blob: 11e65e0c2b4e4fea8775c7b2783ab6a1acc3f43d (
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
|
/* { dg-do compile } */
/* { dg-options "-O3 -mdejagnu-cpu=power9 -mvsx" } */
/* { dg-require-effective-target powerpc_vsx } */
/* Verify that we vectorize this SAD loop using vabsduh. */
extern int abs (int __x) __attribute__ ((__nothrow__, __leaf__)) __attribute__ ((__const__));
static int
foo (unsigned short *w, int i, unsigned short *x, int j)
{
int tot = 0;
for (int a = 0; a < 16; a++)
{
for (int b = 0; b < 8; b++)
tot += abs (w[b] - x[b]);
w += i;
x += j;
}
return tot;
}
void
bar (unsigned short *w, unsigned short *x, int i, int *result)
{
*result = foo (w, 8, x, i);
}
/* { dg-final { scan-assembler-times "vabsduh" 16 } } */
/* { dg-final { scan-assembler-times "vsum4shs" 16 } } */
/* { dg-final { scan-assembler-times "vadduwm" 17 } } */
/* Note: One of the 16 adds is optimized out (add with zero),
leaving 15. The extra two adds are for the final reduction. */
|
