mbed-os 6.10 versione
cmsis_dsp/ComplexMathFunctions/arm_cmplx_mult_cmplx_q15.c@1:fdd22bb7aa52, 2012-11-28 (annotated)
- Committer:
- emilmont
- Date:
- Wed Nov 28 12:30:09 2012 +0000
- Revision:
- 1:fdd22bb7aa52
- Child:
- 2:da51fb522205
DSP library code
Who changed what in which revision?
User | Revision | Line number | New contents of line |
---|---|---|---|
emilmont | 1:fdd22bb7aa52 | 1 | /* ---------------------------------------------------------------------- |
emilmont | 1:fdd22bb7aa52 | 2 | * Copyright (C) 2010 ARM Limited. All rights reserved. |
emilmont | 1:fdd22bb7aa52 | 3 | * |
emilmont | 1:fdd22bb7aa52 | 4 | * $Date: 15. February 2012 |
emilmont | 1:fdd22bb7aa52 | 5 | * $Revision: V1.1.0 |
emilmont | 1:fdd22bb7aa52 | 6 | * |
emilmont | 1:fdd22bb7aa52 | 7 | * Project: CMSIS DSP Library |
emilmont | 1:fdd22bb7aa52 | 8 | * Title: arm_cmplx_mult_cmplx_q15.c |
emilmont | 1:fdd22bb7aa52 | 9 | * |
emilmont | 1:fdd22bb7aa52 | 10 | * Description: Q15 complex-by-complex multiplication |
emilmont | 1:fdd22bb7aa52 | 11 | * |
emilmont | 1:fdd22bb7aa52 | 12 | * Target Processor: Cortex-M4/Cortex-M3/Cortex-M0 |
emilmont | 1:fdd22bb7aa52 | 13 | * |
emilmont | 1:fdd22bb7aa52 | 14 | * Version 1.1.0 2012/02/15 |
emilmont | 1:fdd22bb7aa52 | 15 | * Updated with more optimizations, bug fixes and minor API changes. |
emilmont | 1:fdd22bb7aa52 | 16 | * |
emilmont | 1:fdd22bb7aa52 | 17 | * Version 1.0.10 2011/7/15 |
emilmont | 1:fdd22bb7aa52 | 18 | * Big Endian support added and Merged M0 and M3/M4 Source code. |
emilmont | 1:fdd22bb7aa52 | 19 | * |
emilmont | 1:fdd22bb7aa52 | 20 | * Version 1.0.3 2010/11/29 |
emilmont | 1:fdd22bb7aa52 | 21 | * Re-organized the CMSIS folders and updated documentation. |
emilmont | 1:fdd22bb7aa52 | 22 | * |
emilmont | 1:fdd22bb7aa52 | 23 | * Version 1.0.2 2010/11/11 |
emilmont | 1:fdd22bb7aa52 | 24 | * Documentation updated. |
emilmont | 1:fdd22bb7aa52 | 25 | * |
emilmont | 1:fdd22bb7aa52 | 26 | * Version 1.0.1 2010/10/05 |
emilmont | 1:fdd22bb7aa52 | 27 | * Production release and review comments incorporated. |
emilmont | 1:fdd22bb7aa52 | 28 | * |
emilmont | 1:fdd22bb7aa52 | 29 | * Version 1.0.0 2010/09/20 |
emilmont | 1:fdd22bb7aa52 | 30 | * Production release and review comments incorporated. |
emilmont | 1:fdd22bb7aa52 | 31 | * -------------------------------------------------------------------- */ |
emilmont | 1:fdd22bb7aa52 | 32 | |
emilmont | 1:fdd22bb7aa52 | 33 | #include "arm_math.h" |
emilmont | 1:fdd22bb7aa52 | 34 | |
emilmont | 1:fdd22bb7aa52 | 35 | /** |
emilmont | 1:fdd22bb7aa52 | 36 | * @ingroup groupCmplxMath |
emilmont | 1:fdd22bb7aa52 | 37 | */ |
emilmont | 1:fdd22bb7aa52 | 38 | |
emilmont | 1:fdd22bb7aa52 | 39 | /** |
emilmont | 1:fdd22bb7aa52 | 40 | * @addtogroup CmplxByCmplxMult |
emilmont | 1:fdd22bb7aa52 | 41 | * @{ |
emilmont | 1:fdd22bb7aa52 | 42 | */ |
emilmont | 1:fdd22bb7aa52 | 43 | |
emilmont | 1:fdd22bb7aa52 | 44 | /** |
