tmk_core/tool/mbed/mbed-sdk/libraries/dsp/cmsis_dsp/ComplexMathFunctions/arm_cmplx_mag_squared_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_mag_squared_q15.c
   9 *
  10 * Description:  Q15 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
  41 #include "arm_math.h"
  42
  43 /**
  44  * @ingroup groupCmplxMath
  45  */
  46
  47 /**
  48  * @addtogroup cmplx_mag_squared
  49  * @{
  50  */
  51
  52 /**
  53  * @brief  Q15 complex magnitude squared
  54  * @param  *pSrc points to the complex input vector
  55  * @param  *pDst points to the real output vector
  56  * @param  numSamples number of complex samples in the input vector
  57  * @return none.
  58  *
  59  * <b>Scaling and Overflow Behavior:</b>
  60  * \par
  61  * The function implements 1.15 by 1.15 multiplications and finally output is converted into 3.13 format.
  62  */
  63
  64 void arm_cmplx_mag_squared_q15(
  65   q15_t * pSrc,
  66   q15_t * pDst,
  67   uint32_t numSamples)
  68 {
  69   q31_t acc0, acc1;                              /* Accumulators */
  70
  71 #ifndef ARM_MATH_CM0_FAMILY
  72
  73   /* Run the below code for Cortex-M4 and Cortex-M3 */
  74   uint32_t blkCnt;                               /* loop counter */
  75   q31_t in1, in2, in3, in4;
  76   q31_t acc2, acc3;
  77
  78   /*loop Unrolling */
  79   blkCnt = numSamples >> 2u;
  80
  81   /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.
  82    ** a second loop below computes the remaining 1 to 3 samples. */
  83   while(blkCnt > 0u)
  84   {
  85     /* C[0] = (A[0] * A[0] + A[1] * A[1]) */
  86     in1 = *__SIMD32(pSrc)++;
  87     in2 = *__SIMD32(pSrc)++;
  88     in3 = *__SIMD32(pSrc)++;
  89     in4 = *__SIMD32(pSrc)++;
  90
  91     acc0 = __SMUAD(in1, in1);
  92     acc1 = __SMUAD(in2, in2);
  93     acc2 = __SMUAD(in3, in3);
  94     acc3 = __SMUAD(in4, in4);
  95
  96     /* store the result in 3.13 format in the destination buffer. */
  97     *pDst++ = (q15_t) (acc0 >> 17);
  98     *pDst++ = (q15_t) (acc1 >> 17);
  99     *pDst++ = (q15_t) (acc2 >> 17);
 100     *pDst++ = (q15_t) (acc3 >> 17);
 101
 102     /* Decrement the loop counter */
 103     blkCnt--;
 104   }
 105
 106   /* If the numSamples is not a multiple of 4, compute any remaining output samples here.
 107    ** No loop unrolling is used. */
 108   blkCnt = numSamples % 0x4u;
 109
 110   while(blkCnt > 0u)
 111   {
 112     /* C[0] = (A[0] * A[0] + A[1] * A[1]) */
 113     in1 = *__SIMD32(pSrc)++;
 114     acc0 = __SMUAD(in1, in1);
 115
 116     /* store the result in 3.13 format in the destination buffer. */
 117     *pDst++ = (q15_t) (acc0 >> 17);
 118
 119     /* Decrement the loop counter */
 120     blkCnt--;
 121   }
 122
 123 #else
 124
 125   /* Run the below code for Cortex-M0 */
 126   q15_t real, imag;                              /* Temporary variables to store real and imaginary values */
 127
 128   while(numSamples > 0u)
 129   {
 130     /* out = ((real * real) + (imag * imag)) */
 131     real = *pSrc++;
 132     imag = *pSrc++;
 133     acc0 = (real * real);
 134     acc1 = (imag * imag);
 135     /* store the result in 3.13 format in the destination buffer. */
 136     *pDst++ = (q15_t) (((q63_t) acc0 + acc1) >> 17);
 137
 138     /* Decrement the loop counter */
 139     numSamples--;
 140   }
 141
 142 #endif /* #ifndef ARM_MATH_CM0_FAMILY */
 143
 144 }
 145
 146 /**
 147  * @} end of cmplx_mag_squared group
 148  */