/* ----------------------------------------------------------------------    
* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
*    
* $Date:        19. March 2015
* $Revision: 	V.1.4.5  
*    
* Project: 	    CMSIS DSP Library    
* Title:		arm_mean_q15.c    
*    
* Description:	Mean value of a Q15 vector.   
*    
* 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 groupStats    
 */

/**    
 * @addtogroup mean    
 * @{    
 */

/**    
 * @brief Mean value of a Q15 vector.    
 * @param[in]       *pSrc points to the input vector    
 * @param[in]       blockSize length of the input vector    
 * @param[out]      *pResult mean value returned here    
 * @return none.    
 *    
 * @details    
 * <b>Scaling and Overflow Behavior:</b>    
 * \par    
 * The function is implemented using a 32-bit internal accumulator.    
 * The input is represented in 1.15 format and is accumulated in a 32-bit     
 * accumulator in 17.15 format.     
 * There is no risk of internal overflow with this approach, and the     
 * full precision of intermediate result is preserved.     
 * Finally, the accumulator is saturated and truncated to yield a result of 1.15 format.    
 *    
 */


void arm_mean_q15(
  q15_t * pSrc,
  uint32_t blockSize,
  q15_t * pResult)
{
  q31_t sum = 0;                                 /* Temporary result storage */
  uint32_t blkCnt;                               /* loop counter */

#ifndef ARM_MATH_CM0_FAMILY

  /* Run the below code for Cortex-M4 and Cortex-M3 */
  q31_t in;

  /*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[0] + A[1] + A[2] + ... + A[blockSize-1]) */
    in = *__SIMD32(pSrc)++;
    sum += ((in << 16) >> 16);
    sum += (in >> 16);
    in = *__SIMD32(pSrc)++;
    sum += ((in << 16) >> 16);
    sum += (in >> 16);

    /* 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;

#else

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

  /* Loop over blockSize number of values */
  blkCnt = blockSize;

#endif /* #ifndef ARM_MATH_CM0_FAMILY */

  while(blkCnt > 0u)
  {
    /* C = (A[0] + A[1] + A[2] + ... + A[blockSize-1]) */
    sum += *pSrc++;

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

  /* C = (A[0] + A[1] + A[2] + ... + A[blockSize-1]) / blockSize  */
  /* Store the result to the destination */
  *pResult = (q15_t) (sum / (q31_t)blockSize);
}

/**    
 * @} end of mean group    
 */