Re: [OpenACC 3/11] new target hook

[Nathan Sidwell <nathan at acm dot org>]

This patch implements a new OpenACC target hook.  It is used during 
device-specific lowering and allows a backend to indicate whether it needs to 
know about a fork/join for a particular axis.

For instance, in PTX we don't care about gang-level fork and join.  We also 
don't care if the size of that dimension is 1.

The default implementation of the hook never only cares if the oacc_fork and 
oacc_join RTL  expanders exist (and they don't on the host compiler).

nathan

2015-10-20  Nathan Sidwell  <nathan@codesourcery.com>

	* target.def (fork_join): New GOACC hook.
	* targhooks.h (default_goacc_fork_join): Declare.
	* omp-low.c (default_goacc_forkjoin): New.
	* doc/tm.texi.in (TARGET_GOACC_FORK_JOIN): Add.
	* doc/tm.texi: Regenerate.
	* config/nvptx/nvptx.c (nvptx_xform_fork_join): New.
	(TARGET_GOACC_FOR_JOIN): Override.

Index: config/nvptx/nvptx.c
===================================================================
--- config/nvptx/nvptx.c	(revision 229096)
+++ config/nvptx/nvptx.c	(working copy)
@@ -2146,7 +2146,26 @@ nvptx_goacc_validate_dims (tree ARG_UNUS
 
   return changed;
 }
-
+
+/* Determine whether fork & joins are needed.  */
+
+static bool
+nvptx_xform_fork_join (gcall *call, const int dims[],
+		       bool ARG_UNUSED (is_fork))
+{
+  tree arg = gimple_call_arg (call, 1);
+  unsigned axis = TREE_INT_CST_LOW (arg);
+
+  /* We only care about worker and vector partitioning.  */
+  if (axis < GOMP_DIM_WORKER)
+    return true;
+
+  /* If the size is 1, there's no partitioning.  */
+  if (dims[axis] == 1)
+    return true;
+
+  return false;
+}
 #undef TARGET_OPTION_OVERRIDE
 #define TARGET_OPTION_OVERRIDE nvptx_option_override
 
@@ -2236,6 +2255,9 @@ nvptx_goacc_validate_dims (tree ARG_UNUS
 #undef TARGET_GOACC_VALIDATE_DIMS
 #define TARGET_GOACC_VALIDATE_DIMS nvptx_goacc_validate_dims
 
+#undef TARGET_GOACC_FORK_JOIN
+#define TARGET_GOACC_FORK_JOIN nvptx_xform_fork_join
+
 struct gcc_target targetm = TARGET_INITIALIZER;
 
 #include "gt-nvptx.h"
Index: doc/tm.texi
===================================================================
--- doc/tm.texi	(revision 229096)
+++ doc/tm.texi	(working copy)
@@ -5748,7 +5748,7 @@ usable.  In that case, the smaller the n
 to use it.
 @end deftypefn
 
-@deftypefn {Target Hook} bool TARGET_GOACC_VALIDATE_DIMS (tree @var{decl}, int @var{dims[]}, int @var{fn_level})
+@deftypefn {Target Hook} bool TARGET_GOACC_VALIDATE_DIMS (tree @var{decl}, int *@var{dims}, int @var{fn_level})
 This hook should check the launch dimensions provided for an OpenACC
 compute region, or routine.  Defaulted values are represented as -1
 and non-constant values as 0. The @var{fn_level} is negative for the
@@ -5760,6 +5760,13 @@ true, if changes have been made.  You mu
 provide dimensions larger than 1.
 @end deftypefn
 
+@deftypefn {Target Hook} bool TARGET_GOACC_FORK_JOIN (gcall *@var{call}, const int *@var{dims}, bool @var{is_fork})
+This hook should convert IFN_GOACC_FORK and IFN_GOACC_JOIN function
+calls to target-specific gimple.  It is executed during the oacc_xform
+pass.  It should return true, if the functions should be deleted.  The
+default hook returns true, if there are no RTL expanders for them.
+@end deftypefn
+
 @node Anchored Addresses
 @section Anchored Addresses
 @cindex anchored addresses
Index: doc/tm.texi.in
===================================================================
--- doc/tm.texi.in	(revision 229096)
+++ doc/tm.texi.in	(working copy)
@@ -4249,6 +4249,8 @@ address;  but often a machine-dependent
 
 @hook TARGET_GOACC_VALIDATE_DIMS
 
+@hook TARGET_GOACC_FORK_JOIN
+
 @node Anchored Addresses
 @section Anchored Addresses
 @cindex anchored addresses
Index: omp-low.c
===================================================================
--- omp-low.c	(revision 229096)
+++ omp-low.c	(working copy)
@@ -17532,6 +17532,29 @@ oacc_validate_dims (tree fn, tree attrs,
   return fn_level;
 }
 
+/* Default fork/join early expander.  Delete the function calls if
+   there is no RTL expander.  */
+
+bool
+default_goacc_fork_join (gcall *ARG_UNUSED (call),
+			 const int *ARG_UNUSED (dims), bool is_fork)
+{
+  if (is_fork)
+    {
+#ifndef HAVE_oacc_fork
+      return true;
+#endif
+    }
+  else
+    {
+#ifndef HAVE_oacc_join
+      return true;
+#endif
+    }
+
+  return false;
+}
+
 /* Main entry point for oacc transformations which run on the device
    compiler after LTO, so we know what the target device is at this
    point (including the host fallback).  */
Index: target.def
===================================================================
--- target.def	(revision 229096)
+++ target.def	(working copy)
@@ -1655,9 +1655,19 @@ should fill in anything that needs to de
 non-defaults.  Diagnostics should be issued as appropriate.  Return\n\
 true, if changes have been made.  You must override this hook to\n\
 provide dimensions larger than 1.",
-bool, (tree decl, int dims[], int fn_level),
+bool, (tree decl, int *dims, int fn_level),
 default_goacc_validate_dims)
 
+DEFHOOK
+(fork_join,
+"This hook should convert IFN_UNIQUE calls for IFN_UNIQUE_GOACC_FORK\n\
+and IFN_UNIQUE_GOACC_JOIN   to target-specific gimple.  It is executed\n\
+during the oacc_device_lower pass.  It should return true, if the\n\
+functions should be deleted.  The default hook returns true, if there\n\
+are no RTL expanders for these actions.", 
+bool, (gcall *call, const int *dims, bool is_fork),
+default_goacc_fork_join)
+
 HOOK_VECTOR_END (goacc)
 
 /* Functions relating to vectorization.  */
Index: targhooks.h
===================================================================
--- targhooks.h	(revision 229096)
+++ targhooks.h	(working copy)
@@ -109,6 +109,7 @@ extern void default_destroy_cost_data (v
 
 /* OpenACC hooks.  */
 extern bool default_goacc_validate_dims (tree, int [], int);
+extern bool default_goacc_fork_join (gcall *, const int [], bool);
 
 /* These are here, and not in hooks.[ch], because not all users of
    hooks.h include tm.h, and thus we don't have CUMULATIVE_ARGS.  */