summaryrefslogtreecommitdiffstats
path: root/third_party/simde/simde/arm/neon/rev16.h
blob: 55fe38c2e23aaa9e0a4dc4c22c1d164f1107b821 (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
/* SPDX-License-Identifier: MIT
 *
 * Permission is hereby granted, free of charge, to any person
 * obtaining a copy of this software and associated documentation
 * files (the "Software"), to deal in the Software without
 * restriction, including without limitation the rights to use, copy,
 * modify, merge, publish, distribute, sublicense, and/or sell copies
 * of the Software, and to permit persons to whom the Software is
 * furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice shall be
 * included in all copies or substantial portions of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
 * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
 * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
 * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
 * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
 * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
 * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 * SOFTWARE.
 *
 * Copyright:
 *   2020      Evan Nemerson <evan@nemerson.com>
 *   2020      Christopher Moore <moore@free.fr>
 */

#if !defined(SIMDE_ARM_NEON_REV16_H)
#define SIMDE_ARM_NEON_REV16_H

#include "reinterpret.h"
#include "types.h"

HEDLEY_DIAGNOSTIC_PUSH
SIMDE_DISABLE_UNWANTED_DIAGNOSTICS
SIMDE_BEGIN_DECLS_

SIMDE_FUNCTION_ATTRIBUTES
simde_int8x8_t
simde_vrev16_s8(simde_int8x8_t a) {
  #if defined(SIMDE_ARM_NEON_A32V7_NATIVE)
    return vrev16_s8(a);
  #else
    simde_int8x8_private
      r_,
      a_ = simde_int8x8_to_private(a);

    #if defined(SIMDE_X86_SSSE3_NATIVE) && defined(SIMDE_X86_MMX_NATIVE)
      r_.m64 = _mm_shuffle_pi8(a_.m64, _mm_set_pi8(6, 7, 4, 5, 2, 3, 0, 1));
    #elif defined(SIMDE_SHUFFLE_VECTOR_) && !defined(SIMDE_BUG_GCC_100762)
      r_.values = SIMDE_SHUFFLE_VECTOR_(8, 8, a_.values, a_.values, 1, 0, 3, 2, 5, 4, 7, 6);
    #else
      SIMDE_VECTORIZE
      for (size_t i = 0 ; i < (sizeof(r_.values) / sizeof(r_.values[0])) ; i++) {
        r_.values[i] = a_.values[i ^ 1];
      }
    #endif

    return simde_int8x8_from_private(r_);
  #endif
}
#if defined(SIMDE_ARM_NEON_A32V7_ENABLE_NATIVE_ALIASES)
  #undef vrev16_s8
  #define vrev16_s8(a) simde_vrev16_s8(a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde_uint8x8_t
simde_vrev16_u8(simde_uint8x8_t a) {
  #if defined(SIMDE_ARM_NEON_A32V7_NATIVE)
    return vrev16_u8(a);
  #else
    return simde_vreinterpret_u8_s8(simde_vrev16_s8(simde_vreinterpret_s8_u8(a)));
  #endif
}
#if defined(SIMDE_ARM_NEON_A32V7_ENABLE_NATIVE_ALIASES)
  #undef vrev16_u8
  #define vrev16_u8(a) simde_vrev16_u8(a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde_int8x16_t
simde_vrev16q_s8(simde_int8x16_t a) {
  #if defined(SIMDE_ARM_NEON_A32V7_NATIVE)
    return vrev16q_s8(a);
  #elif defined(SIMDE_POWER_ALTIVEC_P8_NATIVE)
    return HEDLEY_REINTERPRET_CAST(SIMDE_POWER_ALTIVEC_VECTOR(signed char),
                                   vec_revb(HEDLEY_REINTERPRET_CAST(SIMDE_POWER_ALTIVEC_VECTOR(signed short), a)));
  #elif defined(SIMDE_POWER_ALTIVEC_P7_NATIVE)
    return HEDLEY_REINTERPRET_CAST(SIMDE_POWER_ALTIVEC_VECTOR(signed char),
                                   vec_reve(HEDLEY_REINTERPRET_CAST(SIMDE_POWER_ALTIVEC_VECTOR(signed short), vec_reve(a))));
  #else
    simde_int8x16_private
      r_,
      a_ = simde_int8x16_to_private(a);

    #if defined(SIMDE_X86_SSSE3_NATIVE)
      r_.m128i = _mm_shuffle_epi8(a_.m128i, _mm_set_epi8(14, 15, 12, 13, 10, 11, 8, 9, 6, 7, 4, 5, 2, 3, 0, 1));
    #elif defined(SIMDE_WASM_SIMD128_NATIVE)
      r_.v128 = wasm_i8x16_shuffle(a_.v128, a_.v128, 1, 0, 3, 2, 5, 4, 7, 6, 9, 8, 11, 10, 13, 12, 15, 14);
    #elif defined(SIMDE_SHUFFLE_VECTOR_)
      r_.values = SIMDE_SHUFFLE_VECTOR_(8, 16, a_.values, a_.values, 1, 0, 3, 2, 5, 4, 7, 6, 9, 8, 11, 10, 13, 12, 15, 14);
    #else
      SIMDE_VECTORIZE
      for (size_t i = 0 ; i < (sizeof(r_.values) / sizeof(r_.values[0])) ; i++) {
        r_.values[i] = a_.values[i ^ 1];
      }
    #endif

    return simde_int8x16_from_private(r_);
  #endif
}
#if defined(SIMDE_ARM_NEON_A32V7_ENABLE_NATIVE_ALIASES)
  #undef vrev16q_s8
  #define vrev16q_s8(a) simde_vrev16q_s8(a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde_uint8x16_t
simde_vrev16q_u8(simde_uint8x16_t a) {
  #if defined(SIMDE_ARM_NEON_A32V7_NATIVE)
    return vrev16q_u8(a);
  #else
    return simde_vreinterpretq_u8_s8(simde_vrev16q_s8(simde_vreinterpretq_s8_u8(a)));
  #endif
}
#if defined(SIMDE_ARM_NEON_A32V7_ENABLE_NATIVE_ALIASES)
  #undef vrev16q_u8
  #define vrev16q_u8(a) simde_vrev16q_u8(a)
#endif

SIMDE_END_DECLS_
HEDLEY_DIAGNOSTIC_POP

#endif /* !defined(SIMDE_ARM_NEON_REV16_H) */