/* ----------------------------------------------------------------------
 * Project:      CMSIS DSP Library
 * Title:        arm_rms_f32.c
 * Description:  Root mean square value of an array of F32 type
 *
 * $Date:        27. January 2017
 * $Revision:    V.1.5.1
 *
 * Target Processor: Cortex-M cores
 * -------------------------------------------------------------------- */
/*
 * Copyright (C) 2010-2017 ARM Limited or its affiliates. All rights reserved.
 *
 * SPDX-License-Identifier: Apache-2.0
 *
 * Licensed under the Apache License, Version 2.0 (the License); you may
 * not use this file except in compliance with the License.
 * You may obtain a copy of the License at
 *
 * www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an AS IS BASIS, WITHOUT
 * WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

#include "arm_math.h"

/**
 * @ingroup groupStats
 */

/**
 * @defgroup RMS Root mean square (RMS)
 *
 *
 * Calculates the Root Mean Sqaure of the elements in the input vector.
 * The underlying algorithm is used:
 *
 * <pre>
 * 	Result = sqrt(((pSrc[0] * pSrc[0] + pSrc[1] * pSrc[1] + ... + pSrc[blockSize-1] * pSrc[blockSize-1]) / blockSize));
 * </pre>
 *
 * There are separate functions for floating point, Q31, and Q15 data types.
 */

/**
 * @addtogroup RMS
 * @{
 */


/**
 * @brief Root Mean Square 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 rms value returned here
 * @return none.
 *
 */

void arm_rms_f32(
  float32_t * pSrc,
  uint32_t blockSize,
  float32_t * pResult)
{
  float32_t sum = 0.0f;                          /* Accumulator */
  float32_t in;                                  /* Tempoprary variable to store input value */
  uint32_t blkCnt;                               /* loop counter */

#if defined (ARM_MATH_DSP)
  /* Run the below code for Cortex-M4 and Cortex-M3 */

  /* 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 sum of the squares and then store the result in a temporary variable, sum  */
    in = *pSrc++;
    sum += in * in;
    in = *pSrc++;
    sum += in * in;
    in = *pSrc++;
    sum += in * in;
    in = *pSrc++;
    sum += 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;

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

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

#endif /* #if defined (ARM_MATH_DSP) */

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

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

  /* Compute Rms and store the result in the destination */
  arm_sqrt_f32(sum / (float32_t) blockSize, pResult);
}

/**
 * @} end of RMS group
 */