openmp: Differentiate between order(concurrent) and order(reproducible:concurrent)

While OpenMP 5.1 implies order(concurrent) is the same thing as
order(reproducible:concurrent), this is going to change in OpenMP 5.2, where
essentially order(concurrent) means nothing is stated on whether it is
reproducible or unconstrained (and is determined by other means, e.g. for/do
with schedule static or runtime with static being selected is implicitly
reproducible, distribute with dist_schedule static is implicitly reproducible,
loop is implicitly reproducible) and when the modifier is specified explicitly,
it overrides the implicit behavior either way.
And, when order(reproducible:concurrent) is used with e.g. schedule(dynamic)
or some other schedule that is by definition not reproducible, it is
implementation's duty to ensure it is reproducible, either by remembering how
it scheduled some loop and then replaying the same schedule when seeing loops
with the same directive/schedule/number of iterations, or by overriding the
schedule to some reproducible one.

This patch doesn't implement the 5.2 wording just yet, but in the FEs
differentiates between the 3 states - no explicit modifier, explicit reproducible
or explicit unconstrainted, so that the middle-end can easily switch any time.
Instead it follows the 5.1 wording where both order(concurrent) (implicit or
explicit) or order(reproducible:concurrent) imply reproducibility.
And, it implements the easier method, when for/do should be reproducible, it
just chooses static schedule.  order(concurrent) implies no OpenMP APIs in the
loop body nor threadprivate vars, so the exact scheduling isn't (easily at least)
observable.

2021-10-01  Jakub Jelinek  <jakub@redhat.com>

gcc/
	* tree.h (OMP_CLAUSE_ORDER_REPRODUCIBLE): Define.
	* tree-pretty-print.c (dump_omp_clause) <case OMP_CLAUSE_ORDER>: Print
	reproducible: for OMP_CLAUSE_ORDER_REPRODUCIBLE.
	* omp-general.c (omp_extract_for_data): If OMP_CLAUSE_ORDER is seen
	without OMP_CLAUSE_ORDER_UNCONSTRAINED, overwrite sched_kind to
	OMP_CLAUSE_SCHEDULE_STATIC.
gcc/c-family/
	* c-omp.c (c_omp_split_clauses): Also copy
	OMP_CLAUSE_ORDER_REPRODUCIBLE.
gcc/c/
	* c-parser.c (c_parser_omp_clause_order): Set
	OMP_CLAUSE_ORDER_REPRODUCIBLE for explicit reproducible: modifier.
gcc/cp/
	* parser.c (cp_parser_omp_clause_order): Set
	OMP_CLAUSE_ORDER_REPRODUCIBLE for explicit reproducible: modifier.
gcc/fortran/
	* gfortran.h (gfc_omp_clauses): Add order_reproducible bitfield.
	* dump-parse-tree.c (show_omp_clauses): Print REPRODUCIBLE: for it.
	* openmp.c (gfc_match_omp_clauses): Set order_reproducible for
	explicit reproducible: modifier.
	* trans-openmp.c (gfc_trans_omp_clauses): Set
	OMP_CLAUSE_ORDER_REPRODUCIBLE for order_reproducible.
	(gfc_split_omp_clauses): Also copy order_reproducible.
gcc/testsuite/
	* gfortran.dg/gomp/order-5.f90: Adjust scan-tree-dump-times regexps.
libgomp/
	* testsuite/libgomp.c-c++-common/order-reproducible-1.c: New test.
	* testsuite/libgomp.c-c++-common/order-reproducible-2.c: New test.

