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
|
/* Test that the compiler properly optimizes floating point multiply
and add instructions into vfmaddss, vfmsubss, vfnmaddss,
vfnmsubss on FMA4 systems. */
/* { dg-do compile } */
/* { dg-require-effective-target lp64 } */
/* { dg-options "-O2 -mfma4" } */
extern void exit (int);
float
flt_mul_add (float a, float b, float c)
{
return (a * b) + c;
}
double
dbl_mul_add (double a, double b, double c)
{
return (a * b) + c;
}
float
flt_mul_sub (float a, float b, float c)
{
return (a * b) - c;
}
double
dbl_mul_sub (double a, double b, double c)
{
return (a * b) - c;
}
float
flt_neg_mul_add (float a, float b, float c)
{
return (-(a * b)) + c;
}
double
dbl_neg_mul_add (double a, double b, double c)
{
return (-(a * b)) + c;
}
float
flt_neg_mul_sub (float a, float b, float c)
{
return (-(a * b)) - c;
}
double
dbl_neg_mul_sub (double a, double b, double c)
{
return (-(a * b)) - c;
}
float f[10] = { 2, 3, 4 };
double d[10] = { 2, 3, 4 };
int main ()
{
f[3] = flt_mul_add (f[0], f[1], f[2]);
f[4] = flt_mul_sub (f[0], f[1], f[2]);
f[5] = flt_neg_mul_add (f[0], f[1], f[2]);
f[6] = flt_neg_mul_sub (f[0], f[1], f[2]);
d[3] = dbl_mul_add (d[0], d[1], d[2]);
d[4] = dbl_mul_sub (d[0], d[1], d[2]);
d[5] = dbl_neg_mul_add (d[0], d[1], d[2]);
d[6] = dbl_neg_mul_sub (d[0], d[1], d[2]);
exit (0);
}
/* { dg-final { scan-assembler "vfmaddss" } } */
/* { dg-final { scan-assembler "vfmaddsd" } } */
/* { dg-final { scan-assembler "vfmsubss" } } */
/* { dg-final { scan-assembler "vfmsubsd" } } */
/* { dg-final { scan-assembler "vfnmaddss" } } */
/* { dg-final { scan-assembler "vfnmaddsd" } } */
/* { dg-final { scan-assembler "vfnmsubss" } } */
/* { dg-final { scan-assembler "vfnmsubsd" } } */
|
