summaryrefslogtreecommitdiff
path: root/arch/arm64/lib/xor-neon.c
blob: 131c60c27dff646aad80816d1dd26f5e8d11cf0c (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
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
/*
 * arch/arm64/lib/xor-neon.c
 *
 * Authors: Jackie Liu <liuyun01@kylinos.cn>
 * Copyright (C) 2018,Tianjin KYLIN Information Technology Co., Ltd.
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 */

#include <linux/raid/xor.h>
#include <linux/module.h>
#include <asm/neon-intrinsics.h>

void xor_arm64_neon_2(unsigned long bytes, unsigned long *p1,
	unsigned long *p2)
{
	uint64_t *dp1 = (uint64_t *)p1;
	uint64_t *dp2 = (uint64_t *)p2;

	register uint64x2_t v0, v1, v2, v3;
	long lines = bytes / (sizeof(uint64x2_t) * 4);

	do {
		/* p1 ^= p2 */
		v0 = veorq_u64(vld1q_u64(dp1 +  0), vld1q_u64(dp2 +  0));
		v1 = veorq_u64(vld1q_u64(dp1 +  2), vld1q_u64(dp2 +  2));
		v2 = veorq_u64(vld1q_u64(dp1 +  4), vld1q_u64(dp2 +  4));
		v3 = veorq_u64(vld1q_u64(dp1 +  6), vld1q_u64(dp2 +  6));

		/* store */
		vst1q_u64(dp1 +  0, v0);
		vst1q_u64(dp1 +  2, v1);
		vst1q_u64(dp1 +  4, v2);
		vst1q_u64(dp1 +  6, v3);

		dp1 += 8;
		dp2 += 8;
	} while (--lines > 0);
}

void xor_arm64_neon_3(unsigned long bytes, unsigned long *p1,
	unsigned long *p2, unsigned long *p3)
{
	uint64_t *dp1 = (uint64_t *)p1;
	uint64_t *dp2 = (uint64_t *)p2;
	uint64_t *dp3 = (uint64_t *)p3;

	register uint64x2_t v0, v1, v2, v3;
	long lines = bytes / (sizeof(uint64x2_t) * 4);

	do {
		/* p1 ^= p2 */
		v0 = veorq_u64(vld1q_u64(dp1 +  0), vld1q_u64(dp2 +  0));
		v1 = veorq_u64(vld1q_u64(dp1 +  2), vld1q_u64(dp2 +  2));
		v2 = veorq_u64(vld1q_u64(dp1 +  4), vld1q_u64(dp2 +  4));
		v3 = veorq_u64(vld1q_u64(dp1 +  6), vld1q_u64(dp2 +  6));

		/* p1 ^= p3 */
		v0 = veorq_u64(v0, vld1q_u64(dp3 +  0));
		v1 = veorq_u64(v1, vld1q_u64(dp3 +  2));
		v2 = veorq_u64(v2, vld1q_u64(dp3 +  4));
		v3 = veorq_u64(v3, vld1q_u64(dp3 +  6));

		/* store */
		vst1q_u64(dp1 +  0, v0);
		vst1q_u64(dp1 +  2, v1);
		vst1q_u64(dp1 +  4, v2);
		vst1q_u64(dp1 +  6, v3);

		dp1 += 8;
		dp2 += 8;
		dp3 += 8;
	} while (--lines > 0);
}

void xor_arm64_neon_4(unsigned long bytes, unsigned long *p1,
	unsigned long *p2, unsigned long *p3, unsigned long *p4)
{
	uint64_t *dp1 = (uint64_t *)p1;
	uint64_t *dp2 = (uint64_t *)p2;
	uint64_t *dp3 = (uint64_t *)p3;
	uint64_t *dp4 = (uint64_t *)p4;

	register uint64x2_t v0, v1, v2, v3;
	long lines = bytes / (sizeof(uint64x2_t) * 4);

	do {
		/* p1 ^= p2 */
		v0 = veorq_u64(vld1q_u64(dp1 +  0), vld1q_u64(dp2 +  0));
		v1 = veorq_u64(vld1q_u64(dp1 +  2), vld1q_u64(dp2 +  2));
		v2 = veorq_u64(vld1q_u64(dp1 +  4), vld1q_u64(dp2 +  4));
		v3 = veorq_u64(vld1q_u64(dp1 +  6), vld1q_u64(dp2 +  6));

