gimplify.c (gimplify_scan_omp_clauses): No special handling for OMP_CLAUSE_TILE.

2017-02-09  Nathan Sidwell  <nathan@codesourcery.com>
	    Cesar Philippidis  <cesar@codesourcery.com>
	    Joseph Myers  <joseph@codesourcery.com>
	    Chung-Lin Tang  <cltang@codesourcery.com>

	gcc/
	* gimplify.c (gimplify_scan_omp_clauses): No special handling for
	OMP_CLAUSE_TILE.
	(gimplify_adjust_omp_clauses): Don't delete TILE.
	(gimplify_omp_for): Deal with TILE.
	* internal-fn.c (expand_GOACC_TILE): New function.
	* internal-fn.def (GOACC_DIM_POS): Comment may be overly conservative.
	(GOACC_TILE): New.
	* omp-expand.c (struct oacc_collapse): Add tile and outer fields.
	(expand_oacc_collapse_init): Add LOC paramter.  Initialize tile
	element fields.
	(expand_oacc_collapse_vars): Add INNER parm, adjust for tiling,
	avoid DIV for outermost collapse var.
	(expand_oacc_for): Insert tile element loop as needed.  Adjust.
	Remove out of date comments, fix whitespace.
	* omp-general.c (omp_extract_for_data): Deal with tiling.
	* omp-general.h (enum oacc_loop_flags): Add OLF_TILE flag,
	adjust OLF_DIM_BASE value.
	(struct omp_for_data): Add tiling field.
	* omp-low.c (scan_sharing_clauses): Allow OMP_CLAUSE_TILE.
	(lower_oacc_head_mark): Add OLF_TILE as appropriate.  Ensure 2 levels
	for auto loops.  Remove default auto determining, moved to
	oacc_loop_fixed_partitions.
	* omp-offload.c (struct oacc_loop): Change 'ifns' to vector of call
	stmts, add e_mask field.
	(oacc_dim_call): New function, abstracted out from oacc_thread_numbers.
	(oacc_thread_numbers): Use oacc_dim_call.
	(oacc_xform_tile): New.
	(new_oacc_loop_raw): Initialize e_mask, adjust for ifns vector.
	(finish_oacc_loop): Adjust for ifns vector.
	(oacc_loop_discover_walk): Append loop abstraction sites to list,
	add case for GOACC_TILE fns.
	(oacc_loop_xform_loop): Delete.
	(oacc_loop_process): Iterate over call list directly, and add
	handling for GOACC_TILE fns.
	(oacc_loop_fixed_partitions): Determine default auto, deal with TILE,
	dump partitioning.
	(oacc_loop_auto_partitions): Add outer_assign parm. Assign all but
	vector partitioning to outer loops.  Assign 2 partitions to loops
	when available. Add TILE handling.
	(oacc_loop_partition): Adjust oacc_loop_auto_partitions call.
	(execite_oacc_device_lower): Process GOACC_TILE fns, ignore unknown specs.
	* tree-nested.c (convert_nonlocal_omp_clauses): Allow OMP_CLAUSE_TILE.
	* tree.c (omp_clause_num_ops): Adjust TILE ops.
	* tree.h (OMP_CLAUSE_TILE_ITERVAR, OMP_CLAUSE_TILE_COUNT): New.

	gcc/c/
	* c-parser.c (c_parser_omp_clause_collapse): Disallow tile.
	(c_parser_oacc_clause_tile): Disallow collapse. Fix parsing and
	semantic checking.
	* c-parser.c (c_parser_omp_for_loop): Accept tiling constructs.

	gcc/cp/
	* parser.c (cp_parser_oacc_clause_tile): Disallow collapse.  Fix
	parsing.  Parse constant expression. Remove semantic checking.
	(cp_parser_omp_clause_collapse): Disallow tile.
	(cp_parser_omp_for_loop): Deal with tile clause.  Don't emit a parse
	error about missing for after already emitting one.  Use more
	conventional for idiom for unbounded loop.
	* pt.c (tsubst_omp_clauses): Handle OMP_CLAUSE_TILE.
	* semantics.c (finish_omp_clauses): Correct TILE semantic check.
	(finish_omp_for): Deal with tile clause.

	gcc/fortran/
	* openmp.c (resolve_omp_clauses): Error on directives
	containing both tile and collapse clauses.
	(resolve_oacc_loop_blocks): Represent '*' tile arguments as zero.
	* trans-openmp.c (gfc_trans_omp_do): Lower tiled loops like
	collapsed loops.

	gcc/testsuite/
	* c-c++-common/goacc/combined-directives.c: Remove xfail.
	* c-c++-common/goacc/loop-auto-1.c: Adjust and add additional case.
	* c-c++-common/goacc/loop-auto-2.c: New.
	* c-c++-common/goacc/tile.c: Include stdbool, fix expected errors.
	* c-c++-common/goacc/tile-2.c: New.
	* g++.dg/goacc/template.C: Test tile subst.  Adjust erroneous uses.
	* g++.dg/goacc/tile-1.C: New, check tile subst.
	* gcc.dg/goacc/loop-processing-1.c: Adjust dg-final pattern.
	* gfortran.dg/goacc/combined-directives.f90: Remove xfail.
	* gfortran.dg/goacc/tile-1.f90: New test.
	* gfortran.dg/goacc/tile-2.f90: New test.
	* gfortran.dg/goacc/tile-lowering.f95: New test.

	libgomp/
	* testsuite/libgomp.oacc-c-c++-common/tile-1.c: New.
	* testsuite/libgomp.oacc-c-c++-common/loop-auto-1.c: Adjust and
	add additional case.
	* testsuite/libgomp.oacc-c-c++-common/vprop.c: XFAIL under
	"openacc_nvidia_accel_selected".
	* libgomp.oacc-fortran/nested-function-1.f90 (test2):
	Add num_workers(8) clause.

