Laxmi Kant Tiwari / mbed-dsp

CMSIS DSP Lib

Fork of mbed-dsp by mbed official

cmsis_dsp/StatisticsFunctions/arm_power_q31.c@2:da51fb522205, 2013-05-30 (annotated)

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_power_q31.c
emilmont 1:fdd22bb7aa52 9 *
emilmont 2:da51fb522205 10 * Description: Sum of the squares of the elements of a Q31 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 * @addtogroup power
emilmont 1:fdd22bb7aa52 41 * @{
emilmont 1:fdd22bb7aa52 42 */
emilmont 1:fdd22bb7aa52 43
emilmont 1:fdd22bb7aa52 44 /**
emilmont 1:fdd22bb7aa52 45 * @brief Sum of the squares 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 sum of the squares 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 a 64-bit internal accumulator.
emilmont 1:fdd22bb7aa52 56 * The input is represented in 1.31 format.
emilmont 1:fdd22bb7aa52 57 * Intermediate multiplication yields a 2.62 format, and this
emilmont 1:fdd22bb7aa52 58 * result is truncated to 2.48 format by discarding the lower 14 bits.
emilmont 1:fdd22bb7aa52 59 * The 2.48 result is then added without saturation to a 64-bit accumulator in 16.48 format.
emilmont 1:fdd22bb7aa52 60 * With 15 guard bits in the accumulator, there is no risk of overflow, and the
emilmont 1:fdd22bb7aa52 61 * full precision of the intermediate multiplication is preserved.
emilmont 1:fdd22bb7aa52 62 * Finally, the return result is in 16.48 format.
emilmont 1:fdd22bb7aa52 63 *
emilmont 1:fdd22bb7aa52 64 */
emilmont 1:fdd22bb7aa52 65
emilmont 1:fdd22bb7aa52 66 void arm_power_q31(
emilmont 1:fdd22bb7aa52 67 q31_t * pSrc,
emilmont 1:fdd22bb7aa52 68 uint32_t blockSize,
emilmont 1:fdd22bb7aa52 69 q63_t * pResult)
emilmont 1:fdd22bb7aa52 70 {
emilmont 1:fdd22bb7aa52 71 q63_t sum = 0; /* Temporary result storage */
emilmont 1:fdd22bb7aa52 72 q31_t in;
emilmont 1:fdd22bb7aa52 73 uint32_t blkCnt; /* loop counter */
emilmont 1:fdd22bb7aa52 74
emilmont 1:fdd22bb7aa52 75
emilmont 1:fdd22bb7aa52 76 #ifndef ARM_MATH_CM0
emilmont 1:fdd22bb7aa52 77
emilmont 1:fdd22bb7aa52 78 /* Run the below code for Cortex-M4 and Cortex-M3 */
emilmont 1:fdd22bb7aa52 79
emilmont 1:fdd22bb7aa52 80 /*loop Unrolling */
emilmont 1:fdd22bb7aa52 81 blkCnt = blockSize >> 2u;
emilmont 1:fdd22bb7aa52 82
emilmont 1:fdd22bb7aa52 83 /* First part of the processing with loop unrolling. Compute 4 outputs at a time.
emilmont 1:fdd22bb7aa52 84 ** a second loop below computes the remaining 1 to 3 samples. */
emilmont 1:fdd22bb7aa52 85 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 86 {
emilmont 1:fdd22bb7aa52 87 /* C = A[0] * A[0] + A[1] * A[1] + A[2] * A[2] + ... + A[blockSize-1] * A[blockSize-1] */
emilmont 1:fdd22bb7aa52 88 /* Compute Power then shift intermediate results by 14 bits to maintain 16.48 format and then store the result in a temporary variable sum, providing 15 guard bits. */
emilmont 1:fdd22bb7aa52 89 in = *pSrc++;
emilmont 1:fdd22bb7aa52 90 sum += ((q63_t) in * in) >> 14u;
emilmont 1:fdd22bb7aa52 91
emilmont 1:fdd22bb7aa52 92 in = *pSrc++;
emilmont 1:fdd22bb7aa52 93 sum += ((q63_t) in * in) >> 14u;
emilmont 1:fdd22bb7aa52 94
emilmont 1:fdd22bb7aa52 95 in = *pSrc++;
emilmont 1:fdd22bb7aa52 96 sum += ((q63_t) in * in) >> 14u;
emilmont 1:fdd22bb7aa52 97
emilmont 1:fdd22bb7aa52 98 in = *pSrc++;
emilmont 1:fdd22bb7aa52 99 sum += ((q63_t) in * in) >> 14u;
emilmont 1:fdd22bb7aa52 100
emilmont 1:fdd22bb7aa52 101 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 102 blkCnt--;
emilmont 1:fdd22bb7aa52 103 }
emilmont 1:fdd22bb7aa52 104
emilmont 1:fdd22bb7aa52 105 /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
emilmont 1:fdd22bb7aa52 106 ** No loop unrolling is used. */
emilmont 1:fdd22bb7aa52 107 blkCnt = blockSize % 0x4u;
emilmont 1:fdd22bb7aa52 108
emilmont 1:fdd22bb7aa52 109 #else
emilmont 1:fdd22bb7aa52 110
emilmont 1:fdd22bb7aa52 111 /* Run the below code for Cortex-M0 */
emilmont 1:fdd22bb7aa52 112
emilmont 1:fdd22bb7aa52 113 /* Loop over blockSize number of values */
emilmont 1:fdd22bb7aa52 114 blkCnt = blockSize;
emilmont 1:fdd22bb7aa52 115
emilmont 1:fdd22bb7aa52 116 #endif /* #ifndef ARM_MATH_CM0 */
emilmont 1:fdd22bb7aa52 117
emilmont 1:fdd22bb7aa52 118 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 119 {
emilmont 1:fdd22bb7aa52 120 /* C = A[0] * A[0] + A[1] * A[1] + A[2] * A[2] + ... + A[blockSize-1] * A[blockSize-1] */
emilmont 1:fdd22bb7aa52 121 /* Compute Power and then store the result in a temporary variable, sum. */
emilmont 1:fdd22bb7aa52 122 in = *pSrc++;
emilmont 1:fdd22bb7aa52 123 sum += ((q63_t) in * in) >> 14u;
emilmont 1:fdd22bb7aa52 124
emilmont 1:fdd22bb7aa52 125 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 126 blkCnt--;
emilmont 1:fdd22bb7aa52 127 }
emilmont 1:fdd22bb7aa52 128
emilmont 1:fdd22bb7aa52 129 /* Store the results in 16.48 format */
emilmont 1:fdd22bb7aa52 130 *pResult = sum;
emilmont 1:fdd22bb7aa52 131 }
emilmont 1:fdd22bb7aa52 132
emilmont 1:fdd22bb7aa52 133 /**
emilmont 1:fdd22bb7aa52 134 * @} end of power group
emilmont 1:fdd22bb7aa52 135 */