mkoffload.c (process): Change offload data format.

	gcc/
	* config/nvptx/mkoffload.c (process): Change offload data format.

	libgomp/
	* plugin/plugin-nvptx.c (targ_fn_launch): Use GOMP_DIM_MAX.
	(struct targ_ptx_obj): New.
	(nvptx_tdata): Move earlier, change data format.
	(link_ptx): Take targ_ptx_obj ptr and count.  Allow multiple
	objects.
	(GOMP_OFFLOAD_load_image): Adjust.

Co-Authored-By: Bernd Schmidt <bernds@codesourcery.com>
From-SVN: r228308

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index ba25406f2ba45cb51f40a3e5138dd408a09da21c..6b5304819705dec6ab93e74fd0cb8987570716c8 100644 (file)
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,7 @@
+2015-09-30  Nathan Sidwell  <nathan@codesourcery.com>
+
+       * config/nvptx/mkoffload.c (process): Change offload data format.
+
 2015-09-30  Jeff Law  <law@redhat.com>
 
        * tree-ssa-dom.c (optimize_stmt): Collapse control flow statements

diff --git a/gcc/config/nvptx/mkoffload.c b/gcc/config/nvptx/mkoffload.c
index 99c0254e5865e9b4dda666eedf78ceb6ff713f3c..926c82beea9ec347a96e0a1d02bcd41f08a30ec0 100644 (file)
--- a/gcc/config/nvptx/mkoffload.c
+++ b/gcc/config/nvptx/mkoffload.c
@@ -843,39 +843,53 @@ process (FILE *in, FILE *out)
   Token *tok = tokenize (input);
   const char *comma;
   id_map const *id;
+  unsigned obj_count = 0;
+  unsigned ix;
 
   do
     tok = parse_file (tok);
   while (tok->kind);
 
-  fprintf (out, "static const char ptx_code[] = \n");
+  fprintf (out, "static const char ptx_code_%u[] = \n", obj_count++);
   write_stmts (out, rev_stmts (decls));
   write_stmts (out, rev_stmts (vars));
   write_stmts (out, rev_stmts (fns));
   fprintf (out, ";\n\n");
 
+  /* Dump out array of pointers to ptx object strings.  */
+  fprintf (out, "static const struct ptx_obj {\n"
+          "  const char *code;\n"
+          "  __SIZE_TYPE__ size;\n"
+          "} ptx_objs[] = {");
+  for (comma = "", ix = 0; ix != obj_count; comma = ",", ix++)
+    fprintf (out, "%s\n\t{ptx_code_%u, sizeof (ptx_code_%u)}", comma, ix, ix);
+  fprintf (out, "\n};\n\n");
+
+  /* Dump out variable idents.  */
   fprintf (out, "static const char *const var_mappings[] = {");
   for (comma = "", id = var_ids; id; comma = ",", id = id->next)
     fprintf (out, "%s\n\t%s", comma, id->ptx_name);
   fprintf (out, "\n};\n\n");
 
+  /* Dump out function idents.  */
   fprintf (out, "static const struct nvptx_fn {\n"
           "  const char *name;\n"
-          "  unsigned short dim[3];\n"
-          "} func_mappings[] = {\n");
+          "  unsigned short dim[%d];\n"
+          "} func_mappings[] = {\n", GOMP_DIM_MAX);
   for (comma = "", id = func_ids; id; comma = ",", id = id->next)
     fprintf (out, "%s\n\t{%s}", comma, id->ptx_name);
   fprintf (out, "\n};\n\n");
 
   fprintf (out,
           "static const struct nvptx_tdata {\n"
-          "  const char *ptx_src;\n"
+          "  const struct ptx_obj *ptx_objs;\n"
+          "  unsigned ptx_num;\n"
           "  const char *const *var_names;\n"
-          "  __SIZE_TYPE__ var_num;\n"
+          "  unsigned var_num;\n"
           "  const struct nvptx_fn *fn_names;\n"
-          "  __SIZE_TYPE__ fn_num;\n"
+          "  unsigned fn_num;\n"
           "} target_data = {\n"
-          "  ptx_code,\n"
+          "  ptx_objs, sizeof (ptx_objs) / sizeof (ptx_objs[0]),\n"
           "  var_mappings,"
           "  sizeof (var_mappings) / sizeof (var_mappings[0]),\n"
           "  func_mappings,"

diff --git a/libgomp/ChangeLog b/libgomp/ChangeLog
index fcf80e26e99441fa1f2c212cac74366b13e0614b..b38234b878884eacdb2688ce6297ec763cd012b0 100644 (file)
--- a/libgomp/ChangeLog
+++ b/libgomp/ChangeLog
@@ -1,3 +1,13 @@
+2015-09-30  Nathan Sidwell  <nathan@codesourcery.com>
+           Bernd Schmidt <bernds@codesourcery.com>
+
+       * plugin/plugin-nvptx.c (targ_fn_launch): Use GOMP_DIM_MAX.
+       (struct targ_ptx_obj): New.
+       (nvptx_tdata): Move earlier, change data format.
+       (link_ptx): Take targ_ptx_obj ptr and count.  Allow multiple
+       objects.
+       (GOMP_OFFLOAD_load_image): Adjust.
+
 2015-09-30  Thomas Schwinge  <thomas@codesourcery.com>
 
        * testsuite/libgomp.oacc-c-c++-common/abort-1.c: Add checkpoint.

diff --git a/libgomp/plugin/plugin-nvptx.c b/libgomp/plugin/plugin-nvptx.c
index 41fd9b454ebda1ad80e144ab6bd4d1d73aee11b0..cedcc592bf0ae0e9d247c40ea7288c97413592f7 100644 (file)
--- a/libgomp/plugin/plugin-nvptx.c
+++ b/libgomp/plugin/plugin-nvptx.c
@@ -224,9 +224,31 @@ map_push (struct ptx_stream *s, int async, size_t size, void **h, void **d)
 struct targ_fn_launch
 {
   const char *fn;
-  unsigned short dim[3];
+  unsigned short dim[GOMP_DIM_MAX];
 };
 
+/* Target PTX object information.  */
+
+struct targ_ptx_obj
+{
+  const char *code;
+  size_t size;
+};
+
+/* Target data image information.  */
+
+typedef struct nvptx_tdata
+{
+  const struct targ_ptx_obj *ptx_objs;
+  unsigned ptx_num;
+
+  const char *const *var_names;
+  unsigned var_num;
+
+  const struct targ_fn_launch *fn_descs;
+  unsigned fn_num;
+} nvptx_tdata_t;
+
 /* Descriptor of a loaded function.  */
 
 struct targ_fn_descriptor
@@ -688,7 +710,8 @@ nvptx_get_num_devices (void)
 
 
 static void
-link_ptx (CUmodule *module, const char *ptx_code)
+link_ptx (CUmodule *module, const struct targ_ptx_obj *ptx_objs,
+         unsigned num_objs)
 {
   CUjit_option opts[7];
   void *optvals[7];
@@ -702,8 +725,6 @@ link_ptx (CUmodule *module, const char *ptx_code)
   void *linkout;
   size_t linkoutsize __attribute__ ((unused));
 
-  GOMP_PLUGIN_debug (0, "attempting to load:\n---\n%s\n---\n", ptx_code);
-
   opts[0] = CU_JIT_WALL_TIME;
   optvals[0] = &elapsed;
 
@@ -758,25 +779,37 @@ link_ptx (CUmodule *module, const char *ptx_code)
                         cuda_error (r));
     }
 
-  /* cuLinkAddData's 'data' argument erroneously omits the const qualifier.  */
-  r = cuLinkAddData (linkstate, CU_JIT_INPUT_PTX, (char *)ptx_code,
-              strlen (ptx_code) + 1, 0, 0, 0, 0);
-  if (r != CUDA_SUCCESS)
+  for (; num_objs--; ptx_objs++)
     {
-      GOMP_PLUGIN_error ("Link error log %s\n", &elog[0]);
-      GOMP_PLUGIN_fatal ("cuLinkAddData (ptx_code) error: %s", cuda_error (r));
+      /* cuLinkAddData's 'data' argument erroneously omits the const
+        qualifier.  */
+      GOMP_PLUGIN_debug (0, "Loading:\n---\n%s\n---\n", ptx_objs->code);
+      r = cuLinkAddData (linkstate, CU_JIT_INPUT_PTX, (char*)ptx_objs->code,
+                        ptx_objs->size, 0, 0, 0, 0);
+      if (r != CUDA_SUCCESS)
+       {
+         GOMP_PLUGIN_error ("Link error log %s\n", &elog[0]);
+         GOMP_PLUGIN_fatal ("cuLinkAddData (ptx_code) error: %s",
+                            cuda_error (r));
+       }
     }
 
+  GOMP_PLUGIN_debug (0, "Linking\n");
   r = cuLinkComplete (linkstate, &linkout, &linkoutsize);
-  if (r != CUDA_SUCCESS)
-    GOMP_PLUGIN_fatal ("cuLinkComplete error: %s", cuda_error (r));
 
   GOMP_PLUGIN_debug (0, "Link complete: %fms\n", elapsed);
   GOMP_PLUGIN_debug (0, "Link log %s\n", &ilog[0]);
 
+  if (r != CUDA_SUCCESS)
+    GOMP_PLUGIN_fatal ("cuLinkComplete error: %s", cuda_error (r));
+
   r = cuModuleLoadData (module, linkout);
   if (r != CUDA_SUCCESS)
     GOMP_PLUGIN_fatal ("cuModuleLoadData error: %s", cuda_error (r));
+
+  r = cuLinkDestroy (linkstate);
+  if (r != CUDA_SUCCESS)
+    GOMP_PLUGIN_fatal ("cuLinkDestory error: %s", cuda_error (r));
 }
 
 static void
@@ -1502,19 +1535,6 @@ GOMP_OFFLOAD_fini_device (int n)
   pthread_mutex_unlock (&ptx_dev_lock);
 }
 
-/* Data emitted by mkoffload.  */
-
-typedef struct nvptx_tdata
-{
-  const char *ptx_src;
-
-  const char *const *var_names;
-  size_t var_num;
-
-  const struct targ_fn_launch *fn_descs;
-  size_t fn_num;
-} nvptx_tdata_t;
-
 /* Return the libgomp version number we're compatible with.  There is
    no requirement for cross-version compatibility.  */
 
@@ -1553,7 +1573,7 @@ GOMP_OFFLOAD_load_image (int ord, unsigned version, const void *target_data,
   
   nvptx_attach_host_thread_to_device (ord);
 
-  link_ptx (&module, img_header->ptx_src);
+  link_ptx (&module, img_header->ptx_objs, img_header->ptx_num);
 
   /* The mkoffload utility emits a struct of pointers/integers at the
      start of each offload image.  The array of kernel names and the