arm_math.h

   * @brief Dot product of Q31 vectors.
   * @param[in]       *pSrcA points to the first input vector
   * @param[in]       *pSrcB points to the second input vector
   * @param[in]       blockSize number of samples in each vector
   * @param[out]      *result output result returned here
   * @return none.
   */

  void arm_dot_prod_q31(
  q31_t * pSrcA,
  q31_t * pSrcB,
  uint32_t blockSize,
  q63_t * result);

  /**
   * @brief  Shifts the elements of a Q7 vector a specified number of bits.
   * @param[in]  *pSrc points to the input vector
   * @param[in]  shiftBits number of bits to shift.  A positive value shifts left; a negative value shifts right.
   * @param[out]  *pDst points to the output vector
   * @param[in]  blockSize number of samples in the vector
   * @return none.
   */

  void arm_shift_q7(
  q7_t * pSrc,
  int8_t shiftBits,
  q7_t * pDst,
  uint32_t blockSize);

  /**
   * @brief  Shifts the elements of a Q15 vector a specified number of bits.
   * @param[in]  *pSrc points to the input vector
   * @param[in]  shiftBits number of bits to shift.  A positive value shifts left; a negative value shifts right.
   * @param[out]  *pDst points to the output vector
   * @param[in]  blockSize number of samples in the vector
   * @return none.
   */

  void arm_shift_q15(
  q15_t * pSrc,
  int8_t shiftBits,
  q15_t * pDst,
  uint32_t blockSize);

  /**
   * @brief  Shifts the elements of a Q31 vector a specified number of bits.
   * @param[in]  *pSrc points to the input vector
   * @param[in]  shiftBits number of bits to shift.  A positive value shifts left; a negative value shifts right.
   * @param[out]  *pDst points to the output vector
   * @param[in]  blockSize number of samples in the vector
   * @return none.
   */

  void arm_shift_q31(
  q31_t * pSrc,
  int8_t shiftBits,
  q31_t * pDst,
  uint32_t blockSize);

  /**
   * @brief  Adds a constant offset to a floating-point vector.
   * @param[in]  *pSrc points to the input vector
   * @param[in]  offset is the offset to be added
   * @param[out]  *pDst points to the output vector
   * @param[in]  blockSize number of samples in the vector
   * @return none.
   */

  void arm_offset_f32(
  float32_t * pSrc,
  float32_t offset,
  float32_t * pDst,
  uint32_t blockSize);

  /**
   * @brief  Adds a constant offset to a Q7 vector.
   * @param[in]  *pSrc points to the input vector
   * @param[in]  offset is the offset to be added
   * @param[out]  *pDst points to the output vector
   * @param[in]  blockSize number of samples in the vector
   * @return none.
   */

  void arm_offset_q7(
  q7_t * pSrc,
  q7_t offset,
  q7_t * pDst,
  uint32_t blockSize);

  /**
   * @brief  Adds a constant offset to a Q15 vector.
   * @param[in]  *pSrc points to the input vector
   * @param[in]  offset is the offset to be added
   * @param[out]  *pDst points to the output vector
   * @param[in]  blockSize number of samples in the vector
   * @return none.
   */

  void arm_offset_q15(
  q15_t * pSrc,
  q15_t offset,
  q15_t * pDst,
  uint32_t blockSize);

  /**
   * @brief  Adds a constant offset to a Q31 vector.
   * @param[in]  *pSrc points to the input vector
   * @param[in]  offset is the offset to be added
   * @param[out]  *pDst points to the output vector
   * @param[in]  blockSize number of samples in the vector
   * @return none.
   */

  void arm_offset_q31(
  q31_t * pSrc,
  q31_t offset,
  q31_t * pDst,
  uint32_t blockSize);

  /**
   * @brief  Negates the elements of a floating-point vector.
   * @param[in]  *pSrc points to the input vector
   * @param[out]  *pDst points to the output vector
   * @param[in]  blockSize number of samples in the vector
   * @return none.
   */

  void arm_negate_f32(
  float32_t * pSrc,
  float32_t * pDst,
  uint32_t blockSize);

  /**
   * @brief  Negates the elements of a Q7 vector.
   * @param[in]  *pSrc points to the input vector
   * @param[out]  *pDst points to the output vector
   * @param[in]  blockSize number of samples in the vector
   * @return none.
   */

  void arm_negate_q7(
  q7_t * pSrc,
  q7_t * pDst,
  uint32_t blockSize);

  /**
   * @brief  Negates the elements of a Q15 vector.
   * @param[in]  *pSrc points to the input vector
   * @param[out]  *pDst points to the output vector
   * @param[in]  blockSize number of samples in the vector
   * @return none.
   */

  void arm_negate_q15(
  q15_t * pSrc,
  q15_t * pDst,
  uint32_t blockSize);

