Reference reduction localization

gcc/ChangeLog
	* gimplify.cc (privatize_reduction): New struct.
	(localize_reductions_r, localize_reductions): New functions.
	(gimplify_omp_for): Call localize_reductions.
	(gimplify_omp_workshare): Likewise.
	* omp-low.cc (lower_oacc_reductions): Handle localized reductions.
	Create fewer temp vars.
	* tree-core.h (omp_clause_code): Add OMP_CLAUSE_REDUCTION_PRIVATE_DECL
	documentation.
	* tree.cc (omp_clause_num_ops): Bump number of ops for
	OMP_CLAUSE_REDUCTION to 6.
	(walk_tree_1): Adjust accordingly.
	* tree.h (OMP_CLAUSE_REDUCTION_PRIVATE_DECL): Add macro.

gcc/testsuite/ChangeLog
	* gfortran.dg/goacc/modules.f95: Remove xfail on bogus warnings.

libgomp/ChangeLog
	* testsuite/libgomp.oacc-fortran/optional-reduction.f90: Remove
	xfail on bogus warnings.
	* testsuite/libgomp.oacc-fortran/parallel-reduction.f90: Likewise.
	* testsuite/libgomp.oacc-fortran/pr70643.f90: Likewise.
	* testsuite/libgomp.oacc-fortran/reduction-5.f90: Likewise.
	* testsuite/libgomp.oacc-fortran/reduction-7.f90: Likewise.
	* testsuite/libgomp.oacc-fortran/reference-reductions.f90: Likewise.

Co-Authored-By: Julian Brown <julian@codesourcery.com>
Co-Authored-By: Sandra Loosemore <sloosemore@baylibre.com>

6 files changed, 121 insertions, 37 deletions

diff --git a/gcc/gimplify.cc b/gcc/gimplify.cc
index 8afa993..2a351b0 100644
--- a/gcc/gimplify.cc
+++ b/gcc/gimplify.cc
@@ -295,6 +295,11 @@ struct gimplify_omp_ctx
   int defaultmap[5];
 };
 
+struct privatize_reduction
+{
+  tree ref_var, local_var;
+};
+
 static struct gimplify_ctx *gimplify_ctxp;
 static struct gimplify_omp_ctx *gimplify_omp_ctxp;
 static bool in_omp_construct;
@@ -16167,6 +16172,80 @@ gimplify_omp_loop_xform (tree *expr_p, gimple_seq *pre_p)
   return GS_ALL_DONE;
 }
 
+/* Helper function for localize_reductions.  Replace all uses of REF_VAR with
+   LOCAL_VAR.  */
+
+static tree
+localize_reductions_r (tree *tp, int *walk_subtrees, void *data)
+{
+  enum tree_code tc = TREE_CODE (*tp);
+  struct privatize_reduction *pr = (struct privatize_reduction *) data;
+
+  if (TYPE_P (*tp))
+    *walk_subtrees = 0;
+
+  switch (tc)
+    {
+    case INDIRECT_REF:
+    case MEM_REF:
+      if (TREE_OPERAND (*tp, 0) == pr->ref_var)
+	*tp = pr->local_var;
+
+      *walk_subtrees = 0;
+      break;
+
+    case VAR_DECL:
+    case PARM_DECL:
+    case RESULT_DECL:
+      if (*tp == pr->ref_var)
+	*tp = pr->local_var;
+
+      *walk_subtrees = 0;
+      break;
+
+    default:
+      break;
+    }
+
+  return NULL_TREE;
+}
+
+/* OpenACC worker and vector loop state propagation requires reductions
+   to be inside local variables.  This function replaces all reference-type
+   reductions variables associated with the loop with a local copy.  It is
+   also used to create private copies of reduction variables for those
+   which are not associated with acc loops.  */
+
+static void
+localize_reductions (tree clauses, tree body)
+{
+  tree c, var, type, new_var;
+  struct privatize_reduction pr;
+
+  for (c = clauses; c; c = OMP_CLAUSE_CHAIN (c))
+    if (OMP_CLAUSE_CODE (c) == OMP_CLAUSE_REDUCTION)
+      {
+	var = OMP_CLAUSE_DECL (c);
+
+	if (!lang_hooks.decls.omp_privatize_by_reference (var))
+	  {
+	    OMP_CLAUSE_REDUCTION_PRIVATE_DECL (c) = NULL;
+	    continue;
+	  }
+
+	type = TREE_TYPE (TREE_TYPE (var));
+	new_var = create_tmp_var (type, IDENTIFIER_POINTER (DECL_NAME (var)));
+
+	pr.ref_var = var;
+	pr.local_var = new_var;
+
+	walk_tree (&body, localize_reductions_r, &pr, NULL);
+
+	OMP_CLAUSE_REDUCTION_PRIVATE_DECL (c) = new_var;
+      }
+}
+
+
 /* Gimplify the gross structure of an OMP_FOR statement.  */
 
