mbed-os 6.10 versione
cmsis_dsp/ComplexMathFunctions/arm_cmplx_dot_prod_q31.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_dot_prod_q31.c |
emilmont | 1:fdd22bb7aa52 | 9 | * |
emilmont | 1:fdd22bb7aa52 | 10 | * Description: Q31 complex dot product |
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 cmplx_dot_prod |
emilmont | 1:fdd22bb7aa52 | 41 | * @{ |
emilmont | 1:fdd22bb7aa52 | 42 | */ |
emilmont | 1:fdd22bb7aa52 | 43 | |
emilmont | 1:fdd22bb7aa52 | 44 | /** |
emilmont | 1:fdd22bb7aa52 | 45 | * @brief Q31 complex dot product |
emilmont | 1:fdd22bb7aa52 | 46 | * @param *pSrcA points to the first input vector |
emilmont | 1:fdd22bb7aa52 | 47 | * @param *pSrcB points to the second input vector |
emilmont | 1:fdd22bb7aa52 | 48 | * @param numSamples number of complex samples in each vector |
emilmont | 1:fdd22bb7aa52 | 49 | * @param *realResult real part of the result returned here |
emilmont | 1:fdd22bb7aa52 | 50 | * @param *imagResult imaginary part of the result returned here |
emilmont | 1:fdd22bb7aa52 | 51 | * @return none. |
emilmont | 1:fdd22bb7aa52 | 52 | * |
emilmont | 1:fdd22bb7aa52 | 53 | * <b>Scaling and Overflow Behavior:</b> |
emilmont | 1:fdd22bb7aa52 | 54 | * \par |
emilmont | 1:fdd22bb7aa52 | 55 | * The function is implemented using an internal 64-bit accumulator. |
emilmont | 1:fdd22bb7aa52 | 56 | * The intermediate 1.31 by 1.31 multiplications are performed with 64-bit precision and then shifted to 16.48 format. |
emilmont | 1:fdd22bb7aa52 | 57 | * The internal real and imaginary accumulators are in 16.48 format and provide 15 guard bits. |
emilmont | 1:fdd22bb7aa52 | 58 | * Additions are nonsaturating and no overflow will occur as long as <code>numSamples</code> is less than 32768. |
emilmont | 1:fdd22bb7aa52 | 59 | * The return results <code>realResult</code> and <code>imagResult</code> are in 16.48 format. |
emilmont | 1:fdd22bb7aa52 | 60 | * Input down scaling is not required. |
emilmont | 1:fdd22bb7aa52 | 61 | */ |
emilmont | 1:fdd22bb7aa52 | 62 | |
emilmont | 1:fdd22bb7aa52 | 63 | void arm_cmplx_dot_prod_q31( |
emilmont | 1:fdd22bb7aa52 | 64 | q31_t * pSrcA, |
emilmont | 1:fdd22bb7aa52 | 65 | q31_t * pSrcB, |
emilmont | 1:fdd22bb7aa52 | 66 | uint32_t numSamples, |
emilmont | 1:fdd22bb7aa52 | 67 | q63_t * realResult, |
emilmont | 1:fdd22bb7aa52 | 68 | q63_t * imagResult) |
emilmont | 1:fdd22bb7aa52 | 69 | { |
emilmont | 1:fdd22bb7aa52 | 70 | q63_t real_sum = 0, imag_sum = 0; /* Temporary result storage */ |
emilmont | 1:fdd22bb7aa52 | 71 | |
emilmont | 1:fdd22bb7aa52 | 72 | #ifndef ARM_MATH_CM0 |
emilmont | 1:fdd22bb7aa52 | 73 | |
emilmont | 1:fdd22bb7aa52 | 74 | /* Run the below code for Cortex-M4 and Cortex-M3 */ |
emilmont | 1:fdd22bb7aa52 | 75 | uint32_t blkCnt; /* loop counter */ |
emilmont | 1:fdd22bb7aa52 | 76 | |
emilmont | 1:fdd22bb7aa52 | 77 | |
emilmont | 1:fdd22bb7aa52 | 78 | /*loop Unrolling */ |
emilmont | 1:fdd22bb7aa52 | 79 | blkCnt = numSamples >> 2u; |
emilmont | 1:fdd22bb7aa52 | 80 | |
emilmont | 1:fdd22bb7aa52 | 81 | /* First part of the processing with loop unrolling. Compute 4 outputs at a time. |
emilmont | 1:fdd22bb7aa52 | 82 | ** a second loop below computes the remaining 1 to 3 samples. */ |
emilmont | 1:fdd22bb7aa52 | 83 | while(blkCnt > 0u) |
emilmont | 1:fdd22bb7aa52 | 84 | { |
emilmont | 1:fdd22bb7aa52 | 85 | /* CReal = A[0]* B[0] + A[2]* B[2] + A[4]* B[4] + .....+ A[numSamples-2]* B[numSamples-2] */ |
emilmont | 1:fdd22bb7aa52 | 86 | /* Convert real data in 2.62 to 16.48 by 14 right shifts */ |
emilmont | 1:fdd22bb7aa52 | 87 | real_sum += (q63_t) * pSrcA++ * (*pSrcB++) >> 14; |
emilmont | 1:fdd22bb7aa52 | 88 | /* CImag = A[1]* B[1] + A[3]* B[3] + A[5]* B[5] + .....+ A[numSamples-1]* B[numSamples-1] */ |
