1
/*M///////////////////////////////////////////////////////////////////////////////////////
3
// IMPORTANT: READ BEFORE DOWNLOADING, COPYING, INSTALLING OR USING.
5
// By downloading, copying, installing or using the software you agree to this license.
6
// If you do not agree to this license, do not download, install,
7
// copy or use the software.
11
// For Open Source Computer Vision Library
13
// Copyright (C) 2000-2008, Intel Corporation, all rights reserved.
14
// Copyright (C) 2009, Willow Garage Inc., all rights reserved.
15
// Third party copyrights are property of their respective owners.
17
// Redistribution and use in source and binary forms, with or without modification,
18
// are permitted provided that the following conditions are met:
20
// * Redistribution's of source code must retain the above copyright notice,
21
// this list of conditions and the following disclaimer.
23
// * Redistribution's in binary form must reproduce the above copyright notice,
24
// this list of conditions and the following disclaimer in the documentation
25
// and/or other materials provided with the distribution.
27
// * The name of the copyright holders may not be used to endorse or promote products
28
// derived from this software without specific prior written permission.
30
// This software is provided by the copyright holders and contributors "as is" and
31
// any express or implied warranties, including, but not limited to, the implied
32
// warranties of merchantability and fitness for a particular purpose are disclaimed.
33
// In no event shall the Intel Corporation or contributors be liable for any direct,
34
// indirect, incidental, special, exemplary, or consequential damages
35
// (including, but not limited to, procurement of substitute goods or services;
36
// loss of use, data, or profits; or business interruption) however caused
37
// and on any theory of liability, whether in contract, strict liability,
38
// or tort (including negligence or otherwise) arising in any way out of
39
// the use of this software, even if advised of the possibility of such damage.
43
#ifndef __OPENCV_CUDA_VEC_DISTANCE_DETAIL_HPP__
44
#define __OPENCV_CUDA_VEC_DISTANCE_DETAIL_HPP__
46
#include "../datamov_utils.hpp"
50
namespace cv { namespace cuda { namespace device
52
namespace vec_distance_detail
54
template <int THREAD_DIM, int N> struct UnrollVecDiffCached
56
template <typename Dist, typename T1, typename T2>
57
static __device__ void calcCheck(const T1* vecCached, const T2* vecGlob, int len, Dist& dist, int ind)
61
T1 val1 = *vecCached++;
64
ForceGlob<T2>::Load(vecGlob, ind, val2);
66
dist.reduceIter(val1, val2);
68
UnrollVecDiffCached<THREAD_DIM, N - 1>::calcCheck(vecCached, vecGlob, len, dist, ind + THREAD_DIM);
72
template <typename Dist, typename T1, typename T2>
73
static __device__ void calcWithoutCheck(const T1* vecCached, const T2* vecGlob, Dist& dist)
75
T1 val1 = *vecCached++;
78
ForceGlob<T2>::Load(vecGlob, 0, val2);
79
vecGlob += THREAD_DIM;
81
dist.reduceIter(val1, val2);
83
UnrollVecDiffCached<THREAD_DIM, N - 1>::calcWithoutCheck(vecCached, vecGlob, dist);
86
template <int THREAD_DIM> struct UnrollVecDiffCached<THREAD_DIM, 0>
88
template <typename Dist, typename T1, typename T2>
89
static __device__ __forceinline__ void calcCheck(const T1*, const T2*, int, Dist&, int)
93
template <typename Dist, typename T1, typename T2>
94
static __device__ __forceinline__ void calcWithoutCheck(const T1*, const T2*, Dist&)
99
template <int THREAD_DIM, int MAX_LEN, bool LEN_EQ_MAX_LEN> struct VecDiffCachedCalculator;
100
template <int THREAD_DIM, int MAX_LEN> struct VecDiffCachedCalculator<THREAD_DIM, MAX_LEN, false>
102
template <typename Dist, typename T1, typename T2>
103
static __device__ __forceinline__ void calc(const T1* vecCached, const T2* vecGlob, int len, Dist& dist, int tid)
105
UnrollVecDiffCached<THREAD_DIM, MAX_LEN / THREAD_DIM>::calcCheck(vecCached, vecGlob, len, dist, tid);
108
template <int THREAD_DIM, int MAX_LEN> struct VecDiffCachedCalculator<THREAD_DIM, MAX_LEN, true>
110
template <typename Dist, typename T1, typename T2>
111
static __device__ __forceinline__ void calc(const T1* vecCached, const T2* vecGlob, int len, Dist& dist, int tid)
113
UnrollVecDiffCached<THREAD_DIM, MAX_LEN / THREAD_DIM>::calcWithoutCheck(vecCached, vecGlob + tid, dist);
116
} // namespace vec_distance_detail
117
}}} // namespace cv { namespace cuda { namespace cudev
121
#endif // __OPENCV_CUDA_VEC_DISTANCE_DETAIL_HPP__