11 files changed, 53 insertions, 10 deletions

diff --git a/gcc/c-family/c-omp.c b/gcc/c-family/c-omp.c
index 1f07a0a..2849fda 100644
--- a/gcc/c-family/c-omp.c
+++ b/gcc/c-family/c-omp.c
@@ -2128,6 +2128,8 @@ c_omp_split_clauses (location_t loc, enum tree_code code,
 				    OMP_CLAUSE_ORDER);
 	      OMP_CLAUSE_ORDER_UNCONSTRAINED (c)
 		= OMP_CLAUSE_ORDER_UNCONSTRAINED (clauses);
+	      OMP_CLAUSE_ORDER_REPRODUCIBLE (c)
+		= OMP_CLAUSE_ORDER_REPRODUCIBLE (clauses);
 	      OMP_CLAUSE_CHAIN (c) = cclauses[C_OMP_CLAUSE_SPLIT_DISTRIBUTE];
 	      cclauses[C_OMP_CLAUSE_SPLIT_DISTRIBUTE] = c;
 	    }
@@ -2139,6 +2141,8 @@ c_omp_split_clauses (location_t loc, enum tree_code code,
 					OMP_CLAUSE_ORDER);
 		  OMP_CLAUSE_ORDER_UNCONSTRAINED (c)
 		    = OMP_CLAUSE_ORDER_UNCONSTRAINED (clauses);
+		  OMP_CLAUSE_ORDER_REPRODUCIBLE (c)
+		    = OMP_CLAUSE_ORDER_REPRODUCIBLE (clauses);
 		  OMP_CLAUSE_CHAIN (c) = cclauses[C_OMP_CLAUSE_SPLIT_FOR];
 		  cclauses[C_OMP_CLAUSE_SPLIT_FOR] = c;
 		  s = C_OMP_CLAUSE_SPLIT_SIMD;
diff --git a/gcc/c/c-parser.c b/gcc/c/c-parser.c
index 21ff25d..a66f43f 100644
--- a/gcc/c/c-parser.c
+++ b/gcc/c/c-parser.c
@@ -14626,6 +14626,7 @@ c_parser_omp_clause_order (c_parser *parser, tree list)
   tree c;
   const char *p;
   bool unconstrained = false;
+  bool reproducible = false;
 
   matching_parens parens;
   if (!parens.require_open (parser))
@@ -14636,7 +14637,9 @@ c_parser_omp_clause_order (c_parser *parser, tree list)
       p = IDENTIFIER_POINTER (c_parser_peek_token (parser)->value);
       if (strcmp (p, "unconstrained") == 0)
 	unconstrained = true;
-      else if (strcmp (p, "reproducible") != 0)
+      else if (strcmp (p, "reproducible") == 0)
+	reproducible = true;
+      else
 	{
 	  c_parser_error (parser, "expected %<reproducible%> or "
 				  "%<unconstrained%>");
@@ -14661,6 +14664,7 @@ c_parser_omp_clause_order (c_parser *parser, tree list)
   check_no_duplicate_clause (list, OMP_CLAUSE_ORDER, "order");
   c = build_omp_clause (loc, OMP_CLAUSE_ORDER);
   OMP_CLAUSE_ORDER_UNCONSTRAINED (c) = unconstrained;
+  OMP_CLAUSE_ORDER_REPRODUCIBLE (c) = reproducible;
   OMP_CLAUSE_CHAIN (c) = list;
   return c;
 
diff --git a/gcc/cp/parser.c b/gcc/cp/parser.c
index 04f5a24..c6f1a97 100644
--- a/gcc/cp/parser.c
+++ b/gcc/cp/parser.c
@@ -37735,6 +37735,7 @@ cp_parser_omp_clause_order (cp_parser *parser, tree list, location_t location)
   tree c, id;
   const char *p;
   bool unconstrained = false;
+  bool reproducible = false;
 
   matching_parens parens;
   if (!parens.require_open (parser))
@@ -37747,7 +37748,9 @@ cp_parser_omp_clause_order (cp_parser *parser, tree list, location_t location)
       p = IDENTIFIER_POINTER (id);
       if (strcmp (p, "unconstrained") == 0)
 	unconstrained = true;
-      else if (strcmp (p, "reproducible") != 0)
+      else if (strcmp (p, "reproducible") == 0)
+	reproducible = true;
+      else
 	{
 	  cp_parser_error (parser, "expected %<reproducible%> or "
 				   "%<unconstrained%>");
@@ -37778,6 +37781,7 @@ cp_parser_omp_clause_order (cp_parser *parser, tree list, location_t location)
   check_no_duplicate_clause (list, OMP_CLAUSE_ORDER, "order", location);
   c = build_omp_clause (location, OMP_CLAUSE_ORDER);
   OMP_CLAUSE_ORDER_UNCONSTRAINED (c) = unconstrained;
+  OMP_CLAUSE_ORDER_REPRODUCIBLE (c) = reproducible;
   OMP_CLAUSE_CHAIN (c) = list;
   return c;
 
