1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
|
/* ----------------------------------------------------------------------
* Copyright (C) 2010 ARM Limited. All rights reserved.
*
* $Date: 15. February 2012
* $Revision: V1.1.0
*
* Project: CMSIS DSP Library
* Title: arm_rfft_f32.c
*
* Description: RFFT & RIFFT Floating point process function
*
* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
*
* Version 1.1.0 2012/02/15
* Updated with more optimizations, bug fixes and minor API changes.
*
* Version 1.0.10 2011/7/15
* Big Endian support added and Merged M0 and M3/M4 Source code.
*
* Version 1.0.3 2010/11/29
* Re-organized the CMSIS folders and updated documentation.
*
* Version 1.0.2 2010/11/11
* Documentation updated.
*
* Version 1.0.1 2010/10/05
* Production release and review comments incorporated.
*
* Version 1.0.0 2010/09/20
* Production release and review comments incorporated.
*
* Version 0.0.7 2010/06/10
* Misra-C changes done
* -------------------------------------------------------------------- */
#include "arm_math.h"
/**
* @ingroup groupTransforms
*/
/**
* @defgroup RFFT_RIFFT Real FFT Functions
*
* \par
* Complex FFT/IFFT typically assumes complex input and output. However many applications use real valued data in time domain.
* Real FFT/IFFT efficiently process real valued sequences with the advantage of requirement of low memory and with less complexity.
*
* \par
* This set of functions implements Real Fast Fourier Transforms(RFFT) and Real Inverse Fast Fourier Transform(RIFFT)
* for Q15, Q31, and floating-point data types.
*
*
* \par Algorithm:
*
* <b>Real Fast Fourier Transform:</b>
* \par
* Real FFT of N-point is calculated using CFFT of N/2-point and Split RFFT process as shown below figure.
* \par
* \image html RFFT.gif "Real Fast Fourier Transform"
* \par
* The RFFT functions operate on blocks of input and output data and each call to the function processes
* <code>fftLenR</code> samples through the transform. <code>pSrc</code> points to input array containing <code>fftLenR</code> values.
* <code>pDst</code> points to output array containing <code>2*fftLenR</code> values. \n
* Input for real FFT is in the order of
* <pre>{real[0], real[1], real[2], real[3], ..}</pre>
* Output for real FFT is complex and are in the order of
* <pre>{real(0), imag(0), real(1), imag(1), ...}</pre>
*
* <b>Real Inverse Fast Fourier Transform:</b>
* \par
* Real IFFT of N-point is calculated using Split RIFFT process and CFFT of N/2-point as shown below figure.
* \par
* \image html RIFFT.gif "Real Inverse Fast Fourier Transform"
* \par
* The RIFFT functions operate on blocks of input and output data and each call to the function processes
* <code>2*fftLenR</code> samples through the transform. <code>pSrc</code> points to input array containing <code>2*fftLenR</code> values.
* <code>pDst</code> points to output array containing <code>fftLenR</code> values. \n
* Input for real IFFT is complex and are in the order of
* <pre>{real(0), imag(0), real(1), imag(1), ...}</pre>
* Output for real IFFT is real and in the order of
* <pre>{real[0], real[1], real[2], real[3], ..}</pre>
*
* \par Lengths supported by the transform:
* \par
* Real FFT/IFFT supports the lengths [128, 512, 2048], as it internally uses CFFT/CIFFT.
*
* \par Instance Structure
* A separate instance structure must be defined for each Instance but the twiddle factors can be reused.
* There are separate instance structure declarations for each of the 3 supported data types.
*
* \par Initialization Functions
* There is also an associated initialization function for each data type.
* The initialization function performs the following operations:
* - Sets the values of the internal structure fields.
* - Initializes twiddle factor tables.
* - Initializes CFFT data structure fields.
* \par
* Use of the initialization function is optional.
* However, if the initialization function is used, then the instance structure cannot be placed into a const data section.
* To place an instance structure into a const data section, the instance structure must be manually initialized.
* Manually initialize the instance structure as follows:
* <pre>
*arm_rfft_instance_f32 S = {fftLenReal, fftLenBy2, ifftFlagR, bitReverseFlagR, twidCoefRModifier, pTwiddleAReal, pTwiddleBReal, pCfft};
*arm_rfft_instance_q31 S = {fftLenReal, fftLenBy2, ifftFlagR, bitReverseFlagR, twidCoefRModifier, pTwiddleAReal, pTwiddleBReal, pCfft};
*arm_rfft_instance_q15 S = {fftLenReal, fftLenBy2, ifftFlagR, bitReverseFlagR, twidCoefRModifier, pTwiddleAReal, pTwiddleBReal, pCfft};
* </pre>
* where <code>fftLenReal</code> length of RFFT/RIFFT; <code>fftLenBy2</code> length of CFFT/CIFFT.
