Joep D / CMSIS_DSP_5

The CMSIS DSP 5 library

Dependents:   Nucleo-Heart-Rate ejercicioVrms2 PROYECTOFINAL ejercicioVrms ... more

functions/ComplexMathFunctions/arm_cmplx_mult_cmplx_f32.c@3:4098b9d3d571, 2018-06-21 (annotated)

Committer:
xorjoep
Date:
Thu Jun 21 11:56:27 2018 +0000
Revision:
3:4098b9d3d571
Parent:
1:24714b45cd1b 
headers is a folder not a library

Who changed what in which revision?

UserRevisionLine numberNew contents of line
xorjoep 1:24714b45cd1b 1 /* ----------------------------------------------------------------------
xorjoep 1:24714b45cd1b 2 * Project: CMSIS DSP Library
xorjoep 1:24714b45cd1b 3 * Title: arm_cmplx_mult_cmplx_f32.c
xorjoep 1:24714b45cd1b 4 * Description: Floating-point complex-by-complex multiplication
xorjoep 1:24714b45cd1b 5 *
xorjoep 1:24714b45cd1b 6 * $Date: 27. January 2017
xorjoep 1:24714b45cd1b 7 * $Revision: V.1.5.1
xorjoep 1:24714b45cd1b 8 *
xorjoep 1:24714b45cd1b 9 * Target Processor: Cortex-M cores
xorjoep 1:24714b45cd1b 10 * -------------------------------------------------------------------- */
xorjoep 1:24714b45cd1b 11 /*
xorjoep 1:24714b45cd1b 12 * Copyright (C) 2010-2017 ARM Limited or its affiliates. All rights reserved.
xorjoep 1:24714b45cd1b 13 *
xorjoep 1:24714b45cd1b 14 * SPDX-License-Identifier: Apache-2.0
xorjoep 1:24714b45cd1b 15 *
xorjoep 1:24714b45cd1b 16 * Licensed under the Apache License, Version 2.0 (the License); you may
xorjoep 1:24714b45cd1b 17 * not use this file except in compliance with the License.
xorjoep 1:24714b45cd1b 18 * You may obtain a copy of the License at
xorjoep 1:24714b45cd1b 19 *
xorjoep 1:24714b45cd1b 20 * www.apache.org/licenses/LICENSE-2.0
xorjoep 1:24714b45cd1b 21 *
xorjoep 1:24714b45cd1b 22 * Unless required by applicable law or agreed to in writing, software
xorjoep 1:24714b45cd1b 23 * distributed under the License is distributed on an AS IS BASIS, WITHOUT
xorjoep 1:24714b45cd1b 24 * WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
xorjoep 1:24714b45cd1b 25 * See the License for the specific language governing permissions and
xorjoep 1:24714b45cd1b 26 * limitations under the License.
xorjoep 1:24714b45cd1b 27 */
xorjoep 1:24714b45cd1b 28
xorjoep 1:24714b45cd1b 29 #include "arm_math.h"
xorjoep 1:24714b45cd1b 30
xorjoep 1:24714b45cd1b 31 /**
xorjoep 1:24714b45cd1b 32 * @ingroup groupCmplxMath
xorjoep 1:24714b45cd1b 33 */
xorjoep 1:24714b45cd1b 34
xorjoep 1:24714b45cd1b 35 /**
xorjoep 1:24714b45cd1b 36 * @defgroup CmplxByCmplxMult Complex-by-Complex Multiplication
xorjoep 1:24714b45cd1b 37 *
xorjoep 1:24714b45cd1b 38 * Multiplies a complex vector by another complex vector and generates a complex result.
xorjoep 1:24714b45cd1b 39 * The data in the complex arrays is stored in an interleaved fashion
xorjoep 1:24714b45cd1b 40 * (real, imag, real, imag, ...).
xorjoep 1:24714b45cd1b 41 * The parameter <code>numSamples</code> represents the number of complex
xorjoep 1:24714b45cd1b 42 * samples processed. The complex arrays have a total of <code>2*numSamples</code>
xorjoep 1:24714b45cd1b 43 * real values.
