Laxmi Kant Tiwari / mbed-dsp

CMSIS DSP Lib

Fork of mbed-dsp by mbed official

cmsis_dsp/ComplexMathFunctions/arm_cmplx_mag_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_cmplx_mag_q15.c
emilmont 1:fdd22bb7aa52 9 *
emilmont 1:fdd22bb7aa52 10 * Description: Q15 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 /**
emilmont 1:fdd22bb7aa52 46 * @brief Q15 complex magnitude
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 1.15 by 1.15 multiplications and finally output is converted into 2.14 format.
emilmont 1:fdd22bb7aa52 55 */
emilmont 1:fdd22bb7aa52 56
emilmont 1:fdd22bb7aa52 57 void arm_cmplx_mag_q15(
emilmont 1:fdd22bb7aa52 58 q15_t * pSrc,
emilmont 1:fdd22bb7aa52 59 q15_t * pDst,
emilmont 1:fdd22bb7aa52 60 uint32_t numSamples)
emilmont 1:fdd22bb7aa52 61 {
emilmont 1:fdd22bb7aa52 62 q31_t acc0, acc1; /* Accumulators */
emilmont 1:fdd22bb7aa52 63
emilmont 1:fdd22bb7aa52 64 #ifndef ARM_MATH_CM0
emilmont 1:fdd22bb7aa52 65
emilmont 1:fdd22bb7aa52 66 /* Run the below code for Cortex-M4 and Cortex-M3 */
emilmont 1:fdd22bb7aa52 67 uint32_t blkCnt; /* loop counter */
emilmont 1:fdd22bb7aa52 68 q31_t in1, in2, in3, in4;
emilmont 1:fdd22bb7aa52 69 q31_t acc2, acc3;
emilmont 1:fdd22bb7aa52 70
emilmont 1:fdd22bb7aa52 71
emilmont 1:fdd22bb7aa52 72 /*loop Unrolling */
emilmont 1:fdd22bb7aa52 73 blkCnt = numSamples >> 2u;
emilmont 1:fdd22bb7aa52 74
emilmont 1:fdd22bb7aa52 75 /* First part of the processing with loop unrolling. Compute 4 outputs at a time.
emilmont 1:fdd22bb7aa52 76 ** a second loop below computes the remaining 1 to 3 samples. */
emilmont 1:fdd22bb7aa52 77 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 78 {
emilmont 1:fdd22bb7aa52 79
emilmont 1:fdd22bb7aa52 80 /* C[0] = sqrt(A[0] * A[0] + A[1] * A[1]) */
emilmont 1:fdd22bb7aa52 81 in1 = *__SIMD32(pSrc)++;
emilmont 1:fdd22bb7aa52 82 in2 = *__SIMD32(pSrc)++;
emilmont 1:fdd22bb7aa52 83 in3 = *__SIMD32(pSrc)++;
emilmont 1:fdd22bb7aa52 84 in4 = *__SIMD32(pSrc)++;
emilmont 1:fdd22bb7aa52 85
emilmont 1:fdd22bb7aa52 86 acc0 = __SMUAD(in1, in1);
emilmont 1:fdd22bb7aa52 87 acc1 = __SMUAD(in2, in2);
emilmont 1:fdd22bb7aa52 88 acc2 = __SMUAD(in3, in3);
emilmont 1:fdd22bb7aa52 89 acc3 = __SMUAD(in4, in4);
emilmont 1:fdd22bb7aa52 90
emilmont 1:fdd22bb7aa52 91 /* store the result in 2.14 format in the destination buffer. */
emilmont 1:fdd22bb7aa52 92 arm_sqrt_q15((q15_t) ((acc0) >> 17), pDst++);
emilmont 1:fdd22bb7aa52 93 arm_sqrt_q15((q15_t) ((acc1) >> 17), pDst++);
emilmont 1:fdd22bb7aa52 94 arm_sqrt_q15((q15_t) ((acc2) >> 17), pDst++);
emilmont 1:fdd22bb7aa52 95 arm_sqrt_q15((q15_t) ((acc3) >> 17), pDst++);
emilmont 1:fdd22bb7aa52 96
emilmont 1:fdd22bb7aa52 97 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 98 blkCnt--;
emilmont 1:fdd22bb7aa52 99 }
emilmont 1:fdd22bb7aa52 100
emilmont 1:fdd22bb7aa52 101 /* If the numSamples is not a multiple of 4, compute any remaining output samples here.
emilmont 1:fdd22bb7aa52 102 ** No loop unrolling is used. */
emilmont 1:fdd22bb7aa52 103 blkCnt = numSamples % 0x4u;
emilmont 1:fdd22bb7aa52 104
emilmont 1:fdd22bb7aa52 105 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 106 {
emilmont 1:fdd22bb7aa52 107 /* C[0] = sqrt(A[0] * A[0] + A[1] * A[1]) */
emilmont 1:fdd22bb7aa52 108 in1 = *__SIMD32(pSrc)++;
emilmont 1:fdd22bb7aa52 109 acc0 = __SMUAD(in1, in1);
emilmont 1:fdd22bb7aa52 110
emilmont 1:fdd22bb7aa52 111 /* store the result in 2.14 format in the destination buffer. */
emilmont 1:fdd22bb7aa52 112 arm_sqrt_q15((q15_t) (acc0 >> 17), pDst++);
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 #else
emilmont 1:fdd22bb7aa52 119
emilmont 1:fdd22bb7aa52 120 /* Run the below code for Cortex-M0 */
emilmont 1:fdd22bb7aa52 121 q15_t real, imag; /* Temporary variables to hold input values */
emilmont 1:fdd22bb7aa52 122
emilmont 1:fdd22bb7aa52 123 while(numSamples > 0u)
emilmont 1:fdd22bb7aa52 124 {
emilmont 1:fdd22bb7aa52 125 /* out = sqrt(real * real + imag * imag) */
emilmont 1:fdd22bb7aa52 126 real = *pSrc++;
emilmont 1:fdd22bb7aa52 127 imag = *pSrc++;
emilmont 1:fdd22bb7aa52 128
emilmont 1:fdd22bb7aa52 129 acc0 = (real * real);
emilmont 1:fdd22bb7aa52 130 acc1 = (imag * imag);
emilmont 1:fdd22bb7aa52 131
emilmont 1:fdd22bb7aa52 132 /* store the result in 2.14 format in the destination buffer. */
emilmont 1:fdd22bb7aa52 133 arm_sqrt_q15((q15_t) (((q63_t) acc0 + acc1) >> 17), pDst++);
emilmont 1:fdd22bb7aa52 134
emilmont 1:fdd22bb7aa52 135 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 136 numSamples--;
emilmont 1:fdd22bb7aa52 137 }
emilmont 1:fdd22bb7aa52 138
emilmont 1:fdd22bb7aa52 139 #endif /* #ifndef ARM_MATH_CM0 */
emilmont 1:fdd22bb7aa52 140
emilmont 1:fdd22bb7aa52 141 }
emilmont 1:fdd22bb7aa52 142
emilmont 1:fdd22bb7aa52 143 /**
emilmont 1:fdd22bb7aa52 144 * @} end of cmplx_mag group
emilmont 1:fdd22bb7aa52 145 */