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
|
/* ----------------------------------------------------------------------
* Project: CMSIS DSP Library
* Title: arm_cfft_q15.c
* Description: Combined Radix Decimation in Q15 Frequency CFFT processing function
*
* $Date: 18. March 2019
* $Revision: V1.6.0
*
* Target Processor: Cortex-M cores
* -------------------------------------------------------------------- */
/*
* Copyright (C) 2010-2019 ARM Limited or its affiliates. All rights reserved.
*
* SPDX-License-Identifier: Apache-2.0
*
* Licensed under the Apache License, Version 2.0 (the License); you may
* not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an AS IS BASIS, WITHOUT
* WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
#include "arm_math.h"
extern void arm_radix4_butterfly_q15(
q15_t * pSrc,
uint32_t fftLen,
const q15_t * pCoef,
uint32_t twidCoefModifier);
extern void arm_radix4_butterfly_inverse_q15(
q15_t * pSrc,
uint32_t fftLen,
const q15_t * pCoef,
uint32_t twidCoefModifier);
extern void arm_bitreversal_16(
uint16_t * pSrc,
const uint16_t bitRevLen,
const uint16_t * pBitRevTable);
void arm_cfft_radix4by2_q15(
q15_t * pSrc,
uint32_t fftLen,
const q15_t * pCoef);
void arm_cfft_radix4by2_inverse_q15(
q15_t * pSrc,
uint32_t fftLen,
const q15_t * pCoef);
/**
@ingroup groupTransforms
*/
/**
@addtogroup ComplexFFT
@{
*/
/**
@brief Processing function for Q15 complex FFT.
@param[in] S points to an instance of Q15 CFFT structure
@param[in,out] p1 points to the complex data buffer of size <code>2*fftLen</code>. Processing occurs in-place
@param[in] ifftFlag flag that selects transform direction
- value = 0: forward transform
- value = 1: inverse transform
@param[in] bitReverseFlag flag that enables / disables bit reversal of output
- value = 0: disables bit reversal of output
- value = 1: enables bit reversal of output
@return none
*/
void arm_cfft_q15(
const arm_cfft_instance_q15 * S,
q15_t * p1,
uint8_t ifftFlag,
uint8_t bitReverseFlag)
{
uint32_t L = S->fftLen;
if (ifftFlag == 1U)
{
switch (L)
{
case 16:
case 64:
case 256:
case 1024:
case 4096:
arm_radix4_butterfly_inverse_q15 ( p1, L, (q15_t*)S->pTwiddle, 1 );
break;
case 32:
case 128:
case 512:
case 2048:
arm_cfft_radix4by2_inverse_q15 ( p1, L, S->pTwiddle );
break;
}
}
else
{
switch (L)
{
case 16:
case 64:
case 256:
case 1024:
case 4096:
arm_radix4_butterfly_q15 ( p1, L, (q15_t*)S->pTwiddle, 1 );
break;
case 32:
case 128:
case 512:
case 2048:
arm_cfft_radix4by2_q15 ( p1, L, S->pTwiddle );
break;
}
}
if ( bitReverseFlag )
arm_bitreversal_16 ((uint16_t*) p1, S->bitRevLength, S->pBitRevTable);
}
/**
@} end of ComplexFFT group
*/
void arm_cfft_radix4by2_q15(
q15_t * pSrc,
uint32_t fftLen,
const q15_t * pCoef)
{
uint32_t i;
uint32_t n2;
q15_t p0, p1, p2, p3;
#if defined (ARM_MATH_DSP)
q31_t T, S, R;
q31_t coeff, out1, out2;
const q15_t *pC = pCoef;
q15_t *pSi = pSrc;
q15_t *pSl = pSrc + fftLen;
#else
uint32_t l;
q15_t xt, yt, cosVal, sinVal;
#endif
n2 = fftLen >> 1U;
#if defined (ARM_MATH_DSP)
for (i = n2; i > 0; i--)
{
coeff = read_q15x2_ia ((q15_t **) &pC);
T = read_q15x2 (pSi);
T = __SHADD16(T, 0); /* this is just a SIMD arithmetic shift right by 1 */
S = read_q15x2 (pSl);
S = __SHADD16(S, 0); /* this is just a SIMD arithmetic shift right by 1 */
R = __QSUB16(T, S);
write_q15x2_ia (&pSi, __SHADD16(T, S));
#ifndef ARM_MATH_BIG_ENDIAN
