summaryrefslogtreecommitdiff
path: root/amiga/hash/xxhash.c
blob: d55a361540e5110cd78f09a2abcb2ef4573c9b0f (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
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
/*
xxHash - Fast Hash algorithm
Copyright (C) 2012-2015, Yann Collet

BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)

Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are
met:

* Redistributions of source code must retain the above copyright
notice, this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above
copyright notice, this list of conditions and the following disclaimer
in the documentation and/or other materials provided with the
distribution.

THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

You can contact the author at :
- xxHash source repository : https://github.com/Cyan4973/xxHash
*/


/**************************************
*  Tuning parameters
**************************************/
/* XXH_FORCE_MEMORY_ACCESS
 * By default, access to unaligned memory is controlled by `memcpy()`, which is safe and portable.
 * Unfortunately, on some target/compiler combinations, the generated assembly is sub-optimal.
 * The below switch allow to select different access method for improved performance.
 * Method 0 (default) : use `memcpy()`. Safe and portable.
 * Method 1 : `__packed` statement. It depends on compiler extension (ie, not portable).
 *            This method is safe if your compiler supports it, and *generally* as fast or faster than `memcpy`.
 * Method 2 : direct access. This method is portable but violate C standard.
 *            It can generate buggy code on targets which generate assembly depending on alignment.
 *            But in some circumstances, it's the only known way to get the most performance (ie GCC + ARMv6)
 * See http://stackoverflow.com/a/32095106/646947 for details.
 * Prefer these methods in priority order (0 > 1 > 2)
 */
#ifndef XXH_FORCE_MEMORY_ACCESS   /* can be defined externally, on command line for example */
#  if defined(__GNUC__) && ( defined(__ARM_ARCH_6__) || defined(__ARM_ARCH_6J__) || defined(__ARM_ARCH_6K__) || defined(__ARM_ARCH_6Z__) || defined(__ARM_ARCH_6ZK__) || defined(__ARM_ARCH_6T2__) )
#    define XXH_FORCE_MEMORY_ACCESS 2
#  elif defined(__INTEL_COMPILER) || \
  (defined(__GNUC__) && ( defined(__ARM_ARCH_7__) || defined(__ARM_ARCH_7A__) || defined(__ARM_ARCH_7R__) || defined(__ARM_ARCH_7M__) || defined(__ARM_ARCH_7S__) ))
#    define XXH_FORCE_MEMORY_ACCESS 1
#  endif
#endif

/* XXH_ACCEPT_NULL_INPUT_POINTER :
 * If the input pointer is a null pointer, xxHash default behavior is to trigger a memory access error, since it is a bad pointer.
 * When this option is enabled, xxHash output for null input pointers will be the same as a null-length input.
 * By default, this option is disabled. To enable it, uncomment below define :
 */
/* #define XXH_ACCEPT_NULL_INPUT_POINTER 1 */

/* XXH_FORCE_NATIVE_FORMAT :
 * By default, xxHash library provides endian-independant Hash values, based on little-endian convention.
 * Results are therefore identical for little-endian and big-endian CPU.
 * This comes at a performance cost for big-endian CPU, since some swapping is required to emulate little-endian format.
 * Should endian-independance be of no importance for your application, you may set the #define below to 1,
 * to improve speed for Big-endian CPU.
 * This option has no impact on Little_Endian CPU.
 */
#define XXH_FORCE_NATIVE_FORMAT 1

/* XXH_USELESS_ALIGN_BRANCH :
 * This is a minor performance trick, only useful with lots of very small keys.
 * It means : don't make a test between aligned/unaligned, because performance will be the same.
 * It saves one initial branch per hash.
 */
#if defined(__i386) || defined(_M_IX86) || defined(__x86_64__) || defined(_M_X64)
#  define XXH_USELESS_ALIGN_BRANCH 1
#endif


/**************************************
*  Compiler Specific Options
***************************************/
#ifdef _MSC_VER    /* Visual Studio */
#  pragma warning(disable : 4127)      /* disable: C4127: conditional expression is constant */
#  define FORCE_INLINE static __forceinline
#else
#  if defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L   /* C99 */
#    ifdef __GNUC__
#      define FORCE_INLINE static inline __attribute__((always_inline))
#    else
#      define FORCE_INLINE static inline
#    endif
#  else
#    define FORCE_INLINE static
#  endif /* __STDC_VERSION__ */
#endif


