mbed official / mbed-dsp

CMSIS DSP library

Dependents:   performance_timer Surfboard_ gps2rtty Capstone ... more

Legacy Warning

This is an mbed 2 library. To learn more about mbed OS 5, visit the docs.

cmsis_dsp/ComplexMathFunctions/arm_cmplx_mag_squared_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_cmplx_mag_squared_q31.c
emilmont 1:fdd22bb7aa52 9 *
emilmont 2:da51fb522205 10 * Description: Q31 complex magnitude squared.
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_squared
emilmont 1:fdd22bb7aa52 41 * @{
emilmont 1:fdd22bb7aa52 42 */
emilmont 1:fdd22bb7aa52 43
emilmont 1:fdd22bb7aa52 44
emilmont 1:fdd22bb7aa52 45 /**
emilmont 1:fdd22bb7aa52 46 * @brief Q31 complex magnitude squared
emilmont 1:fdd22bb7aa52 47 * @param *pSrc points to the complex input vector
emilmont 1:fdd22bb7aa52 48 * @param *pDst points to the real output vector
emilmont 1:fdd22bb7aa52 49 * @param numSamples number of complex samples in the input vector
emilmont 1:fdd22bb7aa52 50 * @return none.
emilmont 1:fdd22bb7aa52 51 *
emilmont 1:fdd22bb7aa52 52 * <b>Scaling and Overflow Behavior:</b>
emilmont 1:fdd22bb7aa52 53 * \par
emilmont 1:fdd22bb7aa52 54 * The function implements 1.31 by 1.31 multiplications and finally output is converted into 3.29 format.
emilmont 1:fdd22bb7aa52 55 * Input down scaling is not required.
emilmont 1:fdd22bb7aa52 56 */
emilmont 1:fdd22bb7aa52 57
emilmont 1:fdd22bb7aa52 58 void arm_cmplx_mag_squared_q31(
emilmont 1:fdd22bb7aa52 59 q31_t * pSrc,
emilmont 1:fdd22bb7aa52 60 q31_t * pDst,
emilmont 1:fdd22bb7aa52 61 uint32_t numSamples)
emilmont 1:fdd22bb7aa52 62 {
emilmont 1:fdd22bb7aa52 63 q31_t real, imag; /* Temporary variables to store real and imaginary values */
emilmont 1:fdd22bb7aa52 64 q31_t acc0, acc1; /* Accumulators */
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 uint32_t blkCnt; /* loop counter */
emilmont 1:fdd22bb7aa52 70
emilmont 1:fdd22bb7aa52 71 /* loop Unrolling */
emilmont 1:fdd22bb7aa52 72 blkCnt = numSamples >> 2u;
emilmont 1:fdd22bb7aa52 73
emilmont 1:fdd22bb7aa52 74 /* First part of the processing with loop unrolling. Compute 4 outputs at a time.
emilmont 1:fdd22bb7aa52 75 ** a second loop below computes the remaining 1 to 3 samples. */
emilmont 1:fdd22bb7aa52 76 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 77 {
emilmont 1:fdd22bb7aa52 78 /* C[0] = (A[0] * A[0] + A[1] * A[1]) */
emilmont 1:fdd22bb7aa52 79 real = *pSrc++;
emilmont 1:fdd22bb7aa52 80 imag = *pSrc++;
emilmont 1:fdd22bb7aa52 81 acc0 = (q31_t) (((q63_t) real * real) >> 33);
emilmont 1:fdd22bb7aa52 82 acc1 = (q31_t) (((q63_t) imag * imag) >> 33);
emilmont 1:fdd22bb7aa52 83 /* store the result in 3.29 format in the destination buffer. */
emilmont 1:fdd22bb7aa52 84 *pDst++ = acc0 + acc1;
emilmont 1:fdd22bb7aa52 85
emilmont 1:fdd22bb7aa52 86 real = *pSrc++;
emilmont 1:fdd22bb7aa52 87 imag = *pSrc++;
emilmont 1:fdd22bb7aa52 88 acc0 = (q31_t) (((q63_t) real * real) >> 33);
emilmont 1:fdd22bb7aa52 89 acc1 = (q31_t) (((q63_t) imag * imag) >> 33);
emilmont 1:fdd22bb7aa52 90 /* store the result in 3.29 format in the destination buffer. */
