Laxmi Kant Tiwari / mbed-dsp

CMSIS DSP Lib

Fork of mbed-dsp by mbed official

cmsis_dsp/StatisticsFunctions/arm_var_q15.c@4:9cee975aadce, 2014-06-23 (annotated)

Committer:
mbed_official
Date:
Mon Jun 23 09:30:09 2014 +0100
Revision:
4:9cee975aadce
Parent:
3:7a284390b0ce 
Synchronized with git revision 6e7c7bcec41226f536474daae3c13d49e4c0e865



Full URL: https://github.com/mbedmicro/mbed/commit/6e7c7bcec41226f536474daae3c13d49e4c0e865/



Fix signed unsigned compare in dsp library

Who changed what in which revision?

UserRevisionLine numberNew contents of line
emilmont 1:fdd22bb7aa52 1 /* ----------------------------------------------------------------------
mbed_official 3:7a284390b0ce 2 * Copyright (C) 2010-2013 ARM Limited. All rights reserved.
emilmont 1:fdd22bb7aa52 3 *
mbed_official 3:7a284390b0ce 4 * $Date: 17. January 2013
mbed_official 3:7a284390b0ce 5 * $Revision: V1.4.1
emilmont 1:fdd22bb7aa52 6 *
emilmont 2:da51fb522205 7 * Project: CMSIS DSP Library
emilmont 2:da51fb522205 8 * Title: arm_var_q15.c
emilmont 1:fdd22bb7aa52 9 *
emilmont 2:da51fb522205 10 * Description: Variance of an array of Q15 type.
emilmont 1:fdd22bb7aa52 11 *
emilmont 1:fdd22bb7aa52 12 * Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
emilmont 1:fdd22bb7aa52 13 *
mbed_official 3:7a284390b0ce 14 * Redistribution and use in source and binary forms, with or without
mbed_official 3:7a284390b0ce 15 * modification, are permitted provided that the following conditions
mbed_official 3:7a284390b0ce 16 * are met:
mbed_official 3:7a284390b0ce 17 * - Redistributions of source code must retain the above copyright
mbed_official 3:7a284390b0ce 18 * notice, this list of conditions and the following disclaimer.
mbed_official 3:7a284390b0ce 19 * - Redistributions in binary form must reproduce the above copyright
mbed_official 3:7a284390b0ce 20 * notice, this list of conditions and the following disclaimer in
mbed_official 3:7a284390b0ce 21 * the documentation and/or other materials provided with the
mbed_official 3:7a284390b0ce 22 * distribution.
mbed_official 3:7a284390b0ce 23 * - Neither the name of ARM LIMITED nor the names of its contributors
mbed_official 3:7a284390b0ce 24 * may be used to endorse or promote products derived from this
mbed_official 3:7a284390b0ce 25 * software without specific prior written permission.
mbed_official 3:7a284390b0ce 26 *
mbed_official 3:7a284390b0ce 27 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
mbed_official 3:7a284390b0ce 28 * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
mbed_official 3:7a284390b0ce 29 * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
mbed_official 3:7a284390b0ce 30 * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
mbed_official 3:7a284390b0ce 31 * COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
mbed_official 3:7a284390b0ce 32 * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
mbed_official 3:7a284390b0ce 33 * BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
mbed_official 3:7a284390b0ce 34 * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
mbed_official 3:7a284390b0ce 35 * CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
mbed_official 3:7a284390b0ce 36 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
mbed_official 3:7a284390b0ce 37 * ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
mbed_official 3:7a284390b0ce 38 * POSSIBILITY OF SUCH DAMAGE.
emilmont 1:fdd22bb7aa52 39 * -------------------------------------------------------------------- */
emilmont 1:fdd22bb7aa52 40
emilmont 1:fdd22bb7aa52 41 #include "arm_math.h"
emilmont 1:fdd22bb7aa52 42
emilmont 1:fdd22bb7aa52 43 /**
emilmont 1:fdd22bb7aa52 44 * @ingroup groupStats
emilmont 1:fdd22bb7aa52 45 */
emilmont 1:fdd22bb7aa52 46
emilmont 1:fdd22bb7aa52 47 /**
emilmont 1:fdd22bb7aa52 48 * @addtogroup variance
emilmont 1:fdd22bb7aa52 49 * @{
emilmont 1:fdd22bb7aa52 50 */