/**************************************
*  Includes & Memory related functions
***************************************/
#include "xxhash.h"
/* Modify the local functions below should you wish to use some other memory routines */
/* for malloc(), free() */
#include <stdlib.h>
static void* XXH_malloc(size_t s) { return malloc(s); }
static void  XXH_free  (void* p)  { free(p); }
/* for memcpy() */
#include <string.h>
static void* XXH_memcpy(void* dest, const void* src, size_t size) { return memcpy(dest,src,size); }


/**************************************
*  Basic Types
***************************************/
#if defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L   /* C99 */
# include <stdint.h>
  typedef uint8_t  BYTE;
  typedef uint16_t U16;
  typedef uint32_t U32;
  typedef  int32_t S32;
  typedef uint64_t U64;
#else
  typedef unsigned char      BYTE;
  typedef unsigned short     U16;
  typedef unsigned int       U32;
  typedef   signed int       S32;
  typedef unsigned long long U64;
#endif


#if (defined(XXH_FORCE_MEMORY_ACCESS) && (XXH_FORCE_MEMORY_ACCESS==2))

/* Force direct memory access. Only works on CPU which support unaligned memory access in hardware */
static U32 XXH_read32(const void* memPtr) { return *(const U32*) memPtr; }
static U64 XXH_read64(const void* memPtr) { return *(const U64*) memPtr; }

#elif (defined(XXH_FORCE_MEMORY_ACCESS) && (XXH_FORCE_MEMORY_ACCESS==1))

/* __pack instructions are safer, but compiler specific, hence potentially problematic for some compilers */
/* currently only defined for gcc and icc */
typedef union { U32 u32; U64 u64; } __attribute__((packed)) unalign;

static U32 XXH_read32(const void* ptr) { return ((const unalign*)ptr)->u32; }
static U64 XXH_read64(const void* ptr) { return ((const unalign*)ptr)->u64; }

#else

/* portable and safe solution. Generally efficient.
 * see : http://stackoverflow.com/a/32095106/646947
 */

static U32 XXH_read32(const void* memPtr)
{
    U32 val;
    memcpy(&val, memPtr, sizeof(val));
    return val;
}

static U64 XXH_read64(const void* memPtr)
{
    U64 val;
    memcpy(&val, memPtr, sizeof(val));
    return val;
}

#endif // XXH_FORCE_DIRECT_MEMORY_ACCESS


/******************************************
*  Compiler-specific Functions and Macros
******************************************/
#define GCC_VERSION (__GNUC__ * 100 + __GNUC_MINOR__)

/* Note : although _rotl exists for minGW (GCC under windows), performance seems poor */
#if defined(_MSC_VER)
#  define XXH_rotl32(x,r) _rotl(x,r)
#  define XXH_rotl64(x,r) _rotl64(x,r)
#else
#  define XXH_rotl32(x,r) ((x << r) | (x >> (32 - r)))
#  define XXH_rotl64(x,r) ((x << r) | (x >> (64 - r)))
#endif

#if defined(_MSC_VER)     /* Visual Studio */
#  define XXH_swap32 _byteswap_ulong
#  define XXH_swap64 _byteswap_uint64
#elif GCC_VERSION >= 403
#  define XXH_swap32 __builtin_bswap32
#  define XXH_swap64 __builtin_bswap64
#else
static U32 XXH_swap32 (U32 x)
{
    return  ((x << 24) & 0xff000000 ) |
            ((x <<  8) & 0x00ff0000 ) |
            ((x >>  8) & 0x0000ff00 ) |
            ((x >> 24) & 0x000000ff );
}
static U64 XXH_swap64 (U64 x)
{
    return  ((x << 56) & 0xff00000000000000ULL) |
            ((x << 40) & 0x00ff000000000000ULL) |
            ((x << 24) & 0x0000ff0000000000ULL) |
            ((x << 8)  & 0x000000ff00000000ULL) |
            ((x >> 8)  & 0x00000000ff000000ULL) |
            ((x >> 24) & 0x0000000000ff0000ULL) |
            ((x >> 40) & 0x000000000000ff00ULL) |
            ((x >> 56) & 0x00000000000000ffULL);
}
#endif


/***************************************
*  Architecture Macros
***************************************/
typedef enum { XXH_bigEndian=0, XXH_littleEndian=1 } XXH_endianess;

