/* ----------------------------------------------------------------------    
* Copyright (C) 2010-2013 ARM Limited. All rights reserved.    
*    
* $Date:        17. January 2013
* $Revision: 	V1.4.1  
*    
* Project: 	    CMSIS DSP Library    
* Title:		arm_std_f32.c    
*    
* Description:	Standard deviation of the elements of a floating-point 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    
 */

/**    
 * @defgroup STD Standard deviation    
 *    
 * Calculates the standard deviation of the elements in the input vector.     
 * The underlying algorithm is used:    
 *   
 * <pre>    
 * 	Result = sqrt((sumOfSquares - sum<sup>2</sup> / blockSize) / (blockSize - 1))   
 *   
 *	   where, sumOfSquares = pSrc[0] * pSrc[0] + pSrc[1] * pSrc[1] + ... + pSrc[blockSize-1] * pSrc[blockSize-1]   
 *   
 *	                   sum = pSrc[0] + pSrc[1] + pSrc[2] + ... + pSrc[blockSize-1]   
 * </pre>   
 *    
 * There are separate functions for floating point, Q31, and Q15 data types.    
 */

/**    
 * @addtogroup STD    
 * @{    
 */


/**    
 * @brief Standard deviation of the elements of a floating-point vector.    
 * @param[in]       *pSrc points to the input vector    
 * @param[in]       blockSize length of the input vector    
 * @param[out]      *pResult standard deviation value returned here    
 * @return none.    
 *    
 */


void arm_std_f32(
  float32_t * pSrc,
  uint32_t blockSize,
  float32_t * pResult)
{
  float32_t sum = 0.0f;                          /* Temporary result storage */
  float32_t sumOfSquares = 0.0f;                 /* Sum of squares */
  float32_t in;                                  /* input value */
  uint32_t blkCnt;                               /* loop counter */

#ifndef ARM_MATH_CM0_FAMILY

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

  float32_t meanOfSquares, mean, squareOfMean;

  /*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[0] + A[1] * A[1] + ... + A[blockSize-1] * A[blockSize-1])  */
    /* Compute Sum of squares of the input samples    
     * and then store the result in a temporary variable, sum. */
    in = *pSrc++;
    sum += in;
    sumOfSquares += in * in;
    in = *pSrc++;
    sum += in;
    sumOfSquares += in * in;
    in = *pSrc++;
    sum += in;
    sumOfSquares += in * in;
    in = *pSrc++;
    sum += in;
    sumOfSquares += in * in;

    /* 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[0] * A[0] + A[1] * A[1] + ... + A[blockSize-1] * A[blockSize-1]) */
    /* Compute Sum of squares of the input samples    
     * and then store the result in a temporary variable, sum. */
    in = *pSrc++;
    sum += in;
    sumOfSquares += in * in;

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

  /* Compute Mean of squares of the input samples    
   * and then store the result in a temporary variable, meanOfSquares. */
  meanOfSquares = sumOfSquares / ((float32_t) blockSize - 1.0f);

  /* Compute mean of all input values */
  mean = sum / (float32_t) blockSize;

  /* Compute square of mean */
  squareOfMean = (mean * mean) * (((float32_t) blockSize) /
                                  ((float32_t) blockSize - 1.0f));

  /* Compute standard deviation and then store the result to the destination */
  arm_sqrt_f32((meanOfSquares - squareOfMean), pResult);

#else

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

  float32_t squareOfSum;                         /* Square of Sum */
  float32_t var;                                 /* Temporary varaince storage */

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

  while(blkCnt > 0u)
  {
    /* C = (A[0] * A[0] + A[1] * A[1] + ... + A[blockSize-1] * A[blockSize-1]) */
    /* Compute Sum of squares of the input samples     
     * and then store the result in a temporary variable, sumOfSquares. */
    in = *pSrc++;
    sumOfSquares += in * in;

    /* C = (A[0] + A[1] + ... + A[blockSize-1]) */
    /* Compute Sum of the input samples     
     * and then store the result in a temporary variable, sum. */
    sum += in;

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

  /* Compute the square of sum */
  squareOfSum = ((sum * sum) / (float32_t) blockSize);

  /* Compute the variance */
  var = ((sumOfSquares - squareOfSum) / (float32_t) (blockSize - 1.0f));

  /* Compute standard deviation and then store the result to the destination */
  arm_sqrt_f32(var, pResult);

#endif /* #ifndef ARM_MATH_CM0_FAMILY */

}

/**    
 * @} end of STD group    
 */