svd Signed-off-by: Yurii <yurii@skymind.io> * Refactored cholesky helper and implementation of cuda solver cholesky batch. * - implementation of cuda kernel for tile bp Signed-off-by: Yurii <yurii@skymind.io> * Implementation of cholesky and logdet with cuda kernels. * - implementation of cuda kernel for sru_bidirectional Signed-off-by: Yurii <yurii@skymind.io> * Fixed cholesky helper. * Cholesky op helper implementation. Working double-based cublas implementation. * bad import excluded Signed-off-by: raver119 <raver119@gmail.com> * Finished with cuda implementation of cholesky helper and tests. * - implementation of cuda kernel for sru_bidirectional_backprop operation Signed-off-by: Yurii <yurii@skymind.io> * Implementation of matrix_inverse op helper with cuda kernels. The first revision. * - start working on gruCell_bp Signed-off-by: Yurii <yurii@skymind.io> * Implementation of matrix_inverse helper. * - further work on new gruCell_bp Signed-off-by: Yurii <yurii@skymind.io> * cuBLAS related fixes Signed-off-by: raver119 <raver119@gmail.com> * calculateOutputShapes() now passes device buffers as well Signed-off-by: raver119 <raver119@gmail.com> * special concat/average/accumulate init host pointers now Signed-off-by: raver119 <raver119@gmail.com> * few more tweaks Signed-off-by: raver119 <raver119@gmail.com> * additional CudaDataBufferFactory signatures certain for data types Signed-off-by: raver119 <raver119@gmail.com> * cuSolver host buffer Signed-off-by: raver119 <raver119@gmail.com> * buffer to buffer memcpy host ptr allocation Signed-off-by: raver119 <raver119@gmail.com>
2019-07-12 10:51:51 +02:00
FORCEINLINE void setCublasHandle(void *handle) {_cublasHandle = handle; };
2019-06-06 14:21:15 +02:00
#endif // JCPP
#endif // CUDA
LaunchContext(Nd4jPointer cudaStream, Nd4jPointer reductionPointer = nullptr, Nd4jPointer scalarPointer = nullptr, Nd4jPointer allocationPointer = nullptr);
LaunchContext();
~LaunchContext();
nd4j::memory::Workspace* getWorkspace() const { return _workspace; }
void setWorkspace(nd4j::memory::Workspace* theWorkspace) {
_workspace = theWorkspace;
}
int getDeviceID() const {return _deviceID;}
void setDeviceID(int deviceID) { _deviceID = deviceID; }
static LaunchContext* defaultContext();
};
}
#endif //LIBND4J_CUDACONTEXT_H