tmk_core/tool/mbed/mbed-sdk/libraries/dsp/cmsis_dsp/BasicMathFunctions/arm_add_q7.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_q7.c
   9 *
  10 * Description:  Q7 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  * @brief Q7 vector addition.
  54  * @param[in]       *pSrcA points to the first input vector
  55  * @param[in]       *pSrcB points to the second input vector
  56  * @param[out]      *pDst points to the output vector
  57  * @param[in]       blockSize number of samples in each vector
  58  * @return none.
  59  *
  60  * <b>Scaling and Overflow Behavior:</b>
  61  * \par
  62  * The function uses saturating arithmetic.
  63  * Results outside of the allowable Q7 range [0x80 0x7F] will be saturated.
  64  */
  65
  66 void arm_add_q7(
  67   q7_t * pSrcA,
  68   q7_t * pSrcB,
  69   q7_t * pDst,
  70   uint32_t blockSize)
  71 {
  72   uint32_t blkCnt;                               /* loop counter */
  73
  74 #ifndef ARM_MATH_CM0_FAMILY
  75
  76 /* Run the below code for Cortex-M4 and Cortex-M3 */
  77
  78
  79   /*loop Unrolling */
  80   blkCnt = blockSize >> 2u;
  81
  82   /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.
  83    ** a second loop below computes the remaining 1 to 3 samples. */
  84   while(blkCnt > 0u)
  85   {
  86     /* C = A + B */
  87     /* Add and then store the results in the destination buffer. */
  88     *__SIMD32(pDst)++ = __QADD8(*__SIMD32(pSrcA)++, *__SIMD32(pSrcB)++);
  89
  90     /* Decrement the loop counter */
  91     blkCnt--;
  92   }
  93
  94   /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
  95    ** No loop unrolling is used. */
  96   blkCnt = blockSize % 0x4u;
  97
  98   while(blkCnt > 0u)
  99   {
 100     /* C = A + B */
 101     /* Add and then store the results in the destination buffer. */
 102     *pDst++ = (q7_t) __SSAT(*pSrcA++ + *pSrcB++, 8);
 103
 104     /* Decrement the loop counter */
 105     blkCnt--;
 106   }
 107
 108 #else
 109
 110   /* Run the below code for Cortex-M0 */
 111
 112
 113
 114   /* Initialize blkCnt with number of samples */
 115   blkCnt = blockSize;
 116
 117   while(blkCnt > 0u)
 118   {
 119     /* C = A + B */
 120     /* Add and then store the results in the destination buffer. */
 121     *pDst++ = (q7_t) __SSAT((q15_t) * pSrcA++ + *pSrcB++, 8);
 122
 123     /* Decrement the loop counter */
 124     blkCnt--;
 125   }
 126
 127 #endif /* #ifndef ARM_MATH_CM0_FAMILY */
 128
 129
 130 }
 131
 132 /**
 133  * @} end of BasicAdd group
 134  */