Skip to content

Commit 5448d91

Browse files
committed
AVX and SSE4.1 optimized conversion implementations migrated to separate files
1 parent 20f603a commit 5448d91

File tree

4 files changed

+386
-211
lines changed

4 files changed

+386
-211
lines changed

modules/core/src/convert.avx2.cpp

Lines changed: 78 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,78 @@
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) 2009-2011, 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+
#include "precomp.hpp"
45+
#include "convert.hpp"
46+
47+
namespace cv
48+
{
49+
namespace opt_AVX2
50+
{
51+
52+
void cvtScale_s16s32f32Line_AVX2(const short* src, int* dst, float scale, float shift, int width)
53+
{
54+
int x = 0;
55+
56+
__m256 scale256 = _mm256_set1_ps(scale);
57+
__m256 shift256 = _mm256_set1_ps(shift);
58+
const int shuffle = 0xD8;
59+
60+
for (; x <= width - 16; x += 16)
61+
{
62+
__m256i v_src = _mm256_loadu_si256((const __m256i *)(src + x));
63+
v_src = _mm256_permute4x64_epi64(v_src, shuffle);
64+
__m256i v_src_lo = _mm256_srai_epi32(_mm256_unpacklo_epi16(v_src, v_src), 16);
65+
__m256i v_src_hi = _mm256_srai_epi32(_mm256_unpackhi_epi16(v_src, v_src), 16);
66+
__m256 v_dst0 = _mm256_add_ps(_mm256_mul_ps(_mm256_cvtepi32_ps(v_src_lo), scale256), shift256);
67+
__m256 v_dst1 = _mm256_add_ps(_mm256_mul_ps(_mm256_cvtepi32_ps(v_src_hi), scale256), shift256);
68+
_mm256_storeu_si256((__m256i *)(dst + x), _mm256_cvtps_epi32(v_dst0));
69+
_mm256_storeu_si256((__m256i *)(dst + x + 8), _mm256_cvtps_epi32(v_dst1));
70+
}
71+
72+
for (; x < width; x++)
73+
dst[x] = saturate_cast<int>(src[x] * scale + shift);
74+
}
75+
76+
}
77+
}
78+
/* End of file. */

0 commit comments

Comments
 (0)