  /**
   * @brief  Negates the elements of a Q31 vector.
   * @param[in]  *pSrc points to the input vector
   * @param[out]  *pDst points to the output vector
   * @param[in]  blockSize number of samples in the vector
   * @return none.
   */

  void arm_negate_q31(
  q31_t * pSrc,
  q31_t * pDst,
  uint32_t blockSize);
  /**
   * @brief  Copies the elements of a floating-point vector. 
   * @param[in]  *pSrc input pointer
   * @param[out]  *pDst output pointer
   * @param[in]  blockSize number of samples to process
   * @return none.
   */
  void arm_copy_f32(
  float32_t * pSrc,
  float32_t * pDst,
  uint32_t blockSize);

  /**
   * @brief  Copies the elements of a Q7 vector. 
   * @param[in]  *pSrc input pointer
   * @param[out]  *pDst output pointer
   * @param[in]  blockSize number of samples to process
   * @return none.
   */
  void arm_copy_q7(
  q7_t * pSrc,
  q7_t * pDst,
  uint32_t blockSize);

  /**
   * @brief  Copies the elements of a Q15 vector. 
   * @param[in]  *pSrc input pointer
   * @param[out]  *pDst output pointer
   * @param[in]  blockSize number of samples to process
   * @return none.
   */
  void arm_copy_q15(
  q15_t * pSrc,
  q15_t * pDst,
  uint32_t blockSize);

  /**
   * @brief  Copies the elements of a Q31 vector. 
   * @param[in]  *pSrc input pointer
   * @param[out]  *pDst output pointer
   * @param[in]  blockSize number of samples to process
   * @return none.
   */
  void arm_copy_q31(
  q31_t * pSrc,
  q31_t * pDst,
  uint32_t blockSize);
  /**
   * @brief  Fills a constant value into a floating-point vector. 
   * @param[in]  value input value to be filled
   * @param[out]  *pDst output pointer
   * @param[in]  blockSize number of samples to process
   * @return none.
   */
  void arm_fill_f32(
  float32_t value,
  float32_t * pDst,
  uint32_t blockSize);

  /**
   * @brief  Fills a constant value into a Q7 vector. 
   * @param[in]  value input value to be filled
   * @param[out]  *pDst output pointer
   * @param[in]  blockSize number of samples to process
   * @return none.
   */
  void arm_fill_q7(
  q7_t value,
  q7_t * pDst,
  uint32_t blockSize);

  /**
   * @brief  Fills a constant value into a Q15 vector. 
   * @param[in]  value input value to be filled
   * @param[out]  *pDst output pointer
   * @param[in]  blockSize number of samples to process
   * @return none.
   */
  void arm_fill_q15(
  q15_t value,
  q15_t * pDst,
  uint32_t blockSize);

  /**
   * @brief  Fills a constant value into a Q31 vector. 
   * @param[in]  value input value to be filled
   * @param[out]  *pDst output pointer
   * @param[in]  blockSize number of samples to process
   * @return none.
   */
  void arm_fill_q31(
  q31_t value,
  q31_t * pDst,
  uint32_t blockSize);

/**  
 * @brief Convolution of floating-point sequences.  
 * @param[in] *pSrcA points to the first input sequence.  
 * @param[in] srcALen length of the first input sequence.  
 * @param[in] *pSrcB points to the second input sequence.  
 * @param[in] srcBLen length of the second input sequence.  
 * @param[out] *pDst points to the location where the output result is written.  Length srcALen+srcBLen-1.  
 * @return none.  
 */

  void arm_conv_f32(
  float32_t * pSrcA,
  uint32_t srcALen,
  float32_t * pSrcB,
  uint32_t srcBLen,
  float32_t * pDst);

  
  /**   
   * @brief Convolution of Q15 sequences.   
   * @param[in] *pSrcA points to the first input sequence.   
   * @param[in] srcALen length of the first input sequence.   
   * @param[in] *pSrcB points to the second input sequence.   
   * @param[in] srcBLen length of the second input sequence.   
   * @param[out] *pDst points to the block of output data  Length srcALen+srcBLen-1.   
   * @param[in]  *pScratch1 points to scratch buffer of size max(srcALen, srcBLen) + 2*min(srcALen, srcBLen) - 2.   
   * @param[in]  *pScratch2 points to scratch buffer of size min(srcALen, srcBLen).   
   * @return none.   
   */


  void arm_conv_opt_q15(
  q15_t * pSrcA,
  uint32_t srcALen,
  q15_t * pSrcB,
  uint32_t srcBLen,
  q15_t * pDst,
  q15_t * pScratch1,
  q15_t * pScratch2);


