5c5b31975e
As noted in the PR, we were no longer using ST3 for the testcase and instead stored each lane individually. This is because we'd split the store group during SLP and couldn't recover when SLP failed. However, we can also get better code with ST3 and ST4 even if SLP would have succeeded, such as for vect-complex-5.c. I'm not sure exactly where the cut-off point is, but it seems reasonable to allow the split if either of the new groups would operate on full vectors *within* rather than across scalar loop iterations. E.g. on a Cortex-A57, pr99873_3.c performs better using ST4 while pr99873_2.c performs better with SLP. Another factor is that SLP can handle smaller iteration counts than IFN_STORE_LANES can, but we don't have the infrastructure to choose reliably based on that. gcc/ PR tree-optimization/99873 * tree-vect-slp.c (vect_slp_prefer_store_lanes_p): New function. (vect_build_slp_instance): Don't split store groups that could use IFN_STORE_LANES. gcc/testsuite/ * gcc.dg/vect/slp-21.c: Only expect 2 of the loops to use SLP if IFN_STORE_LANES is available. * gcc.dg/vect/vect-complex-5.c: Expect no loops to use SLP if IFN_STORE_LANES is available. * gcc.target/aarch64/pr99873_1.c: New test. * gcc.target/aarch64/pr99873_2.c: Likewise. * gcc.target/aarch64/pr99873_3.c: Likewise. * gcc.target/aarch64/sve/pr99873_1.c: Likewise. * gcc.target/aarch64/sve/pr99873_2.c: Likewise. * gcc.target/aarch64/sve/pr99873_3.c: Likewise.
45 lines
1.0 KiB
C
45 lines
1.0 KiB
C
/* { dg-require-effective-target vect_int } */
|
|
|
|
#include <stdarg.h>
|
|
#include "tree-vect.h"
|
|
|
|
#define N 16
|
|
|
|
struct foostr {
|
|
_Complex short f1;
|
|
_Complex short f2;
|
|
};
|
|
|
|
_Complex short a1[64] __attribute__ ((__aligned__(__BIGGEST_ALIGNMENT__)));
|
|
_Complex short a2[64] __attribute__ ((__aligned__(__BIGGEST_ALIGNMENT__)));
|
|
_Complex short b1[64] __attribute__ ((__aligned__(__BIGGEST_ALIGNMENT__)));
|
|
_Complex short b2[64] __attribute__ ((__aligned__(__BIGGEST_ALIGNMENT__)));
|
|
struct foostr c[64] __attribute__ ((__aligned__(__BIGGEST_ALIGNMENT__)));
|
|
|
|
__attribute__ ((noinline)) void
|
|
foo (void)
|
|
{
|
|
int i;
|
|
|
|
for (i = 0; i < N; i++)
|
|
{
|
|
c[i].f1 = a1[i] + b1[i];
|
|
c[i].f2 = a2[i] + b2[i];
|
|
}
|
|
|
|
}
|
|
|
|
int
|
|
main (void)
|
|
{
|
|
int i;
|
|
check_vect ();
|
|
|
|
foo ();
|
|
|
|
return 0;
|
|
}
|
|
|
|
/* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 0 "vect" { target vect_load_lanes } } } */
|
|
/* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 2 "vect" { target { ! vect_load_lanes } xfail { ! vect_hw_misalign } } } } */
|