CMSIS DSP Library from CMSIS 2.0. See http://www.onarm.com/cmsis/ for full details
Dependents: K22F_DSP_Matrix_least_square BNO055-ELEC3810 1BNO055 ECE4180Project--Slave2 ... more
src/Cortex-M4-M3/ComplexMathFunctions/arm_cmplx_mult_cmplx_q31.c@0:1014af42efd9, 2011-03-10 (annotated)
- Committer:
- simon
- Date:
- Thu Mar 10 15:07:50 2011 +0000
- Revision:
- 0:1014af42efd9
Who changed what in which revision?
User | Revision | Line number | New contents of line |
---|---|---|---|
simon | 0:1014af42efd9 | 1 | /* ---------------------------------------------------------------------- |
simon | 0:1014af42efd9 | 2 | * Copyright (C) 2010 ARM Limited. All rights reserved. |
simon | 0:1014af42efd9 | 3 | * |
simon | 0:1014af42efd9 | 4 | * $Date: 29. November 2010 |
simon | 0:1014af42efd9 | 5 | * $Revision: V1.0.3 |
simon | 0:1014af42efd9 | 6 | * |
simon | 0:1014af42efd9 | 7 | * Project: CMSIS DSP Library |
simon | 0:1014af42efd9 | 8 | * Title: arm_cmplx_mult_cmplx_q31.c |
simon | 0:1014af42efd9 | 9 | * |
simon | 0:1014af42efd9 | 10 | * Description: Q31 complex-by-complex multiplication |
simon | 0:1014af42efd9 | 11 | * |
simon | 0:1014af42efd9 | 12 | * Target Processor: Cortex-M4/Cortex-M3 |
simon | 0:1014af42efd9 | 13 | * |
simon | 0:1014af42efd9 | 14 | * Version 1.0.3 2010/11/29 |
simon | 0:1014af42efd9 | 15 | * Re-organized the CMSIS folders and updated documentation. |
simon | 0:1014af42efd9 | 16 | * |
simon | 0:1014af42efd9 | 17 | * Version 1.0.2 2010/11/11 |
simon | 0:1014af42efd9 | 18 | * Documentation updated. |
simon | 0:1014af42efd9 | 19 | * |
simon | 0:1014af42efd9 | 20 | * Version 1.0.1 2010/10/05 |
simon | 0:1014af42efd9 | 21 | * Production release and review comments incorporated. |
simon | 0:1014af42efd9 | 22 | * |
simon | 0:1014af42efd9 | 23 | * Version 1.0.0 2010/09/20 |
simon | 0:1014af42efd9 | 24 | * Production release and review comments incorporated. |
simon | 0:1014af42efd9 | 25 | * -------------------------------------------------------------------- */ |
simon | 0:1014af42efd9 | 26 | |
simon | 0:1014af42efd9 | 27 | #include "arm_math.h" |
simon | 0:1014af42efd9 | 28 | |
simon | 0:1014af42efd9 | 29 | /** |
simon | 0:1014af42efd9 | 30 | * @ingroup groupCmplxMath |
simon | 0:1014af42efd9 | 31 | */ |
simon | 0:1014af42efd9 | 32 | |
simon | 0:1014af42efd9 | 33 | /** |
simon | 0:1014af42efd9 | 34 | * @addtogroup CmplxByCmplxMult |
simon | 0:1014af42efd9 | 35 | * @{ |
simon | 0:1014af42efd9 | 36 | */ |
simon | 0:1014af42efd9 | 37 | |
simon | 0:1014af42efd9 | 38 | |
simon | 0:1014af42efd9 | 39 | /** |
simon | 0:1014af42efd9 | 40 | * @brief Q31 complex-by-complex multiplication |
simon | 0:1014af42efd9 | 41 | * @param[in] *pSrcA points to the first input vector |
simon | 0:1014af42efd9 | 42 | * @param[in] *pSrcB points to the second input vector |
simon | 0:1014af42efd9 | 43 | * @param[out] *pDst points to the output vector |
simon | 0:1014af42efd9 | 44 | * @param[in] numSamples number of complex samples in each vector |
