From: Tobias Burnus <tobias@codesourcery.com>
To: gcc-patches <gcc-patches@gcc.gnu.org>, Jakub Jelinek <jakub@redhat.com>
Subject: Re: [Patch] libgomp: Use libnuma for OpenMP's partition=nearest allocation trait
Date: Wed, 12 Jul 2023 14:05:22 +0200 [thread overview]
Message-ID: <5b66591e-6af2-7219-acfc-640aeffad0b0@codesourcery.com> (raw)
In-Reply-To: <34fce57b-69a0-a9fd-f8ff-671ee7f94227@codesourcery.com>
[-- Attachment #1: Type: text/plain, Size: 2537 bytes --]
Now committed as r14-2462-g450b05ce54d3f0.
Changes to the patch in previous email:
* I fixed some issues found on the way,
* The wording in the .texi has been improved/expanded, and
* I included two testcases to exercise the two libraries (or
the default allocator when it is not available at runtime).
Given that the default allocation already works fine (nearest)
and the normal "malloc" is more economic in terms of memory
handling (not multiples of page size or requesting a fixed
pool size), I was wondering whether this patch is really needed.
But at the end: default can be changed (cf. below) and given
the user the choice makes sense. The manual states what GCC does
which should help to make a conscious choice.
* * *
I did experiment with the testcase attached to previous email
plus using dlopen to obtain the functions from libnuma if available.
It was also using:
/* { dg-do run { target { dlopen } } } */
/* { dg-additional-options "-ldl" } */
However, the Linux kernel too often placed the allocated memory
on the "wrong" node to be usable as a testcase. I did get be
0 to 15 misplaced allocations, depending on the run.
Hence, there is no such testcase. Using numactrl --preferred=1 I
could force the normal allocation to (mostly) use node 1 for
allocations such that the difference between partiton = default/environment
vs. partition = nearest was clearly visible. Hence it does work.
Otherwise, the same applies as I wrote the yesterday:
On 11.07.23 12:35, Tobias Burnus wrote:
> While by default 'malloc' allocates memory on the same node as the
> calling
> process/thread ('numactl --show' shows 'preferred node: current',
> Linux kernel memory policy MPOL_DEFAULT), this can be changed.
> For instance, when running the program as follows, 'malloc' now
> prefers to allocate on the second node:
> numactl --preferred=1 ./myproc
>
> Thus, it seems to be sensible to provide a means to ensure the 'nearest'
> allocation. The MPOL_LOCAL policy does so, as provided by
> libnuma's numa_alloc_local. (Which is just wrapper around the syscalls
> mmap and mbind.) As with (lib)memkind, there is a run-time dlopen check
> for (lib)numa - and no numa*.h is required when bulding GCC.
-----------------
Siemens Electronic Design Automation GmbH; Anschrift: Arnulfstraße 201, 80634 München; Gesellschaft mit beschränkter Haftung; Geschäftsführer: Thomas Heurung, Frank Thürauf; Sitz der Gesellschaft: München; Registergericht München, HRB 106955
[-- Attachment #2: committed.diff --]
[-- Type: text/x-patch, Size: 37392 bytes --]
commit 450b05ce54d3f08c583c3b5341233ce0df99725b
Author: Tobias Burnus <tobias@codesourcery.com>
Date: Wed Jul 12 13:50:21 2023 +0200
libgomp: Use libnuma for OpenMP's partition=nearest allocation trait
As with the memkind library, it is only used when found at runtime;
it does not need to be present when building GCC.
The included testcase does not check whether the memory has been placed
on the nearest node as the Linux kernel memory handling too often ignores
that hint, using a different node for the allocation. However, when
running with 'numactl --preferred=<node> ./executable', it is clearly
visible that the feature works by comparing malloc/default vs. nearest
placement (using get_mempolicy to obtain the node for a mem addr).
libgomp/ChangeLog:
* allocator.c: Add ifdef for LIBGOMP_USE_LIBNUMA.
(enum gomp_numa_memkind_kind): Renamed from gomp_memkind_kind;
add GOMP_MEMKIND_LIBNUMA.
(struct gomp_libnuma_data, gomp_init_libnuma, gomp_get_libnuma): New.
(omp_init_allocator): Handle partition=nearest with libnuma if avail.
(omp_aligned_alloc, omp_free, omp_aligned_calloc, omp_realloc): Add
numa_alloc_local (+ memset), numa_free, and numa_realloc calls as
needed.
* config/linux/allocator.c (LIBGOMP_USE_LIBNUMA): Define
* libgomp.texi: Fix a typo; use 'fi' instead of its ligature char.
(Memory allocation): Renamed from 'Memory allocation with libmemkind';
updated for libnuma usage.
* testsuite/libgomp.c-c++-common/alloc-11.c: New test.
* testsuite/libgomp.c-c++-common/alloc-12.c: New test.
