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
|
//===-- Memcpy implementation -----------------------------------*- C++ -*-===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
#ifndef LLVM_LIBC_SRC_STRING_MEMORY_UTILS_MEMCPY_IMPLEMENTATIONS_H
#define LLVM_LIBC_SRC_STRING_MEMORY_UTILS_MEMCPY_IMPLEMENTATIONS_H
#include "src/__support/architectures.h"
#include "src/__support/common.h"
#include "src/string/memory_utils/elements.h"
#include "src/string/memory_utils/utils.h"
#include <stddef.h> // size_t
// Design rationale
// ================
//
// Using a profiler to observe size distributions for calls into libc
// functions, it was found most operations act on a small number of bytes.
// This makes it important to favor small sizes.
//
// The tests for `count` are in ascending order so the cost of branching is
// proportional to the cost of copying.
//
// The function is written in C++ for several reasons:
// - The compiler can __see__ the code, this is useful when performing Profile
// Guided Optimization as the optimized code can take advantage of branching
// probabilities.
// - It also allows for easier customization and favors testing multiple
// implementation parameters.
// - As compilers and processors get better, the generated code is improved
// with little change on the code side.
namespace __llvm_libc {
static inline void inline_memcpy(char *__restrict dst,
const char *__restrict src, size_t count) {
#if defined(LLVM_LIBC_ARCH_X86)
/////////////////////////////////////////////////////////////////////////////
// LLVM_LIBC_ARCH_X86
/////////////////////////////////////////////////////////////////////////////
using namespace __llvm_libc::x86;
// Whether to use only rep;movsb.
constexpr bool kUseOnlyRepMovsb =
LLVM_LIBC_IS_DEFINED(LLVM_LIBC_MEMCPY_X86_USE_ONLY_REPMOVSB);
// kRepMovsBSize == -1 : Only CopyAligned is used.
// kRepMovsBSize == 0 : Only RepMovsb is used.
// else CopyAligned is used up to kRepMovsBSize and then RepMovsb.
constexpr size_t kRepMovsBSize =
#if defined(LLVM_LIBC_MEMCPY_X86_USE_REPMOVSB_FROM_SIZE)
LLVM_LIBC_MEMCPY_X86_USE_REPMOVSB_FROM_SIZE;
#else
-1;
#endif // LLVM_LIBC_MEMCPY_X86_USE_REPMOVSB_FROM_SIZE
// Whether target supports AVX instructions.
constexpr bool kHasAvx = LLVM_LIBC_IS_DEFINED(__AVX__);
#if defined(__AVX__)
using LoopBlockSize = _64;
#else
using LoopBlockSize = _32;
#endif
if (kUseOnlyRepMovsb)
return Copy<Accelerator>(dst, src, count);
if (count == 0)
return;
if (count == 1)
return Copy<_1>(dst, src);
if (count == 2)
return Copy<_2>(dst, src);
if (count == 3)
return Copy<_3>(dst, src);
if (count == 4)
return Copy<_4>(dst, src);
if (count < 8)
return Copy<HeadTail<_4>>(dst, src, count);
if (count < 16)
return Copy<HeadTail<_8>>(dst, src, count);
if (count < 32)
return Copy<HeadTail<_16>>(dst, src, count);
if (count < 64)
return Copy<HeadTail<_32>>(dst, src, count);
if (count < 128)
return Copy<HeadTail<_64>>(dst, src, count);
if (kHasAvx && count < 256)
return Copy<HeadTail<_128>>(dst, src, count);
if (count <= kRepMovsBSize)
return Copy<Align<_32, Arg::Dst>::Then<Loop<LoopBlockSize>>>(dst, src,
count);
return Copy<Accelerator>(dst, src, count);
#elif defined(LLVM_LIBC_ARCH_AARCH64)
/////////////////////////////////////////////////////////////////////////////
// LLVM_LIBC_ARCH_AARCH64
/////////////////////////////////////////////////////////////////////////////
using namespace __llvm_libc::scalar;
if (count == 0)
return;
if (count == 1)
return Copy<_1>(dst, src);
if (count == 2)
return Copy<_2>(dst, src);
if (count == 3)
return Copy<_3>(dst, src);
if (count == 4)
return Copy<_4>(dst, src);
if (count < 8)
return Copy<HeadTail<_4>>(dst, src, count);
if (count < 16)
return Copy<HeadTail<_8>>(dst, src, count);
if (count < 32)
return Copy<HeadTail<_16>>(dst, src, count);
if (count < 64)
return Copy<HeadTail<_32>>(dst, src, count);
if (count < 128)
return Copy<HeadTail<_64>>(dst, src, count);
return Copy<Align<_16, Arg::Src>::Then<Loop<_64>>>(dst, src, count);
#else
/////////////////////////////////////////////////////////////////////////////
// Default
/////////////////////////////////////////////////////////////////////////////
using namespace __llvm_libc::scalar;
if (count == 0)
return;
if (count == 1)
return Copy<_1>(dst, src);
if (count == 2)
return Copy<_2>(dst, src);
if (count == 3)
return Copy<_3>(dst, src);
if (count == 4)
return Copy<_4>(dst, src);
if (count < 8)
return Copy<HeadTail<_4>>(dst, src, count);
if (count < 16)
return Copy<HeadTail<_8>>(dst, src, count);
if (count < 32)
return Copy<HeadTail<_16>>(dst, src, count);
if (count < 64)
return Copy<HeadTail<_32>>(dst, src, count);
if (count < 128)
return Copy<HeadTail<_64>>(dst, src, count);
return Copy<Align<_32, Arg::Src>::Then<Loop<_32>>>(dst, src, count);
#endif
}
} // namespace __llvm_libc
#endif // LLVM_LIBC_SRC_STRING_MEMORY_UTILS_MEMCPY_IMPLEMENTATIONS_H
|
