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
|
/* { dg-do compile { target { powerpc*-*-* } } } */
/* { dg-skip-if "" { powerpc*-*-darwin* } { "*" } { "" } } */
/* { dg-require-effective-target powerpc_altivec_ok } */
/* { dg-options "-O3 -ftree-vectorize -mcpu=power6 -maltivec -ffast-math -ffp-contract=off" } */
/* { dg-final { scan-assembler-times "vmaddfp" 1 } } */
/* { dg-final { scan-assembler-times "fmadd " 1 } } */
/* { dg-final { scan-assembler-times "fmadds" 1 } } */
/* { dg-final { scan-assembler-times "fmsub " 1 } } */
/* { dg-final { scan-assembler-times "fmsubs" 1 } } */
/* { dg-final { scan-assembler-times "fnmadd " 1 } } */
/* { dg-final { scan-assembler-times "fnmadds" 1 } } */
/* { dg-final { scan-assembler-times "fnmsub " 1 } } */
/* { dg-final { scan-assembler-times "fnmsubs" 1 } } */
/* Only the functions calling the builtin should generate an appropriate
(a * b) + c instruction. */
double
builtin_fma (double b, double c, double d)
{
return __builtin_fma (b, c, d); /* fmadd */
}
double
builtin_fms (double b, double c, double d)
{
return __builtin_fma (b, c, -d); /* fmsub */
}
double
builtin_fnma (double b, double c, double d)
{
return - __builtin_fma (b, c, d); /* fnmadd */
}
double
builtin_fnms (double b, double c, double d)
{
return - __builtin_fma (b, c, -d); /* fnmsub */
}
float
builtin_fmaf (float b, float c, float d)
{
return __builtin_fmaf (b, c, d); /* fmadds */
}
float
builtin_fmsf (float b, float c, float d)
{
return __builtin_fmaf (b, c, -d); /* fmsubs */
}
float
builtin_fnmaf (float b, float c, float d)
{
return - __builtin_fmaf (b, c, d); /* fnmadds */
}
float
builtin_fnmsf (float b, float c, float d)
{
return - __builtin_fmaf (b, c, -d); /* fnmsubs */
}
double
normal_fma (double b, double c, double d)
{
return (b * c) + d; /* fmul/fadd */
}
float
normal_fmaf (float b, float c, float d)
{
return (b * c) + d; /* fmuls/fadds */
}
#ifndef SIZE
#define SIZE 1024
#endif
float vfa[SIZE] __attribute__((__aligned__(32)));
float vfb[SIZE] __attribute__((__aligned__(32)));
float vfc[SIZE] __attribute__((__aligned__(32)));
float vfd[SIZE] __attribute__((__aligned__(32)));
void
vector_fmaf (void)
{
int i;
for (i = 0; i < SIZE; i++)
vfa[i] = __builtin_fmaf (vfb[i], vfc[i], vfd[i]); /* vaddfp */
}
|
