summaryrefslogblamecommitdiff
path: root/Drivers/CMSIS/DSP/Source/TransformFunctions/arm_cfft_radix4_q31.c
blob: b7ea7e5e969bc26d7a32b51501098df0f191af36 (plain) (tree)
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
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827


























































































































































































































































































































































































































































































































































































































































































































































































































































                                                                                                                                                          
/* ----------------------------------------------------------------------
 * Project:      CMSIS DSP Library
 * Title:        arm_cfft_radix4_q31.c
 * Description:  This file has function definition of Radix-4 FFT & IFFT function and
 *               In-place bit reversal using bit reversal table
 *
 * $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"

void arm_radix4_butterfly_inverse_q31(
        q31_t * pSrc,
        uint32_t fftLen,
  const q31_t * pCoef,
        uint32_t twidCoefModifier);

void arm_radix4_butterfly_q31(
        q31_t * pSrc,
        uint32_t fftLen,
  const q31_t * pCoef,
        uint32_t twidCoefModifier);

void arm_bitreversal_q31(
        q31_t * pSrc,
        uint32_t fftLen,
        uint16_t bitRevFactor,
  const uint16_t * pBitRevTab);

/**
  @ingroup groupTransforms
 */

/**
  @addtogroup ComplexFFT
  @{
 */

/**
  @brief         Processing function for the Q31 CFFT/CIFFT.
  @deprecated    Do not use this function.  It has been superseded by \ref arm_cfft_q31 and will be removed in the future.
  @param[in]     S    points to an instance of the Q31 CFFT/CIFFT structure
  @param[in,out] pSrc points to the complex data buffer of size <code>2*fftLen</code>. Processing occurs in-place
  @return        none
 
  @par Input and output formats:
                 Internally input is downscaled by 2 for every stage to avoid saturations inside CFFT/CIFFT process.
                 Hence the output format is different for different FFT sizes.
                 The input and output formats for different FFT sizes and number of bits to upscale are mentioned in the tables below for CFFT and CIFFT:
  @par
                 \image html CFFTQ31.gif "Input and Output Formats for Q31 CFFT"
                 \image html CIFFTQ31.gif "Input and Output Formats for Q31 CIFFT"
 */

void arm_cfft_radix4_q31(
  const arm_cfft_radix4_instance_q31 * S,
        q31_t * pSrc)
{
  if (S->ifftFlag == 1U)
  {
    /* Complex IFFT radix-4 */
    arm_radix4_butterfly_inverse_q31(pSrc, S->fftLen, S->pTwiddle, S->twidCoefModifier);
  }
  else
  {
    /* Complex FFT radix-4 */
    arm_radix4_butterfly_q31(pSrc, S->fftLen, S->pTwiddle, S->twidCoefModifier);
  }

  if (S->bitReverseFlag == 1U)
  {
    /*  Bit Reversal */
    arm_bitreversal_q31(pSrc, S->fftLen, S->bitRevFactor, S->pBitRevTable);
  }

}

/**
  @} end of ComplexFFT group
 */

/*
 * Radix-4 FFT algorithm used is :
 *
 * Input real and imaginary data:
 * x(n) = xa + j * ya
 * x(n+N/4 ) = xb + j * yb
 * x(n+N/2 ) = xc + j * yc
 * x(n+3N 4) = xd + j * yd
 *
 *
 * Output real and imaginary data:
 * x(4r) = xa'+ j * ya'
 * x(4r+1) = xb'+ j * yb'
 * x(4r+2) = xc'+ j * yc'
 * x(4r+3) = xd'+ j * yd'
 *
 *
 * Twiddle factors for radix-4 FFT:
 * Wn = co1 + j * (- si1)
 * W2n = co2 + j * (- si2)
 * W3n = co3 + j * (- si3)
 *
 *  Butterfly implementation:
 * xa' = xa + xb + xc + xd
 * ya' = ya + yb + yc + yd
 * xb' = (xa+yb-xc-yd)* co1 + (ya-xb-yc+xd)* (si1)
 * yb' = (ya-xb-yc+xd)* co1 - (xa+yb-xc-yd)* (si1)
 * xc' = (xa-xb+xc-xd)* co2 + (ya-yb+yc-yd)* (si2)
 * yc' = (ya-yb+yc-yd)* co2 - (xa-xb+xc-xd)* (si2)
 * xd' = (xa-yb-xc+yd)* co3 + (ya+xb-yc-xd)* (si3)
 * yd' = (ya+xb-yc-xd)* co3 - (xa-yb-xc+yd)* (si3)
 *
 */

