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_q15.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_q15.c
emilmont 1:fdd22bb7aa52 9 *
emilmont 2:da51fb522205 10 * Description: Q15 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 * @brief Q15 complex magnitude squared
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 1.15 by 1.15 multiplications and finally output is converted into 3.13 format.
emilmont 1:fdd22bb7aa52 54 */
emilmont 1:fdd22bb7aa52 55
emilmont 1:fdd22bb7aa52 56 void arm_cmplx_mag_squared_q15(
emilmont 1:fdd22bb7aa52 57 q15_t * pSrc,
emilmont 1:fdd22bb7aa52 58 q15_t * pDst,
emilmont 1:fdd22bb7aa52 59 uint32_t numSamples)
emilmont 1:fdd22bb7aa52 60 {
emilmont 1:fdd22bb7aa52 61 q31_t acc0, acc1; /* Accumulators */
emilmont 1:fdd22bb7aa52 62
emilmont 1:fdd22bb7aa52 63 #ifndef ARM_MATH_CM0
emilmont 1:fdd22bb7aa52 64
emilmont 1:fdd22bb7aa52 65 /* Run the below code for Cortex-M4 and Cortex-M3 */
emilmont 1:fdd22bb7aa52 66 uint32_t blkCnt; /* loop counter */
emilmont 1:fdd22bb7aa52 67 q31_t in1, in2, in3, in4;
emilmont 1:fdd22bb7aa52 68 q31_t acc2, acc3;
emilmont 1:fdd22bb7aa52 69
emilmont 1:fdd22bb7aa52 70 /*loop Unrolling */
emilmont 1:fdd22bb7aa52 71 blkCnt = numSamples >> 2u;
emilmont 1:fdd22bb7aa52 72
emilmont 1:fdd22bb7aa52 73 /* First part of the processing with loop unrolling. Compute 4 outputs at a time.
emilmont 1:fdd22bb7aa52 74 ** a second loop below computes the remaining 1 to 3 samples. */
emilmont 1:fdd22bb7aa52 75 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 76 {
emilmont 1:fdd22bb7aa52 77 /* C[0] = (A[0] * A[0] + A[1] * A[1]) */
emilmont 1:fdd22bb7aa52 78 in1 = *__SIMD32(pSrc)++;
emilmont 1:fdd22bb7aa52 79 in2 = *__SIMD32(pSrc)++;
emilmont 1:fdd22bb7aa52 80 in3 = *__SIMD32(pSrc)++;
emilmont 1:fdd22bb7aa52 81 in4 = *__SIMD32(pSrc)++;
emilmont 1:fdd22bb7aa52 82
emilmont 1:fdd22bb7aa52 83 acc0 = __SMUAD(in1, in1);
emilmont 1:fdd22bb7aa52 84 acc1 = __SMUAD(in2, in2);
emilmont 1:fdd22bb7aa52 85 acc2 = __SMUAD(in3, in3);
emilmont 1:fdd22bb7aa52 86 acc3 = __SMUAD(in4, in4);
emilmont 1:fdd22bb7aa52 87
emilmont 1:fdd22bb7aa52 88 /* store the result in 3.13 format in the destination buffer. */
emilmont 1:fdd22bb7aa52 89 *pDst++ = (q15_t) (acc0 >> 17);
emilmont 1:fdd22bb7aa52 90 *pDst++ = (q15_t) (acc1 >> 17);
emilmont 1:fdd22bb7aa52 91 *pDst++ = (q15_t) (acc2 >> 17);
emilmont 1:fdd22bb7aa52 92 *pDst++ = (q15_t) (acc3 >> 17);
emilmont 1:fdd22bb7aa52 93
emilmont 1:fdd22bb7aa52 94 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 95 blkCnt--;
emilmont 1:fdd22bb7aa52 96 }
emilmont 1:fdd22bb7aa52 97
emilmont 1:fdd22bb7aa52 98 /* If the numSamples is not a multiple of 4, compute any remaining output samples here.
emilmont 1:fdd22bb7aa52 99 ** No loop unrolling is used. */
emilmont 1:fdd22bb7aa52 100 blkCnt = numSamples % 0x4u;
emilmont 1:fdd22bb7aa52 101
emilmont 1:fdd22bb7aa52 102 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 103 {
emilmont 1:fdd22bb7aa52 104 /* C[0] = (A[0] * A[0] + A[1] * A[1]) */
emilmont 1:fdd22bb7aa52 105 in1 = *__SIMD32(pSrc)++;
emilmont 1:fdd22bb7aa52 106 acc0 = __SMUAD(in1, in1);
emilmont 1:fdd22bb7aa52 107
emilmont 1:fdd22bb7aa52 108 /* store the result in 3.13 format in the destination buffer. */
emilmont 1:fdd22bb7aa52 109 *pDst++ = (q15_t) (acc0 >> 17);
emilmont 1:fdd22bb7aa52 110
emilmont 1:fdd22bb7aa52 111 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 112 blkCnt--;
emilmont 1:fdd22bb7aa52 113 }
emilmont 1:fdd22bb7aa52 114
emilmont 1:fdd22bb7aa52 115 #else
emilmont 1:fdd22bb7aa52 116
emilmont 1:fdd22bb7aa52 117 /* Run the below code for Cortex-M0 */
emilmont 1:fdd22bb7aa52 118 q15_t real, imag; /* Temporary variables to store real and imaginary values */
emilmont 1:fdd22bb7aa52 119
emilmont 1:fdd22bb7aa52 120 while(numSamples > 0u)
emilmont 1:fdd22bb7aa52 121 {
emilmont 1:fdd22bb7aa52 122 /* out = ((real * real) + (imag * imag)) */
emilmont 1:fdd22bb7aa52 123 real = *pSrc++;
emilmont 1:fdd22bb7aa52 124 imag = *pSrc++;
emilmont 1:fdd22bb7aa52 125 acc0 = (real * real);
emilmont 1:fdd22bb7aa52 126 acc1 = (imag * imag);
emilmont 1:fdd22bb7aa52 127 /* store the result in 3.13 format in the destination buffer. */
emilmont 1:fdd22bb7aa52 128 *pDst++ = (q15_t) (((q63_t) acc0 + acc1) >> 17);
emilmont 1:fdd22bb7aa52 129
emilmont 1:fdd22bb7aa52 130 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 131 numSamples--;
emilmont 1:fdd22bb7aa52 132 }
emilmont 1:fdd22bb7aa52 133
emilmont 1:fdd22bb7aa52 134 #endif /* #ifndef ARM_MATH_CM0 */
emilmont 1:fdd22bb7aa52 135
emilmont 1:fdd22bb7aa52 136 }
emilmont 1:fdd22bb7aa52 137
emilmont 1:fdd22bb7aa52 138 /**
emilmont 1:fdd22bb7aa52 139 * @} end of cmplx_mag_squared group
emilmont 1:fdd22bb7aa52 140 */