mbed-os 6.10 versione
cmsis_dsp/ComplexMathFunctions/arm_cmplx_mult_cmplx_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
Synchronized with git revision e69956aba2f68a2a26ac26b051f8d349deaa1ce8
Who changed what in which revision?
User | Revision | Line number | New 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_mult_cmplx_f32.c |
emilmont | 1:fdd22bb7aa52 | 9 | * |
emilmont | 2:da51fb522205 | 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 | * |
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 | #include "arm_math.h" |
emilmont | 1:fdd22bb7aa52 | 41 | |
emilmont | 1:fdd22bb7aa52 | 42 | /** |
emilmont | 1:fdd22bb7aa52 | 43 | * @ingroup groupCmplxMath |
emilmont | 1:fdd22bb7aa52 | 44 | */ |
emilmont | 1:fdd22bb7aa52 | 45 | |
emilmont | 1:fdd22bb7aa52 | 46 | /** |
emilmont | 1:fdd22bb7aa52 | 47 | * @defgroup CmplxByCmplxMult Complex-by-Complex Multiplication |
emilmont | 1:fdd22bb7aa52 | 48 | * |
emilmont | 1:fdd22bb7aa52 | 49 | * Multiplies a complex vector by another complex vector and generates a complex result. |
emilmont | 1:fdd22bb7aa52 | 50 | * The data in the complex arrays is stored in an interleaved fashion |
emilmont | 1:fdd22bb7aa52 | 51 | * (real, imag, real, imag, ...). |
emilmont | 1:fdd22bb7aa52 | 52 | * The parameter <code>numSamples</code> represents the number of complex |
emilmont | 1:fdd22bb7aa52 | 53 | * samples processed. The complex arrays have a total of <code>2*numSamples</code> |
emilmont | 1:fdd22bb7aa52 | 54 | * real values. |
emilmont | 1:fdd22bb7aa52 | 55 | * |
emilmont | 1:fdd22bb7aa52 | 56 | * The underlying algorithm is used: |
emilmont | 1:fdd22bb7aa52 | 57 | * |
emilmont | 1:fdd22bb7aa52 | 58 | * <pre> |
emilmont | 1:fdd22bb7aa52 | 59 | * for(n=0; n<numSamples; n++) { |
emilmont | 1:fdd22bb7aa52 | 60 | * pDst[(2*n)+0] = pSrcA[(2*n)+0] * pSrcB[(2*n)+0] - pSrcA[(2*n)+1] * pSrcB[(2*n)+1]; |
emilmont | 1:fdd22bb7aa52 | 61 | * pDst[(2*n)+1] = pSrcA[(2*n)+0] * pSrcB[(2*n)+1] + pSrcA[(2*n)+1] * pSrcB[(2*n)+0]; |
emilmont | 1:fdd22bb7aa52 | 62 | * } |
emilmont | 1:fdd22bb7aa52 | 63 | * </pre> |
emilmont | 1:fdd22bb7aa52 | 64 | * |
emilmont | 1:fdd22bb7aa52 | 65 | * There are separate functions for floating-point, Q15, and Q31 data types. |
emilmont | 1:fdd22bb7aa52 | 66 | */ |
emilmont | 1:fdd22bb7aa52 | 67 | |
emilmont | 1:fdd22bb7aa52 | 68 | /** |
emilmont | 1:fdd22bb7aa52 | 69 | * @addtogroup CmplxByCmplxMult |
emilmont | 1:fdd22bb7aa52 | 70 | * @{ |
emilmont | 1:fdd22bb7aa52 | 71 | */ |
emilmont | 1:fdd22bb7aa52 | 72 | |
emilmont | 1:fdd22bb7aa52 | 73 | |
emilmont | 1:fdd22bb7aa52 | 74 | /** |
emilmont | 1:fdd22bb7aa52 | 75 | * @brief Floating-point complex-by-complex multiplication |
