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
|
#ifndef HAVE_SAT_ARITH
#define HAVE_SAT_ARITH
#include <stdint-gcc.h>
/******************************************************************************/
/* Saturation Add (unsigned and signed) */
/******************************************************************************/
#define DEF_SAT_U_ADD_FMT_1(T) \
T __attribute__((noinline)) \
sat_u_add_##T##_fmt_1 (T x, T y) \
{ \
return (x + y) | (-(T)((T)(x + y) < x)); \
}
#define DEF_SAT_U_ADD_FMT_2(T) \
T __attribute__((noinline)) \
sat_u_add_##T##_fmt_2 (T x, T y) \
{ \
return (T)(x + y) >= x ? (x + y) : -1; \
}
#define DEF_SAT_U_ADD_FMT_3(T) \
T __attribute__((noinline)) \
sat_u_add_##T##_fmt_3 (T x, T y) \
{ \
T ret; \
T overflow = __builtin_add_overflow (x, y, &ret); \
return (T)(-overflow) | ret; \
}
#define DEF_SAT_U_ADD_FMT_4(T) \
T __attribute__((noinline)) \
sat_u_add_##T##_fmt_4 (T x, T y) \
{ \
T ret; \
return __builtin_add_overflow (x, y, &ret) ? -1 : ret; \
}
#define DEF_SAT_U_ADD_FMT_5(T) \
T __attribute__((noinline)) \
sat_u_add_##T##_fmt_5 (T x, T y) \
{ \
T ret; \
return __builtin_add_overflow (x, y, &ret) == 0 ? ret : -1; \
}
#define DEF_SAT_U_ADD_FMT_6(T) \
T __attribute__((noinline)) \
sat_u_add_##T##_fmt_6 (T x, T y) \
{ \
return (T)(x + y) < x ? -1 : (x + y); \
}
#define DEF_VEC_SAT_U_ADD_FMT_1(T) \
void __attribute__((noinline)) \
vec_sat_u_add_##T##_fmt_1 (T *out, T *op_1, T *op_2, unsigned limit) \
{ \
unsigned i; \
for (i = 0; i < limit; i++) \
{ \
T x = op_1[i]; \
T y = op_2[i]; \
out[i] = (x + y) | (-(T)((T)(x + y) < x)); \
} \
}
#define RUN_SAT_U_ADD_FMT_1(T, x, y) sat_u_add_##T##_fmt_1(x, y)
#define RUN_SAT_U_ADD_FMT_2(T, x, y) sat_u_add_##T##_fmt_2(x, y)
#define RUN_SAT_U_ADD_FMT_3(T, x, y) sat_u_add_##T##_fmt_3(x, y)
#define RUN_SAT_U_ADD_FMT_4(T, x, y) sat_u_add_##T##_fmt_4(x, y)
#define RUN_SAT_U_ADD_FMT_5(T, x, y) sat_u_add_##T##_fmt_5(x, y)
#define RUN_SAT_U_ADD_FMT_6(T, x, y) sat_u_add_##T##_fmt_6(x, y)
#define RUN_VEC_SAT_U_ADD_FMT_1(T, out, op_1, op_2, N) \
vec_sat_u_add_##T##_fmt_1(out, op_1, op_2, N)
/******************************************************************************/
/* Saturation Sub (Unsigned and Signed) */
/******************************************************************************/
#define DEF_SAT_U_SUB_FMT_1(T) \
T __attribute__((noinline)) \
sat_u_sub_##T##_fmt_1 (T x, T y) \
{ \
return (x - y) & (-(T)(x >= y)); \
}
#define DEF_SAT_U_SUB_FMT_2(T) \
T __attribute__((noinline)) \
sat_u_sub_##T##_fmt_2 (T x, T y) \
{ \
return (x - y) & (-(T)(x > y)); \
}
#define DEF_SAT_U_SUB_FMT_3(T) \
T __attribute__((noinline)) \
sat_u_sub_##T##_fmt_3 (T x, T y) \
