353 lines
8.4 KiB
C
353 lines
8.4 KiB
C
<<<<<<< HEAD
|
|
/* ----------------------------------------------------------------------
|
|
* Project: CMSIS DSP Library
|
|
* Title: arm_abs_f32.c
|
|
* Description: Floating-point vector absolute value
|
|
*
|
|
* $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"
|
|
#include <math.h>
|
|
|
|
/**
|
|
@ingroup groupMath
|
|
*/
|
|
|
|
/**
|
|
@defgroup BasicAbs Vector Absolute Value
|
|
|
|
Computes the absolute value of a vector on an element-by-element basis.
|
|
|
|
<pre>
|
|
pDst[n] = abs(pSrc[n]), 0 <= n < blockSize.
|
|
</pre>
|
|
|
|
The functions support in-place computation allowing the source and
|
|
destination pointers to reference the same memory buffer.
|
|
There are separate functions for floating-point, Q7, Q15, and Q31 data types.
|
|
*/
|
|
|
|
/**
|
|
@addtogroup BasicAbs
|
|
@{
|
|
*/
|
|
|
|
/**
|
|
@brief Floating-point vector absolute value.
|
|
@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
|
|
*/
|
|
|
|
|
|
#if defined(ARM_MATH_MVEF) && !defined(ARM_MATH_AUTOVECTORIZE)
|
|
|
|
#include "arm_helium_utils.h"
|
|
|
|
void arm_abs_f32(
|
|
const float32_t * pSrc,
|
|
float32_t * pDst,
|
|
uint32_t blockSize)
|
|
{
|
|
uint32_t blkCnt; /* Loop counter */
|
|
f32x4_t vec1;
|
|
f32x4_t res;
|
|
|
|
|
|
/* Compute 4 outputs at a time */
|
|
blkCnt = blockSize >> 2U;
|
|
|
|
while (blkCnt > 0U)
|
|
{
|
|
/* C = |A| */
|
|
|
|
/* Calculate absolute values and then store the results in the destination buffer. */
|
|
vec1 = vld1q(pSrc);
|
|
res = vabsq(vec1);
|
|
vst1q(pDst, res);
|
|
|
|
/* Increment pointers */
|
|
pSrc += 4;
|
|
pDst += 4;
|
|
|
|
/* Decrement the loop counter */
|
|
blkCnt--;
|
|
}
|
|
|
|
/* Tail */
|
|
blkCnt = blockSize & 0x3;
|
|
|
|
|
|
if (blkCnt > 0U)
|
|
{
|
|
/* C = |A| */
|
|
mve_pred16_t p0 = vctp32q(blkCnt);
|
|
vec1 = vld1q(pSrc);
|
|
vstrwq_p(pDst, vabsq(vec1), p0);
|
|
}
|
|
|
|
}
|
|
|
|
#else
|
|
void arm_abs_f32(
|
|
const float32_t * pSrc,
|
|
float32_t * pDst,
|
|
uint32_t blockSize)
|
|
{
|
|
uint32_t blkCnt; /* Loop counter */
|
|
|
|
#if defined(ARM_MATH_NEON) && !defined(ARM_MATH_AUTOVECTORIZE)
|
|
f32x4_t vec1;
|
|
f32x4_t res;
|
|
|
|
/* Compute 4 outputs at a time */
|
|
blkCnt = blockSize >> 2U;
|
|
|
|
while (blkCnt > 0U)
|
|
{
|
|
/* C = |A| */
|
|
|
|
/* Calculate absolute values and then store the results in the destination buffer. */
|
|
vec1 = vld1q_f32(pSrc);
|
|
res = vabsq_f32(vec1);
|
|
vst1q_f32(pDst, res);
|
|
|
|
/* Increment pointers */
|
|
pSrc += 4;
|
|
pDst += 4;
|
|
|
|
/* Decrement the loop counter */
|
|
blkCnt--;
|
|
}
|
|
|
|
/* Tail */
|
|
blkCnt = blockSize & 0x3;
|
|
|
|
#else
|
|
#if defined (ARM_MATH_LOOPUNROLL) && !defined(ARM_MATH_AUTOVECTORIZE)
|
|
|
|
/* Loop unrolling: Compute 4 outputs at a time */
|
|
blkCnt = blockSize >> 2U;
|
|
|
|
while (blkCnt > 0U)
|
|
{
|
|
/* C = |A| */
|
|
|
|
/* Calculate absolute and store result in destination buffer. */
|
|
*pDst++ = fabsf(*pSrc++);
|
|
|
|
*pDst++ = fabsf(*pSrc++);
|
|
|
|
*pDst++ = fabsf(*pSrc++);
|
|
|
|
*pDst++ = fabsf(*pSrc++);
