[PATCH 3/7] OpenMP 4.0 offloading infrastructure: Offload tables.

gcc/
	* Makefile.in (GTFILES): Add omp-low.h to list of GC files.
	* cgraphunit.c: Include omp-low.h.
	* doc/tm.texi: Regenerate.
	* doc/tm.texi.in (TARGET_RECORD_OFFLOAD_SYMBOL): Document.
	* gengtype.c (open_base_files): Add omp-low.h to ifiles.
	* lto-cgraph.c (output_offload_tables): New function.
	(input_offload_tables): Likewise.
	* lto-section-in.c (lto_section_name): Add "offload_table".
	* lto-section-names.h (OFFLOAD_VAR_TABLE_SECTION_NAME): Define.
	(OFFLOAD_FUNC_TABLE_SECTION_NAME): Likewise.
	* lto-streamer-out.c (lto_output): Call output_offload_tables.
	* lto-streamer.h (lto_section_type): Add LTO_section_offload_table.
	(output_offload_tables, input_offload_tables): Declare.
	* omp-low.c: Include common/common-target.h and lto-section-names.h.
	(offload_funcs, offload_vars): New global <tree, va_gc> vectors.
	(expand_omp_target): Add child_fn into offload_funcs vector.
	(add_decls_addresses_to_decl_constructor): New function.
	(omp_finish_file): Likewise.
	* omp-low.h (omp_finish_file, offload_funcs, offload_vars): Declare.
	* target.def (record_offload_symbol): New DEFHOOK.
	* toplev.c: Include omp-low.h.
	(compile_file): Call omp_finish_file.
	* varpool.c: Include omp-low.h.
	(varpool_node::get_create): Add decl into offload_vars vector.

gcc/lto/
	* lto/lto.c (read_cgraph_and_symbols): Call input_offload_tables.

Co-Authored-By: Andrey Turetskiy <andrey.turetskiy@intel.com>
Co-Authored-By: Bernd Schmidt <bernds@codesourcery.com>
Co-Authored-By: Ilya Tocar <ilya.tocar@intel.com>
Co-Authored-By: Michael Zolotukhin <michael.v.zolotukhin@intel.com>

From-SVN: r217489

1 files changed, 94 insertions, 0 deletions

diff --git a/gcc/lto-cgraph.c b/gcc/lto-cgraph.c
index fc8410c..b29d1b5 100644
--- a/gcc/lto-cgraph.c
+++ b/gcc/lto-cgraph.c
@@ -61,6 +61,7 @@ along with GCC; see the file COPYING3.  If not see
 #include "context.h"
 #include "pass_manager.h"
 #include "ipa-utils.h"
+#include "omp-low.h"
 
 /* True when asm nodes has been output.  */
 bool asm_nodes_output = false;
@@ -1068,6 +1069,50 @@ read_string (struct lto_input_block *ib)
   return str;
 }
 
+/* Output function/variable tables that will allow libgomp to look up offload
+   target code.
+   OFFLOAD_FUNCS is filled in expand_omp_target, OFFLOAD_VARS is filled in
+   varpool_node::get_create.  In WHOPR (partitioned) mode during the WPA stage
+   both OFFLOAD_FUNCS and OFFLOAD_VARS are filled by input_offload_tables.  */
+
+void
+output_offload_tables (void)
+{
+  if (vec_safe_is_empty (offload_funcs) && vec_safe_is_empty (offload_vars))
+    return;
+
+  struct lto_simple_output_block *ob
+    = lto_create_simple_output_block (LTO_section_offload_table);
+
+  for (unsigned i = 0; i < vec_safe_length (offload_funcs); i++)
+    {
+      streamer_write_enum (ob->main_stream, LTO_symtab_tags,
+			   LTO_symtab_last_tag, LTO_symtab_unavail_node);
+      lto_output_fn_decl_index (ob->decl_state, ob->main_stream,
+				(*offload_funcs)[i]);
+    }
+
+  for (unsigned i = 0; i < vec_safe_length (offload_vars); i++)
+    {
+      streamer_write_enum (ob->main_stream, LTO_symtab_tags,
+			   LTO_symtab_last_tag, LTO_symtab_variable);
+      lto_output_var_decl_index (ob->decl_state, ob->main_stream,
+				 (*offload_vars)[i]);
+    }
+
+  streamer_write_uhwi_stream (ob->main_stream, 0);
+  lto_destroy_simple_output_block (ob);
+
+  /* In WHOPR mode during the WPA stage the joint offload tables need to be
+     streamed to one partition only.  That's why we free offload_funcs and
+     offload_vars after the first call of output_offload_tables.  */
+  if (flag_wpa)
+    {
+      vec_free (offload_funcs);
+      vec_free (offload_vars);
+    }
+}
+
 /* Overwrite the information in NODE based on FILE_DATA, TAG, FLAGS,
    STACK_SIZE, SELF_TIME and SELF_SIZE.  This is called either to initialize
    NODE or to replace the values in it, for instance because the first
@@ -1794,6 +1839,55 @@ input_symtab (void)
     }
 }
 
+/* Input function/variable tables that will allow libgomp to look up offload
+   target code, and store them into OFFLOAD_FUNCS and OFFLOAD_VARS.  */
+
+void
+input_offload_tables (void)
+{
+  struct lto_file_decl_data **file_data_vec = lto_get_file_decl_data ();
+  struct lto_file_decl_data *file_data;
+  unsigned int j = 0;
+
+  while ((file_data = file_data_vec[j++]))
+    {
+      const char *data;
+      size_t len;
+      struct lto_input_block *ib
+	= lto_create_simple_input_block (file_data, LTO_section_offload_table,
+					 &data, &len);
+      if (!ib)
+	continue;
+
+      enum LTO_symtab_tags tag
+	= streamer_read_enum (ib, LTO_symtab_tags, LTO_symtab_last_tag);
+      while (tag)
+	{
+	  if (tag == LTO_symtab_unavail_node)
+	    {
+	      int decl_index = streamer_read_uhwi (ib);
+	      tree fn_decl
+		= lto_file_decl_data_get_fn_decl (file_data, decl_index);
+	      vec_safe_push (offload_funcs, fn_decl);
+	    }
+	  else if (tag == LTO_symtab_variable)
+	    {
+	      int decl_index = streamer_read_uhwi (ib);
+	      tree var_decl
+		= lto_file_decl_data_get_var_decl (file_data, decl_index);
+	      vec_safe_push (offload_vars, var_decl);
+	    }
+	  else
+	    fatal_error ("invalid offload table in %s", file_data->file_name);
+
+	  tag = streamer_read_enum (ib, LTO_symtab_tags, LTO_symtab_last_tag);
+	}
+
+      lto_destroy_simple_input_block (file_data, LTO_section_offload_table,
+				      ib, data, len);
+    }
+}
+
 /* True when we need optimization summary for NODE.  */
 
 static int