neon_utils.hpp

00001 /*M///////////////////////////////////////////////////////////////////////////////////////
00002 //
00003 //  IMPORTANT: READ BEFORE DOWNLOADING, COPYING, INSTALLING OR USING.
00004 //
00005 //  By downloading, copying, installing or using the software you agree to this license.
00006 //  If you do not agree to this license, do not download, install,
00007 //  copy or use the software.
00008 //
00009 //
00010 //                          License Agreement
00011 //                For Open Source Computer Vision Library
00012 //
00013 // Copyright (C) 2015, Itseez Inc., all rights reserved.
00014 // Third party copyrights are property of their respective owners.
00015 //
00016 // Redistribution and use in source and binary forms, with or without modification,
00017 // are permitted provided that the following conditions are met:
00018 //
00019 //   * Redistribution's of source code must retain the above copyright notice,
00020 //     this list of conditions and the following disclaimer.
00021 //
00022 //   * Redistribution's in binary form must reproduce the above copyright notice,
00023 //     this list of conditions and the following disclaimer in the documentation
00024 //     and/or other materials provided with the distribution.
00025 //
00026 //   * The name of the copyright holders may not be used to endorse or promote products
00027 //     derived from this software without specific prior written permission.
00028 //
00029 // This software is provided by the copyright holders and contributors "as is" and
00030 // any express or implied warranties, including, but not limited to, the implied
00031 // warranties of merchantability and fitness for a particular purpose are disclaimed.
00032 // In no event shall the Intel Corporation or contributors be liable for any direct,
00033 // indirect, incidental, special, exemplary, or consequential damages
00034 // (including, but not limited to, procurement of substitute goods or services;
00035 // loss of use, data, or profits; or business interruption) however caused
00036 // and on any theory of liability, whether in contract, strict liability,
00037 // or tort (including negligence or otherwise) arising in any way out of
00038 // the use of this software, even if advised of the possibility of such damage.
00039 //
00040 //M*/
00041 
00042 #ifndef __OPENCV_HAL_NEON_UTILS_HPP__
00043 #define __OPENCV_HAL_NEON_UTILS_HPP__
00044 
00045 #include "opencv2/core/cvdef.h"
00046 
00047 //! @addtogroup core_utils_neon
00048 //! @{
00049 
00050 #if CV_NEON
00051 
00052 inline int32x2_t cv_vrnd_s32_f32(float32x2_t v)
00053 {
00054     static int32x2_t v_sign = vdup_n_s32(1 << 31),
00055         v_05 = vreinterpret_s32_f32(vdup_n_f32(0.5f));
00056 
00057     int32x2_t v_addition = vorr_s32(v_05, vand_s32(v_sign, vreinterpret_s32_f32(v)));
00058     return vcvt_s32_f32(vadd_f32(v, vreinterpret_f32_s32(v_addition)));
00059 }
00060 
00061 inline int32x4_t cv_vrndq_s32_f32(float32x4_t v)
00062 {
00063     static int32x4_t v_sign = vdupq_n_s32(1 << 31),
00064         v_05 = vreinterpretq_s32_f32(vdupq_n_f32(0.5f));
00065 
00066     int32x4_t v_addition = vorrq_s32(v_05, vandq_s32(v_sign, vreinterpretq_s32_f32(v)));
00067     return vcvtq_s32_f32(vaddq_f32(v, vreinterpretq_f32_s32(v_addition)));
00068 }
00069 
00070 inline uint32x2_t cv_vrnd_u32_f32(float32x2_t v)
00071 {
00072     static float32x2_t v_05 = vdup_n_f32(0.5f);
00073     return vcvt_u32_f32(vadd_f32(v, v_05));
00074 }
00075 
00076 inline uint32x4_t cv_vrndq_u32_f32(float32x4_t v)
00077 {
00078     static float32x4_t v_05 = vdupq_n_f32(0.5f);
00079     return vcvtq_u32_f32(vaddq_f32(v, v_05));
00080 }
00081 
00082 inline float32x4_t cv_vrecpq_f32(float32x4_t val)
00083 {
00084     float32x4_t reciprocal = vrecpeq_f32(val);
00085     reciprocal = vmulq_f32(vrecpsq_f32(val, reciprocal), reciprocal);
00086     reciprocal = vmulq_f32(vrecpsq_f32(val, reciprocal), reciprocal);
00087     return reciprocal;
00088 }
00089 
00090 inline float32x2_t cv_vrecp_f32(float32x2_t val)
00091 {
00092     float32x2_t reciprocal = vrecpe_f32(val);
00093     reciprocal = vmul_f32(vrecps_f32(val, reciprocal), reciprocal);
00094     reciprocal = vmul_f32(vrecps_f32(val, reciprocal), reciprocal);
00095     return reciprocal;
00096 }
00097 
00098 inline float32x4_t cv_vrsqrtq_f32(float32x4_t val)
00099 {
00100     float32x4_t e = vrsqrteq_f32(val);
00101     e = vmulq_f32(vrsqrtsq_f32(vmulq_f32(e, e), val), e);
00102     e = vmulq_f32(vrsqrtsq_f32(vmulq_f32(e, e), val), e);
00103     return e;
00104 }
00105 
00106 inline float32x2_t cv_vrsqrt_f32(float32x2_t val)
00107 {
00108     float32x2_t e = vrsqrte_f32(val);
00109     e = vmul_f32(vrsqrts_f32(vmul_f32(e, e), val), e);
00110     e = vmul_f32(vrsqrts_f32(vmul_f32(e, e), val), e);
00111     return e;
00112 }
00113 
00114 inline float32x4_t cv_vsqrtq_f32(float32x4_t val)
00115 {
00116     return cv_vrecpq_f32(cv_vrsqrtq_f32(val));
00117 }
00118 
00119 inline float32x2_t cv_vsqrt_f32(float32x2_t val)
00120 {
00121     return cv_vrecp_f32(cv_vrsqrt_f32(val));
00122 }
00123 
00124 #endif
00125 
00126 //! @}
00127 
00128 #endif // __OPENCV_HAL_NEON_UTILS_HPP__
00129