提交 | 用户 | age
|
483170
|
1 |
/* ---------------------------------------------------------------------- |
Q |
2 |
* Copyright (C) 2010-2014 ARM Limited. All rights reserved. |
|
3 |
* |
|
4 |
* $Date: 19. March 2015 |
|
5 |
* $Revision: V.1.4.5 |
|
6 |
* |
|
7 |
* Project: CMSIS DSP Library |
|
8 |
* Title: arm_cfft_radix4_f32.c |
|
9 |
* |
|
10 |
* Description: Radix-4 Decimation in Frequency CFFT & CIFFT Floating point processing function |
|
11 |
* |
|
12 |
* |
|
13 |
* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0 |
|
14 |
* |
|
15 |
* Redistribution and use in source and binary forms, with or without |
|
16 |
* modification, are permitted provided that the following conditions |
|
17 |
* are met: |
|
18 |
* - Redistributions of source code must retain the above copyright |
|
19 |
* notice, this list of conditions and the following disclaimer. |
|
20 |
* - Redistributions in binary form must reproduce the above copyright |
|
21 |
* notice, this list of conditions and the following disclaimer in |
|
22 |
* the documentation and/or other materials provided with the |
|
23 |
* distribution. |
|
24 |
* - Neither the name of ARM LIMITED nor the names of its contributors |
|
25 |
* may be used to endorse or promote products derived from this |
|
26 |
* software without specific prior written permission. |
|
27 |
* |
|
28 |
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS |
|
29 |
* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT |
|
30 |
* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS |
|
31 |
* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE |
|
32 |
* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, |
|
33 |
* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, |
|
34 |
* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; |
|
35 |
* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER |
|
36 |
* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT |
|
37 |
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN |
|
38 |
* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE |
|
39 |
* POSSIBILITY OF SUCH DAMAGE. |
|
40 |
* -------------------------------------------------------------------- */ |
|
41 |
|
|
42 |
#include "arm_math.h" |
|
43 |
|
|
44 |
extern void arm_bitreversal_f32( |
|
45 |
float32_t * pSrc, |
|
46 |
uint16_t fftSize, |
|
47 |
uint16_t bitRevFactor, |
|
48 |
uint16_t * pBitRevTab); |
|
49 |
|
|
50 |
/** |
|
51 |
* @ingroup groupTransforms |
|
52 |
*/ |
|
53 |
|
|
54 |
/* ---------------------------------------------------------------------- |
|
55 |
** Internal helper function used by the FFTs |
|
56 |
** ------------------------------------------------------------------- */ |
|
57 |
|
|
58 |
/* |
|
59 |
* @brief Core function for the floating-point CFFT butterfly process. |
|
60 |
* @param[in, out] *pSrc points to the in-place buffer of floating-point data type. |
|
61 |
* @param[in] fftLen length of the FFT. |
|
62 |
* @param[in] *pCoef points to the twiddle coefficient buffer. |
|
63 |
* @param[in] twidCoefModifier twiddle coefficient modifier that supports different size FFTs with the same twiddle factor table. |
|
64 |
* @return none. |
|
65 |
*/ |
|
66 |
|
|
67 |
void arm_radix4_butterfly_f32( |
|
68 |
float32_t * pSrc, |
|
69 |
uint16_t fftLen, |
|
70 |
float32_t * pCoef, |
|
71 |
uint16_t twidCoefModifier) |
|
72 |
{ |
|
73 |
|
|
74 |
float32_t co1, co2, co3, si1, si2, si3; |
|
75 |
uint32_t ia1, ia2, ia3; |
|
76 |
uint32_t i0, i1, i2, i3; |
|
77 |
uint32_t n1, n2, j, k; |
|
78 |
|
|
79 |
#ifndef ARM_MATH_CM0_FAMILY_FAMILY |
|
80 |
|
|
81 |
/* Run the below code for Cortex-M4 and Cortex-M3 */ |
|
82 |
|
|
83 |
float32_t xaIn, yaIn, xbIn, ybIn, xcIn, ycIn, xdIn, ydIn; |
|
84 |
float32_t Xaplusc, Xbplusd, Yaplusc, Ybplusd, Xaminusc, Xbminusd, Yaminusc, |
|
85 |
Ybminusd; |
|
86 |
float32_t Xb12C_out, Yb12C_out, Xc12C_out, Yc12C_out, Xd12C_out, Yd12C_out; |
|
87 |
float32_t Xb12_out, Yb12_out, Xc12_out, Yc12_out, Xd12_out, Yd12_out; |
|
88 |
float32_t *ptr1; |
|
89 |
float32_t p0,p1,p2,p3,p4,p5; |
|
90 |
float32_t a0,a1,a2,a3,a4,a5,a6,a7; |
|
91 |
|
|
92 |
/* Initializations for the first stage */ |
|
93 |
n2 = fftLen; |
|
94 |
n1 = n2; |
|
95 |
|
|
96 |
/* n2 = fftLen/4 */ |
|
97 |
n2 >>= 2u; |
|
98 |
i0 = 0u; |
|
99 |
ia1 = 0u; |
|
100 |
|
|
101 |
j = n2; |
|
102 |
|
|
103 |
/* Calculation of first stage */ |
|
104 |
do |
|
105 |
{ |
|
106 |
/* index calculation for the input as, */ |
|
107 |
/* pSrc[i0 + 0], pSrc[i0 + fftLen/4], pSrc[i0 + fftLen/2], pSrc[i0 + 3fftLen/4] */ |
|
108 |
i1 = i0 + n2; |
|
109 |
i2 = i1 + n2; |
|
110 |
i3 = i2 + n2; |
|
111 |
|
|
112 |
xaIn = pSrc[(2u * i0)]; |
|
113 |
yaIn = pSrc[(2u * i0) + 1u]; |
|
114 |
|
|
115 |
xbIn = pSrc[(2u * i1)]; |
|
116 |
ybIn = pSrc[(2u * i1) + 1u]; |
|
117 |
|
|
118 |
xcIn = pSrc[(2u * i2)]; |
|
119 |
ycIn = pSrc[(2u * i2) + 1u]; |
|
120 |
|
|
121 |
xdIn = pSrc[(2u * i3)]; |
|
122 |
ydIn = pSrc[(2u * i3) + 1u]; |