emilmont 1:fdd22bb7aa52 51
emilmont 1:fdd22bb7aa52 52 /**
emilmont 1:fdd22bb7aa52 53 * @brief Variance of the elements of a Q15 vector.
emilmont 1:fdd22bb7aa52 54 * @param[in] *pSrc points to the input vector
emilmont 1:fdd22bb7aa52 55 * @param[in] blockSize length of the input vector
emilmont 1:fdd22bb7aa52 56 * @param[out] *pResult variance value returned here
emilmont 1:fdd22bb7aa52 57 * @return none.
emilmont 1:fdd22bb7aa52 58 *
emilmont 1:fdd22bb7aa52 59 * @details
emilmont 1:fdd22bb7aa52 60 * <b>Scaling and Overflow Behavior:</b>
emilmont 1:fdd22bb7aa52 61 *
emilmont 1:fdd22bb7aa52 62 * \par
emilmont 1:fdd22bb7aa52 63 * The function is implemented using a 64-bit internal accumulator.
emilmont 1:fdd22bb7aa52 64 * The input is represented in 1.15 format.
emilmont 1:fdd22bb7aa52 65 * Intermediate multiplication yields a 2.30 format, and this
emilmont 1:fdd22bb7aa52 66 * result is added without saturation to a 64-bit accumulator in 34.30 format.
emilmont 1:fdd22bb7aa52 67 * With 33 guard bits in the accumulator, there is no risk of overflow, and the
emilmont 1:fdd22bb7aa52 68 * full precision of the intermediate multiplication is preserved.
emilmont 1:fdd22bb7aa52 69 * Finally, the 34.30 result is truncated to 34.15 format by discarding the lower
emilmont 1:fdd22bb7aa52 70 * 15 bits, and then saturated to yield a result in 1.15 format.
emilmont 1:fdd22bb7aa52 71 *
emilmont 1:fdd22bb7aa52 72 */
emilmont 1:fdd22bb7aa52 73
emilmont 1:fdd22bb7aa52 74
emilmont 1:fdd22bb7aa52 75 void arm_var_q15(
emilmont 1:fdd22bb7aa52 76 q15_t * pSrc,
emilmont 1:fdd22bb7aa52 77 uint32_t blockSize,
emilmont 1:fdd22bb7aa52 78 q31_t * pResult)
emilmont 1:fdd22bb7aa52 79 {
emilmont 1:fdd22bb7aa52 80 q31_t sum = 0; /* Accumulator */
emilmont 1:fdd22bb7aa52 81 q31_t meanOfSquares, squareOfMean; /* Mean of square and square of mean */
emilmont 1:fdd22bb7aa52 82 q15_t mean; /* mean */
emilmont 1:fdd22bb7aa52 83 uint32_t blkCnt; /* loop counter */
emilmont 1:fdd22bb7aa52 84 q15_t t; /* Temporary variable */
emilmont 1:fdd22bb7aa52 85 q63_t sumOfSquares = 0; /* Accumulator */
emilmont 1:fdd22bb7aa52 86
mbed_official 3:7a284390b0ce 87 #ifndef ARM_MATH_CM0_FAMILY
emilmont 1:fdd22bb7aa52 88
emilmont 1:fdd22bb7aa52 89 /* Run the below code for Cortex-M4 and Cortex-M3 */
emilmont 1:fdd22bb7aa52 90
emilmont 1:fdd22bb7aa52 91 q31_t in; /* Input variable */
emilmont 1:fdd22bb7aa52 92 q15_t in1; /* Temporary variable */
emilmont 1:fdd22bb7aa52 93
emilmont 1:fdd22bb7aa52 94 /*loop Unrolling */
emilmont 1:fdd22bb7aa52 95 blkCnt = blockSize >> 2u;
emilmont 1:fdd22bb7aa52 96
emilmont 1:fdd22bb7aa52 97 /* First part of the processing with loop unrolling. Compute 4 outputs at a time.
emilmont 1:fdd22bb7aa52 98 ** a second loop below computes the remaining 1 to 3 samples. */
emilmont 1:fdd22bb7aa52 99 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 100 {
emilmont 1:fdd22bb7aa52 101 /* C = (A[0] * A[0] + A[1] * A[1] + ... + A[blockSize-1] * A[blockSize-1]) */
emilmont 1:fdd22bb7aa52 102 /* Compute Sum of squares of the input samples
emilmont 1:fdd22bb7aa52 103 * and then store the result in a temporary variable, sum. */
emilmont 1:fdd22bb7aa52 104 in = *__SIMD32(pSrc)++;
emilmont 1:fdd22bb7aa52 105 sum += ((in << 16) >> 16);
emilmont 1:fdd22bb7aa52 106 sum += (in >> 16);
emilmont 1:fdd22bb7aa52 107 sumOfSquares = __SMLALD(in, in, sumOfSquares);
emilmont 1:fdd22bb7aa52 108 in = *__SIMD32(pSrc)++;
emilmont 1:fdd22bb7aa52 109 sum += ((in << 16) >> 16);
emilmont 1:fdd22bb7aa52 110 sum += (in >> 16);
emilmont 1:fdd22bb7aa52 111 sumOfSquares = __SMLALD(in, in, sumOfSquares);
emilmont 1:fdd22bb7aa52 112
emilmont 1:fdd22bb7aa52 113 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 114 blkCnt--;
emilmont 1:fdd22bb7aa52 115 }
emilmont 1:fdd22bb7aa52 116
emilmont 1:fdd22bb7aa52 117 /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
