mbed-os 6.10 versione
cmsis_dsp/ComplexMathFunctions/arm_cmplx_dot_prod_f32.c@2:da51fb522205, 2013-05-30 (annotated)
- Committer:
- emilmont
- Date:
- Thu May 30 17:10:11 2013 +0100
- Revision:
- 2:da51fb522205
- Parent:
- 1:fdd22bb7aa52
- Child:
- 3:7a284390b0ce
Keep "cmsis-dsp" module in synch with its source
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 | 2:da51fb522205 | 5 | * $Revision: V1.1.0 |
emilmont | 1:fdd22bb7aa52 | 6 | * |
emilmont | 2:da51fb522205 | 7 | * Project: CMSIS DSP Library |
emilmont | 2:da51fb522205 | 8 | * Title: arm_cmplx_dot_prod_f32.c |
emilmont | 1:fdd22bb7aa52 | 9 | * |
emilmont | 2:da51fb522205 | 10 | * Description: Floating-point 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 | * @defgroup cmplx_dot_prod Complex Dot Product |
emilmont | 1:fdd22bb7aa52 | 41 | * |
emilmont | 1:fdd22bb7aa52 | 42 | * Computes the dot product of two complex vectors. |
emilmont | 1:fdd22bb7aa52 | 43 | * The vectors are multiplied element-by-element and then summed. |
emilmont | 1:fdd22bb7aa52 | 44 | * |
emilmont | 1:fdd22bb7aa52 | 45 | * The <code>pSrcA</code> points to the first complex input vector and |
emilmont | 1:fdd22bb7aa52 | 46 | * <code>pSrcB</code> points to the second complex input vector. |
emilmont | 1:fdd22bb7aa52 | 47 | * <code>numSamples</code> specifies the number of complex samples |
emilmont | 1:fdd22bb7aa52 | 48 | * and the data in each array is stored in an interleaved fashion |
emilmont | 1:fdd22bb7aa52 | 49 | * (real, imag, real, imag, ...). |
emilmont | 1:fdd22bb7aa52 | 50 | * Each array has a total of <code>2*numSamples</code> values. |
emilmont | 1:fdd22bb7aa52 | 51 | * |
emilmont | 1:fdd22bb7aa52 | 52 | * The underlying algorithm is used: |
emilmont | 1:fdd22bb7aa52 | 53 | * <pre> |
emilmont | 1:fdd22bb7aa52 | 54 | * realResult=0; |
emilmont | 1:fdd22bb7aa52 | 55 | * imagResult=0; |
emilmont | 1:fdd22bb7aa52 | 56 | * for(n=0; n<numSamples; n++) { |
emilmont | 1:fdd22bb7aa52 | 57 | * realResult += pSrcA[(2*n)+0]*pSrcB[(2*n)+0] - pSrcA[(2*n)+1]*pSrcB[(2*n)+1]; |
emilmont | 1:fdd22bb7aa52 | 58 | * imagResult += pSrcA[(2*n)+0]*pSrcB[(2*n)+1] + pSrcA[(2*n)+1]*pSrcB[(2*n)+0]; |
emilmont | 1:fdd22bb7aa52 | 59 | * } |
emilmont | 1:fdd22bb7aa52 | 60 | * </pre> |
emilmont | 1:fdd22bb7aa52 | 61 | * |
emilmont | 1:fdd22bb7aa52 | 62 | * There are separate functions for floating-point, Q15, and Q31 data types. |
emilmont | 1:fdd22bb7aa52 | 63 | */ |
emilmont | 1:fdd22bb7aa52 | 64 | |
emilmont | 1:fdd22bb7aa52 | 65 | /** |
emilmont | 1:fdd22bb7aa52 | 66 | * @addtogroup cmplx_dot_prod |
emilmont | 1:fdd22bb7aa52 | 67 | * @{ |
emilmont | 1:fdd22bb7aa52 | 68 | */ |
emilmont | 1:fdd22bb7aa52 | 69 | |
emilmont | 1:fdd22bb7aa52 | 70 | /** |
emilmont | 1:fdd22bb7aa52 | 71 | * @brief Floating-point complex dot product |
