diff mbox

[gomp4] useless reduction locks and other bug fixes

Message ID 55E63353.9090501@mentor.com
State New
Headers show

Commit Message

Cesar Philippidis Sept. 1, 2015, 11:22 p.m. UTC 
[Attaching patch this time.]

On 09/01/2015 04:21 PM, Cesar Philippidis wrote:
> This patch teaches lower_oacc_reductions not to generate calls to
> GOACC_{UN}LOCK if they aren't any reductions. That situation can happen
> when there is a fake gang reduction on a private variable.
> 
> I also found a bug where the lower_rec_input_clauses expects there to be
> a data mapping for the reduction variable when there isn't, e.g. for
> private/local reduction variables. And I made the nvptx backend aware of
> the fact that the lhs of a call to REDUCTION_TEARDOWN may be have been
> optimized away for worker reductions too. I have a couple of test cases
> for these bugs, but I'll include them with my upcoming auto-independent
> loop patch.
> 
> This patch has been committed to gomp-4_0-branch.
> 
> Cesar
>
diff mbox

Patch

2015-09-01  Cesar Philippidis  <cesar@codesourcery.com>

	gcc/
	* config/nvptx/nvptx.c (nvptx_goacc_reduction_teardown): Allow
	lhs to be NULL for worker reductions too.
	* omp-low.c (lower_rec_input_clauses): Bail out on OpenACC reductions.
	(lower_oacc_reductions): Use maybe_lookup_decl for private reductions.
	Don't emit locks for fake private gang reductions.


diff --git a/gcc/config/nvptx/nvptx.c b/gcc/config/nvptx/nvptx.c
index 1b85892..51f2893 100644
--- a/gcc/config/nvptx/nvptx.c
+++ b/gcc/config/nvptx/nvptx.c
@@ -4229,14 +4229,19 @@  nvptx_goacc_reduction_teardown (gimple call)
   tree rid = gimple_call_arg (call, 5);
   gimple_seq seq = NULL;
 
+  if (v == NULL)
+    {
+      gsi_remove (&gsi, true);
+      return false;
+    }
+
   push_gimplify_context (true);
 
   switch (loop_dim)
     {
     case GOMP_DIM_GANG:
     case GOMP_DIM_VECTOR:
-      if (v)
-	gimplify_assign (v, local_var, &seq);
+      gimplify_assign (v, local_var, &seq);
       break;
     case GOMP_DIM_WORKER:
       {
diff --git a/gcc/omp-low.c b/gcc/omp-low.c
index fdca880..bfef298 100644
--- a/gcc/omp-low.c
+++ b/gcc/omp-low.c
@@ -3892,7 +3892,14 @@  lower_rec_input_clauses (tree clauses, gimple_seq *ilist, gimple_seq *dlist,
 
 	  new_var = var = OMP_CLAUSE_DECL (c);
 	  if (c_kind != OMP_CLAUSE_COPYIN)
-	    new_var = lookup_decl (var, ctx);
+	    {
+	      /* Not all OpenACC reductions require new mappings.  */
+	      if (is_gimple_omp_oacc (ctx->stmt)
+		  && (new_var = maybe_lookup_decl (var, ctx)) == NULL)
+		new_var = var;
+	      else
+		new_var = lookup_decl (var, ctx);
+	    }
 
 	  if (c_kind == OMP_CLAUSE_SHARED || c_kind == OMP_CLAUSE_COPYIN)
 	    {
@@ -4724,6 +4731,8 @@  lower_oacc_reductions (enum internal_fn ifn, int loop_dim, tree clauses,
   tree c, tcode, gwv, rid, lid = build_int_cst (integer_type_node, oacc_lid);
   int oacc_rid, i;
   unsigned mask = extract_oacc_loop_mask (ctx);
+  gimple_seq red_seq = NULL;
+  int num_reductions = 0;
   enum tree_code rcode;
 
   /* Remove the outer-most level of parallelism from the loop.  */
@@ -4753,14 +4762,6 @@  lower_oacc_reductions (enum internal_fn ifn, int loop_dim, tree clauses,
       gimplify_and_add (call, ilist);
     }
 
-  /* Call GOACC_LOCK.  */
-  if (ifn == IFN_GOACC_REDUCTION_FINI && write_back)
-    {
-      call = build_call_expr_internal_loc (UNKNOWN_LOCATION, IFN_GOACC_LOCK,
-					   void_type_node, 2, dim, lid);
-      gimplify_and_add (call, ilist);
-    }
-
   for (c = clauses, oacc_rid = 0;
        c && write_back;
        c = OMP_CLAUSE_CHAIN (c), oacc_rid++)
@@ -4776,7 +4777,9 @@  lower_oacc_reductions (enum internal_fn ifn, int loop_dim, tree clauses,
 
       var = OMP_CLAUSE_REDUCTION_PRIVATE_DECL (c);
       if (var == NULL_TREE)
-	var = lookup_decl (orig, ctx);
+	var = maybe_lookup_decl (orig, ctx);
+      if (var == NULL_TREE)
+	var = orig;
 
       res = build_outer_var_ref (orig, ctx);
 
@@ -4811,16 +4814,32 @@  lower_oacc_reductions (enum internal_fn ifn, int loop_dim, tree clauses,
       call = build_call_expr_internal_loc (UNKNOWN_LOCATION, ifn,
 					   TREE_TYPE (var), 6, ref_to_res,
 					   var, gwv, tcode, lid, rid);
-      gimplify_assign (var, call, ilist);
+      gimplify_assign (var, call, &red_seq);
+      num_reductions++;
     }
 
-  /* Call GOACC_UNLOCK.  */
-  if (ifn == IFN_GOACC_REDUCTION_FINI && write_back)
+  if (num_reductions)
     {
-      dim = build_int_cst (integer_type_node, loop_dim);
-      call = build_call_expr_internal_loc (UNKNOWN_LOCATION, IFN_GOACC_UNLOCK,
-					   void_type_node, 2, dim, lid);
-      gimplify_and_add (call, ilist);
+      /* Call GOACC_LOCK.  */
+      if (ifn == IFN_GOACC_REDUCTION_FINI && write_back)
+	{
+	  call = build_call_expr_internal_loc (UNKNOWN_LOCATION,
+					       IFN_GOACC_LOCK, void_type_node,
+					       2, dim, lid);
+	  gimplify_and_add (call, ilist);
+	}
+
+      gimple_seq_add_seq (ilist, red_seq);
+
+      /* Call GOACC_UNLOCK.  */
+      if (ifn == IFN_GOACC_REDUCTION_FINI && write_back)
+	{
+	  dim = build_int_cst (integer_type_node, loop_dim);
+	  call = build_call_expr_internal_loc (UNKNOWN_LOCATION,
+					       IFN_GOACC_UNLOCK,
+					       void_type_node, 2, dim, lid);
+	  gimplify_and_add (call, ilist);
+	}
     }
 }