|
123 |
|
|
124 |
/* xa + xc */ |
|
125 |
Xaplusc = xaIn + xcIn; |
|
126 |
/* xb + xd */ |
|
127 |
Xbplusd = xbIn + xdIn; |
|
128 |
/* ya + yc */ |
|
129 |
Yaplusc = yaIn + ycIn; |
|
130 |
/* yb + yd */ |
|
131 |
Ybplusd = ybIn + ydIn; |
|
132 |
|
|
133 |
/* index calculation for the coefficients */ |
|
134 |
ia2 = ia1 + ia1; |
|
135 |
co2 = pCoef[ia2 * 2u]; |
|
136 |
si2 = pCoef[(ia2 * 2u) + 1u]; |
|
137 |
|
|
138 |
/* xa - xc */ |
|
139 |
Xaminusc = xaIn - xcIn; |
|
140 |
/* xb - xd */ |
|
141 |
Xbminusd = xbIn - xdIn; |
|
142 |
/* ya - yc */ |
|
143 |
Yaminusc = yaIn - ycIn; |
|
144 |
/* yb - yd */ |
|
145 |
Ybminusd = ybIn - ydIn; |
|
146 |
|
|
147 |
/* xa' = xa + xb + xc + xd */ |
|
148 |
pSrc[(2u * i0)] = Xaplusc + Xbplusd; |
|
149 |
/* ya' = ya + yb + yc + yd */ |
|
150 |
pSrc[(2u * i0) + 1u] = Yaplusc + Ybplusd; |
|
151 |
|
|
152 |
/* (xa - xc) + (yb - yd) */ |
|
153 |
Xb12C_out = (Xaminusc + Ybminusd); |
|
154 |
/* (ya - yc) + (xb - xd) */ |
|
155 |
Yb12C_out = (Yaminusc - Xbminusd); |
|
156 |
/* (xa + xc) - (xb + xd) */ |
|
157 |
Xc12C_out = (Xaplusc - Xbplusd); |
|
158 |
/* (ya + yc) - (yb + yd) */ |
|
159 |
Yc12C_out = (Yaplusc - Ybplusd); |
|
160 |
/* (xa - xc) - (yb - yd) */ |
|
161 |
Xd12C_out = (Xaminusc - Ybminusd); |
|
162 |
/* (ya - yc) + (xb - xd) */ |
|
163 |
Yd12C_out = (Xbminusd + Yaminusc); |
|
164 |
|
|
165 |
co1 = pCoef[ia1 * 2u]; |
|
166 |
si1 = pCoef[(ia1 * 2u) + 1u]; |
|
167 |
|
|
168 |
/* index calculation for the coefficients */ |
|
169 |
ia3 = ia2 + ia1; |
|
170 |
co3 = pCoef[ia3 * 2u]; |
|
171 |
si3 = pCoef[(ia3 * 2u) + 1u]; |
|
172 |
|
|
173 |
Xb12_out = Xb12C_out * co1; |
|
174 |
Yb12_out = Yb12C_out * co1; |
|
175 |
Xc12_out = Xc12C_out * co2; |
|
176 |
Yc12_out = Yc12C_out * co2; |
|
177 |
Xd12_out = Xd12C_out * co3; |
|
178 |
Yd12_out = Yd12C_out * co3; |
|
179 |
|
|
180 |
/* xb' = (xa+yb-xc-yd)co1 - (ya-xb-yc+xd)(si1) */ |
|
181 |
//Xb12_out -= Yb12C_out * si1; |
|
182 |
p0 = Yb12C_out * si1; |
|
183 |
/* yb' = (ya-xb-yc+xd)co1 + (xa+yb-xc-yd)(si1) */ |
|
184 |
//Yb12_out += Xb12C_out * si1; |
|
185 |
p1 = Xb12C_out * si1; |
|
186 |
/* xc' = (xa-xb+xc-xd)co2 - (ya-yb+yc-yd)(si2) */ |
|
187 |
//Xc12_out -= Yc12C_out * si2; |
|
188 |
p2 = Yc12C_out * si2; |
|
189 |
/* yc' = (ya-yb+yc-yd)co2 + (xa-xb+xc-xd)(si2) */ |
|
190 |
//Yc12_out += Xc12C_out * si2; |
|
191 |
p3 = Xc12C_out * si2; |
|
192 |
/* xd' = (xa-yb-xc+yd)co3 - (ya+xb-yc-xd)(si3) */ |
|
193 |
//Xd12_out -= Yd12C_out * si3; |
|
194 |
p4 = Yd12C_out * si3; |
|
195 |
/* yd' = (ya+xb-yc-xd)co3 + (xa-yb-xc+yd)(si3) */ |
|
196 |
//Yd12_out += Xd12C_out * si3; |
|
197 |
p5 = Xd12C_out * si3; |
|
198 |
|
|
199 |
Xb12_out += p0; |
|
200 |
Yb12_out -= p1; |
|
201 |
Xc12_out += p2; |
|
202 |
Yc12_out -= p3; |
|
203 |
Xd12_out += p4; |
|
204 |
Yd12_out -= p5; |
|
205 |
|
|
206 |
/* xc' = (xa-xb+xc-xd)co2 + (ya-yb+yc-yd)(si2) */ |
|
207 |
pSrc[2u * i1] = Xc12_out; |
|
208 |
|
|
209 |
/* yc' = (ya-yb+yc-yd)co2 - (xa-xb+xc-xd)(si2) */ |
|
210 |
pSrc[(2u * i1) + 1u] = Yc12_out; |
|
211 |
|
|
212 |
/* xb' = (xa+yb-xc-yd)co1 + (ya-xb-yc+xd)(si1) */ |
|
213 |
pSrc[2u * i2] = Xb12_out; |
|
214 |
|
|
215 |
/* yb' = (ya-xb-yc+xd)co1 - (xa+yb-xc-yd)(si1) */ |
|
216 |
pSrc[(2u * i2) + 1u] = Yb12_out; |
|
217 |
|
|
218 |
/* xd' = (xa-yb-xc+yd)co3 + (ya+xb-yc-xd)(si3) */ |
|
219 |
pSrc[2u * i3] = Xd12_out; |
|
220 |
|
|
221 |
/* yd' = (ya+xb-yc-xd)co3 - (xa-yb-xc+yd)(si3) */ |
|
222 |
pSrc[(2u * i3) + 1u] = Yd12_out; |
|
223 |
|
|
224 |
/* Twiddle coefficients index modifier */ |
|
225 |
ia1 += twidCoefModifier; |
|
226 |
|
|
227 |
/* Updating input index */ |
|
228 |
i0++; |
|
229 |
|
|
230 |
} |
|
231 |
while(--j); |
|
232 |
|
|
233 |
twidCoefModifier <<= 2u; |
|
234 |
|
|
235 |
/* Calculation of second stage to excluding last stage */ |
|
236 |
for (k = fftLen >> 2u; k > 4u; k >>= 2u) |
|
237 |
{ |
|
238 |
/* Initializations for the first stage */ |
|
239 |
n1 = n2; |
|
240 |
n2 >>= 2u; |
|
241 |
ia1 = 0u; |
|
242 |
|
|
243 |
/* Calculation of first stage */ |
|
244 |
j = 0; |
|
245 |
do |
|
246 |
{ |
|
247 |
/* index calculation for the coefficients */ |
|
248 |
ia2 = ia1 + ia1; |
|
249 |
ia3 = ia2 + ia1; |
|
250 |
co1 = pCoef[ia1 * 2u]; |
|
251 |
si1 = pCoef[(ia1 * 2u) + 1u]; |
|
252 |
co2 = pCoef[ia2 * 2u]; |
|
253 |
si2 = pCoef[(ia2 * 2u) + 1u]; |
|
254 |
co3 = pCoef[ia3 * 2u]; |
|
255 |
si3 = pCoef[(ia3 * 2u) + 1u]; |
|
256 |
|
|
257 |
/* Twiddle coefficients index modifier */ |
|
258 |
ia1 += twidCoefModifier; |
|
259 |
|
|
260 |
i0 = j; |
|
261 |
do |
|
262 |
{ |
|
263 |
/* index calculation for the input as, */ |
|
264 |
/* pSrc[i0 + 0], pSrc[i0 + fftLen/4], pSrc[i0 + fftLen/2], pSrc[i0 + 3fftLen/4] */ |
|
265 |
i1 = i0 + n2; |
|
266 |
i2 = i1 + n2; |
|
267 |
i3 = i2 + n2; |
|
268 |
|
|
269 |
xaIn = pSrc[(2u * i0)]; |
|
270 |
yaIn = pSrc[(2u * i0) + 1u]; |
|
271 |
|
|
272 |
xbIn = pSrc[(2u * i1)]; |
|
273 |
ybIn = pSrc[(2u * i1) + 1u]; |
|
274 |
|
|
