| 提交 | 用户 | age | ||
| bfc108 | 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_q31.c | |
| 9 | * | |
| 10 | * Description: Q31 complex magnitude | |
| 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 | * @addtogroup cmplx_mag | |
| 49 | * @{ | |
| 50 | */ | |
| 51 | ||
| 52 | /** | |
| 53 | * @brief Q31 complex magnitude | |
| 54 | * @param *pSrc points to the complex input vector | |
| 55 | * @param *pDst points to the real output vector | |
| 56 | * @param numSamples number of complex samples in the input vector | |
| 57 | * @return none. | |
| 58 | * | |
| 59 | * <b>Scaling and Overflow Behavior:</b> | |
| 60 | * \par | |
| 61 | * The function implements 1.31 by 1.31 multiplications and finally output is converted into 2.30 format. | |
| 62 | * Input down scaling is not required. | |
| 63 | */ | |
| 64 | ||
| 65 | void arm_cmplx_mag_q31( | |
| 66 | q31_t * pSrc, | |
| 67 | q31_t * pDst, | |
| 68 | uint32_t numSamples) | |
| 69 | { | |
| 70 | q31_t real, imag; /* Temporary variables to hold input values */ | |
| 71 | q31_t acc0, acc1; /* Accumulators */ | |
| 72 | uint32_t blkCnt; /* loop counter */ | |
| 73 | ||
| 74 | #ifndef ARM_MATH_CM0_FAMILY | |
| 75 | ||
| 76 | /* Run the below code for Cortex-M4 and Cortex-M3 */ | |
| 77 | q31_t real1, real2, imag1, imag2; /* Temporary variables to hold input values */ | |
| 78 | q31_t out1, out2, out3, out4; /* Accumulators */ | |
| 79 | q63_t mul1, mul2, mul3, mul4; /* Temporary variables */ | |
| 80 | ||
| 81 | ||
| 82 | /*loop Unrolling */ | |
| 83 | blkCnt = numSamples >> 2u; | |
| 84 | ||
| 85 | /* First part of the processing with loop unrolling. Compute 4 outputs at a time. | |
| 86 | ** a second loop below computes the remaining 1 to 3 samples. */ | |
| 87 | while(blkCnt > 0u) | |
| 88 | { | |
| 89 | /* read complex input from source buffer */ | |
| 90 | real1 = pSrc[0]; | |
| 91 | imag1 = pSrc[1]; | |
| 92 | real2 = pSrc[2]; | |
| 93 | imag2 = pSrc[3]; | |
| 94 | ||
| 95 | /* calculate power of input values */ | |
| 96 | mul1 = (q63_t) real1 *real1; | |
| 97 | mul2 = (q63_t) imag1 *imag1; | |
| 98 | mul3 = (q63_t) real2 *real2; | |
| 99 | mul4 = (q63_t) imag2 *imag2; | |
| 100 | ||
| 101 | /* get the result to 3.29 format */ | |
| 102 | out1 = (q31_t) (mul1 >> 33); | |
| 103 | out2 = (q31_t) (mul2 >> 33); | |
| 104 | out3 = (q31_t) (mul3 >> 33); | |
| 105 | out4 = (q31_t) (mul4 >> 33); | |
| 106 | ||
| 107 | /* add real and imaginary accumulators */ | |
| 108 | out1 = out1 + out2; | |
| 109 | out3 = out3 + out4; | |
| 110 | ||
| 111 | /* read complex input from source buffer */ | |
| 112 | real1 = pSrc[4]; | |
| 113 | imag1 = pSrc[5]; | |
| 114 | real2 = pSrc[6]; | |
| 115 | imag2 = pSrc[7]; | |
| 116 | ||
| 117 | /* calculate square root */ | |
| 118 | arm_sqrt_q31(out1, &pDst[0]); | |
| 119 | ||
| 120 | /* calculate power of input values */ | |
| 121 | mul1 = (q63_t) real1 *real1; | |
| 122 | ||
| 123 | /* calculate square root */ | |
| 124 | arm_sqrt_q31(out3, &pDst[1]); | |
| 125 | ||
| 126 | /* calculate power of input values */ | |
| 127 | mul2 = (q63_t) imag1 *imag1; | |
| 128 | mul3 = (q63_t) real2 *real2; | |
| 129 | mul4 = (q63_t) imag2 *imag2; | |
| 130 | ||
| 131 | /* get the result to 3.29 format */ | |
| 132 | out1 = (q31_t) (mul1 >> 33); | |
| 133 | out2 = (q31_t) (mul2 >> 33); | |
| 134 | out3 = (q31_t) (mul3 >> 33); | |
| 135 | out4 = (q31_t) (mul4 >> 33); | |
| 136 | ||
| 137 | /* add real and imaginary accumulators */ | |
| 138 | out1 = out1 + out2; | |
| 139 | out3 = out3 + out4; | |
| 140 | ||
| 141 | /* calculate square root */ | |
| 142 | arm_sqrt_q31(out1, &pDst[2]); | |
| 143 | ||
| 144 | /* increment destination by 8 to process next samples */ | |
| 145 | pSrc += 8u; | |
| 146 | ||
| 147 | /* calculate square root */ | |
| 148 | arm_sqrt_q31(out3, &pDst[3]); | |
| 149 | ||
| 150 | /* increment destination by 4 to process next samples */ | |
| 151 | pDst += 4u; | |
| 152 | ||
| 153 | /* Decrement the loop counter */ | |
| 154 | blkCnt--; | |
| 155 | } | |
| 156 | ||
| 157 | /* If the numSamples is not a multiple of 4, compute any remaining output samples here. | |
| 158 | ** No loop unrolling is used. */ | |
| 159 | blkCnt = numSamples % 0x4u; | |
| 160 | ||
| 161 | #else | |
| 162 | ||
| 163 | /* Run the below code for Cortex-M0 */ | |
| 164 | blkCnt = numSamples; | |
| 165 | ||
| 166 | #endif /* #ifndef ARM_MATH_CM0_FAMILY */ | |
| 167 | ||
| 168 | while(blkCnt > 0u) | |
| 169 | { | |
| 170 | /* C[0] = sqrt(A[0] * A[0] + A[1] * A[1]) */ | |
| 171 | real = *pSrc++; | |
| 172 | imag = *pSrc++; | |
| 173 | acc0 = (q31_t) (((q63_t) real * real) >> 33); | |
| 174 | acc1 = (q31_t) (((q63_t) imag * imag) >> 33); | |
| 175 | /* store the result in 2.30 format in the destination buffer. */ | |
| 176 | arm_sqrt_q31(acc0 + acc1, pDst++); | |
| 177 | ||
| 178 | /* Decrement the loop counter */ | |
| 179 | blkCnt--; | |
| 180 | } | |
| 181 | } | |
| 182 | ||
| 183 | /** | |
| 184 | * @} end of cmplx_mag group | |
| 185 | */ | |