emilmont 1:fdd22bb7aa52 91 *pDst++ = acc0 + acc1;
emilmont 1:fdd22bb7aa52 92
emilmont 1:fdd22bb7aa52 93 real = *pSrc++;
emilmont 1:fdd22bb7aa52 94 imag = *pSrc++;
emilmont 1:fdd22bb7aa52 95 acc0 = (q31_t) (((q63_t) real * real) >> 33);
emilmont 1:fdd22bb7aa52 96 acc1 = (q31_t) (((q63_t) imag * imag) >> 33);
emilmont 1:fdd22bb7aa52 97 /* store the result in 3.29 format in the destination buffer. */
emilmont 1:fdd22bb7aa52 98 *pDst++ = acc0 + acc1;
emilmont 1:fdd22bb7aa52 99
emilmont 1:fdd22bb7aa52 100 real = *pSrc++;
emilmont 1:fdd22bb7aa52 101 imag = *pSrc++;
emilmont 1:fdd22bb7aa52 102 acc0 = (q31_t) (((q63_t) real * real) >> 33);
emilmont 1:fdd22bb7aa52 103 acc1 = (q31_t) (((q63_t) imag * imag) >> 33);
emilmont 1:fdd22bb7aa52 104 /* store the result in 3.29 format in the destination buffer. */
emilmont 1:fdd22bb7aa52 105 *pDst++ = acc0 + acc1;
emilmont 1:fdd22bb7aa52 106
emilmont 1:fdd22bb7aa52 107 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 108 blkCnt--;
emilmont 1:fdd22bb7aa52 109 }
emilmont 1:fdd22bb7aa52 110
emilmont 1:fdd22bb7aa52 111 /* If the numSamples is not a multiple of 4, compute any remaining output samples here.
emilmont 1:fdd22bb7aa52 112 ** No loop unrolling is used. */
emilmont 1:fdd22bb7aa52 113 blkCnt = numSamples % 0x4u;
emilmont 1:fdd22bb7aa52 114
emilmont 1:fdd22bb7aa52 115 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 116 {
emilmont 1:fdd22bb7aa52 117 /* C[0] = (A[0] * A[0] + A[1] * A[1]) */
emilmont 1:fdd22bb7aa52 118 real = *pSrc++;
emilmont 1:fdd22bb7aa52 119 imag = *pSrc++;
emilmont 1:fdd22bb7aa52 120 acc0 = (q31_t) (((q63_t) real * real) >> 33);
emilmont 1:fdd22bb7aa52 121 acc1 = (q31_t) (((q63_t) imag * imag) >> 33);
emilmont 1:fdd22bb7aa52 122 /* store the result in 3.29 format in the destination buffer. */
emilmont 1:fdd22bb7aa52 123 *pDst++ = acc0 + acc1;
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 #else
emilmont 1:fdd22bb7aa52 130
emilmont 1:fdd22bb7aa52 131 /* Run the below code for Cortex-M0 */
emilmont 1:fdd22bb7aa52 132
emilmont 1:fdd22bb7aa52 133 while(numSamples > 0u)
emilmont 1:fdd22bb7aa52 134 {
emilmont 1:fdd22bb7aa52 135 /* out = ((real * real) + (imag * imag)) */
emilmont 1:fdd22bb7aa52 136 real = *pSrc++;
emilmont 1:fdd22bb7aa52 137 imag = *pSrc++;
emilmont 1:fdd22bb7aa52 138 acc0 = (q31_t) (((q63_t) real * real) >> 33);
emilmont 1:fdd22bb7aa52 139 acc1 = (q31_t) (((q63_t) imag * imag) >> 33);
emilmont 1:fdd22bb7aa52 140 /* store the result in 3.29 format in the destination buffer. */
emilmont 1:fdd22bb7aa52 141 *pDst++ = acc0 + acc1;
emilmont 1:fdd22bb7aa52 142
emilmont 1:fdd22bb7aa52 143 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 144 numSamples--;
emilmont 1:fdd22bb7aa52 145 }
emilmont 1:fdd22bb7aa52 146
emilmont 1:fdd22bb7aa52 147 #endif /* #ifndef ARM_MATH_CM0 */
emilmont 1:fdd22bb7aa52 148
emilmont 1:fdd22bb7aa52 149 }
emilmont 1:fdd22bb7aa52 150
emilmont 1:fdd22bb7aa52 151 /**
emilmont 1:fdd22bb7aa52 152 * @} end of cmplx_mag_squared group
emilmont 1:fdd22bb7aa52 153 */