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
|
/* { dg-do compile } */
/* { dg-require-effective-target arm_v8_2a_fp16_neon_ok } */
/* { dg-options "-O2 -ffast-math" } */
/* { dg-add-options arm_v8_2a_fp16_neon } */
/* Test instructions generated for half-precision arithmetic. */
typedef __fp16 float16_t;
typedef __simd64_float16_t float16x4_t;
typedef __simd128_float16_t float16x8_t;
typedef short int16x4_t __attribute__ ((vector_size (8)));
typedef short int int16x8_t __attribute__ ((vector_size (16)));
float16_t
fp16_abs (float16_t a)
{
return (a < 0) ? -a : a;
}
#define TEST_UNOP(NAME, OPERATOR, TY) \
TY test_##NAME##_##TY (TY a) \
{ \
return OPERATOR (a); \
}
#define TEST_BINOP(NAME, OPERATOR, TY) \
TY test_##NAME##_##TY (TY a, TY b) \
{ \
return a OPERATOR b; \
}
#define TEST_CMP(NAME, OPERATOR, RTY, TY) \
RTY test_##NAME##_##TY (TY a, TY b) \
{ \
return a OPERATOR b; \
}
/* Scalars. */
TEST_UNOP (neg, -, float16_t)
TEST_UNOP (abs, fp16_abs, float16_t)
TEST_BINOP (add, +, float16_t)
TEST_BINOP (sub, -, float16_t)
TEST_BINOP (mult, *, float16_t)
TEST_BINOP (div, /, float16_t)
TEST_CMP (equal, ==, int, float16_t)
TEST_CMP (unequal, !=, int, float16_t)
TEST_CMP (lessthan, <, int, float16_t)
TEST_CMP (greaterthan, >, int, float16_t)
TEST_CMP (lessthanequal, <=, int, float16_t)
TEST_CMP (greaterthanqual, >=, int, float16_t)
/* Vectors of size 4. */
TEST_UNOP (neg, -, float16x4_t)
TEST_BINOP (add, +, float16x4_t)
TEST_BINOP (sub, -, float16x4_t)
TEST_BINOP (mult, *, float16x4_t)
TEST_BINOP (div, /, float16x4_t)
TEST_CMP (equal, ==, int16x4_t, float16x4_t)
TEST_CMP (unequal, !=, int16x4_t, float16x4_t)
TEST_CMP (lessthan, <, int16x4_t, float16x4_t)
TEST_CMP (greaterthan, >, int16x4_t, float16x4_t)
TEST_CMP (lessthanequal, <=, int16x4_t, float16x4_t)
TEST_CMP (greaterthanqual, >=, int16x4_t, float16x4_t)
/* Vectors of size 8. */
TEST_UNOP (neg, -, float16x8_t)
TEST_BINOP (add, +, float16x8_t)
TEST_BINOP (sub, -, float16x8_t)
TEST_BINOP (mult, *, float16x8_t)
TEST_BINOP (div, /, float16x8_t)
TEST_CMP (equal, ==, int16x8_t, float16x8_t)
TEST_CMP (unequal, !=, int16x8_t, float16x8_t)
TEST_CMP (lessthan, <, int16x8_t, float16x8_t)
TEST_CMP (greaterthan, >, int16x8_t, float16x8_t)
TEST_CMP (lessthanequal, <=, int16x8_t, float16x8_t)
TEST_CMP (greaterthanqual, >=, int16x8_t, float16x8_t)
/* { dg-final { scan-assembler-times {vneg\.f16\ts[0-9]+, s[0-9]+} 1 } } */
/* { dg-final { scan-assembler-times {vneg\.f16\td[0-9]+, d[0-9]+} 1 } } */
/* { dg-final { scan-assembler-times {vneg\.f16\tq[0-9]+, q[0-9]+} 1 } } */
/* { dg-final { scan-assembler-times {vabs\.f16\ts[0-9]+, s[0-9]+} 2 } } */
/* { dg-final { scan-assembler-times {vadd\.f16\ts[0-9]+, s[0-9]+, s[0-9]+} 13 } } */
/* { dg-final { scan-assembler-times {vsub\.f16\ts[0-9]+, s[0-9]+, s[0-9]+} 13 } } */
/* { dg-final { scan-assembler-times {vmul\.f16\ts[0-9]+, s[0-9]+, s[0-9]+} 13 } } */
/* { dg-final { scan-assembler-times {vdiv\.f16\ts[0-9]+, s[0-9]+, s[0-9]+} 13 } } */
/* { dg-final { scan-assembler-times {vcmp\.f32\ts[0-9]+, s[0-9]+} 26 } } */
/* { dg-final { scan-assembler-times {vcmpe\.f32\ts[0-9]+, s[0-9]+} 52 } } */
/* { dg-final { scan-assembler-not {vadd\.f32} } } */
/* { dg-final { scan-assembler-not {vsub\.f32} } } */
/* { dg-final { scan-assembler-not {vmul\.f32} } } */
/* { dg-final { scan-assembler-not {vdiv\.f32} } } */
/* { dg-final { scan-assembler-not {vcmp\.f16} } } */
/* { dg-final { scan-assembler-not {vcmpe\.f16} } } */
|