275 |
xcIn = pSrc[(2u * i2)]; |
|
276 |
ycIn = pSrc[(2u * i2) + 1u]; |
|
277 |
|
|
278 |
xdIn = pSrc[(2u * i3)]; |
|
279 |
ydIn = pSrc[(2u * i3) + 1u]; |
|
280 |
|
|
281 |
/* xa - xc */ |
|
282 |
Xaminusc = xaIn - xcIn; |
|
283 |
/* (xb - xd) */ |
|
284 |
Xbminusd = xbIn - xdIn; |
|
285 |
/* ya - yc */ |
|
286 |
Yaminusc = yaIn - ycIn; |
|
287 |
/* (yb - yd) */ |
|
288 |
Ybminusd = ybIn - ydIn; |
|
289 |
|
|
290 |
/* xa + xc */ |
|
291 |
Xaplusc = xaIn + xcIn; |
|
292 |
/* xb + xd */ |
|
293 |
Xbplusd = xbIn + xdIn; |
|
294 |
/* ya + yc */ |
|
295 |
Yaplusc = yaIn + ycIn; |
|
296 |
/* yb + yd */ |
|
297 |
Ybplusd = ybIn + ydIn; |
|
298 |
|
|
299 |
/* (xa - xc) + (yb - yd) */ |
|
300 |
Xb12C_out = (Xaminusc + Ybminusd); |
|
301 |
/* (ya - yc) - (xb - xd) */ |
|
302 |
Yb12C_out = (Yaminusc - Xbminusd); |
|
303 |
/* xa + xc -(xb + xd) */ |
|
304 |
Xc12C_out = (Xaplusc - Xbplusd); |
|
305 |
/* (ya + yc) - (yb + yd) */ |
|
306 |
Yc12C_out = (Yaplusc - Ybplusd); |
|
307 |
/* (xa - xc) - (yb - yd) */ |
|
308 |
Xd12C_out = (Xaminusc - Ybminusd); |
|
309 |
/* (ya - yc) + (xb - xd) */ |
|
310 |
Yd12C_out = (Xbminusd + Yaminusc); |
|
311 |
|
|
312 |
pSrc[(2u * i0)] = Xaplusc + Xbplusd; |
|
313 |
pSrc[(2u * i0) + 1u] = Yaplusc + Ybplusd; |
|
314 |
|
|
315 |
Xb12_out = Xb12C_out * co1; |
|
316 |
Yb12_out = Yb12C_out * co1; |
|
317 |
Xc12_out = Xc12C_out * co2; |
|
318 |
Yc12_out = Yc12C_out * co2; |
|
319 |
Xd12_out = Xd12C_out * co3; |
|
320 |
Yd12_out = Yd12C_out * co3; |
|
321 |
|
|
322 |
/* xb' = (xa+yb-xc-yd)co1 - (ya-xb-yc+xd)(si1) */ |
|
323 |
//Xb12_out -= Yb12C_out * si1; |
|
324 |
p0 = Yb12C_out * si1; |
|
325 |
/* yb' = (ya-xb-yc+xd)co1 + (xa+yb-xc-yd)(si1) */ |
|
326 |
//Yb12_out += Xb12C_out * si1; |
|
327 |
p1 = Xb12C_out * si1; |
|
328 |
/* xc' = (xa-xb+xc-xd)co2 - (ya-yb+yc-yd)(si2) */ |
|
329 |
//Xc12_out -= Yc12C_out * si2; |
|
330 |
p2 = Yc12C_out * si2; |
|
331 |
/* yc' = (ya-yb+yc-yd)co2 + (xa-xb+xc-xd)(si2) */ |
|
332 |
//Yc12_out += Xc12C_out * si2; |
|
333 |
p3 = Xc12C_out * si2; |
|
334 |
/* xd' = (xa-yb-xc+yd)co3 - (ya+xb-yc-xd)(si3) */ |
|
335 |
//Xd12_out -= Yd12C_out * si3; |
|
336 |
p4 = Yd12C_out * si3; |
|
337 |
/* yd' = (ya+xb-yc-xd)co3 + (xa-yb-xc+yd)(si3) */ |
|
338 |
//Yd12_out += Xd12C_out * si3; |
|
339 |
p5 = Xd12C_out * si3; |
|
340 |
|
|
341 |
Xb12_out += p0; |
|
342 |
Yb12_out -= p1; |
|
343 |
Xc12_out += p2; |
|
344 |
Yc12_out -= p3; |
|
345 |
Xd12_out += p4; |
|
346 |
Yd12_out -= p5; |
|
347 |
|
|
348 |
/* xc' = (xa-xb+xc-xd)co2 + (ya-yb+yc-yd)(si2) */ |
|
349 |
pSrc[2u * i1] = Xc12_out; |
|
350 |
|
|
351 |
/* yc' = (ya-yb+yc-yd)co2 - (xa-xb+xc-xd)(si2) */ |
|
352 |
pSrc[(2u * i1) + 1u] = Yc12_out; |
|
353 |
|
|
354 |
/* xb' = (xa+yb-xc-yd)co1 + (ya-xb-yc+xd)(si1) */ |
|
355 |
pSrc[2u * i2] = Xb12_out; |
|
356 |
|
|
357 |
/* yb' = (ya-xb-yc+xd)co1 - (xa+yb-xc-yd)(si1) */ |
|
358 |
pSrc[(2u * i2) + 1u] = Yb12_out; |
|
359 |
|
|
360 |
/* xd' = (xa-yb-xc+yd)co3 + (ya+xb-yc-xd)(si3) */ |
|
361 |
pSrc[2u * i3] = Xd12_out; |
|
362 |
|
|
363 |
/* yd' = (ya+xb-yc-xd)co3 - (xa-yb-xc+yd)(si3) */ |
|
364 |
pSrc[(2u * i3) + 1u] = Yd12_out; |
|
365 |
|
|
366 |
i0 += n1; |
|
367 |
} while(i0 < fftLen); |
|
368 |
j++; |
|
369 |
} while(j <= (n2 - 1u)); |
|
370 |
twidCoefModifier <<= 2u; |
|
371 |
} |
|
372 |
|
|
373 |
j = fftLen >> 2; |
|
374 |
ptr1 = &pSrc[0]; |
|
375 |
|
|
376 |
/* Calculations of last stage */ |
|
377 |
do |
|
378 |
{ |
|
379 |
xaIn = ptr1[0]; |
|
380 |
yaIn = ptr1[1]; |
|
381 |
xbIn = ptr1[2]; |
|
382 |
ybIn = ptr1[3]; |
|
383 |
xcIn = ptr1[4]; |
|
384 |
ycIn = ptr1[5]; |
|
385 |
xdIn = ptr1[6]; |
|
386 |
ydIn = ptr1[7]; |
|
387 |
|
|
388 |
/* xa + xc */ |
|
389 |
Xaplusc = xaIn + xcIn; |
|
390 |
|
|
391 |
/* xa - xc */ |
|
392 |
Xaminusc = xaIn - xcIn; |
|
393 |
|
|
394 |
/* ya + yc */ |
|
395 |
Yaplusc = yaIn + ycIn; |
|
396 |
|
|
397 |
/* ya - yc */ |
|
398 |
Yaminusc = yaIn - ycIn; |
|
399 |
|
|
400 |
/* xb + xd */ |
|
401 |
Xbplusd = xbIn + xdIn; |
|
402 |
|
|
403 |
/* yb + yd */ |
|
404 |
Ybplusd = ybIn + ydIn; |
|
405 |
|
|
406 |
/* (xb-xd) */ |
|
407 |
Xbminusd = xbIn - xdIn; |
|
408 |
|
|
409 |
/* (yb-yd) */ |
|
410 |
Ybminusd = ybIn - ydIn; |
|
411 |
|
|
412 |
/* xa' = xa + xb + xc + xd */ |
|
413 |
a0 = (Xaplusc + Xbplusd); |
|
414 |
/* ya' = ya + yb + yc + yd */ |
|
415 |
a1 = (Yaplusc + Ybplusd); |
|
416 |
/* xc' = (xa-xb+xc-xd) */ |
|
417 |
a2 = (Xaplusc - Xbplusd); |
|
418 |
/* yc' = (ya-yb+yc-yd) */ |
|
419 |
a3 = (Yaplusc - Ybplusd); |
|
420 |
/* xb' = (xa+yb-xc-yd) */ |
|
421 |
a4 = (Xaminusc + Ybminusd); |
|
422 |
/* yb' = (ya-xb-yc+xd) */ |
|
423 |
a5 = (Yaminusc - Xbminusd); |
|
424 |
/* xd' = (xa-yb-xc+yd)) */ |
|
425 |
a6 = (Xaminusc - Ybminusd); |
|
426 |
/* yd' = (ya+xb-yc-xd) */ |
|
427 |
a7 = (Xbminusd + Yaminusc); |
|
428 |
|
|
429 |
ptr1[0] = a0; |
|
430 |
ptr1[1] = a1; |
|
431 |
ptr1[2] = a2; |
|
432 |
ptr1[3] = a3; |
|
433 |
ptr1[4] = a4; |
|
434 |
ptr1[5] = a5; |
|
435 |
