arm_biquad_cascade_df1_f32.c

Go to the documentation of this file.

/* ----------------------------------------------------------------------    
* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
*    
* $Date:        19. March 2015
* $Revision:    V.1.4.5
*    
* Project:      CMSIS DSP Library    
* Title:        arm_biquad_cascade_df1_f32.c    
*    
* Description:  Processing function for the    
*               floating-point Biquad cascade DirectFormI(DF1) filter.    
*    
* 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"

void arm_biquad_cascade_df1_f32(
  const arm_biquad_casd_df1_inst_f32 * S,
  float32_t * pSrc,
  float32_t * pDst,
  uint32_t blockSize)
{
  float32_t *pIn = pSrc;                         /*  source pointer            */
  float32_t *pOut = pDst;                        /*  destination pointer       */
  float32_t *pState = S->pState;                 /*  pState pointer            */
  float32_t *pCoeffs = S->pCoeffs;               /*  coefficient pointer       */
  float32_t acc;                                 /*  Simulates the accumulator */
  float32_t b0, b1, b2, a1, a2;                  /*  Filter coefficients       */
  float32_t Xn1, Xn2, Yn1, Yn2;                  /*  Filter pState variables   */
  float32_t Xn;                                  /*  temporary input           */
  uint32_t sample, stage = S->numStages;         /*  loop counters             */


#ifndef ARM_MATH_CM0_FAMILY

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

  do
  {
    /* Reading the coefficients */
    b0 = *pCoeffs++;
    b1 = *pCoeffs++;
    b2 = *pCoeffs++;
    a1 = *pCoeffs++;
    a2 = *pCoeffs++;

    /* Reading the pState values */
    Xn1 = pState[0];
    Xn2 = pState[1];
    Yn1 = pState[2];
    Yn2 = pState[3];

    /* Apply loop unrolling and compute 4 output values simultaneously. */
    /*      The variable acc hold output values that are being computed:    
     *    
     *    acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1]   + a2 * y[n-2]    
     *    acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1]   + a2 * y[n-2]    
     *    acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1]   + a2 * y[n-2]    
     *    acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1]   + a2 * y[n-2]    
     */

    sample = 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(sample > 0u)
    {
      /* Read the first input */
      Xn = *pIn++;

      /* acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2] */
      Yn2 = (b0 * Xn) + (b1 * Xn1) + (b2 * Xn2) + (a1 * Yn1) + (a2 * Yn2);

      /* Store the result in the accumulator in the destination buffer. */
      *pOut++ = Yn2;

      /* Every time after the output is computed state should be updated. */
      /* The states should be updated as:  */
      /* Xn2 = Xn1    */
      /* Xn1 = Xn     */
      /* Yn2 = Yn1    */
      /* Yn1 = acc   */

      /* Read the second input */
      Xn2 = *pIn++;

      /* acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2] */
      Yn1 = (b0 * Xn2) + (b1 * Xn) + (b2 * Xn1) + (a1 * Yn2) + (a2 * Yn1);

      /* Store the result in the accumulator in the destination buffer. */
      *pOut++ = Yn1;

      /* Every time after the output is computed state should be updated. */
      /* The states should be updated as:  */
      /* Xn2 = Xn1    */
      /* Xn1 = Xn     */
      /* Yn2 = Yn1    */
      /* Yn1 = acc   */

      /* Read the third input */
      Xn1 = *pIn++;

      /* acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2] */
      Yn2 = (b0 * Xn1) + (b1 * Xn2) + (b2 * Xn) + (a1 * Yn1) + (a2 * Yn2);

      /* Store the result in the accumulator in the destination buffer. */
      *pOut++ = Yn2;

      /* Every time after the output is computed state should be updated. */
      /* The states should be updated as: */
      /* Xn2 = Xn1    */
      /* Xn1 = Xn     */
      /* Yn2 = Yn1    */
      /* Yn1 = acc   */