emilmont | 1:fdd22bb7aa52 | 89 | /* Convert imag data in 2.62 to 16.48 by 14 right shifts */ |
emilmont | 1:fdd22bb7aa52 | 90 | imag_sum += (q63_t) * pSrcA++ * (*pSrcB++) >> 14; |
emilmont | 1:fdd22bb7aa52 | 91 | |
emilmont | 1:fdd22bb7aa52 | 92 | real_sum += (q63_t) * pSrcA++ * (*pSrcB++) >> 14; |
emilmont | 1:fdd22bb7aa52 | 93 | imag_sum += (q63_t) * pSrcA++ * (*pSrcB++) >> 14; |
emilmont | 1:fdd22bb7aa52 | 94 | |
emilmont | 1:fdd22bb7aa52 | 95 | real_sum += (q63_t) * pSrcA++ * (*pSrcB++) >> 14; |
emilmont | 1:fdd22bb7aa52 | 96 | imag_sum += (q63_t) * pSrcA++ * (*pSrcB++) >> 14; |
emilmont | 1:fdd22bb7aa52 | 97 | |
emilmont | 1:fdd22bb7aa52 | 98 | real_sum += (q63_t) * pSrcA++ * (*pSrcB++) >> 14; |
emilmont | 1:fdd22bb7aa52 | 99 | imag_sum += (q63_t) * pSrcA++ * (*pSrcB++) >> 14; |
emilmont | 1:fdd22bb7aa52 | 100 | |
emilmont | 1:fdd22bb7aa52 | 101 | |
emilmont | 1:fdd22bb7aa52 | 102 | /* Decrement the loop counter */ |
emilmont | 1:fdd22bb7aa52 | 103 | blkCnt--; |
emilmont | 1:fdd22bb7aa52 | 104 | } |
emilmont | 1:fdd22bb7aa52 | 105 | |
emilmont | 1:fdd22bb7aa52 | 106 | /* If the numSamples is not a multiple of 4, compute any remaining output samples here. |
emilmont | 1:fdd22bb7aa52 | 107 | ** No loop unrolling is used. */ |
emilmont | 1:fdd22bb7aa52 | 108 | blkCnt = numSamples % 0x4u; |
emilmont | 1:fdd22bb7aa52 | 109 | |
emilmont | 1:fdd22bb7aa52 | 110 | while(blkCnt > 0u) |
emilmont | 1:fdd22bb7aa52 | 111 | { |
emilmont | 1:fdd22bb7aa52 | 112 | /* CReal = A[0]* B[0] + A[2]* B[2] + A[4]* B[4] + .....+ A[numSamples-2]* B[numSamples-2] */ |
emilmont | 1:fdd22bb7aa52 | 113 | real_sum += (q63_t) * pSrcA++ * (*pSrcB++) >> 14; |
emilmont | 1:fdd22bb7aa52 | 114 | /* CImag = A[1]* B[1] + A[3]* B[3] + A[5]* B[5] + .....+ A[numSamples-1]* B[numSamples-1] */ |
emilmont | 1:fdd22bb7aa52 | 115 | imag_sum += (q63_t) * pSrcA++ * (*pSrcB++) >> 14; |
emilmont | 1:fdd22bb7aa52 | 116 | |
emilmont | 1:fdd22bb7aa52 | 117 | /* Decrement the loop counter */ |
emilmont | 1:fdd22bb7aa52 | 118 | blkCnt--; |
emilmont | 1:fdd22bb7aa52 | 119 | } |
emilmont | 1:fdd22bb7aa52 | 120 | |
emilmont | 1:fdd22bb7aa52 | 121 | #else |
emilmont | 1:fdd22bb7aa52 | 122 | |
emilmont | 1:fdd22bb7aa52 | 123 | /* Run the below code for Cortex-M0 */ |
emilmont | 1:fdd22bb7aa52 | 124 | |
emilmont | 1:fdd22bb7aa52 | 125 | while(numSamples > 0u) |
emilmont | 1:fdd22bb7aa52 | 126 | { |
emilmont | 1:fdd22bb7aa52 | 127 | /* outReal = realA[0]* realB[0] + realA[2]* realB[2] + realA[4]* realB[4] + .....+ realA[numSamples-2]* realB[numSamples-2] */ |
emilmont | 1:fdd22bb7aa52 | 128 | real_sum += (q63_t) * pSrcA++ * (*pSrcB++) >> 14; |
emilmont | 1:fdd22bb7aa52 | 129 | /* outImag = imagA[1]* imagB[1] + imagA[3]* imagB[3] + imagA[5]* imagB[5] + .....+ imagA[numSamples-1]* imagB[numSamples-1] */ |
emilmont | 1:fdd22bb7aa52 | 130 | imag_sum += (q63_t) * pSrcA++ * (*pSrcB++) >> 14; |
emilmont | 1:fdd22bb7aa52 | 131 | |
emilmont | 1:fdd22bb7aa52 | 132 | /* Decrement the loop counter */ |
emilmont | 1:fdd22bb7aa52 | 133 | numSamples--; |
emilmont | 1:fdd22bb7aa52 | 134 | } |
emilmont | 1:fdd22bb7aa52 | 135 | |
emilmont | 1:fdd22bb7aa52 | 136 | #endif /* #ifndef ARM_MATH_CM0 */ |
emilmont | 1:fdd22bb7aa52 | 137 | |
emilmont | 1:fdd22bb7aa52 | 138 | /* Store the real and imaginary results in 16.48 format */ |
emilmont | 1:fdd22bb7aa52 | 139 | *realResult = real_sum; |
emilmont | 1:fdd22bb7aa52 | 140 | *imagResult = imag_sum; |
emilmont | 1:fdd22bb7aa52 | 141 | } |
emilmont | 1:fdd22bb7aa52 | 142 | |
emilmont | 1:fdd22bb7aa52 | 143 | /** |
emilmont | 1:fdd22bb7aa52 | 144 | * @} end of cmplx_dot_prod group |
emilmont | 1:fdd22bb7aa52 | 145 | */ |