ptr1[6] = a6; |
|
436 |
ptr1[7] = a7; |
|
437 |
|
|
438 |
/* increment pointer by 8 */ |
|
439 |
ptr1 += 8u; |
|
440 |
} while(--j); |
|
441 |
|
|
442 |
#else |
|
443 |
|
|
444 |
float32_t t1, t2, r1, r2, s1, s2; |
|
445 |
|
|
446 |
/* Run the below code for Cortex-M0 */ |
|
447 |
|
|
448 |
/* Initializations for the fft calculation */ |
|
449 |
n2 = fftLen; |
|
450 |
n1 = n2; |
|
451 |
for (k = fftLen; k > 1u; k >>= 2u) |
|
452 |
{ |
|
453 |
/* Initializations for the fft calculation */ |
|
454 |
n1 = n2; |
|
455 |
n2 >>= 2u; |
|
456 |
ia1 = 0u; |
|
457 |
|
|
458 |
/* FFT Calculation */ |
|
459 |
j = 0; |
|
460 |
do |
|
461 |
{ |
|
462 |
/* index calculation for the coefficients */ |
|
463 |
ia2 = ia1 + ia1; |
|
464 |
ia3 = ia2 + ia1; |
|
465 |
co1 = pCoef[ia1 * 2u]; |
|
466 |
si1 = pCoef[(ia1 * 2u) + 1u]; |
|
467 |
co2 = pCoef[ia2 * 2u]; |
|
468 |
si2 = pCoef[(ia2 * 2u) + 1u]; |
|
469 |
co3 = pCoef[ia3 * 2u]; |
|
470 |
si3 = pCoef[(ia3 * 2u) + 1u]; |
|
471 |
|
|
472 |
/* Twiddle coefficients index modifier */ |
|
473 |
ia1 = ia1 + twidCoefModifier; |
|
474 |
|
|
475 |
i0 = j; |
|
476 |
do |
|
477 |
{ |
|
478 |
/* index calculation for the input as, */ |
|
479 |
/* pSrc[i0 + 0], pSrc[i0 + fftLen/4], pSrc[i0 + fftLen/2], pSrc[i0 + 3fftLen/4] */ |
|
480 |
i1 = i0 + n2; |
|
481 |
i2 = i1 + n2; |
|
482 |
i3 = i2 + n2; |
|
483 |
|
|
484 |
/* xa + xc */ |
|
485 |
r1 = pSrc[(2u * i0)] + pSrc[(2u * i2)]; |
|
486 |
|
|
487 |
/* xa - xc */ |
|
488 |
r2 = pSrc[(2u * i0)] - pSrc[(2u * i2)]; |
|
489 |
|
|
490 |
/* ya + yc */ |
|
491 |
s1 = pSrc[(2u * i0) + 1u] + pSrc[(2u * i2) + 1u]; |
|
492 |
|
|
493 |
/* ya - yc */ |
|
494 |
s2 = pSrc[(2u * i0) + 1u] - pSrc[(2u * i2) + 1u]; |
|
495 |
|
|
496 |
/* xb + xd */ |
|
497 |
t1 = pSrc[2u * i1] + pSrc[2u * i3]; |
|
498 |
|
|
499 |
/* xa' = xa + xb + xc + xd */ |
|
500 |
pSrc[2u * i0] = r1 + t1; |
|
501 |
|
|
502 |
/* xa + xc -(xb + xd) */ |
|
503 |
r1 = r1 - t1; |
|
504 |
|
|
505 |
/* yb + yd */ |
|
506 |
t2 = pSrc[(2u * i1) + 1u] + pSrc[(2u * i3) + 1u]; |
|
507 |
|
|
508 |
/* ya' = ya + yb + yc + yd */ |
|
509 |
pSrc[(2u * i0) + 1u] = s1 + t2; |
|
510 |
|
|
511 |
/* (ya + yc) - (yb + yd) */ |
|
512 |
s1 = s1 - t2; |
|
513 |
|
|
514 |
/* (yb - yd) */ |
|
515 |
t1 = pSrc[(2u * i1) + 1u] - pSrc[(2u * i3) + 1u]; |
|
516 |
|
|
517 |
/* (xb - xd) */ |
|
518 |
t2 = pSrc[2u * i1] - pSrc[2u * i3]; |
|
519 |
|
|
520 |
/* xc' = (xa-xb+xc-xd)co2 + (ya-yb+yc-yd)(si2) */ |
|
521 |
pSrc[2u * i1] = (r1 * co2) + (s1 * si2); |
|
522 |
|
|
523 |
/* yc' = (ya-yb+yc-yd)co2 - (xa-xb+xc-xd)(si2) */ |
|
524 |
pSrc[(2u * i1) + 1u] = (s1 * co2) - (r1 * si2); |
|
525 |
|
|
526 |
/* (xa - xc) + (yb - yd) */ |
|
527 |
r1 = r2 + t1; |
|
528 |
|
|
529 |
/* (xa - xc) - (yb - yd) */ |
|
530 |
r2 = r2 - t1; |
|
531 |
|
|
532 |
/* (ya - yc) - (xb - xd) */ |
|
533 |
s1 = s2 - t2; |
|
534 |
|
|
535 |
/* (ya - yc) + (xb - xd) */ |
|
536 |
s2 = s2 + t2; |
|
537 |
|
|
538 |
/* xb' = (xa+yb-xc-yd)co1 + (ya-xb-yc+xd)(si1) */ |
|
539 |
pSrc[2u * i2] = (r1 * co1) + (s1 * si1); |
|
540 |
|
|
541 |
/* yb' = (ya-xb-yc+xd)co1 - (xa+yb-xc-yd)(si1) */ |
|
542 |
pSrc[(2u * i2) + 1u] = (s1 * co1) - (r1 * si1); |
|
543 |
|
|
544 |
/* xd' = (xa-yb-xc+yd)co3 + (ya+xb-yc-xd)(si3) */ |
|
545 |
pSrc[2u * i3] = (r2 * co3) + (s2 * si3); |
|
546 |
|
|
547 |
/* yd' = (ya+xb-yc-xd)co3 - (xa-yb-xc+yd)(si3) */ |
|
548 |
pSrc[(2u * i3) + 1u] = (s2 * co3) - (r2 * si3); |
|
549 |
|
|
550 |
i0 += n1; |
|
551 |
} while( i0 < fftLen); |
|
552 |
j++; |
|
553 |
} while(j <= (n2 - 1u)); |
|
554 |
twidCoefModifier <<= 2u; |
|
555 |
} |
|
556 |
|
|
557 |
#endif /* #ifndef ARM_MATH_CM0_FAMILY_FAMILY */ |
|
558 |
|
|
559 |
} |
|
560 |
|
|
561 |
/* |
|
562 |
* @brief Core function for the floating-point CIFFT butterfly process. |
|
563 |
* @param[in, out] *pSrc points to the in-place buffer of floating-point data type. |
|
564 |
* @param[in] fftLen length of the FFT. |
|
565 |
* @param[in] *pCoef points to twiddle coefficient buffer. |
|
566 |
* @param[in] twidCoefModifier twiddle coefficient modifier that supports different size FFTs with the same twiddle factor table. |
|
567 |
* @param[in] onebyfftLen value of 1/fftLen. |
|
568 |
* @return none. |
|
569 |
*/ |
|
570 |
|
|
571 |
void arm_radix4_butterfly_inverse_f32( |
|
572 |
float32_t * pSrc, |
|
573 |
uint16_t fftLen, |
|
574 |
float32_t * pCoef, |
|
575 |
uint16_t twidCoefModifier, |
|
576 |
float32_t onebyfftLen) |
|
577 |
{ |
|
578 |
float32_t co1, co2, co3, si1, si2, si3; |
|
579 |
uint32_t ia1, ia2, ia3; |
|
580 |
uint32_t i0, i1, i2, i3; |
|
581 |
uint32_t n1, n2, j, k; |
|
582 |
|
|
583 |
#ifndef ARM_MATH_CM0_FAMILY_FAMILY |
|
584 |
|
|
585 |
float32_t xaIn, yaIn, xbIn, ybIn, xcIn, ycIn, xdIn, ydIn; |
|
586 |
float32_t Xaplusc, Xbplusd, Yaplusc, Ybplusd, Xaminusc, Xbminusd, Yaminusc, |
|
587 |
Ybminusd; |
|
588 |
float32_t Xb12C_out, Yb12C_out, Xc12C_out, Yc12C_out, Xd12C_out, Yd12C_out; |
|
589 |
