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_mult_cmplx_f32.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_mult_cmplx_f32.c
emilmont 1:fdd22bb7aa52 9 *
emilmont 1:fdd22bb7aa52 10 * Description: Floating-point complex-by-complex multiplication
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 #include "arm_math.h"
emilmont 1:fdd22bb7aa52 33
emilmont 1:fdd22bb7aa52 34 /**
emilmont 1:fdd22bb7aa52 35 * @ingroup groupCmplxMath
emilmont 1:fdd22bb7aa52 36 */
emilmont 1:fdd22bb7aa52 37
emilmont 1:fdd22bb7aa52 38 /**
emilmont 1:fdd22bb7aa52 39 * @defgroup CmplxByCmplxMult Complex-by-Complex Multiplication
emilmont 1:fdd22bb7aa52 40 *
emilmont 1:fdd22bb7aa52 41 * Multiplies a complex vector by another complex vector and generates a complex result.
emilmont 1:fdd22bb7aa52 42 * The data in the complex arrays is stored in an interleaved fashion
emilmont 1:fdd22bb7aa52 43 * (real, imag, real, imag, ...).
emilmont 1:fdd22bb7aa52 44 * The parameter <code>numSamples</code> represents the number of complex
emilmont 1:fdd22bb7aa52 45 * samples processed. The complex arrays have a total of <code>2*numSamples</code>
emilmont 1:fdd22bb7aa52 46 * real values.
emilmont 1:fdd22bb7aa52 47 *
emilmont 1:fdd22bb7aa52 48 * The underlying algorithm is used:
emilmont 1:fdd22bb7aa52 49 *
emilmont 1:fdd22bb7aa52 50 * <pre>
emilmont 1:fdd22bb7aa52 51 * for(n=0; n<numSamples; n++) {
emilmont 1:fdd22bb7aa52 52 * pDst[(2*n)+0] = pSrcA[(2*n)+0] * pSrcB[(2*n)+0] - pSrcA[(2*n)+1] * pSrcB[(2*n)+1];
emilmont 1:fdd22bb7aa52 53 * pDst[(2*n)+1] = pSrcA[(2*n)+0] * pSrcB[(2*n)+1] + pSrcA[(2*n)+1] * pSrcB[(2*n)+0];
emilmont 1:fdd22bb7aa52 54 * }
emilmont 1:fdd22bb7aa52 55 * </pre>
emilmont 1:fdd22bb7aa52 56 *
emilmont 1:fdd22bb7aa52 57 * There are separate functions for floating-point, Q15, and Q31 data types.
emilmont 1:fdd22bb7aa52 58 */
emilmont 1:fdd22bb7aa52 59
emilmont 1:fdd22bb7aa52 60 /**
emilmont 1:fdd22bb7aa52 61 * @addtogroup CmplxByCmplxMult
emilmont 1:fdd22bb7aa52 62 * @{
emilmont 1:fdd22bb7aa52 63 */
emilmont 1:fdd22bb7aa52 64
emilmont 1:fdd22bb7aa52 65
emilmont 1:fdd22bb7aa52 66 /**
emilmont 1:fdd22bb7aa52 67 * @brief Floating-point complex-by-complex multiplication
emilmont 1:fdd22bb7aa52 68 * @param[in] *pSrcA points to the first input vector
emilmont 1:fdd22bb7aa52 69 * @param[in] *pSrcB points to the second input vector
emilmont 1:fdd22bb7aa52 70 * @param[out] *pDst points to the output vector
emilmont 1:fdd22bb7aa52 71 * @param[in] numSamples number of complex samples in each vector
emilmont 1:fdd22bb7aa52 72 * @return none.
emilmont 1:fdd22bb7aa52 73 */
emilmont 1:fdd22bb7aa52 74
emilmont 1:fdd22bb7aa52 75 void arm_cmplx_mult_cmplx_f32(
emilmont 1:fdd22bb7aa52 76 float32_t * pSrcA,
emilmont 1:fdd22bb7aa52 77 float32_t * pSrcB,
emilmont 1:fdd22bb7aa52 78 float32_t * pDst,
emilmont 1:fdd22bb7aa52 79 uint32_t numSamples)
emilmont 1:fdd22bb7aa52 80 {
emilmont 1:fdd22bb7aa52 81 float32_t a1, b1, c1, d1; /* Temporary variables to store real and imaginary values */
emilmont 1:fdd22bb7aa52 82 uint32_t blkCnt; /* loop counters */
emilmont 1:fdd22bb7aa52 83
emilmont 1:fdd22bb7aa52 84 #ifndef ARM_MATH_CM0
emilmont 1:fdd22bb7aa52 85
emilmont 1:fdd22bb7aa52 86 /* Run the below code for Cortex-M4 and Cortex-M3 */
emilmont 1:fdd22bb7aa52 87 float32_t a2, b2, c2, d2; /* Temporary variables to store real and imaginary values */
emilmont 1:fdd22bb7aa52 88 float32_t acc1, acc2, acc3, acc4;
emilmont 1:fdd22bb7aa52 89
emilmont 1:fdd22bb7aa52 90
emilmont 1:fdd22bb7aa52 91 /* loop Unrolling */
emilmont 1:fdd22bb7aa52 92 blkCnt = numSamples >> 2u;
emilmont 1:fdd22bb7aa52 93
emilmont 1:fdd22bb7aa52 94 /* First part of the processing with loop unrolling. Compute 4 outputs at a time.
