nvptx.opt (moptimize): New flag.

	* config/nvptx/nvptx.opt (moptimize): New flag.
	* config/nvptx/nvptx.c (nvptx_option_override): Set nvptx_optimize
	default.
	(nvptx_optimize_inner): New.
	(nvptx_process_pars): Call it when optimizing.
	* doc/invoke.texi (Nvidia PTX Options): Document -moptimize.

From-SVN: r230137

gcc/ChangeLog

+2015-11-10  Nathan Sidwell  <nathan@codesourcery.com>
+
+	* config/nvptx/nvptx.opt (moptimize): New flag.
+	* config/nvptx/nvptx.c (nvptx_option_override): Set nvptx_optimize
+	default.
+	(nvptx_optimize_inner): New.
+	(nvptx_process_pars): Call it when optimizing.
+	* doc/invoke.texi (Nvidia PTX Options): Document -moptimize.
+
 2015-11-10  Bill Schmidt  <wschmidt@linux.vnet.ibm.com>
 
 	* config/rs6000/rs6000.c (rs6000_secondary_reload_direct_move):

gcc/config/nvptx/nvptx.c

@@ -137,6 +137,9 @@ nvptx_option_override (void)
   write_symbols = NO_DEBUG;
   debug_info_level = DINFO_LEVEL_NONE;
 
+  if (nvptx_optimize < 0)
+    nvptx_optimize = optimize > 0;
+
   declared_fndecls_htab = hash_table<tree_hasher>::create_ggc (17);
   needed_fndecls_htab = hash_table<tree_hasher>::create_ggc (17);
   declared_libfuncs_htab
@@ -2942,6 +2945,69 @@ nvptx_skip_par (unsigned mask, parallel *par)
   nvptx_single (mask, par->forked_block, pre_tail);
 }
 
+/* If PAR has a single inner parallel and PAR itself only contains
+   empty entry and exit blocks, swallow the inner PAR.  */
+
+static void
+nvptx_optimize_inner (parallel *par)
+{
+  parallel *inner = par->inner;
+
+  /* We mustn't be the outer dummy par.  */
+  if (!par->mask)
+    return;
+
+  /* We must have a single inner par.  */
+  if (!inner || inner->next)
+    return;
+
+  /* We must only contain 2 blocks ourselves -- the head and tail of
+     the inner par.  */
+  if (par->blocks.length () != 2)
+    return;
+
+  /* We must be disjoint partitioning.  As we only have vector and
+     worker partitioning, this is sufficient to guarantee the pars
+     have adjacent partitioning.  */
+  if ((par->mask & inner->mask) & (GOMP_DIM_MASK (GOMP_DIM_MAX) - 1))
+    /* This indicates malformed code generation.  */
+    return;
+
+  /* The outer forked insn should be immediately followed by the inner
+     fork insn.  */
+  rtx_insn *forked = par->forked_insn;
+  rtx_insn *fork = BB_END (par->forked_block);
+
+  if (NEXT_INSN (forked) != fork)
+    return;
+  gcc_checking_assert (recog_memoized (fork) == CODE_FOR_nvptx_fork);
+
+  /* The outer joining insn must immediately follow the inner join
+     insn.  */
+  rtx_insn *joining = par->joining_insn;
+  rtx_insn *join = inner->join_insn;
+  if (NEXT_INSN (join) != joining)
+    return;
+
+  /* Preconditions met.  Swallow the inner par.  */
+  if (dump_file)
+    fprintf (dump_file, "Merging loop %x [%d,%d] into %x [%d,%d]\n",
+	     inner->mask, inner->forked_block->index,
+	     inner->join_block->index,
+	     par->mask, par->forked_block->index, par->join_block->index);
+
+  par->mask |= inner->mask & (GOMP_DIM_MASK (GOMP_DIM_MAX) - 1);
+
+  par->blocks.reserve (inner->blocks.length ());
+  while (inner->blocks.length ())
+    par->blocks.quick_push (inner->blocks.pop ());
+
+  par->inner = inner->inner;
+  inner->inner = NULL;
+
+  delete inner;
+}
+
 /* Process the parallel PAR and all its contained
    parallels.  We do everything but the neutering.  Return mask of
    partitioned modes used within this parallel.  */
@@ -2949,6 +3015,9 @@ nvptx_skip_par (unsigned mask, parallel *par)
 static unsigned
 nvptx_process_pars (parallel *par)
 {
+  if (nvptx_optimize)
+    nvptx_optimize_inner (par);
+  
   unsigned inner_mask = par->mask;
 
   /* Do the inner parallels first.  */

gcc/config/nvptx/nvptx.opt

@@ -28,3 +28,7 @@ Generate code for a 64-bit ABI.
 mmainkernel
 Target Report RejectNegative
 Link in code for a __main kernel.
+
+moptimize
+Target Report Var(nvptx_optimize) Init(-1)
+Optimize partition neutering

gcc/doc/invoke.texi

@@ -873,7 +873,7 @@ Objective-C and Objective-C++ Dialects}.
 -march=@var{arch} -mbmx -mno-bmx -mcdx -mno-cdx}
 
 @emph{Nvidia PTX Options}
-@gccoptlist{-m32 -m64 -mmainkernel}
+@gccoptlist{-m32 -m64 -mmainkernel -moptimize}
 
 @emph{PDP-11 Options}
 @gccoptlist{-mfpu  -msoft-float  -mac0  -mno-ac0  -m40  -m45  -m10 @gol
@@ -18960,6 +18960,11 @@ Generate code for 32-bit or 64-bit ABI.
 Link in code for a __main kernel.  This is for stand-alone instead of
 offloading execution.
 
+@item -moptimize
+@opindex moptimize
+Apply partitioned execution optimizations.  This is the default when any
+level of optimization is selected.
+
 @end table
 
 @node PDP-11 Options

gcc/testsuite/ChangeLog

+2015-11-10  Nathan Sidwell  <nathan@codesourcery.com>
+
+	* gcc.dg/goacc/nvptx-opt-1.c: New test.
+
 2015-11-10  Ilya Enkovich  <enkovich.gnu@gmail.com>
 
 	* gcc.target/i386/mask-pack.c: New test.