slow5lib-sys 0.2.0

Low-level bindings to the slow5lib C library
Documentation 
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

#include "streamvbyte.h"

#if defined(_MSC_VER)
/* Microsoft C/C++-compatible compiler */
#include <intrin.h>
#elif defined(__GNUC__) && (defined(__x86_64__) || defined(__i386__))
/* GCC-compatible compiler, targeting x86/x86-64 */
#include <x86intrin.h>
#elif defined(__GNUC__) && defined(__ARM_NEON__)
/* GCC-compatible compiler, targeting ARM with NEON */
#include <arm_neon.h>
#elif defined(__GNUC__) && defined(__IWMMXT__)
/* GCC-compatible compiler, targeting ARM with WMMX */
#include <mmintrin.h>
#elif (defined(__GNUC__) || defined(__xlC__)) &&                               \
    (defined(__VEC__) || defined(__ALTIVEC__))
/* XLC or GCC-compatible compiler, targeting PowerPC with VMX/VSX */
#include <altivec.h>
#elif defined(__GNUC__) && defined(__SPE__)
/* GCC-compatible compiler, targeting PowerPC with SPE */
#include <spe.h>
#endif

#include <string.h> // for memcpy
#include "streamvbyte_shuffle_tables_decode.h"


#ifdef __ARM_NEON__
#include "streamvbyte_arm_decode.c"
#endif

#ifdef STREAMVBYTE_SSSE3
#include "streamvbyte_x64_decode.c"
#endif // STREAMVBYTE_SSSE3

static inline uint32_t _decode_data(const uint8_t **dataPtrPtr, uint8_t code) {
  const uint8_t *dataPtr = *dataPtrPtr;
  uint32_t val;

  if (code == 0) { // 1 byte
    val = (uint32_t)*dataPtr;
    dataPtr += 1;
  } else if (code == 1) { // 2 bytes
    val = 0;
    memcpy(&val, dataPtr, 2); // assumes little endian
    dataPtr += 2;
  } else if (code == 2) { // 3 bytes
    val = 0;
    memcpy(&val, dataPtr, 3); // assumes little endian
    dataPtr += 3;
  } else { // code == 3
    memcpy(&val, dataPtr, 4);
    dataPtr += 4;
  }

  *dataPtrPtr = dataPtr;
  return val;
}
static const uint8_t *svb_decode_scalar(uint32_t *outPtr, const uint8_t *keyPtr,
                                        const uint8_t *dataPtr,
                                        uint32_t count) {
  if (count == 0)
    return dataPtr; // no reads or writes if no data

  uint8_t shift = 0;
  uint32_t key = *keyPtr++;
  for (uint32_t c = 0; c < count; c++) {
    if (shift == 8) {
      shift = 0;
      key = *keyPtr++;
    }
    uint32_t val = _decode_data(&dataPtr, (key >> shift) & 0x3);
    *outPtr++ = val;
    shift += 2;
  }

  return dataPtr; // pointer to first unused byte after end
}

// Read count 32-bit integers in maskedvbyte format from in, storing the result
// in out.  Returns the number of bytes read.
// NOTE: I am appending __slow5_ here
size_t __slow5_streamvbyte_decode(const uint8_t *in, uint32_t *out, uint32_t count) {
  if (count == 0)
    return 0;

  const uint8_t *keyPtr = in;               // full list of keys is next
  uint32_t keyLen = ((count + 3) / 4);      // 2-bits per key (rounded up)
  const uint8_t *dataPtr = keyPtr + keyLen; // data starts at end of keys

#ifdef STREAMVBYTE_SSSE3
  dataPtr = svb_decode_avx_simple(out, keyPtr, dataPtr, count);
  out += count & ~ 31;
  keyPtr += (count/4) & ~ 7;
  count &= 31;
#elif defined(__ARM_NEON__)
  dataPtr = svb_decode_vector(out, keyPtr, dataPtr, count);
  out += count - (count & 3);
  keyPtr += count/4;
  count &= 3;
#endif

  return svb_decode_scalar(out, keyPtr, dataPtr, count) - in;

}