| 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_mag_squared_f32.c | |
| 9 | * | |
| 10 | * Description: Floating-point complex magnitude squared. | |
| 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 | #include "arm_math.h" | |
| 41 | ||
| 42 | /** | |
| 43 | * @ingroup groupCmplxMath | |
| 44 | */ | |
| 45 | ||
| 46 | /** | |
| 47 | * @defgroup cmplx_mag_squared Complex Magnitude Squared | |
| 48 | * | |
| 49 | * Computes the magnitude squared of the elements of a complex data vector. | |
| 50 | * | |
| 51 | * The <code>pSrc</code> points to the source data and | |
| 52 | * <code>pDst</code> points to the where the result should be written. | |
| 53 | * <code>numSamples</code> specifies the number of complex samples | |
| 54 | * in the input array and the data is stored in an interleaved fashion | |
| 55 | * (real, imag, real, imag, ...). | |
| 56 | * The input array has a total of <code>2*numSamples</code> values; | |
| 57 | * the output array has a total of <code>numSamples</code> values. | |
| 58 | * | |
| 59 | * The underlying algorithm is used: | |
| 60 | * | |
| 61 | * <pre> | |
| 62 | * for(n=0; n<numSamples; n++) { | |
| 63 | * pDst[n] = pSrc[(2*n)+0]^2 + pSrc[(2*n)+1]^2; | |
| 64 | * } | |
| 65 | * </pre> | |
| 66 | * | |
| 67 | * There are separate functions for floating-point, Q15, and Q31 data types. | |
| 68 | */ | |
| 69 | ||
| 70 | /** | |
| 71 | * @addtogroup cmplx_mag_squared | |
| 72 | * @{ | |
| 73 | */ | |
| 74 | ||
| 75 | ||
| 76 | /** | |
| 77 | * @brief Floating-point complex magnitude squared | |
| 78 | * @param[in] *pSrc points to the complex input vector | |
| 79 | * @param[out] *pDst points to the real output vector | |
| 80 | * @param[in] numSamples number of complex samples in the input vector | |
| 81 | * @return none. | |
| 82 | */ | |
| 83 | ||
| 84 | void arm_cmplx_mag_squared_f32( | |
| 85 | float32_t * pSrc, | |
| 86 | float32_t * pDst, | |
| 87 | uint32_t numSamples) | |
| 88 | { | |
| 89 | float32_t real, imag; /* Temporary variables to store real and imaginary values */ | |
| 90 | uint32_t blkCnt; /* loop counter */ | |
| 91 | ||
| 92 | #ifndef ARM_MATH_CM0_FAMILY | |
| 93 | float32_t real1, real2, real3, real4; /* Temporary variables to hold real values */ | |
| 94 | float32_t imag1, imag2, imag3, imag4; /* Temporary variables to hold imaginary values */ | |
| 95 | float32_t mul1, mul2, mul3, mul4; /* Temporary variables */ | |
| 96 | float32_t mul5, mul6, mul7, mul8; /* Temporary variables */ | |
| 97 | float32_t out1, out2, out3, out4; /* Temporary variables to hold output values */ | |
| 98 | ||
| 99 | /*loop Unrolling */ | |
| 100 | blkCnt = numSamples >> 2u; | |
| 101 | ||
| 102 | /* First part of the processing with loop unrolling. Compute 4 outputs at a time. | |
| 103 | ** a second loop below computes the remaining 1 to 3 samples. */ | |
| 104 | while(blkCnt > 0u) | |
| 105 | { | |
| 106 | /* C[0] = (A[0] * A[0] + A[1] * A[1]) */ | |
| 107 | /* read real input sample from source buffer */ | |
| 108 | real1 = pSrc[0]; | |
| 109 | /* read imaginary input sample from source buffer */ | |
| 110 | imag1 = pSrc[1]; | |
| 111 | ||
| 112 | /* calculate power of real value */ | |
| 113 | mul1 = real1 * real1; | |
| 114 | ||