emilmont | 1:fdd22bb7aa52 | 76 | * @param[in] *pSrcA points to the first input vector |
emilmont | 1:fdd22bb7aa52 | 77 | * @param[in] *pSrcB points to the second input vector |
emilmont | 1:fdd22bb7aa52 | 78 | * @param[out] *pDst points to the output vector |
emilmont | 1:fdd22bb7aa52 | 79 | * @param[in] numSamples number of complex samples in each vector |
emilmont | 1:fdd22bb7aa52 | 80 | * @return none. |
emilmont | 1:fdd22bb7aa52 | 81 | */ |
emilmont | 1:fdd22bb7aa52 | 82 | |
emilmont | 1:fdd22bb7aa52 | 83 | void arm_cmplx_mult_cmplx_f32( |
emilmont | 1:fdd22bb7aa52 | 84 | float32_t * pSrcA, |
emilmont | 1:fdd22bb7aa52 | 85 | float32_t * pSrcB, |
emilmont | 1:fdd22bb7aa52 | 86 | float32_t * pDst, |
emilmont | 1:fdd22bb7aa52 | 87 | uint32_t numSamples) |
emilmont | 1:fdd22bb7aa52 | 88 | { |
emilmont | 1:fdd22bb7aa52 | 89 | float32_t a1, b1, c1, d1; /* Temporary variables to store real and imaginary values */ |
emilmont | 1:fdd22bb7aa52 | 90 | uint32_t blkCnt; /* loop counters */ |
emilmont | 1:fdd22bb7aa52 | 91 | |
mbed_official | 3:7a284390b0ce | 92 | #ifndef ARM_MATH_CM0_FAMILY |
emilmont | 1:fdd22bb7aa52 | 93 | |
emilmont | 1:fdd22bb7aa52 | 94 | /* Run the below code for Cortex-M4 and Cortex-M3 */ |
emilmont | 1:fdd22bb7aa52 | 95 | float32_t a2, b2, c2, d2; /* Temporary variables to store real and imaginary values */ |
emilmont | 1:fdd22bb7aa52 | 96 | float32_t acc1, acc2, acc3, acc4; |
emilmont | 1:fdd22bb7aa52 | 97 | |
emilmont | 1:fdd22bb7aa52 | 98 | |
emilmont | 1:fdd22bb7aa52 | 99 | /* loop Unrolling */ |
emilmont | 1:fdd22bb7aa52 | 100 | blkCnt = numSamples >> 2u; |
emilmont | 1:fdd22bb7aa52 | 101 | |
emilmont | 1:fdd22bb7aa52 | 102 | /* First part of the processing with loop unrolling. Compute 4 outputs at a time. |
emilmont | 1:fdd22bb7aa52 | 103 | ** a second loop below computes the remaining 1 to 3 samples. */ |
emilmont | 1:fdd22bb7aa52 | 104 | while(blkCnt > 0u) |
emilmont | 1:fdd22bb7aa52 | 105 | { |
emilmont | 1:fdd22bb7aa52 | 106 | /* C[2 * i] = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1]. */ |
emilmont | 1:fdd22bb7aa52 | 107 | /* C[2 * i + 1] = A[2 * i] * B[2 * i + 1] + A[2 * i + 1] * B[2 * i]. */ |
emilmont | 1:fdd22bb7aa52 | 108 | a1 = *pSrcA; /* A[2 * i] */ |
emilmont | 1:fdd22bb7aa52 | 109 | c1 = *pSrcB; /* B[2 * i] */ |
emilmont | 1:fdd22bb7aa52 | 110 | |
emilmont | 1:fdd22bb7aa52 | 111 | b1 = *(pSrcA + 1); /* A[2 * i + 1] */ |
emilmont | 1:fdd22bb7aa52 | 112 | acc1 = a1 * c1; /* acc1 = A[2 * i] * B[2 * i] */ |
emilmont | 1:fdd22bb7aa52 | 113 | |
emilmont | 1:fdd22bb7aa52 | 114 | a2 = *(pSrcA + 2); /* A[2 * i + 2] */ |
emilmont | 1:fdd22bb7aa52 | 115 | acc2 = (b1 * c1); /* acc2 = A[2 * i + 1] * B[2 * i] */ |