float32_t Xb12_out, Yb12_out, Xc12_out, Yc12_out, Xd12_out, Yd12_out; |
|
590 |
float32_t *ptr1; |
|
591 |
float32_t p0,p1,p2,p3,p4,p5,p6,p7; |
|
592 |
float32_t a0,a1,a2,a3,a4,a5,a6,a7; |
|
593 |
|
|
594 |
|
|
595 |
/* Initializations for the first stage */ |
|
596 |
n2 = fftLen; |
|
597 |
n1 = n2; |
|
598 |
|
|
599 |
/* n2 = fftLen/4 */ |
|
600 |
n2 >>= 2u; |
|
601 |
i0 = 0u; |
|
602 |
ia1 = 0u; |
|
603 |
|
|
604 |
j = n2; |
|
605 |
|
|
606 |
/* Calculation of first stage */ |
|
607 |
do |
|
608 |
{ |
|
609 |
/* index calculation for the input as, */ |
|
610 |
/* pSrc[i0 + 0], pSrc[i0 + fftLen/4], pSrc[i0 + fftLen/2], pSrc[i0 + 3fftLen/4] */ |
|
611 |
i1 = i0 + n2; |
|
612 |
i2 = i1 + n2; |
|
613 |
i3 = i2 + n2; |
|
614 |
|
|
615 |
/* Butterfly implementation */ |
|
616 |
xaIn = pSrc[(2u * i0)]; |
|
617 |
yaIn = pSrc[(2u * i0) + 1u]; |
|
618 |
|
|
619 |
xcIn = pSrc[(2u * i2)]; |
|
620 |
ycIn = pSrc[(2u * i2) + 1u]; |
|
621 |
|
|
622 |
xbIn = pSrc[(2u * i1)]; |
|
623 |
ybIn = pSrc[(2u * i1) + 1u]; |
|
624 |
|
|
625 |
xdIn = pSrc[(2u * i3)]; |
|
626 |
ydIn = pSrc[(2u * i3) + 1u]; |
|
627 |
|
|
628 |
/* xa + xc */ |
|
629 |
Xaplusc = xaIn + xcIn; |
|
630 |
/* xb + xd */ |
|
631 |
Xbplusd = xbIn + xdIn; |
|
632 |
/* ya + yc */ |
|
633 |
Yaplusc = yaIn + ycIn; |
|
634 |
/* yb + yd */ |
|
635 |
Ybplusd = ybIn + ydIn; |
|
636 |
|
|
637 |
/* index calculation for the coefficients */ |
|
638 |
ia2 = ia1 + ia1; |
|
639 |
co2 = pCoef[ia2 * 2u]; |
|
640 |
si2 = pCoef[(ia2 * 2u) + 1u]; |
|
641 |
|
|
642 |
/* xa - xc */ |
|
643 |
Xaminusc = xaIn - xcIn; |
|
644 |
/* xb - xd */ |
|
645 |
Xbminusd = xbIn - xdIn; |
|
646 |
/* ya - yc */ |
|
647 |
Yaminusc = yaIn - ycIn; |
|
648 |
/* yb - yd */ |
|
649 |
Ybminusd = ybIn - ydIn; |
|
650 |
|
|
651 |
/* xa' = xa + xb + xc + xd */ |
|
652 |
pSrc[(2u * i0)] = Xaplusc + Xbplusd; |
|
653 |
|
|
654 |
/* ya' = ya + yb + yc + yd */ |
|
655 |
pSrc[(2u * i0) + 1u] = Yaplusc + Ybplusd; |
|
656 |
|
|
657 |
/* (xa - xc) - (yb - yd) */ |
|
658 |
Xb12C_out = (Xaminusc - Ybminusd); |
|
659 |
/* (ya - yc) + (xb - xd) */ |
|
660 |
Yb12C_out = (Yaminusc + Xbminusd); |
|
661 |
/* (xa + xc) - (xb + xd) */ |
|
662 |
Xc12C_out = (Xaplusc - Xbplusd); |
|
663 |
/* (ya + yc) - (yb + yd) */ |
|
664 |
Yc12C_out = (Yaplusc - Ybplusd); |
|
665 |
/* (xa - xc) + (yb - yd) */ |
|
666 |
Xd12C_out = (Xaminusc + Ybminusd); |
|
667 |
/* (ya - yc) - (xb - xd) */ |
|
668 |
Yd12C_out = (Yaminusc - Xbminusd); |
|
669 |
|
|
670 |
co1 = pCoef[ia1 * 2u]; |
|
671 |
si1 = pCoef[(ia1 * 2u) + 1u]; |
|
672 |
|
|
673 |
/* index calculation for the coefficients */ |
|
674 |
ia3 = ia2 + ia1; |
|
675 |
co3 = pCoef[ia3 * 2u]; |
|
676 |
si3 = pCoef[(ia3 * 2u) + 1u]; |
|
677 |
|
|
678 |
Xb12_out = Xb12C_out * co1; |
|
679 |
Yb12_out = Yb12C_out * co1; |
|
680 |
Xc12_out = Xc12C_out * co2; |
|
681 |
Yc12_out = Yc12C_out * co2; |
|
682 |
Xd12_out = Xd12C_out * co3; |
|
683 |
Yd12_out = Yd12C_out * co3; |
|
684 |
|
|
685 |
/* xb' = (xa+yb-xc-yd)co1 - (ya-xb-yc+xd)(si1) */ |
|
686 |
//Xb12_out -= Yb12C_out * si1; |
|
687 |
p0 = Yb12C_out * si1; |
|
688 |
/* yb' = (ya-xb-yc+xd)co1 + (xa+yb-xc-yd)(si1) */ |
|
689 |
//Yb12_out += Xb12C_out * si1; |
|
690 |
p1 = Xb12C_out * si1; |
|
691 |
/* xc' = (xa-xb+xc-xd)co2 - (ya-yb+yc-yd)(si2) */ |
|
692 |
//Xc12_out -= Yc12C_out * si2; |
|
693 |
p2 = Yc12C_out * si2; |
|
694 |
/* yc' = (ya-yb+yc-yd)co2 + (xa-xb+xc-xd)(si2) */ |
|
695 |
//Yc12_out += Xc12C_out * si2; |
|
696 |
p3 = Xc12C_out * si2; |
|
697 |
/* xd' = (xa-yb-xc+yd)co3 - (ya+xb-yc-xd)(si3) */ |
|
698 |
//Xd12_out -= Yd12C_out * si3; |
|
699 |
p4 = Yd12C_out * si3; |
|
700 |
/* yd' = (ya+xb-yc-xd)co3 + (xa-yb-xc+yd)(si3) */ |
|
701 |
//Yd12_out += Xd12C_out * si3; |
|
702 |
p5 = Xd12C_out * si3; |
|
703 |
|
|
704 |
Xb12_out -= p0; |
|
705 |
Yb12_out += p1; |
|
706 |
Xc12_out -= p2; |
|
707 |
Yc12_out += p3; |
|
708 |
Xd12_out -= p4; |
|
709 |
Yd12_out += p5; |
|
710 |
|
|
711 |
/* xc' = (xa-xb+xc-xd)co2 - (ya-yb+yc-yd)(si2) */ |
|
712 |
pSrc[2u * i1] = Xc12_out; |
|
713 |
|
|
714 |
/* yc' = (ya-yb+yc-yd)co2 + (xa-xb+xc-xd)(si2) */ |
|
715 |
pSrc[(2u * i1) + 1u] = Yc12_out; |
|
716 |
|
|
717 |
/* xb' = (xa+yb-xc-yd)co1 - (ya-xb-yc+xd)(si1) */ |
|
718 |
pSrc[2u * i2] = Xb12_out; |
|
719 |
|
|
720 |
/* yb' = (ya-xb-yc+xd)co1 + (xa+yb-xc-yd)(si1) */ |
|
721 |
pSrc[(2u * i2) + 1u] = Yb12_out; |
|
722 |
|
|
723 |
/* xd' = (xa-yb-xc+yd)co3 - (ya+xb-yc-xd)(si3) */ |
|
724 |
pSrc[2u * i3] = Xd12_out; |
|
725 |
|
|
726 |
/* yd' = (ya+xb-yc-xd)co3 + (xa-yb-xc+yd)(si3) */ |
|
727 |
pSrc[(2u * i3) + 1u] = Yd12_out; |
|
728 |
|
|
729 |
/* Twiddle coefficients index modifier */ |
|
730 |
ia1 = ia1 + twidCoefModifier; |
|
731 |
|
|
732 |
/* Updating input index */ |
|
733 |
i0 = i0 + 1u; |
|
734 |
|
|
735 |
} while(--j); |
|
736 |
|
|
737 |
twidCoefModifier <<= 2u; |
|
738 |
|
|
739 |
/* Calculation of second stage to excluding last stage */ |
|
740 |
for (k = fftLen >> 2u; k > 4u; k >>= 2u) |
|
741 |
