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_add_f32.c
|
||||
* Description: Floating-point vector addition
|
||||
*
|
||||
* $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
|
||||
*
|
||||
|
|
@ -29,110 +29,117 @@
|
|||
#include "arm_math.h"
|
||||
|
||||
/**
|
||||
* @ingroup groupMath
|
||||
@ingroup groupMath
|
||||
*/
|
||||
|
||||
/**
|
||||
* @defgroup BasicAdd Vector Addition
|
||||
*
|
||||
* Element-by-element addition of two vectors.
|
||||
*
|
||||
* <pre>
|
||||
* pDst[n] = pSrcA[n] + pSrcB[n], 0 <= n < blockSize.
|
||||
* </pre>
|
||||
*
|
||||
* There are separate functions for floating-point, Q7, Q15, and Q31 data types.
|
||||
@defgroup BasicAdd Vector Addition
|
||||
|
||||
Element-by-element addition of two vectors.
|
||||
|
||||
<pre>
|
||||
pDst[n] = pSrcA[n] + pSrcB[n], 0 <= n < blockSize.
|
||||
</pre>
|
||||
|
||||
There are separate functions for floating-point, Q7, Q15, and Q31 data types.
|
||||
*/
|
||||
|
||||
/**
|
||||
* @addtogroup BasicAdd
|
||||
* @{
|
||||
@addtogroup BasicAdd
|
||||
@{
|
||||
*/
|
||||
|
||||
/**
|
||||
* @brief Floating-point vector addition.
|
||||
* @param[in] *pSrcA points to the first input vector
|
||||
* @param[in] *pSrcB points to the second input vector
|
||||
* @param[out] *pDst points to the output vector
|
||||
* @param[in] blockSize number of samples in each vector
|
||||
* @return none.
|
||||
@brief Floating-point vector addition.
|
||||
@param[in] pSrcA points to first input vector
|
||||
@param[in] pSrcB points to second input vector
|
||||
@param[out] pDst points to output vector
|
||||
@param[in] blockSize number of samples in each vector
|
||||
@return none
|
||||
*/
|
||||
|
||||
void arm_add_f32(
|
||||
float32_t * pSrcA,
|
||||
float32_t * pSrcB,
|
||||
float32_t * pDst,
|
||||
uint32_t blockSize)
|
||||
const float32_t * pSrcA,
|
||||
const float32_t * pSrcB,
|
||||
float32_t * pDst,
|
||||
uint32_t blockSize)
|
||||
{
|
||||
uint32_t blkCnt; /* loop counter */
|
||||
uint32_t blkCnt; /* Loop counter */
|
||||
|
||||
#if defined (ARM_MATH_DSP)
|
||||
#if defined(ARM_MATH_NEON)
|
||||
float32x4_t vec1;
|
||||
float32x4_t vec2;
|
||||
float32x4_t res;
|
||||
|
||||
/* Run the below code for Cortex-M4 and Cortex-M3 */
|
||||
float32_t inA1, inA2, inA3, inA4; /* temporary input variabels */
|
||||
float32_t inB1, inB2, inB3, inB4; /* temporary input variables */
|
||||
/* Compute 4 outputs at a time */
|
||||
blkCnt = blockSize >> 2U;
|
||||
|
||||
/*loop Unrolling */
|
||||
while (blkCnt > 0U)
|
||||
{
|
||||
/* C = A + B */
|
||||
|
||||
/* Add and then store the results in the destination buffer. */
|
||||
vec1 = vld1q_f32(pSrcA);
|
||||
vec2 = vld1q_f32(pSrcB);
|
||||
res = vaddq_f32(vec1, vec2);
|
||||
vst1q_f32(pDst, res);
|
||||
|
||||
/* Increment pointers */
|
||||
pSrcA += 4;
|
||||
pSrcB += 4;
|
||||
pDst += 4;
|
||||
|
||||
/* Decrement the loop counter */
|
||||
blkCnt--;
|
||||
}
|
||||
|
||||
/* Tail */
|
||||
blkCnt = blockSize & 0x3;
|
||||
|
||||
#else
|
||||
#if defined (ARM_MATH_LOOPUNROLL)
|
||||
|
||||
/* Loop unrolling: Compute 4 outputs at a time */
|
||||
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 + B */
|
||||
/* Add and then store the results in the destination buffer. */
|
||||
|
||||
/* read four inputs from sourceA and four inputs from sourceB */
|
||||
inA1 = *pSrcA;
|
||||
inB1 = *pSrcB;
|
||||
inA2 = *(pSrcA + 1);
|
||||
inB2 = *(pSrcB + 1);
|
||||
inA3 = *(pSrcA + 2);
|
||||
inB3 = *(pSrcB + 2);
|
||||
inA4 = *(pSrcA + 3);
|
||||
inB4 = *(pSrcB + 3);
|
||||
/* Add and store result in destination buffer. */
|
||||
*pDst++ = (*pSrcA++) + (*pSrcB++);
|
||||
*pDst++ = (*pSrcA++) + (*pSrcB++);
|
||||
*pDst++ = (*pSrcA++) + (*pSrcB++);
|
||||
*pDst++ = (*pSrcA++) + (*pSrcB++);
|
||||
|
||||
/* C = A + B */
|
||||
/* add and store result to destination */
|
||||
*pDst = inA1 + inB1;
|
||||
*(pDst + 1) = inA2 + inB2;
|
||||
*(pDst + 2) = inA3 + inB3;
|
||||
*(pDst + 3) = inA4 + inB4;
|
||||
|
||||
/* update pointers to process next samples */
|
||||
pSrcA += 4U;
|
||||
pSrcB += 4U;
|
||||
pDst += 4U;
|
||||
|
||||
|
||||
/* Decrement the loop counter */
|
||||
/* Decrement loop counter */
|
||||
blkCnt--;
|
||||
}
|
||||
|
||||
/* If the blockSize is not a multiple of 4, compute any remaining output samples here.
|
||||
** No loop unrolling is used. */
|
||||
/* Loop unrolling: Compute remaining outputs */
|
||||
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) */
|
||||
#endif /* #if defined (ARM_MATH_LOOPUNROLL) */
|
||||
#endif /* #if defined(ARM_MATH_NEON) */
|
||||
|
||||
while (blkCnt > 0U)
|
||||
{
|
||||
/* C = A + B */
|
||||
/* Add and then store the results in the destination buffer. */
|
||||
|
||||
/* Add and store result in destination buffer. */
|
||||
*pDst++ = (*pSrcA++) + (*pSrcB++);
|
||||
|
||||
/* Decrement the loop counter */
|
||||
/* Decrement loop counter */
|
||||
blkCnt--;
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
/**
|
||||
* @} end of BasicAdd group
|
||||
@} end of BasicAdd group
|
||||
*/
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue