| 提交 | 用户 | age | ||
| 8b51c7 | 1 | /* ---------------------------------------------------------------------- |
| Q | 2 | * Copyright (C) 2010-2014 ARM Limited. All rights reserved. |
| 3 | * | |
| 4 | * $Date: 19. March 2015 | |
| 5 | * $Revision: V.1.4.5 | |
| 6 | * | |
| 7 | * Project: CMSIS DSP Library | |
| 8 | * Title: arm_cmplx_mult_real_f32.c | |
| 9 | * | |
| 10 | * Description: Floating-point complex by real multiplication | |
| 11 | * | |
| 12 | * Target Processor: Cortex-M4/Cortex-M3/Cortex-M0 | |
| 13 | * | |
| 14 | * Redistribution and use in source and binary forms, with or without | |
| 15 | * modification, are permitted provided that the following conditions | |
| 16 | * are met: | |
| 17 | * - Redistributions of source code must retain the above copyright | |
| 18 | * notice, this list of conditions and the following disclaimer. | |
| 19 | * - Redistributions in binary form must reproduce the above copyright | |
| 20 | * notice, this list of conditions and the following disclaimer in | |
| 21 | * the documentation and/or other materials provided with the | |
| 22 | * distribution. | |
| 23 | * - Neither the name of ARM LIMITED nor the names of its contributors | |
| 24 | * may be used to endorse or promote products derived from this | |
| 25 | * software without specific prior written permission. | |
| 26 | * | |
| 27 | * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS | |
| 28 | * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT | |
| 29 | * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS | |
| 30 | * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE | |
| 31 | * COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, | |
| 32 | * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, | |
| 33 | * BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; | |
| 34 | * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER | |
| 35 | * CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT | |
| 36 | * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN | |
| 37 | * ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE | |
| 38 | * POSSIBILITY OF SUCH DAMAGE. | |
| 39 | * -------------------------------------------------------------------- */ | |
| 40 | ||
| 41 | #include "arm_math.h" | |
| 42 | ||
| 43 | /** | |
| 44 | * @ingroup groupCmplxMath | |
| 45 | */ | |
| 46 | ||
| 47 | /** | |
| 48 | * @defgroup CmplxByRealMult Complex-by-Real Multiplication | |
| 49 | * | |
| 50 | * Multiplies a complex vector by a real vector and generates a complex result. | |
| 51 | * The data in the complex arrays is stored in an interleaved fashion | |
| 52 | * (real, imag, real, imag, ...). | |
| 53 | * The parameter <code>numSamples</code> represents the number of complex | |
| 54 | * samples processed. The complex arrays have a total of <code>2*numSamples</code> | |
| 55 | * real values while the real array has a total of <code>numSamples</code> | |
| 56 | * real values. | |
| 57 | * | |
| 58 | * The underlying algorithm is used: | |
| 59 | * | |
| 60 | * <pre> | |
| 61 | * for(n=0; n<numSamples; n++) { | |
| 62 | * pCmplxDst[(2*n)+0] = pSrcCmplx[(2*n)+0] * pSrcReal[n]; | |
| 63 | * pCmplxDst[(2*n)+1] = pSrcCmplx[(2*n)+1] * pSrcReal[n]; | |
| 64 | * } | |
| 65 | * </pre> | |
| 66 | * | |
| 67 | * There are separate functions for floating-point, Q15, and Q31 data types. | |
| 68 | */ | |
| 69 | ||
| 70 | /** | |
| 71 | * @addtogroup CmplxByRealMult | |
| 72 | * @{ | |
| 73 | */ | |
| 74 | ||
| 75 | ||
| 76 | /** | |
| 77 | * @brief Floating-point complex-by-real multiplication | |
| 78 | * @param[in] *pSrcCmplx points to the complex input vector | |
| 79 | * @param[in] *pSrcReal points to the real input vector | |
| 80 | * @param[out] *pCmplxDst points to the complex output vector | |
| 81 | * @param[in] numSamples number of samples in each vector | |
| 82 | * @return none. | |
| 83 | */ | |
| 84 | ||
| 85 | void arm_cmplx_mult_real_f32( | |
| 86 | float32_t * pSrcCmplx, | |
| 87 | float32_t * pSrcReal, | |
| 88 | float32_t * pCmplxDst, | |
| 89 | uint32_t numSamples) | |
| 90 | { | |
| 91 | float32_t in; /* Temporary variable to store input value */ | |
| 92 | uint32_t blkCnt; /* loop counters */ | |
| 93 | ||
| 94 | #ifndef ARM_MATH_CM0_FAMILY | |
| 95 | ||
| 96 | /* Run the below code for Cortex-M4 and Cortex-M3 */ | |
| 97 | float32_t inA1, inA2, inA3, inA4; /* Temporary variables to hold input data */ | |
| 98 | float32_t inA5, inA6, inA7, inA8; /* Temporary variables to hold input data */ | |
| 99 | float32_t inB1, inB2, inB3, inB4; /* Temporary variables to hold input data */ | |
