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_mean_f32.c
|
||||
* Description: Mean value of a floating-point vector
|
||||
*
|
||||
* $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
|
||||
*
|
||||
|
|
@ -29,82 +29,70 @@
|
|||
#include "arm_math.h"
|
||||
|
||||
/**
|
||||
* @ingroup groupStats
|
||||
@ingroup groupStats
|
||||
*/
|
||||
|
||||
/**
|
||||
* @defgroup mean Mean
|
||||
*
|
||||
* Calculates the mean of the input vector. Mean is defined as the average of the elements in the vector.
|
||||
* The underlying algorithm is used:
|
||||
*
|
||||
* <pre>
|
||||
* Result = (pSrc[0] + pSrc[1] + pSrc[2] + ... + pSrc[blockSize-1]) / blockSize;
|
||||
* </pre>
|
||||
*
|
||||
* There are separate functions for floating-point, Q31, Q15, and Q7 data types.
|
||||
@defgroup mean Mean
|
||||
|
||||
Calculates the mean of the input vector. Mean is defined as the average of the elements in the vector.
|
||||
The underlying algorithm is used:
|
||||
|
||||
<pre>
|
||||
Result = (pSrc[0] + pSrc[1] + pSrc[2] + ... + pSrc[blockSize-1]) / blockSize;
|
||||
</pre>
|
||||
|
||||
There are separate functions for floating-point, Q31, Q15, and Q7 data types.
|
||||
*/
|
||||
|
||||
/**
|
||||
* @addtogroup mean
|
||||
* @{
|
||||
@addtogroup mean
|
||||
@{
|
||||
*/
|
||||
|
||||
|
||||
/**
|
||||
* @brief Mean value of a floating-point vector.
|
||||
* @param[in] *pSrc points to the input vector
|
||||
* @param[in] blockSize length of the input vector
|
||||
* @param[out] *pResult mean value returned here
|
||||
* @return none.
|
||||
@brief Mean value of a floating-point vector.
|
||||
@param[in] pSrc points to the input vector.
|
||||
@param[in] blockSize number of samples in input vector.
|
||||
@param[out] pResult mean value returned here.
|
||||
@return none
|
||||
*/
|
||||
|
||||
#if defined(ARM_MATH_NEON_EXPERIMENTAL)
|
||||
void arm_mean_f32(
|
||||
float32_t * pSrc,
|
||||
const float32_t * pSrc,
|
||||
uint32_t blockSize,
|
||||
float32_t * pResult)
|
||||
{
|
||||
float32_t sum = 0.0f; /* Temporary result storage */
|
||||
uint32_t blkCnt; /* loop counter */
|
||||
float32x4_t sumV = vdupq_n_f32(0.0f); /* Temporary result storage */
|
||||
float32x2_t sumV2;
|
||||
|
||||
#if defined (ARM_MATH_DSP)
|
||||
/* Run the below code for Cortex-M4 and Cortex-M3 */
|
||||
uint32_t blkCnt; /* Loop counter */
|
||||
|
||||
float32_t in1, in2, in3, in4;
|
||||
float32x4_t inV;
|
||||
|
||||
/*loop Unrolling */
|
||||
blkCnt = blockSize >> 2U;
|
||||
|
||||
/* First part of the processing with loop unrolling. Compute 4 outputs at a time.
|
||||
/* Compute 4 outputs at a time.
|
||||
** a second loop below computes the remaining 1 to 3 samples. */
|
||||
while (blkCnt > 0U)
|
||||
{
|
||||
/* C = (A[0] + A[1] + A[2] + ... + A[blockSize-1]) */
|
||||
in1 = *pSrc++;
|
||||
in2 = *pSrc++;
|
||||
in3 = *pSrc++;
|
||||
in4 = *pSrc++;
|
||||
|
||||
sum += in1;
|
||||
sum += in2;
|
||||
sum += in3;
|
||||
sum += in4;
|
||||
|
||||
inV = vld1q_f32(pSrc);
|
||||
sumV = vaddq_f32(sumV, inV);
|
||||
|
||||
pSrc += 4;
|
||||
/* Decrement the loop counter */
|
||||
blkCnt--;
|
||||
}
|
||||
|
||||
sumV2 = vpadd_f32(vget_low_f32(sumV),vget_high_f32(sumV));
|
||||
sum = sumV2[0] + sumV2[1];
|
||||
|
||||
/* 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 */
|
||||
|
||||
/* Loop over blockSize number of values */
|
||||
blkCnt = blockSize;
|
||||
|
||||
#endif /* #if defined (ARM_MATH_DSP) */
|
||||
blkCnt = blockSize & 3;
|
||||
|
||||
while (blkCnt > 0U)
|
||||
{
|
||||
|
|
@ -119,7 +107,60 @@ void arm_mean_f32(
|
|||
/* Store the result to the destination */
|
||||
*pResult = sum / (float32_t) blockSize;
|
||||
}
|
||||
#else
|
||||
void arm_mean_f32(
|
||||
const float32_t * pSrc,
|
||||
uint32_t blockSize,
|
||||
float32_t * pResult)
|
||||
{
|
||||
uint32_t blkCnt; /* Loop counter */
|
||||
float32_t sum = 0.0f; /* Temporary result storage */
|
||||
|
||||
#if defined (ARM_MATH_LOOPUNROLL)
|
||||
|
||||
/* Loop unrolling: Compute 4 outputs at a time */
|
||||
blkCnt = blockSize >> 2U;
|
||||
|
||||
while (blkCnt > 0U)
|
||||
{
|
||||
/* C = (A[0] + A[1] + A[2] + ... + A[blockSize-1]) */
|
||||
sum += *pSrc++;
|
||||
|
||||
sum += *pSrc++;
|
||||
|
||||
sum += *pSrc++;
|
||||
|
||||
sum += *pSrc++;
|
||||
|
||||
/* Decrement the 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[0] + A[1] + A[2] + ... + A[blockSize-1]) */
|
||||
sum += *pSrc++;
|
||||
|
||||
/* Decrement loop counter */
|
||||
blkCnt--;
|
||||
}
|
||||
|
||||
/* C = (A[0] + A[1] + A[2] + ... + A[blockSize-1]) / blockSize */
|
||||
/* Store result to destination */
|
||||
*pResult = (sum / blockSize);
|
||||
}
|
||||
#endif /* #if defined(ARM_MATH_NEON) */
|
||||
|
||||
/**
|
||||
* @} end of mean group
|
||||
@} end of mean group
|
||||
*/
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue