blob: 93ca0ff2e96d1b97f430283c5226be0c3a4e320d (
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
62
|
/* { dg-require-effective-target vect_int } */
#include <stdarg.h>
#include "tree-vect.h"
#define N 64
#define DOT1 21834
#define DOT2 21876
unsigned short X[N] __attribute__ ((__aligned__(__BIGGEST_ALIGNMENT__)));
unsigned short Y[N] __attribute__ ((__aligned__(__BIGGEST_ALIGNMENT__)));
/* short->short->int dot product.
Not detected as a dot-product pattern.
Requires support for non-widneing multiplication and widening-summation.
Vectorized with loop-aware SLP. */
__attribute__ ((noinline)) unsigned int
foo1(int len, int *result1, int *result2)
{
int i;
unsigned int res1 = 10, res2 = 20;
unsigned short prod;
for (i=0; i<len; i++) {
prod = X[2*i] * Y[2*i];
res1 += prod;
prod = X[2*i+1] * Y[2*i+1];
res2 += prod;
}
*result1 = res1;
*result2 = res2;
return 0;
}
int main (void)
{
unsigned int dot1, dot2;
unsigned short i;
check_vect ();
for (i=0; i<N; i++) {
X[i] = i;
Y[i] = 64-i;
}
foo1 (N/2, &dot1, &dot2);
if (dot1 != DOT1 || dot2 != DOT2)
abort ();
return 0;
}
/* The initialization loop in main also gets vectorized. */
/* { dg-final { scan-tree-dump-times "vect_recog_dot_prod_pattern: detected" 1 "vect" { xfail *-*-* } } } */
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 2 "vect" { target { vect_short_mult && { vect_widen_sum_hi_to_si && vect_unpack } } } } } */
/* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 1 "vect" { xfail { vect_widen_sum_hi_to_si_pattern || { ! vect_unpack } } } } } */
/* { dg-final { cleanup-tree-dump "vect" } } */
|