      /* Read the forth input */
      Xn = *pIn++;

      /* acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2] */
      Yn1 = (b0 * Xn) + (b1 * Xn1) + (b2 * Xn2) + (a1 * Yn2) + (a2 * Yn1);

      /* Store the result in the accumulator in the destination buffer. */
      *pOut++ = Yn1;

      /* Every time after the output is computed state should be updated. */
      /* The states should be updated as:  */
      /* Xn2 = Xn1    */
      /* Xn1 = Xn     */
      /* Yn2 = Yn1    */
      /* Yn1 = acc   */
      Xn2 = Xn1;
      Xn1 = Xn;

      /* decrement the loop counter */
      sample--;

    }

    /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
     ** No loop unrolling is used. */
    sample = blockSize & 0x3u;

    while(sample > 0u)
    {
      /* Read the input */
      Xn = *pIn++;

      /* acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2] */
      acc = (b0 * Xn) + (b1 * Xn1) + (b2 * Xn2) + (a1 * Yn1) + (a2 * Yn2);

      /* Store the result in the accumulator in the destination buffer. */
      *pOut++ = acc;

      /* Every time after the output is computed state should be updated. */
      /* The states should be updated as:    */
      /* Xn2 = Xn1    */
      /* Xn1 = Xn     */
      /* Yn2 = Yn1    */
      /* Yn1 = acc   */
      Xn2 = Xn1;
      Xn1 = Xn;
      Yn2 = Yn1;
      Yn1 = acc;

      /* decrement the loop counter */
      sample--;

    }

    /*  Store the updated state variables back into the pState array */
    *pState++ = Xn1;
    *pState++ = Xn2;
    *pState++ = Yn1;
    *pState++ = Yn2;

    /*  The first stage goes from the input buffer to the output buffer. */
    /*  Subsequent numStages  occur in-place in the output buffer */
    pIn = pDst;

    /* Reset the output pointer */
    pOut = pDst;

    /* decrement the loop counter */
    stage--;

  } while(stage > 0u);

#else

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

  do
  {
    /* Reading the coefficients */
    b0 = *pCoeffs++;
    b1 = *pCoeffs++;
    b2 = *pCoeffs++;
    a1 = *pCoeffs++;
    a2 = *pCoeffs++;

    /* Reading the pState values */
    Xn1 = pState[0];
    Xn2 = pState[1];
    Yn1 = pState[2];
    Yn2 = pState[3];

    /*      The variables acc holds the output value that is computed:        
     *    acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1]   + a2 * y[n-2]        
     */

    sample = blockSize;

    while(sample > 0u)
    {
      /* Read the input */
      Xn = *pIn++;

      /* acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2] */
      acc = (b0 * Xn) + (b1 * Xn1) + (b2 * Xn2) + (a1 * Yn1) + (a2 * Yn2);

      /* Store the result in the accumulator in the destination buffer. */
      *pOut++ = acc;

      /* Every time after the output is computed state should be updated. */
      /* The states should be updated as:    */
      /* Xn2 = Xn1    */
      /* Xn1 = Xn     */
      /* Yn2 = Yn1    */
      /* Yn1 = acc   */
      Xn2 = Xn1;
      Xn1 = Xn;
      Yn2 = Yn1;
      Yn1 = acc;

      /* decrement the loop counter */
      sample--;
    }

    /*  Store the updated state variables back into the pState array */
    *pState++ = Xn1;
    *pState++ = Xn2;
    *pState++ = Yn1;
    *pState++ = Yn2;

    /*  The first stage goes from the input buffer to the output buffer. */
    /*  Subsequent numStages  occur in-place in the output buffer */
    pIn = pDst;

    /* Reset the output pointer */
    pOut = pDst;

    /* decrement the loop counter */
    stage--;

  } while(stage > 0u);

#endif /*   #ifndef ARM_MATH_CM0_FAMILY         */

}