CMSIS DSP library

Dependents:   KL25Z_FFT_Demo Hat_Board_v5_1 KL25Z_FFT_Demo_tony KL25Z_FFT_Demo_tony ... more

Fork of mbed-dsp by mbed official

cmsis_dsp/StatisticsFunctions/arm_power_q15.c

Committer:
emilmont
Date:
2013-05-30
Revision:
2:da51fb522205
Parent:
1:fdd22bb7aa52
Child:
3:7a284390b0ce

File content as of revision 2:da51fb522205:

/* ----------------------------------------------------------------------    
* Copyright (C) 2010 ARM Limited. All rights reserved.    
*    
* $Date:        15. February 2012  
* $Revision: 	V1.1.0  
*    
* Project: 	    CMSIS DSP Library    
* Title:		arm_power_q15.c    
*    
* Description:	Sum of the squares of the elements of a Q15 vector.    
*    
* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
*  
* Version 1.1.0 2012/02/15 
*    Updated with more optimizations, bug fixes and minor API changes.  
*   
* Version 1.0.10 2011/7/15  
*    Big Endian support added and Merged M0 and M3/M4 Source code.   
*    
* Version 1.0.3 2010/11/29   
*    Re-organized the CMSIS folders and updated documentation.    
*     
* Version 1.0.2 2010/11/11    
*    Documentation updated.     
*    
* Version 1.0.1 2010/10/05     
*    Production release and review comments incorporated.    
*    
* Version 1.0.0 2010/09/20     
*    Production release and review comments incorporated.    
* -------------------------------------------------------------------- */

#include "arm_math.h"

/**    
 * @ingroup groupStats    
 */

/**    
 * @addtogroup power    
 * @{    
 */

/**    
 * @brief Sum of the squares of the elements of a Q15 vector.    
 * @param[in]       *pSrc points to the input vector    
 * @param[in]       blockSize length of the input vector    
 * @param[out]      *pResult sum of the squares value returned here    
 * @return none.    
 *    
 * @details    
 * <b>Scaling and Overflow Behavior:</b>    
 *    
 * \par    
 * The function is implemented using a 64-bit internal accumulator.     
 * The input is represented in 1.15 format.   
 * Intermediate multiplication yields a 2.30 format, and this    
 * result is added without saturation to a 64-bit accumulator in 34.30 format.    
 * With 33 guard bits in the accumulator, there is no risk of overflow, and the    
 * full precision of the intermediate multiplication is preserved.    
 * Finally, the return result is in 34.30 format.     
 *    
 */

void arm_power_q15(
  q15_t * pSrc,
  uint32_t blockSize,
  q63_t * pResult)
{
  q63_t sum = 0;                                 /* Temporary result storage */

#ifndef ARM_MATH_CM0

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

  q31_t in32;                                    /* Temporary variable to store input value */
  q15_t in16;                                    /* Temporary variable to store input value */
  uint32_t blkCnt;                               /* loop counter */


  /* 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[2] * A[2] + ... + A[blockSize-1] * A[blockSize-1] */
    /* Compute Power and then store the result in a temporary variable, sum. */
    in32 = *__SIMD32(pSrc)++;
    sum = __SMLALD(in32, in32, sum);
    in32 = *__SIMD32(pSrc)++;
    sum = __SMLALD(in32, in32, sum);

    /* 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[2] * A[2] + ... + A[blockSize-1] * A[blockSize-1] */
    /* Compute Power and then store the result in a temporary variable, sum. */
    in16 = *pSrc++;
    sum = __SMLALD(in16, in16, sum);

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

#else

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

  q15_t in;                                      /* Temporary variable to store input value */
  uint32_t blkCnt;                               /* loop counter */


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

  while(blkCnt > 0u)
  {
    /* C = A[0] * A[0] + A[1] * A[1] + A[2] * A[2] + ... + A[blockSize-1] * A[blockSize-1] */
    /* Compute Power and then store the result in a temporary variable, sum. */
    in = *pSrc++;
    sum += ((q31_t) in * in);

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

#endif /* #ifndef ARM_MATH_CM0 */

  /* Store the results in 34.30 format  */
  *pResult = sum;
}

/**    
 * @} end of power group    
 */