mbed-os 6.10 versione
cmsis_dsp/ComplexMathFunctions/arm_cmplx_mag_squared_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_mag_squared_f32.c |
emilmont | 1:fdd22bb7aa52 | 9 | * |
emilmont | 2:da51fb522205 | 10 | * Description: Floating-point complex magnitude squared. |
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 | #include "arm_math.h" |
emilmont | 1:fdd22bb7aa52 | 33 | |
emilmont | 1:fdd22bb7aa52 | 34 | /** |
emilmont | 1:fdd22bb7aa52 | 35 | * @ingroup groupCmplxMath |
emilmont | 1:fdd22bb7aa52 | 36 | */ |
emilmont | 1:fdd22bb7aa52 | 37 | |
emilmont | 1:fdd22bb7aa52 | 38 | /** |
emilmont | 1:fdd22bb7aa52 | 39 | * @defgroup cmplx_mag_squared Complex Magnitude Squared |
emilmont | 1:fdd22bb7aa52 | 40 | * |
emilmont | 1:fdd22bb7aa52 | 41 | * Computes the magnitude squared of the elements of a complex data vector. |
emilmont | 1:fdd22bb7aa52 | 42 | * |
emilmont | 1:fdd22bb7aa52 | 43 | * The <code>pSrc</code> points to the source data and |
emilmont | 1:fdd22bb7aa52 | 44 | * <code>pDst</code> points to the where the result should be written. |
emilmont | 1:fdd22bb7aa52 | 45 | * <code>numSamples</code> specifies the number of complex samples |
emilmont | 1:fdd22bb7aa52 | 46 | * in the input array and the data is stored in an interleaved fashion |
emilmont | 1:fdd22bb7aa52 | 47 | * (real, imag, real, imag, ...). |
emilmont | 1:fdd22bb7aa52 | 48 | * The input array has a total of <code>2*numSamples</code> values; |
emilmont | 1:fdd22bb7aa52 | 49 | * the output array has a total of <code>numSamples</code> values. |
emilmont | 1:fdd22bb7aa52 | 50 | * |
emilmont | 1:fdd22bb7aa52 | 51 | * The underlying algorithm is used: |
emilmont | 1:fdd22bb7aa52 | 52 | * |
emilmont | 1:fdd22bb7aa52 | 53 | * <pre> |
emilmont | 1:fdd22bb7aa52 | 54 | * for(n=0; n<numSamples; n++) { |
emilmont | 1:fdd22bb7aa52 | 55 | * pDst[n] = pSrc[(2*n)+0]^2 + pSrc[(2*n)+1]^2; |
emilmont | 1:fdd22bb7aa52 | 56 | * } |
emilmont | 1:fdd22bb7aa52 | 57 | * </pre> |
emilmont | 1:fdd22bb7aa52 | 58 | * |
emilmont | 1:fdd22bb7aa52 | 59 | * There are separate functions for floating-point, Q15, and Q31 data types. |
emilmont | 1:fdd22bb7aa52 | 60 | */ |
emilmont | 1:fdd22bb7aa52 | 61 | |
emilmont | 1:fdd22bb7aa52 | 62 | /** |
emilmont | 1:fdd22bb7aa52 | 63 | * @addtogroup cmplx_mag_squared |
emilmont | 1:fdd22bb7aa52 | 64 | * @{ |
emilmont | 1:fdd22bb7aa52 | 65 | */ |
emilmont | 1:fdd22bb7aa52 | 66 | |
emilmont | 1:fdd22bb7aa52 | 67 | |
emilmont | 1:fdd22bb7aa52 | 68 | /** |
emilmont | 1:fdd22bb7aa52 | 69 | * @brief Floating-point complex magnitude squared |
emilmont | 1:fdd22bb7aa52 | 70 | * @param[in] *pSrc points to the complex input vector |