---
libgomp/allocator.c | 202 ++++++++++++---
libgomp/config/linux/allocator.c | 1 +
libgomp/libgomp.texi | 42 +++-
libgomp/testsuite/libgomp.c-c++-common/alloc-11.c | 285 ++++++++++++++++++++++
libgomp/testsuite/libgomp.c-c++-common/alloc-12.c | 217 ++++++++++++++++
5 files changed, 708 insertions(+), 39 deletions(-)
diff --git a/libgomp/allocator.c b/libgomp/allocator.c
index 25c0f150302..b3187ab2911 100644
--- a/libgomp/allocator.c
+++ b/libgomp/allocator.c
@@ -31,13 +31,13 @@
#include "libgomp.h"
#include <stdlib.h>
#include <string.h>
-#ifdef LIBGOMP_USE_MEMKIND
+#if defined(LIBGOMP_USE_MEMKIND) || defined(LIBGOMP_USE_LIBNUMA)
#include <dlfcn.h>
#endif
#define omp_max_predefined_alloc omp_thread_mem_alloc
-enum gomp_memkind_kind
+enum gomp_numa_memkind_kind
{
GOMP_MEMKIND_NONE = 0,
#define GOMP_MEMKIND_KINDS \
@@ -50,7 +50,8 @@ enum gomp_memkind_kind
#define GOMP_MEMKIND_KIND(kind) GOMP_MEMKIND_##kind
GOMP_MEMKIND_KINDS,
#undef GOMP_MEMKIND_KIND
- GOMP_MEMKIND_COUNT
+ GOMP_MEMKIND_COUNT,
+ GOMP_MEMKIND_LIBNUMA = GOMP_MEMKIND_COUNT
};
struct omp_allocator_data
@@ -65,7 +66,7 @@ struct omp_allocator_data
unsigned int fallback : 8;
unsigned int pinned : 1;
unsigned int partition : 7;
-#ifdef LIBGOMP_USE_MEMKIND
+#if defined(LIBGOMP_USE_MEMKIND) || defined(LIBGOMP_USE_LIBNUMA)
unsigned int memkind : 8;
#endif
#ifndef HAVE_SYNC_BUILTINS
@@ -81,6 +82,14 @@ struct omp_mem_header
void *pad;
};
+struct gomp_libnuma_data
+{
+ void *numa_handle;
+ void *(*numa_alloc_local) (size_t);
+ void *(*numa_realloc) (void *, size_t, size_t);
+ void (*numa_free) (void *, size_t);
+};
+
struct gomp_memkind_data
{
void *memkind_handle;
@@ -92,6 +101,50 @@ struct gomp_memkind_data
void **kinds[GOMP_MEMKIND_COUNT];
};
+#ifdef LIBGOMP_USE_LIBNUMA
+static struct gomp_libnuma_data *libnuma_data;
+static pthread_once_t libnuma_data_once = PTHREAD_ONCE_INIT;
+
+static void
+gomp_init_libnuma (void)
+{
+ void *handle = dlopen ("libnuma.so.1", RTLD_LAZY);
+ struct gomp_libnuma_data *data;
+
+ data = calloc (1, sizeof (struct gomp_libnuma_data));
+ if (data == NULL)
+ {
+ if (handle)
+ dlclose (handle);
+ return;
+ }
+ if (!handle)
+ {
+ __atomic_store_n (&libnuma_data, data, MEMMODEL_RELEASE);
+ return;
+ }
+ data->numa_handle = handle;
+ data->numa_alloc_local
+ = (__typeof (data->numa_alloc_local)) dlsym (handle, "numa_alloc_local");
+ data->numa_realloc
+ = (__typeof (data->numa_realloc)) dlsym (handle, "numa_realloc");
+ data->numa_free
+ = (__typeof (data->numa_free)) dlsym (handle, "numa_free");
+ __atomic_store_n (&libnuma_data, data, MEMMODEL_RELEASE);
+}
+
+static struct gomp_libnuma_data *
+gomp_get_libnuma (void)
+{
+ struct gomp_libnuma_data *data
+ = __atomic_load_n (&libnuma_data, MEMMODEL_ACQUIRE);
+ if (data)
+ return data;
+ pthread_once (&libnuma_data_once, gomp_init_libnuma);
+ return __atomic_load_n (&libnuma_data, MEMMODEL_ACQUIRE);
+}
+#endif
+
#ifdef LIBGOMP_USE_MEMKIND
static struct gomp_memkind_data *memkind_data;
static pthread_once_t memkind_data_once = PTHREAD_ONCE_INIT;
@@ -166,7 +219,7 @@ omp_init_allocator (omp_memspace_handle_t memspace, int ntraits,
struct omp_allocator_data data
= { memspace, 1, ~(uintptr_t) 0, 0, 0, omp_atv_contended, omp_atv_all,
omp_atv_default_mem_fb, omp_atv_false, omp_atv_environment,
-#ifdef LIBGOMP_USE_MEMKIND
+#if defined(LIBGOMP_USE_MEMKIND) || defined(LIBGOMP_USE_LIBNUMA)
GOMP_MEMKIND_NONE
#endif
};
@@ -285,8 +338,8 @@ omp_init_allocator (omp_memspace_handle_t memspace, int ntraits,
switch (memspace)
{
- case omp_high_bw_mem_space:
#ifdef LIBGOMP_USE_MEMKIND
+ case omp_high_bw_mem_space:
struct gomp_memkind_data *memkind_data;
memkind_data = gomp_get_memkind ();
if (data.partition == omp_atv_interleaved
@@ -300,17 +353,15 @@ omp_init_allocator (omp_memspace_handle_t memspace, int ntraits,
data.memkind = GOMP_MEMKIND_HBW_PREFERRED;
break;
}
-#endif
break;
case omp_large_cap_mem_space:
-#ifdef LIBGOMP_USE_MEMKIND
memkind_data = gomp_get_memkind ();
if (memkind_data->kinds[GOMP_MEMKIND_DAX_KMEM_ALL])
data.memkind = GOMP_MEMKIND_DAX_KMEM_ALL;
else if (memkind_data->kinds[GOMP_MEMKIND_DAX_KMEM])
data.memkind = GOMP_MEMKIND_DAX_KMEM;
-#endif
break;
+#endif
default:
#ifdef LIBGOMP_USE_MEMKIND
if (data.partition == omp_atv_interleaved)
@@ -323,6 +374,14 @@ omp_init_allocator (omp_memspace_handle_t memspace, int ntraits,
break;
}
+#ifdef LIBGOMP_USE_LIBNUMA
+ if (data.memkind == GOMP_MEMKIND_NONE && data.partition == omp_atv_nearest)
+ {
+ data.memkind = GOMP_MEMKIND_LIBNUMA;
+ libnuma_data = gomp_get_libnuma ();
+ }
+#endif
+
/* No support for this so far. */
if (data.pinned)
return omp_null_allocator;