emilmont | 1:fdd22bb7aa52 | 72 | * @param *pSrcA points to the first input vector |
emilmont | 1:fdd22bb7aa52 | 73 | * @param *pSrcB points to the second input vector |
emilmont | 1:fdd22bb7aa52 | 74 | * @param numSamples number of complex samples in each vector |
emilmont | 1:fdd22bb7aa52 | 75 | * @param *realResult real part of the result returned here |
emilmont | 1:fdd22bb7aa52 | 76 | * @param *imagResult imaginary part of the result returned here |
emilmont | 1:fdd22bb7aa52 | 77 | * @return none. |
emilmont | 1:fdd22bb7aa52 | 78 | */ |
emilmont | 1:fdd22bb7aa52 | 79 | |
emilmont | 1:fdd22bb7aa52 | 80 | void arm_cmplx_dot_prod_f32( |
emilmont | 1:fdd22bb7aa52 | 81 | float32_t * pSrcA, |
emilmont | 1:fdd22bb7aa52 | 82 | float32_t * pSrcB, |
emilmont | 1:fdd22bb7aa52 | 83 | uint32_t numSamples, |
emilmont | 1:fdd22bb7aa52 | 84 | float32_t * realResult, |
emilmont | 1:fdd22bb7aa52 | 85 | float32_t * imagResult) |
emilmont | 1:fdd22bb7aa52 | 86 | { |
emilmont | 1:fdd22bb7aa52 | 87 | float32_t real_sum = 0.0f, imag_sum = 0.0f; /* Temporary result storage */ |
emilmont | 1:fdd22bb7aa52 | 88 | |
emilmont | 1:fdd22bb7aa52 | 89 | #ifndef ARM_MATH_CM0 |
emilmont | 1:fdd22bb7aa52 | 90 | |
emilmont | 1:fdd22bb7aa52 | 91 | /* Run the below code for Cortex-M4 and Cortex-M3 */ |
emilmont | 1:fdd22bb7aa52 | 92 | uint32_t blkCnt; /* loop counter */ |
emilmont | 1:fdd22bb7aa52 | 93 | |
emilmont | 1:fdd22bb7aa52 | 94 | /*loop Unrolling */ |
emilmont | 1:fdd22bb7aa52 | 95 | blkCnt = numSamples >> 2u; |
emilmont | 1:fdd22bb7aa52 | 96 | |
emilmont | 1:fdd22bb7aa52 | 97 | /* First part of the processing with loop unrolling. Compute 4 outputs at a time. |
emilmont | 1:fdd22bb7aa52 | 98 | ** a second loop below computes the remaining 1 to 3 samples. */ |
emilmont | 1:fdd22bb7aa52 | 99 | while(blkCnt > 0u) |
emilmont | 1:fdd22bb7aa52 | 100 | { |
emilmont | 1:fdd22bb7aa52 | 101 | /* CReal = A[0]* B[0] + A[2]* B[2] + A[4]* B[4] + .....+ A[numSamples-2]* B[numSamples-2] */ |
emilmont | 1:fdd22bb7aa52 | 102 | real_sum += (*pSrcA++) * (*pSrcB++); |
emilmont | 1:fdd22bb7aa52 | 103 | /* CImag = A[1]* B[1] + A[3]* B[3] + A[5]* B[5] + .....+ A[numSamples-1]* B[numSamples-1] */ |
emilmont | 1:fdd22bb7aa52 | 104 | imag_sum += (*pSrcA++) * (*pSrcB++); |
emilmont | 1:fdd22bb7aa52 | 105 | |
emilmont | 1:fdd22bb7aa52 | 106 | real_sum += (*pSrcA++) * (*pSrcB++); |
emilmont | 1:fdd22bb7aa52 | 107 | imag_sum += (*pSrcA++) * (*pSrcB++); |
emilmont | 1:fdd22bb7aa52 | 108 | |
emilmont | 1:fdd22bb7aa52 | 109 | real_sum += (*pSrcA++) * (*pSrcB++); |
emilmont | 1:fdd22bb7aa52 | 110 | imag_sum += (*pSrcA++) * (*pSrcB++); |
emilmont | 1:fdd22bb7aa52 | 111 | |
emilmont | 1:fdd22bb7aa52 | 112 | real_sum += (*pSrcA++) * (*pSrcB++); |
emilmont | 1:fdd22bb7aa52 | 113 | imag_sum += (*pSrcA++) * (*pSrcB++); |