emilmont | 1:fdd22bb7aa52 | 71 | * @param[out] *pDst points to the real output vector |
emilmont | 1:fdd22bb7aa52 | 72 | * @param[in] numSamples number of complex samples in the input vector |
emilmont | 1:fdd22bb7aa52 | 73 | * @return none. |
emilmont | 1:fdd22bb7aa52 | 74 | */ |
emilmont | 1:fdd22bb7aa52 | 75 | |
emilmont | 1:fdd22bb7aa52 | 76 | void arm_cmplx_mag_squared_f32( |
emilmont | 1:fdd22bb7aa52 | 77 | float32_t * pSrc, |
emilmont | 1:fdd22bb7aa52 | 78 | float32_t * pDst, |
emilmont | 1:fdd22bb7aa52 | 79 | uint32_t numSamples) |
emilmont | 1:fdd22bb7aa52 | 80 | { |
emilmont | 1:fdd22bb7aa52 | 81 | float32_t real, imag; /* Temporary variables to store real and imaginary values */ |
emilmont | 1:fdd22bb7aa52 | 82 | uint32_t blkCnt; /* loop counter */ |
emilmont | 1:fdd22bb7aa52 | 83 | |
emilmont | 1:fdd22bb7aa52 | 84 | #ifndef ARM_MATH_CM0 |
emilmont | 1:fdd22bb7aa52 | 85 | float32_t real1, real2, real3, real4; /* Temporary variables to hold real values */ |
emilmont | 1:fdd22bb7aa52 | 86 | float32_t imag1, imag2, imag3, imag4; /* Temporary variables to hold imaginary values */ |
emilmont | 1:fdd22bb7aa52 | 87 | float32_t mul1, mul2, mul3, mul4; /* Temporary variables */ |
emilmont | 1:fdd22bb7aa52 | 88 | float32_t mul5, mul6, mul7, mul8; /* Temporary variables */ |
emilmont | 1:fdd22bb7aa52 | 89 | float32_t out1, out2, out3, out4; /* Temporary variables to hold output values */ |
emilmont | 1:fdd22bb7aa52 | 90 | |
emilmont | 1:fdd22bb7aa52 | 91 | /*loop Unrolling */ |
emilmont | 1:fdd22bb7aa52 | 92 | blkCnt = numSamples >> 2u; |
emilmont | 1:fdd22bb7aa52 | 93 | |
emilmont | 1:fdd22bb7aa52 | 94 | /* First part of the processing with loop unrolling. Compute 4 outputs at a time. |
emilmont | 1:fdd22bb7aa52 | 95 | ** a second loop below computes the remaining 1 to 3 samples. */ |
emilmont | 1:fdd22bb7aa52 | 96 | while(blkCnt > 0u) |
emilmont | 1:fdd22bb7aa52 | 97 | { |
emilmont | 1:fdd22bb7aa52 | 98 | /* C[0] = (A[0] * A[0] + A[1] * A[1]) */ |
emilmont | 1:fdd22bb7aa52 | 99 | /* read real input sample from source buffer */ |
emilmont | 1:fdd22bb7aa52 | 100 | real1 = pSrc[0]; |
emilmont | 1:fdd22bb7aa52 | 101 | /* read imaginary input sample from source buffer */ |
emilmont | 1:fdd22bb7aa52 | 102 | imag1 = pSrc[1]; |
emilmont | 1:fdd22bb7aa52 | 103 | |
emilmont | 1:fdd22bb7aa52 | 104 | /* calculate power of real value */ |
emilmont | 1:fdd22bb7aa52 | 105 | mul1 = real1 * real1; |
emilmont | 1:fdd22bb7aa52 | 106 | |
emilmont | 1:fdd22bb7aa52 | 107 | /* read real input sample from source buffer */ |
emilmont | 1:fdd22bb7aa52 | 108 | real2 = pSrc[2]; |
emilmont | 1:fdd22bb7aa52 | 109 | |
emilmont | 1:fdd22bb7aa52 | 110 | /* calculate power of imaginary value */ |
emilmont | 1:fdd22bb7aa52 | 111 | mul2 = imag1 * imag1; |
