Re: Ping [PATCH, Fortran, pr78505, v1] [F08] Coarray source allocation not synchronizing on oversubscribed cores

[Andre Vehreschild <vehre at gmx dot de>]

Ping!

On Fri, 2 Dec 2016 16:46:29 +0100
Andre Vehreschild <vehre@gmx.de> wrote:

> Hi all,
> 
> attached patch adds a call to sync_all after an ALLOCATE allocating a coarray.
> This is to adhere to standard wanting:
> 
> ..., execution of the segment (11.6.2) following the statement is delayed
> until all other active images in the current team have executed the same
> statement the same number of times in this team.
> 
> This, esp. the "statement", means that assigning the SOURCE= is to come before
> the sync all, which means we have to do it explicitly after that assignment.
> Or the other way around the sync all can be done in library caf_register().
> 
> Bootstraps and regtests ok on x86_64-linux/F23. Ok for trunk?
> 
> Regards,
> 	Andre


-- 
Andre Vehreschild * Email: vehre ad gmx dot de

Attachment: pr78505_v1.clog
Description: Text document

diff --git a/gcc/fortran/trans-stmt.c b/gcc/fortran/trans-stmt.c
index 514db28..2219bcc 100644
--- a/gcc/fortran/trans-stmt.c
+++ b/gcc/fortran/trans-stmt.c
@@ -5506,7 +5506,7 @@ gfc_trans_allocate (gfc_code * code)
   stmtblock_t block;
   stmtblock_t post;
   tree nelems;
-  bool upoly_expr, tmp_expr3_len_flag = false, al_len_needs_set;
+  bool upoly_expr, tmp_expr3_len_flag = false, al_len_needs_set, is_coarray ;
   gfc_symtree *newsym = NULL;
 
   if (!code->ext.alloc.list)
@@ -5516,6 +5516,7 @@ gfc_trans_allocate (gfc_code * code)
   expr3 = expr3_vptr = expr3_len = expr3_esize = NULL_TREE;
   label_errmsg = label_finish = errmsg = errlen = NULL_TREE;
   e3_is = E3_UNSET;
+  is_coarray = false;
 
   gfc_init_block (&block);
   gfc_init_block (&post);
@@ -5555,8 +5556,9 @@ gfc_trans_allocate (gfc_code * code)
      expression.  */
   if (code->expr3)
     {
-      bool vtab_needed = false, temp_var_needed = false,
-	  is_coarray = gfc_is_coarray (code->expr3);
+      bool vtab_needed = false, temp_var_needed = false;
+
+      is_coarray = gfc_is_coarray (code->expr3);
 
       /* Figure whether we need the vtab from expr3.  */
       for (al = code->ext.alloc.list; !vtab_needed && al != NULL;
@@ -6093,6 +6095,9 @@ gfc_trans_allocate (gfc_code * code)
 	      tree caf_decl, token;
 	      gfc_se caf_se;
 
+	      /* Set flag, to add synchronize after the allocate.  */
+	      is_coarray = true;
+
 	      gfc_init_se (&caf_se, NULL);
 
 	      caf_decl = gfc_get_tree_for_caf_expr (expr);
@@ -6114,6 +6119,11 @@ gfc_trans_allocate (gfc_code * code)
 	}
       else
 	{
+	  /* Allocating coarrays needs a sync after the allocate executed.
+	     Set the flag to add the sync after all objects are allocated.  */
+	  is_coarray = is_coarray || (gfc_caf_attr (expr).codimension
+				      && flag_coarray == GFC_FCOARRAY_LIB);
+
 	  if (expr->ts.type == BT_CHARACTER && al_len != NULL_TREE
 	      && expr3_len != NULL_TREE)
 	    {
@@ -6357,6 +6367,15 @@ gfc_trans_allocate (gfc_code * code)
       gfc_add_modify (&block, se.expr, tmp);
     }
 
+  if (is_coarray && flag_coarray == GFC_FCOARRAY_LIB)
+    {
+      /* Add a sync all after the allocation has been executed.  */
+      tmp = build_call_expr_loc (input_location, gfor_fndecl_caf_sync_all,
+				 3, null_pointer_node, null_pointer_node,
+				 integer_zero_node);
+      gfc_add_expr_to_block (&post, tmp);
+    }
+
   gfc_add_block_to_block (&block, &se.post);
   gfc_add_block_to_block (&block, &post);
 
diff --git a/gcc/testsuite/gfortran.dg/coarray_alloc_with_implicit_sync_1.f90 b/gcc/testsuite/gfortran.dg/coarray_alloc_with_implicit_sync_1.f90
new file mode 100644
index 0000000..1dbbcb7
--- /dev/null
+++ b/gcc/testsuite/gfortran.dg/coarray_alloc_with_implicit_sync_1.f90
@@ -0,0 +1,10 @@
+! { dg-do compile }
+! { dg-options "-fdump-tree-original -fcoarray=lib" }
+! Check that allocating a coarray adds an implicit sync all.
+ 
+ implicit none
+ integer, allocatable :: f(:)[:]
+ allocate( f(20)[*], source = 1 )
+end
+
+! { dg-final { scan-tree-dump-times "_gfortran_caf_sync_all \\(" 1 "original" } }