|
|
|
|
/* 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) */
|
|
#endif /* #if defined(ARM_MATH_NEON) */
|
|
|
|
while (blkCnt > 0U)
|
|
{
|
|
/* C = |A| */
|
|
|
|
/* Calculate absolute and store result in destination buffer. */
|
|
*pDst++ = fabsf(*pSrc++);
|
|
|
|
/* Decrement loop counter */
|
|
blkCnt--;
|
|
}
|
|
|
|
}
|
|
#endif /* defined(ARM_MATH_MVEF) && !defined(ARM_MATH_AUTOVECTORIZE) */
|
|
/**
|
|
@} end of BasicAbs group
|
|
*/
|
|
=======
|
|
/* ----------------------------------------------------------------------
|
|
* Project: CMSIS DSP Library
|
|
* Title: arm_abs_f32.c
|
|
* Description: Floating-point vector absolute value
|
|
*
|
|
* $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"
|
|
#include <math.h>
|
|
|
|
/**
|
|
* @ingroup groupMath
|
|
*/
|
|
|
|
/**
|
|
* @defgroup BasicAbs Vector Absolute Value
|
|
*
|
|
* Computes the absolute value of a vector on an element-by-element basis.
|
|
*
|
|
* <pre>
|
|
* pDst[n] = abs(pSrc[n]), 0 <= n < blockSize.
|
|
* </pre>
|
|
*
|
|
* The functions support in-place computation allowing the source and
|
|
* destination pointers to reference the same memory buffer.
|
|
* There are separate functions for floating-point, Q7, Q15, and Q31 data types.
|
|
*/
|
|
|
|
/**
|
|
* @addtogroup BasicAbs
|
|
* @{
|
|
*/
|
|
|
|
/**
|
|
* @brief Floating-point vector absolute value.
|
|
* @param[in] *pSrc points to the input buffer
|
|
* @param[out] *pDst points to the output buffer
|
|
* @param[in] blockSize number of samples in each vector
|
|
* @return none.
|
|
*/
|
|
|
|
void arm_abs_f32(
|
|
float32_t * pSrc,
|
|
float32_t * pDst,
|
|
uint32_t blockSize)
|
|
{
|
|
uint32_t blkCnt; /* loop counter */
|
|
|
|
#if defined (ARM_MATH_DSP)
|
|
|
|
/* Run the below code for Cortex-M4 and Cortex-M3 */
|
|
float32_t in1, in2, in3, in4; /* 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| */
|
|
/* Calculate absolute and then store the results in the destination buffer. */
|
|
/* read sample from source */
|
|
in1 = *pSrc;
|
|
in2 = *(pSrc + 1);
|
|
in3 = *(pSrc + 2);
|
|
|
|
/* find absolute value */
|
|
in1 = fabsf(in1);
|
|
|
|
/* read sample from source */
|
|
in4 = *(pSrc + 3);
|
|
|
|
/* find absolute value */
|
|
in2 = fabsf(in2);
|
|
|
|
/* read sample from source */
|
|
*pDst = in1;
|
|
|
|
/* find absolute value */
|
|
in3 = fabsf(in3);
|
|
|
|
/* find absolute value */
|
|
in4 = fabsf(in4);
|
|
|
|
/* store result to destination */
|
|
*(pDst + 1) = in2;
|
|
|
|
/* store result to destination */
|
|
*(pDst + 2) = in3;
|
|
|
|
/* store result to destination */
|
|
*(pDst + 3) = in4;
|
|
|
|
|
|
/* Update source pointer to process next sampels */
|
|
pSrc += 4U;
|
|
|
|
/* Update destination pointer to process next sampels */
|
|
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| */
|
|
/* Calculate absolute and then store the results in the destination buffer. */
|
|
*pDst++ = fabsf(*pSrc++);
|
|
|
|
/* Decrement the loop counter */
|
|
blkCnt--;
|
|
}
|
|
}
|
|
|
|
/**
|
|
* @} end of BasicAbs group
|
|
*/
|
|
>>>>>>> upper
|