emilmont 1:fdd22bb7aa52 95 ** a second loop below computes the remaining 1 to 3 samples. */
emilmont 1:fdd22bb7aa52 96 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 97 {
emilmont 1:fdd22bb7aa52 98 /* C[2 * i] = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1]. */
emilmont 1:fdd22bb7aa52 99 /* C[2 * i + 1] = A[2 * i] * B[2 * i + 1] + A[2 * i + 1] * B[2 * i]. */
emilmont 1:fdd22bb7aa52 100 a1 = *pSrcA; /* A[2 * i] */
emilmont 1:fdd22bb7aa52 101 c1 = *pSrcB; /* B[2 * i] */
emilmont 1:fdd22bb7aa52 102
emilmont 1:fdd22bb7aa52 103 b1 = *(pSrcA + 1); /* A[2 * i + 1] */
emilmont 1:fdd22bb7aa52 104 acc1 = a1 * c1; /* acc1 = A[2 * i] * B[2 * i] */
emilmont 1:fdd22bb7aa52 105
emilmont 1:fdd22bb7aa52 106 a2 = *(pSrcA + 2); /* A[2 * i + 2] */
emilmont 1:fdd22bb7aa52 107 acc2 = (b1 * c1); /* acc2 = A[2 * i + 1] * B[2 * i] */
emilmont 1:fdd22bb7aa52 108
emilmont 1:fdd22bb7aa52 109 d1 = *(pSrcB + 1); /* B[2 * i + 1] */
emilmont 1:fdd22bb7aa52 110 c2 = *(pSrcB + 2); /* B[2 * i + 2] */
emilmont 1:fdd22bb7aa52 111 acc1 -= b1 * d1; /* acc1 = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1] */
emilmont 1:fdd22bb7aa52 112
emilmont 1:fdd22bb7aa52 113 d2 = *(pSrcB + 3); /* B[2 * i + 3] */
emilmont 1:fdd22bb7aa52 114 acc3 = a2 * c2; /* acc3 = A[2 * i + 2] * B[2 * i + 2] */
emilmont 1:fdd22bb7aa52 115
emilmont 1:fdd22bb7aa52 116 b2 = *(pSrcA + 3); /* A[2 * i + 3] */
emilmont 1:fdd22bb7aa52 117 acc2 += (a1 * d1); /* acc2 = A[2 * i + 1] * B[2 * i] + A[2 * i] * B[2 * i + 1] */
emilmont 1:fdd22bb7aa52 118
emilmont 1:fdd22bb7aa52 119 a1 = *(pSrcA + 4); /* A[2 * i + 4] */
emilmont 1:fdd22bb7aa52 120 acc4 = (a2 * d2); /* acc4 = A[2 * i + 2] * B[2 * i + 3] */
emilmont 1:fdd22bb7aa52 121
emilmont 1:fdd22bb7aa52 122 c1 = *(pSrcB + 4); /* B[2 * i + 4] */
emilmont 1:fdd22bb7aa52 123 acc3 -= (b2 * d2); /* acc3 = A[2 * i + 2] * B[2 * i + 2] - A[2 * i + 3] * B[2 * i + 3] */
emilmont 1:fdd22bb7aa52 124 *pDst = acc1; /* C[2 * i] = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1] */
emilmont 1:fdd22bb7aa52 125
emilmont 1:fdd22bb7aa52 126 b1 = *(pSrcA + 5); /* A[2 * i + 5] */
emilmont 1:fdd22bb7aa52 127 acc4 += b2 * c2; /* acc4 = A[2 * i + 2] * B[2 * i + 3] + A[2 * i + 3] * B[2 * i + 2] */
emilmont 1:fdd22bb7aa52 128
emilmont 1:fdd22bb7aa52 129 *(pDst + 1) = acc2; /* C[2 * i + 1] = A[2 * i + 1] * B[2 * i] + A[2 * i] * B[2 * i + 1] */
emilmont 1:fdd22bb7aa52 130 acc1 = (a1 * c1);
emilmont 1:fdd22bb7aa52 131
emilmont 1:fdd22bb7aa52 132 d1 = *(pSrcB + 5);
emilmont 1:fdd22bb7aa52 133 acc2 = (b1 * c1);
emilmont 1:fdd22bb7aa52 134
emilmont 1:fdd22bb7aa52 135 *(pDst + 2) = acc3;
emilmont 1:fdd22bb7aa52 136 *(pDst + 3) = acc4;
emilmont 1:fdd22bb7aa52 137
emilmont 1:fdd22bb7aa52 138 a2 = *(pSrcA + 6);