emilmont | 1:fdd22bb7aa52 | 112 | |
emilmont | 1:fdd22bb7aa52 | 113 | /* read imaginary input sample from source buffer */ |
emilmont | 1:fdd22bb7aa52 | 114 | imag2 = pSrc[3]; |
emilmont | 1:fdd22bb7aa52 | 115 | |
emilmont | 1:fdd22bb7aa52 | 116 | /* calculate power of real value */ |
emilmont | 1:fdd22bb7aa52 | 117 | mul3 = real2 * real2; |
emilmont | 1:fdd22bb7aa52 | 118 | |
emilmont | 1:fdd22bb7aa52 | 119 | /* read real input sample from source buffer */ |
emilmont | 1:fdd22bb7aa52 | 120 | real3 = pSrc[4]; |
emilmont | 1:fdd22bb7aa52 | 121 | |
emilmont | 1:fdd22bb7aa52 | 122 | /* calculate power of imaginary value */ |
emilmont | 1:fdd22bb7aa52 | 123 | mul4 = imag2 * imag2; |
emilmont | 1:fdd22bb7aa52 | 124 | |
emilmont | 1:fdd22bb7aa52 | 125 | /* read imaginary input sample from source buffer */ |
emilmont | 1:fdd22bb7aa52 | 126 | imag3 = pSrc[5]; |
emilmont | 1:fdd22bb7aa52 | 127 | |
emilmont | 1:fdd22bb7aa52 | 128 | /* calculate power of real value */ |
emilmont | 1:fdd22bb7aa52 | 129 | mul5 = real3 * real3; |
emilmont | 1:fdd22bb7aa52 | 130 | /* calculate power of imaginary value */ |
emilmont | 1:fdd22bb7aa52 | 131 | mul6 = imag3 * imag3; |
emilmont | 1:fdd22bb7aa52 | 132 | |
emilmont | 1:fdd22bb7aa52 | 133 | /* read real input sample from source buffer */ |
emilmont | 1:fdd22bb7aa52 | 134 | real4 = pSrc[6]; |
emilmont | 1:fdd22bb7aa52 | 135 | |
emilmont | 1:fdd22bb7aa52 | 136 | /* accumulate real and imaginary powers */ |
emilmont | 1:fdd22bb7aa52 | 137 | out1 = mul1 + mul2; |
emilmont | 1:fdd22bb7aa52 | 138 | |
emilmont | 1:fdd22bb7aa52 | 139 | /* read imaginary input sample from source buffer */ |
emilmont | 1:fdd22bb7aa52 | 140 | imag4 = pSrc[7]; |
emilmont | 1:fdd22bb7aa52 | 141 | |
emilmont | 1:fdd22bb7aa52 | 142 | /* accumulate real and imaginary powers */ |
emilmont | 1:fdd22bb7aa52 | 143 | out2 = mul3 + mul4; |
emilmont | 1:fdd22bb7aa52 | 144 | |
emilmont | 1:fdd22bb7aa52 | 145 | /* calculate power of real value */ |
emilmont | 1:fdd22bb7aa52 | 146 | mul7 = real4 * real4; |
emilmont | 1:fdd22bb7aa52 | 147 | /* calculate power of imaginary value */ |
emilmont | 1:fdd22bb7aa52 | 148 | mul8 = imag4 * imag4; |
emilmont | 1:fdd22bb7aa52 | 149 | |
emilmont | 1:fdd22bb7aa52 | 150 | /* store output to destination */ |
emilmont | 1:fdd22bb7aa52 | 151 | pDst[0] = out1; |
emilmont | 1:fdd22bb7aa52 | 152 | |
emilmont | 1:fdd22bb7aa52 | 153 | /* accumulate real and imaginary powers */ |
emilmont | 1:fdd22bb7aa52 | 154 | out3 = mul5 + mul6; |
emilmont | 1:fdd22bb7aa52 | 155 | |
emilmont | 1:fdd22bb7aa52 | 156 | /* store output to destination */ |
emilmont | 1:fdd22bb7aa52 | 157 | pDst[1] = out2; |
emilmont | 1:fdd22bb7aa52 | 158 | |