diff --git a/gcc/fortran/dump-parse-tree.c b/gcc/fortran/dump-parse-tree.c
index 28eb09e..64e04c0 100644
--- a/gcc/fortran/dump-parse-tree.c
+++ b/gcc/fortran/dump-parse-tree.c
@@ -1634,6 +1634,8 @@ show_omp_clauses (gfc_omp_clauses *omp_clauses)
       fputs (" ORDER(", dumpfile);
       if (omp_clauses->order_unconstrained)
 	fputs ("UNCONSTRAINED:", dumpfile);
+      else if (omp_clauses->order_reproducible)
+	fputs ("REPRODUCIBLE:", dumpfile);
       fputs ("CONCURRENT)", dumpfile);
     }
   if (omp_clauses->ordered)
diff --git a/gcc/fortran/gfortran.h b/gcc/fortran/gfortran.h
index 7ef835b..c25d1cc 100644
--- a/gcc/fortran/gfortran.h
+++ b/gcc/fortran/gfortran.h
@@ -1491,8 +1491,8 @@ typedef struct gfc_omp_clauses
   unsigned inbranch:1, notinbranch:1, nogroup:1;
   unsigned sched_simd:1, sched_monotonic:1, sched_nonmonotonic:1;
   unsigned simd:1, threads:1, depend_source:1, destroy:1, order_concurrent:1;
-  unsigned order_unconstrained:1, capture:1, grainsize_strict:1;
-  unsigned num_tasks_strict:1;
+  unsigned order_unconstrained:1, order_reproducible:1, capture:1;
+  unsigned grainsize_strict:1, num_tasks_strict:1;
   ENUM_BITFIELD (gfc_omp_sched_kind) sched_kind:3;
   ENUM_BITFIELD (gfc_omp_device_type) device_type:2;
   ENUM_BITFIELD (gfc_omp_memorder) memorder:3;
diff --git a/gcc/fortran/openmp.c b/gcc/fortran/openmp.c
index 9ee52d6..6a4ca28 100644
--- a/gcc/fortran/openmp.c
+++ b/gcc/fortran/openmp.c
@@ -2374,8 +2374,9 @@ gfc_match_omp_clauses (gfc_omp_clauses **cp, const omp_mask mask,
 	    {
 	      if (m == MATCH_ERROR)
 		goto error;
-	      if (gfc_match (" reproducible : concurrent )") == MATCH_YES
-		  || gfc_match (" concurrent )") == MATCH_YES)
+	      if (gfc_match (" reproducible : concurrent )") == MATCH_YES)
+		c->order_reproducible = true;
+	      else if (gfc_match (" concurrent )") == MATCH_YES)
 		;
 	      else if (gfc_match (" unconstrained : concurrent )") == MATCH_YES)
 		c->order_unconstrained = true;
diff --git a/gcc/fortran/trans-openmp.c b/gcc/fortran/trans-openmp.c
index 4ca2c3f..d234d1b 100644
--- a/gcc/fortran/trans-openmp.c
+++ b/gcc/fortran/trans-openmp.c
@@ -3804,6 +3804,7 @@ gfc_trans_omp_clauses (stmtblock_t *block, gfc_omp_clauses *clauses,
     {
       c = build_omp_clause (gfc_get_location (&where), OMP_CLAUSE_ORDER);
       OMP_CLAUSE_ORDER_UNCONSTRAINED (c) = clauses->order_unconstrained;
+      OMP_CLAUSE_ORDER_REPRODUCIBLE (c) = clauses->order_reproducible;
       omp_clauses = gfc_trans_add_clause (c, omp_clauses);
     }
 