emilmont 1:fdd22bb7aa52 139 acc1 -= (b1 * d1);
emilmont 1:fdd22bb7aa52 140
emilmont 1:fdd22bb7aa52 141 c2 = *(pSrcB + 6);
emilmont 1:fdd22bb7aa52 142 acc2 += (a1 * d1);
emilmont 1:fdd22bb7aa52 143
emilmont 1:fdd22bb7aa52 144 b2 = *(pSrcA + 7);
emilmont 1:fdd22bb7aa52 145 acc3 = (a2 * c2);
emilmont 1:fdd22bb7aa52 146
emilmont 1:fdd22bb7aa52 147 d2 = *(pSrcB + 7);
emilmont 1:fdd22bb7aa52 148 acc4 = (b2 * c2);
emilmont 1:fdd22bb7aa52 149
emilmont 1:fdd22bb7aa52 150 *(pDst + 4) = acc1;
emilmont 1:fdd22bb7aa52 151 pSrcA += 8u;
emilmont 1:fdd22bb7aa52 152
emilmont 1:fdd22bb7aa52 153 acc3 -= (b2 * d2);
emilmont 1:fdd22bb7aa52 154 acc4 += (a2 * d2);
emilmont 1:fdd22bb7aa52 155
emilmont 1:fdd22bb7aa52 156 *(pDst + 5) = acc2;
emilmont 1:fdd22bb7aa52 157 pSrcB += 8u;
emilmont 1:fdd22bb7aa52 158
emilmont 1:fdd22bb7aa52 159 *(pDst + 6) = acc3;
emilmont 1:fdd22bb7aa52 160 *(pDst + 7) = acc4;
emilmont 1:fdd22bb7aa52 161
emilmont 1:fdd22bb7aa52 162 pDst += 8u;
emilmont 1:fdd22bb7aa52 163
emilmont 1:fdd22bb7aa52 164 /* Decrement the numSamples loop counter */
emilmont 1:fdd22bb7aa52 165 blkCnt--;
emilmont 1:fdd22bb7aa52 166 }
emilmont 1:fdd22bb7aa52 167
emilmont 1:fdd22bb7aa52 168 /* If the numSamples is not a multiple of 4, compute any remaining output samples here.
emilmont 1:fdd22bb7aa52 169 ** No loop unrolling is used. */
emilmont 1:fdd22bb7aa52 170 blkCnt = numSamples % 0x4u;
emilmont 1:fdd22bb7aa52 171
emilmont 1:fdd22bb7aa52 172 #else
emilmont 1:fdd22bb7aa52 173
emilmont 1:fdd22bb7aa52 174 /* Run the below code for Cortex-M0 */
emilmont 1:fdd22bb7aa52 175 blkCnt = numSamples;
emilmont 1:fdd22bb7aa52 176
emilmont 1:fdd22bb7aa52 177 #endif /* #ifndef ARM_MATH_CM0 */
emilmont 1:fdd22bb7aa52 178
emilmont 1:fdd22bb7aa52 179 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 180 {
emilmont 1:fdd22bb7aa52 181 /* C[2 * i] = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1]. */
emilmont 1:fdd22bb7aa52 182 /* C[2 * i + 1] = A[2 * i] * B[2 * i + 1] + A[2 * i + 1] * B[2 * i]. */
emilmont 1:fdd22bb7aa52 183 a1 = *pSrcA++;
emilmont 1:fdd22bb7aa52 184 b1 = *pSrcA++;
emilmont 1:fdd22bb7aa52 185 c1 = *pSrcB++;
emilmont 1:fdd22bb7aa52 186 d1 = *pSrcB++;
emilmont 1:fdd22bb7aa52 187
emilmont 1:fdd22bb7aa52 188 /* store the result in the destination buffer. */
emilmont 1:fdd22bb7aa52 189 *pDst++ = (a1 * c1) - (b1 * d1);
emilmont 1:fdd22bb7aa52 190 *pDst++ = (a1 * d1) + (b1 * c1);
emilmont 1:fdd22bb7aa52 191
emilmont 1:fdd22bb7aa52 192 /* Decrement the numSamples loop counter */
emilmont 1:fdd22bb7aa52 193 blkCnt--;
emilmont 1:fdd22bb7aa52 194 }
emilmont 1:fdd22bb7aa52 195 }
emilmont 1:fdd22bb7aa52 196
emilmont 1:fdd22bb7aa52 197 /**
emilmont 1:fdd22bb7aa52 198 * @} end of CmplxByCmplxMult group
emilmont 1:fdd22bb7aa52 199 */