File content as of revision 1:fdd22bb7aa52:

/* ----------------------------------------------------------------------    
* Copyright (C) 2010 ARM Limited. All rights reserved.    
*    
* $Date:        15. February 2012  
* $Revision:     V1.1.0  
*    
* Project:         CMSIS DSP Library    
* Title:        arm_mat_add_q31.c    
*    
* Description:    Q31 matrix addition    
*    
* 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.    
*    
* Version 0.0.5  2010/04/26     
*    incorporated review comments and updated with latest CMSIS layer    
*    
* Version 0.0.3  2010/03/10     
*    Initial version    
* -------------------------------------------------------------------- */

#include "arm_math.h"

/**      
 * @ingroup groupMatrix      
 */

/**      
 * @addtogroup MatrixAdd      
 * @{      
 */

/**      
 * @brief Q31 matrix addition.      
 * @param[in]       *pSrcA points to the first input matrix structure      
 * @param[in]       *pSrcB points to the second input matrix structure      
 * @param[out]      *pDst points to output matrix structure      
 * @return             The function returns either      
 * <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.      
 *      
 * <b>Scaling and Overflow Behavior:</b>      
 * \par      
 * The function uses saturating arithmetic.      
 * Results outside of the allowable Q31 range [0x80000000 0x7FFFFFFF] will be saturated.      
 */

arm_status arm_mat_add_q31(
  const arm_matrix_instance_q31 * pSrcA,
  const arm_matrix_instance_q31 * pSrcB,
  arm_matrix_instance_q31 * pDst)
{
  q31_t *pIn1 = pSrcA->pData;                    /* input data matrix pointer A */
  q31_t *pIn2 = pSrcB->pData;                    /* input data matrix pointer B */
  q31_t *pOut = pDst->pData;                     /* output data matrix pointer */
  q31_t inA1, inB1;                              /* temporary variables */

#ifndef ARM_MATH_CM0

  q31_t inA2, inB2;                              /* temporary variables */
  q31_t out1, out2;                              /* temporary variables */

#endif //      #ifndef ARM_MATH_CM0

  uint32_t numSamples;                           /* total number of elements in the matrix  */
  uint32_t blkCnt;                               /* loop counters */
  arm_status status;                             /* status of matrix addition */

#ifdef ARM_MATH_MATRIX_CHECK
  /* Check for matrix mismatch condition */
  if((pSrcA->numRows != pSrcB->numRows) ||
     (pSrcA->numCols != pSrcB->numCols) ||
     (pSrcA->numRows != pDst->numRows) || (pSrcA->numCols != pDst->numCols))
  {
    /* Set status as ARM_MATH_SIZE_MISMATCH */
    status = ARM_MATH_SIZE_MISMATCH;
  }
  else
#endif
  {
    /* Total number of samples in the input matrix */
    numSamples = (uint32_t) pSrcA->numRows * pSrcA->numCols;

#ifndef ARM_MATH_CM0

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

    /* Loop Unrolling */
    blkCnt = numSamples >> 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(m,n) = A(m,n) + B(m,n) */
      /* Add, saturate and then store the results in the destination buffer. */
      /* Read values from source A */
      inA1 = pIn1[0];

      /* Read values from source B */
      inB1 = pIn2[0];

      /* Read values from source A */
      inA2 = pIn1[1];

      /* Add and saturate */
      out1 = __QADD(inA1, inB1);

      /* Read values from source B */
      inB2 = pIn2[1];

      /* Read values from source A */
      inA1 = pIn1[2];

      /* Add and saturate */
      out2 = __QADD(inA2, inB2);

      /* Read values from source B */
      inB1 = pIn2[2];

      /* Store result in destination */
      pOut[0] = out1;
      pOut[1] = out2;

      /* Read values from source A */
      inA2 = pIn1[3];

      /* Read values from source B */
      inB2 = pIn2[3];

      /* Add and saturate */
      out1 = __QADD(inA1, inB1);
      out2 = __QADD(inA2, inB2);

      /* Store result in destination */
      pOut[2] = out1;
      pOut[3] = out2;

      /* update pointers to process next sampels */
      pIn1 += 4u;
      pIn2 += 4u;
      pOut += 4u;

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

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

#else

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

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


#endif /* #ifndef ARM_MATH_CM0 */

    while(blkCnt > 0u)
    {
      /* C(m,n) = A(m,n) + B(m,n) */
      /* Add, saturate and then store the results in the destination buffer. */
      inA1 = *pIn1++;
      inB1 = *pIn2++;

      inA1 = __QADD(inA1, inB1);

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

      *pOut++ = inA1;

    }

    /* set status as ARM_MATH_SUCCESS */
    status = ARM_MATH_SUCCESS;
  }

  /* Return to application */
  return (status);
}

/**      
 * @} end of MatrixAdd group      
 */