* <code>ifftFlagR</code> Flag for selection of RFFT or RIFFT(Set ifftFlagR to calculate RIFFT otherwise calculates RFFT);
* <code>bitReverseFlagR</code> Flag for selection of output order(Set bitReverseFlagR to output in normal order otherwise output in bit reversed order);
* <code>twidCoefRModifier</code> modifier for twiddle factor table which supports 128, 512, 2048 RFFT lengths with same table;
* <code>pTwiddleAReal</code>points to A array of twiddle coefficients; <code>pTwiddleBReal</code>points to B array of twiddle coefficients;
* <code>pCfft</code> points to the CFFT Instance structure. The CFFT structure also needs to be initialized, refer to arm_cfft_radix4_f32() for details regarding
* static initialization of cfft structure.
*
* \par Fixed-Point Behavior
* Care must be taken when using the fixed-point versions of the RFFT/RIFFT function.
* Refer to the function specific documentation below for usage guidelines.
*/
/*--------------------------------------------------------------------
* Internal functions prototypes
*--------------------------------------------------------------------*/
void arm_split_rfft_f32(
float32_t * pSrc,
uint32_t fftLen,
float32_t * pATable,
float32_t * pBTable,
float32_t * pDst,
uint32_t modifier);
void arm_split_rifft_f32(
float32_t * pSrc,
uint32_t fftLen,
float32_t * pATable,
float32_t * pBTable,
float32_t * pDst,
uint32_t modifier);
/**
* @addtogroup RFFT_RIFFT
* @{
*/
/**
* @brief Processing function for the floating-point RFFT/RIFFT.
* @param[in] *S points to an instance of the floating-point RFFT/RIFFT structure.
* @param[in] *pSrc points to the input buffer.
* @param[out] *pDst points to the output buffer.
* @return none.
*/
void arm_rfft_f32(
const arm_rfft_instance_f32 * S,
float32_t * pSrc,
float32_t * pDst)
{
const arm_cfft_radix4_instance_f32 *S_CFFT = S->pCfft;
/* Calculation of Real IFFT of input */
if(S->ifftFlagR == 1u)
{
/* Real IFFT core process */
arm_split_rifft_f32(pSrc, S->fftLenBy2, S->pTwiddleAReal,
S->pTwiddleBReal, pDst, S->twidCoefRModifier);
/* Complex radix-4 IFFT process */
arm_radix4_butterfly_inverse_f32(pDst, S_CFFT->fftLen,
S_CFFT->pTwiddle,
S_CFFT->twidCoefModifier,
S_CFFT->onebyfftLen);
/* Bit reversal process */
if(S->bitReverseFlagR == 1u)
{
arm_bitreversal_f32(pDst, S_CFFT->fftLen,
S_CFFT->bitRevFactor, S_CFFT->pBitRevTable);
}
}
else
{
/* Calculation of RFFT of input */
/* Complex radix-4 FFT process */
arm_radix4_butterfly_f32(pSrc, S_CFFT->fftLen,
S_CFFT->pTwiddle, S_CFFT->twidCoefModifier);
/* Bit reversal process */
if(S->bitReverseFlagR == 1u)
{
arm_bitreversal_f32(pSrc, S_CFFT->fftLen,
S_CFFT->bitRevFactor, S_CFFT->pBitRevTable);
}
/* Real FFT core process */
arm_split_rfft_f32(pSrc, S->fftLenBy2, S->pTwiddleAReal,
S->pTwiddleBReal, pDst, S->twidCoefRModifier);
}
}
/**
* @} end of RFFT_RIFFT group
*/
/**
* @brief Core Real FFT process
* @param[in] *pSrc points to the input buffer.
* @param[in] fftLen length of FFT.
* @param[in] *pATable points to the twiddle Coef A buffer.
* @param[in] *pBTable points to the twiddle Coef B buffer.
* @param[out] *pDst points to the output buffer.
* @param[in] modifier twiddle coefficient modifier that supports different size FFTs with the same twiddle factor table.
* @return none.
