tool/mbed/mbed-sdk/libraries/dsp/cmsis_dsp/ComplexMathFunctions/arm_cmplx_mag_squared_f32.c

   1 /* ----------------------------------------------------------------------
   2 * Copyright (C) 2010-2013 ARM Limited. All rights reserved.
   3 *
   4 * $Date:        17. January 2013
   5 * $Revision:    V1.4.1
   6 *
   7 * Project:          CMSIS DSP Library
   8 * Title:                arm_cmplx_mag_squared_f32.c
   9 *
  10 * Description:  Floating-point complex magnitude squared.
  11 *
  12 * Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
  13 *
  14 * Redistribution and use in source and binary forms, with or without
  15 * modification, are permitted provided that the following conditions
  16 * are met:
  17 *   - Redistributions of source code must retain the above copyright
  18 *     notice, this list of conditions and the following disclaimer.
  19 *   - Redistributions in binary form must reproduce the above copyright
  20 *     notice, this list of conditions and the following disclaimer in
  21 *     the documentation and/or other materials provided with the
  22 *     distribution.
  23 *   - Neither the name of ARM LIMITED nor the names of its contributors
  24 *     may be used to endorse or promote products derived from this
  25 *     software without specific prior written permission.
  26 *
  27 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
  28 * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
  29 * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
  30 * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
  31 * COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
  32 * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
  33 * BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
  34 * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
  35 * CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
  36 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
  37 * ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
  38 * POSSIBILITY OF SUCH DAMAGE.
  39 * ---------------------------------------------------------------------------- */
  40 #include "arm_math.h"
  41
  42 /**
  43  * @ingroup groupCmplxMath
  44  */
  45
  46 /**
  47  * @defgroup cmplx_mag_squared Complex Magnitude Squared
  48  *
  49  * Computes the magnitude squared of the elements of a complex data vector.
  50  *
  51  * The <code>pSrc</code> points to the source data and
  52  * <code>pDst</code> points to the where the result should be written.
  53  * <code>numSamples</code> specifies the number of complex samples
  54  * in the input array and the data is stored in an interleaved fashion
  55  * (real, imag, real, imag, ...).
  56  * The input array has a total of <code>2*numSamples</code> values;
  57  * the output array has a total of <code>numSamples</code> values.
  58  *
  59  * The underlying algorithm is used:
  60  *
  61  * <pre>
  62  * for(n=0; n<numSamples; n++) {
  63  *     pDst[n] = pSrc[(2*n)+0]^2 + pSrc[(2*n)+1]^2;
  64  * }
  65  * </pre>
  66  *
  67  * There are separate functions for floating-point, Q15, and Q31 data types.
  68  */
  69
  70 /**
  71  * @addtogroup cmplx_mag_squared
  72  * @{
  73  */
  74
  75
  76 /**
  77  * @brief  Floating-point complex magnitude squared
  78  * @param[in]  *pSrc points to the complex input vector
  79  * @param[out]  *pDst points to the real output vector
  80  * @param[in]  numSamples number of complex samples in the input vector
  81  * @return none.
  82  */
  83
  84 void arm_cmplx_mag_squared_f32(
  85   float32_t * pSrc,
  86   float32_t * pDst,
  87   uint32_t numSamples)
  88 {
  89   float32_t real, imag;                          /* Temporary variables to store real and imaginary values */
  90   uint32_t blkCnt;                               /* loop counter */
  91
  92 #ifndef ARM_MATH_CM0_FAMILY
  93   float32_t real1, real2, real3, real4;          /* Temporary variables to hold real values */
  94   float32_t imag1, imag2, imag3, imag4;          /* Temporary variables to hold imaginary values */
  95   float32_t mul1, mul2, mul3, mul4;              /* Temporary variables */
  96   float32_t mul5, mul6, mul7, mul8;              /* Temporary variables */
  97   float32_t out1, out2, out3, out4;              /* Temporary variables to hold output values */
  98
  99   /*loop Unrolling */
 100   blkCnt = numSamples >> 2u;
 101
 102   /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.
 103    ** a second loop below computes the remaining 1 to 3 samples. */
 104   while(blkCnt > 0u)
 105   {
 106     /* C[0] = (A[0] * A[0] + A[1] * A[1]) */
 107     /* read real input sample from source buffer */
 108     real1 = pSrc[0];
 109     /* read imaginary input sample from source buffer */
 110     imag1 = pSrc[1];
 111
 112     /* calculate power of real value */
 113     mul1 = real1 * real1;
 114
 115     /* read real input sample from source buffer */
 116     real2 = pSrc[2];
 117
 118     /* calculate power of imaginary value */
 119     mul2 = imag1 * imag1;
 120
 121     /* read imaginary input sample from source buffer */
 122     imag2 = pSrc[3];
 123
 124     /* calculate power of real value */
 125     mul3 = real2 * real2;
 126
 127     /* read real input sample from source buffer */
 128     real3 = pSrc[4];
 129
 130     /* calculate power of imaginary value */
 131     mul4 = imag2 * imag2;
 132
 133     /* read imaginary input sample from source buffer */
 134     imag3 = pSrc[5];
 135
 136     /* calculate power of real value */
 137     mul5 = real3 * real3;
 138     /* calculate power of imaginary value */
 139     mul6 = imag3 * imag3;
 140
 141     /* read real input sample from source buffer */
 142     real4 = pSrc[6];
 143
 144     /* accumulate real and imaginary powers */
 145     out1 = mul1 + mul2;
 146
 147     /* read imaginary input sample from source buffer */
 148     imag4 = pSrc[7];
 149
 150     /* accumulate real and imaginary powers */
 151     out2 = mul3 + mul4;
 152
 153     /* calculate power of real value */
 154     mul7 = real4 * real4;
 155     /* calculate power of imaginary value */
 156     mul8 = imag4 * imag4;
 157
 158     /* store output to destination */
 159     pDst[0] = out1;
 160
 161     /* accumulate real and imaginary powers */
 162     out3 = mul5 + mul6;
 163
 164     /* store output to destination */
 165     pDst[1] = out2;
 166
 167     /* accumulate real and imaginary powers */
 168     out4 = mul7 + mul8;
 169
 170     /* store output to destination */
 171     pDst[2] = out3;
 172
 173     /* increment destination pointer by 8 to process next samples */
 174     pSrc += 8u;
 175
 176     /* store output to destination */
 177     pDst[3] = out4;
 178
 179     /* increment destination pointer by 4 to process next samples */
 180     pDst += 4u;
 181
 182     /* Decrement the loop counter */
 183     blkCnt--;
 184   }
 185
 186   /* If the numSamples is not a multiple of 4, compute any remaining output samples here.
 187    ** No loop unrolling is used. */
 188   blkCnt = numSamples % 0x4u;
 189
 190 #else
 191
 192   /* Run the below code for Cortex-M0 */
 193
 194   blkCnt = numSamples;
 195
 196 #endif /* #ifndef ARM_MATH_CM0_FAMILY */
 197
 198   while(blkCnt > 0u)
 199   {
 200     /* C[0] = (A[0] * A[0] + A[1] * A[1]) */
 201     real = *pSrc++;
 202     imag = *pSrc++;
 203
 204     /* out = (real * real) + (imag * imag) */
 205     /* store the result in the destination buffer. */
 206     *pDst++ = (real * real) + (imag * imag);
 207
 208     /* Decrement the loop counter */
 209     blkCnt--;
 210   }
 211 }
 212
 213 /**
 214  * @} end of cmplx_mag_squared group
 215  */