Laxmi Kant Tiwari / mbed-dsp

CMSIS DSP Lib

Fork of mbed-dsp by mbed official

cmsis_dsp/StatisticsFunctions/arm_mean_q15.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_mean_q15.c
emilmont 1:fdd22bb7aa52 9 *
emilmont 1:fdd22bb7aa52 10 * Description: Mean value of a Q15 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 mean
emilmont 1:fdd22bb7aa52 41 * @{
emilmont 1:fdd22bb7aa52 42 */
emilmont 1:fdd22bb7aa52 43
emilmont 1:fdd22bb7aa52 44 /**
emilmont 1:fdd22bb7aa52 45 * @brief Mean value of a Q15 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 mean 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 * \par
emilmont 1:fdd22bb7aa52 54 * The function is implemented using a 32-bit internal accumulator.
emilmont 1:fdd22bb7aa52 55 * The input is represented in 1.15 format and is accumulated in a 32-bit
emilmont 1:fdd22bb7aa52 56 * accumulator in 17.15 format.
emilmont 1:fdd22bb7aa52 57 * There is no risk of internal overflow with this approach, and the
emilmont 1:fdd22bb7aa52 58 * full precision of intermediate result is preserved.
emilmont 1:fdd22bb7aa52 59 * Finally, the accumulator is saturated and truncated to yield a result of 1.15 format.
emilmont 1:fdd22bb7aa52 60 *
emilmont 1:fdd22bb7aa52 61 */
emilmont 1:fdd22bb7aa52 62
emilmont 1:fdd22bb7aa52 63
emilmont 1:fdd22bb7aa52 64 void arm_mean_q15(
emilmont 1:fdd22bb7aa52 65 q15_t * pSrc,
emilmont 1:fdd22bb7aa52 66 uint32_t blockSize,
emilmont 1:fdd22bb7aa52 67 q15_t * pResult)
emilmont 1:fdd22bb7aa52 68 {
emilmont 1:fdd22bb7aa52 69 q31_t sum = 0; /* Temporary result storage */
emilmont 1:fdd22bb7aa52 70 uint32_t blkCnt; /* loop counter */
emilmont 1:fdd22bb7aa52 71
emilmont 1:fdd22bb7aa52 72 #ifndef ARM_MATH_CM0
emilmont 1:fdd22bb7aa52 73
emilmont 1:fdd22bb7aa52 74 /* Run the below code for Cortex-M4 and Cortex-M3 */
emilmont 1:fdd22bb7aa52 75 q31_t in;
emilmont 1:fdd22bb7aa52 76
emilmont 1:fdd22bb7aa52 77 /*loop Unrolling */
emilmont 1:fdd22bb7aa52 78 blkCnt = blockSize >> 2u;
emilmont 1:fdd22bb7aa52 79
emilmont 1:fdd22bb7aa52 80 /* First part of the processing with loop unrolling. Compute 4 outputs at a time.
emilmont 1:fdd22bb7aa52 81 ** a second loop below computes the remaining 1 to 3 samples. */
emilmont 1:fdd22bb7aa52 82 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 83 {
emilmont 1:fdd22bb7aa52 84 /* C = (A[0] + A[1] + A[2] + ... + A[blockSize-1]) */
emilmont 1:fdd22bb7aa52 85 in = *__SIMD32(pSrc)++;
emilmont 1:fdd22bb7aa52 86 sum += ((in << 16) >> 16);
emilmont 1:fdd22bb7aa52 87 sum += (in >> 16);
emilmont 1:fdd22bb7aa52 88 in = *__SIMD32(pSrc)++;
emilmont 1:fdd22bb7aa52 89 sum += ((in << 16) >> 16);
emilmont 1:fdd22bb7aa52 90 sum += (in >> 16);
emilmont 1:fdd22bb7aa52 91
emilmont 1:fdd22bb7aa52 92 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 93 blkCnt--;
emilmont 1:fdd22bb7aa52 94 }
emilmont 1:fdd22bb7aa52 95
emilmont 1:fdd22bb7aa52 96 /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
emilmont 1:fdd22bb7aa52 97 ** No loop unrolling is used. */
emilmont 1:fdd22bb7aa52 98 blkCnt = blockSize % 0x4u;
emilmont 1:fdd22bb7aa52 99
emilmont 1:fdd22bb7aa52 100 #else
emilmont 1:fdd22bb7aa52 101
emilmont 1:fdd22bb7aa52 102 /* Run the below code for Cortex-M0 */
emilmont 1:fdd22bb7aa52 103
emilmont 1:fdd22bb7aa52 104 /* Loop over blockSize number of values */
emilmont 1:fdd22bb7aa52 105 blkCnt = blockSize;
emilmont 1:fdd22bb7aa52 106
emilmont 1:fdd22bb7aa52 107 #endif /* #ifndef ARM_MATH_CM0 */
emilmont 1:fdd22bb7aa52 108
emilmont 1:fdd22bb7aa52 109 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 110 {
emilmont 1:fdd22bb7aa52 111 /* C = (A[0] + A[1] + A[2] + ... + A[blockSize-1]) */
emilmont 1:fdd22bb7aa52 112 sum += *pSrc++;
emilmont 1:fdd22bb7aa52 113
emilmont 1:fdd22bb7aa52 114 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 115 blkCnt--;
emilmont 1:fdd22bb7aa52 116 }
emilmont 1:fdd22bb7aa52 117
emilmont 1:fdd22bb7aa52 118 /* C = (A[0] + A[1] + A[2] + ... + A[blockSize-1]) / blockSize */
emilmont 1:fdd22bb7aa52 119 /* Store the result to the destination */
emilmont 1:fdd22bb7aa52 120 *pResult = (q15_t) (sum / blockSize);
emilmont 1:fdd22bb7aa52 121 }
emilmont 1:fdd22bb7aa52 122
emilmont 1:fdd22bb7aa52 123 /**
emilmont 1:fdd22bb7aa52 124 * @} end of mean group
emilmont 1:fdd22bb7aa52 125 */