xorjoep 1:24714b45cd1b 44 *
xorjoep 1:24714b45cd1b 45 * The underlying algorithm is used:
xorjoep 1:24714b45cd1b 46 *
xorjoep 1:24714b45cd1b 47 * <pre>
xorjoep 1:24714b45cd1b 48 * for(n=0; n<numSamples; n++) {
xorjoep 1:24714b45cd1b 49 * pDst[(2*n)+0] = pSrcA[(2*n)+0] * pSrcB[(2*n)+0] - pSrcA[(2*n)+1] * pSrcB[(2*n)+1];
xorjoep 1:24714b45cd1b 50 * pDst[(2*n)+1] = pSrcA[(2*n)+0] * pSrcB[(2*n)+1] + pSrcA[(2*n)+1] * pSrcB[(2*n)+0];
xorjoep 1:24714b45cd1b 51 * }
xorjoep 1:24714b45cd1b 52 * </pre>
xorjoep 1:24714b45cd1b 53 *
xorjoep 1:24714b45cd1b 54 * There are separate functions for floating-point, Q15, and Q31 data types.
xorjoep 1:24714b45cd1b 55 */
xorjoep 1:24714b45cd1b 56
xorjoep 1:24714b45cd1b 57 /**
xorjoep 1:24714b45cd1b 58 * @addtogroup CmplxByCmplxMult
xorjoep 1:24714b45cd1b 59 * @{
xorjoep 1:24714b45cd1b 60 */
xorjoep 1:24714b45cd1b 61
xorjoep 1:24714b45cd1b 62
xorjoep 1:24714b45cd1b 63 /**
xorjoep 1:24714b45cd1b 64 * @brief Floating-point complex-by-complex multiplication
xorjoep 1:24714b45cd1b 65 * @param[in] *pSrcA points to the first input vector
xorjoep 1:24714b45cd1b 66 * @param[in] *pSrcB points to the second input vector
xorjoep 1:24714b45cd1b 67 * @param[out] *pDst points to the output vector
xorjoep 1:24714b45cd1b 68 * @param[in] numSamples number of complex samples in each vector
xorjoep 1:24714b45cd1b 69 * @return none.
xorjoep 1:24714b45cd1b 70 */
xorjoep 1:24714b45cd1b 71
xorjoep 1:24714b45cd1b 72 void arm_cmplx_mult_cmplx_f32(
xorjoep 1:24714b45cd1b 73 float32_t * pSrcA,
xorjoep 1:24714b45cd1b 74 float32_t * pSrcB,
xorjoep 1:24714b45cd1b 75 float32_t * pDst,
xorjoep 1:24714b45cd1b 76 uint32_t numSamples)
xorjoep 1:24714b45cd1b 77 {
xorjoep 1:24714b45cd1b 78 float32_t a1, b1, c1, d1; /* Temporary variables to store real and imaginary values */
xorjoep 1:24714b45cd1b 79 uint32_t blkCnt; /* loop counters */
xorjoep 1:24714b45cd1b 80
xorjoep 1:24714b45cd1b 81 #if defined (ARM_MATH_DSP)
xorjoep 1:24714b45cd1b 82
xorjoep 1:24714b45cd1b 83 /* Run the below code for Cortex-M4 and Cortex-M3 */
xorjoep 1:24714b45cd1b 84 float32_t a2, b2, c2, d2; /* Temporary variables to store real and imaginary values */
xorjoep 1:24714b45cd1b 85 float32_t acc1, acc2, acc3, acc4;
xorjoep 1:24714b45cd1b 86
xorjoep 1:24714b45cd1b 87
xorjoep 1:24714b45cd1b 88 /* loop Unrolling */
xorjoep 1:24714b45cd1b 89 blkCnt = numSamples >> 2U;
xorjoep 1:24714b45cd1b 90
xorjoep 1:24714b45cd1b 91 /* First part of the processing with loop unrolling. Compute 4 outputs at a time.
