Laxmi Kant Tiwari / mbed-dsp

CMSIS DSP Lib

Fork of mbed-dsp by mbed official

cmsis_dsp/FastMathFunctions/arm_sqrt_q31.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 1:fdd22bb7aa52 7 * Project: CMSIS DSP Library
emilmont 2:da51fb522205 8 * Title: arm_sqrt_q31.c
emilmont 1:fdd22bb7aa52 9 *
emilmont 2:da51fb522205 10 * Description: Q31 square root function.
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 #include "arm_math.h"
emilmont 1:fdd22bb7aa52 41 #include "arm_common_tables.h"
emilmont 1:fdd22bb7aa52 42
emilmont 1:fdd22bb7aa52 43 /**
emilmont 1:fdd22bb7aa52 44 * @ingroup groupFastMath
emilmont 1:fdd22bb7aa52 45 */
emilmont 1:fdd22bb7aa52 46
emilmont 1:fdd22bb7aa52 47 /**
emilmont 1:fdd22bb7aa52 48 * @addtogroup SQRT
emilmont 1:fdd22bb7aa52 49 * @{
emilmont 1:fdd22bb7aa52 50 */
emilmont 1:fdd22bb7aa52 51
emilmont 1:fdd22bb7aa52 52 /**
emilmont 1:fdd22bb7aa52 53 * @brief Q31 square root function.
emilmont 1:fdd22bb7aa52 54 * @param[in] in input value. The range of the input value is [0 +1) or 0x00000000 to 0x7FFFFFFF.
emilmont 1:fdd22bb7aa52 55 * @param[out] *pOut square root of input value.
mbed_official 3:7a284390b0ce 56 * @return The function returns ARM_MATH_SUCCESS if the input value is positive
mbed_official 3:7a284390b0ce 57 * and ARM_MATH_ARGUMENT_ERROR if the input is negative. For
mbed_official 3:7a284390b0ce 58 * negative inputs, the function returns *pOut = 0.
emilmont 1:fdd22bb7aa52 59 */
emilmont 1:fdd22bb7aa52 60
emilmont 1:fdd22bb7aa52 61 arm_status arm_sqrt_q31(
emilmont 1:fdd22bb7aa52 62 q31_t in,
emilmont 1:fdd22bb7aa52 63 q31_t * pOut)
emilmont 1:fdd22bb7aa52 64 {
emilmont 1:fdd22bb7aa52 65 q31_t number, temp1, bits_val1, var1, signBits1, half;
emilmont 1:fdd22bb7aa52 66 float32_t temp_float1;
mbed_official 3:7a284390b0ce 67 union
mbed_official 3:7a284390b0ce 68 {
mbed_official 3:7a284390b0ce 69 q31_t fracval;
mbed_official 3:7a284390b0ce 70 float32_t floatval;
mbed_official 3:7a284390b0ce 71 } tempconv;
emilmont 1:fdd22bb7aa52 72
emilmont 1:fdd22bb7aa52 73 number = in;
emilmont 1:fdd22bb7aa52 74
emilmont 1:fdd22bb7aa52 75 /* If the input is a positive number then compute the signBits. */
emilmont 1:fdd22bb7aa52 76 if(number > 0)
emilmont 1:fdd22bb7aa52 77 {
emilmont 1:fdd22bb7aa52 78 signBits1 = __CLZ(number) - 1;
emilmont 1:fdd22bb7aa52 79
emilmont 1:fdd22bb7aa52 80 /* Shift by the number of signBits1 */
emilmont 1:fdd22bb7aa52 81 if((signBits1 % 2) == 0)
emilmont 1:fdd22bb7aa52 82 {
emilmont 1:fdd22bb7aa52 83 number = number << signBits1;
emilmont 1:fdd22bb7aa52 84 }
emilmont 1:fdd22bb7aa52 85 else
emilmont 1:fdd22bb7aa52 86 {
emilmont 1:fdd22bb7aa52 87 number = number << (signBits1 - 1);
emilmont 1:fdd22bb7aa52 88 }
emilmont 1:fdd22bb7aa52 89
emilmont 1:fdd22bb7aa52 90 /* Calculate half value of the number */
emilmont 1:fdd22bb7aa52 91 half = number >> 1;
emilmont 1:fdd22bb7aa52 92 /* Store the number for later use */
emilmont 1:fdd22bb7aa52 93 temp1 = number;
emilmont 1:fdd22bb7aa52 94
emilmont 1:fdd22bb7aa52 95 /*Convert to float */