@@ -357,8 +416,8 @@ omp_aligned_alloc (size_t alignment, size_t size,
struct omp_allocator_data *allocator_data;
size_t new_size, new_alignment;
void *ptr, *ret;
-#ifdef LIBGOMP_USE_MEMKIND
- enum gomp_memkind_kind memkind;
+#if defined(LIBGOMP_USE_MEMKIND) || defined(LIBGOMP_USE_LIBNUMA)
+ enum gomp_numa_memkind_kind memkind;
#endif
if (__builtin_expect (size == 0, 0))
@@ -379,7 +438,7 @@ retry:
allocator_data = (struct omp_allocator_data *) allocator;
if (new_alignment < allocator_data->alignment)
new_alignment = allocator_data->alignment;
-#ifdef LIBGOMP_USE_MEMKIND
+#if defined(LIBGOMP_USE_MEMKIND) || defined(LIBGOMP_USE_LIBNUMA)
memkind = allocator_data->memkind;
#endif
}
@@ -388,8 +447,10 @@ retry:
allocator_data = NULL;
if (new_alignment < sizeof (void *))
new_alignment = sizeof (void *);
-#ifdef LIBGOMP_USE_MEMKIND
+#if defined(LIBGOMP_USE_MEMKIND) || defined(LIBGOMP_USE_LIBNUMA)
memkind = GOMP_MEMKIND_NONE;
+#endif
+#ifdef LIBGOMP_USE_MEMKIND
if (allocator == omp_high_bw_mem_alloc)
memkind = GOMP_MEMKIND_HBW_PREFERRED;
else if (allocator == omp_large_cap_mem_alloc)
@@ -444,6 +505,13 @@ retry:
allocator_data->used_pool_size = used_pool_size;
gomp_mutex_unlock (&allocator_data->lock);
#endif
+#ifdef LIBGOMP_USE_LIBNUMA
+ if (memkind == GOMP_MEMKIND_LIBNUMA)
+ ptr = libnuma_data->numa_alloc_local (new_size);
+# ifdef LIBGOMP_USE_MEMKIND
+ else
+# endif
+#endif
#ifdef LIBGOMP_USE_MEMKIND
if (memkind)
{
@@ -469,6 +537,13 @@ retry:
}
else
{
+#ifdef LIBGOMP_USE_LIBNUMA
+ if (memkind == GOMP_MEMKIND_LIBNUMA)
+ ptr = libnuma_data->numa_alloc_local (new_size);
+# ifdef LIBGOMP_USE_MEMKIND
+ else
+# endif
+#endif
#ifdef LIBGOMP_USE_MEMKIND
if (memkind)
{
@@ -502,7 +577,7 @@ fail:
{
case omp_atv_default_mem_fb:
if ((new_alignment > sizeof (void *) && new_alignment > alignment)
-#ifdef LIBGOMP_USE_MEMKIND
+#if defined(LIBGOMP_USE_MEMKIND) || defined(LIBGOMP_USE_LIBNUMA)
|| memkind
#endif
|| (allocator_data
@@ -577,6 +652,16 @@ omp_free (void *ptr, omp_allocator_handle_t allocator)
gomp_mutex_unlock (&allocator_data->lock);
#endif
}
+#ifdef LIBGOMP_USE_LIBNUMA
+ if (allocator_data->memkind == GOMP_MEMKIND_LIBNUMA)
+ {
+ libnuma_data->numa_free (data->ptr, data->size);
+ return;
+ }
+# ifdef LIBGOMP_USE_MEMKIND
+ else
+# endif
+#endif
#ifdef LIBGOMP_USE_MEMKIND
if (allocator_data->memkind)
{
@@ -590,7 +675,7 @@ omp_free (void *ptr, omp_allocator_handle_t allocator)
#ifdef LIBGOMP_USE_MEMKIND
else
{
- enum gomp_memkind_kind memkind = GOMP_MEMKIND_NONE;
+ enum gomp_numa_memkind_kind memkind = GOMP_MEMKIND_NONE;
if (data->allocator == omp_high_bw_mem_alloc)
memkind = GOMP_MEMKIND_HBW_PREFERRED;
else if (data->allocator == omp_large_cap_mem_alloc)
@@ -625,8 +710,8 @@ omp_aligned_calloc (size_t alignment, size_t nmemb, size_t size,
struct omp_allocator_data *allocator_data;
size_t new_size, size_temp, new_alignment;
void *ptr, *ret;
-#ifdef LIBGOMP_USE_MEMKIND
- enum gomp_memkind_kind memkind;
+#if defined(LIBGOMP_USE_MEMKIND) || defined(LIBGOMP_USE_LIBNUMA)
+ enum gomp_numa_memkind_kind memkind;
#endif
if (__builtin_expect (size == 0 || nmemb == 0, 0))
@@ -647,7 +732,7 @@ retry:
allocator_data = (struct omp_allocator_data *) allocator;
if (new_alignment < allocator_data->alignment)
new_alignment = allocator_data->alignment;
-#ifdef LIBGOMP_USE_MEMKIND
+#if defined(LIBGOMP_USE_MEMKIND) || defined(LIBGOMP_USE_LIBNUMA)
memkind = allocator_data->memkind;
#endif
}
@@ -656,8 +741,10 @@ retry:
allocator_data = NULL;
if (new_alignment < sizeof (void *))
new_alignment = sizeof (void *);
-#ifdef LIBGOMP_USE_MEMKIND
+#if defined(LIBGOMP_USE_MEMKIND) || defined(LIBGOMP_USE_LIBNUMA)
memkind = GOMP_MEMKIND_NONE;
+#endif
+#ifdef LIBGOMP_USE_MEMKIND
if (allocator == omp_high_bw_mem_alloc)
memkind = GOMP_MEMKIND_HBW_PREFERRED;
else if (allocator == omp_large_cap_mem_alloc)
@@ -714,6 +801,15 @@ retry:
allocator_data->used_pool_size = used_pool_size;
gomp_mutex_unlock (&allocator_data->lock);
#endif
+#ifdef LIBGOMP_USE_LIBNUMA
+ if (memkind == GOMP_MEMKIND_LIBNUMA)
+ /* numa_alloc_local uses mmap with MAP_ANONYMOUS, returning
+ memory that is initialized to zero. */
+ ptr = libnuma_data->numa_alloc_local (new_size);
+# ifdef LIBGOMP_USE_MEMKIND
+ else
+# endif
+#endif
#ifdef LIBGOMP_USE_MEMKIND
if (memkind)
{
@@ -739,6 +835,15 @@ retry:
}
else
{
+#ifdef LIBGOMP_USE_LIBNUMA
+ if (memkind == GOMP_MEMKIND_LIBNUMA)
+ /* numa_alloc_local uses mmap with MAP_ANONYMOUS, returning
+ memory that is initialized to zero. */
+ ptr = libnuma_data->numa_alloc_local (new_size);
+# ifdef LIBGOMP_USE_MEMKIND
+ else
+# endif
+#endif
#ifdef LIBGOMP_USE_MEMKIND
