dsp - CMSIS DSP Library from CMSIS 2.0. See http://www.…

Users » simon » Code » dsp

CMSIS DSP Library from CMSIS 2.0. See http://www.onarm.com/cmsis/ for full details

Dependents: K22F_DSP_Matrix_least_square BNO055-ELEC3810 1BNO055 ECE4180Project--Slave2 ... more

src/Cortex-M4-M3/StatisticsFunctions/arm_var_q15.c@0:1014af42efd9, 2011-03-10 (annotated)

Committer:: simon
Date:: Thu Mar 10 15:07:50 2011 +0000
Revision:: 0:1014af42efd9

Who changed what in which revision?

User	Revision	Line number	New contents of line
simon	0:1014af42efd9	1	/* ----------------------------------------------------------------------
simon	0:1014af42efd9	2	* Copyright (C) 2010 ARM Limited. All rights reserved.
simon	0:1014af42efd9	3	*
simon	0:1014af42efd9	4	* $Date: 29. November 2010
simon	0:1014af42efd9	5	* $Revision: V1.0.3
simon	0:1014af42efd9	6	*
simon	0:1014af42efd9	7	* Project: CMSIS DSP Library
simon	0:1014af42efd9	8	* Title: arm_var_q15.c
simon	0:1014af42efd9	9	*
simon	0:1014af42efd9	10	* Description: Variance of an array of Q15 type.
simon	0:1014af42efd9	11	*
simon	0:1014af42efd9	12	* Target Processor: Cortex-M4/Cortex-M3
simon	0:1014af42efd9	13	*
simon	0:1014af42efd9	14	* Version 1.0.3 2010/11/29
simon	0:1014af42efd9	15	* Re-organized the CMSIS folders and updated documentation.
simon	0:1014af42efd9	16	*
simon	0:1014af42efd9	17	* Version 1.0.2 2010/11/11
simon	0:1014af42efd9	18	* Documentation updated.
simon	0:1014af42efd9	19	*
simon	0:1014af42efd9	20	* Version 1.0.1 2010/10/05
simon	0:1014af42efd9	21	* Production release and review comments incorporated.
simon	0:1014af42efd9	22	*
simon	0:1014af42efd9	23	* Version 1.0.0 2010/09/20
simon	0:1014af42efd9	24	* Production release and review comments incorporated.
simon	0:1014af42efd9	25	* -------------------------------------------------------------------- */
simon	0:1014af42efd9	26
simon	0:1014af42efd9	27	#include "arm_math.h"
simon	0:1014af42efd9	28
simon	0:1014af42efd9	29	/**
simon	0:1014af42efd9	30	* @ingroup groupStats
simon	0:1014af42efd9	31	*/
simon	0:1014af42efd9	32
simon	0:1014af42efd9	33	/**
simon	0:1014af42efd9	34	* @addtogroup variance
simon	0:1014af42efd9	35	* @{
simon	0:1014af42efd9	36	*/
simon	0:1014af42efd9	37
simon	0:1014af42efd9	38	/**
simon	0:1014af42efd9	39	* @brief Variance of the elements of a Q15 vector.
simon	0:1014af42efd9	40	* @param[in] *pSrc points to the input vector
simon	0:1014af42efd9	41	* @param[in] blockSize length of the input vector
simon	0:1014af42efd9	42	* @param[out] *pResult variance value returned here
simon	0:1014af42efd9	43	* @return none.
simon	0:1014af42efd9	44	*
simon	0:1014af42efd9	45	* @details
simon	0:1014af42efd9	46	* <b>Scaling and Overflow Behavior:</b>
simon	0:1014af42efd9	47	*
simon	0:1014af42efd9	48	* \par
simon	0:1014af42efd9	49	* The function is implemented using a 64-bit internal accumulator.
simon	0:1014af42efd9	50	* The input is represented in 1.15 format.
simon	0:1014af42efd9	51	* Intermediate multiplication yields a 2.30 format, and this
simon	0:1014af42efd9	52	* result is added without saturation to a 64-bit accumulator in 34.30 format.
simon	0:1014af42efd9	53	* With 33 guard bits in the accumulator, there is no risk of overflow, and the
simon	0:1014af42efd9	54	* full precision of the intermediate multiplication is preserved.
simon	0:1014af42efd9	55	* Finally, the 34.30 result is truncated to 34.15 format by discarding the lower
simon	0:1014af42efd9	56	* 15 bits, and then saturated to yield a result in 1.15 format.
simon	0:1014af42efd9	57	*
simon	0:1014af42efd9	58	*/
simon	0:1014af42efd9	59
simon	0:1014af42efd9	60
simon	0:1014af42efd9	61	void arm_var_q15(
simon	0:1014af42efd9	62	q15_t * pSrc,
simon	0:1014af42efd9	63	uint32_t blockSize,
simon	0:1014af42efd9	64	q31_t * pResult)
simon	0:1014af42efd9	65	{
simon	0:1014af42efd9	66	q63_t sum = 0; /* Accumulator */
simon	0:1014af42efd9	67	q31_t meanOfSquares, squareOfMean; /* Mean of square and square of mean */
simon	0:1014af42efd9	68	q15_t mean; /* mean */
simon	0:1014af42efd9	69	q31_t in; /* Input variable */
simon	0:1014af42efd9	70	q15_t in1; /* Temporary variable */
simon	0:1014af42efd9	71	uint32_t blkCnt; /* loop counter */
simon	0:1014af42efd9	72	q15_t t; /* Temporary variable */
simon	0:1014af42efd9	73	q15_t pIn; / Temporary pointer */
simon	0:1014af42efd9	74
simon	0:1014af42efd9	75	pIn = pSrc;
simon	0:1014af42efd9	76
simon	0:1014af42efd9	77	/loop Unrolling /
simon	0:1014af42efd9	78	blkCnt = blockSize >> 2u;
simon	0:1014af42efd9	79
simon	0:1014af42efd9	80	/* First part of the processing with loop unrolling. Compute 4 outputs at a time.
simon	0:1014af42efd9	81	** a second loop below computes the remaining 1 to 3 samples. */
simon	0:1014af42efd9	82	while(blkCnt > 0u)
simon	0:1014af42efd9	83	{
simon	0:1014af42efd9	84	/* C = (A[0] * A[0] + A[1] * A[1] + ... + A[blockSize-1] * A[blockSize-1]) */
simon	0:1014af42efd9	85	/* Compute Sum of squares of the input samples
simon	0:1014af42efd9	86	* and then store the result in a temporary variable, sum. */
simon	0:1014af42efd9	87	in = *__SIMD32(pSrc)++;
simon	0:1014af42efd9	88	sum = __SMLALD(in, in, sum);
simon	0:1014af42efd9	89	in = *__SIMD32(pSrc)++;
simon	0:1014af42efd9	90	sum = __SMLALD(in, in, sum);
simon	0:1014af42efd9	91
simon	0:1014af42efd9	92	/* Decrement the loop counter */
simon	0:1014af42efd9	93	blkCnt--;
simon	0:1014af42efd9	94	}
simon	0:1014af42efd9	95
simon	0:1014af42efd9	96	/* If the blockSize is not a multiple of 4, compute any remaining output samples here.
simon	0:1014af42efd9	97	** No loop unrolling is used. */
simon	0:1014af42efd9	98	blkCnt = blockSize % 0x4u;
simon	0:1014af42efd9	99
simon	0:1014af42efd9	100	while(blkCnt > 0u)
simon	0:1014af42efd9	101	{
simon	0:1014af42efd9	102	/* C = (A[0] * A[0] + A[1] * A[1] + ... + A[blockSize-1] * A[blockSize-1]) */
simon	0:1014af42efd9	103	/* Compute Sum of squares of the input samples
simon	0:1014af42efd9	104	* and then store the result in a temporary variable, sum. */
simon	0:1014af42efd9	105	in1 = *pSrc++;
simon	0:1014af42efd9	106	sum = __SMLALD(in1, in1, sum);
simon	0:1014af42efd9	107
simon	0:1014af42efd9	108	/* Decrement the loop counter */
simon	0:1014af42efd9	109	blkCnt--;
simon	0:1014af42efd9	110	}
simon	0:1014af42efd9	111
simon	0:1014af42efd9	112	/* Compute Mean of squares of the input samples
simon	0:1014af42efd9	113	* and then store the result in a temporary variable, meanOfSquares. */
simon	0:1014af42efd9	114	t = (q15_t) ((1.0f / (float32_t) (blockSize - 1u)) * 16384);
simon	0:1014af42efd9	115	sum = __SSAT((sum >> 15u), 16u);
simon	0:1014af42efd9	116
simon	0:1014af42efd9	117	meanOfSquares = (q31_t) ((sum * t) >> 14u);
simon	0:1014af42efd9	118
simon	0:1014af42efd9	119	/* Reset the accumulator */
simon	0:1014af42efd9	120	sum = 0;
simon	0:1014af42efd9	121
simon	0:1014af42efd9	122	/loop Unrolling /
simon	0:1014af42efd9	123	blkCnt = blockSize >> 2u;
simon	0:1014af42efd9	124
simon	0:1014af42efd9	125	/* Reset the input working pointer */
simon	0:1014af42efd9	126	pSrc = pIn;
simon	0:1014af42efd9	127
simon	0:1014af42efd9	128	/* First part of the processing with loop unrolling. Compute 4 outputs at a time.
simon	0:1014af42efd9	129	** a second loop below computes the remaining 1 to 3 samples. */
simon	0:1014af42efd9	130	while(blkCnt > 0u)
simon	0:1014af42efd9	131	{
simon	0:1014af42efd9	132	/* C = (A[0] + A[1] + A[2] + ... + A[blockSize-1]) */
simon	0:1014af42efd9	133	/* Compute sum of all input values and then store the result in a temporary variable, sum. */
simon	0:1014af42efd9	134	sum += *pSrc++;
simon	0:1014af42efd9	135	sum += *pSrc++;
simon	0:1014af42efd9	136	sum += *pSrc++;
simon	0:1014af42efd9	137	sum += *pSrc++;
simon	0:1014af42efd9	138
simon	0:1014af42efd9	139	/* Decrement the loop counter */
simon	0:1014af42efd9	140	blkCnt--;
simon	0:1014af42efd9	141	}
simon	0:1014af42efd9	142
simon	0:1014af42efd9	143	/* If the blockSize is not a multiple of 4, compute any remaining output samples here.
simon	0:1014af42efd9	144	** No loop unrolling is used. */
simon	0:1014af42efd9	145	blkCnt = blockSize % 0x4u;
simon	0:1014af42efd9	146
simon	0:1014af42efd9	147	while(blkCnt > 0u)
simon	0:1014af42efd9	148	{
simon	0:1014af42efd9	149	/* C = (A[0] + A[1] + A[2] + ... + A[blockSize-1]) */
simon	0:1014af42efd9	150	/* Compute sum of all input values and then store the result in a temporary variable, sum. */
simon	0:1014af42efd9	151	sum += *pSrc++;
simon	0:1014af42efd9	152
simon	0:1014af42efd9	153	/* Decrement the loop counter */
simon	0:1014af42efd9	154	blkCnt--;
simon	0:1014af42efd9	155	}
simon	0:1014af42efd9	156
simon	0:1014af42efd9	157	/* Compute mean of all input values */
simon	0:1014af42efd9	158	t = (q15_t) ((1.0f / (float32_t) (blockSize * (blockSize - 1u))) * 32768);
simon	0:1014af42efd9	159	mean = __SSAT(sum, 16u);
simon	0:1014af42efd9	160
simon	0:1014af42efd9	161	/* Compute square of mean */
simon	0:1014af42efd9	162	squareOfMean = ((q31_t) mean * mean) >> 15;
simon	0:1014af42efd9	163	squareOfMean = (q31_t) (((q63_t) squareOfMean * t) >> 15);
simon	0:1014af42efd9	164
simon	0:1014af42efd9	165	/* Compute variance and then store the result to the destination */
simon	0:1014af42efd9	166	*pResult = (meanOfSquares - squareOfMean);
simon	0:1014af42efd9	167
simon	0:1014af42efd9	168	}
simon	0:1014af42efd9	169
simon	0:1014af42efd9	170	/**
simon	0:1014af42efd9	171	* @} end of variance group
simon	0:1014af42efd9	172	*/

Repository toolbox

Export to desktop IDE

Repository details

Type:	Library
Created:	10 Mar 2011
Imports:	907
Forks:	1
Commits:	3
Dependents:	5
Dependencies:	0
Followers:	35

src/Cortex-M4-M3/StatisticsFunctions/arm_var_q15.c@0:1014af42efd9, 2011-03-10 (annotated)

Who changed what in which revision?

Repository toolbox

Repository details

Important Information for this Arm website

Access Warning