/**  
 * @brief Convolution of Q15 sequences.  
 * @param[in] *pSrcA points to the first input sequence.  
 * @param[in] srcALen length of the first input sequence.  
 * @param[in] *pSrcB points to the second input sequence.  
 * @param[in] srcBLen length of the second input sequence.  
 * @param[out] *pDst points to the location where the output result is written.  Length srcALen+srcBLen-1.  
 * @return none.  
 */

  void arm_conv_q15(
  q15_t * pSrcA,
  uint32_t srcALen,
  q15_t * pSrcB,
  uint32_t srcBLen,
  q15_t * pDst);

  /**
   * @brief Convolution of Q15 sequences (fast version) for Cortex-M3 and Cortex-M4
   * @param[in] *pSrcA points to the first input sequence.
   * @param[in] srcALen length of the first input sequence.
   * @param[in] *pSrcB points to the second input sequence.
   * @param[in] srcBLen length of the second input sequence.
   * @param[out] *pDst points to the block of output data  Length srcALen+srcBLen-1.
   * @return none.
   */

  void arm_conv_fast_q15(
        q15_t * pSrcA,
       uint32_t srcALen,
        q15_t * pSrcB,
       uint32_t srcBLen,
       q15_t * pDst);

  /**
   * @brief Convolution of Q15 sequences (fast version) for Cortex-M3 and Cortex-M4
   * @param[in] *pSrcA points to the first input sequence.
   * @param[in] srcALen length of the first input sequence.
   * @param[in] *pSrcB points to the second input sequence.
   * @param[in] srcBLen length of the second input sequence.
   * @param[out] *pDst points to the block of output data  Length srcALen+srcBLen-1.
   * @param[in]  *pScratch1 points to scratch buffer of size max(srcALen, srcBLen) + 2*min(srcALen, srcBLen) - 2.   
   * @param[in]  *pScratch2 points to scratch buffer of size min(srcALen, srcBLen).   
   * @return none.   
   */

  void arm_conv_fast_opt_q15(
  q15_t * pSrcA,
  uint32_t srcALen,
  q15_t * pSrcB,
  uint32_t srcBLen,
  q15_t * pDst,
  q15_t * pScratch1,
  q15_t * pScratch2);



  /**
   * @brief Convolution of Q31 sequences.
   * @param[in] *pSrcA points to the first input sequence.
   * @param[in] srcALen length of the first input sequence.
   * @param[in] *pSrcB points to the second input sequence.
   * @param[in] srcBLen length of the second input sequence.
   * @param[out] *pDst points to the block of output data  Length srcALen+srcBLen-1.
   * @return none.
   */

  void arm_conv_q31(
  q31_t * pSrcA,
  uint32_t srcALen,
  q31_t * pSrcB,
  uint32_t srcBLen,
  q31_t * pDst);

  /**
   * @brief Convolution of Q31 sequences (fast version) for Cortex-M3 and Cortex-M4
   * @param[in] *pSrcA points to the first input sequence.
   * @param[in] srcALen length of the first input sequence.
   * @param[in] *pSrcB points to the second input sequence.
   * @param[in] srcBLen length of the second input sequence.
   * @param[out] *pDst points to the block of output data  Length srcALen+srcBLen-1.
   * @return none.
   */

  void arm_conv_fast_q31(
  q31_t * pSrcA,
  uint32_t srcALen,
  q31_t * pSrcB,
  uint32_t srcBLen,
  q31_t * pDst);


    /**   
   * @brief Convolution of Q7 sequences.   
   * @param[in] *pSrcA points to the first input sequence.   
   * @param[in] srcALen length of the first input sequence.   
   * @param[in] *pSrcB points to the second input sequence.   
   * @param[in] srcBLen length of the second input sequence.   
   * @param[out] *pDst points to the block of output data  Length srcALen+srcBLen-1.   
   * @param[in]  *pScratch1 points to scratch buffer(of type q15_t) of size max(srcALen, srcBLen) + 2*min(srcALen, srcBLen) - 2.   
   * @param[in]  *pScratch2 points to scratch buffer (of type q15_t) of size min(srcALen, srcBLen).   
   * @return none.   
   */

  void arm_conv_opt_q7(
  q7_t * pSrcA,
  uint32_t srcALen,
  q7_t * pSrcB,
  uint32_t srcBLen,
  q7_t * pDst,
  q15_t * pScratch1,
  q15_t * pScratch2);



  /**
   * @brief Convolution of Q7 sequences.
   * @param[in] *pSrcA points to the first input sequence.
   * @param[in] srcALen length of the first input sequence.
   * @param[in] *pSrcB points to the second input sequence.
   * @param[in] srcBLen length of the second input sequence.
   * @param[out] *pDst points to the block of output data  Length srcALen+srcBLen-1.
   * @return none.
   */

  void arm_conv_q7(
  q7_t * pSrcA,
  uint32_t srcALen,
  q7_t * pSrcB,
  uint32_t srcBLen,
  q7_t * pDst);


