blob: d44d585ff25aed7394945cff64f20923b5600061 (
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
|
/* { dg-require-effective-target vect_int } */
#include <stdarg.h>
#include "tree-vect.h"
#define A 3
#define B 4
#define N 256
short src[N], dst[N];
void foo (short * __restrict__ dst, short * __restrict__ src, int h,
int stride)
{
int i;
h /= 16;
for (i = 0; i < h; i++)
{
dst[0] += A*src[0] + src[stride];
dst[1] += A*src[1] + src[1+stride];
dst[2] += A*src[2] + src[2+stride];
dst[3] += A*src[3] + src[3+stride];
dst[4] += A*src[4] + src[4+stride];
dst[5] += A*src[5] + src[5+stride];
dst[6] += A*src[6] + src[6+stride];
dst[7] += A*src[7] + src[7+stride];
dst += 8;
src += 8;
asm volatile ("" ::: "memory");
}
}
int main (void)
{
int i;
check_vect ();
for (i = 0; i < N; i++)
{
dst[i] = 0;
src[i] = i;
}
foo (dst, src, N, 8);
#pragma GCC novector
for (i = 0; i < N/2; i++)
{
if (dst[i] != A * i + i + 8)
abort ();
}
return 0;
}
/* Exclude POWER8 (only POWER cpu for which vect_element_align is true)
because loops have vectorized before SLP gets a shot. */
/* { dg-final { scan-tree-dump-times "optimized: basic block" 1 "slp1" { target { vect_element_align && { ! powerpc*-*-* } } } } } */
|