*/
void arm_split_rfft_f32(
float32_t * pSrc,
uint32_t fftLen,
float32_t * pATable,
float32_t * pBTable,
float32_t * pDst,
uint32_t modifier)
{
uint32_t i; /* Loop Counter */
float32_t outR, outI; /* Temporary variables for output */
float32_t *pCoefA, *pCoefB; /* Temporary pointers for twiddle factors */
float32_t CoefA1, CoefA2, CoefB1; /* Temporary variables for twiddle coefficients */
float32_t *pDst1 = &pDst[2], *pDst2 = &pDst[(4u * fftLen) - 1u]; /* temp pointers for output buffer */
float32_t *pSrc1 = &pSrc[2], *pSrc2 = &pSrc[(2u * fftLen) - 1u]; /* temp pointers for input buffer */
/* Init coefficient pointers */
pCoefA = &pATable[modifier * 2u];
pCoefB = &pBTable[modifier * 2u];
i = fftLen - 1u;
while(i > 0u)
{
/*
outR = (pSrc[2 * i] * pATable[2 * i] - pSrc[2 * i + 1] * pATable[2 * i + 1]
+ pSrc[2 * n - 2 * i] * pBTable[2 * i] +
pSrc[2 * n - 2 * i + 1] * pBTable[2 * i + 1]);
*/
/* outI = (pIn[2 * i + 1] * pATable[2 * i] + pIn[2 * i] * pATable[2 * i + 1] +
pIn[2 * n - 2 * i] * pBTable[2 * i + 1] -
pIn[2 * n - 2 * i + 1] * pBTable[2 * i]); */
/* read pATable[2 * i] */
CoefA1 = *pCoefA++;
/* pATable[2 * i + 1] */
CoefA2 = *pCoefA;
/* pSrc[2 * i] * pATable[2 * i] */
outR = *pSrc1 * CoefA1;
/* pSrc[2 * i] * CoefA2 */
outI = *pSrc1++ * CoefA2;
/* (pSrc[2 * i + 1] + pSrc[2 * fftLen - 2 * i + 1]) * CoefA2 */
outR -= (*pSrc1 + *pSrc2) * CoefA2;
/* pSrc[2 * i + 1] * CoefA1 */
outI += *pSrc1++ * CoefA1;
CoefB1 = *pCoefB;
/* pSrc[2 * fftLen - 2 * i + 1] * CoefB1 */
outI -= *pSrc2-- * CoefB1;
/* pSrc[2 * fftLen - 2 * i] * CoefA2 */
outI -= *pSrc2 * CoefA2;
/* pSrc[2 * fftLen - 2 * i] * CoefB1 */
outR += *pSrc2-- * CoefB1;
/* write output */
*pDst1++ = outR;
*pDst1++ = outI;
/* write complex conjugate output */
*pDst2-- = -outI;
*pDst2-- = outR;
/* update coefficient pointer */
pCoefB = pCoefB + (modifier * 2u);
pCoefA = pCoefA + ((modifier * 2u) - 1u);
i--;
}
pDst[2u * fftLen] = pSrc[0] - pSrc[1];
pDst[(2u * fftLen) + 1u] = 0.0f;
pDst[0] = pSrc[0] + pSrc[1];
pDst[1] = 0.0f;
}
/**
* @brief Core Real IFFT process
* @param[in] *pSrc points to the input buffer.
* @param[in] fftLen length of FFT.
* @param[in] *pATable points to the twiddle Coef A buffer.
* @param[in] *pBTable points to the twiddle Coef B buffer.
* @param[out] *pDst points to the output buffer.
* @param[in] modifier twiddle coefficient modifier that supports different size FFTs with the same twiddle factor table.
* @return none.
*/
void arm_split_rifft_f32(
float32_t * pSrc,
uint32_t fftLen,
float32_t * pATable,
float32_t * pBTable,
float32_t * pDst,
uint32_t modifier)
{
float32_t outR, outI; /* Temporary variables for output */
float32_t *pCoefA, *pCoefB; /* Temporary pointers for twiddle factors */
float32_t CoefA1, CoefA2, CoefB1; /* Temporary variables for twiddle coefficients */
float32_t *pSrc1 = &pSrc[0], *pSrc2 = &pSrc[(2u * fftLen) + 1u];
pCoefA = &pATable[0];
pCoefB = &pBTable[0];
while(fftLen > 0u)
{
/*
outR = (pIn[2 * i] * pATable[2 * i] + pIn[2 * i + 1] * pATable[2 * i + 1] +
pIn[2 * n - 2 * i] * pBTable[2 * i] -
pIn[2 * n - 2 * i + 1] * pBTable[2 * i + 1]);
outI = (pIn[2 * i + 1] * pATable[2 * i] - pIn[2 * i] * pATable[2 * i + 1] -
pIn[2 * n - 2 * i] * pBTable[2 * i + 1] -
pIn[2 * n - 2 * i + 1] * pBTable[2 * i]);
*/
CoefA1 = *pCoefA++;
CoefA2 = *pCoefA;
/* outR = (pSrc[2 * i] * CoefA1 */
outR = *pSrc1 * CoefA1;
/* - pSrc[2 * i] * CoefA2 */
outI = -(*pSrc1++) * CoefA2;
/* (pSrc[2 * i + 1] + pSrc[2 * fftLen - 2 * i + 1]) * CoefA2 */
outR += (*pSrc1 + *pSrc2) * CoefA2;
/* pSrc[2 * i + 1] * CoefA1 */
outI += (*pSrc1++) * CoefA1;
CoefB1 = *pCoefB;
/* - pSrc[2 * fftLen - 2 * i + 1] * CoefB1 */
outI -= *pSrc2-- * CoefB1;
/* pSrc[2 * fftLen - 2 * i] * CoefB1 */
outR += *pSrc2 * CoefB1;
/* pSrc[2 * fftLen - 2 * i] * CoefA2 */
outI += *pSrc2-- * CoefA2;
/* write output */
*pDst++ = outR;
*pDst++ = outI;
/* update coefficient pointer */
pCoefB = pCoefB + (modifier * 2u);
pCoefA = pCoefA + ((modifier * 2u) - 1u);
/* Decrement loop count */
fftLen--;
}
}
|