/* XXH_CPU_LITTLE_ENDIAN can be defined externally, for example one the compiler command line */
#ifndef XXH_CPU_LITTLE_ENDIAN
    static const int one = 1;
#   define XXH_CPU_LITTLE_ENDIAN   (*(const char*)(&one))
#endif


/*****************************
*  Memory reads
*****************************/
typedef enum { XXH_aligned, XXH_unaligned } XXH_alignment;

FORCE_INLINE U32 XXH_readLE32_align(const void* ptr, XXH_endianess endian, XXH_alignment align)
{
    if (align==XXH_unaligned)
        return endian==XXH_littleEndian ? XXH_read32(ptr) : XXH_swap32(XXH_read32(ptr));
    else
        return endian==XXH_littleEndian ? *(const U32*)ptr : XXH_swap32(*(const U32*)ptr);
}

FORCE_INLINE U32 XXH_readLE32(const void* ptr, XXH_endianess endian)
{
    return XXH_readLE32_align(ptr, endian, XXH_unaligned);
}

FORCE_INLINE U64 XXH_readLE64_align(const void* ptr, XXH_endianess endian, XXH_alignment align)
{
    if (align==XXH_unaligned)
        return endian==XXH_littleEndian ? XXH_read64(ptr) : XXH_swap64(XXH_read64(ptr));
    else
        return endian==XXH_littleEndian ? *(const U64*)ptr : XXH_swap64(*(const U64*)ptr);
}

FORCE_INLINE U64 XXH_readLE64(const void* ptr, XXH_endianess endian)
{
    return XXH_readLE64_align(ptr, endian, XXH_unaligned);
}


/***************************************
*  Macros
***************************************/
#define XXH_STATIC_ASSERT(c)   { enum { XXH_static_assert = 1/(!!(c)) }; }    /* use only *after* variable declarations */


/***************************************
*  Constants
***************************************/
#define PRIME32_1   2654435761U
#define PRIME32_2   2246822519U
#define PRIME32_3   3266489917U
#define PRIME32_4    668265263U
#define PRIME32_5    374761393U

#define PRIME64_1 11400714785074694791ULL
#define PRIME64_2 14029467366897019727ULL
#define PRIME64_3  1609587929392839161ULL
#define PRIME64_4  9650029242287828579ULL
#define PRIME64_5  2870177450012600261ULL


/*****************************
*  Simple Hash Functions
*****************************/
FORCE_INLINE U32 XXH32_endian_align(const void* input, size_t len, U32 seed, XXH_endianess endian, XXH_alignment align)
{
    const BYTE* p = (const BYTE*)input;
    const BYTE* bEnd = p + len;
    U32 h32;
#define XXH_get32bits(p) XXH_readLE32_align(p, endian, align)

#ifdef XXH_ACCEPT_NULL_INPUT_POINTER
    if (p==NULL)
    {
        len=0;
        bEnd=p=(const BYTE*)(size_t)16;
    }
#endif

    if (len>=16)
    {
        const BYTE* const limit = bEnd - 16;
        U32 v1 = seed + PRIME32_1 + PRIME32_2;
        U32 v2 = seed + PRIME32_2;
        U32 v3 = seed + 0;
        U32 v4 = seed - PRIME32_1;

        do
        {
            v1 += XXH_get32bits(p) * PRIME32_2;
            v1 = XXH_rotl32(v1, 13);
            v1 *= PRIME32_1;
            p+=4;
            v2 += XXH_get32bits(p) * PRIME32_2;
            v2 = XXH_rotl32(v2, 13);
            v2 *= PRIME32_1;
            p+=4;
            v3 += XXH_get32bits(p) * PRIME32_2;
            v3 = XXH_rotl32(v3, 13);
            v3 *= PRIME32_1;
            p+=4;
            v4 += XXH_get32bits(p) * PRIME32_2;
            v4 = XXH_rotl32(v4, 13);
            v4 *= PRIME32_1;
            p+=4;
        }
        while (p<=limit);

        h32 = XXH_rotl32(v1, 1) + XXH_rotl32(v2, 7) + XXH_rotl32(v3, 12) + XXH_rotl32(v4, 18);
    }
    else
    {
        h32  = seed + PRIME32_5;
    }

    h32 += (U32) len;