{ |
|
742 |
/* Initializations for the first stage */ |
|
743 |
n1 = n2; |
|
744 |
n2 >>= 2u; |
|
745 |
ia1 = 0u; |
|
746 |
|
|
747 |
/* Calculation of first stage */ |
|
748 |
j = 0; |
|
749 |
do |
|
750 |
{ |
|
751 |
/* index calculation for the coefficients */ |
|
752 |
ia2 = ia1 + ia1; |
|
753 |
ia3 = ia2 + ia1; |
|
754 |
co1 = pCoef[ia1 * 2u]; |
|
755 |
si1 = pCoef[(ia1 * 2u) + 1u]; |
|
756 |
co2 = pCoef[ia2 * 2u]; |
|
757 |
si2 = pCoef[(ia2 * 2u) + 1u]; |
|
758 |
co3 = pCoef[ia3 * 2u]; |
|
759 |
si3 = pCoef[(ia3 * 2u) + 1u]; |
|
760 |
|
|
761 |
/* Twiddle coefficients index modifier */ |
|
762 |
ia1 = ia1 + twidCoefModifier; |
|
763 |
|
|
764 |
i0 = j; |
|
765 |
do |
|
766 |
{ |
|
767 |
/* index calculation for the input as, */ |
|
768 |
/* pSrc[i0 + 0], pSrc[i0 + fftLen/4], pSrc[i0 + fftLen/2], pSrc[i0 + 3fftLen/4] */ |
|
769 |
i1 = i0 + n2; |
|
770 |
i2 = i1 + n2; |
|
771 |
i3 = i2 + n2; |
|
772 |
|
|
773 |
xaIn = pSrc[(2u * i0)]; |
|
774 |
yaIn = pSrc[(2u * i0) + 1u]; |
|
775 |
|
|
776 |
xbIn = pSrc[(2u * i1)]; |
|
777 |
ybIn = pSrc[(2u * i1) + 1u]; |
|
778 |
|
|
779 |
xcIn = pSrc[(2u * i2)]; |
|
780 |
ycIn = pSrc[(2u * i2) + 1u]; |
|
781 |
|
|
782 |
xdIn = pSrc[(2u * i3)]; |
|
783 |
ydIn = pSrc[(2u * i3) + 1u]; |
|
784 |
|
|
785 |
/* xa - xc */ |
|
786 |
Xaminusc = xaIn - xcIn; |
|
787 |
/* (xb - xd) */ |
|
788 |
Xbminusd = xbIn - xdIn; |
|
789 |
/* ya - yc */ |
|
790 |
Yaminusc = yaIn - ycIn; |
|
791 |
/* (yb - yd) */ |
|
792 |
Ybminusd = ybIn - ydIn; |
|
793 |
|
|
794 |
/* xa + xc */ |
|
795 |
Xaplusc = xaIn + xcIn; |
|
796 |
/* xb + xd */ |
|
797 |
Xbplusd = xbIn + xdIn; |
|
798 |
/* ya + yc */ |
|
799 |
Yaplusc = yaIn + ycIn; |
|
800 |
/* yb + yd */ |
|
801 |
Ybplusd = ybIn + ydIn; |
|
802 |
|
|
803 |
/* (xa - xc) - (yb - yd) */ |
|
804 |
Xb12C_out = (Xaminusc - Ybminusd); |
|
805 |
/* (ya - yc) + (xb - xd) */ |
|
806 |
Yb12C_out = (Yaminusc + Xbminusd); |
|
807 |
/* xa + xc -(xb + xd) */ |
|
808 |
Xc12C_out = (Xaplusc - Xbplusd); |
|
809 |
/* (ya + yc) - (yb + yd) */ |
|
810 |
Yc12C_out = (Yaplusc - Ybplusd); |
|
811 |
/* (xa - xc) + (yb - yd) */ |
|
812 |
Xd12C_out = (Xaminusc + Ybminusd); |
|
813 |
/* (ya - yc) - (xb - xd) */ |
|
814 |
Yd12C_out = (Yaminusc - Xbminusd); |
|
815 |
|
|
816 |
pSrc[(2u * i0)] = Xaplusc + Xbplusd; |
|
817 |
pSrc[(2u * i0) + 1u] = Yaplusc + Ybplusd; |
|
818 |
|
|
819 |
Xb12_out = Xb12C_out * co1; |
|
820 |
Yb12_out = Yb12C_out * co1; |
|
821 |
Xc12_out = Xc12C_out * co2; |
|
822 |
Yc12_out = Yc12C_out * co2; |
|
823 |
Xd12_out = Xd12C_out * co3; |
|
824 |
Yd12_out = Yd12C_out * co3; |
|
825 |
|
|
826 |
/* xb' = (xa+yb-xc-yd)co1 - (ya-xb-yc+xd)(si1) */ |
|
827 |
//Xb12_out -= Yb12C_out * si1; |
|
828 |
p0 = Yb12C_out * si1; |
|
829 |
/* yb' = (ya-xb-yc+xd)co1 + (xa+yb-xc-yd)(si1) */ |
|
830 |
//Yb12_out += Xb12C_out * si1; |
|
831 |
p1 = Xb12C_out * si1; |
|
832 |
/* xc' = (xa-xb+xc-xd)co2 - (ya-yb+yc-yd)(si2) */ |
|
833 |
//Xc12_out -= Yc12C_out * si2; |
|
834 |
p2 = Yc12C_out * si2; |
|
835 |
/* yc' = (ya-yb+yc-yd)co2 + (xa-xb+xc-xd)(si2) */ |
|
836 |
//Yc12_out += Xc12C_out * si2; |
|
837 |
p3 = Xc12C_out * si2; |
|
838 |
/* xd' = (xa-yb-xc+yd)co3 - (ya+xb-yc-xd)(si3) */ |
|
839 |
//Xd12_out -= Yd12C_out * si3; |
|
840 |
p4 = Yd12C_out * si3; |
|
841 |
/* yd' = (ya+xb-yc-xd)co3 + (xa-yb-xc+yd)(si3) */ |
|
842 |
//Yd12_out += Xd12C_out * si3; |
|
843 |
p5 = Xd12C_out * si3; |
|
844 |
|
|
845 |
Xb12_out -= p0; |
|
846 |
Yb12_out += p1; |
|
847 |
Xc12_out -= p2; |
|
848 |
Yc12_out += p3; |
|
849 |
Xd12_out -= p4; |
|
850 |
Yd12_out += p5; |
|
851 |
|
|
852 |
/* xc' = (xa-xb+xc-xd)co2 - (ya-yb+yc-yd)(si2) */ |
|
853 |
pSrc[2u * i1] = Xc12_out; |
|
854 |
|
|
855 |
/* yc' = (ya-yb+yc-yd)co2 + (xa-xb+xc-xd)(si2) */ |
|
856 |
pSrc[(2u * i1) + 1u] = Yc12_out; |
|
857 |
|
|
858 |
/* xb' = (xa+yb-xc-yd)co1 - (ya-xb-yc+xd)(si1) */ |
|
859 |
pSrc[2u * i2] = Xb12_out; |
|
860 |
|
|
861 |
/* yb' = (ya-xb-yc+xd)co1 + (xa+yb-xc-yd)(si1) */ |
|
862 |
pSrc[(2u * i2) + 1u] = Yb12_out; |
|
863 |
|
|
864 |
/* xd' = (xa-yb-xc+yd)co3 - (ya+xb-yc-xd)(si3) */ |
|
865 |
pSrc[2u * i3] = Xd12_out; |
|
866 |
|
|
867 |
/* yd' = (ya+xb-yc-xd)co3 + (xa-yb-xc+yd)(si3) */ |
|
868 |
pSrc[(2u * i3) + 1u] = Yd12_out; |
|
869 |
|
|
870 |
i0 += n1; |
|
871 |
} while(i0 < fftLen); |
|
872 |
j++; |
|
873 |
} while(j <= (n2 - 1u)); |
|
874 |
twidCoefModifier <<= 2u; |
|
875 |
} |
|
876 |
/* Initializations of last stage */ |
|
877 |
|
|
878 |
j = fftLen >> 2; |
|
879 |
ptr1 = &pSrc[0]; |
|
880 |
|
|
881 |
/* Calculations of last stage */ |
|
882 |
do |
|
883 |
{ |
|
884 |
xaIn = ptr1[0]; |
|
885 |
yaIn = ptr1[1]; |
|
886 |
xbIn = ptr1[2]; |
|
887 |
ybIn = ptr1[3]; |
|
888 |
xcIn = ptr1[4]; |
|
889 |
ycIn = ptr1[5]; |
|
890 |
xdIn = ptr1[6]; |
|
891 |
ydIn = ptr1[7]; |
|
892 |
|
|
893 |
/* Butterfly implementation */ |
|
894 |
/* xa + xc */ |
|
895 |
Xaplusc = xaIn + xcIn; |
|
896 |
|
|
897 |
/* xa - xc */ |
|
898 |
Xaminusc = xaIn - xcIn; |
