Loading...
1/*
2 * This program is free software; you can redistribute it and/or modify
3 * it under the terms of the GNU General Public License as published by
4 * the Free Software Foundation; either version 2 of the License, or
5 * (at your option) any later version.
6 *
7 * This program is distributed in the hope that it will be useful,
8 * but WITHOUT ANY WARRANTY; without even the implied warranty of
9 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
10 * GNU General Public License for more details.
11 *
12 * You should have received a copy of the GNU General Public License
13 * along with this program; if not, write to the Free Software
14 * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
15 *
16 * Copyright (C) IBM Corporation, 2012
17 *
18 * Author: Anton Blanchard <anton@au.ibm.com>
19 */
20
21/*
22 * Sparse (as at v0.5.0) gets very, very confused by this file.
23 * Make it a bit simpler for it.
24 */
25#if !defined(__CHECKER__)
26#include <altivec.h>
27#else
28#define vec_xor(a, b) a ^ b
29#define vector __attribute__((vector_size(16)))
30#endif
31
32#include "xor_vmx.h"
33
34typedef vector signed char unative_t;
35
36#define DEFINE(V) \
37 unative_t *V = (unative_t *)V##_in; \
38 unative_t V##_0, V##_1, V##_2, V##_3
39
40#define LOAD(V) \
41 do { \
42 V##_0 = V[0]; \
43 V##_1 = V[1]; \
44 V##_2 = V[2]; \
45 V##_3 = V[3]; \
46 } while (0)
47
48#define STORE(V) \
49 do { \
50 V[0] = V##_0; \
51 V[1] = V##_1; \
52 V[2] = V##_2; \
53 V[3] = V##_3; \
54 } while (0)
55
56#define XOR(V1, V2) \
57 do { \
58 V1##_0 = vec_xor(V1##_0, V2##_0); \
59 V1##_1 = vec_xor(V1##_1, V2##_1); \
60 V1##_2 = vec_xor(V1##_2, V2##_2); \
61 V1##_3 = vec_xor(V1##_3, V2##_3); \
62 } while (0)
63
64void __xor_altivec_2(unsigned long bytes, unsigned long *v1_in,
65 unsigned long *v2_in)
66{
67 DEFINE(v1);
68 DEFINE(v2);
69 unsigned long lines = bytes / (sizeof(unative_t)) / 4;
70
71 do {
72 LOAD(v1);
73 LOAD(v2);
74 XOR(v1, v2);
75 STORE(v1);
76
77 v1 += 4;
78 v2 += 4;
79 } while (--lines > 0);
80}
81
82void __xor_altivec_3(unsigned long bytes, unsigned long *v1_in,
83 unsigned long *v2_in, unsigned long *v3_in)
84{
85 DEFINE(v1);
86 DEFINE(v2);
87 DEFINE(v3);
88 unsigned long lines = bytes / (sizeof(unative_t)) / 4;
89
90 do {
91 LOAD(v1);
92 LOAD(v2);
93 LOAD(v3);
94 XOR(v1, v2);
95 XOR(v1, v3);
96 STORE(v1);
97
98 v1 += 4;
99 v2 += 4;
100 v3 += 4;
101 } while (--lines > 0);
102}
103
104void __xor_altivec_4(unsigned long bytes, unsigned long *v1_in,
105 unsigned long *v2_in, unsigned long *v3_in,
106 unsigned long *v4_in)
107{
108 DEFINE(v1);
109 DEFINE(v2);
110 DEFINE(v3);
111 DEFINE(v4);
112 unsigned long lines = bytes / (sizeof(unative_t)) / 4;
113
114 do {
115 LOAD(v1);
116 LOAD(v2);
117 LOAD(v3);
118 LOAD(v4);
119 XOR(v1, v2);
120 XOR(v3, v4);
121 XOR(v1, v3);
122 STORE(v1);
123
124 v1 += 4;
125 v2 += 4;
126 v3 += 4;
127 v4 += 4;
128 } while (--lines > 0);
129}
130
131void __xor_altivec_5(unsigned long bytes, unsigned long *v1_in,
132 unsigned long *v2_in, unsigned long *v3_in,
133 unsigned long *v4_in, unsigned long *v5_in)
134{
135 DEFINE(v1);
136 DEFINE(v2);
137 DEFINE(v3);
138 DEFINE(v4);
139 DEFINE(v5);
140 unsigned long lines = bytes / (sizeof(unative_t)) / 4;
141
142 do {
143 LOAD(v1);
144 LOAD(v2);
145 LOAD(v3);
146 LOAD(v4);
147 LOAD(v5);
148 XOR(v1, v2);
149 XOR(v3, v4);
150 XOR(v1, v5);
151 XOR(v1, v3);
152 STORE(v1);
153
154 v1 += 4;
155 v2 += 4;
156 v3 += 4;
157 v4 += 4;
158 v5 += 4;
159 } while (--lines > 0);
160}
1// SPDX-License-Identifier: GPL-2.0-or-later
2/*
3 *
4 * Copyright (C) IBM Corporation, 2012
5 *
6 * Author: Anton Blanchard <anton@au.ibm.com>
7 */
8
9/*
10 * Sparse (as at v0.5.0) gets very, very confused by this file.
