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
|
/*
* SPDX-License-Identifier: BSD-3-Clause
* Copyright (C) IBM Corporation 2014.
*/
#ifndef _RTE_MEMCPY_PPC_64_H_
#define _RTE_MEMCPY_PPC_64_H_
#include <stdint.h>
#include <string.h>
#include "rte_altivec.h"
#include "rte_common.h"
#ifdef __cplusplus
extern "C" {
#endif
#include "generic/rte_memcpy.h"
#if (GCC_VERSION >= 90000 && GCC_VERSION < 90400)
#pragma GCC diagnostic push
#pragma GCC diagnostic ignored "-Warray-bounds"
#endif
static inline void
rte_mov16(uint8_t *dst, const uint8_t *src)
{
vec_vsx_st(vec_vsx_ld(0, src), 0, dst);
}
static inline void
rte_mov32(uint8_t *dst, const uint8_t *src)
{
vec_vsx_st(vec_vsx_ld(0, src), 0, dst);
vec_vsx_st(vec_vsx_ld(16, src), 16, dst);
}
static inline void
rte_mov48(uint8_t *dst, const uint8_t *src)
{
vec_vsx_st(vec_vsx_ld(0, src), 0, dst);
vec_vsx_st(vec_vsx_ld(16, src), 16, dst);
vec_vsx_st(vec_vsx_ld(32, src), 32, dst);
}
static inline void
rte_mov64(uint8_t *dst, const uint8_t *src)
{
vec_vsx_st(vec_vsx_ld(0, src), 0, dst);
vec_vsx_st(vec_vsx_ld(16, src), 16, dst);
vec_vsx_st(vec_vsx_ld(32, src), 32, dst);
vec_vsx_st(vec_vsx_ld(48, src), 48, dst);
}
static inline void
rte_mov128(uint8_t *dst, const uint8_t *src)
{
vec_vsx_st(vec_vsx_ld(0, src), 0, dst);
vec_vsx_st(vec_vsx_ld(16, src), 16, dst);
vec_vsx_st(vec_vsx_ld(32, src), 32, dst);
vec_vsx_st(vec_vsx_ld(48, src), 48, dst);
vec_vsx_st(vec_vsx_ld(64, src), 64, dst);
vec_vsx_st(vec_vsx_ld(80, src), 80, dst);
vec_vsx_st(vec_vsx_ld(96, src), 96, dst);
vec_vsx_st(vec_vsx_ld(112, src), 112, dst);
}
static inline void
rte_mov256(uint8_t *dst, const uint8_t *src)
{
rte_mov128(dst, src);
rte_mov128(dst + 128, src + 128);
}
#define rte_memcpy(dst, src, n) \
__extension__ ({ \
(__builtin_constant_p(n)) ? \
memcpy((dst), (src), (n)) : \
rte_memcpy_func((dst), (src), (n)); })
static inline void *
rte_memcpy_func(void *dst, const void *src, size_t n)
{
void *ret = dst;
/* We can't copy < 16 bytes using XMM registers so do it manually. */
if (n < 16) {
if (n & 0x01) {
*(uint8_t *)dst = *(const uint8_t *)src;
dst = (uint8_t *)dst + 1;
src = (const uint8_t *)src + 1;
}
if (n & 0x02) {
*(uint16_t *)dst = *(const uint16_t *)src;
dst = (uint16_t *)dst + 1;
src = (const uint16_t *)src + 1;
}
if (n & 0x04) {
*(uint32_t *)dst = *(const uint32_t *)src;
dst = (uint32_t *)dst + 1;
src = (const uint32_t *)src + 1;
}
if (n & 0x08)
*(uint64_t *)dst = *(const uint64_t *)src;
return ret;
}
/* Special fast cases for <= 128 bytes */
if (n <= 32) {
rte_mov16((uint8_t *)dst, (const uint8_t *)src);
rte_mov16((uint8_t *)dst - 16 + n,
(const uint8_t *)src - 16 + n);
return ret;
}
if (n <= 64) {
rte_mov32((uint8_t *)dst, (const uint8_t *)src);
rte_mov32((uint8_t *)dst - 32 + n,
(const uint8_t *)src - 32 + n);
return ret;
}
if (n <= 128) {
rte_mov64((uint8_t *)dst, (const uint8_t *)src);
rte_mov64((uint8_t *)dst - 64 + n,
(const uint8_t *)src - 64 + n);
return ret;
}
/*
* For large copies > 128 bytes. This combination of 256, 64 and 16 byte
* copies was found to be faster than doing 128 and 32 byte copies as
* well.
*/
for ( ; n >= 256; n -= 256) {
rte_mov256((uint8_t *)dst, (const uint8_t *)src);
dst = (uint8_t *)dst + 256;
src = (const uint8_t *)src + 256;
}
/*
* We split the remaining bytes (which will be less than 256) into
* 64byte (2^6) chunks.
* Using incrementing integers in the case labels of a switch statement
* encourages the compiler to use a jump table. To get incrementing
* integers, we shift the 2 relevant bits to the LSB position to first
* get decrementing integers, and then subtract.
*/
switch (3 - (n >> 6)) {
case 0x00:
rte_mov64((uint8_t *)dst, (const uint8_t *)src);
n -= 64;
dst = (uint8_t *)dst + 64;
src = (const uint8_t *)src + 64; /* fallthrough */
case 0x01:
rte_mov64((uint8_t *)dst, (const uint8_t *)src);
n -= 64;
dst = (uint8_t *)dst + 64;
src = (const uint8_t *)src + 64; /* fallthrough */
case 0x02:
rte_mov64((uint8_t *)dst, (const uint8_t *)src);
n -= 64;
dst = (uint8_t *)dst + 64;
src = (const uint8_t *)src + 64; /* fallthrough */
default:
;
}
/*
* We split the remaining bytes (which will be less than 64) into
* 16byte (2^4) chunks, using the same switch structure as above.
*/
switch (3 - (n >> 4)) {
case 0x00:
rte_mov16((uint8_t *)dst, (const uint8_t *)src);
n -= 16;
dst = (uint8_t *)dst + 16;
src = (const uint8_t *)src + 16; /* fallthrough */
case 0x01:
rte_mov16((uint8_t *)dst, (const uint8_t *)src);
n -= 16;
dst = (uint8_t *)dst + 16;
src = (const uint8_t *)src + 16; /* fallthrough */
case 0x02:
rte_mov16((uint8_t *)dst, (const uint8_t *)src);
n -= 16;
dst = (uint8_t *)dst + 16;
src = (const uint8_t *)src + 16; /* fallthrough */
default:
;
}
/* Copy any remaining bytes, without going beyond end of buffers */
if (n != 0)
rte_mov16((uint8_t *)dst - 16 + n,
(const uint8_t *)src - 16 + n);
return ret;
}
#if (GCC_VERSION >= 90000 && GCC_VERSION < 90400)
#pragma GCC diagnostic pop
#endif
#ifdef __cplusplus
}
#endif
#endif /* _RTE_MEMCPY_PPC_64_H_ */
|