    while (p+4<=bEnd)
    {
        h32 += XXH_get32bits(p) * PRIME32_3;
        h32  = XXH_rotl32(h32, 17) * PRIME32_4 ;
        p+=4;
    }

    while (p<bEnd)
    {
        h32 += (*p) * PRIME32_5;
        h32 = XXH_rotl32(h32, 11) * PRIME32_1 ;
        p++;
    }

    h32 ^= h32 >> 15;
    h32 *= PRIME32_2;
    h32 ^= h32 >> 13;
    h32 *= PRIME32_3;
    h32 ^= h32 >> 16;

    return h32;
}


unsigned int XXH32 (const void* input, size_t len, unsigned int seed)
{
#if 0
    /* Simple version, good for code maintenance, but unfortunately slow for small inputs */
    XXH32_state_t state;
    XXH32_reset(&state, seed);
    XXH32_update(&state, input, len);
    return XXH32_digest(&state);
#else
    XXH_endianess endian_detected = (XXH_endianess)XXH_CPU_LITTLE_ENDIAN;

#  if !defined(XXH_USELESS_ALIGN_BRANCH)
    if ((((size_t)input) & 3) == 0)   /* Input is 4-bytes aligned, leverage the speed benefit */
    {
        if ((endian_detected==XXH_littleEndian) || XXH_FORCE_NATIVE_FORMAT)
            return XXH32_endian_align(input, len, seed, XXH_littleEndian, XXH_aligned);
        else
            return XXH32_endian_align(input, len, seed, XXH_bigEndian, XXH_aligned);
    }
#  endif

    if ((endian_detected==XXH_littleEndian) || XXH_FORCE_NATIVE_FORMAT)
        return XXH32_endian_align(input, len, seed, XXH_littleEndian, XXH_unaligned);
    else
        return XXH32_endian_align(input, len, seed, XXH_bigEndian, XXH_unaligned);
#endif
}

FORCE_INLINE U64 XXH64_endian_align(const void* input, size_t len, U64 seed, XXH_endianess endian, XXH_alignment align)
{
    const BYTE* p = (const BYTE*)input;
    const BYTE* bEnd = p + len;
    U64 h64;
#define XXH_get64bits(p) XXH_readLE64_align(p, endian, align)

#ifdef XXH_ACCEPT_NULL_INPUT_POINTER
    if (p==NULL)
    {
        len=0;
        bEnd=p=(const BYTE*)(size_t)32;
    }
#endif

    if (len>=32)
    {
        const BYTE* const limit = bEnd - 32;
        U64 v1 = seed + PRIME64_1 + PRIME64_2;
        U64 v2 = seed + PRIME64_2;
        U64 v3 = seed + 0;
        U64 v4 = seed - PRIME64_1;

        do
        {
            v1 += XXH_get64bits(p) * PRIME64_2;
            p+=8;
            v1 = XXH_rotl64(v1, 31);
            v1 *= PRIME64_1;
            v2 += XXH_get64bits(p) * PRIME64_2;
            p+=8;
            v2 = XXH_rotl64(v2, 31);
            v2 *= PRIME64_1;
            v3 += XXH_get64bits(p) * PRIME64_2;
            p+=8;
            v3 = XXH_rotl64(v3, 31);
            v3 *= PRIME64_1;
            v4 += XXH_get64bits(p) * PRIME64_2;
            p+=8;
            v4 = XXH_rotl64(v4, 31);
            v4 *= PRIME64_1;
        }
        while (p<=limit);

        h64 = XXH_rotl64(v1, 1) + XXH_rotl64(v2, 7) + XXH_rotl64(v3, 12) + XXH_rotl64(v4, 18);

        v1 *= PRIME64_2;
        v1 = XXH_rotl64(v1, 31);
        v1 *= PRIME64_1;
        h64 ^= v1;
        h64 = h64 * PRIME64_1 + PRIME64_4;

        v2 *= PRIME64_2;
        v2 = XXH_rotl64(v2, 31);
        v2 *= PRIME64_1;
        h64 ^= v2;
        h64 = h64 * PRIME64_1 + PRIME64_4;

        v3 *= PRIME64_2;
        v3 = XXH_rotl64(v3, 31);
        v3 *= PRIME64_1;
        h64 ^= v3;
        h64 = h64 * PRIME64_1 + PRIME64_4;