 static enum gimplify_status
@@ -16426,6 +16505,24 @@ gimplify_omp_for (tree *expr_p, gimple_seq *pre_p)
       gcc_unreachable ();
     }
 
+  if (ort == ORT_ACC)
+    {
+      gimplify_omp_ctx *outer = gimplify_omp_ctxp;
+
+      while (outer
+	     && outer->region_type != ORT_ACC_PARALLEL
+	     && outer->region_type != ORT_ACC_KERNELS)
+	outer = outer->outer_context;
+
+      /* FIXME: Reductions only work in parallel regions at present.  We avoid
+	 doing the reduction localization transformation in kernels regions
+	 here, because the code to remove reductions in kernels regions cannot
+	 handle that.  */
+      if (outer && outer->region_type == ORT_ACC_PARALLEL)
+	localize_reductions (OMP_FOR_CLAUSES (for_stmt),
+			     OMP_FOR_BODY (for_stmt));
+    }
+
   /* Set OMP_CLAUSE_LINEAR_NO_COPYIN flag on explicit linear
      clause for the IV.  */
   if (ort == ORT_SIMD && TREE_VEC_LENGTH (OMP_FOR_INIT (for_stmt)) == 1)
@@ -18038,6 +18135,11 @@ gimplify_omp_workshare (tree *expr_p, gimple_seq *pre_p)
       || (ort & ORT_HOST_TEAMS) == ORT_HOST_TEAMS)
     {
       push_gimplify_context ();
+
+      /* FIXME: Reductions are not supported in kernels regions yet.  */
+      if (/*ort == ORT_ACC_KERNELS ||*/ ort == ORT_ACC_PARALLEL)
+	localize_reductions (OMP_CLAUSES (expr), OMP_BODY (expr));
+
       gimple *g = gimplify_and_return_first (OMP_BODY (expr), &body);
       if (gimple_code (g) == GIMPLE_BIND)
 	pop_gimplify_context (g);
diff --git a/gcc/omp-low.cc b/gcc/omp-low.cc
index 387517c..0188251 100644
--- a/gcc/omp-low.cc
+++ b/gcc/omp-low.cc
@@ -7658,9 +7658,9 @@ lower_oacc_reductions (location_t loc, tree clauses, tree level, bool inner,
 	gcc_checking_assert (!is_oacc_kernels_decomposed_part (ctx));
 
 	tree orig = OMP_CLAUSE_DECL (c);
-	tree var = maybe_lookup_decl (orig, ctx);
+	tree var;
 	tree ref_to_res = NULL_TREE;
-	tree incoming, outgoing, v1, v2, v3;
+	tree incoming, outgoing;
 	bool is_private = false;
 	bool is_fpp = false;
 
@@ -7673,6 +7673,9 @@ lower_oacc_reductions (location_t loc, tree clauses, tree level, bool inner,
 	  rcode = BIT_IOR_EXPR;
 	tree op = build_int_cst (unsigned_type_node, rcode);
 
+	var = OMP_CLAUSE_REDUCTION_PRIVATE_DECL (c);
+	if (!var)
+	  var = maybe_lookup_decl (orig, ctx);
 	if (!var)
 	  var = orig;
 
@@ -7781,37 +7784,13 @@ lower_oacc_reductions (location_t loc, tree clauses, tree level, bool inner,
 	if (!ref_to_res)
 	  ref_to_res = integer_zero_node;
 
