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
|
// Simd PowerPC specific implementations -*- C++ -*-
// Copyright (C) 2020-2025 Free Software Foundation, Inc.
//
// This file is part of the GNU ISO C++ Library. This library is free
// software; you can redistribute it and/or modify it under the
// terms of the GNU General Public License as published by the
// Free Software Foundation; either version 3, or (at your option)
// any later version.
// This library is distributed in the hope that it will be useful,
// but WITHOUT ANY WARRANTY; without even the implied warranty of
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
// GNU General Public License for more details.
// Under Section 7 of GPL version 3, you are granted additional
// permissions described in the GCC Runtime Library Exception, version
// 3.1, as published by the Free Software Foundation.
// You should have received a copy of the GNU General Public License and
// a copy of the GCC Runtime Library Exception along with this program;
// see the files COPYING3 and COPYING.RUNTIME respectively. If not, see
// <http://www.gnu.org/licenses/>.
#ifndef _GLIBCXX_EXPERIMENTAL_SIMD_PPC_H_
#define _GLIBCXX_EXPERIMENTAL_SIMD_PPC_H_
#if __cplusplus >= 201703L
#ifndef __ALTIVEC__
#error "simd_ppc.h may only be included when AltiVec/VMX is available"
#endif
#include <altivec.h>
_GLIBCXX_SIMD_BEGIN_NAMESPACE
// _SimdImplPpc {{{
template <typename _Abi, typename>
struct _SimdImplPpc : _SimdImplBuiltin<_Abi>
{
using _Base = _SimdImplBuiltin<_Abi>;
// Byte and halfword shift instructions on PPC only consider the low 3 or 4
// bits of the RHS. Consequently, shifting by sizeof(_Tp)*CHAR_BIT (or more)
// is UB without extra measures. To match scalar behavior, byte and halfword
// shifts need an extra fixup step.
// _S_bit_shift_left {{{
template <typename _Tp, size_t _Np>
_GLIBCXX_SIMD_INTRINSIC static constexpr _SimdWrapper<_Tp, _Np>
_S_bit_shift_left(_SimdWrapper<_Tp, _Np> __x, _SimdWrapper<_Tp, _Np> __y)
{
__x = _Base::_S_bit_shift_left(__x, __y);
if constexpr (sizeof(_Tp) < sizeof(int))
__x._M_data
= (__y._M_data < sizeof(_Tp) * __CHAR_BIT__) & __x._M_data;
return __x;
}
template <typename _Tp, size_t _Np>
_GLIBCXX_SIMD_INTRINSIC static constexpr _SimdWrapper<_Tp, _Np>
_S_bit_shift_left(_SimdWrapper<_Tp, _Np> __x, int __y)
{
__x = _Base::_S_bit_shift_left(__x, __y);
if constexpr (sizeof(_Tp) < sizeof(int))
{
if (__y >= int(sizeof(_Tp) * __CHAR_BIT__))
return {};
}
return __x;
}
// }}}
// _S_bit_shift_right {{{
template <typename _Tp, size_t _Np>
_GLIBCXX_SIMD_INTRINSIC static constexpr _SimdWrapper<_Tp, _Np>
_S_bit_shift_right(_SimdWrapper<_Tp, _Np> __x, _SimdWrapper<_Tp, _Np> __y)
{
if constexpr (sizeof(_Tp) < sizeof(int))
{
constexpr int __nbits = sizeof(_Tp) * __CHAR_BIT__;
if constexpr (is_unsigned_v<_Tp>)
return (__y._M_data < __nbits)
& _Base::_S_bit_shift_right(__x, __y)._M_data;
else
{
_Base::_S_masked_assign(_SimdWrapper<_Tp, _Np>(__y._M_data
>= __nbits),
__y, __nbits - 1);
return _Base::_S_bit_shift_right(__x, __y);
}
}
else
return _Base::_S_bit_shift_right(__x, __y);
}
template <typename _Tp, size_t _Np>
_GLIBCXX_SIMD_INTRINSIC static constexpr _SimdWrapper<_Tp, _Np>
_S_bit_shift_right(_SimdWrapper<_Tp, _Np> __x, int __y)
{
if constexpr (sizeof(_Tp) < sizeof(int))
{
constexpr int __nbits = sizeof(_Tp) * __CHAR_BIT__;
if (__y >= __nbits)
{
if constexpr (is_unsigned_v<_Tp>)
return {};
else
return _Base::_S_bit_shift_right(__x, __nbits - 1);
}
}
return _Base::_S_bit_shift_right(__x, __y);
}
// }}}
};
// }}}
// _MaskImplPpc {{{
template <typename _Abi, typename>
struct _MaskImplPpc : _MaskImplBuiltin<_Abi>
{
using _Base = _MaskImplBuiltin<_Abi>;
// _S_popcount {{{
template <typename _Tp>
_GLIBCXX_SIMD_INTRINSIC static int
_S_popcount(simd_mask<_Tp, _Abi> __k)
{
const auto __kv = __as_vector(__k);
if constexpr (__have_power10vec)
{
using _Intrin = __intrinsic_type16_t<make_unsigned_t<__int_for_sizeof_t<_Tp>>>;
return vec_cntm(reinterpret_cast<_Intrin>(__kv), 1);
}
else if constexpr (sizeof(_Tp) >= sizeof(int))
{
using _Intrin = __intrinsic_type16_t<int>;
const int __sum = -vec_sums(__intrin_bitcast<_Intrin>(__kv), _Intrin())[3];
return __sum / (sizeof(_Tp) / sizeof(int));
}
else
{
const auto __summed_to_int = vec_sum4s(__to_intrin(__kv), __intrinsic_type16_t<int>());
return -vec_sums(__summed_to_int, __intrinsic_type16_t<int>())[3];
}
}
// }}}
};
// }}}
_GLIBCXX_SIMD_END_NAMESPACE
#endif // __cplusplus >= 201703L
#endif // _GLIBCXX_EXPERIMENTAL_SIMD_PPC_H_
// vim: foldmethod=marker foldmarker={{{,}}} sw=2 noet ts=8 sts=2 tw=100
|