emilmont | 1:fdd22bb7aa52 | 45 | * @brief Q15 complex-by-complex multiplication |
emilmont | 1:fdd22bb7aa52 | 46 | * @param[in] *pSrcA points to the first input vector |
emilmont | 1:fdd22bb7aa52 | 47 | * @param[in] *pSrcB points to the second input vector |
emilmont | 1:fdd22bb7aa52 | 48 | * @param[out] *pDst points to the output vector |
emilmont | 1:fdd22bb7aa52 | 49 | * @param[in] numSamples number of complex samples in each vector |
emilmont | 1:fdd22bb7aa52 | 50 | * @return none. |
emilmont | 1:fdd22bb7aa52 | 51 | * |
emilmont | 1:fdd22bb7aa52 | 52 | * <b>Scaling and Overflow Behavior:</b> |
emilmont | 1:fdd22bb7aa52 | 53 | * \par |
emilmont | 1:fdd22bb7aa52 | 54 | * The function implements 1.15 by 1.15 multiplications and finally output is converted into 3.13 format. |
emilmont | 1:fdd22bb7aa52 | 55 | */ |
emilmont | 1:fdd22bb7aa52 | 56 | |
emilmont | 1:fdd22bb7aa52 | 57 | void arm_cmplx_mult_cmplx_q15( |
emilmont | 1:fdd22bb7aa52 | 58 | q15_t * pSrcA, |
emilmont | 1:fdd22bb7aa52 | 59 | q15_t * pSrcB, |
emilmont | 1:fdd22bb7aa52 | 60 | q15_t * pDst, |
emilmont | 1:fdd22bb7aa52 | 61 | uint32_t numSamples) |
emilmont | 1:fdd22bb7aa52 | 62 | { |
emilmont | 1:fdd22bb7aa52 | 63 | q15_t a, b, c, d; /* Temporary variables to store real and imaginary values */ |
emilmont | 1:fdd22bb7aa52 | 64 | |
emilmont | 1:fdd22bb7aa52 | 65 | #ifndef ARM_MATH_CM0 |
emilmont | 1:fdd22bb7aa52 | 66 | |
emilmont | 1:fdd22bb7aa52 | 67 | /* Run the below code for Cortex-M4 and Cortex-M3 */ |
emilmont | 1:fdd22bb7aa52 | 68 | uint32_t blkCnt; /* loop counters */ |
emilmont | 1:fdd22bb7aa52 | 69 | |
emilmont | 1:fdd22bb7aa52 | 70 | /* loop Unrolling */ |
emilmont | 1:fdd22bb7aa52 | 71 | blkCnt = numSamples >> 2u; |
emilmont | 1:fdd22bb7aa52 | 72 | |
emilmont | 1:fdd22bb7aa52 | 73 | /* First part of the processing with loop unrolling. Compute 4 outputs at a time. |
emilmont | 1:fdd22bb7aa52 | 74 | ** a second loop below computes the remaining 1 to 3 samples. */ |
emilmont | 1:fdd22bb7aa52 | 75 | while(blkCnt > 0u) |
emilmont | 1:fdd22bb7aa52 | 76 | { |
emilmont | 1:fdd22bb7aa52 | 77 | /* C[2 * i] = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1]. */ |
emilmont | 1:fdd22bb7aa52 | 78 | /* C[2 * i + 1] = A[2 * i] * B[2 * i + 1] + A[2 * i + 1] * B[2 * i]. */ |
emilmont | 1:fdd22bb7aa52 | 79 | a = *pSrcA++; |
emilmont | 1:fdd22bb7aa52 | 80 | b = *pSrcA++; |
emilmont | 1:fdd22bb7aa52 | 81 | c = *pSrcB++; |
emilmont | 1:fdd22bb7aa52 | 82 | d = *pSrcB++; |
emilmont | 1:fdd22bb7aa52 | 83 | |
emilmont | 1:fdd22bb7aa52 | 84 | /* store the result in 3.13 format in the destination buffer. */ |
emilmont | 1:fdd22bb7aa52 | 85 | *pDst++ = |
emilmont | 1:fdd22bb7aa52 | 86 | (q15_t) (q31_t) (((q31_t) a * c) >> 17) - (((q31_t) b * d) >> 17); |
emilmont | 1:fdd22bb7aa52 | 87 | /* store the result in 3.13 format in the destination buffer. */ |
emilmont | 1:fdd22bb7aa52 | 88 | *pDst++ = |
emilmont | 1:fdd22bb7aa52 | 89 | (q15_t) (q31_t) (((q31_t) a * d) >> 17) + (((q31_t) b * c) >> 17); |