| 100 | float32_t out1, out2, out3, out4; /* Temporary variables to hold output data */ | |
| 101 | float32_t out5, out6, out7, out8; /* Temporary variables to hold output data */ | |
| 102 | ||
| 103 | /* loop Unrolling */ | |
| 104 | blkCnt = numSamples >> 2u; | |
| 105 | ||
| 106 | /* First part of the processing with loop unrolling. Compute 4 outputs at a time. | |
| 107 | ** a second loop below computes the remaining 1 to 3 samples. */ | |
| 108 | while(blkCnt > 0u) | |
| 109 | { | |
| 110 | /* C[2 * i] = A[2 * i] * B[i]. */ | |
| 111 | /* C[2 * i + 1] = A[2 * i + 1] * B[i]. */ | |
| 112 | /* read input from complex input buffer */ | |
| 113 | inA1 = pSrcCmplx[0]; | |
| 114 | inA2 = pSrcCmplx[1]; | |
| 115 | /* read input from real input buffer */ | |
| 116 | inB1 = pSrcReal[0]; | |
| 117 | ||
| 118 | /* read input from complex input buffer */ | |
| 119 | inA3 = pSrcCmplx[2]; | |
| 120 | ||
| 121 | /* multiply complex buffer real input with real buffer input */ | |
| 122 | out1 = inA1 * inB1; | |
| 123 | ||
| 124 | /* read input from complex input buffer */ | |
| 125 | inA4 = pSrcCmplx[3]; | |
| 126 | ||
| 127 | /* multiply complex buffer imaginary input with real buffer input */ | |
| 128 | out2 = inA2 * inB1; | |
| 129 | ||
| 130 | /* read input from real input buffer */ | |
| 131 | inB2 = pSrcReal[1]; | |
| 132 | /* read input from complex input buffer */ | |
| 133 | inA5 = pSrcCmplx[4]; | |
| 134 | ||
| 135 | /* multiply complex buffer real input with real buffer input */ | |
| 136 | out3 = inA3 * inB2; | |
| 137 | ||
| 138 | /* read input from complex input buffer */ | |
| 139 | inA6 = pSrcCmplx[5]; | |
| 140 | /* read input from real input buffer */ | |
| 141 | inB3 = pSrcReal[2]; | |
| 142 | ||
| 143 | /* multiply complex buffer imaginary input with real buffer input */ | |
| 144 | out4 = inA4 * inB2; | |
| 145 | ||
| 146 | /* read input from complex input buffer */ | |
| 147 | inA7 = pSrcCmplx[6]; | |
| 148 | ||
| 149 | /* multiply complex buffer real input with real buffer input */ | |
| 150 | out5 = inA5 * inB3; | |
| 151 | ||
| 152 | /* read input from complex input buffer */ | |
| 153 | inA8 = pSrcCmplx[7]; | |
| 154 | ||
| 155 | /* multiply complex buffer imaginary input with real buffer input */ | |
| 156 | out6 = inA6 * inB3; | |
| 157 | ||
| 158 | /* read input from real input buffer */ | |
| 159 | inB4 = pSrcReal[3]; | |
| 160 | ||
| 161 | /* store result to destination bufer */ | |
| 162 | pCmplxDst[0] = out1; | |
| 163 | ||
| 164 | /* multiply complex buffer real input with real buffer input */ | |
| 165 | out7 = inA7 * inB4; | |
| 166 | ||
| 167 | /* store result to destination bufer */ | |
| 168 | pCmplxDst[1] = out2; | |
| 169 | ||
| 170 | /* multiply complex buffer imaginary input with real buffer input */ | |
| 171 | out8 = inA8 * inB4; | |
| 172 | ||
| 173 | /* store result to destination bufer */ | |
| 174 | pCmplxDst[2] = out3; | |
| 175 | pCmplxDst[3] = out4; | |
| 176 | pCmplxDst[4] = out5; | |
| 177 | ||
| 178 | /* incremnet complex input buffer by 8 to process next samples */ | |
| 179 | pSrcCmplx += 8u; | |
| 180 | ||
| 181 | /* store result to destination bufer */ | |
| 182 | pCmplxDst[5] = out6; | |
| 183 | ||
| 184 | /* increment real input buffer by 4 to process next samples */ | |
| 185 | pSrcReal += 4u; | |
| 186 | ||
| 187 | /* store result to destination bufer */ | |
| 188 | pCmplxDst[6] = out7; | |
| 189 | pCmplxDst[7] = out8; | |
| 190 | ||
| 191 | /* increment destination buffer by 8 to process next sampels */ | |
| 192 | pCmplxDst += 8u; | |
| 193 | ||
| 194 | /* Decrement the numSamples loop counter */ | |
| 195 | blkCnt--; | |
| 196 | } | |
| 197 | ||
| 198 | /* If the numSamples is not a multiple of 4, compute any remaining output samples here. | |
| 199 | ** No loop unrolling is used. */ | |
| 200 | blkCnt = numSamples % 0x4u; | |
| 201 | ||
| 202 | #else | |
| 203 | ||
| 204 | /* Run the below code for Cortex-M0 */ | |
| 205 | blkCnt = numSamples; | |
| 206 | ||
| 207 | #endif /* #ifndef ARM_MATH_CM0_FAMILY */ | |
| 208 | ||
| 209 | while(blkCnt > 0u) | |
| 210 | { | |
| 211 | /* C[2 * i] = A[2 * i] * B[i]. */ | |
| 212 | /* C[2 * i + 1] = A[2 * i + 1] * B[i]. */ | |
| 213 | in = *pSrcReal++; | |
| 214 | /* store the result in the destination buffer. */ | |
| 215 | *pCmplxDst++ = (*pSrcCmplx++) * (in); | |
| 216 | *pCmplxDst++ = (*pSrcCmplx++) * (in); | |
| 217 | ||
| 218 | /* Decrement the numSamples loop counter */ | |
| 219 | blkCnt--; | |
| 220 | } | |
| 221 | } | |
| 222 | ||
| 223 | /** | |
| 224 | * @} end of CmplxByRealMult group | |
| 225 | */ | |