/**
  @brief         Core function for the Q31 CFFT butterfly process.
  @param[in,out] pSrc             points to the in-place buffer of Q31 data type.
  @param[in]     fftLen           length of the FFT.
  @param[in]     pCoef            points to twiddle coefficient buffer.
  @param[in]     twidCoefModifier twiddle coefficient modifier that supports different size FFTs with the same twiddle factor table.
  @return        none
 */

void arm_radix4_butterfly_q31(
        q31_t * pSrc,
        uint32_t fftLen,
  const q31_t * pCoef,
        uint32_t twidCoefModifier)
{
        uint32_t n1, n2, ia1, ia2, ia3, i0, i1, i2, i3, j, k;
        q31_t t1, t2, r1, r2, s1, s2, co1, co2, co3, si1, si2, si3;
        
        q31_t xa, xb, xc, xd;
        q31_t ya, yb, yc, yd;
        q31_t xa_out, xb_out, xc_out, xd_out;
        q31_t ya_out, yb_out, yc_out, yd_out;
        
        q31_t *ptr1;

  /* Total process is divided into three stages */

  /* process first stage, middle stages, & last stage */


  /* start of first stage process */

  /*  Initializations for the first stage */
  n2 = fftLen;
  n1 = n2;
  /* n2 = fftLen/4 */
  n2 >>= 2U;
  i0 = 0U;
  ia1 = 0U;

  j = n2;

  /*  Calculation of first stage */
  do
  {
    /*  index calculation for the input as, */
    /*  pSrc[i0 + 0], pSrc[i0 + fftLen/4], pSrc[i0 + fftLen/2U], pSrc[i0 + 3fftLen/4] */
    i1 = i0 + n2;
    i2 = i1 + n2;
    i3 = i2 + n2;

    /* input is in 1.31(q31) format and provide 4 guard bits for the input */

    /*  Butterfly implementation */
    /* xa + xc */
    r1 = (pSrc[(2U * i0)] >> 4U) + (pSrc[(2U * i2)] >> 4U);
    /* xa - xc */
    r2 = (pSrc[(2U * i0)] >> 4U) - (pSrc[(2U * i2)] >> 4U);

    /* xb + xd */
    t1 = (pSrc[(2U * i1)] >> 4U) + (pSrc[(2U * i3)] >> 4U);

    /* ya + yc */
    s1 = (pSrc[(2U * i0) + 1U] >> 4U) + (pSrc[(2U * i2) + 1U] >> 4U);
    /* ya - yc */
    s2 = (pSrc[(2U * i0) + 1U] >> 4U) - (pSrc[(2U * i2) + 1U] >> 4U);

    /* xa' = xa + xb + xc + xd */
    pSrc[2U * i0] = (r1 + t1);
    /* (xa + xc) - (xb + xd) */
    r1 = r1 - t1;
    /* yb + yd */
    t2 = (pSrc[(2U * i1) + 1U] >> 4U) + (pSrc[(2U * i3) + 1U] >> 4U);

    /* ya' = ya + yb + yc + yd */
    pSrc[(2U * i0) + 1U] = (s1 + t2);

    /* (ya + yc) - (yb + yd) */
    s1 = s1 - t2;

    /* yb - yd */
    t1 = (pSrc[(2U * i1) + 1U] >> 4U) - (pSrc[(2U * i3) + 1U] >> 4U);
    /* xb - xd */
    t2 = (pSrc[(2U * i1)] >> 4U) - (pSrc[(2U * i3)] >> 4U);

    /*  index calculation for the coefficients */
    ia2 = 2U * ia1;
    co2 = pCoef[(ia2 * 2U)];
    si2 = pCoef[(ia2 * 2U) + 1U];

    /* xc' = (xa-xb+xc-xd)co2 + (ya-yb+yc-yd)(si2) */
    pSrc[2U * i1] = (((int32_t) (((q63_t) r1 * co2) >> 32)) +
                     ((int32_t) (((q63_t) s1 * si2) >> 32))) << 1U;

    /* yc' = (ya-yb+yc-yd)co2 - (xa-xb+xc-xd)(si2) */
    pSrc[(2U * i1) + 1U] = (((int32_t) (((q63_t) s1 * co2) >> 32)) -
                            ((int32_t) (((q63_t) r1 * si2) >> 32))) << 1U;

    /* (xa - xc) + (yb - yd) */
    r1 = r2 + t1;
    /* (xa - xc) - (yb - yd) */
    r2 = r2 - t1;

    /* (ya - yc) - (xb - xd) */
    s1 = s2 - t2;
    /* (ya - yc) + (xb - xd) */
    s2 = s2 + t2;

    co1 = pCoef[(ia1 * 2U)];
    si1 = pCoef[(ia1 * 2U) + 1U];

    /* xb' = (xa+yb-xc-yd)co1 + (ya-xb-yc+xd)(si1) */
    pSrc[2U * i2] = (((int32_t) (((q63_t) r1 * co1) >> 32)) +
                     ((int32_t) (((q63_t) s1 * si1) >> 32))) << 1U;

    /* yb' = (ya-xb-yc+xd)co1 - (xa+yb-xc-yd)(si1) */
    pSrc[(2U * i2) + 1U] = (((int32_t) (((q63_t) s1 * co1) >> 32)) -
                            ((int32_t) (((q63_t) r1 * si1) >> 32))) << 1U;

    /*  index calculation for the coefficients */
    ia3 = 3U * ia1;
    co3 = pCoef[(ia3 * 2U)];
    si3 = pCoef[(ia3 * 2U) + 1U];

    /* xd' = (xa-yb-xc+yd)co3 + (ya+xb-yc-xd)(si3) */
    pSrc[2U * i3] = (((int32_t) (((q63_t) r2 * co3) >> 32)) +
                     ((int32_t) (((q63_t) s2 * si3) >> 32))) << 1U;

    /* yd' = (ya+xb-yc-xd)co3 - (xa-yb-xc+yd)(si3) */
    pSrc[(2U * i3) + 1U] = (((int32_t) (((q63_t) s2 * co3) >> 32)) -
                            ((int32_t) (((q63_t) r2 * si3) >> 32))) << 1U;

    /*  Twiddle coefficients index modifier */
    ia1 = ia1 + twidCoefModifier;

    /*  Updating input index */
    i0 = i0 + 1U;

  } while (--j);

  /* end of first stage process */

  /* data is in 5.27(q27) format */


  /* start of Middle stages process */


  /* each stage in middle stages provides two down scaling of the input */

  twidCoefModifier <<= 2U;


  for (k = fftLen / 4U; k > 4U; k >>= 2U)
  {
    /*  Initializations for the first stage */
    n1 = n2;
    n2 >>= 2U;
    ia1 = 0U;

    /*  Calculation of first stage */
    for (j = 0U; j <= (n2 - 1U); j++)
    {
      /*  index calculation for the coefficients */
      ia2 = ia1 + ia1;
      ia3 = ia2 + ia1;
      co1 = pCoef[(ia1 * 2U)];
      si1 = pCoef[(ia1 * 2U) + 1U];
      co2 = pCoef[(ia2 * 2U)];
      si2 = pCoef[(ia2 * 2U) + 1U];
      co3 = pCoef[(ia3 * 2U)];
      si3 = pCoef[(ia3 * 2U) + 1U];
      /*  Twiddle coefficients index modifier */
      ia1 = ia1 + twidCoefModifier;

      for (i0 = j; i0 < fftLen; i0 += n1)
      {
        /*  index calculation for the input as, */
        /*  pSrc[i0 + 0], pSrc[i0 + fftLen/4], pSrc[i0 + fftLen/2U], pSrc[i0 + 3fftLen/4] */
        i1 = i0 + n2;
        i2 = i1 + n2;
        i3 = i2 + n2;

        /*  Butterfly implementation */
        /* xa + xc */
        r1 = pSrc[2U * i0] + pSrc[2U * i2];
        /* xa - xc */
        r2 = pSrc[2U * i0] - pSrc[2U * i2];

        /* ya + yc */
        s1 = pSrc[(2U * i0) + 1U] + pSrc[(2U * i2) + 1U];
        /* ya - yc */
        s2 = pSrc[(2U * i0) + 1U] - pSrc[(2U * i2) + 1U];

        /* xb + xd */
        t1 = pSrc[2U * i1] + pSrc[2U * i3];

        /* xa' = xa + xb + xc + xd */
        pSrc[2U * i0] = (r1 + t1) >> 2U;
        /* xa + xc -(xb + xd) */
        r1 = r1 - t1;

        /* yb + yd */
        t2 = pSrc[(2U * i1) + 1U] + pSrc[(2U * i3) + 1U];
        /* ya' = ya + yb + yc + yd */
        pSrc[(2U * i0) + 1U] = (s1 + t2) >> 2U;

        /* (ya + yc) - (yb + yd) */
        s1 = s1 - t2;

        /* (yb - yd) */
        t1 = pSrc[(2U * i1) + 1U] - pSrc[(2U * i3) + 1U];
        /* (xb - xd) */
        t2 = pSrc[2U * i1] - pSrc[2U * i3];

        /* xc' = (xa-xb+xc-xd)co2 + (ya-yb+yc-yd)(si2) */
        pSrc[2U * i1] = (((int32_t) (((q63_t) r1 * co2) >> 32)) +
                         ((int32_t) (((q63_t) s1 * si2) >> 32))) >> 1U;

        /* yc' = (ya-yb+yc-yd)co2 - (xa-xb+xc-xd)(si2) */
        pSrc[(2U * i1) + 1U] = (((int32_t) (((q63_t) s1 * co2) >> 32)) -
                                ((int32_t) (((q63_t) r1 * si2) >> 32))) >> 1U;

        /* (xa - xc) + (yb - yd) */
        r1 = r2 + t1;
        /* (xa - xc) - (yb - yd) */
        r2 = r2 - t1;

        /* (ya - yc) -  (xb - xd) */
        s1 = s2 - t2;
        /* (ya - yc) +  (xb - xd) */
        s2 = s2 + t2;

        /* xb' = (xa+yb-xc-yd)co1 + (ya-xb-yc+xd)(si1) */
        pSrc[2U * i2] = (((int32_t) (((q63_t) r1 * co1) >> 32)) +
                         ((int32_t) (((q63_t) s1 * si1) >> 32))) >> 1U;

        /* yb' = (ya-xb-yc+xd)co1 - (xa+yb-xc-yd)(si1) */
        pSrc[(2U * i2) + 1U] = (((int32_t) (((q63_t) s1 * co1) >> 32)) -
                                ((int32_t) (((q63_t) r1 * si1) >> 32))) >> 1U;

        /* xd' = (xa-yb-xc+yd)co3 + (ya+xb-yc-xd)(si3) */
        pSrc[2U * i3] = (((int32_t) (((q63_t) r2 * co3) >> 32)) +
                         ((int32_t) (((q63_t) s2 * si3) >> 32))) >> 1U;

        /* yd' = (ya+xb-yc-xd)co3 - (xa-yb-xc+yd)(si3) */
        pSrc[(2U * i3) + 1U] = (((int32_t) (((q63_t) s2 * co3) >> 32)) -
                                ((int32_t) (((q63_t) r2 * si3) >> 32))) >> 1U;
      }
    }
    twidCoefModifier <<= 2U;
  }

  /* End of Middle stages process */

  /* data is in 11.21(q21) format for the 1024 point as there are 3 middle stages */
  /* data is in 9.23(q23) format for the 256 point as there are 2 middle stages */
  /* data is in 7.25(q25) format for the 64 point as there are 1 middle stage */
  /* data is in 5.27(q27) format for the 16 point as there are no middle stages */


  /* start of Last stage process */
  /*  Initializations for the last stage */
  j = fftLen >> 2;
  ptr1 = &pSrc[0];

  /*  Calculations of last stage */
  do
  {
    /* Read xa (real), ya(imag) input */
    xa = *ptr1++;
    ya = *ptr1++;

    /* Read xb (real), yb(imag) input */
    xb = *ptr1++;
    yb = *ptr1++;

    /* Read xc (real), yc(imag) input */
    xc = *ptr1++;
    yc = *ptr1++;

    /* Read xc (real), yc(imag) input */
    xd = *ptr1++;
    yd = *ptr1++;

