Laxmi Kant Tiwari / mbed-dsp

CMSIS DSP Lib

Fork of mbed-dsp by mbed official

cmsis_dsp/StatisticsFunctions/arm_power_f32.c@1:fdd22bb7aa52, 2012-11-28 (annotated)

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_power_f32.c
emilmont 1:fdd22bb7aa52 9 *
emilmont 1:fdd22bb7aa52 10 * Description: Sum of the squares 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 * Version 0.0.7 2010/06/10
emilmont 1:fdd22bb7aa52 33 * Misra-C changes done
emilmont 1:fdd22bb7aa52 34 * ---------------------------------------------------------------------------- */
emilmont 1:fdd22bb7aa52 35
emilmont 1:fdd22bb7aa52 36 #include "arm_math.h"
emilmont 1:fdd22bb7aa52 37
emilmont 1:fdd22bb7aa52 38 /**
emilmont 1:fdd22bb7aa52 39 * @ingroup groupStats
emilmont 1:fdd22bb7aa52 40 */
emilmont 1:fdd22bb7aa52 41
emilmont 1:fdd22bb7aa52 42 /**
emilmont 1:fdd22bb7aa52 43 * @defgroup power Power
emilmont 1:fdd22bb7aa52 44 *
emilmont 1:fdd22bb7aa52 45 * Calculates the sum of the squares of the elements in the input vector.
emilmont 1:fdd22bb7aa52 46 * The underlying algorithm is used:
emilmont 1:fdd22bb7aa52 47 *
emilmont 1:fdd22bb7aa52 48 * <pre>
emilmont 1:fdd22bb7aa52 49 * Result = pSrc[0] * pSrc[0] + pSrc[1] * pSrc[1] + pSrc[2] * pSrc[2] + ... + pSrc[blockSize-1] * pSrc[blockSize-1];
emilmont 1:fdd22bb7aa52 50 * </pre>
emilmont 1:fdd22bb7aa52 51 *
emilmont 1:fdd22bb7aa52 52 * There are separate functions for floating point, Q31, Q15, and Q7 data types.
emilmont 1:fdd22bb7aa52 53 */
emilmont 1:fdd22bb7aa52 54
emilmont 1:fdd22bb7aa52 55 /**
emilmont 1:fdd22bb7aa52 56 * @addtogroup power
emilmont 1:fdd22bb7aa52 57 * @{
emilmont 1:fdd22bb7aa52 58 */
emilmont 1:fdd22bb7aa52 59
emilmont 1:fdd22bb7aa52 60
emilmont 1:fdd22bb7aa52 61 /**
emilmont 1:fdd22bb7aa52 62 * @brief Sum of the squares of the elements of a floating-point vector.
emilmont 1:fdd22bb7aa52 63 * @param[in] *pSrc points to the input vector
emilmont 1:fdd22bb7aa52 64 * @param[in] blockSize length of the input vector
emilmont 1:fdd22bb7aa52 65 * @param[out] *pResult sum of the squares value returned here
emilmont 1:fdd22bb7aa52 66 * @return none.
emilmont 1:fdd22bb7aa52 67 *
emilmont 1:fdd22bb7aa52 68 */
emilmont 1:fdd22bb7aa52 69
emilmont 1:fdd22bb7aa52 70
emilmont 1:fdd22bb7aa52 71 void arm_power_f32(
emilmont 1:fdd22bb7aa52 72 float32_t * pSrc,
emilmont 1:fdd22bb7aa52 73 uint32_t blockSize,
emilmont 1:fdd22bb7aa52 74 float32_t * pResult)
emilmont 1:fdd22bb7aa52 75 {
emilmont 1:fdd22bb7aa52 76 float32_t sum = 0.0f; /* accumulator */
emilmont 1:fdd22bb7aa52 77 float32_t in; /* Temporary variable to store input value */
emilmont 1:fdd22bb7aa52 78 uint32_t blkCnt; /* loop counter */
emilmont 1:fdd22bb7aa52 79
