The following fixes too aggressive disabling of peeling for gaps for
interleaving and load-lanes (as well as fixing the test so it applies
for multi-element as well).
Bootstrapped on x86_64-unknown-linux-gnu, testing in progress.
Richard.
2017-03-06 Richard Biener <rguent...@suse.de>
PR tree-optimization/79824
* tree-vect-stmts.c (get_group_load_store_type): Fix alignment
check disabling peeling for gaps.
* gcc.dg/vect/pr79824-1.c: New testcase.
* gcc.dg/vect/pr79824-2.c: Likewise.
Index: gcc/tree-vect-stmts.c
===================================================================
--- gcc/tree-vect-stmts.c (revision 245908)
+++ gcc/tree-vect-stmts.c (working copy)
@@ -1731,7 +1731,7 @@ get_group_load_store_type (gimple *stmt,
bool single_element_p = (stmt == first_stmt
&& !GROUP_NEXT_ELEMENT (stmt_info));
unsigned HOST_WIDE_INT gap = GROUP_GAP (vinfo_for_stmt (first_stmt));
- int nunits = TYPE_VECTOR_SUBPARTS (vectype);
+ unsigned nunits = TYPE_VECTOR_SUBPARTS (vectype);
/* True if the vectorized statements would access beyond the last
statement in the group. */
@@ -1794,9 +1794,13 @@ get_group_load_store_type (gimple *stmt,
/* If there is a gap at the end of the group then these optimizations
would access excess elements in the last iteration. */
bool would_overrun_p = (gap != 0);
- /* If the access is aligned an overrun is fine. */
+ /* If the access is aligned an overrun is fine, but only if the
+ overrun is not inside an unused vector (if the gap is as large
+ or larger than a vector). */
if (would_overrun_p
- && aligned_access_p (STMT_VINFO_DATA_REF (stmt_info)))
+ && gap < nunits
+ && aligned_access_p
+ (STMT_VINFO_DATA_REF (vinfo_for_stmt (first_stmt))))
would_overrun_p = false;
if (!STMT_VINFO_STRIDED_P (stmt_info)
&& (can_overrun_p || !would_overrun_p)
Index: gcc/testsuite/gcc.dg/vect/pr79824-1.c
===================================================================
--- gcc/testsuite/gcc.dg/vect/pr79824-1.c (nonexistent)
+++ gcc/testsuite/gcc.dg/vect/pr79824-1.c (working copy)
@@ -0,0 +1,46 @@
+/* { dg-require-effective-target mmap } */
+
+#include <sys/mman.h>
+#include <stdio.h>
+#include "tree-vect.h"
+
+#define COUNT 320
+#define MMAP_SIZE 0x10000
+#define ADDRESS 0x1122000000
+#define TYPE double
+
+#ifndef MAP_ANONYMOUS
+#define MAP_ANONYMOUS MAP_ANON
+#endif
+
+void __attribute__((noinline))
+foo (TYPE *__restrict a, TYPE *__restrict b)
+{
+ int n;
+
+ b = __builtin_assume_aligned (b, sizeof (TYPE) * 2);
+ a = __builtin_assume_aligned (a, sizeof (TYPE) * 2);
+ for (n = 0; n < COUNT; n++)
+ a[n] = b[n * 4];
+}
+
+int
+main (void)
+{
+ void *x;
+ size_t b_offset;
+
+ check_vect ();
+
+ x = mmap ((void *) ADDRESS, MMAP_SIZE, PROT_READ | PROT_WRITE,
+ MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+ if (x == MAP_FAILED)
+ {
+ perror ("mmap");
+ return 1;
+ }
+
+ b_offset = MMAP_SIZE - (4 * COUNT - 2) * sizeof (TYPE);
+ foo ((TYPE *) x, (TYPE *) ((char *) x + b_offset));
+ return 0;
+}
Index: gcc/testsuite/gcc.dg/vect/pr79824-2.c
===================================================================
--- gcc/testsuite/gcc.dg/vect/pr79824-2.c (nonexistent)
+++ gcc/testsuite/gcc.dg/vect/pr79824-2.c (working copy)
@@ -0,0 +1,48 @@
+/* { dg-require-effective-target mmap } */
+
+#include <sys/mman.h>
+#include <stdio.h>
+#include "tree-vect.h"
+
+#define COUNT 320
+#define MMAP_SIZE 0x10000
+#define ADDRESS 0x1122000000
+#define TYPE double
+
+#ifndef MAP_ANONYMOUS
+#define MAP_ANONYMOUS MAP_ANON
+#endif
+
+void __attribute__((noinline))
+foo (TYPE *__restrict a, TYPE *__restrict b)
+{
+ int n;
+
+ b = __builtin_assume_aligned (b, sizeof (TYPE) * 2);
+ a = __builtin_assume_aligned (a, sizeof (TYPE) * 2);
+ for (n = 0; n < COUNT; n++)
+ {
+ a[n] = b[n * 4] + b[n * 4 + 1];
+ }
+}
+
+int
+main (void)
+{
+ void *x;
+ size_t b_offset;
+
+ check_vect ();
+
+ x = mmap ((void *) ADDRESS, MMAP_SIZE, PROT_READ | PROT_WRITE,
+ MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+ if (x == MAP_FAILED)
+ {
+ perror ("mmap");
+ return 1;
+ }
+
+ b_offset = MMAP_SIZE - (4 * COUNT - 2) * sizeof (TYPE);
+ foo ((TYPE *) x, (TYPE *) ((char *) x + b_offset));
+ return 0;
+}
