Hi!
The gomp_work_share struct is designed to have first half mostly readonly,
set once, and the second half meant for writes, with the middle being
64-byte aligned. The following patch uses (as an optimization) the new
gomp_aligned_alloc if it is not the fallback implementation.
Tested on x86_64-linux, committed to trunk.
2018-10-26 Jakub Jelinek <ja...@redhat.com>
* libgomp.h (GOMP_HAVE_EFFICIENT_ALIGNED_ALLOC): Define unless
gomp_aligned_alloc uses fallback implementation.
* alloc.c (NEED_SPECIAL_GOMP_ALIGNED_FREE): Don't define.
(gomp_aligned_free): Use !defined(GOMP_HAVE_EFFICIENT_ALIGNED_ALLOC)
instead of defined(NEED_SPECIAL_GOMP_ALIGNED_FREE).
* work.c (alloc_work_share): Use gomp_aligned_alloc instead of
gomp_malloc if GOMP_HAVE_EFFICIENT_ALIGNED_ALLOC is defined.
--- libgomp/libgomp.h.jj 2018-10-25 12:01:49.673340585 +0200
+++ libgomp/libgomp.h 2018-10-26 18:09:34.626281156 +0200
@@ -86,6 +86,15 @@ enum memmodel
/* alloc.c */
+#if defined(HAVE_ALIGNED_ALLOC) \
+ || defined(HAVE__ALIGNED_MALLOC) \
+ || defined(HAVE_POSIX_MEMALIGN) \
+ || defined(HAVE_MEMALIGN)
+/* Defined if gomp_aligned_alloc doesn't use fallback version
+ and free can be used instead of gomp_aligned_free. */
+#define GOMP_HAVE_EFFICIENT_ALIGNED_ALLOC 1
+#endif
+
extern void *gomp_malloc (size_t) __attribute__((malloc));
extern void *gomp_malloc_cleared (size_t) __attribute__((malloc));
extern void *gomp_realloc (void *, size_t);
--- libgomp/alloc.c.jj 2018-09-27 15:53:01.635671568 +0200
+++ libgomp/alloc.c 2018-10-26 18:10:36.745266239 +0200
@@ -87,7 +87,6 @@ gomp_aligned_alloc (size_t al, size_t si
((void **) ap)[-1] = p;
ret = ap;
}
-#define NEED_SPECIAL_GOMP_ALIGNED_FREE
}
#endif
if (ret == NULL)
@@ -98,10 +97,10 @@ gomp_aligned_alloc (size_t al, size_t si
void
gomp_aligned_free (void *ptr)
{
-#ifdef NEED_SPECIAL_GOMP_ALIGNED_FREE
+#ifdef GOMP_HAVE_EFFICIENT_ALIGNED_ALLOC
+ free (ptr);
+#else
if (ptr)
free (((void **) ptr)[-1]);
-#else
- free (ptr);
#endif
}
--- libgomp/work.c.jj 2018-04-30 13:21:06.574866351 +0200
+++ libgomp/work.c 2018-10-26 18:12:02.324868021 +0200
@@ -76,7 +76,15 @@ alloc_work_share (struct gomp_team *team
#endif
team->work_share_chunk *= 2;
+ /* Allocating gomp_work_share structures aligned is just an
+ optimization, don't do it when using the fallback method. */
+#ifdef GOMP_HAVE_EFFICIENT_ALIGNED_ALLOC
+ ws = gomp_aligned_alloc (__alignof (struct gomp_work_share),
+ team->work_share_chunk
+ * sizeof (struct gomp_work_share));
+#else
ws = gomp_malloc (team->work_share_chunk * sizeof (struct gomp_work_share));
+#endif
ws->next_alloc = team->work_shares[0].next_alloc;
team->work_shares[0].next_alloc = ws;
team->work_share_list_alloc = &ws[1];
Jakub
