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_dot_prod_f32.c@3:7a284390b0ce, 2013-11-08 (annotated)

Committer:
mbed_official
Date:
Fri Nov 08 13:45:10 2013 +0000
Revision:
3:7a284390b0ce
Parent:
2:da51fb522205
Child:
5:3762170b6d4d
Synchronized with git revision e69956aba2f68a2a26ac26b051f8d349deaa1ce8

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 2:da51fb522205 7 * Project: CMSIS DSP Library
emilmont 2:da51fb522205 8 * Title: arm_cmplx_dot_prod_f32.c
emilmont 1:fdd22bb7aa52 9 *
emilmont 2:da51fb522205 10 * Description: Floating-point complex dot product
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
emilmont 1:fdd22bb7aa52 41 #include "arm_math.h"
emilmont 1:fdd22bb7aa52 42
emilmont 1:fdd22bb7aa52 43 /**
emilmont 1:fdd22bb7aa52 44 * @ingroup groupCmplxMath
emilmont 1:fdd22bb7aa52 45 */
emilmont 1:fdd22bb7aa52 46
emilmont 1:fdd22bb7aa52 47 /**
emilmont 1:fdd22bb7aa52 48 * @defgroup cmplx_dot_prod Complex Dot Product
emilmont 1:fdd22bb7aa52 49 *
emilmont 1:fdd22bb7aa52 50 * Computes the dot product of two complex vectors.
emilmont 1:fdd22bb7aa52 51 * The vectors are multiplied element-by-element and then summed.
emilmont 1:fdd22bb7aa52 52 *
emilmont 1:fdd22bb7aa52 53 * The <code>pSrcA</code> points to the first complex input vector and
emilmont 1:fdd22bb7aa52 54 * <code>pSrcB</code> points to the second complex input vector.
emilmont 1:fdd22bb7aa52 55 * <code>numSamples</code> specifies the number of complex samples
emilmont 1:fdd22bb7aa52 56 * and the data in each array is stored in an interleaved fashion
emilmont 1:fdd22bb7aa52 57 * (real, imag, real, imag, ...).
emilmont 1:fdd22bb7aa52 58 * Each array has a total of <code>2*numSamples</code> values.
emilmont 1:fdd22bb7aa52 59 *
emilmont 1:fdd22bb7aa52 60 * The underlying algorithm is used:
emilmont 1:fdd22bb7aa52 61 * <pre>
emilmont 1:fdd22bb7aa52 62 * realResult=0;
emilmont 1:fdd22bb7aa52 63 * imagResult=0;
emilmont 1:fdd22bb7aa52 64 * for(n=0; n<numSamples; n++) {
emilmont 1:fdd22bb7aa52 65 * realResult += pSrcA[(2*n)+0]*pSrcB[(2*n)+0] - pSrcA[(2*n)+1]*pSrcB[(2*n)+1];
emilmont 1:fdd22bb7aa52 66 * imagResult += pSrcA[(2*n)+0]*pSrcB[(2*n)+1] + pSrcA[(2*n)+1]*pSrcB[(2*n)+0];
emilmont 1:fdd22bb7aa52 67 * }
emilmont 1:fdd22bb7aa52 68 * </pre>
emilmont 1:fdd22bb7aa52 69 *
emilmont 1:fdd22bb7aa52 70 * There are separate functions for floating-point, Q15, and Q31 data types.
emilmont 1:fdd22bb7aa52 71 */
emilmont 1:fdd22bb7aa52 72
emilmont 1:fdd22bb7aa52 73 /**
emilmont 1:fdd22bb7aa52 74 * @addtogroup cmplx_dot_prod
emilmont 1:fdd22bb7aa52 75 * @{
emilmont 1:fdd22bb7aa52 76 */
emilmont 1:fdd22bb7aa52 77
emilmont 1:fdd22bb7aa52 78 /**
emilmont 1:fdd22bb7aa52 79 * @brief Floating-point complex dot product
emilmont 1:fdd22bb7aa52 80 * @param *pSrcA points to the first input vector
emilmont 1:fdd22bb7aa52 81 * @param *pSrcB points to the second input vector
emilmont 1:fdd22bb7aa52 82 * @param numSamples number of complex samples in each vector
emilmont 1:fdd22bb7aa52 83 * @param *realResult real part of the result returned here
emilmont 1:fdd22bb7aa52 84 * @param *imagResult imaginary part of the result returned here
emilmont 1:fdd22bb7aa52 85 * @return none.
emilmont 1:fdd22bb7aa52 86 */
emilmont 1:fdd22bb7aa52 87
emilmont 1:fdd22bb7aa52 88 void arm_cmplx_dot_prod_f32(
emilmont 1:fdd22bb7aa52 89 float32_t * pSrcA,
emilmont 1:fdd22bb7aa52 90 float32_t * pSrcB,
emilmont 1:fdd22bb7aa52 91 uint32_t numSamples,
emilmont 1:fdd22bb7aa52 92 float32_t * realResult,
emilmont 1:fdd22bb7aa52 93 float32_t * imagResult)
emilmont 1:fdd22bb7aa52 94 {
emilmont 1:fdd22bb7aa52 95 float32_t real_sum = 0.0f, imag_sum = 0.0f; /* Temporary result storage */
emilmont 1:fdd22bb7aa52 96
mbed_official 3:7a284390b0ce 97 #ifndef ARM_MATH_CM0_FAMILY
emilmont 1:fdd22bb7aa52 98
emilmont 1:fdd22bb7aa52 99 /* Run the below code for Cortex-M4 and Cortex-M3 */
emilmont 1:fdd22bb7aa52 100 uint32_t blkCnt; /* loop counter */
emilmont 1:fdd22bb7aa52 101
emilmont 1:fdd22bb7aa52 102 /*loop Unrolling */
emilmont 1:fdd22bb7aa52 103 blkCnt = numSamples >> 2u;
emilmont 1:fdd22bb7aa52 104
emilmont 1:fdd22bb7aa52 105 /* First part of the processing with loop unrolling. Compute 4 outputs at a time.
