Details | Last modification | View Log | RSS feed
| Rev | Author | Line No. | Line |
|---|---|---|---|
| 2 | mjames | 1 | /* ---------------------------------------------------------------------- |
| 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 | */ |