xorjoep 1:24714b45cd1b 92 ** a second loop below computes the remaining 1 to 3 samples. */
xorjoep 1:24714b45cd1b 93 while (blkCnt > 0U)
xorjoep 1:24714b45cd1b 94 {
xorjoep 1:24714b45cd1b 95 /* C[2 * i] = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1]. */
xorjoep 1:24714b45cd1b 96 /* C[2 * i + 1] = A[2 * i] * B[2 * i + 1] + A[2 * i + 1] * B[2 * i]. */
xorjoep 1:24714b45cd1b 97 a1 = *pSrcA; /* A[2 * i] */
xorjoep 1:24714b45cd1b 98 c1 = *pSrcB; /* B[2 * i] */
xorjoep 1:24714b45cd1b 99
xorjoep 1:24714b45cd1b 100 b1 = *(pSrcA + 1); /* A[2 * i + 1] */
xorjoep 1:24714b45cd1b 101 acc1 = a1 * c1; /* acc1 = A[2 * i] * B[2 * i] */
xorjoep 1:24714b45cd1b 102
xorjoep 1:24714b45cd1b 103 a2 = *(pSrcA + 2); /* A[2 * i + 2] */
xorjoep 1:24714b45cd1b 104 acc2 = (b1 * c1); /* acc2 = A[2 * i + 1] * B[2 * i] */
xorjoep 1:24714b45cd1b 105
xorjoep 1:24714b45cd1b 106 d1 = *(pSrcB + 1); /* B[2 * i + 1] */
xorjoep 1:24714b45cd1b 107 c2 = *(pSrcB + 2); /* B[2 * i + 2] */
xorjoep 1:24714b45cd1b 108 acc1 -= b1 * d1; /* acc1 = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1] */
xorjoep 1:24714b45cd1b 109
xorjoep 1:24714b45cd1b 110 d2 = *(pSrcB + 3); /* B[2 * i + 3] */
xorjoep 1:24714b45cd1b 111 acc3 = a2 * c2; /* acc3 = A[2 * i + 2] * B[2 * i + 2] */
xorjoep 1:24714b45cd1b 112
xorjoep 1:24714b45cd1b 113 b2 = *(pSrcA + 3); /* A[2 * i + 3] */
xorjoep 1:24714b45cd1b 114 acc2 += (a1 * d1); /* acc2 = A[2 * i + 1] * B[2 * i] + A[2 * i] * B[2 * i + 1] */
xorjoep 1:24714b45cd1b 115
xorjoep 1:24714b45cd1b 116 a1 = *(pSrcA + 4); /* A[2 * i + 4] */
xorjoep 1:24714b45cd1b 117 acc4 = (a2 * d2); /* acc4 = A[2 * i + 2] * B[2 * i + 3] */
xorjoep 1:24714b45cd1b 118
xorjoep 1:24714b45cd1b 119 c1 = *(pSrcB + 4); /* B[2 * i + 4] */
xorjoep 1:24714b45cd1b 120 acc3 -= (b2 * d2); /* acc3 = A[2 * i + 2] * B[2 * i + 2] - A[2 * i + 3] * B[2 * i + 3] */
xorjoep 1:24714b45cd1b 121 *pDst = acc1; /* C[2 * i] = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1] */
xorjoep 1:24714b45cd1b 122
xorjoep 1:24714b45cd1b 123 b1 = *(pSrcA + 5); /* A[2 * i + 5] */
xorjoep 1:24714b45cd1b 124 acc4 += b2 * c2; /* acc4 = A[2 * i + 2] * B[2 * i + 3] + A[2 * i + 3] * B[2 * i + 2] */
xorjoep 1:24714b45cd1b 125
xorjoep 1:24714b45cd1b 126 *(pDst + 1) = acc2; /* C[2 * i + 1] = A[2 * i + 1] * B[2 * i] + A[2 * i] * B[2 * i + 1] */
xorjoep 1:24714b45cd1b 127 acc1 = (a1 * c1);
xorjoep 1:24714b45cd1b 128
xorjoep 1:24714b45cd1b 129 d1 = *(pSrcB + 5);
xorjoep 1:24714b45cd1b 130 acc2 = (b1 * c1);
xorjoep 1:24714b45cd1b 131
xorjoep 1:24714b45cd1b 132 *(pDst + 2) = acc3;
xorjoep 1:24714b45cd1b 133 *(pDst + 3) = acc4;
xorjoep 1:24714b45cd1b 134
xorjoep 1:24714b45cd1b 135 a2 = *(pSrcA + 6);
