CMSIS DSP Library from CMSIS 2.0. See http://www.onarm.com/cmsis/ for full details

Dependents:   K22F_DSP_Matrix_least_square BNO055-ELEC3810 1BNO055 ECE4180Project--Slave2 ... more

Committer:
simon
Date:
Thu Mar 10 15:07:50 2011 +0000
Revision:
0:1014af42efd9

        

Who changed what in which revision?

UserRevisionLine numberNew contents of line
simon 0:1014af42efd9 1 /* ----------------------------------------------------------------------
simon 0:1014af42efd9 2 * Copyright (C) 2010 ARM Limited. All rights reserved.
simon 0:1014af42efd9 3 *
simon 0:1014af42efd9 4 * $Date: 29. November 2010
simon 0:1014af42efd9 5 * $Revision: V1.0.3
simon 0:1014af42efd9 6 *
simon 0:1014af42efd9 7 * Project: CMSIS DSP Library
simon 0:1014af42efd9 8 * Title: arm_cmplx_dot_prod_f32.c
simon 0:1014af42efd9 9 *
simon 0:1014af42efd9 10 * Description: Floating-point complex dot product
simon 0:1014af42efd9 11 *
simon 0:1014af42efd9 12 * Target Processor: Cortex-M4/Cortex-M3
simon 0:1014af42efd9 13 *
simon 0:1014af42efd9 14 * Version 1.0.3 2010/11/29
simon 0:1014af42efd9 15 * Re-organized the CMSIS folders and updated documentation.
simon 0:1014af42efd9 16 *
simon 0:1014af42efd9 17 * Version 1.0.2 2010/11/11
simon 0:1014af42efd9 18 * Documentation updated.
simon 0:1014af42efd9 19 *
simon 0:1014af42efd9 20 * Version 1.0.1 2010/10/05
simon 0:1014af42efd9 21 * Production release and review comments incorporated.
simon 0:1014af42efd9 22 *
simon 0:1014af42efd9 23 * Version 1.0.0 2010/09/20
simon 0:1014af42efd9 24 * Production release and review comments incorporated.
simon 0:1014af42efd9 25 * ---------------------------------------------------------------------------- */
simon 0:1014af42efd9 26
simon 0:1014af42efd9 27 #include "arm_math.h"
simon 0:1014af42efd9 28
simon 0:1014af42efd9 29 /**
simon 0:1014af42efd9 30 * @ingroup groupCmplxMath
simon 0:1014af42efd9 31 */
simon 0:1014af42efd9 32
simon 0:1014af42efd9 33 /**
simon 0:1014af42efd9 34 * @defgroup cmplx_dot_prod Complex Dot Product
simon 0:1014af42efd9 35 *
simon 0:1014af42efd9 36 * Computes the dot product of two complex vectors.
simon 0:1014af42efd9 37 * The vectors are multiplied element-by-element and then summed.
simon 0:1014af42efd9 38 *
simon 0:1014af42efd9 39 * The <code>pSrcA</code> points to the first complex input vector and
simon 0:1014af42efd9 40 * <code>pSrcB</code> points to the second complex input vector.
simon 0:1014af42efd9 41 * <code>numSamples</code> specifies the number of complex samples
simon 0:1014af42efd9 42 * and the data in each array is stored in an interleaved fashion
simon 0:1014af42efd9 43 * (real, imag, real, imag, ...).
simon 0:1014af42efd9 44 * Each array has a total of <code>2*numSamples</code> values.
simon 0:1014af42efd9 45 *
simon 0:1014af42efd9 46 * The underlying algorithm is used:
simon 0:1014af42efd9 47 * <pre>
simon 0:1014af42efd9 48 * realResult=0;
simon 0:1014af42efd9 49 * imagResult=0;
simon 0:1014af42efd9 50 * for(n=0; n<numSamples; n++) {
simon 0:1014af42efd9 51 * realResult += pSrcA[(2*n)+0]*pSrcB[(2*n)+0] - pSrcA[(2*n)+1]*pSrcB[(2*n)+1];
simon 0:1014af42efd9 52 * imagResult += pSrcA[(2*n)+0]*pSrcB[(2*n)+1] + pSrcA[(2*n)+1]*pSrcB[(2*n)+0];
simon 0:1014af42efd9 53 * }
simon 0:1014af42efd9 54 * </pre>
simon 0:1014af42efd9 55 *
simon 0:1014af42efd9 56 * There are separate functions for floating-point, Q15, and Q31 data types.
simon 0:1014af42efd9 57 */
simon 0:1014af42efd9 58
simon 0:1014af42efd9 59 /**
simon 0:1014af42efd9 60 * @addtogroup cmplx_dot_prod
simon 0:1014af42efd9 61 * @{
simon 0:1014af42efd9 62 */
simon 0:1014af42efd9 63
simon 0:1014af42efd9 64 /**