        v4 *= PRIME64_2;
        v4 = XXH_rotl64(v4, 31);
        v4 *= PRIME64_1;
        h64 ^= v4;
        h64 = h64 * PRIME64_1 + PRIME64_4;
    }
    else
    {
        h64  = seed + PRIME64_5;
    }

    h64 += (U64) len;

    while (p+8<=bEnd)
    {
        U64 k1 = XXH_get64bits(p);
        k1 *= PRIME64_2;
        k1 = XXH_rotl64(k1,31);
        k1 *= PRIME64_1;
        h64 ^= k1;
        h64 = XXH_rotl64(h64,27) * PRIME64_1 + PRIME64_4;
        p+=8;
    }

    if (p+4<=bEnd)
    {
        h64 ^= (U64)(XXH_get32bits(p)) * PRIME64_1;
        h64 = XXH_rotl64(h64, 23) * PRIME64_2 + PRIME64_3;
        p+=4;
    }

    while (p<bEnd)
    {
        h64 ^= (*p) * PRIME64_5;
        h64 = XXH_rotl64(h64, 11) * PRIME64_1;
        p++;
    }

    h64 ^= h64 >> 33;
    h64 *= PRIME64_2;
    h64 ^= h64 >> 29;
    h64 *= PRIME64_3;
    h64 ^= h64 >> 32;

    return h64;
}


unsigned long long XXH64 (const void* input, size_t len, unsigned long long seed)
{
#if 0
    /* Simple version, good for code maintenance, but unfortunately slow for small inputs */
    XXH64_state_t state;
    XXH64_reset(&state, seed);
    XXH64_update(&state, input, len);
    return XXH64_digest(&state);
#else
    XXH_endianess endian_detected = (XXH_endianess)XXH_CPU_LITTLE_ENDIAN;

#  if !defined(XXH_USELESS_ALIGN_BRANCH)
    if ((((size_t)input) & 7)==0)   /* Input is aligned, let's leverage the speed advantage */
    {
        if ((endian_detected==XXH_littleEndian) || XXH_FORCE_NATIVE_FORMAT)
            return XXH64_endian_align(input, len, seed, XXH_littleEndian, XXH_aligned);
        else
            return XXH64_endian_align(input, len, seed, XXH_bigEndian, XXH_aligned);
    }
#  endif

    if ((endian_detected==XXH_littleEndian) || XXH_FORCE_NATIVE_FORMAT)
        return XXH64_endian_align(input, len, seed, XXH_littleEndian, XXH_unaligned);
    else
        return XXH64_endian_align(input, len, seed, XXH_bigEndian, XXH_unaligned);
#endif
}

/****************************************************
*  Advanced Hash Functions
****************************************************/

/*** Allocation ***/
typedef struct
{
    U64 total_len;
    U32 seed;
    U32 v1;
    U32 v2;
    U32 v3;
    U32 v4;
    U32 mem32[4];   /* defined as U32 for alignment */
    U32 memsize;
} XXH_istate32_t;

typedef struct
{
    U64 total_len;
    U64 seed;
    U64 v1;
    U64 v2;
    U64 v3;
    U64 v4;
    U64 mem64[4];   /* defined as U64 for alignment */
    U32 memsize;
} XXH_istate64_t;


XXH32_state_t* XXH32_createState(void)
{
    XXH_STATIC_ASSERT(sizeof(XXH32_state_t) >= sizeof(XXH_istate32_t));   /* A compilation error here means XXH32_state_t is not large enough */
    return (XXH32_state_t*)XXH_malloc(sizeof(XXH32_state_t));
}
XXH_errorcode XXH32_freeState(XXH32_state_t* statePtr)
{
    XXH_free(statePtr);
    return XXH_OK;
}

XXH64_state_t* XXH64_createState(void)
{
    XXH_STATIC_ASSERT(sizeof(XXH64_state_t) >= sizeof(XXH_istate64_t));   /* A compilation error here means XXH64_state_t is not large enough */
    return (XXH64_state_t*)XXH_malloc(sizeof(XXH64_state_t));
}
XXH_errorcode XXH64_freeState(XXH64_state_t* statePtr)
{
    XXH_free(statePtr);
    return XXH_OK;
}


