Book a Demo!
CoCalc Logo Icon
StoreFeaturesDocsShareSupportNewsAboutPoliciesSign UpSign In
Tetragramm
GitHub Repository: Tetragramm/opencv
 Path: blob/master/modules/imgproc/src/imgwarp.avx2.cpp
16339 views
1
/*M///////////////////////////////////////////////////////////////////////////////////////

2
//

3
//  IMPORTANT: READ BEFORE DOWNLOADING, COPYING, INSTALLING OR USING.

4
//

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.

8
//

9
//

10
//                           License Agreement

11
//                For Open Source Computer Vision Library

12
//

13
// Copyright (C) 2000-2008, Intel Corporation, all rights reserved.

14
// Copyright (C) 2009, Willow Garage Inc., all rights reserved.

15
// Copyright (C) 2014-2015, Itseez Inc., all rights reserved.

16
// Third party copyrights are property of their respective owners.

17
//

18
// Redistribution and use in source and binary forms, with or without modification,

19
// are permitted provided that the following conditions are met:

20
//

21
//   * Redistribution's of source code must retain the above copyright notice,

22
//     this list of conditions and the following disclaimer.

23
//

24
//   * Redistribution's in binary form must reproduce the above copyright notice,

25
//     this list of conditions and the following disclaimer in the documentation

26
//     and/or other materials provided with the distribution.

27
//

28
//   * The name of the copyright holders may not be used to endorse or promote products

29
//     derived from this software without specific prior written permission.

30
//

31
// This software is provided by the copyright holders and contributors "as is" and

32
// any express or implied warranties, including, but not limited to, the implied

33
// warranties of merchantability and fitness for a particular purpose are disclaimed.

34
// In no event shall the Intel Corporation or contributors be liable for any direct,

35
// indirect, incidental, special, exemplary, or consequential damages

36
// (including, but not limited to, procurement of substitute goods or services;

37
// loss of use, data, or profits; or business interruption) however caused

38
// and on any theory of liability, whether in contract, strict liability,

39
// or tort (including negligence or otherwise) arising in any way out of

40
// the use of this software, even if advised of the possibility of such damage.

41
//

42
//M*/

43


44
/* ////////////////////////////////////////////////////////////////////

45
//

46
//  Geometrical transforms on images and matrices: rotation, zoom etc.

47
//

48
// */

49


50
#include "precomp.hpp"

51
#include "imgwarp.hpp"

52


53
namespace cv

54
{

55
namespace opt_AVX2

56
{

57


58
int warpAffineBlockline(int *adelta, int *bdelta, short* xy, short* alpha, int X0, int Y0, int bw)

59
{

60
    const int AB_BITS = MAX(10, (int)INTER_BITS);

61
    int x1 = 0;

62
    __m256i fxy_mask = _mm256_set1_epi32(INTER_TAB_SIZE - 1);

63
    __m256i XX = _mm256_set1_epi32(X0), YY = _mm256_set1_epi32(Y0);

64
    for (; x1 <= bw - 16; x1 += 16)

65
    {

66
        __m256i tx0, tx1, ty0, ty1;

67
        tx0 = _mm256_add_epi32(_mm256_loadu_si256((const __m256i*)(adelta + x1)), XX);

68
        ty0 = _mm256_add_epi32(_mm256_loadu_si256((const __m256i*)(bdelta + x1)), YY);

69
        tx1 = _mm256_add_epi32(_mm256_loadu_si256((const __m256i*)(adelta + x1 + 8)), XX);

70
        ty1 = _mm256_add_epi32(_mm256_loadu_si256((const __m256i*)(bdelta + x1 + 8)), YY);

71


72
        tx0 = _mm256_srai_epi32(tx0, AB_BITS - INTER_BITS);

73
        ty0 = _mm256_srai_epi32(ty0, AB_BITS - INTER_BITS);

74
        tx1 = _mm256_srai_epi32(tx1, AB_BITS - INTER_BITS);

75
        ty1 = _mm256_srai_epi32(ty1, AB_BITS - INTER_BITS);

76


77
        __m256i fx_ = _mm256_packs_epi32(_mm256_and_si256(tx0, fxy_mask),

78
            _mm256_and_si256(tx1, fxy_mask));

79
        __m256i fy_ = _mm256_packs_epi32(_mm256_and_si256(ty0, fxy_mask),

80
            _mm256_and_si256(ty1, fxy_mask));

81
        tx0 = _mm256_packs_epi32(_mm256_srai_epi32(tx0, INTER_BITS),

82
            _mm256_srai_epi32(tx1, INTER_BITS));

83
        ty0 = _mm256_packs_epi32(_mm256_srai_epi32(ty0, INTER_BITS),

84
            _mm256_srai_epi32(ty1, INTER_BITS));

85
        fx_ = _mm256_adds_epi16(fx_, _mm256_slli_epi16(fy_, INTER_BITS));

86
        fx_ = _mm256_permute4x64_epi64(fx_, (3 << 6) + (1 << 4) + (2 << 2) + 0);

87


88
        _mm256_storeu_si256((__m256i*)(xy + x1 * 2), _mm256_unpacklo_epi16(tx0, ty0));

89
        _mm256_storeu_si256((__m256i*)(xy + x1 * 2 + 16), _mm256_unpackhi_epi16(tx0, ty0));

90
        _mm256_storeu_si256((__m256i*)(alpha + x1), fx_);

91
    }

92
    _mm256_zeroupper();

93
    return x1;

94
}

95


96
}

97
}

98
/* End of file. */

99


100