emilmont 1:fdd22bb7aa52 96 temp_float1 = number * 4.6566128731e-010f;
emilmont 1:fdd22bb7aa52 97 /*Store as integer */
mbed_official 3:7a284390b0ce 98 tempconv.floatval = temp_float1;
mbed_official 3:7a284390b0ce 99 bits_val1 = tempconv.fracval;
emilmont 1:fdd22bb7aa52 100 /* Subtract the shifted value from the magic number to give intial guess */
emilmont 1:fdd22bb7aa52 101 bits_val1 = 0x5f3759df - (bits_val1 >> 1); // gives initial guess
emilmont 1:fdd22bb7aa52 102 /* Store as float */
mbed_official 3:7a284390b0ce 103 tempconv.fracval = bits_val1;
mbed_official 3:7a284390b0ce 104 temp_float1 = tempconv.floatval;
emilmont 1:fdd22bb7aa52 105 /* Convert to integer format */
emilmont 1:fdd22bb7aa52 106 var1 = (q31_t) (temp_float1 * 1073741824);
emilmont 1:fdd22bb7aa52 107
emilmont 1:fdd22bb7aa52 108 /* 1st iteration */
emilmont 1:fdd22bb7aa52 109 var1 = ((q31_t) ((q63_t) var1 * (0x30000000 -
emilmont 1:fdd22bb7aa52 110 ((q31_t)
emilmont 1:fdd22bb7aa52 111 ((((q31_t)
emilmont 1:fdd22bb7aa52 112 (((q63_t) var1 * var1) >> 31)) *
emilmont 1:fdd22bb7aa52 113 (q63_t) half) >> 31))) >> 31)) << 2;
emilmont 1:fdd22bb7aa52 114 /* 2nd iteration */
emilmont 1:fdd22bb7aa52 115 var1 = ((q31_t) ((q63_t) var1 * (0x30000000 -
emilmont 1:fdd22bb7aa52 116 ((q31_t)
emilmont 1:fdd22bb7aa52 117 ((((q31_t)
emilmont 1:fdd22bb7aa52 118 (((q63_t) var1 * var1) >> 31)) *
emilmont 1:fdd22bb7aa52 119 (q63_t) half) >> 31))) >> 31)) << 2;
emilmont 1:fdd22bb7aa52 120 /* 3rd iteration */
emilmont 1:fdd22bb7aa52 121 var1 = ((q31_t) ((q63_t) var1 * (0x30000000 -
emilmont 1:fdd22bb7aa52 122 ((q31_t)
emilmont 1:fdd22bb7aa52 123 ((((q31_t)
emilmont 1:fdd22bb7aa52 124 (((q63_t) var1 * var1) >> 31)) *
emilmont 1:fdd22bb7aa52 125 (q63_t) half) >> 31))) >> 31)) << 2;
emilmont 1:fdd22bb7aa52 126
emilmont 1:fdd22bb7aa52 127 /* Multiply the inverse square root with the original value */
emilmont 1:fdd22bb7aa52 128 var1 = ((q31_t) (((q63_t) temp1 * var1) >> 31)) << 1;
emilmont 1:fdd22bb7aa52 129
emilmont 1:fdd22bb7aa52 130 /* Shift the output down accordingly */
emilmont 1:fdd22bb7aa52 131 if((signBits1 % 2) == 0)
emilmont 1:fdd22bb7aa52 132 {
emilmont 1:fdd22bb7aa52 133 var1 = var1 >> (signBits1 / 2);
emilmont 1:fdd22bb7aa52 134 }
emilmont 1:fdd22bb7aa52 135 else
emilmont 1:fdd22bb7aa52 136 {
emilmont 1:fdd22bb7aa52 137 var1 = var1 >> ((signBits1 - 1) / 2);
emilmont 1:fdd22bb7aa52 138 }
emilmont 1:fdd22bb7aa52 139 *pOut = var1;
emilmont 1:fdd22bb7aa52 140
emilmont 1:fdd22bb7aa52 141 return (ARM_MATH_SUCCESS);
emilmont 1:fdd22bb7aa52 142 }
emilmont 1:fdd22bb7aa52 143 /* If the number is a negative number then store zero as its square root value */
emilmont 1:fdd22bb7aa52 144 else
emilmont 1:fdd22bb7aa52 145 {
emilmont 1:fdd22bb7aa52 146 *pOut = 0;
emilmont 1:fdd22bb7aa52 147 return (ARM_MATH_ARGUMENT_ERROR);
emilmont 1:fdd22bb7aa52 148 }
emilmont 1:fdd22bb7aa52 149 }
emilmont 1:fdd22bb7aa52 150
emilmont 1:fdd22bb7aa52 151 /**
emilmont 1:fdd22bb7aa52 152 * @} end of SQRT group
emilmont 1:fdd22bb7aa52 153 */