When unified shared memory is required, the default memory space should also be
unified.
libgomp/ChangeLog:
* config/linux/allocator.c (linux_memspace_alloc): Check
omp_requires_mask.
(linux_memspace_calloc): Likewise.
(linux_memspace_free): Likewise.
(linux_memspace_realloc): Likewise.
* libgomp.h (omp_requires_mask): New extern.
* target.c (omp_requires_mask): Remove static.
* testsuite/libgomp.c-c++-common/target-implicit-map-4.c: Add
NO_USM_STACK conditional code.
---
libgomp/config/linux/allocator.c | 16 ++++++++++++----
libgomp/libgomp.h | 1 +
libgomp/target.c | 2 +-
.../libgomp.c-c++-common/target-implicit-map-4.c | 16 ++++++++++++++++
4 files changed, 30 insertions(+), 5 deletions(-)
diff --git a/libgomp/config/linux/allocator.c b/libgomp/config/linux/allocator.c
index 81d2877b8f1..a026f49be16 100644
--- a/libgomp/config/linux/allocator.c
+++ b/libgomp/config/linux/allocator.c
@@ -101,7 +101,9 @@ linux_memspace_alloc (omp_memspace_handle_t memspace,
size_t size, int pin,
/* Explicit pinning may not be required. */
pin = pin && !always_pinned_mode;
- if (memspace == ompx_gnu_unified_shared_mem_space)
+ if (memspace == ompx_gnu_unified_shared_mem_space
+ || (memspace == omp_default_mem_space
+ && (omp_requires_mask & GOMP_REQUIRES_UNIFIED_SHARED_MEMORY)))
addr = gomp_usm_alloc (size);
else if (pin)
{
@@ -194,7 +196,9 @@ linux_memspace_calloc (omp_memspace_handle_t memspace,
size_t size, int pin)
/* Explicit pinning may not be required. */
pin = pin && !always_pinned_mode;
- if (memspace == ompx_gnu_unified_shared_mem_space)
+ if (memspace == ompx_gnu_unified_shared_mem_space
+ || (memspace == omp_default_mem_space
+ && (omp_requires_mask & GOMP_REQUIRES_UNIFIED_SHARED_MEMORY)))
{
void *ret = gomp_usm_alloc (size);
memset (ret, 0, size);
@@ -216,7 +220,9 @@ linux_memspace_free (omp_memspace_handle_t memspace, void
*addr, size_t size,
/* Explicit pinning may not be required. */
pin = pin && !always_pinned_mode;
- if (memspace == ompx_gnu_unified_shared_mem_space)
+ if (memspace == ompx_gnu_unified_shared_mem_space
+ || (memspace == omp_default_mem_space
+ && (omp_requires_mask & GOMP_REQUIRES_UNIFIED_SHARED_MEMORY)))
gomp_usm_free (addr);
else if (pin)
{
@@ -244,7 +250,9 @@ linux_memspace_realloc (omp_memspace_handle_t memspace,
void *addr,
/* Explicit pinning may not be required. */
pin = pin && !always_pinned_mode;
- if (memspace == ompx_gnu_unified_shared_mem_space)
+ if (memspace == ompx_gnu_unified_shared_mem_space
+ || (memspace == omp_default_mem_space
+ && (omp_requires_mask & GOMP_REQUIRES_UNIFIED_SHARED_MEMORY)))
/* Realloc is not implemented for USM. */
;
else if (oldpin && pin)
diff --git a/libgomp/libgomp.h b/libgomp/libgomp.h
index 707fcdb39d7..4c5c89c8454 100644
--- a/libgomp/libgomp.h
+++ b/libgomp/libgomp.h
@@ -1123,6 +1123,7 @@ extern int gomp_pause_host (void);
/* target.c */
+extern int omp_requires_mask;
extern void gomp_init_targets_once (void);
extern int gomp_get_num_devices (void);
extern bool gomp_target_task_fn (void *);
diff --git a/libgomp/target.c b/libgomp/target.c
index f0ee2c84197..455cac917c9 100644
--- a/libgomp/target.c
+++ b/libgomp/target.c
@@ -107,7 +107,7 @@ static int num_devices;
static int num_devices_openmp;
/* OpenMP requires mask. */
-static int omp_requires_mask;
+int omp_requires_mask;
/* Similar to gomp_realloc, but release register_lock before gomp_fatal. */
diff --git a/libgomp/testsuite/libgomp.c-c++-common/target-implicit-map-4.c
b/libgomp/testsuite/libgomp.c-c++-common/target-implicit-map-4.c
index 2766312292b..de865352e9b 100644
--- a/libgomp/testsuite/libgomp.c-c++-common/target-implicit-map-4.c
+++ b/libgomp/testsuite/libgomp.c-c++-common/target-implicit-map-4.c
@@ -6,6 +6,9 @@
/* { dg-skip-if "Not all devices allow USM" { offload_device_gcn && { !
omp_usm } } } */
+/* { dg-additional-options "-DNO_USM_STACK" { target offload_target_nvptx } }
*/
+/* { dg-additional-options "-DNO_USM_STACK" { target offload_target_amdgcn } }
*/
+
#pragma omp requires unified_shared_memory
/* Ensure that defaultmap(default : pointer) uses correct OpenMP 5.2
@@ -27,10 +30,23 @@ test_device (int dev)
intptr_t ip = (intptr_t) p2;
intptr_t ipa = (intptr_t) p2a;
+#if NO_USM_STACK
+ int A_init[3] = {1,2,3};
+ int B_init[5] = {4,5,6,7,8};
+ int *A = (int*) malloc (sizeof (A_init));
+ int *B = (int*) malloc (sizeof (B_init));
+ int *p3 = &A[0];
+ int *p3a = &B[0];
+
+ /* Not all USM supports stack variables. */
+ __builtin_memcpy (A, A_init, sizeof (A_init));
+ __builtin_memcpy (B, B_init, sizeof (B_init));
+#else
int A[3] = {1,2,3};
int B[5] = {4,5,6,7,8};
int *p3 = &A[0];
int *p3a = &B[0];
+#endif
const omp_alloctrait_t traits[]
= { { omp_atk_alignment, 128 },
--
2.41.0