emilmont 1:fdd22bb7aa52 80 #ifndef ARM_MATH_CM0
emilmont 1:fdd22bb7aa52 81
emilmont 1:fdd22bb7aa52 82 /* Run the below code for Cortex-M4 and Cortex-M3 */
emilmont 1:fdd22bb7aa52 83
emilmont 1:fdd22bb7aa52 84 /*loop Unrolling */
emilmont 1:fdd22bb7aa52 85 blkCnt = blockSize >> 2u;
emilmont 1:fdd22bb7aa52 86
emilmont 1:fdd22bb7aa52 87 /* First part of the processing with loop unrolling. Compute 4 outputs at a time.
emilmont 1:fdd22bb7aa52 88 ** a second loop below computes the remaining 1 to 3 samples. */
emilmont 1:fdd22bb7aa52 89 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 90 {
emilmont 1:fdd22bb7aa52 91 /* C = A[0] * A[0] + A[1] * A[1] + A[2] * A[2] + ... + A[blockSize-1] * A[blockSize-1] */
emilmont 1:fdd22bb7aa52 92 /* Compute Power and then store the result in a temporary variable, sum. */
emilmont 1:fdd22bb7aa52 93 in = *pSrc++;
emilmont 1:fdd22bb7aa52 94 sum += in * in;
emilmont 1:fdd22bb7aa52 95 in = *pSrc++;
emilmont 1:fdd22bb7aa52 96 sum += in * in;
emilmont 1:fdd22bb7aa52 97 in = *pSrc++;
emilmont 1:fdd22bb7aa52 98 sum += in * in;
emilmont 1:fdd22bb7aa52 99 in = *pSrc++;
emilmont 1:fdd22bb7aa52 100 sum += in * in;
emilmont 1:fdd22bb7aa52 101
emilmont 1:fdd22bb7aa52 102 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 103 blkCnt--;
emilmont 1:fdd22bb7aa52 104 }
emilmont 1:fdd22bb7aa52 105
emilmont 1:fdd22bb7aa52 106 /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
emilmont 1:fdd22bb7aa52 107 ** No loop unrolling is used. */
emilmont 1:fdd22bb7aa52 108 blkCnt = blockSize % 0x4u;
emilmont 1:fdd22bb7aa52 109
emilmont 1:fdd22bb7aa52 110
emilmont 1:fdd22bb7aa52 111 #else
emilmont 1:fdd22bb7aa52 112
emilmont 1:fdd22bb7aa52 113 /* Run the below code for Cortex-M0 */
emilmont 1:fdd22bb7aa52 114
emilmont 1:fdd22bb7aa52 115 /* Loop over blockSize number of values */
emilmont 1:fdd22bb7aa52 116 blkCnt = blockSize;
emilmont 1:fdd22bb7aa52 117
emilmont 1:fdd22bb7aa52 118 #endif /* #ifndef ARM_MATH_CM0 */
emilmont 1:fdd22bb7aa52 119
emilmont 1:fdd22bb7aa52 120
emilmont 1:fdd22bb7aa52 121 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 122 {
emilmont 1:fdd22bb7aa52 123 /* C = A[0] * A[0] + A[1] * A[1] + A[2] * A[2] + ... + A[blockSize-1] * A[blockSize-1] */
emilmont 1:fdd22bb7aa52 124 /* compute power and then store the result in a temporary variable, sum. */
emilmont 1:fdd22bb7aa52 125 in = *pSrc++;
emilmont 1:fdd22bb7aa52 126 sum += 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 /* Store the result to the destination */
emilmont 1:fdd22bb7aa52 133 *pResult = sum;
emilmont 1:fdd22bb7aa52 134 }
emilmont 1:fdd22bb7aa52 135
emilmont 1:fdd22bb7aa52 136 /**
emilmont 1:fdd22bb7aa52 137 * @} end of power group
emilmont 1:fdd22bb7aa52 138 */