/usr/include/ITK-4.5/itkGPUReduction.h is in libinsighttoolkit4-dev 4.5.0-3.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 | /*=========================================================================
*
* Copyright Insight Software Consortium
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0.txt
*
* 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.
*
*=========================================================================*/
#ifndef __itkGPUReduction_h
#define __itkGPUReduction_h
#include "itkObject.h"
#include "itkGPUDataManager.h"
#include "itkGPUKernelManager.h"
#include "itkOpenCLUtil.h"
namespace itk
{
/** Create a helper GPU Kernel class for GPUReduction */
itkGPUKernelClassMacro(GPUReductionKernel);
/**
* \class GPUReduction
*
* This class encapsulate the parallel reduction algorithm. An example
* of this algorithm is to compute the sum of a long array in parallel.
*
* \ingroup ITKGPUCommon
*/
template< typename TElement >
class GPUReduction :
public Object
{
public:
/** Standard class typedefs. */
typedef GPUReduction Self;
typedef Object Superclass;
typedef SmartPointer< Self > Pointer;
typedef SmartPointer< const Self > ConstPointer;
/** Method for creation through the object factory. */
itkNewMacro(Self);
/** Run-time type information (and related methods). */
itkTypeMacro(GPUReduction,
Object);
typedef GPUDataManager::Pointer GPUDataPointer;
itkGetMacro(GPUDataManager, GPUDataPointer);
itkGetMacro(GPUResult, TElement);
itkGetMacro(CPUResult, TElement);
/** Get OpenCL Kernel source as a string, creates a GetOpenCLSource method */
itkGetOpenCLSourceFromKernelMacro(GPUReductionKernel);
unsigned int NextPow2( unsigned int x );
bool isPow2(unsigned int x);
void GetNumBlocksAndThreads(int whichKernel, int n, int maxBlocks, int maxThreads, int &blocks, int &threads);
unsigned int GetReductionKernel(int whichKernel, int blockSize, int isPowOf2);
void AllocateGPUInputBuffer(TElement *h_idata = NULL);
void ReleaseGPUInputBuffer();
void InitializeKernel(unsigned int size);
TElement RandomTest();
TElement GPUGenerateData();
TElement CPUGenerateData(TElement *data, int size);
TElement GPUReduce( cl_int n,
int numThreads,
int numBlocks,
int maxThreads,
int maxBlocks,
int whichKernel,
bool cpuFinalReduction,
int cpuFinalThreshold,
double* dTotalTime,
GPUDataPointer idata,
GPUDataPointer odata);
protected:
GPUReduction();
~GPUReduction();
void PrintSelf(std::ostream & os, Indent indent) const;
/** GPU kernel manager for GPUFiniteDifferenceFunction class */
GPUKernelManager::Pointer m_GPUKernelManager;
GPUDataPointer m_GPUDataManager;
/* GPU kernel handle for GPUComputeUpdate */
int m_ReduceGPUKernelHandle;
int m_TestGPUKernelHandle;
unsigned int m_Size;
bool m_SmallBlock;
TElement m_GPUResult, m_CPUResult;
private:
GPUReduction(const Self &); //purposely not implemented
void operator=(const Self &); //purposely not implemented
};
} // end namespace itk
#ifndef ITK_MANUAL_INSTANTIATION
#include "itkGPUReduction.hxx"
#endif
#endif
|