jaseg/st-cmsis-core-lowfat
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Official ARM version: v5.6.0

Browse source
This commit is contained in:
rihab kouki 2020-07-28 11:24:49 +01:00
parent 9f95ff5b6b
commit 96d6da4e25
2939 changed files with 339304 additions and 113320 deletions
Download patch file Download diff file Expand all files Collapse all files

97
DSP/Source/BasicMathFunctions/arm_add_q7.c
View file

@ -3,13 +3,13 @@
* Title: arm_add_q7.c
* Description: Q7 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
*
@ -29,94 +29,81 @@
#include "arm_math.h"
/**
* @ingroup groupMath
@ingroup groupMath
*/
/**
* @addtogroup BasicAdd
* @{
@addtogroup BasicAdd
@{
*/
/**
* @brief Q7 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.
*
* <b>Scaling and Overflow Behavior:</b>
* \par
* The function uses saturating arithmetic.
* Results outside of the allowable Q7 range [0x80 0x7F] will be saturated.
@brief Q7 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
@par Scaling and Overflow Behavior
The function uses saturating arithmetic.
Results outside of the allowable Q7 range [0x80 0x7F] are saturated.
*/
void arm_add_q7(
q7_t * pSrcA,
q7_t * pSrcB,
q7_t * pDst,
uint32_t blockSize)
const q7_t * pSrcA,
const q7_t * pSrcB,
q7_t * pDst,
uint32_t blockSize)
{
uint32_t blkCnt; /* loop counter */
uint32_t blkCnt; /* Loop counter */
#if defined (ARM_MATH_DSP)
#if defined (ARM_MATH_LOOPUNROLL)
/* Run the below code for Cortex-M4 and Cortex-M3 */
/*loop Unrolling */
/* 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. */
*__SIMD32(pDst)++ = __QADD8(*__SIMD32(pSrcA)++, *__SIMD32(pSrcB)++);
/* Decrement the loop counter */
#if defined (ARM_MATH_DSP)
/* Add and store result in destination buffer (4 samples at a time). */
write_q7x4_ia (&pDst, __QADD8 (read_q7x4_ia ((q7_t **) &pSrcA), read_q7x4_ia ((q7_t **) &pSrcB)));
#else
*pDst++ = (q7_t) __SSAT ((q15_t) *pSrcA++ + *pSrcB++, 8);
*pDst++ = (q7_t) __SSAT ((q15_t) *pSrcA++ + *pSrcB++, 8);
*pDst++ = (q7_t) __SSAT ((q15_t) *pSrcA++ + *pSrcB++, 8);
*pDst++ = (q7_t) __SSAT ((q15_t) *pSrcA++ + *pSrcB++, 8);
#endif
/* 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;
while (blkCnt > 0U)
{
/* C = A + B */
/* Add and then store the results in the destination buffer. */
*pDst++ = (q7_t) __SSAT(*pSrcA++ + *pSrcB++, 8);
/* Decrement the loop counter */
blkCnt--;
}
#else
/* Run the below code for Cortex-M0 */
/* Initialize blkCnt with number of samples */
blkCnt = blockSize;
#endif /* #if defined (ARM_MATH_LOOPUNROLL) */
while (blkCnt > 0U)
{
/* C = A + B */
/* Add and then store the results in the destination buffer. */
*pDst++ = (q7_t) __SSAT((q15_t) * pSrcA++ + *pSrcB++, 8);
/* Decrement the loop counter */
/* Add and store result in destination buffer. */
*pDst++ = (q7_t) __SSAT((q15_t) *pSrcA++ + *pSrcB++, 8);
/* Decrement loop counter */
blkCnt--;
}
#endif /* #if defined (ARM_MATH_DSP) */
}
/**
* @} end of BasicAdd group
@} end of BasicAdd group
*/