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
|
/* Test that the compiler properly generates floating point multiply
and add instructions FMA4 systems. */
/* { dg-do compile } */
/* { dg-require-effective-target lp64 } */
/* { dg-options "-O2 -mfma4" } */
#ifndef __FP_FAST_FMAF
# error "__FP_FAST_FMAF should be defined"
#endif
#ifndef __FP_FAST_FMA
# error "__FP_FAST_FMA should be defined"
#endif
float
flt_mul_add (float a, float b, float c)
{
return __builtin_fmaf (a, b, c);
}
double
dbl_mul_add (double a, double b, double c)
{
return __builtin_fma (a, b, c);
}
float
flt_mul_sub (float a, float b, float c)
{
return __builtin_fmaf (a, b, -c);
}
double
dbl_mul_sub (double a, double b, double c)
{
return __builtin_fma (a, b, -c);
}
float
flt_neg_mul_add_1 (float a, float b, float c)
{
return __builtin_fmaf (-a, b, c);
}
double
dbl_neg_mul_add_1 (double a, double b, double c)
{
return __builtin_fma (-a, b, c);
}
float
flt_neg_mul_add_2 (float a, float b, float c)
{
return __builtin_fmaf (a, -b, c);
}
double
dbl_neg_mul_add_2 (double a, double b, double c)
{
return __builtin_fma (a, -b, c);
}
float
flt_neg_mul_sub (float a, float b, float c)
{
return __builtin_fmaf (-a, b, -c);
}
double
dbl_neg_mul_sub (double a, double b, double c)
{
return __builtin_fma (-a, b, -c);
}
/* { dg-final { scan-assembler-times "vfmaddss" 1 } } */
/* { dg-final { scan-assembler-times "vfmaddsd" 1 } } */
/* { dg-final { scan-assembler-times "vfmsubss" 1 } } */
/* { dg-final { scan-assembler-times "vfmsubsd" 1 } } */
/* { dg-final { scan-assembler-times "vfnmaddss" 2 } } */
/* { dg-final { scan-assembler-times "vfnmaddsd" 2 } } */
/* { dg-final { scan-assembler-times "vfnmsubss" 1 } } */
/* { dg-final { scan-assembler-times "vfnmsubsd" 1 } } */
|