if (memkind)
{
@@ -772,7 +877,7 @@ fail:
{
case omp_atv_default_mem_fb:
if ((new_alignment > sizeof (void *) && new_alignment > alignment)
-#ifdef LIBGOMP_USE_MEMKIND
+#if defined(LIBGOMP_USE_MEMKIND) || defined(LIBGOMP_USE_LIBNUMA)
|| memkind
#endif
|| (allocator_data
@@ -815,8 +920,8 @@ omp_realloc (void *ptr, size_t size, omp_allocator_handle_t allocator,
size_t new_size, old_size, new_alignment, old_alignment;
void *new_ptr, *ret;
struct omp_mem_header *data;
-#ifdef LIBGOMP_USE_MEMKIND
- enum gomp_memkind_kind memkind, free_memkind;
+#if defined(LIBGOMP_USE_MEMKIND) || defined(LIBGOMP_USE_LIBNUMA)
+ enum gomp_numa_memkind_kind memkind, free_memkind;
#endif
if (__builtin_expect (ptr == NULL, 0))
@@ -841,15 +946,17 @@ retry:
allocator_data = (struct omp_allocator_data *) allocator;
if (new_alignment < allocator_data->alignment)
new_alignment = allocator_data->alignment;
-#ifdef LIBGOMP_USE_MEMKIND
+#if defined(LIBGOMP_USE_MEMKIND) || defined(LIBGOMP_USE_LIBNUMA)
memkind = allocator_data->memkind;
#endif
}
else
{
allocator_data = NULL;
-#ifdef LIBGOMP_USE_MEMKIND
+#if defined(LIBGOMP_USE_MEMKIND) || defined(LIBGOMP_USE_LIBNUMA)
memkind = GOMP_MEMKIND_NONE;
+#endif
+#ifdef LIBGOMP_USE_MEMKIND
if (allocator == omp_high_bw_mem_alloc)
memkind = GOMP_MEMKIND_HBW_PREFERRED;
else if (allocator == omp_large_cap_mem_alloc)
@@ -865,15 +972,17 @@ retry:
if (free_allocator > omp_max_predefined_alloc)
{
free_allocator_data = (struct omp_allocator_data *) free_allocator;
-#ifdef LIBGOMP_USE_MEMKIND
+#if defined(LIBGOMP_USE_MEMKIND) || defined(LIBGOMP_USE_LIBNUMA)
free_memkind = free_allocator_data->memkind;
#endif
}
else
{
free_allocator_data = NULL;
-#ifdef LIBGOMP_USE_MEMKIND
+#if defined(LIBGOMP_USE_MEMKIND) || defined(LIBGOMP_USE_LIBNUMA)
free_memkind = GOMP_MEMKIND_NONE;
+#endif
+#ifdef LIBGOMP_USE_MEMKIND
if (free_allocator == omp_high_bw_mem_alloc)
free_memkind = GOMP_MEMKIND_HBW_PREFERRED;
else if (free_allocator == omp_large_cap_mem_alloc)
@@ -953,6 +1062,19 @@ retry:
allocator_data->used_pool_size = used_pool_size;
gomp_mutex_unlock (&allocator_data->lock);
#endif
+#ifdef LIBGOMP_USE_LIBNUMA
+ if (memkind == GOMP_MEMKIND_LIBNUMA)
+ {
+ if (prev_size)
+ new_ptr = libnuma_data->numa_realloc (data->ptr, data->size,
+ new_size);
+ else
+ new_ptr = libnuma_data->numa_alloc_local (new_size);
+ }
+# ifdef LIBGOMP_USE_MEMKIND
+ else
+# endif
+#endif
#ifdef LIBGOMP_USE_MEMKIND
if (memkind)
{
@@ -994,12 +1116,19 @@ retry:
}
else if (new_alignment == sizeof (void *)
&& old_alignment == sizeof (struct omp_mem_header)
-#ifdef LIBGOMP_USE_MEMKIND
+#if defined(LIBGOMP_USE_MEMKIND) || defined(LIBGOMP_USE_LIBNUMA)
&& memkind == free_memkind
#endif
&& (free_allocator_data == NULL
|| free_allocator_data->pool_size == ~(uintptr_t) 0))
{
+#ifdef LIBGOMP_USE_LIBNUMA
+ if (memkind == GOMP_MEMKIND_LIBNUMA)
+ new_ptr = libnuma_data->numa_realloc (data->ptr, data->size, new_size);
+# ifdef LIBGOMP_USE_MEMKIND
+ else
+# endif
+#endif
#ifdef LIBGOMP_USE_MEMKIND
if (memkind)
{
@@ -1021,6 +1150,13 @@ retry:
}
else
{
+#ifdef LIBGOMP_USE_LIBNUMA
+ if (memkind == GOMP_MEMKIND_LIBNUMA)
+ new_ptr = libnuma_data->numa_alloc_local (new_size);
+# ifdef LIBGOMP_USE_MEMKIND
+ else
+# endif
+#endif
#ifdef LIBGOMP_USE_MEMKIND
if (memkind)
{
@@ -1060,6 +1196,16 @@ retry:
gomp_mutex_unlock (&free_allocator_data->lock);
#endif
}
+#ifdef LIBGOMP_USE_LIBNUMA
+ if (free_memkind == GOMP_MEMKIND_LIBNUMA)
+ {
+ libnuma_data->numa_free (data->ptr, data->size);
+ return ret;
+ }
+# ifdef LIBGOMP_USE_MEMKIND
+ else
+# endif
+#endif
#ifdef LIBGOMP_USE_MEMKIND
if (free_memkind)
{
@@ -1079,7 +1225,7 @@ fail:
{
case omp_atv_default_mem_fb:
if (new_alignment > sizeof (void *)
-#ifdef LIBGOMP_USE_MEMKIND
+#if defined(LIBGOMP_USE_MEMKIND) || defined(LIBGOMP_USE_LIBNUMA)
|| memkind
#endif
|| (allocator_data
diff --git a/libgomp/config/linux/allocator.c b/libgomp/config/linux/allocator.c
index 15babcd1ada..64b1b4b9623 100644
--- a/libgomp/config/linux/allocator.c
+++ b/libgomp/config/linux/allocator.c
@@ -31,6 +31,7 @@
#include "libgomp.h"
#if defined(PLUGIN_SUPPORT) && defined(LIBGOMP_USE_PTHREADS)
#define LIBGOMP_USE_MEMKIND
+#define LIBGOMP_USE_LIBNUMA
#endif
#include "../../allocator.c"
diff --git a/libgomp/libgomp.texi b/libgomp/libgomp.texi
index d1a5e67329a..9d910e6883c 100644
--- a/libgomp/libgomp.texi
+++ b/libgomp/libgomp.texi
@@ -2061,7 +2061,7 @@ Special values are output using @code{%} followed by an optional size
specification and then either the single-character field type or its long
name enclosed in curly braces; using @code{%%} will display a literal percent.