11 * Make it a bit simpler for it.
12 */
13#if !defined(__CHECKER__)
14#include <altivec.h>
15#else
16#define vec_xor(a, b) a ^ b
17#define vector __attribute__((vector_size(16)))
18#endif
19
20#include "xor_vmx.h"
21
22typedef vector signed char unative_t;
23
24#define DEFINE(V) \
25 unative_t *V = (unative_t *)V##_in; \
26 unative_t V##_0, V##_1, V##_2, V##_3
27
28#define LOAD(V) \
29 do { \
30 V##_0 = V[0]; \
31 V##_1 = V[1]; \
32 V##_2 = V[2]; \
33 V##_3 = V[3]; \
34 } while (0)
35
36#define STORE(V) \
37 do { \
38 V[0] = V##_0; \
39 V[1] = V##_1; \
40 V[2] = V##_2; \
41 V[3] = V##_3; \
42 } while (0)
43
44#define XOR(V1, V2) \
45 do { \
46 V1##_0 = vec_xor(V1##_0, V2##_0); \
47 V1##_1 = vec_xor(V1##_1, V2##_1); \
48 V1##_2 = vec_xor(V1##_2, V2##_2); \
49 V1##_3 = vec_xor(V1##_3, V2##_3); \
50 } while (0)
51
52void __xor_altivec_2(unsigned long bytes,
53 unsigned long * __restrict v1_in,
54 const unsigned long * __restrict v2_in)
55{
56 DEFINE(v1);
57 DEFINE(v2);
58 unsigned long lines = bytes / (sizeof(unative_t)) / 4;
59
60 do {
61 LOAD(v1);
62 LOAD(v2);
63 XOR(v1, v2);
64 STORE(v1);
65
66 v1 += 4;
67 v2 += 4;
68 } while (--lines > 0);
69}
70
71void __xor_altivec_3(unsigned long bytes,
72 unsigned long * __restrict v1_in,
73 const unsigned long * __restrict v2_in,
74 const unsigned long * __restrict v3_in)
75{
76 DEFINE(v1);
77 DEFINE(v2);
78 DEFINE(v3);
79 unsigned long lines = bytes / (sizeof(unative_t)) / 4;
80
81 do {
82 LOAD(v1);
83 LOAD(v2);
84 LOAD(v3);
85 XOR(v1, v2);
86 XOR(v1, v3);
87 STORE(v1);
88
89 v1 += 4;
90 v2 += 4;
91 v3 += 4;
92 } while (--lines > 0);
93}
94
95void __xor_altivec_4(unsigned long bytes,
96 unsigned long * __restrict v1_in,
97 const unsigned long * __restrict v2_in,
98 const unsigned long * __restrict v3_in,
99 const unsigned long * __restrict v4_in)
100{
101 DEFINE(v1);
102 DEFINE(v2);
103 DEFINE(v3);
104 DEFINE(v4);
105 unsigned long lines = bytes / (sizeof(unative_t)) / 4;
106
107 do {
108 LOAD(v1);
109 LOAD(v2);
110 LOAD(v3);
111 LOAD(v4);
112 XOR(v1, v2);
113 XOR(v3, v4);
114 XOR(v1, v3);
115 STORE(v1);
116
117 v1 += 4;
118 v2 += 4;
119 v3 += 4;
120 v4 += 4;
121 } while (--lines > 0);
122}
123
124void __xor_altivec_5(unsigned long bytes,
125 unsigned long * __restrict v1_in,
126 const unsigned long * __restrict v2_in,
127 const unsigned long * __restrict v3_in,
128 const unsigned long * __restrict v4_in,
129 const unsigned long * __restrict v5_in)
130{
131 DEFINE(v1);
132 DEFINE(v2);
133 DEFINE(v3);
134 DEFINE(v4);
135 DEFINE(v5);
136 unsigned long lines = bytes / (sizeof(unative_t)) / 4;
137
138 do {
139 LOAD(v1);
140 LOAD(v2);
141 LOAD(v3);
142 LOAD(v4);
143 LOAD(v5);
144 XOR(v1, v2);
145 XOR(v3, v4);
146 XOR(v1, v5);
147 XOR(v1, v3);
148 STORE(v1);
149
150 v1 += 4;
151 v2 += 4;
152 v3 += 4;
153 v4 += 4;
154 v5 += 4;
155 } while (--lines > 0);
156}