  /**
   * @brief Partial convolution of floating-point sequences.
   * @param[in]       *pSrcA points to the first input sequence.
   * @param[in]       srcALen length of the first input sequence.
   * @param[in]       *pSrcB points to the second input sequence.
   * @param[in]       srcBLen length of the second input sequence.
   * @param[out]      *pDst points to the block of output data
   * @param[in]       firstIndex is the first output sample to start with.
   * @param[in]       numPoints is the number of output points to be computed.
   * @return  Returns either ARM_MATH_SUCCESS if the function completed correctly or ARM_MATH_ARGUMENT_ERROR if the requested subset is not in the range [0 srcALen+srcBLen-2].
   */

  arm_status arm_conv_partial_f32(
  float32_t * pSrcA,
  uint32_t srcALen,
  float32_t * pSrcB,
  uint32_t srcBLen,
  float32_t * pDst,
  uint32_t firstIndex,
  uint32_t numPoints);

    /**   
   * @brief Partial convolution of Q15 sequences.   
   * @param[in]       *pSrcA points to the first input sequence.   
   * @param[in]       srcALen length of the first input sequence.   
   * @param[in]       *pSrcB points to the second input sequence.   
   * @param[in]       srcBLen length of the second input sequence.   
   * @param[out]      *pDst points to the block of output data   
   * @param[in]       firstIndex is the first output sample to start with.   
   * @param[in]       numPoints is the number of output points to be computed.   
   * @param[in]       * pScratch1 points to scratch buffer of size max(srcALen, srcBLen) + 2*min(srcALen, srcBLen) - 2.   
   * @param[in]       * pScratch2 points to scratch buffer of size min(srcALen, srcBLen).   
   * @return  Returns either ARM_MATH_SUCCESS if the function completed correctly or ARM_MATH_ARGUMENT_ERROR if the requested subset is not in the range [0 srcALen+srcBLen-2].   
   */

  arm_status arm_conv_partial_opt_q15(
  q15_t * pSrcA,
  uint32_t srcALen,
  q15_t * pSrcB,
  uint32_t srcBLen,
  q15_t * pDst,
  uint32_t firstIndex,
  uint32_t numPoints,
  q15_t * pScratch1,
  q15_t * pScratch2);


/**
   * @brief Partial convolution of Q15 sequences.
   * @param[in]       *pSrcA points to the first input sequence.
   * @param[in]       srcALen length of the first input sequence.
   * @param[in]       *pSrcB points to the second input sequence.
   * @param[in]       srcBLen length of the second input sequence.
   * @param[out]      *pDst points to the block of output data
   * @param[in]       firstIndex is the first output sample to start with.
   * @param[in]       numPoints is the number of output points to be computed.
   * @return  Returns either ARM_MATH_SUCCESS if the function completed correctly or ARM_MATH_ARGUMENT_ERROR if the requested subset is not in the range [0 srcALen+srcBLen-2].
   */

  arm_status arm_conv_partial_q15(
  q15_t * pSrcA,
  uint32_t srcALen,
  q15_t * pSrcB,
  uint32_t srcBLen,
  q15_t * pDst,
  uint32_t firstIndex,
  uint32_t numPoints);

  /**
   * @brief Partial convolution of Q15 sequences (fast version) for Cortex-M3 and Cortex-M4
   * @param[in]       *pSrcA points to the first input sequence.
   * @param[in]       srcALen length of the first input sequence.
   * @param[in]       *pSrcB points to the second input sequence.
   * @param[in]       srcBLen length of the second input sequence.
   * @param[out]      *pDst points to the block of output data
   * @param[in]       firstIndex is the first output sample to start with.
   * @param[in]       numPoints is the number of output points to be computed.
   * @return  Returns either ARM_MATH_SUCCESS if the function completed correctly or ARM_MATH_ARGUMENT_ERROR if the requested subset is not in the range [0 srcALen+srcBLen-2].
   */

  arm_status arm_conv_partial_fast_q15(
                q15_t * pSrcA,
               uint32_t srcALen,
                q15_t * pSrcB,
               uint32_t srcBLen,
               q15_t * pDst,
               uint32_t firstIndex,
               uint32_t numPoints);


  /**
   * @brief Partial convolution of Q15 sequences (fast version) for Cortex-M3 and Cortex-M4
   * @param[in]       *pSrcA points to the first input sequence.
   * @param[in]       srcALen length of the first input sequence.
   * @param[in]       *pSrcB points to the second input sequence.
   * @param[in]       srcBLen length of the second input sequence.
   * @param[out]      *pDst points to the block of output data
   * @param[in]       firstIndex is the first output sample to start with.
   * @param[in]       numPoints is the number of output points to be computed.
   * @param[in]       * pScratch1 points to scratch buffer of size max(srcALen, srcBLen) + 2*min(srcALen, srcBLen) - 2.   
   * @param[in]       * pScratch2 points to scratch buffer of size min(srcALen, srcBLen).   
   * @return  Returns either ARM_MATH_SUCCESS if the function completed correctly or ARM_MATH_ARGUMENT_ERROR if the requested subset is not in the range [0 srcALen+srcBLen-2].   
   */

  arm_status arm_conv_partial_fast_opt_q15(
  q15_t * pSrcA,
  uint32_t srcALen,
  q15_t * pSrcB,
  uint32_t srcBLen,
  q15_t * pDst,
  uint32_t firstIndex,
  uint32_t numPoints,
  q15_t * pScratch1,
  q15_t * pScratch2);


  /**
   * @brief Partial convolution of Q31 sequences.
   * @param[in]       *pSrcA points to the first input sequence.
   * @param[in]       srcALen length of the first input sequence.
   * @param[in]       *pSrcB points to the second input sequence.
   * @param[in]       srcBLen length of the second input sequence.
   * @param[out]      *pDst points to the block of output data
   * @param[in]       firstIndex is the first output sample to start with.
   * @param[in]       numPoints is the number of output points to be computed.
   * @return  Returns either ARM_MATH_SUCCESS if the function completed correctly or ARM_MATH_ARGUMENT_ERROR if the requested subset is not in the range [0 srcALen+srcBLen-2].
   */

  arm_status arm_conv_partial_q31(
  q31_t * pSrcA,
  uint32_t srcALen,
  q31_t * pSrcB,
  uint32_t srcBLen,
  q31_t * pDst,
  uint32_t firstIndex,
  uint32_t numPoints);


  /**
   * @brief Partial convolution of Q31 sequences (fast version) for Cortex-M3 and Cortex-M4
   * @param[in]       *pSrcA points to the first input sequence.
   * @param[in]       srcALen length of the first input sequence.
   * @param[in]       *pSrcB points to the second input sequence.
   * @param[in]       srcBLen length of the second input sequence.
   * @param[out]      *pDst points to the block of output data
   * @param[in]       firstIndex is the first output sample to start with.
   * @param[in]       numPoints is the number of output points to be computed.
   * @return  Returns either ARM_MATH_SUCCESS if the function completed correctly or ARM_MATH_ARGUMENT_ERROR if the requested subset is not in the range [0 srcALen+srcBLen-2].
   */

  arm_status arm_conv_partial_fast_q31(
  q31_t * pSrcA,
  uint32_t srcALen,
  q31_t * pSrcB,
  uint32_t srcBLen,
  q31_t * pDst,
  uint32_t firstIndex,
  uint32_t numPoints);


  /**   
   * @brief Partial convolution of Q7 sequences   
   * @param[in]       *pSrcA points to the first input sequence.   
   * @param[in]       srcALen length of the first input sequence.   
   * @param[in]       *pSrcB points to the second input sequence.   
   * @param[in]       srcBLen length of the second input sequence.   
   * @param[out]      *pDst points to the block of output data   
   * @param[in]       firstIndex is the first output sample to start with.   
   * @param[in]       numPoints is the number of output points to be computed.   
   * @param[in]  *pScratch1 points to scratch buffer(of type q15_t) of size max(srcALen, srcBLen) + 2*min(srcALen, srcBLen) - 2.   
   * @param[in]  *pScratch2 points to scratch buffer (of type q15_t) of size min(srcALen, srcBLen).   
   * @return  Returns either ARM_MATH_SUCCESS if the function completed correctly or ARM_MATH_ARGUMENT_ERROR if the requested subset is not in the range [0 srcALen+srcBLen-2].   
   */

  arm_status arm_conv_partial_opt_q7(
  q7_t * pSrcA,
  uint32_t srcALen,
  q7_t * pSrcB,
  uint32_t srcBLen,
  q7_t * pDst,
  uint32_t firstIndex,
  uint32_t numPoints,
  q15_t * pScratch1,
  q15_t * pScratch2);


