Official ARM version: v5.6.0
This commit is contained in:
rihab kouki
parent
9f95ff5b6b
commit
96d6da4e25
2939 changed files with 339304 additions and 113320 deletions
|
|
@ -3,13 +3,13 @@
|
|||
* Title: arm_negate_f32.c
|
||||
* Description: Negates floating-point vectors
|
||||
*
|
||||
* $Date: 27. January 2017
|
||||
* $Revision: V.1.5.1
|
||||
* $Date: 18. March 2019
|
||||
* $Revision: V1.6.0
|
||||
*
|
||||
* Target Processor: Cortex-M cores
|
||||
* -------------------------------------------------------------------- */
|
||||
/*
|
||||
* Copyright (C) 2010-2017 ARM Limited or its affiliates. All rights reserved.
|
||||
* Copyright (C) 2010-2019 ARM Limited or its affiliates. All rights reserved.
|
||||
*
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*
|
||||
|
|
@ -29,106 +29,117 @@
|
|||
#include "arm_math.h"
|
||||
|
||||
/**
|
||||
* @ingroup groupMath
|
||||
@ingroup groupMath
|
||||
*/
|
||||
|
||||
/**
|
||||
* @defgroup negate Vector Negate
|
||||
*
|
||||
* Negates the elements of a vector.
|
||||
*
|
||||
* <pre>
|
||||
* pDst[n] = -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.
|
||||
@defgroup BasicNegate Vector Negate
|
||||
|
||||
Negates the elements of a vector.
|
||||
|
||||
<pre>
|
||||
pDst[n] = -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 negate
|
||||
* @{
|
||||
@addtogroup BasicNegate
|
||||
@{
|
||||
*/
|
||||
|
||||
/**
|
||||
* @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.
|
||||
@brief Negates the elements of a floating-point vector.
|
||||
@param[in] pSrc points to input vector.
|
||||
@param[out] pDst points to output vector.
|
||||
@param[in] blockSize number of samples in each vector.
|
||||
@return none
|
||||
*/
|
||||
|
||||
void arm_negate_f32(
|
||||
float32_t * pSrc,
|
||||
float32_t * pDst,
|
||||
uint32_t blockSize)
|
||||
const float32_t * pSrc,
|
||||
float32_t * pDst,
|
||||
uint32_t blockSize)
|
||||
{
|
||||
uint32_t blkCnt; /* loop counter */
|
||||
uint32_t blkCnt; /* Loop counter */
|
||||
|
||||
#if defined(ARM_MATH_NEON_EXPERIMENTAL)
|
||||
float32x4_t vec1;
|
||||
float32x4_t res;
|
||||
|
||||
#if defined (ARM_MATH_DSP)
|
||||
/* Compute 4 outputs at a time */
|
||||
blkCnt = blockSize >> 2U;
|
||||
|
||||
/* Run the below code for Cortex-M4 and Cortex-M3 */
|
||||
float32_t in1, in2, in3, in4; /* temporary variables */
|
||||
while (blkCnt > 0U)
|
||||
{
|
||||
/* C = -A */
|
||||
|
||||
/*loop Unrolling */
|
||||
blkCnt = blockSize >> 2U;
|
||||
/* Negate and then store the results in the destination buffer. */
|
||||
vec1 = vld1q_f32(pSrc);
|
||||
res = vnegq_f32(vec1);
|
||||
vst1q_f32(pDst, res);
|
||||
|
||||
/* 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)
|
||||
{
|
||||
/* read inputs from source */
|
||||
in1 = *pSrc;
|
||||
in2 = *(pSrc + 1);
|
||||
in3 = *(pSrc + 2);
|
||||
in4 = *(pSrc + 3);
|
||||
/* Increment pointers */
|
||||
pSrc += 4;
|
||||
pDst += 4;
|
||||
|
||||
/* Decrement the loop counter */
|
||||
blkCnt--;
|
||||
}
|
||||
|
||||
/* negate the input */
|
||||
in1 = -in1;
|
||||
in2 = -in2;
|
||||
in3 = -in3;
|
||||
in4 = -in4;
|
||||
|
||||
/* store the result to destination */
|
||||
*pDst = in1;
|
||||
*(pDst + 1) = in2;
|
||||
*(pDst + 2) = in3;
|
||||
*(pDst + 3) = in4;
|
||||
|
||||
/* 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;
|
||||
/* Tail */
|
||||
blkCnt = blockSize & 0x3;
|
||||
|
||||
#else
|
||||
#if defined (ARM_MATH_LOOPUNROLL)
|
||||
|
||||
/* Run the below code for Cortex-M0 */
|
||||
|
||||
/* Initialize blkCnt with number of samples */
|
||||
blkCnt = blockSize;
|
||||
|
||||
#endif /* #if defined (ARM_MATH_DSP) */
|
||||
/* Loop unrolling: Compute 4 outputs at a time */
|
||||
blkCnt = blockSize >> 2U;
|
||||
|
||||
while (blkCnt > 0U)
|
||||
{
|
||||
/* C = -A */
|
||||
/* Negate and then store the results in the destination buffer. */
|
||||
|
||||
/* Negate and store result in destination buffer. */
|
||||
*pDst++ = -*pSrc++;
|
||||
|
||||
/* Decrement the loop counter */
|
||||
*pDst++ = -*pSrc++;
|
||||
|
||||
*pDst++ = -*pSrc++;
|
||||
|
||||
*pDst++ = -*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_EXPERIMENTAL) */
|
||||
|
||||
while (blkCnt > 0U)
|
||||
{
|
||||
/* C = -A */
|
||||
|
||||
/* Negate and store result in destination buffer. */
|
||||
*pDst++ = -*pSrc++;
|
||||
|
||||
/* Decrement loop counter */
|
||||
blkCnt--;
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
/**
|
||||
* @} end of negate group
|
||||
@} end of BasicNegate group
|
||||
*/
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue