aboutsummaryrefslogtreecommitdiff
path: root/vendor/github.com/klauspost/compress/huff0/decompress_amd64.s
blob: 6c65c6e2b25ccfc7ed663e21078807c56303902e (plain)
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
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
// Code generated by command: go run gen.go -out ../decompress_amd64.s -pkg=huff0. DO NOT EDIT.

//go:build amd64 && !appengine && !noasm && gc
// +build amd64,!appengine,!noasm,gc

// func decompress4x_main_loop_amd64(ctx *decompress4xContext)
TEXT ·decompress4x_main_loop_amd64(SB), $8-8
	XORQ DX, DX

	// Preload values
	MOVQ    ctx+0(FP), AX
	MOVBQZX 32(AX), SI
	MOVQ    40(AX), DI
	MOVQ    DI, BX
	MOVQ    72(AX), CX
	MOVQ    CX, (SP)
	MOVQ    48(AX), R8
	MOVQ    56(AX), R9
	MOVQ    (AX), R10
	MOVQ    8(AX), R11
	MOVQ    16(AX), R12
	MOVQ    24(AX), R13

	// Main loop
main_loop:
	MOVQ  BX, DI
	CMPQ  DI, (SP)
	SETGE DL

	// br0.fillFast32()
	MOVQ    32(R10), R14
	MOVBQZX 40(R10), R15
	CMPQ    R15, $0x20
	JBE     skip_fill0
	MOVQ    24(R10), AX
	SUBQ    $0x20, R15
	SUBQ    $0x04, AX
	MOVQ    (R10), BP

	// b.value |= uint64(low) << (b.bitsRead & 63)
	MOVL (AX)(BP*1), BP
	MOVQ R15, CX
	SHLQ CL, BP
	MOVQ AX, 24(R10)
	ORQ  BP, R14

	// exhausted = exhausted || (br0.off < 4)
	CMPQ  AX, $0x04
	SETLT AL
	ORB   AL, DL

skip_fill0:
	// val0 := br0.peekTopBits(peekBits)
	MOVQ R14, BP
	MOVQ SI, CX
	SHRQ CL, BP

	// v0 := table[val0&mask]
	MOVW (R9)(BP*2), CX

	// br0.advance(uint8(v0.entry)
	MOVB CH, AL
	SHLQ CL, R14
	ADDB CL, R15

	// val1 := br0.peekTopBits(peekBits)
	MOVQ SI, CX
	MOVQ R14, BP
	SHRQ CL, BP

	// v1 := table[val1&mask]
	MOVW (R9)(BP*2), CX

	// br0.advance(uint8(v1.entry))
	MOVB CH, AH
	SHLQ CL, R14
	ADDB CL, R15

	// these two writes get coalesced
	// out[id * dstEvery + 0] = uint8(v0.entry >> 8)
	// out[id * dstEvery + 1] = uint8(v1.entry >> 8)
	MOVW AX, (DI)

	// update the bitrader reader structure
	MOVQ R14, 32(R10)
	MOVB R15, 40(R10)
	ADDQ R8, DI

	// br1.fillFast32()
	MOVQ    32(R11), R14
	MOVBQZX 40(R11), R15
	CMPQ    R15, $0x20
	JBE     skip_fill1
	MOVQ    24(R11), AX
	SUBQ    $0x20, R15
	SUBQ    $0x04, AX
	MOVQ    (R11), BP

	// b.value |= uint64(low) << (b.bitsRead & 63)
	MOVL (AX)(BP*1), BP
	MOVQ R15, CX
	SHLQ CL, BP
	MOVQ AX, 24(R11)
	ORQ  BP, R14

	// exhausted = exhausted || (br1.off < 4)
	CMPQ  AX, $0x04
	SETLT AL
	ORB   AL, DL

skip_fill1:
	// val0 := br1.peekTopBits(peekBits)
	MOVQ R14, BP
	MOVQ SI, CX
	SHRQ CL, BP

	// v0 := table[val0&mask]
	MOVW (R9)(BP*2), CX

	// br1.advance(uint8(v0.entry)
	MOVB CH, AL
	SHLQ CL, R14
	ADDB CL, R15

	// val1 := br1.peekTopBits(peekBits)
	MOVQ SI, CX
	MOVQ R14, BP
	SHRQ CL, BP

	// v1 := table[val1&mask]
	MOVW (R9)(BP*2), CX

	// br1.advance(uint8(v1.entry))
	MOVB CH, AH
	SHLQ CL, R14
	ADDB CL, R15

	// these two writes get coalesced
	// out[id * dstEvery + 0] = uint8(v0.entry >> 8)
	// out[id * dstEvery + 1] = uint8(v1.entry >> 8)
	MOVW AX, (DI)

	// update the bitrader reader structure
	MOVQ R14, 32(R11)
	MOVB R15, 40(R11)
	ADDQ R8, DI

	// br2.fillFast32()
	MOVQ    32(R12), R14
	MOVBQZX 40(R12), R15
	CMPQ    R15, $0x20
	JBE     skip_fill2
	MOVQ    24(R12), AX
	SUBQ    $0x20, R15
	SUBQ    $0x04, AX
	MOVQ    (R12), BP

	// b.value |= uint64(low) << (b.bitsRead & 63)
	MOVL (AX)(BP*1), BP
	MOVQ R15, CX
	SHLQ CL, BP
	MOVQ AX, 24(R12)
	ORQ  BP, R14

	// exhausted = exhausted || (br2.off < 4)
	CMPQ  AX, $0x04
	SETLT AL
	ORB   AL, DL

skip_fill2:
	// val0 := br2.peekTopBits(peekBits)
	MOVQ R14, BP
	MOVQ SI, CX
	SHRQ CL, BP

	// v0 := table[val0&mask]
	MOVW (R9)(BP*2), CX

	// br2.advance(uint8(v0.entry)
	MOVB CH, AL
	SHLQ CL, R14
	ADDB CL, R15

	// val1 := br2.peekTopBits(peekBits)
	MOVQ SI, CX
	MOVQ R14, BP
	SHRQ CL, BP

	// v1 := table[val1&mask]
	MOVW (R9)(BP*2), CX

	// br2.advance(uint8(v1.entry))
	MOVB CH, AH
	SHLQ CL, R14
	ADDB CL, R15

	// these two writes get coalesced
	// out[id * dstEvery + 0] = uint8(v0.entry >> 8)
	// out[id * dstEvery + 1] = uint8(v1.entry >> 8)
	MOVW AX, (DI)

	// update the bitrader reader structure
	MOVQ R14, 32(R12)
	MOVB R15, 40(R12)
	ADDQ R8, DI

	// br3.fillFast32()
	MOVQ    32(R13), R14
	MOVBQZX 40(R13), R15
	CMPQ    R15, $0x20
	JBE     skip_fill3
	MOVQ    24(R13), AX
	SUBQ    $0x20, R15
	SUBQ    $0x04, AX
	MOVQ    (R13), BP

	// b.value |= uint64(low) << (b.bitsRead & 63)
	MOVL (AX)(BP*1), BP
	MOVQ R15, CX
	SHLQ CL, BP
	MOVQ AX, 24(R13)
	ORQ  BP, R14

	// exhausted = exhausted || (br3.off < 4)
	CMPQ  AX, $0x04
	SETLT AL
	ORB   AL, DL

skip_fill3:
	// val0 := br3.peekTopBits(peekBits)
	MOVQ R14, BP
	MOVQ SI, CX
	SHRQ CL, BP

	// v0 := table[val0&mask]
	MOVW (R9)(BP*2), CX

	// br3.advance(uint8(v0.entry)
	MOVB CH, AL
	SHLQ CL, R14
	ADDB CL, R15

	// val1 := br3.peekTopBits(peekBits)
	MOVQ SI, CX
	MOVQ R14, BP
	SHRQ CL, BP

	// v1 := table[val1&mask]
	MOVW (R9)(BP*2), CX

	// br3.advance(uint8(v1.entry))
	MOVB CH, AH
	SHLQ CL, R14
	ADDB CL, R15

	// these two writes get coalesced
	// out[id * dstEvery + 0] = uint8(v0.entry >> 8)
	// out[id * dstEvery + 1] = uint8(v1.entry >> 8)
	MOVW AX, (DI)

	// update the bitrader reader structure
	MOVQ  R14, 32(R13)
	MOVB  R15, 40(R13)
	ADDQ  $0x02, BX
	TESTB DL, DL
	JZ    main_loop
	MOVQ  ctx+0(FP), AX
	MOVQ  40(AX), CX
	MOVQ  BX, DX
	SUBQ  CX, DX
	SHLQ  $0x02, DX
	MOVQ  DX, 64(AX)
	RET

// func decompress4x_8b_main_loop_amd64(ctx *decompress4xContext)
TEXT ·decompress4x_8b_main_loop_amd64(SB), $16-8
	XORQ DX, DX

	// Preload values
	MOVQ    ctx+0(FP), CX
	MOVBQZX 32(CX), BX
	MOVQ    40(CX), SI
	MOVQ    SI, (SP)
	MOVQ    72(CX), DX
	MOVQ    DX, 8(SP)
	MOVQ    48(CX), DI
	MOVQ    56(CX), R8
	MOVQ    (CX), R9
	MOVQ    8(CX), R10
	MOVQ    16(CX), R11
	MOVQ    24(CX), R12

	// Main loop
main_loop:
	MOVQ  (SP), SI
	CMPQ  SI, 8(SP)
	SETGE DL

	// br1000.fillFast32()
	MOVQ    32(R9), R13
	MOVBQZX 40(R9), R14
	CMPQ    R14, $0x20
	JBE     skip_fill1000
	MOVQ    24(R9), R15
	SUBQ    $0x20, R14
	SUBQ    $0x04, R15
	MOVQ    (R9), BP

	// b.value |= uint64(low) << (b.bitsRead & 63)
	MOVL (R15)(BP*1), BP
	MOVQ R14, CX
	SHLQ CL, BP
	MOVQ R15, 24(R9)
	ORQ  BP, R13

	// exhausted = exhausted || (br1000.off < 4)
	CMPQ  R15, $0x04
	SETLT AL
	ORB   AL, DL

skip_fill1000:
	// val0 := br0.peekTopBits(peekBits)
	MOVQ R13, R15
	MOVQ BX, CX
	SHRQ CL, R15

	// v0 := table[val0&mask]
	MOVW (R8)(R15*2), CX

	// br0.advance(uint8(v0.entry)
	MOVB CH, AL
	SHLQ CL, R13
	ADDB CL, R14

	// val1 := br0.peekTopBits(peekBits)
	MOVQ R13, R15
	MOVQ BX, CX
	SHRQ CL, R15

	// v1 := table[val0&mask]
	MOVW (R8)(R15*2), CX

	// br0.advance(uint8(v1.entry)
	MOVB   CH, AH
	SHLQ   CL, R13
	ADDB   CL, R14
	BSWAPL AX

	// val2 := br0.peekTopBits(peekBits)
	MOVQ R13, R15
	MOVQ BX, CX
	SHRQ CL, R15

	// v2 := table[val0&mask]
	MOVW (R8)(R15*2), CX

	// br0.advance(uint8(v2.entry)
	MOVB CH, AH
	SHLQ CL, R13
	ADDB CL, R14

	// val3 := br0.peekTopBits(peekBits)
	MOVQ R13, R15
	MOVQ BX, CX
	SHRQ CL, R15

	// v3 := table[val0&mask]
	MOVW (R8)(R15*2), CX

	// br0.advance(uint8(v3.entry)
	MOVB   CH, AL
	SHLQ   CL, R13
	ADDB   CL, R14
	BSWAPL AX

	// these four writes get coalesced
	// out[id * dstEvery + 0] = uint8(v0.entry >> 8)
	// out[id * dstEvery + 1] = uint8(v1.entry >> 8)
	// out[id * dstEvery + 3] = uint8(v2.entry >> 8)
	// out[id * dstEvery + 4] = uint8(v3.entry >> 8)
	MOVL AX, (SI)

	// update the bitreader reader structure
	MOVQ R13, 32(R9)
	MOVB R14, 40(R9)
	ADDQ DI, SI

	// br1001.fillFast32()
	MOVQ    32(R10), R13
	MOVBQZX 40(R10), R14
	CMPQ    R14, $0x20
	JBE     skip_fill1001
	MOVQ    24(R10), R15
	SUBQ    $0x20, R14
	SUBQ    $0x04, R15
	MOVQ    (R10), BP

	// b.value |= uint64(low) << (b.bitsRead & 63)
	MOVL (R15)(BP*1), BP
	MOVQ R14, CX
	SHLQ CL, BP
	MOVQ R15, 24(R10)
	ORQ  BP, R13

	// exhausted = exhausted || (br1001.off < 4)
	CMPQ  R15, $0x04
	SETLT AL
	ORB   AL, DL

skip_fill1001:
	// val0 := br1.peekTopBits(peekBits)
	MOVQ R13, R15
	MOVQ BX, CX
	SHRQ CL, R15

	// v0 := table[val0&mask]
	MOVW (R8)(R15*2), CX

	// br1.advance(uint8(v0.entry)
	MOVB CH, AL
	SHLQ CL, R13
	ADDB CL, R14

	// val1 := br1.peekTopBits(peekBits)
	MOVQ R13, R15
	MOVQ BX, CX
	SHRQ CL, R15

	// v1 := table[val0&mask]
	MOVW (R8)(R15*2), CX

	// br1.advance(uint8(v1.entry)
	MOVB   CH, AH
	SHLQ   CL, R13
	ADDB   CL, R14
	BSWAPL AX

	// val2 := br1.peekTopBits(peekBits)
	MOVQ R13, R15
	MOVQ BX, CX
	SHRQ CL, R15

	// v2 := table[val0&mask]
	MOVW (R8)(R15*2), CX

	// br1.advance(uint8(v2.entry)
	MOVB CH, AH
	SHLQ CL, R13
	ADDB CL, R14

	// val3 := br1.peekTopBits(peekBits)
	MOVQ R13, R15
	MOVQ BX, CX
	SHRQ CL, R15

	// v3 := table[val0&mask]
	MOVW (R8)(R15*2), CX

	// br1.advance(uint8(v3.entry)
	MOVB   CH, AL
	SHLQ   CL, R13
	ADDB   CL, R14
	BSWAPL AX

	// these four writes get coalesced
	// out[id * dstEvery + 0] = uint8(v0.entry >> 8)
	// out[id * dstEvery + 1] = uint8(v1.entry >> 8)
	// out[id * dstEvery + 3] = uint8(v2.entry >> 8)
	// out[id * dstEvery + 4] = uint8(v3.entry >> 8)
	MOVL AX, (SI)

	// update the bitreader reader structure
	MOVQ R13, 32(R10)
	MOVB R14, 40(R10)
	ADDQ DI, SI

	// br1002.fillFast32()
	MOVQ    32(R11), R13
	MOVBQZX 40(R11), R14
	CMPQ    R14, $0x20
	JBE     skip_fill1002
	MOVQ    24(R11), R15
	SUBQ    $0x20, R14
	SUBQ    $0x04, R15
	MOVQ    (R11), BP

	// b.value |= uint64(low) << (b.bitsRead & 63)
	MOVL (R15)(BP*1), BP
	MOVQ R14, CX
	SHLQ CL, BP
	MOVQ R15, 24(R11)
	ORQ  BP, R13

	// exhausted = exhausted || (br1002.off < 4)
	CMPQ  R15, $0x04
	SETLT AL
	ORB   AL, DL

skip_fill1002:
	// val0 := br2.peekTopBits(peekBits)
	MOVQ R13, R15
	MOVQ BX, CX
	SHRQ CL, R15

	// v0 := table[val0&mask]
	MOVW (R8)(R15*2), CX

	// br2.advance(uint8(v0.entry)
	MOVB CH, AL
	SHLQ CL, R13
	ADDB CL, R14

	// val1 := br2.peekTopBits(peekBits)
	MOVQ R13, R15
	MOVQ BX, CX
	SHRQ CL, R15

	// v1 := table[val0&mask]
	MOVW (R8)(R15*2), CX

	// br2.advance(uint8(v1.entry)
	MOVB   CH, AH
	SHLQ   CL, R13
	ADDB   CL, R14
	BSWAPL AX

	// val2 := br2.peekTopBits(peekBits)
	MOVQ R13, R15
	MOVQ BX, CX
	SHRQ CL, R15

	// v2 := table[val0&mask]
	MOVW (R8)(R15*2), CX

	// br2.advance(uint8(v2.entry)
	MOVB CH, AH
	SHLQ CL, R13
	ADDB CL, R14

	// val3 := br2.peekTopBits(peekBits)
	MOVQ R13, R15
	MOVQ BX, CX
	SHRQ CL, R15

	// v3 := table[val0&mask]
	MOVW (R8)(R15*2), CX

	// br2.advance(uint8(v3.entry)
	MOVB   CH, AL
	SHLQ   CL, R13
	ADDB   CL, R14
	BSWAPL AX

	// these four writes get coalesced
	// out[id * dstEvery + 0] = uint8(v0.entry >> 8)
	// out[id * dstEvery + 1] = uint8(v1.entry >> 8)
	// out[id * dstEvery + 3] = uint8(v2.entry >> 8)
	// out[id * dstEvery + 4] = uint8(v3.entry >> 8)
	MOVL AX, (SI)

	// update the bitreader reader structure
	MOVQ R13, 32(R11)
	MOVB R14, 40(R11)
	ADDQ DI, SI

	// br1003.fillFast32()
	MOVQ    32(R12), R13
	MOVBQZX 40(R12), R14
	CMPQ    R14, $0x20
	JBE     skip_fill1003
	MOVQ    24(R12), R15
	SUBQ    $0x20, R14
	SUBQ    $0x04, R15
	MOVQ    (R12), BP

	// b.value |= uint64(low) << (b.bitsRead & 63)
	MOVL (R15)(BP*1), BP
	MOVQ R14, CX
	SHLQ CL, BP
	MOVQ R15, 24(R12)
	ORQ  BP, R13

	// exhausted = exhausted || (br1003.off < 4)
	CMPQ  R15, $0x04
	SETLT AL
	ORB   AL, DL

skip_fill1003:
	// val0 := br3.peekTopBits(peekBits)
	MOVQ R13, R15
	MOVQ BX, CX
	SHRQ CL, R15

	// v0 := table[val0&mask]
	MOVW (R8)(R15*2), CX

	// br3.advance(uint8(v0.entry)
	MOVB CH, AL
	SHLQ CL, R13
	ADDB CL, R14

	// val1 := br3.peekTopBits(peekBits)
	MOVQ R13, R15
	MOVQ BX, CX
	SHRQ CL, R15

	// v1 := table[val0&mask]
	MOVW (R8)(R15*2), CX

	// br3.advance(uint8(v1.entry)
	MOVB   CH, AH
	SHLQ   CL, R13
	ADDB   CL, R14
	BSWAPL AX

	// val2 := br3.peekTopBits(peekBits)
	MOVQ R13, R15
	MOVQ BX, CX
	SHRQ CL, R15

	// v2 := table[val0&mask]
	MOVW (R8)(R15*2), CX

	// br3.advance(uint8(v2.entry)
	MOVB CH, AH
	SHLQ CL, R13
	ADDB CL, R14

	// val3 := br3.peekTopBits(peekBits)
	MOVQ R13, R15
	MOVQ BX, CX
	SHRQ CL, R15

	// v3 := table[val0&mask]
	MOVW (R8)(R15*2), CX

	// br3.advance(uint8(v3.entry)
	MOVB   CH, AL
	SHLQ   CL, R13
	ADDB   CL, R14
	BSWAPL AX

	// these four writes get coalesced
	// out[id * dstEvery + 0] = uint8(v0.entry >> 8)
	// out[id * dstEvery + 1] = uint8(v1.entry >> 8)
	// out[id * dstEvery + 3] = uint8(v2.entry >> 8)
	// out[id * dstEvery + 4] = uint8(v3.entry >> 8)
	MOVL AX, (SI)

	// update the bitreader reader structure
	MOVQ  R13, 32(R12)
	MOVB  R14, 40(R12)
	ADDQ  $0x04, (SP)
	TESTB DL, DL
	JZ    main_loop
	MOVQ  ctx+0(FP), AX
	MOVQ  40(AX), CX
	MOVQ  (SP), DX
	SUBQ  CX, DX
	SHLQ  $0x02, DX
	MOVQ  DX, 64(AX)
	RET

// func decompress1x_main_loop_amd64(ctx *decompress1xContext)
TEXT ·decompress1x_main_loop_amd64(SB), $0-8
	MOVQ    ctx+0(FP), CX
	MOVQ    16(CX), DX
	MOVQ    24(CX), BX
	CMPQ    BX, $0x04
	JB      error_max_decoded_size_exeeded
	LEAQ    (DX)(BX*1), BX
	MOVQ    (CX), SI
	MOVQ    (SI), R8
	MOVQ    24(SI), R9
	MOVQ    32(SI), R10
	MOVBQZX 40(SI), R11
	MOVQ    32(CX), SI
	MOVBQZX 8(CX), DI
	JMP     loop_condition

main_loop:
	// Check if we have room for 4 bytes in the output buffer
	LEAQ 4(DX), CX
	CMPQ CX, BX
	JGE  error_max_decoded_size_exeeded

	// Decode 4 values
	CMPQ R11, $0x20
	JL   bitReader_fillFast_1_end
	SUBQ $0x20, R11
	SUBQ $0x04, R9
	MOVL (R8)(R9*1), R12
	MOVQ R11, CX
	SHLQ CL, R12
	ORQ  R12, R10

bitReader_fillFast_1_end:
	MOVQ    DI, CX
	MOVQ    R10, R12
	SHRQ    CL, R12
	MOVW    (SI)(R12*2), CX
	MOVB    CH, AL
	MOVBQZX CL, CX
	ADDQ    CX, R11
	SHLQ    CL, R10
	MOVQ    DI, CX
	MOVQ    R10, R12
	SHRQ    CL, R12
	MOVW    (SI)(R12*2), CX
	MOVB    CH, AH
	MOVBQZX CL, CX
	ADDQ    CX, R11
	SHLQ    CL, R10
	BSWAPL  AX
	CMPQ    R11, $0x20
	JL      bitReader_fillFast_2_end
	SUBQ    $0x20, R11
	SUBQ    $0x04, R9
	MOVL    (R8)(R9*1), R12
	MOVQ    R11, CX
	SHLQ    CL, R12
	ORQ     R12, R10

bitReader_fillFast_2_end:
	MOVQ    DI, CX
	MOVQ    R10, R12
	SHRQ    CL, R12
	MOVW    (SI)(R12*2), CX
	MOVB    CH, AH
	MOVBQZX CL, CX
	ADDQ    CX, R11
	SHLQ    CL, R10
	MOVQ    DI, CX
	MOVQ    R10, R12
	SHRQ    CL, R12
	MOVW    (SI)(R12*2), CX
	MOVB    CH, AL
	MOVBQZX CL, CX
	ADDQ    CX, R11
	SHLQ    CL, R10
	BSWAPL  AX

	// Store the decoded values
	MOVL AX, (DX)
	ADDQ $0x04, DX

loop_condition:
	CMPQ R9, $0x08
	JGE  main_loop

	// Update ctx structure
	MOVQ ctx+0(FP), AX
	MOVQ DX, CX
	MOVQ 16(AX), DX
	SUBQ DX, CX
	MOVQ CX, 40(AX)
	MOVQ (AX), AX
	MOVQ R9, 24(AX)
	MOVQ R10, 32(AX)
	MOVB R11, 40(AX)
	RET

	// Report error
error_max_decoded_size_exeeded:
	MOVQ ctx+0(FP), AX
	MOVQ $-1, CX
	MOVQ CX, 40(AX)
	RET

// func decompress1x_main_loop_bmi2(ctx *decompress1xContext)
// Requires: BMI2
TEXT ·decompress1x_main_loop_bmi2(SB), $0-8
	MOVQ    ctx+0(FP), CX
	MOVQ    16(CX), DX
	MOVQ    24(CX), BX
	CMPQ    BX, $0x04
	JB      error_max_decoded_size_exeeded
	LEAQ    (DX)(BX*1), BX
	MOVQ    (CX), SI
	MOVQ    (SI), R8
	MOVQ    24(SI), R9
	MOVQ    32(SI), R10
	MOVBQZX 40(SI), R11
	MOVQ    32(CX), SI
	MOVBQZX 8(CX), DI
	JMP     loop_condition

main_loop:
	// Check if we have room for 4 bytes in the output buffer
	LEAQ 4(DX), CX
	CMPQ CX, BX
	JGE  error_max_decoded_size_exeeded

	// Decode 4 values
	CMPQ  R11, $0x20
	JL    bitReader_fillFast_1_end
	SUBQ  $0x20, R11
	SUBQ  $0x04, R9
	MOVL  (R8)(R9*1), CX
	SHLXQ R11, CX, CX
	ORQ   CX, R10

bitReader_fillFast_1_end:
	SHRXQ   DI, R10, CX
	MOVW    (SI)(CX*2), CX
	MOVB    CH, AL
	MOVBQZX CL, CX
	ADDQ    CX, R11
	SHLXQ   CX, R10, R10
	SHRXQ   DI, R10, CX
	MOVW    (SI)(CX*2), CX
	MOVB    CH, AH
	MOVBQZX CL, CX
	ADDQ    CX, R11
	SHLXQ   CX, R10, R10
	BSWAPL  AX
	CMPQ    R11, $0x20
	JL      bitReader_fillFast_2_end
	SUBQ    $0x20, R11
	SUBQ    $0x04, R9
	MOVL    (R8)(R9*1), CX
	SHLXQ   R11, CX, CX
	ORQ     CX, R10

bitReader_fillFast_2_end:
	SHRXQ   DI, R10, CX
	MOVW    (SI)(CX*2), CX
	MOVB    CH, AH
	MOVBQZX CL, CX
	ADDQ    CX, R11
	SHLXQ   CX, R10, R10
	SHRXQ   DI, R10, CX
	MOVW    (SI)(CX*2), CX
	MOVB    CH, AL
	MOVBQZX CL, CX
	ADDQ    CX, R11
	SHLXQ   CX, R10, R10
	BSWAPL  AX

	// Store the decoded values
	MOVL AX, (DX)
	ADDQ $0x04, DX

loop_condition:
	CMPQ R9, $0x08
	JGE  main_loop

	// Update ctx structure
	MOVQ ctx+0(FP), AX
	MOVQ DX, CX
	MOVQ 16(AX), DX
	SUBQ DX, CX
	MOVQ CX, 40(AX)
	MOVQ (AX), AX
	MOVQ R9, 24(AX)
	MOVQ R10, 32(AX)
	MOVB R11, 40(AX)
	RET

	// Report error
error_max_decoded_size_exeeded:
	MOVQ ctx+0(FP), AX
	MOVQ $-1, CX
	MOVQ CX, 40(AX)
	RET