The size specification consists of an optional @code{0.} or @code{.} followed
-by a positive integer, specifing the minimal width of the output. With
+by a positive integer, specifying the minimal width of the output. With
@code{0.} and numerical values, the output is padded with zeros on the left;
with @code{.}, the output is padded by spaces on the left; otherwise, the
output is padded by spaces on the right. If unset, the value is
@@ -2079,8 +2079,8 @@ Supported field types are:
@tab value returned by
@code{omp_get_ancestor_thread_num(omp_get_level()-1)}
@item H @tab host @tab name of the host that executes the thread
-@item P @tab process_id @tab process identifier
-@item i @tab native_thread_id @tab native thread identifier
+@item P @tab process_id @tab process identifier
+@item i @tab native_thread_id @tab native thread identifier
@item A @tab thread_affinity
@tab comma separated list of integer values or ranges, representing the
processors on which a process might execute, subject to affinity
@@ -4584,7 +4584,7 @@ offloading devices (it's not clear if they should be):
@menu
* Implementation-defined ICV Initialization::
* OpenMP Context Selectors::
-* Memory allocation with libmemkind::
+* Memory allocation::
@end menu
@node Implementation-defined ICV Initialization
@@ -4631,8 +4631,8 @@ smaller number. On non-host devices, the value of the
@tab See @code{-march=} in ``Nvidia PTX Options''
@end multitable
-@node Memory allocation with libmemkind
-@section Memory allocation with libmemkind
+@node Memory allocation
+@section Memory allocation
For the memory spaces, the following applies:
@itemize
@@ -4652,20 +4652,40 @@ creating memory allocators requesting
@itemize
@item the memory space @code{omp_high_bw_mem_space}
@item the memory space @code{omp_large_cap_mem_space}
-@item the partition trait @code{omp_atv_interleaved}; note that for
+@item the @code{partition} trait @code{interleaved}; note that for
@code{omp_large_cap_mem_space} the allocation will not be interleaved
@end itemize
+On Linux systems, where the @uref{https://github.com/numactl/numactl, numa
+library} (@code{libnuma.so.1}) is available at runtime, it used when creating
+memory allocators requesting
+
+@itemize
+@item the @code{partition} trait @code{nearest}, except when both the
+libmemkind library is available and the memory space is either
+@code{omp_large_cap_mem_space} or @code{omp_high_bw_mem_space}
+@end itemize
+
+Note that the numa library will round up the allocation size to a multiple of
+the system page size; therefore, consider using it only with large data or
+by sharing allocations via the @code{pool_size} trait. Furthermore, the Linux
+kernel does not guarantee that an allocation will always be on the nearest NUMA
+node nor that after reallocation the same node will be used. Note additionally
+that, on Linux, the default setting of the memory placement policy is to use the
+current node; therefore, unless the memory placement policy has been overridden,
+the @code{partition} trait @code{environment} (the default) will be effectively
+a @code{nearest} allocation.
+
Additional notes:
@itemize
@item The @code{pinned} trait is unsupported.
@item For the @code{partition} trait, the partition part size will be the same
as the requested size (i.e. @code{interleaved} or @code{blocked} has no
effect), except for @code{interleaved} when the memkind library is
- available. Furthermore, for @code{nearest} the memory might not be
- on the same NUMA node as thread that allocated the memory; on Linux,
- this is in particular the case when the memory placement policy is
- set to preferred.
+ available. Furthermore, for @code{nearest} and unless the numa library
+ is available, the memory might not be on the same NUMA node as thread
+ that allocated the memory; on Linux, this is in particular the case when
+ the memory placement policy is set to preferred.
@item The @code{access} trait has no effect such that memory is always
accessible by all threads.
@item The @code{sync_hint} trait has no effect.
diff --git a/libgomp/testsuite/libgomp.c-c++-common/alloc-11.c b/libgomp/testsuite/libgomp.c-c++-common/alloc-11.c
new file mode 100644
index 00000000000..5fbadf4406a
--- /dev/null
+++ b/libgomp/testsuite/libgomp.c-c++-common/alloc-11.c
@@ -0,0 +1,285 @@
+/* This testcase is mostly the same as alloc-9.c.
+ However, on systems where the numa and/or memkind libraries are
+ installed, libgomp uses those. This test ensures that the minimal
+ features work. Note: No attempt has been made to verify the parition
+ hints interleaved and nearest as the kernal purposely ignore them once
+ in a while and it would also require a 'dlopen' dance.
+
+ memkind is used for omp_high_bw_mem_space, omp_large_cap_mem_space
+ and partition = interleaved, albeit it won't be interleaved for
+ omp_large_cap_mem_space.
+
+ numa is used for partition = nearest, unless memkind is used. */
+
+#include <omp.h>
+#include <stdint.h>
+#include <stdlib.h>
+
+const omp_alloctrait_t traits2[]
+= { { omp_atk_alignment, 16 },