emilmont | 1:fdd22bb7aa52 | 114 | |
emilmont | 1:fdd22bb7aa52 | 115 | /* Decrement the loop counter */ |
emilmont | 1:fdd22bb7aa52 | 116 | blkCnt--; |
emilmont | 1:fdd22bb7aa52 | 117 | } |
emilmont | 1:fdd22bb7aa52 | 118 | |
emilmont | 1:fdd22bb7aa52 | 119 | /* If the numSamples is not a multiple of 4, compute any remaining output samples here. |
emilmont | 1:fdd22bb7aa52 | 120 | ** No loop unrolling is used. */ |
emilmont | 1:fdd22bb7aa52 | 121 | blkCnt = numSamples % 0x4u; |
emilmont | 1:fdd22bb7aa52 | 122 | |
emilmont | 1:fdd22bb7aa52 | 123 | while(blkCnt > 0u) |
emilmont | 1:fdd22bb7aa52 | 124 | { |
emilmont | 1:fdd22bb7aa52 | 125 | /* CReal = A[0]* B[0] + A[2]* B[2] + A[4]* B[4] + .....+ A[numSamples-2]* B[numSamples-2] */ |
emilmont | 1:fdd22bb7aa52 | 126 | real_sum += (*pSrcA++) * (*pSrcB++); |
emilmont | 1:fdd22bb7aa52 | 127 | /* CImag = A[1]* B[1] + A[3]* B[3] + A[5]* B[5] + .....+ A[numSamples-1]* B[numSamples-1] */ |
emilmont | 1:fdd22bb7aa52 | 128 | imag_sum += (*pSrcA++) * (*pSrcB++); |
emilmont | 1:fdd22bb7aa52 | 129 | |
emilmont | 1:fdd22bb7aa52 | 130 | |
emilmont | 1:fdd22bb7aa52 | 131 | /* Decrement the loop counter */ |
emilmont | 1:fdd22bb7aa52 | 132 | blkCnt--; |
emilmont | 1:fdd22bb7aa52 | 133 | } |
emilmont | 1:fdd22bb7aa52 | 134 | |
emilmont | 1:fdd22bb7aa52 | 135 | #else |
emilmont | 1:fdd22bb7aa52 | 136 | |
emilmont | 1:fdd22bb7aa52 | 137 | /* Run the below code for Cortex-M0 */ |
emilmont | 1:fdd22bb7aa52 | 138 | |
emilmont | 1:fdd22bb7aa52 | 139 | while(numSamples > 0u) |
emilmont | 1:fdd22bb7aa52 | 140 | { |
emilmont | 1:fdd22bb7aa52 | 141 | /* CReal = A[0]* B[0] + A[2]* B[2] + A[4]* B[4] + .....+ A[numSamples-2]* B[numSamples-2] */ |
emilmont | 1:fdd22bb7aa52 | 142 | real_sum += (*pSrcA++) * (*pSrcB++); |
emilmont | 1:fdd22bb7aa52 | 143 | /* CImag = A[1]* B[1] + A[3]* B[3] + A[5]* B[5] + .....+ A[numSamples-1]* B[numSamples-1] */ |
emilmont | 1:fdd22bb7aa52 | 144 | imag_sum += (*pSrcA++) * (*pSrcB++); |
emilmont | 1:fdd22bb7aa52 | 145 | |
emilmont | 1:fdd22bb7aa52 | 146 | |
emilmont | 1:fdd22bb7aa52 | 147 | /* Decrement the loop counter */ |
emilmont | 1:fdd22bb7aa52 | 148 | numSamples--; |
emilmont | 1:fdd22bb7aa52 | 149 | } |
emilmont | 1:fdd22bb7aa52 | 150 | |
emilmont | 1:fdd22bb7aa52 | 151 | #endif /* #ifndef ARM_MATH_CM0 */ |
emilmont | 1:fdd22bb7aa52 | 152 | |
emilmont | 1:fdd22bb7aa52 | 153 | /* Store the real and imaginary results in the destination buffers */ |
emilmont | 1:fdd22bb7aa52 | 154 | *realResult = real_sum; |
emilmont | 1:fdd22bb7aa52 | 155 | *imagResult = imag_sum; |
emilmont | 1:fdd22bb7aa52 | 156 | } |
emilmont | 1:fdd22bb7aa52 | 157 | |
emilmont | 1:fdd22bb7aa52 | 158 | /** |
emilmont | 1:fdd22bb7aa52 | 159 | * @} end of cmplx_dot_prod group |
emilmont | 1:fdd22bb7aa52 | 160 | */ |