CMSIS DSP library

Dependents:   KL25Z_FFT_Demo Hat_Board_v5_1 KL25Z_FFT_Demo_tony KL25Z_FFT_Demo_tony ... more

Fork of mbed-dsp by mbed official

Committer:
emilmont
Date:
Thu May 30 17:10:11 2013 +0100
Revision:
2:da51fb522205
Parent:
1:fdd22bb7aa52
Child:
3:7a284390b0ce
Keep "cmsis-dsp" module in synch with its source

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 2:da51fb522205 5 * $Revision: V1.1.0
emilmont 1:fdd22bb7aa52 6 *
emilmont 2:da51fb522205 7 * Project: CMSIS DSP Library
emilmont 2:da51fb522205 8 * Title: arm_var_q31.c
emilmont 1:fdd22bb7aa52 9 *
emilmont 2:da51fb522205 10 * Description: Variance of an array of Q31 type.
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 * @addtogroup variance
emilmont 1:fdd22bb7aa52 41 * @{
emilmont 1:fdd22bb7aa52 42 */
emilmont 1:fdd22bb7aa52 43
emilmont 1:fdd22bb7aa52 44 /**
emilmont 1:fdd22bb7aa52 45 * @brief Variance of the elements of a Q31 vector.
emilmont 1:fdd22bb7aa52 46 * @param[in] *pSrc points to the input vector
emilmont 1:fdd22bb7aa52 47 * @param[in] blockSize length of the input vector
emilmont 1:fdd22bb7aa52 48 * @param[out] *pResult variance value returned here
emilmont 1:fdd22bb7aa52 49 * @return none.
emilmont 1:fdd22bb7aa52 50 *
emilmont 1:fdd22bb7aa52 51 * @details
emilmont 1:fdd22bb7aa52 52 * <b>Scaling and Overflow Behavior:</b>
emilmont 1:fdd22bb7aa52 53 *
emilmont 1:fdd22bb7aa52 54 *\par
emilmont 1:fdd22bb7aa52 55 * The function is implemented using an internal 64-bit accumulator.
emilmont 1:fdd22bb7aa52 56 * The input is represented in 1.31 format, and intermediate multiplication
emilmont 1:fdd22bb7aa52 57 * yields a 2.62 format.
emilmont 1:fdd22bb7aa52 58 * The accumulator maintains full precision of the intermediate multiplication results,
emilmont 1:fdd22bb7aa52 59 * but provides only a single guard bit.
emilmont 1:fdd22bb7aa52 60 * There is no saturation on intermediate additions.
emilmont 1:fdd22bb7aa52 61 * If the accumulator overflows it wraps around and distorts the result.
emilmont 1:fdd22bb7aa52 62 * In order to avoid overflows completely the input signal must be scaled down by
emilmont 1:fdd22bb7aa52 63 * log2(blockSize) bits, as a total of blockSize additions are performed internally.
emilmont 1:fdd22bb7aa52 64 * Finally, the 2.62 accumulator is right shifted by 31 bits to yield a 1.31 format value.
emilmont 1:fdd22bb7aa52 65 *
emilmont 1:fdd22bb7aa52 66 */
emilmont 1:fdd22bb7aa52 67
emilmont 1:fdd22bb7aa52 68
emilmont 1:fdd22bb7aa52 69 void arm_var_q31(
emilmont 1:fdd22bb7aa52 70 q31_t * pSrc,
emilmont 1:fdd22bb7aa52 71 uint32_t blockSize,
emilmont 1:fdd22bb7aa52 72 q63_t * pResult)
emilmont 1:fdd22bb7aa52 73 {
emilmont 1:fdd22bb7aa52 74 q63_t sum = 0, sumSquare = 0; /* Accumulator */
emilmont 1:fdd22bb7aa52 75 q31_t meanOfSquares, squareOfMean; /* square of mean and mean of square */
emilmont 1:fdd22bb7aa52 76 q31_t mean; /* mean */
emilmont 1:fdd22bb7aa52 77 q31_t in; /* input value */
emilmont 1:fdd22bb7aa52 78 q31_t t; /* Temporary variable */
emilmont 1:fdd22bb7aa52 79 uint32_t blkCnt; /* loop counter */
emilmont 1:fdd22bb7aa52 80
emilmont 1:fdd22bb7aa52 81 #ifndef ARM_MATH_CM0
emilmont 1:fdd22bb7aa52 82
emilmont 1:fdd22bb7aa52 83 /* Run the below code for Cortex-M4 and Cortex-M3 */
emilmont 1:fdd22bb7aa52 84 q63_t sumSquare1 = 0; /* Accumulator */
emilmont 1:fdd22bb7aa52 85 q31_t in1, in2, in3, in4; /* Temporary input variables */
emilmont 1:fdd22bb7aa52 86
emilmont 1:fdd22bb7aa52 87 /*loop Unrolling */
emilmont 1:fdd22bb7aa52 88 blkCnt = blockSize >> 2u;
emilmont 1:fdd22bb7aa52 89
emilmont 1:fdd22bb7aa52 90 /* First part of the processing with loop unrolling. Compute 4 outputs at a time.
emilmont 1:fdd22bb7aa52 91 ** a second loop below computes the remaining 1 to 3 samples. */
emilmont 1:fdd22bb7aa52 92 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 93 {
emilmont 1:fdd22bb7aa52 94 /* C = (A[0] * A[0] + A[1] * A[1] + ... + A[blockSize-1] * A[blockSize-1]) */