+ { omp_atk_sync_hint, omp_atv_default },
+ { omp_atk_access, omp_atv_default },
+ { omp_atk_pool_size, 1024 },
+ { omp_atk_fallback, omp_atv_default_mem_fb },
+ { omp_atk_partition, omp_atv_nearest } };
+omp_alloctrait_t traits3[]
+= { { omp_atk_sync_hint, omp_atv_uncontended },
+ { omp_atk_alignment, 32 },
+ { omp_atk_access, omp_atv_all },
+ { omp_atk_pool_size, 512 },
+ { omp_atk_fallback, omp_atv_allocator_fb },
+ { omp_atk_fb_data, 0 },
+ { omp_atk_partition, omp_atv_interleaved } };
+const omp_alloctrait_t traits4[]
+= { { omp_atk_alignment, 128 },
+ { omp_atk_pool_size, 1024 },
+ { omp_atk_fallback, omp_atv_null_fb } };
+
+int
+main ()
+{
+ int *volatile p = (int *) omp_alloc (3 * sizeof (int), omp_default_mem_alloc);
+ int *volatile q;
+ int *volatile r;
+ omp_alloctrait_t traits[4]
+ = { { omp_atk_alignment, 64 },
+ { omp_atk_fallback, omp_atv_null_fb },
+ { omp_atk_pool_size, 4096 },
+ { omp_atk_partition, omp_atv_nearest } };
+ omp_alloctrait_t traits5[2]
+ = { { omp_atk_fallback, omp_atv_null_fb },
+ { omp_atk_pool_size, 4096 } };
+ omp_allocator_handle_t a, a2;
+
+ if ((((uintptr_t) p) % __alignof (int)) != 0)
+ abort ();
+ p[0] = 1;
+ p[1] = 2;
+ p[2] = 3;
+ p = (int *) omp_realloc (p, 4 * sizeof (int), omp_high_bw_mem_alloc, omp_high_bw_mem_alloc);
+ if ((((uintptr_t) p) % __alignof (int)) != 0 || p[0] != 1 || p[1] != 2 || p[2] != 3)
+ abort ();
+ p[0] = 4;
+ p[1] = 5;
+ p[2] = 6;
+ p[3] = 7;
+ p = (int *) omp_realloc (p, 2 * sizeof (int), omp_high_bw_mem_alloc, omp_high_bw_mem_alloc);
+ if ((((uintptr_t) p) % __alignof (int)) != 0 || p[0] != 4 || p[1] != 5)
+ abort ();
+ p[0] = 8;
+ p[1] = 9;
+ if (omp_realloc (p, 0, omp_null_allocator, omp_high_bw_mem_alloc) != NULL)
+ abort ();
+ p = (int *) omp_realloc (NULL, 2 * sizeof (int), omp_large_cap_mem_alloc, omp_null_allocator);
+ if ((((uintptr_t) p) % __alignof (int)) != 0)
+ abort ();
+ p[0] = 1;
+ p[1] = 2;
+ p = (int *) omp_realloc (p, 5 * sizeof (int), omp_large_cap_mem_alloc, omp_large_cap_mem_alloc);
+ if ((((uintptr_t) p) % __alignof (int)) != 0 || p[0] != 1 || p[1] != 2)
+ abort ();
+ p[0] = 3;
+ p[1] = 4;
+ p[2] = 5;
+ p[3] = 6;
+ p[4] = 7;
+ omp_free (p, omp_null_allocator);
+ omp_set_default_allocator (omp_large_cap_mem_alloc);
+ if (omp_realloc (NULL, 0, omp_null_allocator, omp_null_allocator) != NULL)
+ abort ();
+ p = (int *) omp_alloc (sizeof (int), omp_null_allocator);
+ if ((((uintptr_t) p) % __alignof (int)) != 0)
+ abort ();
+ p[0] = 3;
+ p = (int *) omp_realloc (p, 3 * sizeof (int), omp_null_allocator, omp_null_allocator);
+ if ((((uintptr_t) p) % __alignof (int)) != 0 || p[0] != 3)
+ abort ();
+ p[0] = 4;
+ p[1] = 5;
+ p[2] = 6;
+ if (omp_realloc (p, 0, omp_null_allocator, omp_get_default_allocator ()) != NULL)
+ abort ();
+ a = omp_init_allocator (omp_default_mem_space, 4, traits);
+ if (a == omp_null_allocator)
+ abort ();
+ p = (int *) omp_alloc (sizeof (int), a);
+ if ((((uintptr_t) p) % 64) != 0)
+ abort ();
+ p[0] = 7;
+ p = (int *) omp_realloc (p, 3072, a, a);
+ if ((((uintptr_t) p) % 64) != 0 || p[0] != 7)
+ abort ();
+ p[0] = 1;
+ p[3071 / sizeof (int)] = 2;
+ q = (int *) omp_alloc (sizeof (int), a);
+ if ((((uintptr_t) q) % 64) != 0)
+ abort ();
+ q[0] = 8;
+ if (omp_realloc (q, 3072, a, a) != NULL)
+ abort ();
+ omp_free (p, a);
+ omp_free (q, a);
+ p = (int *) omp_alloc (sizeof (int), a);
+ p[0] = 42;
+ p = (int *) omp_realloc (p, 3072, a, a);
+ if (p[0] != 42)
+ abort ();
+ p[0] = 3;
+ p[3071 / sizeof (int)] = 4;
+ omp_realloc (p, 0, omp_null_allocator, omp_null_allocator);
+ omp_set_default_allocator (a);
+ if (omp_get_default_allocator () != a)
+ abort ();
+ p = (int *) omp_alloc (31, omp_null_allocator);
+ if (p == NULL)
+ abort ();
+ p = (int *) omp_realloc (p, 3072, omp_null_allocator, omp_null_allocator);
+ if (p == NULL)
+ abort ();
+ q = (int *) omp_alloc (sizeof (int), omp_null_allocator);
+ if (q == NULL)
+ abort ();
+ if (omp_realloc (q, 3072, omp_null_allocator, omp_null_allocator) != NULL)
+ abort ();
+ omp_free (p, a);
+ omp_free (q, a);
+ omp_destroy_allocator (a);
+
+ a = omp_init_allocator (omp_large_cap_mem_space, 2, traits5);
+ if (a == omp_null_allocator)
+ abort ();
+ omp_set_default_allocator (a);
+ if (omp_get_default_allocator () != a)
+ abort ();
+ p = (int *) omp_alloc (3071, omp_null_allocator);
+ if (p == NULL)
+ abort ();
+ p = (int *) omp_realloc (p, 3072, omp_null_allocator, omp_null_allocator);
+ if (p == NULL)
+ abort ();
+ q = (int *) omp_alloc (sizeof (int), omp_null_allocator);
+ if (q == NULL)
+ abort ();
+ if (omp_realloc (q, 3072, omp_null_allocator, omp_null_allocator) != NULL)
+ abort ();
+ omp_free (p, a);
+ omp_free (q, a);
+ omp_destroy_allocator (a);
+
+ a = omp_init_allocator (omp_default_mem_space,
+ sizeof (traits2) / sizeof (traits2[0]),
+ traits2);
+ if (a == omp_null_allocator)
+ abort ();
+ if (traits3[5].key != omp_atk_fb_data)
+ abort ();
+ traits3[5].value = (uintptr_t) a;
+ a2 = omp_init_allocator (omp_default_mem_space,
+ sizeof (traits3) / sizeof (traits3[0]),
+ traits3);
+ if (a2 == omp_null_allocator)
+ abort ();