/*** Hash feed ***/

XXH_errorcode XXH32_reset(XXH32_state_t* state_in, unsigned int seed)
{
    XXH_istate32_t* state = (XXH_istate32_t*) state_in;
    state->seed = seed;
    state->v1 = seed + PRIME32_1 + PRIME32_2;
    state->v2 = seed + PRIME32_2;
    state->v3 = seed + 0;
    state->v4 = seed - PRIME32_1;
    state->total_len = 0;
    state->memsize = 0;
    return XXH_OK;
}

XXH_errorcode XXH64_reset(XXH64_state_t* state_in, unsigned long long seed)
{
    XXH_istate64_t* state = (XXH_istate64_t*) state_in;
    state->seed = seed;
    state->v1 = seed + PRIME64_1 + PRIME64_2;
    state->v2 = seed + PRIME64_2;
    state->v3 = seed + 0;
    state->v4 = seed - PRIME64_1;
    state->total_len = 0;
    state->memsize = 0;
    return XXH_OK;
}


FORCE_INLINE XXH_errorcode XXH32_update_endian (XXH32_state_t* state_in, const void* input, size_t len, XXH_endianess endian)
{
    XXH_istate32_t* state = (XXH_istate32_t *) state_in;
    const BYTE* p = (const BYTE*)input;
    const BYTE* const bEnd = p + len;

#ifdef XXH_ACCEPT_NULL_INPUT_POINTER
    if (input==NULL) return XXH_ERROR;
#endif

    state->total_len += len;

    if (state->memsize + len < 16)   /* fill in tmp buffer */
    {
        XXH_memcpy((BYTE*)(state->mem32) + state->memsize, input, len);
        state->memsize += (U32)len;
        return XXH_OK;
    }

    if (state->memsize)   /* some data left from previous update */
    {
        XXH_memcpy((BYTE*)(state->mem32) + state->memsize, input, 16-state->memsize);
        {
            const U32* p32 = state->mem32;
            state->v1 += XXH_readLE32(p32, endian) * PRIME32_2;
            state->v1 = XXH_rotl32(state->v1, 13);
            state->v1 *= PRIME32_1;
            p32++;
            state->v2 += XXH_readLE32(p32, endian) * PRIME32_2;
            state->v2 = XXH_rotl32(state->v2, 13);
            state->v2 *= PRIME32_1;
            p32++;
            state->v3 += XXH_readLE32(p32, endian) * PRIME32_2;
            state->v3 = XXH_rotl32(state->v3, 13);
            state->v3 *= PRIME32_1;
            p32++;
            state->v4 += XXH_readLE32(p32, endian) * PRIME32_2;
            state->v4 = XXH_rotl32(state->v4, 13);
            state->v4 *= PRIME32_1;
            p32++;
        }
        p += 16-state->memsize;
        state->memsize = 0;
    }

    if (p <= bEnd-16)
    {
        const BYTE* const limit = bEnd - 16;
        U32 v1 = state->v1;
        U32 v2 = state->v2;
        U32 v3 = state->v3;
        U32 v4 = state->v4;

        do
        {
            v1 += XXH_readLE32(p, endian) * PRIME32_2;
            v1 = XXH_rotl32(v1, 13);
            v1 *= PRIME32_1;
            p+=4;
            v2 += XXH_readLE32(p, endian) * PRIME32_2;
            v2 = XXH_rotl32(v2, 13);
            v2 *= PRIME32_1;
            p+=4;
            v3 += XXH_readLE32(p, endian) * PRIME32_2;
            v3 = XXH_rotl32(v3, 13);
            v3 *= PRIME32_1;
            p+=4;
            v4 += XXH_readLE32(p, endian) * PRIME32_2;
            v4 = XXH_rotl32(v4, 13);
            v4 *= PRIME32_1;
            p+=4;
        }
        while (p<=limit);

        state->v1 = v1;
        state->v2 = v2;
        state->v3 = v3;
        state->v4 = v4;
    }

    if (p < bEnd)
    {
        XXH_memcpy(state->mem32, p, bEnd-p);
        state->memsize = (int)(bEnd-p);
    }

    return XXH_OK;
}

XXH_errorcode XXH32_update (XXH32_state_t* state_in, const void* input, size_t len)
{
    XXH_endianess endian_detected = (XXH_endianess)XXH_CPU_LITTLE_ENDIAN;

    if ((endian_detected==XXH_littleEndian) || XXH_FORCE_NATIVE_FORMAT)
        return XXH32_update_endian(state_in, input, len, XXH_littleEndian);
    else
        return XXH32_update_endian(state_in, input, len, XXH_bigEndian);
}