emilmont | 1:fdd22bb7aa52 | 116 | |
emilmont | 1:fdd22bb7aa52 | 117 | d1 = *(pSrcB + 1); /* B[2 * i + 1] */ |
emilmont | 1:fdd22bb7aa52 | 118 | c2 = *(pSrcB + 2); /* B[2 * i + 2] */ |
emilmont | 1:fdd22bb7aa52 | 119 | acc1 -= b1 * d1; /* acc1 = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1] */ |
emilmont | 1:fdd22bb7aa52 | 120 | |
emilmont | 1:fdd22bb7aa52 | 121 | d2 = *(pSrcB + 3); /* B[2 * i + 3] */ |
emilmont | 1:fdd22bb7aa52 | 122 | acc3 = a2 * c2; /* acc3 = A[2 * i + 2] * B[2 * i + 2] */ |
emilmont | 1:fdd22bb7aa52 | 123 | |
emilmont | 1:fdd22bb7aa52 | 124 | b2 = *(pSrcA + 3); /* A[2 * i + 3] */ |
emilmont | 1:fdd22bb7aa52 | 125 | acc2 += (a1 * d1); /* acc2 = A[2 * i + 1] * B[2 * i] + A[2 * i] * B[2 * i + 1] */ |
emilmont | 1:fdd22bb7aa52 | 126 | |
emilmont | 1:fdd22bb7aa52 | 127 | a1 = *(pSrcA + 4); /* A[2 * i + 4] */ |
emilmont | 1:fdd22bb7aa52 | 128 | acc4 = (a2 * d2); /* acc4 = A[2 * i + 2] * B[2 * i + 3] */ |
emilmont | 1:fdd22bb7aa52 | 129 | |
emilmont | 1:fdd22bb7aa52 | 130 | c1 = *(pSrcB + 4); /* B[2 * i + 4] */ |
emilmont | 1:fdd22bb7aa52 | 131 | acc3 -= (b2 * d2); /* acc3 = A[2 * i + 2] * B[2 * i + 2] - A[2 * i + 3] * B[2 * i + 3] */ |
emilmont | 1:fdd22bb7aa52 | 132 | *pDst = acc1; /* C[2 * i] = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1] */ |
emilmont | 1:fdd22bb7aa52 | 133 | |
emilmont | 1:fdd22bb7aa52 | 134 | b1 = *(pSrcA + 5); /* A[2 * i + 5] */ |
emilmont | 1:fdd22bb7aa52 | 135 | acc4 += b2 * c2; /* acc4 = A[2 * i + 2] * B[2 * i + 3] + A[2 * i + 3] * B[2 * i + 2] */ |
emilmont | 1:fdd22bb7aa52 | 136 | |
emilmont | 1:fdd22bb7aa52 | 137 | *(pDst + 1) = acc2; /* C[2 * i + 1] = A[2 * i + 1] * B[2 * i] + A[2 * i] * B[2 * i + 1] */ |
emilmont | 1:fdd22bb7aa52 | 138 | acc1 = (a1 * c1); |
emilmont | 1:fdd22bb7aa52 | 139 | |
emilmont | 1:fdd22bb7aa52 | 140 | d1 = *(pSrcB + 5); |
emilmont | 1:fdd22bb7aa52 | 141 | acc2 = (b1 * c1); |
emilmont | 1:fdd22bb7aa52 | 142 | |
emilmont | 1:fdd22bb7aa52 | 143 | *(pDst + 2) = acc3; |
emilmont | 1:fdd22bb7aa52 | 144 | *(pDst + 3) = acc4; |
emilmont | 1:fdd22bb7aa52 | 145 | |
emilmont | 1:fdd22bb7aa52 | 146 | a2 = *(pSrcA + 6); |
emilmont | 1:fdd22bb7aa52 | 147 | acc1 -= (b1 * d1); |
emilmont | 1:fdd22bb7aa52 | 148 | |
emilmont | 1:fdd22bb7aa52 | 149 | c2 = *(pSrcB + 6); |
emilmont | 1:fdd22bb7aa52 | 150 | acc2 += (a1 * d1); |
emilmont | 1:fdd22bb7aa52 | 151 | |
emilmont | 1:fdd22bb7aa52 | 152 | b2 = *(pSrcA + 7); |
emilmont | 1:fdd22bb7aa52 | 153 | acc3 = (a2 * c2); |
emilmont | 1:fdd22bb7aa52 | 154 | |
emilmont | 1:fdd22bb7aa52 | 155 | d2 = *(pSrcB + 7); |
emilmont | 1:fdd22bb7aa52 | 156 | acc4 = (b2 * c2); |
emilmont | 1:fdd22bb7aa52 | 157 | |