+ p = (int *) omp_alloc (sizeof (int), a2);
+ if ((((uintptr_t) p) % 32) != 0)
+ abort ();
+ p[0] = 84;
+ p = (int *) omp_realloc (p, 380, a2, a2);
+ if ((((uintptr_t) p) % 32) != 0 || p[0] != 84)
+ abort ();
+ p[0] = 5;
+ p[379 / sizeof (int)] = 6;
+ q = (int *) omp_alloc (sizeof (int), a2);
+ if ((((uintptr_t) q) % 32) != 0)
+ abort ();
+ q[0] = 42;
+ q = (int *) omp_realloc (q, 768, a2, a2);
+ if ((((uintptr_t) q) % 16) != 0 || q[0] != 42)
+ abort ();
+ q[0] = 7;
+ q[767 / sizeof (int)] = 8;
+ r = (int *) omp_realloc (NULL, 512, a2, omp_null_allocator);
+ if ((((uintptr_t) r) % __alignof (int)) != 0)
+ abort ();
+ r[0] = 9;
+ r[511 / sizeof (int)] = 10;
+ omp_free (p, omp_null_allocator);
+ omp_free (q, a2);
+ omp_free (r, omp_null_allocator);
+ p = (int *) omp_alloc (sizeof (int), a2);
+ if ((((uintptr_t) p) % 32) != 0)
+ abort ();
+ p[0] = 85;
+ p = (int *) omp_realloc (p, 320, a, a2);
+ if ((((uintptr_t) p) % 16) != 0 || p[0] != 85)
+ abort ();
+ p[0] = 5;
+ p[319 / sizeof (int)] = 6;
+ q = (int *) omp_alloc (sizeof (int), a);
+ if ((((uintptr_t) q) % 16) != 0)
+ abort ();
+ q[0] = 43;
+ q = (int *) omp_realloc (q, 320, a2, a);
+ if ((((uintptr_t) q) % 32) != 0 || q[0] != 43)
+ abort ();
+ q[0] = 44;
+ q[319 / sizeof (int)] = 8;
+ q = (int *) omp_realloc (q, 568, a2, a2);
+ if ((((uintptr_t) q) % 16) != 0 || q[0] != 44)
+ abort ();
+ q[0] = 7;
+ q[567 / sizeof (int)] = 8;
+ omp_free (p, omp_null_allocator);
+ omp_free (q, a2);
+ omp_destroy_allocator (a2);
+ omp_destroy_allocator (a);
+
+ a = omp_init_allocator (omp_large_cap_mem_space,
+ sizeof (traits4) / sizeof (traits4[0]),
+ traits4);
+ if (a == omp_null_allocator)
+ abort ();
+ if (traits3[5].key != omp_atk_fb_data)
+ abort ();
+ traits3[5].value = (uintptr_t) a;
+ a2 = omp_init_allocator (omp_default_mem_space,
+ sizeof (traits3) / sizeof (traits3[0]),
+ traits3);
+ if (a2 == omp_null_allocator)
+ abort ();
+ omp_set_default_allocator (a2);
+#ifdef __cplusplus
+ p = static_cast <int *> (omp_realloc (NULL, 420));
+#else
+ p = (int *) omp_realloc (NULL, 420, omp_null_allocator, omp_null_allocator);
+#endif
+ if ((((uintptr_t) p) % 32) != 0)
+ abort ();
+ p[0] = 5;
+ p[419 / sizeof (int)] = 6;
+ q = (int *) omp_realloc (NULL, sizeof (int), omp_null_allocator, omp_null_allocator);
+ if ((((uintptr_t) q) % 32) != 0)
+ abort ();
+ q[0] = 99;
+ q = (int *) omp_realloc (q, 700, omp_null_allocator, omp_null_allocator);
+ if ((((uintptr_t) q) % 128) != 0 || q[0] != 99)
+ abort ();
+ q[0] = 7;
+ q[699 / sizeof (int)] = 8;
+ if (omp_realloc (NULL, 768, omp_null_allocator, omp_null_allocator) != NULL)
+ abort ();
+#ifdef __cplusplus
+ omp_free (p);
+ if (omp_realloc (q, 0) != NULL)
+ abort ();
+ omp_free (NULL);
+#else
+ omp_free (p, omp_null_allocator);
+ if (omp_realloc (q, 0, omp_null_allocator, omp_null_allocator) != NULL)
+ abort ();
+ omp_free (NULL, omp_null_allocator);
+#endif
+ omp_free (NULL, omp_null_allocator);
+ omp_destroy_allocator (a2);
+ omp_destroy_allocator (a);
+ return 0;
+}
diff --git a/libgomp/testsuite/libgomp.c-c++-common/alloc-12.c b/libgomp/testsuite/libgomp.c-c++-common/alloc-12.c
new file mode 100644
index 00000000000..e07de3be6a7
--- /dev/null
+++ b/libgomp/testsuite/libgomp.c-c++-common/alloc-12.c
@@ -0,0 +1,217 @@
+/* This testcase is mostly the same as alloc-8.c.
+ However, on systems where the numa and/or memkind libraries are
+ installed, libgomp uses those. This test ensures that the minimal
+ features work. Note: No attempt has been made to verify the parition
+ hints interleaved and nearest as the kernal purposely ignore them once
+ in a while and it would also require a 'dlopen' dance.
+
+ memkind is used for omp_high_bw_mem_space, omp_large_cap_mem_space
+ and partition = interleaved, albeit it won't be interleaved for
+ omp_large_cap_mem_space.
+
+ numa is used for partition = nearest, unless memkind is used. */
+
+#include <omp.h>
+#include <stdint.h>
+#include <stdlib.h>
+
+const omp_alloctrait_t traits2[]
+= { { omp_atk_alignment, 16 },
+ { omp_atk_sync_hint, omp_atv_default },
+ { omp_atk_access, omp_atv_default },
+ { omp_atk_pool_size, 1024 },
+ { omp_atk_fallback, omp_atv_default_mem_fb },
+ { omp_atk_partition, omp_atv_nearest } };
+omp_alloctrait_t traits3[]
+= { { omp_atk_sync_hint, omp_atv_uncontended },
+ { omp_atk_alignment, 32 },
+ { omp_atk_access, omp_atv_all },
+ { omp_atk_pool_size, 512 },
+ { omp_atk_fallback, omp_atv_allocator_fb },
+ { omp_atk_fb_data, 0 },
+ { omp_atk_partition, omp_atv_interleaved } };
+const omp_alloctrait_t traits4[]
+= { { omp_atk_alignment, 128 },
+ { omp_atk_pool_size, 1024 },
+ { omp_atk_fallback, omp_atv_null_fb } };
+
+static void
+check_all_zero (void *ptr, size_t len)
+{
+ char *p = (char *) ptr;
+ for (size_t i = 0; i < len; i++)
+ if (p[i] != '\0')
+ abort ();
+}
+
+int
+main ()
+{
+ int *volatile p = (int *) omp_aligned_calloc (sizeof (int), 3, sizeof (int), omp_high_bw_mem_alloc);
+ check_all_zero (p, 3*sizeof (int));
+ int *volatile q;
+ int *volatile r;
+ int i;
+ omp_alloctrait_t traits[3]
+ = { { omp_atk_alignment, 64 },