/**
   * @brief Partial convolution of Q7 sequences.
   * @param[in]       *pSrcA points to the first input sequence.
   * @param[in]       srcALen length of the first input sequence.
   * @param[in]       *pSrcB points to the second input sequence.
   * @param[in]       srcBLen length of the second input sequence.
   * @param[out]      *pDst points to the block of output data
   * @param[in]       firstIndex is the first output sample to start with.
   * @param[in]       numPoints is the number of output points to be computed.
   * @return  Returns either ARM_MATH_SUCCESS if the function completed correctly or ARM_MATH_ARGUMENT_ERROR if the requested subset is not in the range [0 srcALen+srcBLen-2].
   */

  arm_status arm_conv_partial_q7(
  q7_t * pSrcA,
  uint32_t srcALen,
  q7_t * pSrcB,
  uint32_t srcBLen,
  q7_t * pDst,
  uint32_t firstIndex,
  uint32_t numPoints);



  /**
   * @brief Instance structure for the Q15 FIR decimator.
   */

  typedef struct
  {
    uint8_t M;                      /**< decimation factor. */
    uint16_t numTaps;               /**< number of coefficients in the filter. */
    q15_t *pCoeffs;                  /**< points to the coefficient array. The array is of length numTaps.*/
    q15_t *pState;                   /**< points to the state variable array. The array is of length numTaps+blockSize-1. */
  } arm_fir_decimate_instance_q15;

  /**
   * @brief Instance structure for the Q31 FIR decimator.
   */

  typedef struct
  {
    uint8_t M;                  /**< decimation factor. */
    uint16_t numTaps;           /**< number of coefficients in the filter. */
    q31_t *pCoeffs;              /**< points to the coefficient array. The array is of length numTaps.*/
    q31_t *pState;               /**< points to the state variable array. The array is of length numTaps+blockSize-1. */

  } arm_fir_decimate_instance_q31;

  /**
   * @brief Instance structure for the floating-point FIR decimator.
   */

  typedef struct
  {
    uint8_t M;                          /**< decimation factor. */
    uint16_t numTaps;                   /**< number of coefficients in the filter. */
    float32_t *pCoeffs;                  /**< points to the coefficient array. The array is of length numTaps.*/
    float32_t *pState;                   /**< points to the state variable array. The array is of length numTaps+blockSize-1. */

  } arm_fir_decimate_instance_f32;



  /**
   * @brief Processing function for the floating-point FIR decimator.
   * @param[in] *S points to an instance of the floating-point FIR decimator structure.
   * @param[in] *pSrc points to the block of input data.
   * @param[out] *pDst points to the block of output data
   * @param[in] blockSize number of input samples to process per call.
   * @return none
   */

  void arm_fir_decimate_f32(
  const arm_fir_decimate_instance_f32 * S,
  float32_t * pSrc,
  float32_t * pDst,
  uint32_t blockSize);


  /**
   * @brief  Initialization function for the floating-point FIR decimator.
   * @param[in,out] *S points to an instance of the floating-point FIR decimator structure.
   * @param[in] numTaps  number of coefficients in the filter.
   * @param[in] M  decimation factor.
   * @param[in] *pCoeffs points to the filter coefficients.
   * @param[in] *pState points to the state buffer.
   * @param[in] blockSize number of input samples to process per call.
   * @return    The function returns ARM_MATH_SUCCESS if initialization is successful or ARM_MATH_LENGTH_ERROR if
   * <code>blockSize</code> is not a multiple of <code>M</code>.
   */

  arm_status arm_fir_decimate_init_f32(
  arm_fir_decimate_instance_f32 * S,
  uint16_t numTaps,
  uint8_t M,
  float32_t * pCoeffs,
  float32_t * pState,
  uint32_t blockSize);

  /**
   * @brief Processing function for the Q15 FIR decimator.
   * @param[in] *S points to an instance of the Q15 FIR decimator structure.
   * @param[in] *pSrc points to the block of input data.
   * @param[out] *pDst points to the block of output data
   * @param[in] blockSize number of input samples to process per call.
   * @return none
   */

  void arm_fir_decimate_q15(
  const arm_fir_decimate_instance_q15 * S,
  q15_t * pSrc,
  q15_t * pDst,
  uint32_t blockSize);

  /**
   * @brief Processing function for the Q15 FIR decimator (fast variant) for Cortex-M3 and Cortex-M4.
   * @param[in] *S points to an instance of the Q15 FIR decimator structure.
   * @param[in] *pSrc points to the block of input data.
   * @param[out] *pDst points to the block of output data
   * @param[in] blockSize number of input samples to process per call.
   * @return none
   */

  void arm_fir_decimate_fast_q15(
  const arm_fir_decimate_instance_q15 * S,
  q15_t * pSrc,
  q15_t * pDst,
  uint32_t blockSize);