xorjoep 1:24714b45cd1b 136 acc1 -= (b1 * d1);
xorjoep 1:24714b45cd1b 137
xorjoep 1:24714b45cd1b 138 c2 = *(pSrcB + 6);
xorjoep 1:24714b45cd1b 139 acc2 += (a1 * d1);
xorjoep 1:24714b45cd1b 140
xorjoep 1:24714b45cd1b 141 b2 = *(pSrcA + 7);
xorjoep 1:24714b45cd1b 142 acc3 = (a2 * c2);
xorjoep 1:24714b45cd1b 143
xorjoep 1:24714b45cd1b 144 d2 = *(pSrcB + 7);
xorjoep 1:24714b45cd1b 145 acc4 = (b2 * c2);
xorjoep 1:24714b45cd1b 146
xorjoep 1:24714b45cd1b 147 *(pDst + 4) = acc1;
xorjoep 1:24714b45cd1b 148 pSrcA += 8U;
xorjoep 1:24714b45cd1b 149
xorjoep 1:24714b45cd1b 150 acc3 -= (b2 * d2);
xorjoep 1:24714b45cd1b 151 acc4 += (a2 * d2);
xorjoep 1:24714b45cd1b 152
xorjoep 1:24714b45cd1b 153 *(pDst + 5) = acc2;
xorjoep 1:24714b45cd1b 154 pSrcB += 8U;
xorjoep 1:24714b45cd1b 155
xorjoep 1:24714b45cd1b 156 *(pDst + 6) = acc3;
xorjoep 1:24714b45cd1b 157 *(pDst + 7) = acc4;
xorjoep 1:24714b45cd1b 158
xorjoep 1:24714b45cd1b 159 pDst += 8U;
xorjoep 1:24714b45cd1b 160
xorjoep 1:24714b45cd1b 161 /* Decrement the numSamples loop counter */
xorjoep 1:24714b45cd1b 162 blkCnt--;
xorjoep 1:24714b45cd1b 163 }
xorjoep 1:24714b45cd1b 164
xorjoep 1:24714b45cd1b 165 /* If the numSamples is not a multiple of 4, compute any remaining output samples here.
xorjoep 1:24714b45cd1b 166 ** No loop unrolling is used. */
xorjoep 1:24714b45cd1b 167 blkCnt = numSamples % 0x4U;
xorjoep 1:24714b45cd1b 168
xorjoep 1:24714b45cd1b 169 #else
xorjoep 1:24714b45cd1b 170
xorjoep 1:24714b45cd1b 171 /* Run the below code for Cortex-M0 */
xorjoep 1:24714b45cd1b 172 blkCnt = numSamples;
xorjoep 1:24714b45cd1b 173
xorjoep 1:24714b45cd1b 174 #endif /* #if defined (ARM_MATH_DSP) */
xorjoep 1:24714b45cd1b 175
xorjoep 1:24714b45cd1b 176 while (blkCnt > 0U)
xorjoep 1:24714b45cd1b 177 {
xorjoep 1:24714b45cd1b 178 /* C[2 * i] = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1]. */
xorjoep 1:24714b45cd1b 179 /* C[2 * i + 1] = A[2 * i] * B[2 * i + 1] + A[2 * i + 1] * B[2 * i]. */
xorjoep 1:24714b45cd1b 180 a1 = *pSrcA++;
xorjoep 1:24714b45cd1b 181 b1 = *pSrcA++;
xorjoep 1:24714b45cd1b 182 c1 = *pSrcB++;
xorjoep 1:24714b45cd1b 183 d1 = *pSrcB++;
xorjoep 1:24714b45cd1b 184
xorjoep 1:24714b45cd1b 185 /* store the result in the destination buffer. */
xorjoep 1:24714b45cd1b 186 *pDst++ = (a1 * c1) - (b1 * d1);
xorjoep 1:24714b45cd1b 187 *pDst++ = (a1 * d1) + (b1 * c1);
xorjoep 1:24714b45cd1b 188
xorjoep 1:24714b45cd1b 189 /* Decrement the numSamples loop counter */
xorjoep 1:24714b45cd1b 190 blkCnt--;
xorjoep 1:24714b45cd1b 191 }
xorjoep 1:24714b45cd1b 192 }
xorjoep 1:24714b45cd1b 193
xorjoep 1:24714b45cd1b 194 /**
xorjoep 1:24714b45cd1b 195 * @} end of CmplxByCmplxMult group
xorjoep 1:24714b45cd1b 196 */