arm_sub_q7.c 4.16 KB
Newer Older
Sebastian Renner committed
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131
/* ----------------------------------------------------------------------    
* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
*    
* $Date:        19. March 2015
* $Revision: 	V.1.4.5
*    
* Project: 	    CMSIS DSP Library    
* Title:		arm_sub_q7.c    
*    
* Description:	Q7 vector subtraction.    
*    
* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
*  
* Redistribution and use in source and binary forms, with or without 
* modification, are permitted provided that the following conditions
* are met:
*   - Redistributions of source code must retain the above copyright
*     notice, this list of conditions and the following disclaimer.
*   - Redistributions in binary form must reproduce the above copyright
*     notice, this list of conditions and the following disclaimer in
*     the documentation and/or other materials provided with the 
*     distribution.
*   - Neither the name of ARM LIMITED nor the names of its contributors
*     may be used to endorse or promote products derived from this
*     software without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
* POSSIBILITY OF SUCH DAMAGE.    
* -------------------------------------------------------------------- */

#include "arm_math.h"

/**    
 * @ingroup groupMath    
 */

/**    
 * @addtogroup BasicSub    
 * @{    
 */

/**    
 * @brief Q7 vector subtraction.    
 * @param[in]       *pSrcA points to the first input vector    
 * @param[in]       *pSrcB points to the second input vector    
 * @param[out]      *pDst points to the output vector    
 * @param[in]       blockSize number of samples in each vector    
 * @return none.    
 *    
 * <b>Scaling and Overflow Behavior:</b>    
 * \par    
 * The function uses saturating arithmetic.    
 * Results outside of the allowable Q7 range [0x80 0x7F] will be saturated.    
 */

void arm_sub_q7(
  q7_t * pSrcA,
  q7_t * pSrcB,
  q7_t * pDst,
  uint32_t blockSize)
{
  uint32_t blkCnt;                               /* loop counter */

#ifndef ARM_MATH_CM0_FAMILY

/* Run the below code for Cortex-M4 and Cortex-M3 */

  /*loop Unrolling */
  blkCnt = blockSize >> 2u;

  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
   ** a second loop below computes the remaining 1 to 3 samples. */
  while(blkCnt > 0u)
  {
    /* C = A - B */
    /* Subtract and then store the results in the destination buffer 4 samples at a time. */
    *__SIMD32(pDst)++ = __QSUB8(*__SIMD32(pSrcA)++, *__SIMD32(pSrcB)++);

    /* Decrement the loop counter */
    blkCnt--;
  }

  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
   ** No loop unrolling is used. */
  blkCnt = blockSize % 0x4u;

  while(blkCnt > 0u)
  {
    /* C = A - B */
    /* Subtract and then store the result in the destination buffer. */
    *pDst++ = __SSAT(*pSrcA++ - *pSrcB++, 8);

    /* Decrement the loop counter */
    blkCnt--;
  }

#else

  /* Run the below code for Cortex-M0 */

  /* Initialize blkCnt with number of samples */
  blkCnt = blockSize;

  while(blkCnt > 0u)
  {
    /* C = A - B */
    /* Subtract and then store the result in the destination buffer. */
    *pDst++ = (q7_t) __SSAT((q15_t) * pSrcA++ - *pSrcB++, 8);

    /* Decrement the loop counter */
    blkCnt--;
  }

#endif /* #ifndef ARM_MATH_CM0_FAMILY */


}

/**    
 * @} end of BasicSub group    
 */