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_DEVICE_WARP_HPP__
44
#define __OPENCV_CUDA_DEVICE_WARP_HPP__
47
* @deprecated Use @ref cudev instead.
52
namespace cv { namespace cuda { namespace device
59
WARP_SIZE = 1 << LOG_WARP_SIZE,
63
/** \brief Returns the warp lane ID of the calling thread. */
64
static __device__ __forceinline__ unsigned int laneId()
67
asm("mov.u32 %0, %laneid;" : "=r"(ret) );
71
template<typename It, typename T>
72
static __device__ __forceinline__ void fill(It beg, It end, const T& value)
74
for(It t = beg + laneId(); t < end; t += STRIDE)
78
template<typename InIt, typename OutIt>
79
static __device__ __forceinline__ OutIt copy(InIt beg, InIt end, OutIt out)
81
for(InIt t = beg + laneId(); t < end; t += STRIDE, out += STRIDE)
86
template<typename InIt, typename OutIt, class UnOp>
87
static __device__ __forceinline__ OutIt transform(InIt beg, InIt end, OutIt out, UnOp op)
89
for(InIt t = beg + laneId(); t < end; t += STRIDE, out += STRIDE)
94
template<typename InIt1, typename InIt2, typename OutIt, class BinOp>
95
static __device__ __forceinline__ OutIt transform(InIt1 beg1, InIt1 end1, InIt2 beg2, OutIt out, BinOp op)
97
unsigned int lane = laneId();
99
InIt1 t1 = beg1 + lane;
100
InIt2 t2 = beg2 + lane;
101
for(; t1 < end1; t1 += STRIDE, t2 += STRIDE, out += STRIDE)
106
template <class T, class BinOp>
107
static __device__ __forceinline__ T reduce(volatile T *ptr, BinOp op)
109
const unsigned int lane = laneId();
113
T partial = ptr[lane];
115
ptr[lane] = partial = op(partial, ptr[lane + 16]);
116
ptr[lane] = partial = op(partial, ptr[lane + 8]);
117
ptr[lane] = partial = op(partial, ptr[lane + 4]);
118
ptr[lane] = partial = op(partial, ptr[lane + 2]);
119
ptr[lane] = partial = op(partial, ptr[lane + 1]);
125
template<typename OutIt, typename T>
126
static __device__ __forceinline__ void yota(OutIt beg, OutIt end, T value)
128
unsigned int lane = laneId();
131
for(OutIt t = beg + lane; t < end; t += STRIDE, value += STRIDE)
135
}}} // namespace cv { namespace cuda { namespace cudev
139
#endif /* __OPENCV_CUDA_DEVICE_WARP_HPP__ */