		/* p1 ^= p3 */
		v0 = veorq_u64(v0, vld1q_u64(dp3 +  0));
		v1 = veorq_u64(v1, vld1q_u64(dp3 +  2));
		v2 = veorq_u64(v2, vld1q_u64(dp3 +  4));
		v3 = veorq_u64(v3, vld1q_u64(dp3 +  6));

		/* p1 ^= p4 */
		v0 = veorq_u64(v0, vld1q_u64(dp4 +  0));
		v1 = veorq_u64(v1, vld1q_u64(dp4 +  2));
		v2 = veorq_u64(v2, vld1q_u64(dp4 +  4));
		v3 = veorq_u64(v3, vld1q_u64(dp4 +  6));

		/* store */
		vst1q_u64(dp1 +  0, v0);
		vst1q_u64(dp1 +  2, v1);
		vst1q_u64(dp1 +  4, v2);
		vst1q_u64(dp1 +  6, v3);

		dp1 += 8;
		dp2 += 8;
		dp3 += 8;
		dp4 += 8;
	} while (--lines > 0);
}

void xor_arm64_neon_5(unsigned long bytes, unsigned long *p1,
	unsigned long *p2, unsigned long *p3,
	unsigned long *p4, unsigned long *p5)
{
	uint64_t *dp1 = (uint64_t *)p1;
	uint64_t *dp2 = (uint64_t *)p2;
	uint64_t *dp3 = (uint64_t *)p3;
	uint64_t *dp4 = (uint64_t *)p4;
	uint64_t *dp5 = (uint64_t *)p5;

	register uint64x2_t v0, v1, v2, v3;
	long lines = bytes / (sizeof(uint64x2_t) * 4);

	do {
		/* p1 ^= p2 */
		v0 = veorq_u64(vld1q_u64(dp1 +  0), vld1q_u64(dp2 +  0));
		v1 = veorq_u64(vld1q_u64(dp1 +  2), vld1q_u64(dp2 +  2));
		v2 = veorq_u64(vld1q_u64(dp1 +  4), vld1q_u64(dp2 +  4));
		v3 = veorq_u64(vld1q_u64(dp1 +  6), vld1q_u64(dp2 +  6));

		/* p1 ^= p3 */
		v0 = veorq_u64(v0, vld1q_u64(dp3 +  0));
		v1 = veorq_u64(v1, vld1q_u64(dp3 +  2));
		v2 = veorq_u64(v2, vld1q_u64(dp3 +  4));
		v3 = veorq_u64(v3, vld1q_u64(dp3 +  6));

		/* p1 ^= p4 */
		v0 = veorq_u64(v0, vld1q_u64(dp4 +  0));
		v1 = veorq_u64(v1, vld1q_u64(dp4 +  2));
		v2 = veorq_u64(v2, vld1q_u64(dp4 +  4));
		v3 = veorq_u64(v3, vld1q_u64(dp4 +  6));

		/* p1 ^= p5 */
		v0 = veorq_u64(v0, vld1q_u64(dp5 +  0));
		v1 = veorq_u64(v1, vld1q_u64(dp5 +  2));
		v2 = veorq_u64(v2, vld1q_u64(dp5 +  4));
		v3 = veorq_u64(v3, vld1q_u64(dp5 +  6));

		/* store */
		vst1q_u64(dp1 +  0, v0);
		vst1q_u64(dp1 +  2, v1);
		vst1q_u64(dp1 +  4, v2);
		vst1q_u64(dp1 +  6, v3);

		dp1 += 8;
		dp2 += 8;
		dp3 += 8;
		dp4 += 8;
		dp5 += 8;
	} while (--lines > 0);
}

struct xor_block_template const xor_block_inner_neon = {
	.name	= "__inner_neon__",
	.do_2	= xor_arm64_neon_2,
	.do_3	= xor_arm64_neon_3,
	.do_4	= xor_arm64_neon_4,
	.do_5	= xor_arm64_neon_5,
};
EXPORT_SYMBOL(xor_block_inner_neon);

MODULE_AUTHOR("Jackie Liu <liuyun01@kylinos.cn>");
MODULE_DESCRIPTION("ARMv8 XOR Extensions");
MODULE_LICENSE("GPL");