{ \
return x > y ? x - y : 0; \
}
#define DEF_SAT_U_SUB_FMT_4(T) \
T __attribute__((noinline)) \
sat_u_sub_##T##_fmt_4 (T x, T y) \
{ \
return x >= y ? x - y : 0; \
}
#define DEF_SAT_U_SUB_FMT_5(T) \
T __attribute__((noinline)) \
sat_u_sub_##T##_fmt_5 (T x, T y) \
{ \
return x < y ? 0 : x - y; \
}
#define DEF_SAT_U_SUB_FMT_6(T) \
T __attribute__((noinline)) \
sat_u_sub_##T##_fmt_6 (T x, T y) \
{ \
return x <= y ? 0 : x - y; \
}
#define DEF_SAT_U_SUB_FMT_7(T) \
T __attribute__((noinline)) \
sat_u_sub_##T##_fmt_7 (T x, T y) \
{ \
T ret; \
T overflow = __builtin_sub_overflow (x, y, &ret); \
return ret & (T)(overflow - 1); \
}
#define DEF_SAT_U_SUB_FMT_8(T) \
T __attribute__((noinline)) \
sat_u_sub_##T##_fmt_8 (T x, T y) \
{ \
T ret; \
T overflow = __builtin_sub_overflow (x, y, &ret); \
return ret & (T)-(!overflow); \
}
#define DEF_SAT_U_SUB_FMT_9(T) \
T __attribute__((noinline)) \
sat_u_sub_##T##_fmt_9 (T x, T y) \
{ \
T ret; \
T overflow = __builtin_sub_overflow (x, y, &ret); \
return overflow ? 0 : ret; \
}
#define DEF_SAT_U_SUB_FMT_10(T) \
T __attribute__((noinline)) \
sat_u_sub_##T##_fmt_10 (T x, T y) \
{ \
T ret; \
T overflow = __builtin_sub_overflow (x, y, &ret); \
return !overflow ? ret : 0; \
}
#define RUN_SAT_U_SUB_FMT_1(T, x, y) sat_u_sub_##T##_fmt_1(x, y)
#define RUN_SAT_U_SUB_FMT_2(T, x, y) sat_u_sub_##T##_fmt_2(x, y)
#define RUN_SAT_U_SUB_FMT_3(T, x, y) sat_u_sub_##T##_fmt_3(x, y)
#define RUN_SAT_U_SUB_FMT_4(T, x, y) sat_u_sub_##T##_fmt_4(x, y)
#define RUN_SAT_U_SUB_FMT_5(T, x, y) sat_u_sub_##T##_fmt_5(x, y)
#define RUN_SAT_U_SUB_FMT_6(T, x, y) sat_u_sub_##T##_fmt_6(x, y)
#define RUN_SAT_U_SUB_FMT_7(T, x, y) sat_u_sub_##T##_fmt_7(x, y)
#define RUN_SAT_U_SUB_FMT_8(T, x, y) sat_u_sub_##T##_fmt_8(x, y)
#define RUN_SAT_U_SUB_FMT_9(T, x, y) sat_u_sub_##T##_fmt_9(x, y)
#define RUN_SAT_U_SUB_FMT_10(T, x, y) sat_u_sub_##T##_fmt_10(x, y)
#define DEF_VEC_SAT_U_SUB_FMT_1(T) \
void __attribute__((noinline)) \
vec_sat_u_sub_##T##_fmt_1 (T *out, T *op_1, T *op_2, unsigned limit) \
{ \
unsigned i; \
for (i = 0; i < limit; i++) \
{ \
T x = op_1[i]; \
T y = op_2[i]; \
out[i] = (x - y) & (-(T)(x >= y)); \
} \
}
#define DEF_VEC_SAT_U_SUB_FMT_2(T) \
void __attribute__((noinline)) \
vec_sat_u_sub_##T##_fmt_2 (T *out, T *op_1, T *op_2, unsigned limit) \
{ \
unsigned i; \
for (i = 0; i < limit; i++) \
{ \
T x = op_1[i]; \
T y = op_2[i]; \
out[i] = (x - y) & (-(T)(x > y)); \
} \
}
#define RUN_VEC_SAT_U_SUB_FMT_1(T, out, op_1, op_2, N) \
vec_sat_u_sub_##T##_fmt_1(out, op_1, op_2, N)
#define RUN_VEC_SAT_U_SUB_FMT_2(T, out, op_1, op_2, N) \
vec_sat_u_sub_##T##_fmt_2(out, op_1, op_2, N)
#endif
|
