Laxmi Kant Tiwari / mbed-dsp

CMSIS DSP Lib

Fork of mbed-dsp by mbed official

cmsis_dsp/ComplexMathFunctions/arm_cmplx_mag_q31.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_cmplx_mag_q31.c
emilmont 1:fdd22bb7aa52 9 *
emilmont 1:fdd22bb7aa52 10 * Description: Q31 complex magnitude
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 groupCmplxMath
emilmont 1:fdd22bb7aa52 37 */
emilmont 1:fdd22bb7aa52 38
emilmont 1:fdd22bb7aa52 39 /**
emilmont 1:fdd22bb7aa52 40 * @addtogroup cmplx_mag
emilmont 1:fdd22bb7aa52 41 * @{
emilmont 1:fdd22bb7aa52 42 */
emilmont 1:fdd22bb7aa52 43
emilmont 1:fdd22bb7aa52 44 /**
emilmont 1:fdd22bb7aa52 45 * @brief Q31 complex magnitude
emilmont 1:fdd22bb7aa52 46 * @param *pSrc points to the complex input vector
emilmont 1:fdd22bb7aa52 47 * @param *pDst points to the real output vector
emilmont 1:fdd22bb7aa52 48 * @param numSamples number of complex samples in the input vector
emilmont 1:fdd22bb7aa52 49 * @return none.
emilmont 1:fdd22bb7aa52 50 *
emilmont 1:fdd22bb7aa52 51 * <b>Scaling and Overflow Behavior:</b>
emilmont 1:fdd22bb7aa52 52 * \par
emilmont 1:fdd22bb7aa52 53 * The function implements 1.31 by 1.31 multiplications and finally output is converted into 2.30 format.
emilmont 1:fdd22bb7aa52 54 * Input down scaling is not required.
emilmont 1:fdd22bb7aa52 55 */
emilmont 1:fdd22bb7aa52 56
emilmont 1:fdd22bb7aa52 57 void arm_cmplx_mag_q31(
emilmont 1:fdd22bb7aa52 58 q31_t * pSrc,
emilmont 1:fdd22bb7aa52 59 q31_t * pDst,
emilmont 1:fdd22bb7aa52 60 uint32_t numSamples)
emilmont 1:fdd22bb7aa52 61 {
emilmont 1:fdd22bb7aa52 62 q31_t real, imag; /* Temporary variables to hold input values */
emilmont 1:fdd22bb7aa52 63 q31_t acc0, acc1; /* Accumulators */
emilmont 1:fdd22bb7aa52 64 uint32_t blkCnt; /* loop counter */
emilmont 1:fdd22bb7aa52 65
emilmont 1:fdd22bb7aa52 66 #ifndef ARM_MATH_CM0
emilmont 1:fdd22bb7aa52 67
emilmont 1:fdd22bb7aa52 68 /* Run the below code for Cortex-M4 and Cortex-M3 */
emilmont 1:fdd22bb7aa52 69 q31_t real1, real2, imag1, imag2; /* Temporary variables to hold input values */
emilmont 1:fdd22bb7aa52 70 q31_t out1, out2, out3, out4; /* Accumulators */
emilmont 1:fdd22bb7aa52 71 q63_t mul1, mul2, mul3, mul4; /* Temporary variables */
emilmont 1:fdd22bb7aa52 72
emilmont 1:fdd22bb7aa52 73
emilmont 1:fdd22bb7aa52 74 /*loop Unrolling */
emilmont 1:fdd22bb7aa52 75 blkCnt = numSamples >> 2u;
emilmont 1:fdd22bb7aa52 76
emilmont 1:fdd22bb7aa52 77 /* First part of the processing with loop unrolling. Compute 4 outputs at a time.
emilmont 1:fdd22bb7aa52 78 ** a second loop below computes the remaining 1 to 3 samples. */
emilmont 1:fdd22bb7aa52 79 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 80 {
emilmont 1:fdd22bb7aa52 81 /* read complex input from source buffer */
emilmont 1:fdd22bb7aa52 82 real1 = pSrc[0];
emilmont 1:fdd22bb7aa52 83 imag1 = pSrc[1];
emilmont 1:fdd22bb7aa52 84 real2 = pSrc[2];
emilmont 1:fdd22bb7aa52 85 imag2 = pSrc[3];
emilmont 1:fdd22bb7aa52 86
emilmont 1:fdd22bb7aa52 87 /* calculate power of input values */
emilmont 1:fdd22bb7aa52 88 mul1 = (q63_t) real1 *real1;
emilmont 1:fdd22bb7aa52 89 mul2 = (q63_t) imag1 *imag1;
emilmont 1:fdd22bb7aa52 90 mul3 = (q63_t) real2 *real2;
emilmont 1:fdd22bb7aa52 91 mul4 = (q63_t) imag2 *imag2;
emilmont 1:fdd22bb7aa52 92
emilmont 1:fdd22bb7aa52 93 /* get the result to 3.29 format */
emilmont 1:fdd22bb7aa52 94 out1 = (q31_t) (mul1 >> 33);
emilmont 1:fdd22bb7aa52 95 out2 = (q31_t) (mul2 >> 33);
emilmont 1:fdd22bb7aa52 96 out3 = (q31_t) (mul3 >> 33);
emilmont 1:fdd22bb7aa52 97 out4 = (q31_t) (mul4 >> 33);
emilmont 1:fdd22bb7aa52 98
emilmont 1:fdd22bb7aa52 99 /* add real and imaginary accumulators */
emilmont 1:fdd22bb7aa52 100 out1 = out1 + out2;