+ { omp_atk_fallback, omp_atv_null_fb },
+ { omp_atk_pool_size, 4096 } };
+ omp_allocator_handle_t a, a2;
+
+ if ((((uintptr_t) p) % __alignof (int)) != 0 || p[0] || p[1] || p[2])
+ abort ();
+ p[0] = 1;
+ p[1] = 2;
+ p[2] = 3;
+ omp_free (p, omp_high_bw_mem_alloc);
+ p = (int *) omp_aligned_calloc (2 * sizeof (int), 1, 2 * sizeof (int), omp_large_cap_mem_alloc);
+ check_all_zero (p, 2*sizeof (int));
+ if ((((uintptr_t) p) % (2 * sizeof (int))) != 0 || p[0] || p[1])
+ abort ();
+ p[0] = 1;
+ p[1] = 2;
+ omp_free (p, omp_null_allocator);
+ omp_set_default_allocator (omp_large_cap_mem_alloc);
+ p = (int *) omp_aligned_calloc (1, 1, sizeof (int), omp_null_allocator);
+ check_all_zero (p, sizeof (int));
+ if ((((uintptr_t) p) % __alignof (int)) != 0 || p[0])
+ abort ();
+ p[0] = 3;
+ omp_free (p, omp_get_default_allocator ());
+
+ a = omp_init_allocator (omp_large_cap_mem_space, 3, traits);
+ if (a == omp_null_allocator)
+ abort ();
+ p = (int *) omp_aligned_calloc (32, 3, 1024, a);
+ check_all_zero (p, 3*1024);
+ if ((((uintptr_t) p) % 64) != 0)
+ abort ();
+ for (i = 0; i < 3072 / sizeof (int); i++)
+ if (p[i])
+ abort ();
+ p[0] = 1;
+ p[3071 / sizeof (int)] = 2;
+ if (omp_aligned_calloc (8, 192, 16, a) != NULL)
+ abort ();
+ omp_free (p, a);
+ p = (int *) omp_aligned_calloc (128, 6, 512, a);
+ check_all_zero (p, 6*512);
+ if ((((uintptr_t) p) % 128) != 0)
+ abort ();
+ for (i = 0; i < 3072 / sizeof (int); i++)
+ if (p[i])
+ abort ();
+ p[0] = 3;
+ p[3071 / sizeof (int)] = 4;
+ omp_free (p, omp_null_allocator);
+ omp_set_default_allocator (a);
+ if (omp_get_default_allocator () != a)
+ abort ();
+ p = (int *) omp_aligned_calloc (64, 12, 256, omp_null_allocator);
+ check_all_zero (p, 12*256);
+ for (i = 0; i < 3072 / sizeof (int); i++)
+ if (p[i])
+ abort ();
+ if (omp_aligned_calloc (8, 128, 24, omp_null_allocator) != NULL)
+ abort ();
+ omp_free (p, a);
+ omp_destroy_allocator (a);
+
+ a = omp_init_allocator (omp_default_mem_space,
+ sizeof (traits2) / sizeof (traits2[0]),
+ traits2);
+ if (a == omp_null_allocator)
+ abort ();
+ if (traits3[5].key != omp_atk_fb_data)
+ abort ();
+ traits3[5].value = (uintptr_t) a;
+ a2 = omp_init_allocator (omp_default_mem_space,
+ sizeof (traits3) / sizeof (traits3[0]),
+ traits3);
+ if (a2 == omp_null_allocator)
+ abort ();
+ p = (int *) omp_aligned_calloc (4, 5, 84, a2);
+ check_all_zero (p, 5*84);
+ for (i = 0; i < 420 / sizeof (int); i++)
+ if (p[i])
+ abort ();
+ if ((((uintptr_t) p) % 32) != 0)
+ abort ();
+ p[0] = 5;
+ p[419 / sizeof (int)] = 6;
+ q = (int *) omp_aligned_calloc (8, 24, 32, a2);
+ check_all_zero (q, 24*32);
+ if ((((uintptr_t) q) % 16) != 0)
+ abort ();
+ for (i = 0; i < 768 / sizeof (int); i++)
+ if (q[i])
+ abort ();
+ q[0] = 7;
+ q[767 / sizeof (int)] = 8;
+ r = (int *) omp_aligned_calloc (8, 64, 8, a2);
+ check_all_zero (r, 64*8);
+ if ((((uintptr_t) r) % 8) != 0)
+ abort ();
+ for (i = 0; i < 512 / sizeof (int); i++)
+ if (r[i])
+ abort ();
+ r[0] = 9;
+ r[511 / sizeof (int)] = 10;
+ omp_free (p, omp_null_allocator);
+ omp_free (q, a2);
+ omp_free (r, omp_null_allocator);
+ omp_destroy_allocator (a2);
+ omp_destroy_allocator (a);
+
+ a = omp_init_allocator (omp_high_bw_mem_space,
+ sizeof (traits4) / sizeof (traits4[0]),
+ traits4);
+ if (a == omp_null_allocator)
+ abort ();
+ if (traits3[5].key != omp_atk_fb_data)
+ abort ();
+ traits3[5].value = (uintptr_t) a;
+ a2 = omp_init_allocator (omp_high_bw_mem_space,
+ sizeof (traits3) / sizeof (traits3[0]),
+ traits3);
+ if (a2 == omp_null_allocator)
+ abort ();
+ omp_set_default_allocator (a2);
+#ifdef __cplusplus
+ p = static_cast <int *> (omp_aligned_calloc (4, 21, 20));
+#else
+ p = (int *) omp_aligned_calloc (4, 21, 20, omp_null_allocator);
+#endif
+ check_all_zero (p, 21*20);
+ if ((((uintptr_t) p) % 32) != 0)
+ abort ();
+ for (i = 0; i < 420 / sizeof (int); i++)
+ if (p[i])
+ abort ();
+ p[0] = 5;
+ p[419 / sizeof (int)] = 6;
+ q = (int *) omp_aligned_calloc (64, 12, 64, omp_null_allocator);
+ check_all_zero (q, 12*64);
+ if ((((uintptr_t) q) % 128) != 0)
+ abort ();
+ for (i = 0; i < 768 / sizeof (int); i++)
+ if (q[i])
+ abort ();
+ q[0] = 7;
+ q[767 / sizeof (int)] = 8;
+ if (omp_aligned_calloc (8, 24, 32, omp_null_allocator) != NULL)
+ abort ();
+#ifdef __cplusplus
+ omp_free (p);
+ omp_free (q);
+ omp_free (NULL);
+#else
+ omp_free (p, omp_null_allocator);
+ omp_free (q, omp_null_allocator);
+ omp_free (NULL, omp_null_allocator);
+#endif
+ omp_free (NULL, omp_null_allocator);
+ omp_destroy_allocator (a2);
+ omp_destroy_allocator (a);
+ return 0;
+}
next prev parent reply other threads:[~2023-07-12 12:05 UTC|newest]
Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-07-11 10:35 Tobias Burnus
2023-07-12 12:05 ` Tobias Burnus [this message]
2023-07-13 16:13 ` Prathamesh Kulkarni
2023-07-14 7:27 ` Tobias Burnus
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=5b66591e-6af2-7219-acfc-640aeffad0b0@codesourcery.com \
--to=tobias@codesourcery.com \
--cc=gcc-patches@gcc.gnu.org \
--cc=jakub@redhat.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).