mirror/gcc
2
0
Fork 0
mirror of git://gcc.gnu.org/git/gcc.git synced 2025-03-21 17:21:03 +08:00
Code Issues Packages Projects Releases Wiki Activity

re PR tree-optimization/65518 (gcc consumes all memory with -O3)

Browse Source 
2015-03-23  Richard Biener  <rguenther@suse.de>

	PR tree-optimization/65518
	* tree-vect-stmts.c (vectorizable_load): Reject single-element
	interleaving cases we generate absymal code for.

	* gcc.dg/vect/pr65518.c: New testcase.

From-SVN: r221595
This commit is contained in:
Richard Biener 2015-03-23 14:59:57 +00:00 committed by Richard Biener
parent d886f7cc33
commit d5f035ea52
4 changed files with 70 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
gcc/ChangeLog
View File

@ -1,3 +1,9 @@
2015-03-23 Richard Biener <rguenther@suse.de>
PR tree-optimization/65518
* tree-vect-stmts.c (vectorizable_load): Reject single-element
interleaving cases we generate absymal code for.
2015-03-23 Richard Biener <rguenther@suse.de>
PR tree-optimization/65494

5
gcc/testsuite/ChangeLog
View File

@ -1,3 +1,8 @@
2015-03-23 Richard Biener <rguenther@suse.de>
PR tree-optimization/65518
* gcc.dg/vect/pr65518.c: New testcase.
2015-03-23 Richard Biener <rguenther@suse.de>
PR tree-optimization/65494

43
gcc/testsuite/gcc.dg/vect/pr65518.c Normal file
View File

@ -0,0 +1,43 @@
/* { dg-do run } */
extern void abort (void);
typedef struct giga
{
unsigned int g[16];
} giga;
unsigned long __attribute__((noinline,noclone))
addfst(giga const *gptr, int num)
{
unsigned int retval = 0;
int i;
for (i = 0; i < num; i++)
retval += gptr[i].g[0];
return retval;
}
int main ()
{
struct giga g[8];
unsigned int n = 1;
int i, j;
for (i = 0; i < 8; ++i)
for (j = 0; j < 16; ++j)
{
g[i].g[j] = n++;
__asm__ volatile ("");
}
if (addfst (g, 8) != 456)
abort ();
return 0;
}
/* We don't want to vectorize the single-element interleaving in the way
we currently do that (without ignoring not needed vectors in the
gap between gptr[0].g[0] and gptr[1].g[0]), because that's very
sub-optimal and causes memory explosion (even though the cost model
should reject that in the end). */
/* { dg-final { scan-tree-dump-times "vectorized 0 loops in function" 2 "vect" } } */
/* { dg-final { cleanup-tree-dump "vect" } } */

16
gcc/tree-vect-stmts.c
View File

@ -5780,6 +5780,22 @@ vectorizable_load (gimple stmt, gimple_stmt_iterator *gsi, gimple *vec_stmt,
gcc_assert (! nested_in_vect_loop && !STMT_VINFO_GATHER_P (stmt_info));
first_stmt = GROUP_FIRST_ELEMENT (stmt_info);
/* If this is single-element interleaving with an element distance
that leaves unused vector loads around punt - we at least create
very sub-optimal code in that case (and blow up memory,
see PR65518). */
if (first_stmt == stmt
&& !GROUP_NEXT_ELEMENT (stmt_info)
&& GROUP_SIZE (stmt_info) > TYPE_VECTOR_SUBPARTS (vectype))
{
if (dump_enabled_p ())
dump_printf_loc (MSG_MISSED_OPTIMIZATION, vect_location,
"single-element interleaving not supported "
"for not adjacent vector loads\n");
return false;
}
if (!slp && !PURE_SLP_STMT (stmt_info))
{
group_size = GROUP_SIZE (vinfo_for_stmt (first_stmt));