tmk_core/tool/mbed/mbed-sdk/libraries/dsp/cmsis_dsp/BasicMathFunctions/arm_add_q31.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_add_q31.c
   9 *
  10 * Description:  Q31 vector addition.
  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 groupMath
  45  */
  46
  47 /**
  48  * @addtogroup BasicAdd
  49  * @{
  50  */
  51
  52
  53 /**
  54  * @brief Q31 vector addition.
  55  * @param[in]       *pSrcA points to the first input vector
  56  * @param[in]       *pSrcB points to the second input vector
  57  * @param[out]      *pDst points to the output vector
  58  * @param[in]       blockSize number of samples in each vector
  59  * @return none.
  60  *
  61  * <b>Scaling and Overflow Behavior:</b>
  62  * \par
  63  * The function uses saturating arithmetic.
  64  * Results outside of the allowable Q31 range[0x80000000 0x7FFFFFFF] will be saturated.
  65  */
  66
  67 void arm_add_q31(
  68   q31_t * pSrcA,
  69   q31_t * pSrcB,
  70   q31_t * pDst,
  71   uint32_t blockSize)
  72 {
  73   uint32_t blkCnt;                               /* loop counter */
  74
  75 #ifndef ARM_MATH_CM0_FAMILY
  76
  77 /* Run the below code for Cortex-M4 and Cortex-M3 */
  78   q31_t inA1, inA2, inA3, inA4;
  79   q31_t inB1, inB2, inB3, inB4;
  80
  81   /*loop Unrolling */
  82   blkCnt = blockSize >> 2u;
  83
  84   /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.
  85    ** a second loop below computes the remaining 1 to 3 samples. */
  86   while(blkCnt > 0u)
  87   {
  88     /* C = A + B */
  89     /* Add and then store the results in the destination buffer. */
  90     inA1 = *pSrcA++;
  91     inA2 = *pSrcA++;
  92     inB1 = *pSrcB++;
  93     inB2 = *pSrcB++;
  94
  95     inA3 = *pSrcA++;
  96     inA4 = *pSrcA++;
  97     inB3 = *pSrcB++;
  98     inB4 = *pSrcB++;
  99
 100     *pDst++ = __QADD(inA1, inB1);
 101     *pDst++ = __QADD(inA2, inB2);
 102     *pDst++ = __QADD(inA3, inB3);
 103     *pDst++ = __QADD(inA4, inB4);
 104
 105     /* Decrement the loop counter */
 106     blkCnt--;
 107   }
 108
 109   /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
 110    ** No loop unrolling is used. */
 111   blkCnt = blockSize % 0x4u;
 112
 113   while(blkCnt > 0u)
 114   {
 115     /* C = A + B */
 116     /* Add and then store the results in the destination buffer. */
 117     *pDst++ = __QADD(*pSrcA++, *pSrcB++);
 118
 119     /* Decrement the loop counter */
 120     blkCnt--;
 121   }
 122
 123 #else
 124
 125   /* Run the below code for Cortex-M0 */
 126
 127
 128
 129   /* Initialize blkCnt with number of samples */
 130   blkCnt = blockSize;
 131
 132   while(blkCnt > 0u)
 133   {
 134     /* C = A + B */
 135     /* Add and then store the results in the destination buffer. */
 136     *pDst++ = (q31_t) clip_q63_to_q31((q63_t) * pSrcA++ + *pSrcB++);
 137
 138     /* Decrement the loop counter */
 139     blkCnt--;
 140   }
 141
 142 #endif /* #ifndef ARM_MATH_CM0_FAMILY */
 143
 144 }
 145
 146 /**
 147  * @} end of BasicAdd group
 148  */