blob: 1bd2ce4ddf20b7e4e19b62e7f4917a36621d3548 (
plain)
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
|
/* Test that the compiler properly optimizes floating point multiply and add
instructions vector into vfmaddps on FMA4 systems. */
/* { dg-do compile } */
/* { dg-require-effective-target lp64 } */
/* { dg-options "-O2 -mfma4 -ftree-vectorize -mtune=generic" } */
extern void exit (int);
typedef float __m256 __attribute__ ((__vector_size__ (32), __may_alias__));
typedef double __m256d __attribute__ ((__vector_size__ (32), __may_alias__));
#define SIZE 10240
union {
__m256 f_align;
__m256d d_align;
float f[SIZE];
double d[SIZE];
} a, b, c, d;
void
flt_mul_add (void)
{
int i;
for (i = 0; i < SIZE; i++)
a.f[i] = (b.f[i] * c.f[i]) + d.f[i];
}
void
dbl_mul_add (void)
{
int i;
for (i = 0; i < SIZE; i++)
a.d[i] = (b.d[i] * c.d[i]) + d.d[i];
}
void
flt_mul_sub (void)
{
int i;
for (i = 0; i < SIZE; i++)
a.f[i] = (b.f[i] * c.f[i]) - d.f[i];
}
void
dbl_mul_sub (void)
{
int i;
for (i = 0; i < SIZE; i++)
a.d[i] = (b.d[i] * c.d[i]) - d.d[i];
}
void
flt_neg_mul_add (void)
{
int i;
for (i = 0; i < SIZE; i++)
a.f[i] = (-(b.f[i] * c.f[i])) + d.f[i];
}
void
dbl_neg_mul_add (void)
{
int i;
for (i = 0; i < SIZE; i++)
a.d[i] = (-(b.d[i] * c.d[i])) + d.d[i];
}
int main ()
{
flt_mul_add ();
flt_mul_sub ();
flt_neg_mul_add ();
dbl_mul_add ();
dbl_mul_sub ();
dbl_neg_mul_add ();
exit (0);
}
/* { dg-final { scan-assembler "vfmaddps" } } */
/* { dg-final { scan-assembler "vfmaddpd" } } */
/* { dg-final { scan-assembler "vfmsubps" } } */
/* { dg-final { scan-assembler "vfmsubpd" } } */
/* { dg-final { scan-assembler "vfnmaddps" } } */
/* { dg-final { scan-assembler "vfnmaddpd" } } */
|