FORCE_INLINE U32 XXH32_digest_endian (const XXH32_state_t* state_in, XXH_endianess endian)
{
    const XXH_istate32_t* state = (const XXH_istate32_t*) state_in;
    const BYTE * p = (const BYTE*)state->mem32;
    const BYTE* bEnd = (const BYTE*)(state->mem32) + state->memsize;
    U32 h32;

    if (state->total_len >= 16)
    {
        h32 = XXH_rotl32(state->v1, 1) + XXH_rotl32(state->v2, 7) + XXH_rotl32(state->v3, 12) + XXH_rotl32(state->v4, 18);
    }
    else
    {
        h32  = state->seed + PRIME32_5;
    }

    h32 += (U32) state->total_len;

    while (p+4<=bEnd)
    {
        h32 += XXH_readLE32(p, endian) * PRIME32_3;
        h32  = XXH_rotl32(h32, 17) * PRIME32_4;
        p+=4;
    }

    while (p<bEnd)
    {
        h32 += (*p) * PRIME32_5;
        h32 = XXH_rotl32(h32, 11) * PRIME32_1;
        p++;
    }

    h32 ^= h32 >> 15;
    h32 *= PRIME32_2;
    h32 ^= h32 >> 13;
    h32 *= PRIME32_3;
    h32 ^= h32 >> 16;

    return h32;
}


unsigned int XXH32_digest (const XXH32_state_t* state_in)
{
    XXH_endianess endian_detected = (XXH_endianess)XXH_CPU_LITTLE_ENDIAN;

    if ((endian_detected==XXH_littleEndian) || XXH_FORCE_NATIVE_FORMAT)
        return XXH32_digest_endian(state_in, XXH_littleEndian);
    else
        return XXH32_digest_endian(state_in, XXH_bigEndian);
}


FORCE_INLINE XXH_errorcode XXH64_update_endian (XXH64_state_t* state_in, const void* input, size_t len, XXH_endianess endian)
{
    XXH_istate64_t * state = (XXH_istate64_t *) state_in;
    const BYTE* p = (const BYTE*)input;
    const BYTE* const bEnd = p + len;

#ifdef XXH_ACCEPT_NULL_INPUT_POINTER
    if (input==NULL) return XXH_ERROR;
#endif

    state->total_len += len;

    if (state->memsize + len < 32)   /* fill in tmp buffer */
    {
        XXH_memcpy(((BYTE*)state->mem64) + state->memsize, input, len);
        state->memsize += (U32)len;
        return XXH_OK;
    }

    if (state->memsize)   /* some data left from previous update */
    {
        XXH_memcpy(((BYTE*)state->mem64) + state->memsize, input, 32-state->memsize);
        {
            const U64* p64 = state->mem64;
            state->v1 += XXH_readLE64(p64, endian) * PRIME64_2;
            state->v1 = XXH_rotl64(state->v1, 31);
            state->v1 *= PRIME64_1;
            p64++;
            state->v2 += XXH_readLE64(p64, endian) * PRIME64_2;
            state->v2 = XXH_rotl64(state->v2, 31);
            state->v2 *= PRIME64_1;
            p64++;
            state->v3 += XXH_readLE64(p64, endian) * PRIME64_2;
            state->v3 = XXH_rotl64(state->v3, 31);
            state->v3 *= PRIME64_1;
            p64++;
            state->v4 += XXH_readLE64(p64, endian) * PRIME64_2;
            state->v4 = XXH_rotl64(state->v4, 31);
            state->v4 *= PRIME64_1;
            p64++;
        }
        p += 32-state->memsize;
        state->memsize = 0;
    }

    if (p+32 <= bEnd)
    {
        const BYTE* const limit = bEnd - 32;
        U64 v1 = state->v1;
        U64 v2 = state->v2;
        U64 v3 = state->v3;
        U64 v4 = state->v4;

        do
        {
            v1 += XXH_readLE64(p, endian) * PRIME64_2;
            v1 = XXH_rotl64(v1, 31);
            v1 *= PRIME64_1;
            p+=8;
            v2 += XXH_readLE64(p, endian) * PRIME64_2;
            v2 = XXH_rotl64(v2, 31);
            v2 *= PRIME64_1;
            p+=8;
            v3 += XXH_readLE64(p, endian) * PRIME64_2;
            v3 = XXH_rotl64(v3, 31);
            v3 *= PRIME64_1;
            p+=8;
            v4 += XXH_readLE64(p, endian) * PRIME64_2;
            v4 = XXH_rotl64(v4, 31);
            v4 *= PRIME64_1;
            p+=8;
        }
        while (p<=limit);

