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
|
/* { dg-require-effective-target vect_int } */
/* { dg-require-effective-target vect_shift } */
#include <stdarg.h>
#include "tree-vect.h"
#define N 512
/* Modified rgb to rgb conversion from FFmpeg. */
__attribute__ ((noinline)) void
foo (unsigned char *src, unsigned char *dst)
{
unsigned char *s = src;
int *d = (int *)dst;
int i;
for (i = 0; i < N/4; i++)
{
const int b = *s++;
const int g = *s++;
const int r = *s++;
const int a = *s++;
*d = ((b>>3) | ((g&0xFC)<<3) | ((r&0xF8)<<8) | (a>>5));
d++;
}
s = src;
d = (int *)dst;
#pragma GCC novector
for (i = 0; i < N/4; i++)
{
const int b = *s++;
const int g = *s++;
const int r = *s++;
const int a = *s++;
if (*d != ((b>>3) | ((g&0xFC)<<3) | ((r&0xF8)<<8) | (a>>5)))
abort ();
d++;
}
}
int main (void)
{
int i;
unsigned char in[N], out[N];
check_vect ();
for (i = 0; i < N; i++)
{
in[i] = i;
out[i] = 255;
__asm__ volatile ("");
}
foo (in, out);
return 0;
}
/* This is an over-widening even though the final result is still an int.
It's better to do one vector of ops on chars and then widen than to
widen and then do 4 vectors of ops on ints. */
/* { dg-final { scan-tree-dump {vect_recog_over_widening_pattern: detected:[^\n]* << 3} "vect" } } */
/* { dg-final { scan-tree-dump {vect_recog_over_widening_pattern: detected:[^\n]* >> 3} "vect" } } */
/* { dg-final { scan-tree-dump {vect_recog_over_widening_pattern: detected:[^\n]* << 8} "vect" } } */
/* { dg-final { scan-tree-dump {vect_recog_over_widening_pattern: detected:[^\n]* >> 5} "vect" } } */
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
|
