tool/mbed/mbed-sdk/libraries/dsp/cmsis_dsp/ComplexMathFunctions/arm_cmplx_dot_prod_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_dot_prod_f32.c
   9 *
  10 * Description:  Floating-point complex dot product
  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
  41 #include "arm_math.h"
  42
  43 /**
  44  * @ingroup groupCmplxMath
  45  */
  46
  47 /**
  48  * @defgroup cmplx_dot_prod Complex Dot Product
  49  *
  50  * Computes the dot product of two complex vectors.
  51  * The vectors are multiplied element-by-element and then summed.
  52  *
  53  * The <code>pSrcA</code> points to the first complex input vector and
  54  * <code>pSrcB</code> points to the second complex input vector.
  55  * <code>numSamples</code> specifies the number of complex samples
  56  * and the data in each array is stored in an interleaved fashion
  57  * (real, imag, real, imag, ...).
  58  * Each array has a total of <code>2*numSamples</code> values.
  59  *
  60  * The underlying algorithm is used:
  61  * <pre>
  62  * realResult=0;
  63  * imagResult=0;
  64  * for(n=0; n<numSamples; n++) {
  65  *     realResult += pSrcA[(2*n)+0]*pSrcB[(2*n)+0] - pSrcA[(2*n)+1]*pSrcB[(2*n)+1];
  66  *     imagResult += pSrcA[(2*n)+0]*pSrcB[(2*n)+1] + pSrcA[(2*n)+1]*pSrcB[(2*n)+0];
  67  * }
  68  * </pre>
  69  *
  70  * There are separate functions for floating-point, Q15, and Q31 data types.
  71  */
  72
  73 /**
  74  * @addtogroup cmplx_dot_prod
  75  * @{
  76  */
  77
  78 /**
  79  * @brief  Floating-point complex dot product
  80  * @param  *pSrcA points to the first input vector
  81  * @param  *pSrcB points to the second input vector
  82  * @param  numSamples number of complex samples in each vector
  83  * @param  *realResult real part of the result returned here
  84  * @param  *imagResult imaginary part of the result returned here
  85  * @return none.
  86  */
  87
  88 void arm_cmplx_dot_prod_f32(
  89   float32_t * pSrcA,
  90   float32_t * pSrcB,
  91   uint32_t numSamples,
  92   float32_t * realResult,
  93   float32_t * imagResult)
  94 {
  95   float32_t real_sum = 0.0f, imag_sum = 0.0f;    /* Temporary result storage */
  96
  97 #ifndef ARM_MATH_CM0_FAMILY
  98
  99   /* Run the below code for Cortex-M4 and Cortex-M3 */
 100   uint32_t blkCnt;                               /* loop counter */
 101
 102   /*loop Unrolling */
 103   blkCnt = numSamples >> 2u;
 104
 105   /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.
 106    ** a second loop below computes the remaining 1 to 3 samples. */
 107   while(blkCnt > 0u)
 108   {
 109     /* CReal = A[0]* B[0] + A[2]* B[2] + A[4]* B[4] + .....+ A[numSamples-2]* B[numSamples-2] */
 110     real_sum += (*pSrcA++) * (*pSrcB++);
 111     /* CImag = A[1]* B[1] + A[3]* B[3] + A[5]* B[5] + .....+ A[numSamples-1]* B[numSamples-1] */
 112     imag_sum += (*pSrcA++) * (*pSrcB++);
 113
 114     real_sum += (*pSrcA++) * (*pSrcB++);
 115     imag_sum += (*pSrcA++) * (*pSrcB++);
 116
 117     real_sum += (*pSrcA++) * (*pSrcB++);
 118     imag_sum += (*pSrcA++) * (*pSrcB++);
 119
 120     real_sum += (*pSrcA++) * (*pSrcB++);
 121     imag_sum += (*pSrcA++) * (*pSrcB++);
 122
 123     /* Decrement the loop counter */
 124     blkCnt--;
 125   }
 126
 127   /* If the numSamples is not a multiple of 4, compute any remaining output samples here.
 128    ** No loop unrolling is used. */
 129   blkCnt = numSamples % 0x4u;
 130
 131   while(blkCnt > 0u)
 132   {
 133     /* CReal = A[0]* B[0] + A[2]* B[2] + A[4]* B[4] + .....+ A[numSamples-2]* B[numSamples-2] */
 134     real_sum += (*pSrcA++) * (*pSrcB++);
 135     /* CImag = A[1]* B[1] + A[3]* B[3] + A[5]* B[5] + .....+ A[numSamples-1]* B[numSamples-1] */
 136     imag_sum += (*pSrcA++) * (*pSrcB++);
 137
 138
 139     /* Decrement the loop counter */
 140     blkCnt--;
 141   }
 142
 143 #else
 144
 145   /* Run the below code for Cortex-M0 */
 146
 147   while(numSamples > 0u)
 148   {
 149     /* CReal = A[0]* B[0] + A[2]* B[2] + A[4]* B[4] + .....+ A[numSamples-2]* B[numSamples-2] */
 150     real_sum += (*pSrcA++) * (*pSrcB++);
 151     /* CImag = A[1]* B[1] + A[3]* B[3] + A[5]* B[5] + .....+ A[numSamples-1]* B[numSamples-1] */
 152     imag_sum += (*pSrcA++) * (*pSrcB++);
 153
 154
 155     /* Decrement the loop counter */
 156     numSamples--;
 157   }
 158
 159 #endif /* #ifndef ARM_MATH_CM0_FAMILY */
 160
 161   /* Store the real and imaginary results in the destination buffers */
 162   *realResult = real_sum;
 163   *imagResult = imag_sum;
 164 }
 165
 166 /**
 167  * @} end of cmplx_dot_prod group
 168  */