  /**
   * @brief  Initialization function for the Q15 FIR decimator.
   * @param[in,out] *S points to an instance of the Q15 FIR decimator structure.
   * @param[in] numTaps  number of coefficients in the filter.
   * @param[in] M  decimation factor.
   * @param[in] *pCoeffs points to the filter coefficients.
   * @param[in] *pState points to the state buffer.
   * @param[in] blockSize number of input samples to process per call.
   * @return    The function returns ARM_MATH_SUCCESS if initialization is successful or ARM_MATH_LENGTH_ERROR if
   * <code>blockSize</code> is not a multiple of <code>M</code>.
   */

  arm_status arm_fir_decimate_init_q15(
  arm_fir_decimate_instance_q15 * S,
  uint16_t numTaps,
  uint8_t M,
  q15_t * pCoeffs,
  q15_t * pState,
  uint32_t blockSize);

  /**
   * @brief Processing function for the Q31 FIR decimator.
   * @param[in] *S points to an instance of the Q31 FIR decimator structure.
   * @param[in] *pSrc points to the block of input data.
   * @param[out] *pDst points to the block of output data
   * @param[in] blockSize number of input samples to process per call.
   * @return none
   */

  void arm_fir_decimate_q31(
  const arm_fir_decimate_instance_q31 * S,
  q31_t * pSrc,
  q31_t * pDst,
  uint32_t blockSize);

  /**
   * @brief Processing function for the Q31 FIR decimator (fast variant) for Cortex-M3 and Cortex-M4.
   * @param[in] *S points to an instance of the Q31 FIR decimator structure.
   * @param[in] *pSrc points to the block of input data.
   * @param[out] *pDst points to the block of output data
   * @param[in] blockSize number of input samples to process per call.
   * @return none
   */

  void arm_fir_decimate_fast_q31(
  arm_fir_decimate_instance_q31 * S,
  q31_t * pSrc,
  q31_t * pDst,
  uint32_t blockSize);


  /**
   * @brief  Initialization function for the Q31 FIR decimator.
   * @param[in,out] *S points to an instance of the Q31 FIR decimator structure.
   * @param[in] numTaps  number of coefficients in the filter.
   * @param[in] M  decimation factor.
   * @param[in] *pCoeffs points to the filter coefficients.
   * @param[in] *pState points to the state buffer.
   * @param[in] blockSize number of input samples to process per call.
   * @return    The function returns ARM_MATH_SUCCESS if initialization is successful or ARM_MATH_LENGTH_ERROR if
   * <code>blockSize</code> is not a multiple of <code>M</code>.
   */

  arm_status arm_fir_decimate_init_q31(
  arm_fir_decimate_instance_q31 * S,
  uint16_t numTaps,
  uint8_t M,
  q31_t * pCoeffs,
  q31_t * pState,
  uint32_t blockSize);



  /**
   * @brief Instance structure for the Q15 FIR interpolator.
   */

  typedef struct
  {
    uint8_t L;                      /**< upsample factor. */
    uint16_t phaseLength;           /**< length of each polyphase filter component. */
    q15_t *pCoeffs;                 /**< points to the coefficient array. The array is of length L*phaseLength. */
    q15_t *pState;                  /**< points to the state variable array. The array is of length blockSize+phaseLength-1. */
  } arm_fir_interpolate_instance_q15;

  /**
   * @brief Instance structure for the Q31 FIR interpolator.
   */

  typedef struct
  {
    uint8_t L;                      /**< upsample factor. */
    uint16_t phaseLength;           /**< length of each polyphase filter component. */
    q31_t *pCoeffs;                  /**< points to the coefficient array. The array is of length L*phaseLength. */
    q31_t *pState;                   /**< points to the state variable array. The array is of length blockSize+phaseLength-1. */
  } arm_fir_interpolate_instance_q31;

  /**
   * @brief Instance structure for the floating-point FIR interpolator.
   */

  typedef struct
  {
    uint8_t L;                     /**< upsample factor. */
    uint16_t phaseLength;          /**< length of each polyphase filter component. */
    float32_t *pCoeffs;             /**< points to the coefficient array. The array is of length L*phaseLength. */
    float32_t *pState;              /**< points to the state variable array. The array is of length phaseLength+numTaps-1. */
  } arm_fir_interpolate_instance_f32;


  /**
   * @brief Processing function for the Q15 FIR interpolator.
   * @param[in] *S        points to an instance of the Q15 FIR interpolator structure.
   * @param[in] *pSrc     points to the block of input data.
   * @param[out] *pDst    points to the block of output data.
   * @param[in] blockSize number of input samples to process per call.
   * @return none.
   */

  void arm_fir_interpolate_q15(
  const arm_fir_interpolate_instance_q15 * S,
  q15_t * pSrc,
  q15_t * pDst,
  uint32_t blockSize);