simon 0:1014af42efd9 65 * @brief Floating-point complex dot product
simon 0:1014af42efd9 66 * @param *pSrcA points to the first input vector
simon 0:1014af42efd9 67 * @param *pSrcB points to the second input vector
simon 0:1014af42efd9 68 * @param numSamples number of complex samples in each vector
simon 0:1014af42efd9 69 * @param *realResult real part of the result returned here
simon 0:1014af42efd9 70 * @param *imagResult imaginary part of the result returned here
simon 0:1014af42efd9 71 * @return none.
simon 0:1014af42efd9 72 */
simon 0:1014af42efd9 73
simon 0:1014af42efd9 74 void arm_cmplx_dot_prod_f32(
simon 0:1014af42efd9 75 float32_t * pSrcA,
simon 0:1014af42efd9 76 float32_t * pSrcB,
simon 0:1014af42efd9 77 uint32_t numSamples,
simon 0:1014af42efd9 78 float32_t * realResult,
simon 0:1014af42efd9 79 float32_t * imagResult)
simon 0:1014af42efd9 80 {
simon 0:1014af42efd9 81 float32_t real_sum = 0.0f, imag_sum = 0.0f; /* Temporary result storage */
simon 0:1014af42efd9 82 uint32_t blkCnt; /* loop counter */
simon 0:1014af42efd9 83
simon 0:1014af42efd9 84 /*loop Unrolling */
simon 0:1014af42efd9 85 blkCnt = numSamples >> 2u;
simon 0:1014af42efd9 86
simon 0:1014af42efd9 87 /* First part of the processing with loop unrolling. Compute 4 outputs at a time.
simon 0:1014af42efd9 88 ** a second loop below computes the remaining 1 to 3 samples. */
simon 0:1014af42efd9 89 while(blkCnt > 0u)
simon 0:1014af42efd9 90 {
simon 0:1014af42efd9 91 /* CReal = A[0]* B[0] + A[2]* B[2] + A[4]* B[4] + .....+ A[numSamples-2]* B[numSamples-2] */
simon 0:1014af42efd9 92 real_sum += (*pSrcA++) * (*pSrcB++);
simon 0:1014af42efd9 93 /* CImag = A[1]* B[1] + A[3]* B[3] + A[5]* B[5] + .....+ A[numSamples-1]* B[numSamples-1] */
simon 0:1014af42efd9 94 imag_sum += (*pSrcA++) * (*pSrcB++);
simon 0:1014af42efd9 95
simon 0:1014af42efd9 96 real_sum += (*pSrcA++) * (*pSrcB++);
simon 0:1014af42efd9 97 imag_sum += (*pSrcA++) * (*pSrcB++);
simon 0:1014af42efd9 98
simon 0:1014af42efd9 99 real_sum += (*pSrcA++) * (*pSrcB++);
simon 0:1014af42efd9 100 imag_sum += (*pSrcA++) * (*pSrcB++);
simon 0:1014af42efd9 101
simon 0:1014af42efd9 102 real_sum += (*pSrcA++) * (*pSrcB++);
simon 0:1014af42efd9 103 imag_sum += (*pSrcA++) * (*pSrcB++);
simon 0:1014af42efd9 104
simon 0:1014af42efd9 105 /* Decrement the loop counter */
simon 0:1014af42efd9 106 blkCnt--;
simon 0:1014af42efd9 107 }
simon 0:1014af42efd9 108
simon 0:1014af42efd9 109 /* If the numSamples is not a multiple of 4, compute any remaining output samples here.
simon 0:1014af42efd9 110 ** No loop unrolling is used. */
simon 0:1014af42efd9 111 blkCnt = numSamples % 0x4u;
simon 0:1014af42efd9 112
simon 0:1014af42efd9 113 while(blkCnt > 0u)
simon 0:1014af42efd9 114 {
simon 0:1014af42efd9 115 /* CReal = A[0]* B[0] + A[2]* B[2] + A[4]* B[4] + .....+ A[numSamples-2]* B[numSamples-2] */
simon 0:1014af42efd9 116 real_sum += (*pSrcA++) * (*pSrcB++);
simon 0:1014af42efd9 117 /* CImag = A[1]* B[1] + A[3]* B[3] + A[5]* B[5] + .....+ A[numSamples-1]* B[numSamples-1] */
simon 0:1014af42efd9 118 imag_sum += (*pSrcA++) * (*pSrcB++);
simon 0:1014af42efd9 119
simon 0:1014af42efd9 120
simon 0:1014af42efd9 121 /* Decrement the loop counter */
simon 0:1014af42efd9 122 blkCnt--;
simon 0:1014af42efd9 123 }
simon 0:1014af42efd9 124
simon 0:1014af42efd9 125 /* Store the real and imaginary results in the destination buffers */
simon 0:1014af42efd9 126 *realResult = real_sum;
simon 0:1014af42efd9 127 *imagResult = imag_sum;
simon 0:1014af42efd9 128 }
simon 0:1014af42efd9 129
simon 0:1014af42efd9 130 /**
simon 0:1014af42efd9 131 * @} end of cmplx_dot_prod group
simon 0:1014af42efd9 132 */