emilmont 1:fdd22bb7aa52 106 ** a second loop below computes the remaining 1 to 3 samples. */
emilmont 1:fdd22bb7aa52 107 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 108 {
emilmont 1:fdd22bb7aa52 109 /* CReal = A[0]* B[0] + A[2]* B[2] + A[4]* B[4] + .....+ A[numSamples-2]* B[numSamples-2] */
emilmont 1:fdd22bb7aa52 110 real_sum += (*pSrcA++) * (*pSrcB++);
emilmont 1:fdd22bb7aa52 111 /* CImag = A[1]* B[1] + A[3]* B[3] + A[5]* B[5] + .....+ A[numSamples-1]* B[numSamples-1] */
emilmont 1:fdd22bb7aa52 112 imag_sum += (*pSrcA++) * (*pSrcB++);
emilmont 1:fdd22bb7aa52 113
emilmont 1:fdd22bb7aa52 114 real_sum += (*pSrcA++) * (*pSrcB++);
emilmont 1:fdd22bb7aa52 115 imag_sum += (*pSrcA++) * (*pSrcB++);
emilmont 1:fdd22bb7aa52 116
emilmont 1:fdd22bb7aa52 117 real_sum += (*pSrcA++) * (*pSrcB++);
emilmont 1:fdd22bb7aa52 118 imag_sum += (*pSrcA++) * (*pSrcB++);
emilmont 1:fdd22bb7aa52 119
emilmont 1:fdd22bb7aa52 120 real_sum += (*pSrcA++) * (*pSrcB++);
emilmont 1:fdd22bb7aa52 121 imag_sum += (*pSrcA++) * (*pSrcB++);
emilmont 1:fdd22bb7aa52 122
emilmont 1:fdd22bb7aa52 123 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 124 blkCnt--;
emilmont 1:fdd22bb7aa52 125 }
emilmont 1:fdd22bb7aa52 126
emilmont 1:fdd22bb7aa52 127 /* If the numSamples is not a multiple of 4, compute any remaining output samples here.
emilmont 1:fdd22bb7aa52 128 ** No loop unrolling is used. */
emilmont 1:fdd22bb7aa52 129 blkCnt = numSamples % 0x4u;
emilmont 1:fdd22bb7aa52 130
emilmont 1:fdd22bb7aa52 131 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 132 {
emilmont 1:fdd22bb7aa52 133 /* CReal = A[0]* B[0] + A[2]* B[2] + A[4]* B[4] + .....+ A[numSamples-2]* B[numSamples-2] */
emilmont 1:fdd22bb7aa52 134 real_sum += (*pSrcA++) * (*pSrcB++);
emilmont 1:fdd22bb7aa52 135 /* CImag = A[1]* B[1] + A[3]* B[3] + A[5]* B[5] + .....+ A[numSamples-1]* B[numSamples-1] */
emilmont 1:fdd22bb7aa52 136 imag_sum += (*pSrcA++) * (*pSrcB++);
emilmont 1:fdd22bb7aa52 137
emilmont 1:fdd22bb7aa52 138
emilmont 1:fdd22bb7aa52 139 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 140 blkCnt--;
emilmont 1:fdd22bb7aa52 141 }
emilmont 1:fdd22bb7aa52 142
emilmont 1:fdd22bb7aa52 143 #else
emilmont 1:fdd22bb7aa52 144
emilmont 1:fdd22bb7aa52 145 /* Run the below code for Cortex-M0 */
emilmont 1:fdd22bb7aa52 146
emilmont 1:fdd22bb7aa52 147 while(numSamples > 0u)
emilmont 1:fdd22bb7aa52 148 {
emilmont 1:fdd22bb7aa52 149 /* CReal = A[0]* B[0] + A[2]* B[2] + A[4]* B[4] + .....+ A[numSamples-2]* B[numSamples-2] */
emilmont 1:fdd22bb7aa52 150 real_sum += (*pSrcA++) * (*pSrcB++);
emilmont 1:fdd22bb7aa52 151 /* CImag = A[1]* B[1] + A[3]* B[3] + A[5]* B[5] + .....+ A[numSamples-1]* B[numSamples-1] */
emilmont 1:fdd22bb7aa52 152 imag_sum += (*pSrcA++) * (*pSrcB++);
emilmont 1:fdd22bb7aa52 153
emilmont 1:fdd22bb7aa52 154
emilmont 1:fdd22bb7aa52 155 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 156 numSamples--;
emilmont 1:fdd22bb7aa52 157 }
emilmont 1:fdd22bb7aa52 158
mbed_official 3:7a284390b0ce 159 #endif /* #ifndef ARM_MATH_CM0_FAMILY */
emilmont 1:fdd22bb7aa52 160
emilmont 1:fdd22bb7aa52 161 /* Store the real and imaginary results in the destination buffers */
emilmont 1:fdd22bb7aa52 162 *realResult = real_sum;
emilmont 1:fdd22bb7aa52 163 *imagResult = imag_sum;
emilmont 1:fdd22bb7aa52 164 }
emilmont 1:fdd22bb7aa52 165
emilmont 1:fdd22bb7aa52 166 /**
emilmont 1:fdd22bb7aa52 167 * @} end of cmplx_dot_prod group
emilmont 1:fdd22bb7aa52 168 */