|
899 |
|
|
900 |
/* ya + yc */ |
|
901 |
Yaplusc = yaIn + ycIn; |
|
902 |
|
|
903 |
/* ya - yc */ |
|
904 |
Yaminusc = yaIn - ycIn; |
|
905 |
|
|
906 |
/* xb + xd */ |
|
907 |
Xbplusd = xbIn + xdIn; |
|
908 |
|
|
909 |
/* yb + yd */ |
|
910 |
Ybplusd = ybIn + ydIn; |
|
911 |
|
|
912 |
/* (xb-xd) */ |
|
913 |
Xbminusd = xbIn - xdIn; |
|
914 |
|
|
915 |
/* (yb-yd) */ |
|
916 |
Ybminusd = ybIn - ydIn; |
|
917 |
|
|
918 |
/* xa' = (xa+xb+xc+xd) * onebyfftLen */ |
|
919 |
a0 = (Xaplusc + Xbplusd); |
|
920 |
/* ya' = (ya+yb+yc+yd) * onebyfftLen */ |
|
921 |
a1 = (Yaplusc + Ybplusd); |
|
922 |
/* xc' = (xa-xb+xc-xd) * onebyfftLen */ |
|
923 |
a2 = (Xaplusc - Xbplusd); |
|
924 |
/* yc' = (ya-yb+yc-yd) * onebyfftLen */ |
|
925 |
a3 = (Yaplusc - Ybplusd); |
|
926 |
/* xb' = (xa-yb-xc+yd) * onebyfftLen */ |
|
927 |
a4 = (Xaminusc - Ybminusd); |
|
928 |
/* yb' = (ya+xb-yc-xd) * onebyfftLen */ |
|
929 |
a5 = (Yaminusc + Xbminusd); |
|
930 |
/* xd' = (xa-yb-xc+yd) * onebyfftLen */ |
|
931 |
a6 = (Xaminusc + Ybminusd); |
|
932 |
/* yd' = (ya-xb-yc+xd) * onebyfftLen */ |
|
933 |
a7 = (Yaminusc - Xbminusd); |
|
934 |
|
|
935 |
p0 = a0 * onebyfftLen; |
|
936 |
p1 = a1 * onebyfftLen; |
|
937 |
p2 = a2 * onebyfftLen; |
|
938 |
p3 = a3 * onebyfftLen; |
|
939 |
p4 = a4 * onebyfftLen; |
|
940 |
p5 = a5 * onebyfftLen; |
|
941 |
p6 = a6 * onebyfftLen; |
|
942 |
p7 = a7 * onebyfftLen; |
|
943 |
|
|
944 |
/* xa' = (xa+xb+xc+xd) * onebyfftLen */ |
|
945 |
ptr1[0] = p0; |
|
946 |
/* ya' = (ya+yb+yc+yd) * onebyfftLen */ |
|
947 |
ptr1[1] = p1; |
|
948 |
/* xc' = (xa-xb+xc-xd) * onebyfftLen */ |
|
949 |
ptr1[2] = p2; |
|
950 |
/* yc' = (ya-yb+yc-yd) * onebyfftLen */ |
|
951 |
ptr1[3] = p3; |
|
952 |
/* xb' = (xa-yb-xc+yd) * onebyfftLen */ |
|
953 |
ptr1[4] = p4; |
|
954 |
/* yb' = (ya+xb-yc-xd) * onebyfftLen */ |
|
955 |
ptr1[5] = p5; |
|
956 |
/* xd' = (xa-yb-xc+yd) * onebyfftLen */ |
|
957 |
ptr1[6] = p6; |
|
958 |
/* yd' = (ya-xb-yc+xd) * onebyfftLen */ |
|
959 |
ptr1[7] = p7; |
|
960 |
|
|
961 |
/* increment source pointer by 8 for next calculations */ |
|
962 |
ptr1 = ptr1 + 8u; |
|
963 |
|
|
964 |
} while(--j); |
|
965 |
|
|
966 |
#else |
|
967 |
|
|
968 |
float32_t t1, t2, r1, r2, s1, s2; |
|
969 |
|
|
970 |
/* Run the below code for Cortex-M0 */ |
|
971 |
|
|
972 |
/* Initializations for the first stage */ |
|
973 |
n2 = fftLen; |
|
974 |
n1 = n2; |
|
975 |
|
|
976 |
/* Calculation of first stage */ |
|
977 |
for (k = fftLen; k > 4u; k >>= 2u) |
|
978 |
{ |
|
979 |
/* Initializations for the first stage */ |
|
980 |
n1 = n2; |
|
981 |
n2 >>= 2u; |
|
982 |
ia1 = 0u; |
|
983 |
|
|
984 |
/* Calculation of first stage */ |
|
985 |
j = 0; |
|
986 |
do |
|
987 |
{ |
|
988 |
/* index calculation for the coefficients */ |
|
989 |
ia2 = ia1 + ia1; |
|
990 |
ia3 = ia2 + ia1; |
|
991 |
co1 = pCoef[ia1 * 2u]; |
|
992 |
si1 = pCoef[(ia1 * 2u) + 1u]; |
|
993 |
co2 = pCoef[ia2 * 2u]; |
|
994 |
si2 = pCoef[(ia2 * 2u) + 1u]; |
|
995 |
co3 = pCoef[ia3 * 2u]; |
|
996 |
si3 = pCoef[(ia3 * 2u) + 1u]; |
|
997 |
|
|
998 |
/* Twiddle coefficients index modifier */ |
|
999 |
ia1 = ia1 + twidCoefModifier; |
|
1000 |
|
|
1001 |
i0 = j; |
|
1002 |
do |
|
1003 |
{ |
|
1004 |
/* index calculation for the input as, */ |
|
1005 |
/* pSrc[i0 + 0], pSrc[i0 + fftLen/4], pSrc[i0 + fftLen/2], pSrc[i0 + 3fftLen/4] */ |
|
1006 |
i1 = i0 + n2; |
|
1007 |
i2 = i1 + n2; |
|
1008 |
i3 = i2 + n2; |
|
1009 |
|
|
1010 |
/* xa + xc */ |
|
1011 |
r1 = pSrc[(2u * i0)] + pSrc[(2u * i2)]; |
|
1012 |
|
|
1013 |
/* xa - xc */ |
|
1014 |
r2 = pSrc[(2u * i0)] - pSrc[(2u * i2)]; |
|
1015 |
|
|
1016 |
/* ya + yc */ |
|
1017 |
s1 = pSrc[(2u * i0) + 1u] + pSrc[(2u * i2) + 1u]; |
|
1018 |
|
|
1019 |
/* ya - yc */ |
|
1020 |
s2 = pSrc[(2u * i0) + 1u] - pSrc[(2u * i2) + 1u]; |
|
1021 |
|
|
1022 |
/* xb + xd */ |
|
1023 |
t1 = pSrc[2u * i1] + pSrc[2u * i3]; |
|
1024 |
|
|
1025 |
/* xa' = xa + xb + xc + xd */ |
|
1026 |
pSrc[2u * i0] = r1 + t1; |
|
1027 |
|
|
1028 |
/* xa + xc -(xb + xd) */ |
|
1029 |
r1 = r1 - t1; |
|
1030 |
|
|
1031 |
/* yb + yd */ |
|
1032 |
t2 = pSrc[(2u * i1) + 1u] + pSrc[(2u * i3) + 1u]; |
|
1033 |
|
|
1034 |
/* ya' = ya + yb + yc + yd */ |
|
1035 |
pSrc[(2u * i0) + 1u] = s1 + t2; |
|
1036 |
|
|
1037 |
/* (ya + yc) - (yb + yd) */ |
|
1038 |
s1 = s1 - t2; |
|
1039 |
|
|
1040 |
/* (yb - yd) */ |
|
1041 |
t1 = pSrc[(2u * i1) + 1u] - pSrc[(2u * i3) + 1u]; |
|
1042 |
|
|
1043 |
/* (xb - xd) */ |
|
1044 |
t2 = pSrc[2u * i1] - pSrc[2u * i3]; |
|
1045 |
|
|
1046 |
/* xc' = (xa-xb+xc-xd)co2 - (ya-yb+yc-yd)(si2) */ |
|
1047 |
pSrc[2u * i1] = (r1 * co2) - (s1 * si2); |
|
1048 |
|
|
1049 |
/* yc' = (ya-yb+yc-yd)co2 + (xa-xb+xc-xd)(si2) */ |
|
1050 |
pSrc[(2u * i1) + 1u] = (s1 * co2) + (r1 * si2); |
|
1051 |
|
|
1052 |
/* (xa - xc) - (yb - yd) */ |
|
1053 |
r1 = r2 - t1; |
|
1054 |
|
|
1055 |
/* (xa - xc) + (yb - yd) */ |
|
1056 |
r2 = r2 + t1; |
|
1057 |
|
|
1058 |
/* (ya - yc) + (xb - xd) */ |
|
1059 |