    /* xa' = xa + xb + xc + xd */
    xa_out = xa + xb + xc + xd;

    /* ya' = ya + yb + yc + yd */
    ya_out = ya + yb + yc + yd;

    /* pointer updation for writing */
    ptr1 = ptr1 - 8U;

    /* writing xa' and ya' */
    *ptr1++ = xa_out;
    *ptr1++ = ya_out;

    xc_out = (xa - xb + xc - xd);
    yc_out = (ya - yb + yc - yd);

    /* writing xc' and yc' */
    *ptr1++ = xc_out;
    *ptr1++ = yc_out;

    xb_out = (xa + yb - xc - yd);
    yb_out = (ya - xb - yc + xd);

    /* writing xb' and yb' */
    *ptr1++ = xb_out;
    *ptr1++ = yb_out;

    xd_out = (xa - yb - xc + yd);
    yd_out = (ya + xb - yc - xd);

    /* writing xd' and yd' */
    *ptr1++ = xd_out;
    *ptr1++ = yd_out;


  } while (--j);

  /* output is in 11.21(q21) format for the 1024 point */
  /* output is in 9.23(q23) format for the 256 point */
  /* output is in 7.25(q25) format for the 64 point */
  /* output is in 5.27(q27) format for the 16 point */

  /* End of last stage process */

}


/**
  @brief         Core function for the Q31 CIFFT butterfly process.
  @param[in,out] pSrc             points to the in-place buffer of Q31 data type.
  @param[in]     fftLen           length of the FFT.
  @param[in]     pCoef            points to twiddle coefficient buffer.
  @param[in]     twidCoefModifier twiddle coefficient modifier that supports different size FFTs with the same twiddle factor table.
  @return        none
 */

/*
 * Radix-4 IFFT algorithm used is :
 *
 * CIFFT uses same twiddle coefficients as CFFT Function
 *  x[k] = x[n] + (j)k * x[n + fftLen/4] + (-1)k * x[n+fftLen/2] + (-j)k * x[n+3*fftLen/4]
 *
 *
 * IFFT is implemented with following changes in equations from FFT
 *
 * Input real and imaginary data:
 * x(n) = xa + j * ya
 * x(n+N/4 ) = xb + j * yb
 * x(n+N/2 ) = xc + j * yc
 * x(n+3N 4) = xd + j * yd
 *
 *
 * Output real and imaginary data:
 * x(4r) = xa'+ j * ya'
 * x(4r+1) = xb'+ j * yb'
 * x(4r+2) = xc'+ j * yc'
 * x(4r+3) = xd'+ j * yd'
 *
 *
 * Twiddle factors for radix-4 IFFT:
 * Wn = co1 + j * (si1)
 * W2n = co2 + j * (si2)
 * W3n = co3 + j * (si3)
 
 * The real and imaginary output values for the radix-4 butterfly are
 * xa' = xa + xb + xc + xd
 * ya' = ya + yb + yc + yd
 * xb' = (xa-yb-xc+yd)* co1 - (ya+xb-yc-xd)* (si1)
 * yb' = (ya+xb-yc-xd)* co1 + (xa-yb-xc+yd)* (si1)
 * xc' = (xa-xb+xc-xd)* co2 - (ya-yb+yc-yd)* (si2)
 * yc' = (ya-yb+yc-yd)* co2 + (xa-xb+xc-xd)* (si2)
 * xd' = (xa+yb-xc-yd)* co3 - (ya-xb-yc+xd)* (si3)
 * yd' = (ya-xb-yc+xd)* co3 + (xa+yb-xc-yd)* (si3)
 *
 */

void arm_radix4_butterfly_inverse_q31(
        q31_t * pSrc,
        uint32_t fftLen,
  const q31_t * pCoef,
        uint32_t twidCoefModifier)
{
        uint32_t n1, n2, ia1, ia2, ia3, i0, i1, i2, i3, j, k;
        q31_t t1, t2, r1, r2, s1, s2, co1, co2, co3, si1, si2, si3;
        q31_t xa, xb, xc, xd;
        q31_t ya, yb, yc, yd;
        q31_t xa_out, xb_out, xc_out, xd_out;
        q31_t ya_out, yb_out, yc_out, yd_out;
        
        q31_t *ptr1;

  /* input is be 1.31(q31) format for all FFT sizes */
  /* Total process is divided into three stages */
  /* process first stage, middle stages, & last stage */

  /* Start of first stage process */

  /* Initializations for the first stage */
  n2 = fftLen;
  n1 = n2;
  /* n2 = fftLen/4 */
  n2 >>= 2U;
  i0 = 0U;
  ia1 = 0U;

  j = n2;

  do
  {
    /* input is in 1.31(q31) format and provide 4 guard bits for the input */

    /*  index calculation for the input as, */
    /*  pSrc[i0 + 0], pSrc[i0 + fftLen/4], pSrc[i0 + fftLen/2U], pSrc[i0 + 3fftLen/4] */
    i1 = i0 + n2;
    i2 = i1 + n2;
    i3 = i2 + n2;

    /*  Butterfly implementation */
    /* xa + xc */
    r1 = (pSrc[2U * i0] >> 4U) + (pSrc[2U * i2] >> 4U);
    /* xa - xc */
    r2 = (pSrc[2U * i0] >> 4U) - (pSrc[2U * i2] >> 4U);

    /* xb + xd */
    t1 = (pSrc[2U * i1] >> 4U) + (pSrc[2U * i3] >> 4U);

    /* ya + yc */
    s1 = (pSrc[(2U * i0) + 1U] >> 4U) + (pSrc[(2U * i2) + 1U] >> 4U);
    /* ya - yc */
    s2 = (pSrc[(2U * i0) + 1U] >> 4U) - (pSrc[(2U * i2) + 1U] >> 4U);

    /* xa' = xa + xb + xc + xd */
    pSrc[2U * i0] = (r1 + t1);
    /* (xa + xc) - (xb + xd) */
    r1 = r1 - t1;
    /* yb + yd */
    t2 = (pSrc[(2U * i1) + 1U] >> 4U) + (pSrc[(2U * i3) + 1U] >> 4U);
    /* ya' = ya + yb + yc + yd */
    pSrc[(2U * i0) + 1U] = (s1 + t2);

    /* (ya + yc) - (yb + yd) */
    s1 = s1 - t2;

    /* yb - yd */
    t1 = (pSrc[(2U * i1) + 1U] >> 4U) - (pSrc[(2U * i3) + 1U] >> 4U);
    /* xb - xd */
    t2 = (pSrc[2U * i1] >> 4U) - (pSrc[2U * i3] >> 4U);

    /*  index calculation for the coefficients */
    ia2 = 2U * ia1;
    co2 = pCoef[ia2 * 2U];
    si2 = pCoef[(ia2 * 2U) + 1U];

    /* xc' = (xa-xb+xc-xd)co2 - (ya-yb+yc-yd)(si2) */
    pSrc[2U * i1] = (((int32_t) (((q63_t) r1 * co2) >> 32)) -
                     ((int32_t) (((q63_t) s1 * si2) >> 32))) << 1U;

    /* yc' = (ya-yb+yc-yd)co2 + (xa-xb+xc-xd)(si2) */
    pSrc[2U * i1 + 1U] = (((int32_t) (((q63_t) s1 * co2) >> 32)) +
                          ((int32_t) (((q63_t) r1 * si2) >> 32))) << 1U;

    /* (xa - xc) - (yb - yd) */
    r1 = r2 - t1;
    /* (xa - xc) + (yb - yd) */
    r2 = r2 + t1;

    /* (ya - yc) + (xb - xd) */
    s1 = s2 + t2;
    /* (ya - yc) - (xb - xd) */
    s2 = s2 - t2;

    co1 = pCoef[ia1 * 2U];
    si1 = pCoef[(ia1 * 2U) + 1U];

    /* xb' = (xa+yb-xc-yd)co1 - (ya-xb-yc+xd)(si1) */
    pSrc[2U * i2] = (((int32_t) (((q63_t) r1 * co1) >> 32)) -
                     ((int32_t) (((q63_t) s1 * si1) >> 32))) << 1U;

    /* yb' = (ya-xb-yc+xd)co1 + (xa+yb-xc-yd)(si1) */
    pSrc[(2U * i2) + 1U] = (((int32_t) (((q63_t) s1 * co1) >> 32)) +
                            ((int32_t) (((q63_t) r1 * si1) >> 32))) << 1U;