emilmont 1:fdd22bb7aa52 101 out3 = out3 + out4;
emilmont 1:fdd22bb7aa52 102
emilmont 1:fdd22bb7aa52 103 /* read complex input from source buffer */
emilmont 1:fdd22bb7aa52 104 real1 = pSrc[4];
emilmont 1:fdd22bb7aa52 105 imag1 = pSrc[5];
emilmont 1:fdd22bb7aa52 106 real2 = pSrc[6];
emilmont 1:fdd22bb7aa52 107 imag2 = pSrc[7];
emilmont 1:fdd22bb7aa52 108
emilmont 1:fdd22bb7aa52 109 /* calculate square root */
emilmont 1:fdd22bb7aa52 110 arm_sqrt_q31(out1, &pDst[0]);
emilmont 1:fdd22bb7aa52 111
emilmont 1:fdd22bb7aa52 112 /* calculate power of input values */
emilmont 1:fdd22bb7aa52 113 mul1 = (q63_t) real1 *real1;
emilmont 1:fdd22bb7aa52 114
emilmont 1:fdd22bb7aa52 115 /* calculate square root */
emilmont 1:fdd22bb7aa52 116 arm_sqrt_q31(out3, &pDst[1]);
emilmont 1:fdd22bb7aa52 117
emilmont 1:fdd22bb7aa52 118 /* calculate power of input values */
emilmont 1:fdd22bb7aa52 119 mul2 = (q63_t) imag1 *imag1;
emilmont 1:fdd22bb7aa52 120 mul3 = (q63_t) real2 *real2;
emilmont 1:fdd22bb7aa52 121 mul4 = (q63_t) imag2 *imag2;
emilmont 1:fdd22bb7aa52 122
emilmont 1:fdd22bb7aa52 123 /* get the result to 3.29 format */
emilmont 1:fdd22bb7aa52 124 out1 = (q31_t) (mul1 >> 33);
emilmont 1:fdd22bb7aa52 125 out2 = (q31_t) (mul2 >> 33);
emilmont 1:fdd22bb7aa52 126 out3 = (q31_t) (mul3 >> 33);
emilmont 1:fdd22bb7aa52 127 out4 = (q31_t) (mul4 >> 33);
emilmont 1:fdd22bb7aa52 128
emilmont 1:fdd22bb7aa52 129 /* add real and imaginary accumulators */
emilmont 1:fdd22bb7aa52 130 out1 = out1 + out2;
emilmont 1:fdd22bb7aa52 131 out3 = out3 + out4;
emilmont 1:fdd22bb7aa52 132
emilmont 1:fdd22bb7aa52 133 /* calculate square root */
emilmont 1:fdd22bb7aa52 134 arm_sqrt_q31(out1, &pDst[2]);
emilmont 1:fdd22bb7aa52 135
emilmont 1:fdd22bb7aa52 136 /* increment destination by 8 to process next samples */
emilmont 1:fdd22bb7aa52 137 pSrc += 8u;
emilmont 1:fdd22bb7aa52 138
emilmont 1:fdd22bb7aa52 139 /* calculate square root */
emilmont 1:fdd22bb7aa52 140 arm_sqrt_q31(out3, &pDst[3]);
emilmont 1:fdd22bb7aa52 141
emilmont 1:fdd22bb7aa52 142 /* increment destination by 4 to process next samples */
emilmont 1:fdd22bb7aa52 143 pDst += 4u;
emilmont 1:fdd22bb7aa52 144
emilmont 1:fdd22bb7aa52 145 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 146 blkCnt--;
emilmont 1:fdd22bb7aa52 147 }
emilmont 1:fdd22bb7aa52 148
emilmont 1:fdd22bb7aa52 149 /* If the numSamples is not a multiple of 4, compute any remaining output samples here.
emilmont 1:fdd22bb7aa52 150 ** No loop unrolling is used. */
emilmont 1:fdd22bb7aa52 151 blkCnt = numSamples % 0x4u;
emilmont 1:fdd22bb7aa52 152
emilmont 1:fdd22bb7aa52 153 #else
emilmont 1:fdd22bb7aa52 154
emilmont 1:fdd22bb7aa52 155 /* Run the below code for Cortex-M0 */
emilmont 1:fdd22bb7aa52 156 blkCnt = numSamples;
emilmont 1:fdd22bb7aa52 157
emilmont 1:fdd22bb7aa52 158 #endif /* #ifndef ARM_MATH_CM0 */
emilmont 1:fdd22bb7aa52 159
emilmont 1:fdd22bb7aa52 160 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 161 {
emilmont 1:fdd22bb7aa52 162 /* C[0] = sqrt(A[0] * A[0] + A[1] * A[1]) */
emilmont 1:fdd22bb7aa52 163 real = *pSrc++;
emilmont 1:fdd22bb7aa52 164 imag = *pSrc++;
emilmont 1:fdd22bb7aa52 165 acc0 = (q31_t) (((q63_t) real * real) >> 33);
emilmont 1:fdd22bb7aa52 166 acc1 = (q31_t) (((q63_t) imag * imag) >> 33);
emilmont 1:fdd22bb7aa52 167 /* store the result in 2.30 format in the destination buffer. */
emilmont 1:fdd22bb7aa52 168 arm_sqrt_q31(acc0 + acc1, pDst++);
emilmont 1:fdd22bb7aa52 169
emilmont 1:fdd22bb7aa52 170 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 171 blkCnt--;
emilmont 1:fdd22bb7aa52 172 }
emilmont 1:fdd22bb7aa52 173 }
emilmont 1:fdd22bb7aa52 174
emilmont 1:fdd22bb7aa52 175 /**
emilmont 1:fdd22bb7aa52 176 * @} end of cmplx_mag group
emilmont 1:fdd22bb7aa52 177 */