@@ -5895,6 +5896,8 @@ gfc_split_omp_clauses (gfc_code *code,
 	    = code->ext.omp_clauses->order_concurrent;
 	  clausesa[GFC_OMP_SPLIT_DISTRIBUTE].order_unconstrained
 	    = code->ext.omp_clauses->order_unconstrained;
+	  clausesa[GFC_OMP_SPLIT_DISTRIBUTE].order_reproducible
+	    = code->ext.omp_clauses->order_reproducible;
 	}
       if (mask & GFC_OMP_MASK_PARALLEL)
 	{
@@ -5951,6 +5954,8 @@ gfc_split_omp_clauses (gfc_code *code,
 	    = code->ext.omp_clauses->order_concurrent;
 	  clausesa[GFC_OMP_SPLIT_DO].order_unconstrained
 	    = code->ext.omp_clauses->order_unconstrained;
+	  clausesa[GFC_OMP_SPLIT_DO].order_reproducible
+	    = code->ext.omp_clauses->order_reproducible;
 	}
       if (mask & GFC_OMP_MASK_SIMD)
 	{
@@ -5969,6 +5974,8 @@ gfc_split_omp_clauses (gfc_code *code,
 	    = code->ext.omp_clauses->order_concurrent;
 	  clausesa[GFC_OMP_SPLIT_SIMD].order_unconstrained
 	    = code->ext.omp_clauses->order_unconstrained;
+	  clausesa[GFC_OMP_SPLIT_SIMD].order_reproducible
+	    = code->ext.omp_clauses->order_reproducible;
 	  /* And this is copied to all.  */
 	  clausesa[GFC_OMP_SPLIT_SIMD].if_expr
 	    = code->ext.omp_clauses->if_expr;
diff --git a/gcc/omp-general.c b/gcc/omp-general.c
index cc6aecb..1e4c0b2 100644
--- a/gcc/omp-general.c
+++ b/gcc/omp-general.c
@@ -193,6 +193,7 @@ omp_extract_for_data (gomp_for *for_stmt, struct omp_for_data *fd,
 		    == GF_OMP_FOR_KIND_DISTRIBUTE;
   bool taskloop = gimple_omp_for_kind (for_stmt)
 		  == GF_OMP_FOR_KIND_TASKLOOP;
+  bool order_reproducible = false;
   tree iterv, countv;
 
   fd->for_stmt = for_stmt;
@@ -277,10 +278,25 @@ omp_extract_for_data (gomp_for *for_stmt, struct omp_for_data *fd,
 	    && !OMP_CLAUSE__SCANTEMP__CONTROL (t))
 	  fd->have_nonctrl_scantemp = true;
 	break;
+      case OMP_CLAUSE_ORDER:
+	/* FIXME: For OpenMP 5.2 this should change to
+	   if (OMP_CLAUSE_ORDER_REPRODUCIBLE (t))
+	   (with the exception of loop construct but that lowers to
+	   no schedule/dist_schedule clauses currently).  */
+	if (!OMP_CLAUSE_ORDER_UNCONSTRAINED (t))
+	  order_reproducible = true;
       default:
 	break;
       }
 
+  /* For order(reproducible:concurrent) schedule ({dynamic,guided,runtime})
+     we have either the option to expensively remember at runtime how we've
+     distributed work from first loop and reuse that in following loops with
+     the same number of iterations and schedule, or just force static schedule.
+     OpenMP API calls etc. aren't allowed in order(concurrent) bodies so
+     users can't observe it easily anyway.  */
+  if (order_reproducible)
+    fd->sched_kind = OMP_CLAUSE_SCHEDULE_STATIC;
   if (fd->collapse > 1 || fd->tiling)
     fd->loops = loops;
   else
diff --git a/gcc/testsuite/gfortran.dg/gomp/order-5.f90 b/gcc/testsuite/gfortran.dg/gomp/order-5.f90
index 4d9e336..0dddb96 100644
--- a/gcc/testsuite/gfortran.dg/gomp/order-5.f90
+++ b/gcc/testsuite/gfortran.dg/gomp/order-5.f90
@@ -116,14 +116,14 @@ subroutine f4 (a)
   end do
 end
 