emilmont | 1:fdd22bb7aa52 | 90 | |
emilmont | 1:fdd22bb7aa52 | 91 | a = *pSrcA++; |
emilmont | 1:fdd22bb7aa52 | 92 | b = *pSrcA++; |
emilmont | 1:fdd22bb7aa52 | 93 | c = *pSrcB++; |
emilmont | 1:fdd22bb7aa52 | 94 | d = *pSrcB++; |
emilmont | 1:fdd22bb7aa52 | 95 | |
emilmont | 1:fdd22bb7aa52 | 96 | /* store the result in 3.13 format in the destination buffer. */ |
emilmont | 1:fdd22bb7aa52 | 97 | *pDst++ = |
emilmont | 1:fdd22bb7aa52 | 98 | (q15_t) (q31_t) (((q31_t) a * c) >> 17) - (((q31_t) b * d) >> 17); |
emilmont | 1:fdd22bb7aa52 | 99 | /* store the result in 3.13 format in the destination buffer. */ |
emilmont | 1:fdd22bb7aa52 | 100 | *pDst++ = |
emilmont | 1:fdd22bb7aa52 | 101 | (q15_t) (q31_t) (((q31_t) a * d) >> 17) + (((q31_t) b * c) >> 17); |
emilmont | 1:fdd22bb7aa52 | 102 | |
emilmont | 1:fdd22bb7aa52 | 103 | a = *pSrcA++; |
emilmont | 1:fdd22bb7aa52 | 104 | b = *pSrcA++; |
emilmont | 1:fdd22bb7aa52 | 105 | c = *pSrcB++; |
emilmont | 1:fdd22bb7aa52 | 106 | d = *pSrcB++; |
emilmont | 1:fdd22bb7aa52 | 107 | |
emilmont | 1:fdd22bb7aa52 | 108 | /* store the result in 3.13 format in the destination buffer. */ |
emilmont | 1:fdd22bb7aa52 | 109 | *pDst++ = |
emilmont | 1:fdd22bb7aa52 | 110 | (q15_t) (q31_t) (((q31_t) a * c) >> 17) - (((q31_t) b * d) >> 17); |
emilmont | 1:fdd22bb7aa52 | 111 | /* store the result in 3.13 format in the destination buffer. */ |
emilmont | 1:fdd22bb7aa52 | 112 | *pDst++ = |
emilmont | 1:fdd22bb7aa52 | 113 | (q15_t) (q31_t) (((q31_t) a * d) >> 17) + (((q31_t) b * c) >> 17); |
emilmont | 1:fdd22bb7aa52 | 114 | |
emilmont | 1:fdd22bb7aa52 | 115 | a = *pSrcA++; |
emilmont | 1:fdd22bb7aa52 | 116 | b = *pSrcA++; |
emilmont | 1:fdd22bb7aa52 | 117 | c = *pSrcB++; |
emilmont | 1:fdd22bb7aa52 | 118 | d = *pSrcB++; |
emilmont | 1:fdd22bb7aa52 | 119 | |
emilmont | 1:fdd22bb7aa52 | 120 | /* store the result in 3.13 format in the destination buffer. */ |
emilmont | 1:fdd22bb7aa52 | 121 | *pDst++ = |
emilmont | 1:fdd22bb7aa52 | 122 | (q15_t) (q31_t) (((q31_t) a * c) >> 17) - (((q31_t) b * d) >> 17); |
emilmont | 1:fdd22bb7aa52 | 123 | /* store the result in 3.13 format in the destination buffer. */ |
emilmont | 1:fdd22bb7aa52 | 124 | *pDst++ = |
emilmont | 1:fdd22bb7aa52 | 125 | (q15_t) (q31_t) (((q31_t) a * d) >> 17) + (((q31_t) b * c) >> 17); |
emilmont | 1:fdd22bb7aa52 | 126 | |
emilmont | 1:fdd22bb7aa52 | 127 | /* Decrement the blockSize loop counter */ |
emilmont | 1:fdd22bb7aa52 | 128 | blkCnt--; |
emilmont | 1:fdd22bb7aa52 | 129 | } |
emilmont | 1:fdd22bb7aa52 | 130 | |
emilmont | 1:fdd22bb7aa52 | 131 | /* If the blockSize is not a multiple of 4, compute any remaining output samples here. |
emilmont | 1:fdd22bb7aa52 | 132 | ** No loop unrolling is used. */ |
emilmont | 1:fdd22bb7aa52 | 133 | blkCnt = numSamples % 0x4u; |
emilmont | 1:fdd22bb7aa52 | 134 | |
emilmont | 1:fdd22bb7aa52 | 135 | while(blkCnt > 0u) |
emilmont | 1:fdd22bb7aa52 | 136 | { |