emilmont 1:fdd22bb7aa52 95 /* Compute Sum of squares of the input samples
emilmont 1:fdd22bb7aa52 96 * and then store the result in a temporary variable, sum. */
emilmont 1:fdd22bb7aa52 97 /* read input samples from source buffer */
emilmont 1:fdd22bb7aa52 98 in1 = pSrc[0];
emilmont 1:fdd22bb7aa52 99 in2 = pSrc[1];
emilmont 1:fdd22bb7aa52 100
emilmont 1:fdd22bb7aa52 101 /* calculate sum of inputs */
emilmont 1:fdd22bb7aa52 102 sum += in1;
emilmont 1:fdd22bb7aa52 103 /* calculate sum of squares */
emilmont 1:fdd22bb7aa52 104 sumSquare += ((q63_t) (in1) * (in1));
emilmont 1:fdd22bb7aa52 105 in3 = pSrc[2];
emilmont 1:fdd22bb7aa52 106 sum += in2;
emilmont 1:fdd22bb7aa52 107 sumSquare1 += ((q63_t) (in2) * (in2));
emilmont 1:fdd22bb7aa52 108 in4 = pSrc[3];
emilmont 1:fdd22bb7aa52 109 sum += in3;
emilmont 1:fdd22bb7aa52 110 sumSquare += ((q63_t) (in3) * (in3));
emilmont 1:fdd22bb7aa52 111 sum += in4;
emilmont 1:fdd22bb7aa52 112 sumSquare1 += ((q63_t) (in4) * (in4));
emilmont 1:fdd22bb7aa52 113
emilmont 1:fdd22bb7aa52 114 /* update input pointer to process next samples */
emilmont 1:fdd22bb7aa52 115 pSrc += 4u;
emilmont 1:fdd22bb7aa52 116
emilmont 1:fdd22bb7aa52 117 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 118 blkCnt--;
emilmont 1:fdd22bb7aa52 119 }
emilmont 1:fdd22bb7aa52 120
emilmont 1:fdd22bb7aa52 121 /* add two accumulators */
emilmont 1:fdd22bb7aa52 122 sumSquare = sumSquare + sumSquare1;
emilmont 1:fdd22bb7aa52 123
emilmont 1:fdd22bb7aa52 124 /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
emilmont 1:fdd22bb7aa52 125 ** No loop unrolling is used. */
emilmont 1:fdd22bb7aa52 126 blkCnt = blockSize % 0x4u;
emilmont 1:fdd22bb7aa52 127
emilmont 1:fdd22bb7aa52 128 #else
emilmont 1:fdd22bb7aa52 129
emilmont 1:fdd22bb7aa52 130 /* Run the below code for Cortex-M0 */
emilmont 1:fdd22bb7aa52 131 blkCnt = blockSize;
emilmont 1:fdd22bb7aa52 132
emilmont 1:fdd22bb7aa52 133 #endif /* #ifndef ARM_MATH_CM0 */
emilmont 1:fdd22bb7aa52 134
emilmont 1:fdd22bb7aa52 135 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 136 {
emilmont 1:fdd22bb7aa52 137 /* C = (A[0] * A[0] + A[1] * A[1] + ... + A[blockSize-1] * A[blockSize-1]) */
emilmont 1:fdd22bb7aa52 138 /* Compute Sum of squares of the input samples
emilmont 1:fdd22bb7aa52 139 * and then store the result in a temporary variable, sum. */
emilmont 1:fdd22bb7aa52 140 in = *pSrc++;
emilmont 1:fdd22bb7aa52 141 sumSquare += ((q63_t) (in) * (in));
emilmont 1:fdd22bb7aa52 142 sum += in;
emilmont 1:fdd22bb7aa52 143
emilmont 1:fdd22bb7aa52 144 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 145 blkCnt--;
emilmont 1:fdd22bb7aa52 146 }
emilmont 1:fdd22bb7aa52 147
emilmont 1:fdd22bb7aa52 148 t = (q31_t) ((1.0f / (float32_t) (blockSize - 1u)) * 1073741824.0f);
emilmont 1:fdd22bb7aa52 149
emilmont 1:fdd22bb7aa52 150 /* Compute Mean of squares of the input samples
emilmont 1:fdd22bb7aa52 151 * and then store the result in a temporary variable, meanOfSquares. */
emilmont 1:fdd22bb7aa52 152 sumSquare = (sumSquare >> 31);
emilmont 1:fdd22bb7aa52 153 meanOfSquares = (q31_t) ((sumSquare * t) >> 30);
emilmont 1:fdd22bb7aa52 154
emilmont 1:fdd22bb7aa52 155 /* Compute mean of all input values */
emilmont 1:fdd22bb7aa52 156 t = (q31_t) ((1.0f / (blockSize * (blockSize - 1u))) * 2147483648.0f);
emilmont 1:fdd22bb7aa52 157 mean = (q31_t) (sum);
emilmont 1:fdd22bb7aa52 158
emilmont 1:fdd22bb7aa52 159 /* Compute square of mean */
emilmont 1:fdd22bb7aa52 160 squareOfMean = (q31_t) (((q63_t) mean * mean) >> 31);
emilmont 1:fdd22bb7aa52 161 squareOfMean = (q31_t) (((q63_t) squareOfMean * t) >> 31);
emilmont 1:fdd22bb7aa52 162
emilmont 1:fdd22bb7aa52 163 /* Compute variance and then store the result to the destination */
emilmont 1:fdd22bb7aa52 164 *pResult = (q63_t) meanOfSquares - squareOfMean;
emilmont 1:fdd22bb7aa52 165
emilmont 1:fdd22bb7aa52 166 }
emilmont 1:fdd22bb7aa52 167
emilmont 1:fdd22bb7aa52 168 /**
emilmont 1:fdd22bb7aa52 169 * @} end of variance group
emilmont 1:fdd22bb7aa52 170 */