-! { dg-final { scan-tree-dump-times "#pragma omp distribute order\\(concurrent\\)" 6 "original"} }
+! { dg-final { scan-tree-dump-times "#pragma omp distribute order\\(reproducible:concurrent\\)" 6 "original"} }
 ! { dg-final { scan-tree-dump-times "#pragma omp distribute order\\(unconstrained:concurrent\\)" 6 "original"} }
-! { dg-final { scan-tree-dump-times "#pragma omp for nowait order\\(concurrent\\)" 6 "original"} }
+! { dg-final { scan-tree-dump-times "#pragma omp for nowait order\\(reproducible:concurrent\\)" 6 "original"} }
 ! { dg-final { scan-tree-dump-times "#pragma omp for nowait order\\(unconstrained:concurrent\\)" 6 "original"} }
-! { dg-final { scan-tree-dump-times "#pragma omp for order\\(concurrent\\)" 2 "original"} }
+! { dg-final { scan-tree-dump-times "#pragma omp for order\\(reproducible:concurrent\\)" 2 "original"} }
 ! { dg-final { scan-tree-dump-times "#pragma omp for order\\(unconstrained:concurrent\\)" 2 "original"} }
 ! { dg-final { scan-tree-dump-times "#pragma omp parallel" 12 "original"} }
-! { dg-final { scan-tree-dump-times "#pragma omp simd linear\\(i:1\\) order\\(concurrent\\)" 6 "original"} }
+! { dg-final { scan-tree-dump-times "#pragma omp simd linear\\(i:1\\) order\\(reproducible:concurrent\\)" 6 "original"} }
 ! { dg-final { scan-tree-dump-times "#pragma omp simd linear\\(i:1\\) order\\(unconstrained:concurrent\\)" 6 "original"} }
 ! { dg-final { scan-tree-dump-times "#pragma omp taskloop" 2 "original"} }
 ! { dg-final { scan-tree-dump-times "#pragma omp teams" 8 "original"} }
diff --git a/gcc/tree-pretty-print.c b/gcc/tree-pretty-print.c
index 35e567c..0b5bdd7 100644
--- a/gcc/tree-pretty-print.c
+++ b/gcc/tree-pretty-print.c
@@ -1165,6 +1165,8 @@ dump_omp_clause (pretty_printer *pp, tree clause, int spc, dump_flags_t flags)
       pp_string (pp, "order(");
       if (OMP_CLAUSE_ORDER_UNCONSTRAINED (clause))
 	pp_string (pp, "unconstrained:");
+      else if (OMP_CLAUSE_ORDER_REPRODUCIBLE (clause))
+	pp_string (pp, "reproducible:");
       pp_string (pp, "concurrent)");
       break;
 
diff --git a/gcc/tree.h b/gcc/tree.h
index 7d1257b..7542d97 100644
--- a/gcc/tree.h
+++ b/gcc/tree.h
@@ -1718,6 +1718,9 @@ class auto_suppress_location_wrappers
 /* True for unconstrained modifier on order(concurrent) clause.  */
 #define OMP_CLAUSE_ORDER_UNCONSTRAINED(NODE) \
   (OMP_CLAUSE_SUBCODE_CHECK (NODE, OMP_CLAUSE_ORDER)->base.public_flag)
+/* True for reproducible modifier on order(concurrent) clause.  */
+#define OMP_CLAUSE_ORDER_REPRODUCIBLE(NODE) \
+  TREE_PROTECTED (OMP_CLAUSE_SUBCODE_CHECK (NODE, OMP_CLAUSE_ORDER))
 
 #define OMP_CLAUSE_REDUCTION_CODE(NODE)	\
   (OMP_CLAUSE_RANGE_CHECK (NODE, OMP_CLAUSE_REDUCTION, \