emilmont | 1:fdd22bb7aa52 | 137 | /* C[2 * i] = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1]. */ |
emilmont | 1:fdd22bb7aa52 | 138 | /* C[2 * i + 1] = A[2 * i] * B[2 * i + 1] + A[2 * i + 1] * B[2 * i]. */ |
emilmont | 1:fdd22bb7aa52 | 139 | a = *pSrcA++; |
emilmont | 1:fdd22bb7aa52 | 140 | b = *pSrcA++; |
emilmont | 1:fdd22bb7aa52 | 141 | c = *pSrcB++; |
emilmont | 1:fdd22bb7aa52 | 142 | d = *pSrcB++; |
emilmont | 1:fdd22bb7aa52 | 143 | |
emilmont | 1:fdd22bb7aa52 | 144 | /* store the result in 3.13 format in the destination buffer. */ |
emilmont | 1:fdd22bb7aa52 | 145 | *pDst++ = |
emilmont | 1:fdd22bb7aa52 | 146 | (q15_t) (q31_t) (((q31_t) a * c) >> 17) - (((q31_t) b * d) >> 17); |
emilmont | 1:fdd22bb7aa52 | 147 | /* store the result in 3.13 format in the destination buffer. */ |
emilmont | 1:fdd22bb7aa52 | 148 | *pDst++ = |
emilmont | 1:fdd22bb7aa52 | 149 | (q15_t) (q31_t) (((q31_t) a * d) >> 17) + (((q31_t) b * c) >> 17); |
emilmont | 1:fdd22bb7aa52 | 150 | |
emilmont | 1:fdd22bb7aa52 | 151 | /* Decrement the blockSize loop counter */ |
emilmont | 1:fdd22bb7aa52 | 152 | blkCnt--; |
emilmont | 1:fdd22bb7aa52 | 153 | } |
emilmont | 1:fdd22bb7aa52 | 154 | |
emilmont | 1:fdd22bb7aa52 | 155 | #else |
emilmont | 1:fdd22bb7aa52 | 156 | |
emilmont | 1:fdd22bb7aa52 | 157 | /* Run the below code for Cortex-M0 */ |
emilmont | 1:fdd22bb7aa52 | 158 | |
emilmont | 1:fdd22bb7aa52 | 159 | while(numSamples > 0u) |
emilmont | 1:fdd22bb7aa52 | 160 | { |
emilmont | 1:fdd22bb7aa52 | 161 | /* C[2 * i] = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1]. */ |
emilmont | 1:fdd22bb7aa52 | 162 | /* C[2 * i + 1] = A[2 * i] * B[2 * i + 1] + A[2 * i + 1] * B[2 * i]. */ |
emilmont | 1:fdd22bb7aa52 | 163 | a = *pSrcA++; |
emilmont | 1:fdd22bb7aa52 | 164 | b = *pSrcA++; |
emilmont | 1:fdd22bb7aa52 | 165 | c = *pSrcB++; |
emilmont | 1:fdd22bb7aa52 | 166 | d = *pSrcB++; |
emilmont | 1:fdd22bb7aa52 | 167 | |
emilmont | 1:fdd22bb7aa52 | 168 | /* store the result in 3.13 format in the destination buffer. */ |
emilmont | 1:fdd22bb7aa52 | 169 | *pDst++ = |
emilmont | 1:fdd22bb7aa52 | 170 | (q15_t) (q31_t) (((q31_t) a * c) >> 17) - (((q31_t) b * d) >> 17); |
emilmont | 1:fdd22bb7aa52 | 171 | /* store the result in 3.13 format in the destination buffer. */ |
emilmont | 1:fdd22bb7aa52 | 172 | *pDst++ = |
emilmont | 1:fdd22bb7aa52 | 173 | (q15_t) (q31_t) (((q31_t) a * d) >> 17) + (((q31_t) b * c) >> 17); |
emilmont | 1:fdd22bb7aa52 | 174 | |
emilmont | 1:fdd22bb7aa52 | 175 | /* Decrement the blockSize loop counter */ |
emilmont | 1:fdd22bb7aa52 | 176 | numSamples--; |
emilmont | 1:fdd22bb7aa52 | 177 | } |
emilmont | 1:fdd22bb7aa52 | 178 | |
emilmont | 1:fdd22bb7aa52 | 179 | #endif /* #ifndef ARM_MATH_CM0 */ |
emilmont | 1:fdd22bb7aa52 | 180 | |
emilmont | 1:fdd22bb7aa52 | 181 | } |
emilmont | 1:fdd22bb7aa52 | 182 | |
emilmont | 1:fdd22bb7aa52 | 183 | /** |
emilmont | 1:fdd22bb7aa52 | 184 | * @} end of CmplxByCmplxMult group |
emilmont | 1:fdd22bb7aa52 | 185 | */ |