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
|
|
@ -1,15 +1,15 @@
|
|||
/* ----------------------------------------------------------------------
|
||||
* Project: CMSIS DSP Library
|
||||
* Title: arm_std_q31.c
|
||||
* Description: Standard deviation of an array of Q31 type.
|
||||
* Description: Standard deviation of the elements of a Q31 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
|
||||
*
|
||||
|
|
@ -29,141 +29,119 @@
|
|||
#include "arm_math.h"
|
||||
|
||||
/**
|
||||
* @ingroup groupStats
|
||||
@ingroup groupStats
|
||||
*/
|
||||
|
||||
/**
|
||||
* @addtogroup STD
|
||||
* @{
|
||||
@addtogroup STD
|
||||
@{
|
||||
*/
|
||||
|
||||
/**
|
||||
* @brief Standard deviation of the elements of a Q31 vector.
|
||||
* @param[in] *pSrc points to the input vector
|
||||
* @param[in] blockSize length of the input vector
|
||||
* @param[out] *pResult standard deviation value returned here
|
||||
* @return none.
|
||||
* @details
|
||||
* <b>Scaling and Overflow Behavior:</b>
|
||||
*
|
||||
*\par
|
||||
* The function is implemented using an internal 64-bit accumulator.
|
||||
* The input is represented in 1.31 format, which is then downshifted by 8 bits
|
||||
* which yields 1.23, and intermediate multiplication yields a 2.46 format.
|
||||
* The accumulator maintains full precision of the intermediate multiplication results,
|
||||
* but provides only a 16 guard bits.
|
||||
* There is no saturation on intermediate additions.
|
||||
* If the accumulator overflows it wraps around and distorts the result.
|
||||
* In order to avoid overflows completely the input signal must be scaled down by
|
||||
* log2(blockSize)-8 bits, as a total of blockSize additions are performed internally.
|
||||
* After division, internal variables should be Q18.46
|
||||
* Finally, the 18.46 accumulator is right shifted by 15 bits to yield a 1.31 format value.
|
||||
*
|
||||
@brief Standard deviation of the elements of a Q31 vector.
|
||||
@param[in] pSrc points to the input vector.
|
||||
@param[in] blockSize number of samples in input vector.
|
||||
@param[out] pResult standard deviation value returned here.
|
||||
@return none
|
||||
|
||||
@par Scaling and Overflow Behavior
|
||||
The function is implemented using an internal 64-bit accumulator.
|
||||
The input is represented in 1.31 format, which is then downshifted by 8 bits
|
||||
which yields 1.23, and intermediate multiplication yields a 2.46 format.
|
||||
The accumulator maintains full precision of the intermediate multiplication results,
|
||||
but provides only a 16 guard bits.
|
||||
There is no saturation on intermediate additions.
|
||||
If the accumulator overflows it wraps around and distorts the result.
|
||||
In order to avoid overflows completely the input signal must be scaled down by
|
||||
log2(blockSize)-8 bits, as a total of blockSize additions are performed internally.
|
||||
After division, internal variables should be Q18.46
|
||||
Finally, the 18.46 accumulator is right shifted by 15 bits to yield a 1.31 format value.
|
||||
*/
|
||||
|
||||
void arm_std_q31(
|
||||
q31_t * pSrc,
|
||||
uint32_t blockSize,
|
||||
q31_t * pResult)
|
||||
const q31_t * pSrc,
|
||||
uint32_t blockSize,
|
||||
q31_t * pResult)
|
||||
{
|
||||
q63_t sum = 0; /* Accumulator */
|
||||
q63_t meanOfSquares, squareOfMean; /* square of mean and mean of square */
|
||||
q31_t in; /* input value */
|
||||
uint32_t blkCnt; /* loop counter */
|
||||
q63_t sumOfSquares = 0; /* Accumulator */
|
||||
uint32_t blkCnt; /* Loop counter */
|
||||
q63_t sum = 0; /* Accumulator */
|
||||
q63_t meanOfSquares, squareOfMean; /* Square of mean and mean of square */
|
||||
q63_t sumOfSquares = 0; /* Sum of squares */
|
||||
q31_t in; /* Temporary variable to store input value */
|
||||
|
||||
if (blockSize == 1U)
|
||||
if (blockSize <= 1U)
|
||||
{
|
||||
*pResult = 0;
|
||||
return;
|
||||
}
|
||||
|
||||
#if defined (ARM_MATH_DSP)
|
||||
/* Run the below code for Cortex-M4 and Cortex-M3 */
|
||||
#if defined (ARM_MATH_LOOPUNROLL)
|
||||
|
||||
/*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[0] * A[0] + A[1] * A[1] + ... + A[blockSize-1] * A[blockSize-1]) */
|
||||
/* Compute Sum of squares of the input samples
|
||||
* and then store the result in a temporary variable, sum. */
|
||||
in = *pSrc++ >> 8U;
|
||||
sum += in;
|
||||
sumOfSquares += ((q63_t) (in) * (in));
|
||||
in = *pSrc++ >> 8U;
|
||||
sum += in;
|
||||
sumOfSquares += ((q63_t) (in) * (in));
|
||||
in = *pSrc++ >> 8U;
|
||||
sum += in;
|
||||
sumOfSquares += ((q63_t) (in) * (in));
|
||||
in = *pSrc++ >> 8U;
|
||||
sum += in;
|
||||
sumOfSquares += ((q63_t) (in) * (in));
|
||||
/* C = A[0] * A[0] + A[1] * A[1] + ... + A[blockSize-1] * A[blockSize-1] */
|
||||
/* C = A[0] + A[1] + ... + A[blockSize-1] */
|
||||
|
||||
/* Decrement the loop counter */
|
||||
in = *pSrc++ >> 8U;
|
||||
/* Compute sum of squares and store result in a temporary variable, sumOfSquares. */
|
||||
sumOfSquares += ((q63_t) (in) * (in));
|
||||
/* Compute sum and store result in a temporary variable, sum. */
|
||||
sum += in;
|
||||
|
||||
in = *pSrc++ >> 8U;
|
||||
sumOfSquares += ((q63_t) (in) * (in));
|
||||
sum += in;
|
||||
|
||||
in = *pSrc++ >> 8U;
|
||||
sumOfSquares += ((q63_t) (in) * (in));
|
||||
sum += in;
|
||||
|
||||
in = *pSrc++ >> 8U;
|
||||
sumOfSquares += ((q63_t) (in) * (in));
|
||||
sum += in;
|
||||
|
||||
/* 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[0] * A[0] + A[1] * A[1] + ... + A[blockSize-1] * A[blockSize-1]) */
|
||||
/* Compute Sum of squares of the input samples
|
||||
* and then store the result in a temporary variable, sum. */
|
||||
in = *pSrc++ >> 8U;
|
||||
sum += in;
|
||||
sumOfSquares += ((q63_t) (in) * (in));
|
||||
|
||||
/* Decrement the loop counter */
|
||||
blkCnt--;
|
||||
}
|
||||
|
||||
/* Compute Mean of squares of the input samples
|
||||
* and then store the result in a temporary variable, meanOfSquares. */
|
||||
meanOfSquares = sumOfSquares / (q63_t)(blockSize - 1U);
|
||||
|
||||
#else
|
||||
/* Run the below code for Cortex-M0 */
|
||||
|
||||
/* Loop over blockSize number of values */
|
||||
/* Initialize blkCnt with number of samples */
|
||||
blkCnt = blockSize;
|
||||
|
||||
#endif /* #if defined (ARM_MATH_LOOPUNROLL) */
|
||||
|
||||
while (blkCnt > 0U)
|
||||
{
|
||||
/* C = (A[0] * A[0] + A[1] * A[1] + ... + A[blockSize-1] * A[blockSize-1]) */
|
||||
/* Compute Sum of squares of the input samples
|
||||
* and then store the result in a temporary variable, sumOfSquares. */
|
||||
in = *pSrc++ >> 8U;
|
||||
sumOfSquares += ((q63_t) (in) * (in));
|
||||
/* C = A[0] * A[0] + A[1] * A[1] + ... + A[blockSize-1] * A[blockSize-1] */
|
||||
/* C = A[0] + A[1] + ... + A[blockSize-1] */
|
||||
|
||||
/* C = (A[0] + A[1] + A[2] + ... + A[blockSize-1]) */
|
||||
/* Compute sum of all input values and then store the result in a temporary variable, sum. */
|
||||
in = *pSrc++ >> 8U;
|
||||
/* Compute sum of squares and store result in a temporary variable, sumOfSquares. */
|
||||
sumOfSquares += ((q63_t) (in) * (in));
|
||||
/* Compute sum and store result in a temporary variable, sum. */
|
||||
sum += in;
|
||||
|
||||
/* Decrement the loop counter */
|
||||
/* Decrement loop counter */
|
||||
blkCnt--;
|
||||
}
|
||||
|
||||
/* Compute Mean of squares of the input samples
|
||||
* and then store the result in a temporary variable, meanOfSquares. */
|
||||
meanOfSquares = sumOfSquares / (q63_t)(blockSize - 1U);
|
||||
|
||||
#endif /* #if defined (ARM_MATH_DSP) */
|
||||
/* Compute Mean of squares and store result in a temporary variable, meanOfSquares. */
|
||||
meanOfSquares = (sumOfSquares / (q63_t)(blockSize - 1U));
|
||||
|
||||
/* Compute square of mean */
|
||||
squareOfMean = sum * sum / (q63_t)(blockSize * (blockSize - 1U));
|
||||
squareOfMean = ( sum * sum / (q63_t)(blockSize * (blockSize - 1U)));
|
||||
|
||||
/* Compute standard deviation and then store the result to the destination */
|
||||
/* Compute standard deviation and store result in destination */
|
||||
arm_sqrt_q31((meanOfSquares - squareOfMean) >> 15U, pResult);
|
||||
}
|
||||
|
||||
/**
|
||||
* @} end of STD group
|
||||
@} end of STD group
|
||||
*/
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue