CMSIS DSP Lib

Fork of mbed-dsp by mbed official

Committer:
emilmont
Date:
Wed Nov 28 12:30:09 2012 +0000
Revision:
1:fdd22bb7aa52
Child:
2:da51fb522205
DSP library code

Who changed what in which revision?

UserRevisionLine numberNew contents of line
emilmont 1:fdd22bb7aa52 1 /* ----------------------------------------------------------------------
emilmont 1:fdd22bb7aa52 2 * Copyright (C) 2010 ARM Limited. All rights reserved.
emilmont 1:fdd22bb7aa52 3 *
emilmont 1:fdd22bb7aa52 4 * $Date: 15. February 2012
emilmont 1:fdd22bb7aa52 5 * $Revision: V1.1.0
emilmont 1:fdd22bb7aa52 6 *
emilmont 1:fdd22bb7aa52 7 * Project: CMSIS DSP Library
emilmont 1:fdd22bb7aa52 8 * Title: arm_std_f32.c
emilmont 1:fdd22bb7aa52 9 *
emilmont 1:fdd22bb7aa52 10 * Description: Standard deviation of the elements of a floating-point vector.
emilmont 1:fdd22bb7aa52 11 *
emilmont 1:fdd22bb7aa52 12 * Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
emilmont 1:fdd22bb7aa52 13 *
emilmont 1:fdd22bb7aa52 14 * Version 1.1.0 2012/02/15
emilmont 1:fdd22bb7aa52 15 * Updated with more optimizations, bug fixes and minor API changes.
emilmont 1:fdd22bb7aa52 16 *
emilmont 1:fdd22bb7aa52 17 * Version 1.0.10 2011/7/15
emilmont 1:fdd22bb7aa52 18 * Big Endian support added and Merged M0 and M3/M4 Source code.
emilmont 1:fdd22bb7aa52 19 *
emilmont 1:fdd22bb7aa52 20 * Version 1.0.3 2010/11/29
emilmont 1:fdd22bb7aa52 21 * Re-organized the CMSIS folders and updated documentation.
emilmont 1:fdd22bb7aa52 22 *
emilmont 1:fdd22bb7aa52 23 * Version 1.0.2 2010/11/11
emilmont 1:fdd22bb7aa52 24 * Documentation updated.
emilmont 1:fdd22bb7aa52 25 *
emilmont 1:fdd22bb7aa52 26 * Version 1.0.1 2010/10/05
emilmont 1:fdd22bb7aa52 27 * Production release and review comments incorporated.
emilmont 1:fdd22bb7aa52 28 *
emilmont 1:fdd22bb7aa52 29 * Version 1.0.0 2010/09/20
emilmont 1:fdd22bb7aa52 30 * Production release and review comments incorporated.
emilmont 1:fdd22bb7aa52 31 * ---------------------------------------------------------------------------- */
emilmont 1:fdd22bb7aa52 32
emilmont 1:fdd22bb7aa52 33 #include "arm_math.h"
emilmont 1:fdd22bb7aa52 34
emilmont 1:fdd22bb7aa52 35 /**
emilmont 1:fdd22bb7aa52 36 * @ingroup groupStats
emilmont 1:fdd22bb7aa52 37 */
emilmont 1:fdd22bb7aa52 38
emilmont 1:fdd22bb7aa52 39 /**
emilmont 1:fdd22bb7aa52 40 * @defgroup STD Standard deviation
emilmont 1:fdd22bb7aa52 41 *
emilmont 1:fdd22bb7aa52 42 * Calculates the standard deviation of the elements in the input vector.
emilmont 1:fdd22bb7aa52 43 * The underlying algorithm is used:
emilmont 1:fdd22bb7aa52 44 *
emilmont 1:fdd22bb7aa52 45 * <pre>
emilmont 1:fdd22bb7aa52 46 * Result = sqrt((sumOfSquares - sum<sup>2</sup> / blockSize) / (blockSize - 1))
emilmont 1:fdd22bb7aa52 47 *
emilmont 1:fdd22bb7aa52 48 * where, sumOfSquares = pSrc[0] * pSrc[0] + pSrc[1] * pSrc[1] + ... + pSrc[blockSize-1] * pSrc[blockSize-1]
emilmont 1:fdd22bb7aa52 49 *
emilmont 1:fdd22bb7aa52 50 * sum = pSrc[0] + pSrc[1] + pSrc[2] + ... + pSrc[blockSize-1]
emilmont 1:fdd22bb7aa52 51 * </pre>
emilmont 1:fdd22bb7aa52 52 *
emilmont 1:fdd22bb7aa52 53 * There are separate functions for floating point, Q31, and Q15 data types.
emilmont 1:fdd22bb7aa52 54 */
emilmont 1:fdd22bb7aa52 55
emilmont 1:fdd22bb7aa52 56 /**
emilmont 1:fdd22bb7aa52 57 * @addtogroup STD
emilmont 1:fdd22bb7aa52 58 * @{
emilmont 1:fdd22bb7aa52 59 */
emilmont 1:fdd22bb7aa52 60
emilmont 1:fdd22bb7aa52 61
emilmont 1:fdd22bb7aa52 62 /**
emilmont 1:fdd22bb7aa52 63 * @brief Standard deviation of the elements of a floating-point vector.
emilmont 1:fdd22bb7aa52 64 * @param[in] *pSrc points to the input vector
emilmont 1:fdd22bb7aa52 65 * @param[in] blockSize length of the input vector
emilmont 1:fdd22bb7aa52 66 * @param[out] *pResult standard deviation value returned here
emilmont 1:fdd22bb7aa52 67 * @return none.
emilmont 1:fdd22bb7aa52 68 *
emilmont 1:fdd22bb7aa52 69 */
emilmont 1:fdd22bb7aa52 70
emilmont 1:fdd22bb7aa52 71
emilmont 1:fdd22bb7aa52 72 void arm_std_f32(
emilmont 1:fdd22bb7aa52 73 float32_t * pSrc,
emilmont 1:fdd22bb7aa52 74 uint32_t blockSize,
emilmont 1:fdd22bb7aa52 75 float32_t * pResult)
emilmont 1:fdd22bb7aa52 76 {
emilmont 1:fdd22bb7aa52 77 float32_t sum = 0.0f; /* Temporary result storage */
emilmont 1:fdd22bb7aa52 78 float32_t sumOfSquares = 0.0f; /* Sum of squares */
emilmont 1:fdd22bb7aa52 79 float32_t in; /* input value */
emilmont 1:fdd22bb7aa52 80 uint32_t blkCnt; /* loop counter */
emilmont 1:fdd22bb7aa52 81
emilmont 1:fdd22bb7aa52 82 #ifndef ARM_MATH_CM0
emilmont 1:fdd22bb7aa52 83
emilmont 1:fdd22bb7aa52 84 /* Run the below code for Cortex-M4 and Cortex-M3 */
emilmont 1:fdd22bb7aa52 85
emilmont 1:fdd22bb7aa52 86 float32_t meanOfSquares, mean, squareOfMean;
emilmont 1:fdd22bb7aa52 87
emilmont 1:fdd22bb7aa52 88 /*loop Unrolling */
emilmont 1:fdd22bb7aa52 89 blkCnt = blockSize >> 2u;
emilmont 1:fdd22bb7aa52 90
emilmont 1:fdd22bb7aa52 91 /* First part of the processing with loop unrolling. Compute 4 outputs at a time.
emilmont 1:fdd22bb7aa52 92 ** a second loop below computes the remaining 1 to 3 samples. */
emilmont 1:fdd22bb7aa52 93 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 94 {
emilmont 1:fdd22bb7aa52 95 /* C = (A[0] * A[0] + A[1] * A[1] + ... + A[blockSize-1] * A[blockSize-1]) */
emilmont 1:fdd22bb7aa52 96 /* Compute Sum of squares of the input samples
emilmont 1:fdd22bb7aa52 97 * and then store the result in a temporary variable, sum. */
emilmont 1:fdd22bb7aa52 98 in = *pSrc++;
emilmont 1:fdd22bb7aa52 99 sum += in;
emilmont 1:fdd22bb7aa52 100 sumOfSquares += in * in;
emilmont 1:fdd22bb7aa52 101 in = *pSrc++;
emilmont 1:fdd22bb7aa52 102 sum += in;
emilmont 1:fdd22bb7aa52 103 sumOfSquares += in * in;
emilmont 1:fdd22bb7aa52 104 in = *pSrc++;
emilmont 1:fdd22bb7aa52 105 sum += in;
emilmont 1:fdd22bb7aa52 106 sumOfSquares += in * in;
emilmont 1:fdd22bb7aa52 107 in = *pSrc++;
emilmont 1:fdd22bb7aa52 108 sum += in;
emilmont 1:fdd22bb7aa52 109 sumOfSquares += in * in;
emilmont 1:fdd22bb7aa52 110
emilmont 1:fdd22bb7aa52 111 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 112 blkCnt--;
emilmont 1:fdd22bb7aa52 113 }
emilmont 1:fdd22bb7aa52 114
emilmont 1:fdd22bb7aa52 115 /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
emilmont 1:fdd22bb7aa52 116 ** No loop unrolling is used. */
emilmont 1:fdd22bb7aa52 117 blkCnt = blockSize % 0x4u;
emilmont 1:fdd22bb7aa52 118
emilmont 1:fdd22bb7aa52 119 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 120 {
emilmont 1:fdd22bb7aa52 121 /* C = (A[0] * A[0] + A[1] * A[1] + ... + A[blockSize-1] * A[blockSize-1]) */
emilmont 1:fdd22bb7aa52 122 /* Compute Sum of squares of the input samples
emilmont 1:fdd22bb7aa52 123 * and then store the result in a temporary variable, sum. */
emilmont 1:fdd22bb7aa52 124 in = *pSrc++;
emilmont 1:fdd22bb7aa52 125 sum += in;
emilmont 1:fdd22bb7aa52 126 sumOfSquares += in * in;
emilmont 1:fdd22bb7aa52 127
emilmont 1:fdd22bb7aa52 128 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 129 blkCnt--;
emilmont 1:fdd22bb7aa52 130 }
emilmont 1:fdd22bb7aa52 131
emilmont 1:fdd22bb7aa52 132 /* Compute Mean of squares of the input samples
emilmont 1:fdd22bb7aa52 133 * and then store the result in a temporary variable, meanOfSquares. */
emilmont 1:fdd22bb7aa52 134 meanOfSquares = sumOfSquares / ((float32_t) blockSize - 1.0f);
emilmont 1:fdd22bb7aa52 135
emilmont 1:fdd22bb7aa52 136 /* Compute mean of all input values */
emilmont 1:fdd22bb7aa52 137 mean = sum / (float32_t) blockSize;
emilmont 1:fdd22bb7aa52 138
emilmont 1:fdd22bb7aa52 139 /* Compute square of mean */
emilmont 1:fdd22bb7aa52 140 squareOfMean = (mean * mean) * (((float32_t) blockSize) /
emilmont 1:fdd22bb7aa52 141 ((float32_t) blockSize - 1.0f));
emilmont 1:fdd22bb7aa52 142
emilmont 1:fdd22bb7aa52 143 /* Compute standard deviation and then store the result to the destination */
emilmont 1:fdd22bb7aa52 144 arm_sqrt_f32((meanOfSquares - squareOfMean), pResult);
emilmont 1:fdd22bb7aa52 145
emilmont 1:fdd22bb7aa52 146 #else
emilmont 1:fdd22bb7aa52 147
emilmont 1:fdd22bb7aa52 148 /* Run the below code for Cortex-M0 */
emilmont 1:fdd22bb7aa52 149
emilmont 1:fdd22bb7aa52 150 float32_t squareOfSum; /* Square of Sum */
emilmont 1:fdd22bb7aa52 151 float32_t var; /* Temporary varaince storage */
emilmont 1:fdd22bb7aa52 152
emilmont 1:fdd22bb7aa52 153 /* Loop over blockSize number of values */
emilmont 1:fdd22bb7aa52 154 blkCnt = blockSize;
emilmont 1:fdd22bb7aa52 155
emilmont 1:fdd22bb7aa52 156 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 157 {
emilmont 1:fdd22bb7aa52 158 /* C = (A[0] * A[0] + A[1] * A[1] + ... + A[blockSize-1] * A[blockSize-1]) */
emilmont 1:fdd22bb7aa52 159 /* Compute Sum of squares of the input samples
emilmont 1:fdd22bb7aa52 160 * and then store the result in a temporary variable, sumOfSquares. */
emilmont 1:fdd22bb7aa52 161 in = *pSrc++;
emilmont 1:fdd22bb7aa52 162 sumOfSquares += in * in;
emilmont 1:fdd22bb7aa52 163
emilmont 1:fdd22bb7aa52 164 /* C = (A[0] + A[1] + ... + A[blockSize-1]) */
emilmont 1:fdd22bb7aa52 165 /* Compute Sum of the input samples
emilmont 1:fdd22bb7aa52 166 * and then store the result in a temporary variable, sum. */
emilmont 1:fdd22bb7aa52 167 sum += in;
emilmont 1:fdd22bb7aa52 168
emilmont 1:fdd22bb7aa52 169 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 170 blkCnt--;
emilmont 1:fdd22bb7aa52 171 }
emilmont 1:fdd22bb7aa52 172
emilmont 1:fdd22bb7aa52 173 /* Compute the square of sum */
emilmont 1:fdd22bb7aa52 174 squareOfSum = ((sum * sum) / (float32_t) blockSize);
emilmont 1:fdd22bb7aa52 175
emilmont 1:fdd22bb7aa52 176 /* Compute the variance */
emilmont 1:fdd22bb7aa52 177 var = ((sumOfSquares - squareOfSum) / (float32_t) (blockSize - 1.0f));
emilmont 1:fdd22bb7aa52 178
emilmont 1:fdd22bb7aa52 179 /* Compute standard deviation and then store the result to the destination */
emilmont 1:fdd22bb7aa52 180 arm_sqrt_f32(var, pResult);
emilmont 1:fdd22bb7aa52 181
emilmont 1:fdd22bb7aa52 182 #endif /* #ifndef ARM_MATH_CM0 */
emilmont 1:fdd22bb7aa52 183
emilmont 1:fdd22bb7aa52 184 }
emilmont 1:fdd22bb7aa52 185
emilmont 1:fdd22bb7aa52 186 /**
emilmont 1:fdd22bb7aa52 187 * @} end of STD group
emilmont 1:fdd22bb7aa52 188 */