tmk_core/tool/mbed/mbed-sdk/libraries/dsp/cmsis_dsp/ComplexMathFunctions/arm_cmplx_dot_prod_q15.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_q15.c
   9 *
  10 * Description:  Processing function for the Q15 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  * @addtogroup cmplx_dot_prod
  49  * @{
  50  */
  51
  52 /**
  53  * @brief  Q15 complex dot product
  54  * @param  *pSrcA points to the first input vector
  55  * @param  *pSrcB points to the second input vector
  56  * @param  numSamples number of complex samples in each vector
  57  * @param  *realResult real part of the result returned here
  58  * @param  *imagResult imaginary part of the result returned here
  59  * @return none.
  60  *
  61  * <b>Scaling and Overflow Behavior:</b>
  62  * \par
  63  * The function is implemented using an internal 64-bit accumulator.
  64  * The intermediate 1.15 by 1.15 multiplications are performed with full precision and yield a 2.30 result.
  65  * These are accumulated in a 64-bit accumulator with 34.30 precision.
  66  * As a final step, the accumulators are converted to 8.24 format.
  67  * The return results <code>realResult</code> and <code>imagResult</code> are in 8.24 format.
  68  */
  69
  70 void arm_cmplx_dot_prod_q15(
  71   q15_t * pSrcA,
  72   q15_t * pSrcB,
  73   uint32_t numSamples,
  74   q31_t * realResult,
  75   q31_t * imagResult)
  76 {
  77   q63_t real_sum = 0, imag_sum = 0;              /* Temporary result storage */
  78
  79 #ifndef ARM_MATH_CM0_FAMILY
  80
  81   /* Run the below code for Cortex-M4 and Cortex-M3 */
  82   uint32_t blkCnt;                               /* loop counter */
  83
  84
  85   /*loop Unrolling */
  86   blkCnt = numSamples >> 2u;
  87
  88   /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.
  89    ** a second loop below computes the remaining 1 to 3 samples. */
  90   while(blkCnt > 0u)
  91   {
  92     /* CReal = A[0]* B[0] + A[2]* B[2] + A[4]* B[4] + .....+ A[numSamples-2]* B[numSamples-2] */
  93     real_sum += ((q31_t) * pSrcA++ * *pSrcB++);
  94
  95     /* CImag = A[1]* B[1] + A[3]* B[3] + A[5]* B[5] + .....+ A[numSamples-1]* B[numSamples-1] */
  96     imag_sum += ((q31_t) * pSrcA++ * *pSrcB++);
  97
  98     real_sum += ((q31_t) * pSrcA++ * *pSrcB++);
  99     imag_sum += ((q31_t) * pSrcA++ * *pSrcB++);
 100
 101     real_sum += ((q31_t) * pSrcA++ * *pSrcB++);
 102     imag_sum += ((q31_t) * pSrcA++ * *pSrcB++);
 103
 104     real_sum += ((q31_t) * pSrcA++ * *pSrcB++);
 105     imag_sum += ((q31_t) * pSrcA++ * *pSrcB++);
 106
 107     /* Decrement the loop counter */
 108     blkCnt--;
 109   }
 110
 111   /* If the numSamples is not a multiple of 4, compute any remaining output samples here.
 112    ** No loop unrolling is used. */
 113   blkCnt = numSamples % 0x4u;
 114
 115   while(blkCnt > 0u)
 116   {
 117     /* CReal = A[0]* B[0] + A[2]* B[2] + A[4]* B[4] + .....+ A[numSamples-2]* B[numSamples-2] */
 118     real_sum += ((q31_t) * pSrcA++ * *pSrcB++);
 119     /* CImag = A[1]* B[1] + A[3]* B[3] + A[5]* B[5] + .....+ A[numSamples-1]* B[numSamples-1] */
 120     imag_sum += ((q31_t) * pSrcA++ * *pSrcB++);
 121
 122     /* Decrement the loop counter */
 123     blkCnt--;
 124   }
 125
 126 #else
 127
 128   /* Run the below code for Cortex-M0 */
 129
 130   while(numSamples > 0u)
 131   {
 132     /* CReal = A[0]* B[0] + A[2]* B[2] + A[4]* B[4] + .....+ A[numSamples-2]* B[numSamples-2] */
 133     real_sum += ((q31_t) * pSrcA++ * *pSrcB++);
 134     /* CImag = A[1]* B[1] + A[3]* B[3] + A[5]* B[5] + .....+ A[numSamples-1]* B[numSamples-1] */
 135     imag_sum += ((q31_t) * pSrcA++ * *pSrcB++);
 136
 137     /* Decrement the loop counter */
 138     numSamples--;
 139   }
 140
 141 #endif /* #ifndef ARM_MATH_CM0_FAMILY */
 142
 143   /* Store the real and imaginary results in 8.24 format  */
 144   /* Convert real data in 34.30 to 8.24 by 6 right shifts */
 145   *realResult = (q31_t) (real_sum) >> 6;
 146   /* Convert imaginary data in 34.30 to 8.24 by 6 right shifts */
 147   *imagResult = (q31_t) (imag_sum) >> 6;
 148 }
 149
 150 /**
 151  * @} end of cmplx_dot_prod group
 152  */