        state->v1 = v1;
        state->v2 = v2;
        state->v3 = v3;
        state->v4 = v4;
    }

    if (p < bEnd)
    {
        XXH_memcpy(state->mem64, p, bEnd-p);
        state->memsize = (int)(bEnd-p);
    }

    return XXH_OK;
}

XXH_errorcode XXH64_update (XXH64_state_t* state_in, const void* input, size_t len)
{
    XXH_endianess endian_detected = (XXH_endianess)XXH_CPU_LITTLE_ENDIAN;

    if ((endian_detected==XXH_littleEndian) || XXH_FORCE_NATIVE_FORMAT)
        return XXH64_update_endian(state_in, input, len, XXH_littleEndian);
    else
        return XXH64_update_endian(state_in, input, len, XXH_bigEndian);
}



FORCE_INLINE U64 XXH64_digest_endian (const XXH64_state_t* state_in, XXH_endianess endian)
{
    const XXH_istate64_t * state = (const XXH_istate64_t *) state_in;
    const BYTE * p = (const BYTE*)state->mem64;
    const BYTE* bEnd = (const BYTE*)state->mem64 + state->memsize;
    U64 h64;

    if (state->total_len >= 32)
    {
        U64 v1 = state->v1;
        U64 v2 = state->v2;
        U64 v3 = state->v3;
        U64 v4 = state->v4;

        h64 = XXH_rotl64(v1, 1) + XXH_rotl64(v2, 7) + XXH_rotl64(v3, 12) + XXH_rotl64(v4, 18);

        v1 *= PRIME64_2;
        v1 = XXH_rotl64(v1, 31);
        v1 *= PRIME64_1;
        h64 ^= v1;
        h64 = h64*PRIME64_1 + PRIME64_4;

        v2 *= PRIME64_2;
        v2 = XXH_rotl64(v2, 31);
        v2 *= PRIME64_1;
        h64 ^= v2;
        h64 = h64*PRIME64_1 + PRIME64_4;

        v3 *= PRIME64_2;
        v3 = XXH_rotl64(v3, 31);
        v3 *= PRIME64_1;
        h64 ^= v3;
        h64 = h64*PRIME64_1 + PRIME64_4;

        v4 *= PRIME64_2;
        v4 = XXH_rotl64(v4, 31);
        v4 *= PRIME64_1;
        h64 ^= v4;
        h64 = h64*PRIME64_1 + PRIME64_4;
    }
    else
    {
        h64  = state->seed + PRIME64_5;
    }

    h64 += (U64) state->total_len;

    while (p+8<=bEnd)
    {
        U64 k1 = XXH_readLE64(p, endian);
        k1 *= PRIME64_2;
        k1 = XXH_rotl64(k1,31);
        k1 *= PRIME64_1;
        h64 ^= k1;
        h64 = XXH_rotl64(h64,27) * PRIME64_1 + PRIME64_4;
        p+=8;
    }

    if (p+4<=bEnd)
    {
        h64 ^= (U64)(XXH_readLE32(p, endian)) * PRIME64_1;
        h64 = XXH_rotl64(h64, 23) * PRIME64_2 + PRIME64_3;
        p+=4;
    }

    while (p<bEnd)
    {
        h64 ^= (*p) * PRIME64_5;
        h64 = XXH_rotl64(h64, 11) * PRIME64_1;
        p++;
    }

    h64 ^= h64 >> 33;
    h64 *= PRIME64_2;
    h64 ^= h64 >> 29;
    h64 *= PRIME64_3;
    h64 ^= h64 >> 32;

    return h64;
}


unsigned long long XXH64_digest (const XXH64_state_t* state_in)
{
    XXH_endianess endian_detected = (XXH_endianess)XXH_CPU_LITTLE_ENDIAN;

    if ((endian_detected==XXH_littleEndian) || XXH_FORCE_NATIVE_FORMAT)
        return XXH64_digest_endian(state_in, XXH_littleEndian);
    else
        return XXH64_digest_endian(state_in, XXH_bigEndian);
}