| 115 | /* read real input sample from source buffer */ | |
| 116 | real2 = pSrc[2]; | |
| 117 | ||
| 118 | /* calculate power of imaginary value */ | |
| 119 | mul2 = imag1 * imag1; | |
| 120 | ||
| 121 | /* read imaginary input sample from source buffer */ | |
| 122 | imag2 = pSrc[3]; | |
| 123 | ||
| 124 | /* calculate power of real value */ | |
| 125 | mul3 = real2 * real2; | |
| 126 | ||
| 127 | /* read real input sample from source buffer */ | |
| 128 | real3 = pSrc[4]; | |
| 129 | ||
| 130 | /* calculate power of imaginary value */ | |
| 131 | mul4 = imag2 * imag2; | |
| 132 | ||
| 133 | /* read imaginary input sample from source buffer */ | |
| 134 | imag3 = pSrc[5]; | |
| 135 | ||
| 136 | /* calculate power of real value */ | |
| 137 | mul5 = real3 * real3; | |
| 138 | /* calculate power of imaginary value */ | |
| 139 | mul6 = imag3 * imag3; | |
| 140 | ||
| 141 | /* read real input sample from source buffer */ | |
| 142 | real4 = pSrc[6]; | |
| 143 | ||
| 144 | /* accumulate real and imaginary powers */ | |
| 145 | out1 = mul1 + mul2; | |
| 146 | ||
| 147 | /* read imaginary input sample from source buffer */ | |
| 148 | imag4 = pSrc[7]; | |
| 149 | ||
| 150 | /* accumulate real and imaginary powers */ | |
| 151 | out2 = mul3 + mul4; | |
| 152 | ||
| 153 | /* calculate power of real value */ | |
| 154 | mul7 = real4 * real4; | |
| 155 | /* calculate power of imaginary value */ | |
| 156 | mul8 = imag4 * imag4; | |
| 157 | ||
| 158 | /* store output to destination */ | |
| 159 | pDst[0] = out1; | |
| 160 | ||
| 161 | /* accumulate real and imaginary powers */ | |
| 162 | out3 = mul5 + mul6; | |
| 163 | ||
| 164 | /* store output to destination */ | |
| 165 | pDst[1] = out2; | |
| 166 | ||
| 167 | /* accumulate real and imaginary powers */ | |
| 168 | out4 = mul7 + mul8; | |
| 169 | ||
| 170 | /* store output to destination */ | |
| 171 | pDst[2] = out3; | |
| 172 | ||
| 173 | /* increment destination pointer by 8 to process next samples */ | |
| 174 | pSrc += 8u; | |
| 175 | ||
| 176 | /* store output to destination */ | |
| 177 | pDst[3] = out4; | |
| 178 | ||
| 179 | /* increment destination pointer by 4 to process next samples */ | |
| 180 | pDst += 4u; | |
| 181 | ||
| 182 | /* Decrement the loop counter */ | |
| 183 | blkCnt--; | |
| 184 | } | |
| 185 | ||
| 186 | /* If the numSamples is not a multiple of 4, compute any remaining output samples here. | |
| 187 | ** No loop unrolling is used. */ | |
| 188 | blkCnt = numSamples % 0x4u; | |
| 189 | ||
| 190 | #else | |
| 191 | ||
| 192 | /* Run the below code for Cortex-M0 */ | |
| 193 | ||
| 194 | blkCnt = numSamples; | |
| 195 | ||
| 196 | #endif /* #ifndef ARM_MATH_CM0_FAMILY */ | |
| 197 | ||
| 198 | while(blkCnt > 0u) | |
| 199 | { | |
| 200 | /* C[0] = (A[0] * A[0] + A[1] * A[1]) */ | |
| 201 | real = *pSrc++; | |
| 202 | imag = *pSrc++; | |
| 203 | ||
| 204 | /* out = (real * real) + (imag * imag) */ | |
| 205 | /* store the result in the destination buffer. */ | |
| 206 | *pDst++ = (real * real) + (imag * imag); | |
| 207 | ||
| 208 | /* Decrement the loop counter */ | |
| 209 | blkCnt--; | |
| 210 | } | |
| 211 | } | |
| 212 | ||
| 213 | /** | |
| 214 | * @} end of cmplx_mag_squared group | |
| 215 | */ | |