    /*  index calculation for the coefficients */
    ia3 = 3U * ia1;
    co3 = pCoef[ia3 * 2U];
    si3 = pCoef[(ia3 * 2U) + 1U];

    /* xd' = (xa-yb-xc+yd)co3 - (ya+xb-yc-xd)(si3) */
    pSrc[2U * i3] = (((int32_t) (((q63_t) r2 * co3) >> 32)) -
                     ((int32_t) (((q63_t) s2 * si3) >> 32))) << 1U;

    /* yd' = (ya+xb-yc-xd)co3 + (xa-yb-xc+yd)(si3) */
    pSrc[(2U * i3) + 1U] = (((int32_t) (((q63_t) s2 * co3) >> 32)) +
                            ((int32_t) (((q63_t) r2 * si3) >> 32))) << 1U;

    /*  Twiddle coefficients index modifier */
    ia1 = ia1 + twidCoefModifier;

    /*  Updating input index */
    i0 = i0 + 1U;

  } while (--j);

  /* data is in 5.27(q27) format */
  /* each stage provides two down scaling of the input */


  /* Start of Middle stages process */

  twidCoefModifier <<= 2U;

  /*  Calculation of second stage to excluding last stage */
  for (k = fftLen / 4U; k > 4U; k >>= 2U)
  {
    /*  Initializations for the first stage */
    n1 = n2;
    n2 >>= 2U;
    ia1 = 0U;

    for (j = 0; j <= (n2 - 1U); j++)
    {
      /*  index calculation for the coefficients */
      ia2 = ia1 + ia1;
      ia3 = ia2 + ia1;
      co1 = pCoef[(ia1 * 2U)];
      si1 = pCoef[(ia1 * 2U) + 1U];
      co2 = pCoef[(ia2 * 2U)];
      si2 = pCoef[(ia2 * 2U) + 1U];
      co3 = pCoef[(ia3 * 2U)];
      si3 = pCoef[(ia3 * 2U) + 1U];
      /*  Twiddle coefficients index modifier */
      ia1 = ia1 + twidCoefModifier;

      for (i0 = j; i0 < fftLen; i0 += n1)
      {
        /*  index calculation for the input as, */
        /*  pSrc[i0 + 0], pSrc[i0 + fftLen/4], pSrc[i0 + fftLen/2U], pSrc[i0 + 3fftLen/4] */
        i1 = i0 + n2;
        i2 = i1 + n2;
        i3 = i2 + n2;

        /*  Butterfly implementation */
        /* xa + xc */
        r1 = pSrc[2U * i0] + pSrc[2U * i2];
        /* xa - xc */
        r2 = pSrc[2U * i0] - pSrc[2U * i2];

        /* ya + yc */
        s1 = pSrc[(2U * i0) + 1U] + pSrc[(2U * i2) + 1U];
        /* ya - yc */
        s2 = pSrc[(2U * i0) + 1U] - pSrc[(2U * i2) + 1U];

        /* xb + xd */
        t1 = pSrc[2U * i1] + pSrc[2U * i3];

        /* xa' = xa + xb + xc + xd */
        pSrc[2U * i0] = (r1 + t1) >> 2U;
        /* xa + xc -(xb + xd) */
        r1 = r1 - t1;
        /* yb + yd */
        t2 = pSrc[(2U * i1) + 1U] + pSrc[(2U * i3) + 1U];
        /* ya' = ya + yb + yc + yd */
        pSrc[(2U * i0) + 1U] = (s1 + t2) >> 2U;

        /* (ya + yc) - (yb + yd) */
        s1 = s1 - t2;

        /* (yb - yd) */
        t1 = pSrc[(2U * i1) + 1U] - pSrc[(2U * i3) + 1U];
        /* (xb - xd) */
        t2 = pSrc[2U * i1] - pSrc[2U * i3];

        /* xc' = (xa-xb+xc-xd)co2 - (ya-yb+yc-yd)(si2) */
        pSrc[2U * i1] = (((int32_t) (((q63_t) r1 * co2) >> 32U)) -
                         ((int32_t) (((q63_t) s1 * si2) >> 32U))) >> 1U;