s1 = s2 + t2; |
|
1060 |
|
|
1061 |
/* (ya - yc) - (xb - xd) */ |
|
1062 |
s2 = s2 - t2; |
|
1063 |
|
|
1064 |
/* xb' = (xa+yb-xc-yd)co1 - (ya-xb-yc+xd)(si1) */ |
|
1065 |
pSrc[2u * i2] = (r1 * co1) - (s1 * si1); |
|
1066 |
|
|
1067 |
/* yb' = (ya-xb-yc+xd)co1 + (xa+yb-xc-yd)(si1) */ |
|
1068 |
pSrc[(2u * i2) + 1u] = (s1 * co1) + (r1 * si1); |
|
1069 |
|
|
1070 |
/* xd' = (xa-yb-xc+yd)co3 - (ya+xb-yc-xd)(si3) */ |
|
1071 |
pSrc[2u * i3] = (r2 * co3) - (s2 * si3); |
|
1072 |
|
|
1073 |
/* yd' = (ya+xb-yc-xd)co3 + (xa-yb-xc+yd)(si3) */ |
|
1074 |
pSrc[(2u * i3) + 1u] = (s2 * co3) + (r2 * si3); |
|
1075 |
|
|
1076 |
i0 += n1; |
|
1077 |
} while( i0 < fftLen); |
|
1078 |
j++; |
|
1079 |
} while(j <= (n2 - 1u)); |
|
1080 |
twidCoefModifier <<= 2u; |
|
1081 |
} |
|
1082 |
/* Initializations of last stage */ |
|
1083 |
n1 = n2; |
|
1084 |
n2 >>= 2u; |
|
1085 |
|
|
1086 |
/* Calculations of last stage */ |
|
1087 |
for (i0 = 0u; i0 <= (fftLen - n1); i0 += n1) |
|
1088 |
{ |
|
1089 |
/* index calculation for the input as, */ |
|
1090 |
/* pSrc[i0 + 0], pSrc[i0 + fftLen/4], pSrc[i0 + fftLen/2], pSrc[i0 + 3fftLen/4] */ |
|
1091 |
i1 = i0 + n2; |
|
1092 |
i2 = i1 + n2; |
|
1093 |
i3 = i2 + n2; |
|
1094 |
|
|
1095 |
/* Butterfly implementation */ |
|
1096 |
/* xa + xc */ |
|
1097 |
r1 = pSrc[2u * i0] + pSrc[2u * i2]; |
|
1098 |
|
|
1099 |
/* xa - xc */ |
|
1100 |
r2 = pSrc[2u * i0] - pSrc[2u * i2]; |
|
1101 |
|
|
1102 |
/* ya + yc */ |
|
1103 |
s1 = pSrc[(2u * i0) + 1u] + pSrc[(2u * i2) + 1u]; |
|
1104 |
|
|
1105 |
/* ya - yc */ |
|
1106 |
s2 = pSrc[(2u * i0) + 1u] - pSrc[(2u * i2) + 1u]; |
|
1107 |
|
|
1108 |
/* xc + xd */ |
|
1109 |
t1 = pSrc[2u * i1] + pSrc[2u * i3]; |
|
1110 |
|
|
1111 |
/* xa' = xa + xb + xc + xd */ |
|
1112 |
pSrc[2u * i0] = (r1 + t1) * onebyfftLen; |
|
1113 |
|
|
1114 |
/* (xa + xb) - (xc + xd) */ |
|
1115 |
r1 = r1 - t1; |
|
1116 |
|
|
1117 |
/* yb + yd */ |
|
1118 |
t2 = pSrc[(2u * i1) + 1u] + pSrc[(2u * i3) + 1u]; |
|
1119 |
|
|
1120 |
/* ya' = ya + yb + yc + yd */ |
|
1121 |
pSrc[(2u * i0) + 1u] = (s1 + t2) * onebyfftLen; |
|
1122 |
|
|
1123 |
/* (ya + yc) - (yb + yd) */ |
|
1124 |
s1 = s1 - t2; |
|
1125 |
|
|
1126 |
/* (yb-yd) */ |
|
1127 |
t1 = pSrc[(2u * i1) + 1u] - pSrc[(2u * i3) + 1u]; |
|
1128 |
|
|
1129 |
/* (xb-xd) */ |
|
1130 |
t2 = pSrc[2u * i1] - pSrc[2u * i3]; |
|
1131 |
|
|
1132 |
/* xc' = (xa-xb+xc-xd)co2 - (ya-yb+yc-yd)(si2) */ |
|
1133 |
pSrc[2u * i1] = r1 * onebyfftLen; |
|
1134 |
|
|
1135 |
/* yc' = (ya-yb+yc-yd)co2 + (xa-xb+xc-xd)(si2) */ |
|
1136 |
pSrc[(2u * i1) + 1u] = s1 * onebyfftLen; |
|
1137 |
|
|
1138 |
/* (xa - xc) - (yb-yd) */ |
|
1139 |
r1 = r2 - t1; |
|
1140 |
|
|
1141 |
/* (xa - xc) + (yb-yd) */ |
|
1142 |
r2 = r2 + t1; |
|
1143 |
|
|
1144 |
/* (ya - yc) + (xb-xd) */ |
|
1145 |
s1 = s2 + t2; |
|
1146 |
|
|
1147 |
/* (ya - yc) - (xb-xd) */ |
|
1148 |
s2 = s2 - t2; |
|
1149 |
|
|
1150 |
/* xb' = (xa+yb-xc-yd)co1 - (ya-xb-yc+xd)(si1) */ |
|
1151 |
pSrc[2u * i2] = r1 * onebyfftLen; |
|
1152 |
|
|
1153 |
/* yb' = (ya-xb-yc+xd)co1 + (xa+yb-xc-yd)(si1) */ |
|
1154 |
pSrc[(2u * i2) + 1u] = s1 * onebyfftLen; |
|
1155 |
|
|
1156 |
/* xd' = (xa-yb-xc+yd)co3 - (ya+xb-yc-xd)(si3) */ |
|
1157 |
pSrc[2u * i3] = r2 * onebyfftLen; |
|
1158 |
|
|
1159 |
/* yd' = (ya+xb-yc-xd)co3 + (xa-yb-xc+yd)(si3) */ |
|
1160 |
pSrc[(2u * i3) + 1u] = s2 * onebyfftLen; |
|
1161 |
} |
|
1162 |
|
|
1163 |
#endif /* #ifndef ARM_MATH_CM0_FAMILY_FAMILY */ |
|
1164 |
} |
|
1165 |
|
|
1166 |
/** |
|
1167 |
* @addtogroup ComplexFFT |
|
1168 |
* @{ |
|
1169 |
*/ |
|
1170 |
|
|
1171 |
/** |
|
1172 |
* @details |
|
1173 |
* @brief Processing function for the floating-point Radix-4 CFFT/CIFFT. |
|
1174 |
* @deprecated Do not use this function. It has been superseded by \ref arm_cfft_f32 and will be removed |
|
1175 |
* in the future. |
|
1176 |
* @param[in] *S points to an instance of the floating-point Radix-4 CFFT/CIFFT structure. |
|
1177 |
* @param[in, out] *pSrc points to the complex data buffer of size <code>2*fftLen</code>. Processing occurs in-place. |
|
1178 |
* @return none. |
|
1179 |
*/ |
|
1180 |
|
|
1181 |
void arm_cfft_radix4_f32( |
|
1182 |
const arm_cfft_radix4_instance_f32 * S, |
|
1183 |
float32_t * pSrc) |
|
1184 |
{ |
|
1185 |
|
|
1186 |
if(S->ifftFlag == 1u) |
|
1187 |
{ |
|
1188 |
/* Complex IFFT radix-4 */ |
|
1189 |
arm_radix4_butterfly_inverse_f32(pSrc, S->fftLen, S->pTwiddle, |
|
1190 |
S->twidCoefModifier, S->onebyfftLen); |
|
1191 |
} |
|
1192 |
else |
|
1193 |
{ |
|
1194 |
/* Complex FFT radix-4 */ |
|
1195 |
arm_radix4_butterfly_f32(pSrc, S->fftLen, S->pTwiddle, |
|
1196 |
S->twidCoefModifier); |
|
1197 |
} |
|
1198 |
|
|
1199 |
if(S->bitReverseFlag == 1u) |
|
1200 |
{ |
|
1201 |
/* Bit Reversal */ |
|
1202 |
arm_bitreversal_f32(pSrc, S->fftLen, S->bitRevFactor, S->pBitRevTable); |
|
1203 |
} |
|
1204 |
|
|
1205 |
} |
|
1206 |
|
|
1207 |
/** |
|
1208 |
* @} end of ComplexFFT group |
|
1209 |
*/ |
|
1210 |
|