1 /*
2
3 Copyright (c) 2009, 2010, 2011 STMicroelectronics
4 Written by Christophe Lyon
5
6 Permission is hereby granted, free of charge, to any person obtaining a copy
7 of this software and associated documentation files (the "Software"), to deal
8 in the Software without restriction, including without limitation the rights
9 to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
10 copies of the Software, and to permit persons to whom the Software is
11 furnished to do so, subject to the following conditions:
12
13 The above copyright notice and this permission notice shall be included in
14 all copies or substantial portions of the Software.
15
16 THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
17 IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
18 FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
19 AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
20 LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
21 OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
22 THE SOFTWARE.
23
24 */
25
26 #if defined(__arm__) || defined(__aarch64__)
27 #include <arm_neon.h>
28 #else
29 #include "stm-arm-neon.h"
30 #endif
31
32 #include "stm-arm-neon-ref.h"
33
34 #define TEST_MSG "VABAL"
exec_vabal(void)35 void exec_vabal (void)
36 {
37 /* Basic test: v4=vabal(v1,v2,v3), then store the result. */
38 #define TEST_VABAL(T1, T2, W, W2, N) \
39 VECT_VAR(vector_res, T1, W2, N) = \
40 vabal_##T2##W(VECT_VAR(vector1, T1, W2, N), \
41 VECT_VAR(vector2, T1, W, N), \
42 VECT_VAR(vector3, T1, W, N)); \
43 vst1q_##T2##W2(VECT_VAR(result, T1, W2, N), VECT_VAR(vector_res, T1, W2, N))
44
45 /* With ARM RVCT, we need to declare variables before any executable
46 statement */
47 #define DECL_VABAL_VAR_LONG(VAR) \
48 DECL_VARIABLE(VAR, int, 16, 8); \
49 DECL_VARIABLE(VAR, int, 32, 4); \
50 DECL_VARIABLE(VAR, int, 64, 2); \
51 DECL_VARIABLE(VAR, uint, 16, 8); \
52 DECL_VARIABLE(VAR, uint, 32, 4); \
53 DECL_VARIABLE(VAR, uint, 64, 2)
54
55 #define DECL_VABAL_VAR_SHORT(VAR) \
56 DECL_VARIABLE(VAR, int, 8, 8); \
57 DECL_VARIABLE(VAR, int, 16, 4); \
58 DECL_VARIABLE(VAR, int, 32, 2); \
59 DECL_VARIABLE(VAR, uint, 8, 8); \
60 DECL_VARIABLE(VAR, uint, 16, 4); \
61 DECL_VARIABLE(VAR, uint, 32, 2)
62
63 DECL_VABAL_VAR_LONG(vector1);
64 DECL_VABAL_VAR_SHORT(vector2);
65 DECL_VABAL_VAR_SHORT(vector3);
66 DECL_VABAL_VAR_LONG(vector_res);
67
68 clean_results ();
69
70 /* Initialize input "vector" from "buffer" */
71 VLOAD(vector1, buffer, q, int, s, 16, 8);
72 VLOAD(vector1, buffer, q, int, s, 32, 4);
73 VLOAD(vector1, buffer, q, int, s, 64, 2);
74 VLOAD(vector1, buffer, q, uint, u, 16, 8);
75 VLOAD(vector1, buffer, q, uint, u, 32, 4);
76 VLOAD(vector1, buffer, q, uint, u, 64, 2);
77
78
79 /* Choose init value arbitrarily */
80 VDUP(vector2, , int, s, 8, 8, 1);
81 VDUP(vector2, , int, s, 16, 4, -13);
82 VDUP(vector2, , int, s, 32, 2, 8);
83 VDUP(vector2, , uint, u, 8, 8, 1);
84 VDUP(vector2, , uint, u, 16, 4, 13);
85 VDUP(vector2, , uint, u, 32, 2, 8);
86
87 /* Choose init value arbitrarily */
88 VDUP(vector3, , int, s, 8, 8, -5);
89 VDUP(vector3, , int, s, 16, 4, 25);
90 VDUP(vector3, , int, s, 32, 2, -40);
91 VDUP(vector3, , uint, u, 8, 8, 100);
92 VDUP(vector3, , uint, u, 16, 4, 2340);
93 VDUP(vector3, , uint, u, 32, 2, 0xffffffff);
94
95 TEST_VABAL(int, s, 8, 16, 8);
96 TEST_VABAL(int, s, 16, 32, 4);
97 TEST_VABAL(int, s, 32, 64, 2);
98 TEST_VABAL(uint, u, 8, 16, 8);
99 TEST_VABAL(uint, u, 16, 32, 4);
100 TEST_VABAL(uint, u, 32, 64, 2);
101
102 dump_results_hex (TEST_MSG);
103
104 /* Use values that could lead to overflow intermediate
105 * calculations. */
106 VDUP(vector2, , int, s, 8, 8, 0x80);
107 VDUP(vector2, , int, s, 16, 4, 0x8000);
108 VDUP(vector2, , int, s, 32, 2, 0x80000000);
109 VDUP(vector2, , uint, u, 8, 8, 1);
110 VDUP(vector2, , uint, u, 16, 4, 13);
111 VDUP(vector2, , uint, u, 32, 2, 8);
112
113 VDUP(vector3, , int, s, 8, 8, 0x7f);
114 VDUP(vector3, , int, s, 16, 4, 0x7fff);
115 VDUP(vector3, , int, s, 32, 2, 0x7fffffff);
116 VDUP(vector3, , uint, u, 8, 8, 0xff);
117 VDUP(vector3, , uint, u, 16, 4, 0xffff);
118 VDUP(vector3, , uint, u, 32, 2, 0xffffffff);
119
120 TEST_VABAL(int, s, 8, 16, 8);
121 TEST_VABAL(int, s, 16, 32, 4);
122 TEST_VABAL(int, s, 32, 64, 2);
123 TEST_VABAL(uint, u, 8, 16, 8);
124 TEST_VABAL(uint, u, 16, 32, 4);
125 TEST_VABAL(uint, u, 32, 64, 2);
126
127 dump_results_hex2 (TEST_MSG, " test intermediate overflow");
128 }
129