On 08/03/2022 11:30, Hafiz Abid Qadeer wrote:
This patches changes calls to malloc/free/calloc/realloc and operator new to
memory allocation functions in libgomp with
allocator=ompx_unified_shared_mem_alloc.
This additional patch adds transformation for omp_target_alloc. The
OpenMP 5.0 document says that addresses allocated this way needs to work
without is_device_ptr. The easiest way to make that work is to make them
USM addresses.
I will commit this to OG11 shortly.
Andrewopenmp: Do USM transform for omp_target_alloc
OpenMP 5.0 says that omp_target_alloc should return USM addresses.
gcc/ChangeLog:
* omp-low.c (usm_transform): Transform omp_target_alloc and
omp_target_free.
libgomp/ChangeLog:
* testsuite/libgomp.c/usm-6.c: Add omp_target_alloc.
gcc/testsuite/ChangeLog:
* c-c++-common/gomp/usm-2.c: Add omp_target_alloc.
* c-c++-common/gomp/usm-3.c: Add omp_target_alloc.
diff --git a/gcc/omp-low.c b/gcc/omp-low.c
index 4e8ab9e4ca0..9235eafd1d7 100644
--- a/gcc/omp-low.c
+++ b/gcc/omp-low.c
@@ -15880,7 +15880,8 @@ usm_transform (gimple_stmt_iterator *gsi_p, bool *,
if ((strcmp (name, "malloc") == 0)
|| (fndecl_built_in_p (fndecl, BUILT_IN_NORMAL)
&& DECL_FUNCTION_CODE (fndecl) == BUILT_IN_MALLOC)
-|| DECL_IS_REPLACEABLE_OPERATOR_NEW_P (fndecl))
+|| DECL_IS_REPLACEABLE_OPERATOR_NEW_P (fndecl)
+|| strcmp (name, "omp_target_alloc") == 0)
{
tree omp_alloc_type
= build_function_type_list (ptr_type_node, size_type_node,
@@ -15952,7 +15953,8 @@ usm_transform (gimple_stmt_iterator *gsi_p, bool *,
|| (fndecl_built_in_p (fndecl, BUILT_IN_NORMAL)
&& DECL_FUNCTION_CODE (fndecl) == BUILT_IN_FREE)
|| (DECL_IS_OPERATOR_DELETE_P (fndecl)
- && DECL_IS_REPLACEABLE_OPERATOR (fndecl)))
+ && DECL_IS_REPLACEABLE_OPERATOR (fndecl))
+ || strcmp (name, "omp_target_free") == 0)
{
tree omp_free_type
= build_function_type_list (void_type_node, ptr_type_node,
diff --git a/gcc/testsuite/c-c++-common/gomp/usm-2.c
b/gcc/testsuite/c-c++-common/gomp/usm-2.c
index 64dbb6be131..8c20ef94e69 100644
--- a/gcc/testsuite/c-c++-common/gomp/usm-2.c
+++ b/gcc/testsuite/c-c++-common/gomp/usm-2.c
@@ -12,6 +12,8 @@ void *aligned_alloc (__SIZE_TYPE__, __SIZE_TYPE__);
void *calloc(__SIZE_TYPE__, __SIZE_TYPE__);
void *realloc(void *, __SIZE_TYPE__);
void free (void *);
+void *omp_target_alloc (__SIZE_TYPE__, int);
+void omp_target_free (void *, int);
#ifdef __cplusplus
}
@@ -24,16 +26,21 @@ foo ()
void *p2 = realloc(p1, 30);
void *p3 = calloc(4, 15);
void *p4 = aligned_alloc(16, 40);
+ void *p5 = omp_target_alloc(50, 1);
free (p2);
free (p3);
free (p4);
+ omp_target_free (p5, 1);
}
/* { dg-final { scan-tree-dump-times "omp_alloc \\(20, 10\\)" 1
"usm_transform" } } */
/* { dg-final { scan-tree-dump-times "omp_realloc \\(.*, 30, 10, 10\\)" 1
"usm_transform" } } */
/* { dg-final { scan-tree-dump-times "omp_calloc \\(4, 15, 10\\)" 1
"usm_transform" } } */
/* { dg-final { scan-tree-dump-times "omp_aligned_alloc \\(16, 40, 10\\)" 1
"usm_transform" } } */
-/* { dg-final { scan-tree-dump-times "omp_free" 3 "usm_transform" } } */
+/* { dg-final { scan-tree-dump-times "omp_alloc \\(50, 10\\)" 1
"usm_transform" } } */
+/* { dg-final { scan-tree-dump-times "omp_free" 4 "usm_transform" } } */
/* { dg-final { scan-tree-dump-not " free" "usm_transform" } } */
/* { dg-final { scan-tree-dump-not " aligned_alloc" "usm_transform" } } */
/* { dg-final { scan-tree-dump-not " malloc" "usm_transform" } } */
+/* { dg-final { scan-tree-dump-not " omp_target_alloc" "usm_transform" } } */
+/* { dg-final { scan-tree-dump-not " omp_target_free" "usm_transform" } } */
diff --git a/gcc/testsuite/c-c++-common/gomp/usm-3.c
b/gcc/testsuite/c-c++-common/gomp/usm-3.c
index 934582ea5fd..2b0cbb45e27 100644
--- a/gcc/testsuite/c-c++-common/gomp/usm-3.c
+++ b/gcc/testsuite/c-c++-common/gomp/usm-3.c
@@ -10,6 +10,8 @@ void *aligned_alloc (__SIZE_TYPE__, __SIZE_TYPE__);
void *calloc(__SIZE_TYPE__, __SIZE_TYPE__);
void *realloc(void *, __SIZE_TYPE__);
void free (void *);
+void *omp_target_alloc (__SIZE_TYPE__, int);
+void omp_target_free (void *, int);
#ifdef __cplusplus
}
@@ -22,16 +24,21 @@ foo ()
void *p2 = realloc(p1, 30);
void *p3 = calloc(4, 15);
void *p4 = aligned_alloc(16, 40);
+ void *p5 = omp_target_alloc(50, 1);
free (p2);
free (p3);
free (p4);
+ omp_target_free (p5, 1);
}
/* { dg-final { scan-tree-dump-times "omp_alloc \\(20, 10\\)" 1
"usm_transform" } } */
/* { dg-final { scan-tree-dump-times "omp_realloc \\(.*, 30, 10, 10\\)" 1
"usm_transform" } } */
/* { dg-final { scan-tree-dump-times "omp_calloc