  /**
   * @brief  Initialization function for the Q15 FIR interpolator.
   * @param[in,out] *S        points to an instance of the Q15 FIR interpolator structure.
   * @param[in]     L         upsample factor.
   * @param[in]     numTaps   number of filter coefficients in the filter.
   * @param[in]     *pCoeffs  points to the filter coefficient buffer.
   * @param[in]     *pState   points to the state buffer.
   * @param[in]     blockSize number of input samples to process per call.
   * @return        The function returns ARM_MATH_SUCCESS if initialization is successful or ARM_MATH_LENGTH_ERROR if
   * the filter length <code>numTaps</code> is not a multiple of the interpolation factor <code>L</code>.
   */

  arm_status arm_fir_interpolate_init_q15(
  arm_fir_interpolate_instance_q15 * S,
  uint8_t L,
  uint16_t numTaps,
  q15_t * pCoeffs,
  q15_t * pState,
  uint32_t blockSize);

  /**
   * @brief Processing function for the Q31 FIR interpolator.
   * @param[in] *S        points to an instance of the Q15 FIR interpolator structure.
   * @param[in] *pSrc     points to the block of input data.
   * @param[out] *pDst    points to the block of output data.
   * @param[in] blockSize number of input samples to process per call.
   * @return none.
   */

  void arm_fir_interpolate_q31(
  const arm_fir_interpolate_instance_q31 * S,
  q31_t * pSrc,
  q31_t * pDst,
  uint32_t blockSize);

  /**
   * @brief  Initialization function for the Q31 FIR interpolator.
   * @param[in,out] *S        points to an instance of the Q31 FIR interpolator structure.
   * @param[in]     L         upsample factor.
   * @param[in]     numTaps   number of filter coefficients in the filter.
   * @param[in]     *pCoeffs  points to the filter coefficient buffer.
   * @param[in]     *pState   points to the state buffer.
   * @param[in]     blockSize number of input samples to process per call.
   * @return        The function returns ARM_MATH_SUCCESS if initialization is successful or ARM_MATH_LENGTH_ERROR if
   * the filter length <code>numTaps</code> is not a multiple of the interpolation factor <code>L</code>.
   */

  arm_status arm_fir_interpolate_init_q31(
  arm_fir_interpolate_instance_q31 * S,
  uint8_t L,
  uint16_t numTaps,
  q31_t * pCoeffs,
  q31_t * pState,
  uint32_t blockSize);


  /**
   * @brief Processing function for the floating-point FIR interpolator.
   * @param[in] *S        points to an instance of the floating-point FIR interpolator structure.
   * @param[in] *pSrc     points to the block of input data.
   * @param[out] *pDst    points to the block of output data.
   * @param[in] blockSize number of input samples to process per call.
   * @return none.
   */

  void arm_fir_interpolate_f32(
  const arm_fir_interpolate_instance_f32 * S,
  float32_t * pSrc,
  float32_t * pDst,
  uint32_t blockSize);

  /**
   * @brief  Initialization function for the floating-point FIR interpolator.
   * @param[in,out] *S        points to an instance of the floating-point FIR interpolator structure.
   * @param[in]     L         upsample factor.
   * @param[in]     numTaps   number of filter coefficients in the filter.
   * @param[in]     *pCoeffs  points to the filter coefficient buffer.
   * @param[in]     *pState   points to the state buffer.
   * @param[in]     blockSize number of input samples to process per call.
   * @return        The function returns ARM_MATH_SUCCESS if initialization is successful or ARM_MATH_LENGTH_ERROR if
   * the filter length <code>numTaps</code> is not a multiple of the interpolation factor <code>L</code>.
   */

  arm_status arm_fir_interpolate_init_f32(
  arm_fir_interpolate_instance_f32 * S,
  uint8_t L,
  uint16_t numTaps,
  float32_t * pCoeffs,
  float32_t * pState,
  uint32_t blockSize);

  /**
   * @brief Instance structure for the high precision Q31 Biquad cascade filter.
   */

  typedef struct
  {
    uint8_t numStages;       /**< number of 2nd order stages in the filter.  Overall order is 2*numStages. */
    q63_t *pState;           /**< points to the array of state coefficients.  The array is of length 4*numStages. */
    q31_t *pCoeffs;          /**< points to the array of coefficients.  The array is of length 5*numStages. */
    uint8_t postShift;       /**< additional shift, in bits, applied to each output sample. */

  } arm_biquad_cas_df1_32x64_ins_q31;


  /**
   * @param[in]  *S        points to an instance of the high precision Q31 Biquad cascade filter structure.
   * @param[in]  *pSrc     points to the block of input data.
   * @param[out] *pDst     points to the block of output data
   * @param[in]  blockSize number of samples to process.
   * @return none.
   */

  void arm_biquad_cas_df1_32x64_q31(
  const arm_biquad_cas_df1_32x64_ins_q31 * S,
  q31_t * pSrc,
  q31_t * pDst,
  uint32_t blockSize);