emilmont 1:fdd22bb7aa52 118 ** No loop unrolling is used. */
emilmont 1:fdd22bb7aa52 119 blkCnt = blockSize % 0x4u;
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[blockSize-1] * A[blockSize-1]) */
emilmont 1:fdd22bb7aa52 124 /* Compute Sum of squares of the input samples
emilmont 1:fdd22bb7aa52 125 * and then store the result in a temporary variable, sum. */
emilmont 1:fdd22bb7aa52 126 in1 = *pSrc++;
emilmont 1:fdd22bb7aa52 127 sum += in1;
emilmont 1:fdd22bb7aa52 128 sumOfSquares = __SMLALD(in1, in1, sumOfSquares);
emilmont 1:fdd22bb7aa52 129
emilmont 1:fdd22bb7aa52 130 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 131 blkCnt--;
emilmont 1:fdd22bb7aa52 132 }
emilmont 1:fdd22bb7aa52 133
emilmont 1:fdd22bb7aa52 134 /* Compute Mean of squares of the input samples
emilmont 1:fdd22bb7aa52 135 * and then store the result in a temporary variable, meanOfSquares. */
emilmont 1:fdd22bb7aa52 136 t = (q15_t) ((1.0f / (float32_t) (blockSize - 1u)) * 16384);
emilmont 1:fdd22bb7aa52 137 sumOfSquares = __SSAT((sumOfSquares >> 15u), 16u);
emilmont 1:fdd22bb7aa52 138
emilmont 1:fdd22bb7aa52 139 meanOfSquares = (q31_t) ((sumOfSquares * t) >> 14u);
emilmont 1:fdd22bb7aa52 140
emilmont 1:fdd22bb7aa52 141 #else
emilmont 1:fdd22bb7aa52 142
emilmont 1:fdd22bb7aa52 143 /* Run the below code for Cortex-M0 */
emilmont 1:fdd22bb7aa52 144
emilmont 1:fdd22bb7aa52 145 q15_t in; /* Temporary variable */
emilmont 1:fdd22bb7aa52 146 /* Loop over blockSize number of values */
emilmont 1:fdd22bb7aa52 147 blkCnt = blockSize;
emilmont 1:fdd22bb7aa52 148
emilmont 1:fdd22bb7aa52 149 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 150 {
emilmont 1:fdd22bb7aa52 151 /* C = (A[0] * A[0] + A[1] * A[1] + ... + A[blockSize-1] * A[blockSize-1]) */
emilmont 1:fdd22bb7aa52 152 /* Compute Sum of squares of the input samples
emilmont 1:fdd22bb7aa52 153 * and then store the result in a temporary variable, sumOfSquares. */
emilmont 1:fdd22bb7aa52 154 in = *pSrc++;
emilmont 1:fdd22bb7aa52 155 sumOfSquares += (in * in);
emilmont 1:fdd22bb7aa52 156
emilmont 1:fdd22bb7aa52 157 /* C = (A[0] + A[1] + A[2] + ... + A[blockSize-1]) */
emilmont 1:fdd22bb7aa52 158 /* Compute sum of all input values and then store the result in a temporary variable, sum. */
emilmont 1:fdd22bb7aa52 159 sum += in;
emilmont 1:fdd22bb7aa52 160
emilmont 1:fdd22bb7aa52 161 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 162 blkCnt--;
emilmont 1:fdd22bb7aa52 163 }
emilmont 1:fdd22bb7aa52 164
emilmont 1:fdd22bb7aa52 165 /* Compute Mean of squares of the input samples
emilmont 1:fdd22bb7aa52 166 * and then store the result in a temporary variable, meanOfSquares. */
emilmont 1:fdd22bb7aa52 167 t = (q15_t) ((1.0f / (float32_t) (blockSize - 1u)) * 16384);
emilmont 1:fdd22bb7aa52 168 sumOfSquares = __SSAT((sumOfSquares >> 15u), 16u);
emilmont 1:fdd22bb7aa52 169 meanOfSquares = (q31_t) ((sumOfSquares * t) >> 14u);
emilmont 1:fdd22bb7aa52 170
mbed_official 3:7a284390b0ce 171 #endif /* #ifndef ARM_MATH_CM0_FAMILY */
emilmont 1:fdd22bb7aa52 172
emilmont 1:fdd22bb7aa52 173 /* Compute mean of all input values */
emilmont 1:fdd22bb7aa52 174 t = (q15_t) ((1.0f / (float32_t) (blockSize * (blockSize - 1u))) * 32768);
emilmont 1:fdd22bb7aa52 175 mean = __SSAT(sum, 16u);
emilmont 1:fdd22bb7aa52 176
emilmont 1:fdd22bb7aa52 177 /* Compute square of mean */
emilmont 1:fdd22bb7aa52 178 squareOfMean = ((q31_t) mean * mean) >> 15;
emilmont 1:fdd22bb7aa52 179 squareOfMean = (q31_t) (((q63_t) squareOfMean * t) >> 15);
emilmont 1:fdd22bb7aa52 180
emilmont 1:fdd22bb7aa52 181 /* Compute variance and then store the result to the destination */
emilmont 1:fdd22bb7aa52 182 *pResult = (meanOfSquares - squareOfMean);
emilmont 1:fdd22bb7aa52 183
emilmont 1:fdd22bb7aa52 184 }
emilmont 1:fdd22bb7aa52 185
emilmont 1:fdd22bb7aa52 186 /**
emilmont 1:fdd22bb7aa52 187 * @} end of variance group
emilmont 1:fdd22bb7aa52 188 */