299 lines
7.3 KiB
C
299 lines
7.3 KiB
C
<<<<<<< HEAD
|
|
/* ----------------------------------------------------------------------
|
|
* Project: CMSIS DSP Library
|
|
* Title: arm_negate_q31.c
|
|
* Description: Negates Q31 vectors
|
|
*
|
|
* $Date: 23 April 2021
|
|
* $Revision: V1.9.0
|
|
*
|
|
* Target Processor: Cortex-M and Cortex-A cores
|
|
* -------------------------------------------------------------------- */
|
|
/*
|
|
* Copyright (C) 2010-2021 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 "dsp/basic_math_functions.h"
|
|
|
|
/**
|
|
@ingroup groupMath
|
|
*/
|
|
|
|
/**
|
|
@addtogroup BasicNegate
|
|
@{
|
|
*/
|
|
|
|
/**
|
|
@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 each vector.
|
|
@return none
|
|
|
|
@par Scaling and Overflow Behavior
|
|
The function uses saturating arithmetic.
|
|
The Q31 value -1 (0x80000000) is saturated to the maximum allowable positive value 0x7FFFFFFF.
|
|
*/
|
|
|
|
#if defined(ARM_MATH_MVEI) && !defined(ARM_MATH_AUTOVECTORIZE)
|
|
|
|
#include "arm_helium_utils.h"
|
|
|
|
void arm_negate_q31(
|
|
const q31_t * pSrc,
|
|
q31_t * pDst,
|
|
uint32_t blockSize)
|
|
{
|
|
uint32_t blkCnt; /* loop counters */
|
|
q31x4_t vecSrc;
|
|
|
|
/* Compute 4 outputs at a time */
|
|
blkCnt = blockSize >> 2;
|
|
while (blkCnt > 0U)
|
|
{
|
|
/*
|
|
* C = -A
|
|
* Negate and then store the results in the destination buffer.
|
|
*/
|
|
vecSrc = vld1q(pSrc);
|
|
vst1q(pDst, vqnegq(vecSrc));
|
|
/*
|
|
* Decrement the blockSize loop counter
|
|
*/
|
|
blkCnt--;
|
|
/*
|
|
* advance vector source and destination pointers
|
|
*/
|
|
pSrc += 4;
|
|
pDst += 4;
|
|
}
|
|
/*
|
|
* tail
|
|
*/
|
|
blkCnt = blockSize & 3;
|
|
if (blkCnt > 0U)
|
|
{
|
|
mve_pred16_t p0 = vctp32q(blkCnt);
|
|
vecSrc = vld1q(pSrc);
|
|
vstrwq_p(pDst, vqnegq(vecSrc), p0);
|
|
}
|
|
}
|
|
|
|
#else
|
|
void arm_negate_q31(
|
|
const q31_t * pSrc,
|
|
q31_t * pDst,
|
|
uint32_t blockSize)
|
|
{
|
|
uint32_t blkCnt; /* Loop counter */
|
|
q31_t in; /* Temporary input variable */
|
|
|
|
#if defined (ARM_MATH_LOOPUNROLL)
|
|
|
|
/* Loop unrolling: Compute 4 outputs at a time */
|
|
blkCnt = blockSize >> 2U;
|
|
|
|
while (blkCnt > 0U)
|
|
{
|
|
/* C = -A */
|
|
|
|
/* Negate and store result in destination buffer. */
|
|
in = *pSrc++;
|
|
#if defined (ARM_MATH_DSP)
|
|
*pDst++ = __QSUB(0, in);
|
|
#else
|
|
*pDst++ = (in == INT32_MIN) ? INT32_MAX : -in;
|
|
#endif
|
|
|
|
in = *pSrc++;
|
|
#if defined (ARM_MATH_DSP)
|
|
*pDst++ = __QSUB(0, in);
|
|
#else
|
|
*pDst++ = (in == INT32_MIN) ? INT32_MAX : -in;
|
|
#endif
|
|
|
|
in = *pSrc++;
|
|
#if defined (ARM_MATH_DSP)
|
|
*pDst++ = __QSUB(0, in);
|
|
#else
|
|
*pDst++ = (in == INT32_MIN) ? INT32_MAX : -in;
|
|
#endif
|
|
|
|
in = *pSrc++;
|
|
#if defined (ARM_MATH_DSP)
|
|
*pDst++ = __QSUB(0, in);
|
|
#else
|
|
*pDst++ = (in == INT32_MIN) ? INT32_MAX : -in;
|
|
#endif
|
|
|
|
/* Decrement loop counter */
|
|
blkCnt--;
|
|
}
|
|
|
|
/* Loop unrolling: Compute remaining outputs */
|
|
blkCnt = blockSize % 0x4U;
|
|
|
|
#else
|
|
|
|
/* Initialize blkCnt with number of samples */
|
|
blkCnt = blockSize;
|
|
|
|
#endif /* #if defined (ARM_MATH_LOOPUNROLL) */
|
|
|
|
while (blkCnt > 0U)
|
|
{
|
|
/* C = -A */
|
|
|
|
/* Negate and store result in destination buffer. */
|
|
in = *pSrc++;
|
|
#if defined (ARM_MATH_DSP)
|
|
*pDst++ = __QSUB(0, in);
|
|
#else
|
|
*pDst++ = (in == INT32_MIN) ? INT32_MAX : -in;
|
|
#endif
|
|
|
|
/* Decrement loop counter */
|
|
blkCnt--;
|
|
}
|
|
|
|
}
|
|
#endif /* defined(ARM_MATH_MVEI) */
|
|
|
|
/**
|
|
@} end of BasicNegate group
|
|
*/
|
|
=======
|
|
/* ----------------------------------------------------------------------
|
|
* Project: CMSIS DSP Library
|
|
* Title: arm_negate_q31.c
|
|
* Description: Negates Q31 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 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.
|
|
*
|
|
* <b>Scaling and Overflow Behavior:</b>
|
|
* \par
|
|
* The function uses saturating arithmetic.
|
|
* The Q31 value -1 (0x80000000) will be saturated to the maximum allowable positive value 0x7FFFFFFF.
|
|
*/
|
|
|
|
void arm_negate_q31(
|
|
q31_t * pSrc,
|
|
q31_t * pDst,
|
|
uint32_t blockSize)
|
|
{
|
|
q31_t in; /* Temporary variable */
|
|
uint32_t blkCnt; /* loop counter */
|
|
|
|
#if defined (ARM_MATH_DSP)
|
|
|
|
/* Run the below code for Cortex-M4 and Cortex-M3 */
|
|
q31_t in1, in2, in3, in4;
|
|
|
|
/*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 */
|
|
/* Negate and then store the results in the destination buffer. */
|
|
in1 = *pSrc++;
|
|
in2 = *pSrc++;
|
|
in3 = *pSrc++;
|
|
in4 = *pSrc++;
|
|
|
|
*pDst++ = __QSUB(0, in1);
|
|
*pDst++ = __QSUB(0, in2);
|
|
*pDst++ = __QSUB(0, in3);
|
|
*pDst++ = __QSUB(0, in4);
|
|
|
|
/* 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 == INT32_MIN) ? INT32_MAX : -in;
|
|
|
|
/* Decrement the loop counter */
|
|
blkCnt--;
|
|
}
|
|
}
|
|
|
|
/**
|
|
* @} end of negate group
|
|
*/
|
|
>>>>>>> upper
|