/* ----------------------------------------------------------------------
 * Project:      CMSIS DSP Library
 * Title:        arm_negate_q15.c
 * Description:  Negates Q15 vectors
 *
 * $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 groupMath
 */

/**
 * @addtogroup negate
 * @{
 */

/**
 * @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.
 *
 * \par Conditions for optimum performance
 *  Input and output buffers should be aligned by 32-bit
 *
 *
 * <b>Scaling and Overflow Behavior:</b>
 * \par
 * The function uses saturating arithmetic.
 * The Q15 value -1 (0x8000) will be saturated to the maximum allowable positive value 0x7FFF.
 */

void arm_negate_q15(
  q15_t * pSrc,
  q15_t * pDst,
  uint32_t blockSize)
{
  uint32_t blkCnt;                               /* loop counter */
  q15_t in;

#if defined (ARM_MATH_DSP)

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

  q31_t in1, in2;                                /* Temporary variables */


  /*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 */
    /* Read two inputs at a time */
    in1 = _SIMD32_OFFSET(pSrc);
    in2 = _SIMD32_OFFSET(pSrc + 2);

    /* negate two samples at a time */
    in1 = __QSUB16(0, in1);

    /* negate two samples at a time */
    in2 = __QSUB16(0, in2);

    /* store the result to destination 2 samples at a time */
    _SIMD32_OFFSET(pDst) = in1;
    /* store the result to destination 2 samples at a time */
    _SIMD32_OFFSET(pDst + 2) = in2;


    /* update pointers to process next samples */
    pSrc += 4u;
    pDst += 4u;

    /* 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 */

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

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

  while (blkCnt > 0u)
  {
    /* C = -A */
    /* Negate and then store the result in the destination buffer. */
    in = *pSrc++;
    *pDst++ = (in == (q15_t) 0x8000) ? 0x7fff : -in;

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

/**
 * @} end of negate group
 */