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
|
#ifndef _ASM_X86_XOR_AVX_H
#define _ASM_X86_XOR_AVX_H
/*
* Optimized RAID-5 checksumming functions for AVX
*
* Copyright (C) 2012 Intel Corporation
* Author: Jim Kukunas <james.t.kukunas@linux.intel.com>
*
* Based on Ingo Molnar and Zach Brown's respective MMX and SSE routines
*
* This program 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; version 2
* of the License.
*/
#ifdef CONFIG_AS_AVX
#include <linux/compiler.h>
#include <asm/i387.h>
#define BLOCK4(i) \
BLOCK(32 * i, 0) \
BLOCK(32 * (i + 1), 1) \
BLOCK(32 * (i + 2), 2) \
BLOCK(32 * (i + 3), 3)
#define BLOCK16() \
BLOCK4(0) \
BLOCK4(4) \
BLOCK4(8) \
BLOCK4(12)
static void xor_avx_2(unsigned long bytes, unsigned long *p0, unsigned long *p1)
{
unsigned long lines = bytes >> 9;
kernel_fpu_begin();
while (lines--) {
#undef BLOCK
#define BLOCK(i, reg) \
do { \
asm volatile("vmovdqa %0, %%ymm" #reg : : "m" (p1[i / sizeof(*p1)])); \
asm volatile("vxorps %0, %%ymm" #reg ", %%ymm" #reg : : \
"m" (p0[i / sizeof(*p0)])); \
asm volatile("vmovdqa %%ymm" #reg ", %0" : \
"=m" (p0[i / sizeof(*p0)])); \
} while (0);
BLOCK16()
p0 = (unsigned long *)((uintptr_t)p0 + 512);
p1 = (unsigned long *)((uintptr_t)p1 + 512);
}
kernel_fpu_end();
}
static void xor_avx_3(unsigned long bytes, unsigned long *p0, unsigned long *p1,
unsigned long *p2)
{
unsigned long lines = bytes >> 9;
kernel_fpu_begin();
while (lines--) {
#undef BLOCK
#define BLOCK(i, reg) \
do { \
asm volatile("vmovdqa %0, %%ymm" #reg : : "m" (p2[i / sizeof(*p2)])); \
asm volatile("vxorps %0, %%ymm" #reg ", %%ymm" #reg : : \
"m" (p1[i / sizeof(*p1)])); \
asm volatile("vxorps %0, %%ymm" #reg ", %%ymm" #reg : : \
"m" (p0[i / sizeof(*p0)])); \
asm volatile("vmovdqa %%ymm" #reg ", %0" : \
"=m" (p0[i / sizeof(*p0)])); \
} while (0);
BLOCK16()
p0 = (unsigned long *)((uintptr_t)p0 + 512);
p1 = (unsigned long *)((uintptr_t)p1 + 512);
p2 = (unsigned long *)((uintptr_t)p2 + 512);
}
kernel_fpu_end();
}
static void xor_avx_4(unsigned long bytes, unsigned long *p0, unsigned long *p1,
unsigned long *p2, unsigned long *p3)
{
unsigned long lines = bytes >> 9;
kernel_fpu_begin();
while (lines--) {
#undef BLOCK
#define BLOCK(i, reg) \
do { \
asm volatile("vmovdqa %0, %%ymm" #reg : : "m" (p3[i / sizeof(*p3)])); \
asm volatile("vxorps %0, %%ymm" #reg ", %%ymm" #reg : : \
"m" (p2[i / sizeof(*p2)])); \
asm volatile("vxorps %0, %%ymm" #reg ", %%ymm" #reg : : \
"m" (p1[i / sizeof(*p1)])); \
asm volatile("vxorps %0, %%ymm" #reg ", %%ymm" #reg : : \
"m" (p0[i / sizeof(*p0)])); \
asm volatile("vmovdqa %%ymm" #reg ", %0" : \
"=m" (p0[i / sizeof(*p0)])); \
} while (0);
BLOCK16();
p0 = (unsigned long *)((uintptr_t)p0 + 512);
p1 = (unsigned long *)((uintptr_t)p1 + 512);
p2 = (unsigned long *)((uintptr_t)p2 + 512);
p3 = (unsigned long *)((uintptr_t)p3 + 512);
}
kernel_fpu_end();
}
static void xor_avx_5(unsigned long bytes, unsigned long *p0, unsigned long *p1,
unsigned long *p2, unsigned long *p3, unsigned long *p4)
{
unsigned long lines = bytes >> 9;
kernel_fpu_begin();
while (lines--) {
#undef BLOCK
#define BLOCK(i, reg) \
do { \
asm volatile("vmovdqa %0, %%ymm" #reg : : "m" (p4[i / sizeof(*p4)])); \
asm volatile("vxorps %0, %%ymm" #reg ", %%ymm" #reg : : \
"m" (p3[i / sizeof(*p3)])); \
asm volatile("vxorps %0, %%ymm" #reg ", %%ymm" #reg : : \
"m" (p2[i / sizeof(*p2)])); \
asm volatile("vxorps %0, %%ymm" #reg ", %%ymm" #reg : : \
"m" (p1[i / sizeof(*p1)])); \
asm volatile("vxorps %0, %%ymm" #reg ", %%ymm" #reg : : \
"m" (p0[i / sizeof(*p0)])); \
asm volatile("vmovdqa %%ymm" #reg ", %0" : \
"=m" (p0[i / sizeof(*p0)])); \
} while (0);
BLOCK16()
p0 = (unsigned long *)((uintptr_t)p0 + 512);
p1 = (unsigned long *)((uintptr_t)p1 + 512);
p2 = (unsigned long *)((uintptr_t)p2 + 512);
p3 = (unsigned long *)((uintptr_t)p3 + 512);
p4 = (unsigned long *)((uintptr_t)p4 + 512);
}
kernel_fpu_end();
}
static struct xor_block_template xor_block_avx = {
.name = "avx",
.do_2 = xor_avx_2,
.do_3 = xor_avx_3,
.do_4 = xor_avx_4,
.do_5 = xor_avx_5,
};
#define AVX_XOR_SPEED \
do { \
if (cpu_has_avx) \
xor_speed(&xor_block_avx); \
} while (0)
#define AVX_SELECT(FASTEST) \
(cpu_has_avx ? &xor_block_avx : FASTEST)
#else
#define AVX_XOR_SPEED {}
#define AVX_SELECT(FASTEST) (FASTEST)
#endif
#endif
|