emilmont | 1:fdd22bb7aa52 | 158 | *(pDst + 4) = acc1; |
emilmont | 1:fdd22bb7aa52 | 159 | pSrcA += 8u; |
emilmont | 1:fdd22bb7aa52 | 160 | |
emilmont | 1:fdd22bb7aa52 | 161 | acc3 -= (b2 * d2); |
emilmont | 1:fdd22bb7aa52 | 162 | acc4 += (a2 * d2); |
emilmont | 1:fdd22bb7aa52 | 163 | |
emilmont | 1:fdd22bb7aa52 | 164 | *(pDst + 5) = acc2; |
emilmont | 1:fdd22bb7aa52 | 165 | pSrcB += 8u; |
emilmont | 1:fdd22bb7aa52 | 166 | |
emilmont | 1:fdd22bb7aa52 | 167 | *(pDst + 6) = acc3; |
emilmont | 1:fdd22bb7aa52 | 168 | *(pDst + 7) = acc4; |
emilmont | 1:fdd22bb7aa52 | 169 | |
emilmont | 1:fdd22bb7aa52 | 170 | pDst += 8u; |
emilmont | 1:fdd22bb7aa52 | 171 | |
emilmont | 1:fdd22bb7aa52 | 172 | /* Decrement the numSamples loop counter */ |
emilmont | 1:fdd22bb7aa52 | 173 | blkCnt--; |
emilmont | 1:fdd22bb7aa52 | 174 | } |
emilmont | 1:fdd22bb7aa52 | 175 | |
emilmont | 1:fdd22bb7aa52 | 176 | /* If the numSamples is not a multiple of 4, compute any remaining output samples here. |
emilmont | 1:fdd22bb7aa52 | 177 | ** No loop unrolling is used. */ |
emilmont | 1:fdd22bb7aa52 | 178 | blkCnt = numSamples % 0x4u; |
emilmont | 1:fdd22bb7aa52 | 179 | |
emilmont | 1:fdd22bb7aa52 | 180 | #else |
emilmont | 1:fdd22bb7aa52 | 181 | |
emilmont | 1:fdd22bb7aa52 | 182 | /* Run the below code for Cortex-M0 */ |
emilmont | 1:fdd22bb7aa52 | 183 | blkCnt = numSamples; |
emilmont | 1:fdd22bb7aa52 | 184 | |
mbed_official | 3:7a284390b0ce | 185 | #endif /* #ifndef ARM_MATH_CM0_FAMILY */ |
emilmont | 1:fdd22bb7aa52 | 186 | |
emilmont | 1:fdd22bb7aa52 | 187 | while(blkCnt > 0u) |
emilmont | 1:fdd22bb7aa52 | 188 | { |
emilmont | 1:fdd22bb7aa52 | 189 | /* C[2 * i] = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1]. */ |
emilmont | 1:fdd22bb7aa52 | 190 | /* C[2 * i + 1] = A[2 * i] * B[2 * i + 1] + A[2 * i + 1] * B[2 * i]. */ |
emilmont | 1:fdd22bb7aa52 | 191 | a1 = *pSrcA++; |
emilmont | 1:fdd22bb7aa52 | 192 | b1 = *pSrcA++; |
emilmont | 1:fdd22bb7aa52 | 193 | c1 = *pSrcB++; |
emilmont | 1:fdd22bb7aa52 | 194 | d1 = *pSrcB++; |
emilmont | 1:fdd22bb7aa52 | 195 | |
emilmont | 1:fdd22bb7aa52 | 196 | /* store the result in the destination buffer. */ |
emilmont | 1:fdd22bb7aa52 | 197 | *pDst++ = (a1 * c1) - (b1 * d1); |
emilmont | 1:fdd22bb7aa52 | 198 | *pDst++ = (a1 * d1) + (b1 * c1); |
emilmont | 1:fdd22bb7aa52 | 199 | |
emilmont | 1:fdd22bb7aa52 | 200 | /* Decrement the numSamples loop counter */ |
emilmont | 1:fdd22bb7aa52 | 201 | blkCnt--; |
emilmont | 1:fdd22bb7aa52 | 202 | } |
emilmont | 1:fdd22bb7aa52 | 203 | } |
emilmont | 1:fdd22bb7aa52 | 204 | |
emilmont | 1:fdd22bb7aa52 | 205 | /** |
emilmont | 1:fdd22bb7aa52 | 206 | * @} end of CmplxByCmplxMult group |
emilmont | 1:fdd22bb7aa52 | 207 | */ |