simon | 0:1014af42efd9 | 45 | * @return none. |
simon | 0:1014af42efd9 | 46 | * |
simon | 0:1014af42efd9 | 47 | * <b>Scaling and Overflow Behavior:</b> |
simon | 0:1014af42efd9 | 48 | * \par |
simon | 0:1014af42efd9 | 49 | * The function implements 1.31 by 1.31 multiplications and finally output is converted into 3.29 format. |
simon | 0:1014af42efd9 | 50 | * Input down scaling is not required. |
simon | 0:1014af42efd9 | 51 | */ |
simon | 0:1014af42efd9 | 52 | |
simon | 0:1014af42efd9 | 53 | void arm_cmplx_mult_cmplx_q31( |
simon | 0:1014af42efd9 | 54 | q31_t * pSrcA, |
simon | 0:1014af42efd9 | 55 | q31_t * pSrcB, |
simon | 0:1014af42efd9 | 56 | q31_t * pDst, |
simon | 0:1014af42efd9 | 57 | uint32_t numSamples) |
simon | 0:1014af42efd9 | 58 | { |
simon | 0:1014af42efd9 | 59 | q31_t a, b, c, d; /* Temporary variables to store real and imaginary values */ |
simon | 0:1014af42efd9 | 60 | uint32_t blkCnt; /* loop counters */ |
simon | 0:1014af42efd9 | 61 | |
simon | 0:1014af42efd9 | 62 | /* loop Unrolling */ |
simon | 0:1014af42efd9 | 63 | blkCnt = numSamples >> 2u; |
simon | 0:1014af42efd9 | 64 | |
simon | 0:1014af42efd9 | 65 | /* First part of the processing with loop unrolling. Compute 4 outputs at a time. |
simon | 0:1014af42efd9 | 66 | ** a second loop below computes the remaining 1 to 3 samples. */ |
simon | 0:1014af42efd9 | 67 | while(blkCnt > 0u) |
simon | 0:1014af42efd9 | 68 | { |
simon | 0:1014af42efd9 | 69 | /* C[2 * i] = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1]. */ |
simon | 0:1014af42efd9 | 70 | /* C[2 * i + 1] = A[2 * i] * B[2 * i + 1] + A[2 * i + 1] * B[2 * i]. */ |
simon | 0:1014af42efd9 | 71 | a = *pSrcA++; |
simon | 0:1014af42efd9 | 72 | b = *pSrcA++; |
simon | 0:1014af42efd9 | 73 | c = *pSrcB++; |
simon | 0:1014af42efd9 | 74 | d = *pSrcB++; |
simon | 0:1014af42efd9 | 75 | |
simon | 0:1014af42efd9 | 76 | /* store the real result in 3.29 format in the destination buffer. */ |
simon | 0:1014af42efd9 | 77 | *pDst++ = (q31_t) ((((q63_t) a * c) >> 33) - (((q63_t) b * d) >> 33)); |
simon | 0:1014af42efd9 | 78 | /* store the imag result in 3.29 format in the destination buffer. */ |
simon | 0:1014af42efd9 | 79 | *pDst++ = (q31_t) ((((q63_t) a * d) >> 33) + (((q63_t) b * c) >> 33)); |
simon | 0:1014af42efd9 | 80 | |
simon | 0:1014af42efd9 | 81 | a = *pSrcA++; |
simon | 0:1014af42efd9 | 82 | b = *pSrcA++; |
simon | 0:1014af42efd9 | 83 | c = *pSrcB++; |
simon | 0:1014af42efd9 | 84 | d = *pSrcB++; |
simon | 0:1014af42efd9 | 85 | |
simon | 0:1014af42efd9 | 86 | /* store the result in 3.29 format in the destination buffer. */ |
simon | 0:1014af42efd9 | 87 | *pDst++ = (q31_t) ((((q63_t) a * c) >> 33) - (((q63_t) b * d) >> 33)); |
simon | 0:1014af42efd9 | 88 | /* store the result in 3.29 format in the destination buffer. */ |
simon | 0:1014af42efd9 | 89 | *pDst++ = (q31_t) ((((q63_t) a * d) >> 33) + (((q63_t) b * c) >> 33)); |
simon | 0:1014af42efd9 | 90 | |
simon | 0:1014af42efd9 | 91 | a = *pSrcA++; |
simon | 0:1014af42efd9 | 92 | b = *pSrcA++; |