From-SVN: r245300

1 files changed, 21 insertions, 19 deletions

diff --git a/gcc/c/c-parser.c b/gcc/c/c-parser.c
index 5c152ab..6e83728 100644
--- a/gcc/c/c-parser.c
+++ b/gcc/c/c-parser.c
@@ -11023,6 +11023,7 @@ c_parser_omp_clause_collapse (c_parser *parser, tree list)
   location_t loc;
 
   check_no_duplicate_clause (list, OMP_CLAUSE_COLLAPSE, "collapse");
+  check_no_duplicate_clause (list, OMP_CLAUSE_TILE, "tile");
 
   loc = c_parser_peek_token (parser)->location;
   if (c_parser_require (parser, CPP_OPEN_PAREN, "expected %<(%>"))
@@ -11933,10 +11934,11 @@ static tree
 c_parser_oacc_clause_tile (c_parser *parser, tree list)
 {
   tree c, expr = error_mark_node;
-  location_t loc, expr_loc;
+  location_t loc;
   tree tile = NULL_TREE;
 
   check_no_duplicate_clause (list, OMP_CLAUSE_TILE, "tile");
+  check_no_duplicate_clause (list, OMP_CLAUSE_COLLAPSE, "collapse");
 
   loc = c_parser_peek_token (parser)->location;
   if (!c_parser_require (parser, CPP_OPEN_PAREN, "expected %<(%>"))
@@ -11944,16 +11946,19 @@ c_parser_oacc_clause_tile (c_parser *parser, tree list)
 
   do
     {
+      if (tile && !c_parser_require (parser, CPP_COMMA, "expected %<,%>"))
+	return list;
+
       if (c_parser_next_token_is (parser, CPP_MULT)
 	  && (c_parser_peek_2nd_token (parser)->type == CPP_COMMA
 	      || c_parser_peek_2nd_token (parser)->type == CPP_CLOSE_PAREN))
 	{
 	  c_parser_consume_token (parser);
-	  expr = integer_minus_one_node;
+	  expr = integer_zero_node;
 	}
       else
 	{
-	  expr_loc = c_parser_peek_token (parser)->location;
+	  location_t expr_loc = c_parser_peek_token (parser)->location;
 	  c_expr cexpr = c_parser_expr_no_commas (parser, NULL);
 	  cexpr = convert_lvalue_to_rvalue (expr_loc, cexpr, false, true);
 	  expr = cexpr.value;
@@ -11965,28 +11970,19 @@ c_parser_oacc_clause_tile (c_parser *parser, tree list)
 	      return list;
 	    }
 
-	  if (!INTEGRAL_TYPE_P (TREE_TYPE (expr)))
-	    {
-	      c_parser_error (parser, "%<tile%> value must be integral");
-	      return list;
-	    }
-
 	  expr = c_fully_fold (expr, false, NULL);
 
-	  /* Attempt to statically determine when expr isn't positive.  */
-	  c = fold_build2_loc (expr_loc, LE_EXPR, boolean_type_node, expr,
-			       build_int_cst (TREE_TYPE (expr), 0));
-	  protected_set_expr_location (c, expr_loc);
-	  if (c == boolean_true_node)
+	  if (!INTEGRAL_TYPE_P (TREE_TYPE (expr))
+	      || !tree_fits_shwi_p (expr)
+	      || tree_to_shwi (expr) <= 0)
 	    {
-	      warning_at (expr_loc, 0,"%<tile%> value must be positive");
-	      expr = integer_one_node;
+	      error_at (expr_loc, "%<tile%> argument needs positive"
+			" integral constant");
+	      expr = integer_zero_node;
 	    }
 	}
 
       tile = tree_cons (NULL_TREE, expr, tile);
-      if (c_parser_next_token_is (parser, CPP_COMMA))
-	c_parser_consume_token (parser);
     }
   while (c_parser_next_token_is_not (parser, CPP_CLOSE_PAREN));
 
@@ -14910,11 +14906,17 @@ c_parser_omp_for_loop (location_t loc, c_parser *parser, enum tree_code code,
   bool fail = false, open_brace_parsed = false;
   int i, collapse = 1, ordered = 0, count, nbraces = 0;
   location_t for_loc;
+  bool tiling = false;
   vec<tree, va_gc> *for_block = make_tree_vector ();
 
   for (cl = clauses; cl; cl = OMP_CLAUSE_CHAIN (cl))
     if (OMP_CLAUSE_CODE (cl) == OMP_CLAUSE_COLLAPSE)
       collapse = tree_to_shwi (OMP_CLAUSE_COLLAPSE_EXPR (cl));
+    else if (OMP_CLAUSE_CODE (cl) == OMP_CLAUSE_TILE)
+      {
+	tiling = true;
+	collapse = list_length (OMP_CLAUSE_TILE_LIST (cl));
+      }
     else if (OMP_CLAUSE_CODE (cl) == OMP_CLAUSE_ORDERED
 	     && OMP_CLAUSE_ORDERED_EXPR (cl))
       {
@@ -14944,7 +14946,7 @@ c_parser_omp_for_loop (location_t loc, c_parser *parser, enum tree_code code,
 	  pc = &OMP_CLAUSE_CHAIN (*pc);
     }
 
-  gcc_assert (collapse >= 1 && ordered >= 0);
+  gcc_assert (tiling || (collapse >= 1 && ordered >= 0));
   count = ordered ? ordered : collapse;
 
   declv = make_tree_vec (count);