out1 = __SMUAD(coeff, R) >> 16U;
out2 = __SMUSDX(coeff, R);
#else
out1 = __SMUSDX(R, coeff) >> 16U;
out2 = __SMUAD(coeff, R);
#endif /* #ifndef ARM_MATH_BIG_ENDIAN */
write_q15x2_ia (&pSl, (q31_t) ((out2) & 0xFFFF0000) | (out1 & 0x0000FFFF));
}
#else /* #if defined (ARM_MATH_DSP) */
for (i = 0; i < n2; i++)
{
cosVal = pCoef[2 * i];
sinVal = pCoef[2 * i + 1];
l = i + n2;
xt = (pSrc[2 * i] >> 1U) - (pSrc[2 * l] >> 1U);
pSrc[2 * i] = ((pSrc[2 * i] >> 1U) + (pSrc[2 * l] >> 1U)) >> 1U;
yt = (pSrc[2 * i + 1] >> 1U) - (pSrc[2 * l + 1] >> 1U);
pSrc[2 * i + 1] = ((pSrc[2 * l + 1] >> 1U) + (pSrc[2 * i + 1] >> 1U)) >> 1U;
pSrc[2 * l] = (((int16_t) (((q31_t) xt * cosVal) >> 16U)) +
((int16_t) (((q31_t) yt * sinVal) >> 16U)) );
pSrc[2 * l + 1] = (((int16_t) (((q31_t) yt * cosVal) >> 16U)) -
((int16_t) (((q31_t) xt * sinVal) >> 16U)) );
}
#endif /* #if defined (ARM_MATH_DSP) */
/* first col */
arm_radix4_butterfly_q15( pSrc, n2, (q15_t*)pCoef, 2U);
/* second col */
arm_radix4_butterfly_q15( pSrc + fftLen, n2, (q15_t*)pCoef, 2U);
n2 = fftLen >> 1U;
for (i = 0; i < n2; i++)
{
p0 = pSrc[4 * i + 0];
p1 = pSrc[4 * i + 1];
p2 = pSrc[4 * i + 2];
p3 = pSrc[4 * i + 3];
p0 <<= 1U;
p1 <<= 1U;
p2 <<= 1U;
p3 <<= 1U;
pSrc[4 * i + 0] = p0;
pSrc[4 * i + 1] = p1;
pSrc[4 * i + 2] = p2;
pSrc[4 * i + 3] = p3;
}
}
void arm_cfft_radix4by2_inverse_q15(
q15_t * pSrc,
uint32_t fftLen,
const q15_t * pCoef)
{
uint32_t i;
uint32_t n2;
q15_t p0, p1, p2, p3;
#if defined (ARM_MATH_DSP)
q31_t T, S, R;
q31_t coeff, out1, out2;
const q15_t *pC = pCoef;
q15_t *pSi = pSrc;
q15_t *pSl = pSrc + fftLen;
#else
uint32_t l;
q15_t xt, yt, cosVal, sinVal;
#endif
n2 = fftLen >> 1U;
#if defined (ARM_MATH_DSP)
for (i = n2; i > 0; i--)
{
coeff = read_q15x2_ia ((q15_t **) &pC);
T = read_q15x2 (pSi);
T = __SHADD16(T, 0); /* this is just a SIMD arithmetic shift right by 1 */
S = read_q15x2 (pSl);
S = __SHADD16(S, 0); /* this is just a SIMD arithmetic shift right by 1 */
R = __QSUB16(T, S);
write_q15x2_ia (&pSi, __SHADD16(T, S));
#ifndef ARM_MATH_BIG_ENDIAN
out1 = __SMUSD(coeff, R) >> 16U;
out2 = __SMUADX(coeff, R);
#else
out1 = __SMUADX(R, coeff) >> 16U;
out2 = __SMUSD(__QSUB(0, coeff), R);
#endif /* #ifndef ARM_MATH_BIG_ENDIAN */
write_q15x2_ia (&pSl, (q31_t) ((out2) & 0xFFFF0000) | (out1 & 0x0000FFFF));
}
#else /* #if defined (ARM_MATH_DSP) */
for (i = 0; i < n2; i++)
{
cosVal = pCoef[2 * i];
sinVal = pCoef[2 * i + 1];
l = i + n2;
xt = (pSrc[2 * i] >> 1U) - (pSrc[2 * l] >> 1U);
pSrc[2 * i] = ((pSrc[2 * i] >> 1U) + (pSrc[2 * l] >> 1U)) >> 1U;
yt = (pSrc[2 * i + 1] >> 1U) - (pSrc[2 * l + 1] >> 1U);
pSrc[2 * i + 1] = ((pSrc[2 * l + 1] >> 1U) + (pSrc[2 * i + 1] >> 1U)) >> 1U;
pSrc[2 * l] = (((int16_t) (((q31_t) xt * cosVal) >> 16U)) -
((int16_t) (((q31_t) yt * sinVal) >> 16U)) );
pSrc[2 * l + 1] = (((int16_t) (((q31_t) yt * cosVal) >> 16U)) +
((int16_t) (((q31_t) xt * sinVal) >> 16U)) );
}
#endif /* #if defined (ARM_MATH_DSP) */
/* first col */
arm_radix4_butterfly_inverse_q15( pSrc, n2, (q15_t*)pCoef, 2U);
/* second col */
arm_radix4_butterfly_inverse_q15( pSrc + fftLen, n2, (q15_t*)pCoef, 2U);
n2 = fftLen >> 1U;
for (i = 0; i < n2; i++)
{
p0 = pSrc[4 * i + 0];
p1 = pSrc[4 * i + 1];
p2 = pSrc[4 * i + 2];
p3 = pSrc[4 * i + 3];
p0 <<= 1U;
p1 <<= 1U;
p2 <<= 1U;
p3 <<= 1U;
pSrc[4 * i + 0] = p0;
pSrc[4 * i + 1] = p1;
pSrc[4 * i + 2] = p2;
pSrc[4 * i + 3] = p3;
}
}
|