simon | 0:1014af42efd9 | 93 | c = *pSrcB++; |
simon | 0:1014af42efd9 | 94 | d = *pSrcB++; |
simon | 0:1014af42efd9 | 95 | |
simon | 0:1014af42efd9 | 96 | /* store the result in 3.29 format in the destination buffer. */ |
simon | 0:1014af42efd9 | 97 | *pDst++ = (q31_t) ((((q63_t) a * c) >> 33) - (((q63_t) b * d) >> 33)); |
simon | 0:1014af42efd9 | 98 | /* store the result in 3.29 format in the destination buffer. */ |
simon | 0:1014af42efd9 | 99 | *pDst++ = (q31_t) ((((q63_t) a * d) >> 33) + (((q63_t) b * c) >> 33)); |
simon | 0:1014af42efd9 | 100 | |
simon | 0:1014af42efd9 | 101 | a = *pSrcA++; |
simon | 0:1014af42efd9 | 102 | b = *pSrcA++; |
simon | 0:1014af42efd9 | 103 | c = *pSrcB++; |
simon | 0:1014af42efd9 | 104 | d = *pSrcB++; |
simon | 0:1014af42efd9 | 105 | |
simon | 0:1014af42efd9 | 106 | /* store the result in 3.29 format in the destination buffer. */ |
simon | 0:1014af42efd9 | 107 | *pDst++ = (q31_t) ((((q63_t) a * c) >> 33) - (((q63_t) b * d) >> 33)); |
simon | 0:1014af42efd9 | 108 | /* store the result in 3.29 format in the destination buffer. */ |
simon | 0:1014af42efd9 | 109 | *pDst++ = (q31_t) ((((q63_t) a * d) >> 33) + (((q63_t) b * c) >> 33)); |
simon | 0:1014af42efd9 | 110 | |
simon | 0:1014af42efd9 | 111 | /* Decrement the blockSize loop counter */ |
simon | 0:1014af42efd9 | 112 | blkCnt--; |
simon | 0:1014af42efd9 | 113 | } |
simon | 0:1014af42efd9 | 114 | |
simon | 0:1014af42efd9 | 115 | /* If the blockSize is not a multiple of 4, compute any remaining output samples here. |
simon | 0:1014af42efd9 | 116 | ** No loop unrolling is used. */ |
simon | 0:1014af42efd9 | 117 | blkCnt = numSamples % 0x4u; |
simon | 0:1014af42efd9 | 118 | |
simon | 0:1014af42efd9 | 119 | while(blkCnt > 0u) |
simon | 0:1014af42efd9 | 120 | { |
simon | 0:1014af42efd9 | 121 | /* C[2 * i] = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1]. */ |
simon | 0:1014af42efd9 | 122 | /* C[2 * i + 1] = A[2 * i] * B[2 * i + 1] + A[2 * i + 1] * B[2 * i]. */ |
simon | 0:1014af42efd9 | 123 | a = *pSrcA++; |
simon | 0:1014af42efd9 | 124 | b = *pSrcA++; |
simon | 0:1014af42efd9 | 125 | c = *pSrcB++; |
simon | 0:1014af42efd9 | 126 | d = *pSrcB++; |
simon | 0:1014af42efd9 | 127 | |
simon | 0:1014af42efd9 | 128 | /* store the result in 3.29 format in the destination buffer. */ |
simon | 0:1014af42efd9 | 129 | *pDst++ = (q31_t) ((((q63_t) a * c) >> 33) - (((q63_t) b * d) >> 33)); |
simon | 0:1014af42efd9 | 130 | /* store the result in 3.29 format in the destination buffer. */ |
simon | 0:1014af42efd9 | 131 | *pDst++ = (q31_t) ((((q63_t) a * d) >> 33) + (((q63_t) b * c) >> 33)); |
simon | 0:1014af42efd9 | 132 | |
simon | 0:1014af42efd9 | 133 | /* Decrement the blockSize loop counter */ |
simon | 0:1014af42efd9 | 134 | blkCnt--; |
simon | 0:1014af42efd9 | 135 | } |
simon | 0:1014af42efd9 | 136 | } |
simon | 0:1014af42efd9 | 137 | |
simon | 0:1014af42efd9 | 138 | /** |
simon | 0:1014af42efd9 | 139 | * @} end of CmplxByCmplxMult group |
simon | 0:1014af42efd9 | 140 | */ |