        /* yc' = (ya-yb+yc-yd)co2 + (xa-xb+xc-xd)(si2) */
        pSrc[(2U * i1) + 1U] = (((int32_t) (((q63_t) s1 * co2) >> 32U)) +
                                ((int32_t) (((q63_t) r1 * si2) >> 32U))) >> 1U;

        /* (xa - xc) - (yb - yd) */
        r1 = r2 - t1;
        /* (xa - xc) + (yb - yd) */
        r2 = r2 + t1;

        /* (ya - yc) +  (xb - xd) */
        s1 = s2 + t2;
        /* (ya - yc) -  (xb - xd) */
        s2 = s2 - t2;

        /* xb' = (xa+yb-xc-yd)co1 - (ya-xb-yc+xd)(si1) */
        pSrc[2U * i2] = (((int32_t) (((q63_t) r1 * co1) >> 32)) -
                         ((int32_t) (((q63_t) s1 * si1) >> 32))) >> 1U;

        /* yb' = (ya-xb-yc+xd)co1 + (xa+yb-xc-yd)(si1) */
        pSrc[(2U * i2) + 1U] = (((int32_t) (((q63_t) s1 * co1) >> 32)) +
                                ((int32_t) (((q63_t) r1 * si1) >> 32))) >> 1U;

        /* xd' = (xa-yb-xc+yd)co3 - (ya+xb-yc-xd)(si3) */
        pSrc[(2U * i3)] = (((int32_t) (((q63_t) r2 * co3) >> 32)) -
                           ((int32_t) (((q63_t) s2 * si3) >> 32))) >> 1U;

        /* yd' = (ya+xb-yc-xd)co3 + (xa-yb-xc+yd)(si3) */
        pSrc[(2U * i3) + 1U] = (((int32_t) (((q63_t) s2 * co3) >> 32)) +
                                ((int32_t) (((q63_t) r2 * si3) >> 32))) >> 1U;
      }
    }
    twidCoefModifier <<= 2U;
  }

  /* End of Middle stages process */

  /* data is in 11.21(q21) format for the 1024 point as there are 3 middle stages */
  /* data is in 9.23(q23) format for the 256 point as there are 2 middle stages */
  /* data is in 7.25(q25) format for the 64 point as there are 1 middle stage */
  /* data is in 5.27(q27) format for the 16 point as there are no middle stages */


  /* Start of last stage process */


  /*  Initializations for the last stage */
  j = fftLen >> 2;
  ptr1 = &pSrc[0];

  /*  Calculations of last stage */
  do
  {
    /* Read xa (real), ya(imag) input */
    xa = *ptr1++;
    ya = *ptr1++;

    /* Read xb (real), yb(imag) input */
    xb = *ptr1++;
    yb = *ptr1++;

    /* Read xc (real), yc(imag) input */
    xc = *ptr1++;
    yc = *ptr1++;

    /* Read xc (real), yc(imag) input */
    xd = *ptr1++;
    yd = *ptr1++;

    /* xa' = xa + xb + xc + xd */
    xa_out = xa + xb + xc + xd;

    /* ya' = ya + yb + yc + yd */
    ya_out = ya + yb + yc + yd;

    /* pointer updation for writing */
    ptr1 = ptr1 - 8U;

    /* writing xa' and ya' */
    *ptr1++ = xa_out;
    *ptr1++ = ya_out;

    xc_out = (xa - xb + xc - xd);
    yc_out = (ya - yb + yc - yd);

    /* writing xc' and yc' */
    *ptr1++ = xc_out;
    *ptr1++ = yc_out;

    xb_out = (xa - yb - xc + yd);
    yb_out = (ya + xb - yc - xd);

    /* writing xb' and yb' */
    *ptr1++ = xb_out;
    *ptr1++ = yb_out;

    xd_out = (xa + yb - xc - yd);
    yd_out = (ya - xb - yc + xd);

    /* writing xd' and yd' */
    *ptr1++ = xd_out;
    *ptr1++ = yd_out;

  } while (--j);

  /* output is in 11.21(q21) format for the 1024 point */
  /* output is in 9.23(q23) format for the 256 point */
  /* output is in 7.25(q25) format for the 64 point */
  /* output is in 5.27(q27) format for the 16 point */

  /* End of last stage process */
}