emilmont | 1:fdd22bb7aa52 | 159 | /* accumulate real and imaginary powers */ |
emilmont | 1:fdd22bb7aa52 | 160 | out4 = mul7 + mul8; |
emilmont | 1:fdd22bb7aa52 | 161 | |
emilmont | 1:fdd22bb7aa52 | 162 | /* store output to destination */ |
emilmont | 1:fdd22bb7aa52 | 163 | pDst[2] = out3; |
emilmont | 1:fdd22bb7aa52 | 164 | |
emilmont | 1:fdd22bb7aa52 | 165 | /* increment destination pointer by 8 to process next samples */ |
emilmont | 1:fdd22bb7aa52 | 166 | pSrc += 8u; |
emilmont | 1:fdd22bb7aa52 | 167 | |
emilmont | 1:fdd22bb7aa52 | 168 | /* store output to destination */ |
emilmont | 1:fdd22bb7aa52 | 169 | pDst[3] = out4; |
emilmont | 1:fdd22bb7aa52 | 170 | |
emilmont | 1:fdd22bb7aa52 | 171 | /* increment destination pointer by 4 to process next samples */ |
emilmont | 1:fdd22bb7aa52 | 172 | pDst += 4u; |
emilmont | 1:fdd22bb7aa52 | 173 | |
emilmont | 1:fdd22bb7aa52 | 174 | /* Decrement the loop counter */ |
emilmont | 1:fdd22bb7aa52 | 175 | blkCnt--; |
emilmont | 1:fdd22bb7aa52 | 176 | } |
emilmont | 1:fdd22bb7aa52 | 177 | |
emilmont | 1:fdd22bb7aa52 | 178 | /* If the numSamples is not a multiple of 4, compute any remaining output samples here. |
emilmont | 1:fdd22bb7aa52 | 179 | ** No loop unrolling is used. */ |
emilmont | 1:fdd22bb7aa52 | 180 | blkCnt = numSamples % 0x4u; |
emilmont | 1:fdd22bb7aa52 | 181 | |
emilmont | 1:fdd22bb7aa52 | 182 | #else |
emilmont | 1:fdd22bb7aa52 | 183 | |
emilmont | 1:fdd22bb7aa52 | 184 | /* Run the below code for Cortex-M0 */ |
emilmont | 1:fdd22bb7aa52 | 185 | |
emilmont | 1:fdd22bb7aa52 | 186 | blkCnt = numSamples; |
emilmont | 1:fdd22bb7aa52 | 187 | |
emilmont | 1:fdd22bb7aa52 | 188 | #endif /* #ifndef ARM_MATH_CM0 */ |
emilmont | 1:fdd22bb7aa52 | 189 | |
emilmont | 1:fdd22bb7aa52 | 190 | while(blkCnt > 0u) |
emilmont | 1:fdd22bb7aa52 | 191 | { |
emilmont | 1:fdd22bb7aa52 | 192 | /* C[0] = (A[0] * A[0] + A[1] * A[1]) */ |
emilmont | 1:fdd22bb7aa52 | 193 | real = *pSrc++; |
emilmont | 1:fdd22bb7aa52 | 194 | imag = *pSrc++; |
emilmont | 1:fdd22bb7aa52 | 195 | |
emilmont | 1:fdd22bb7aa52 | 196 | /* out = (real * real) + (imag * imag) */ |
emilmont | 1:fdd22bb7aa52 | 197 | /* store the result in the destination buffer. */ |
emilmont | 1:fdd22bb7aa52 | 198 | *pDst++ = (real * real) + (imag * imag); |
emilmont | 1:fdd22bb7aa52 | 199 | |
emilmont | 1:fdd22bb7aa52 | 200 | /* Decrement the loop counter */ |
emilmont | 1:fdd22bb7aa52 | 201 | blkCnt--; |
emilmont | 1:fdd22bb7aa52 | 202 | } |
emilmont | 1:fdd22bb7aa52 | 203 | } |
emilmont | 1:fdd22bb7aa52 | 204 | |
emilmont | 1:fdd22bb7aa52 | 205 | /** |
emilmont | 1:fdd22bb7aa52 | 206 | * @} end of cmplx_mag_squared group |
emilmont | 1:fdd22bb7aa52 | 207 | */ |