-	if (omp_privatize_by_reference (orig))
+	if (omp_privatize_by_reference (outgoing))
 	  {
-	    tree type = TREE_TYPE (var);
-	    const char *id = IDENTIFIER_POINTER (DECL_NAME (var));
-
-	    if (!inner)
-	      {
-		tree x = create_tmp_var (TREE_TYPE (type), id);
-		gimplify_assign (var, build_fold_addr_expr (x), fork_seq);
-	      }
-
-	    v1 = create_tmp_var (type, id);
-	    v2 = create_tmp_var (type, id);
-	    v3 = create_tmp_var (type, id);
-
-	    gimplify_assign (v1, var, fork_seq);
-	    gimplify_assign (v2, var, fork_seq);
-	    gimplify_assign (v3, var, fork_seq);
-
-	    var = build_simple_mem_ref (var);
-	    v1 = build_simple_mem_ref (v1);
-	    v2 = build_simple_mem_ref (v2);
-	    v3 = build_simple_mem_ref (v3);
 	    outgoing = build_simple_mem_ref (outgoing);
 
 	    if (!TREE_CONSTANT (incoming))
 	      incoming = build_simple_mem_ref (incoming);
 	  }
-	else
-	  /* Note that 'var' might be a mem ref.  */
-	  v1 = v2 = v3 = var;
 
 	/* Determine position in reduction buffer, which may be used
 	   by target.  The parser has ensured that this is not a
@@ -7845,21 +7824,21 @@ lower_oacc_reductions (location_t loc, tree clauses, tree level, bool inner,
 	  = build_call_expr_internal_loc (loc, IFN_GOACC_REDUCTION,
 					  TREE_TYPE (var), 6, init_code,
 					  unshare_expr (ref_to_res),
-					  unshare_expr (v1), level, op, off);
+					  unshare_expr (var), level, op, off);
 	tree fini_call
 	  = build_call_expr_internal_loc (loc, IFN_GOACC_REDUCTION,
 					  TREE_TYPE (var), 6, fini_code,
 					  unshare_expr (ref_to_res),
-					  unshare_expr (v2), level, op, off);
+					  unshare_expr (var), level, op, off);
 	tree teardown_call
 	  = build_call_expr_internal_loc (loc, IFN_GOACC_REDUCTION,
 					  TREE_TYPE (var), 6, teardown_code,
-					  ref_to_res, unshare_expr (v3),
+					  ref_to_res, unshare_expr (var),
 					  level, op, off);
 
-	gimplify_assign (unshare_expr (v1), setup_call, &before_fork);
-	gimplify_assign (unshare_expr (v2), init_call, &after_fork);
-	gimplify_assign (unshare_expr (v3), fini_call, &before_join);
+	gimplify_assign (unshare_expr (var), setup_call, &before_fork);
+	gimplify_assign (unshare_expr (var), init_call, &after_fork);
+	gimplify_assign (unshare_expr (var), fini_call, &before_join);
 	gimplify_assign (unshare_expr (outgoing), teardown_call, &after_join);
       }
 
diff --git a/gcc/testsuite/gfortran.dg/goacc/modules.f95 b/gcc/testsuite/gfortran.dg/goacc/modules.f95
index 1e8d826..42e715e 100644
--- a/gcc/testsuite/gfortran.dg/goacc/modules.f95
+++ b/gcc/testsuite/gfortran.dg/goacc/modules.f95
@@ -18,8 +18,7 @@ SUBROUTINE reduction_kernel(x_min,x_max,y_min,y_max,arr,sum)
 
 !$ACC DATA PRESENT(arr) COPY(sum)
 !$ACC PARALLEL LOOP REDUCTION(+ : sum)
-  ! { dg-bogus {'sum\.[0-9]+' is used uninitialized} TODO { xfail *-*-* } .-1 }
-  !   { dg-note {'sum\.[0-9]+' was declared here} {} { target *-*-* } .-2 }
+  ! { dg-bogus {'sum\.[0-9]+' is used uninitialized} "" { target *-*-* } .-1 }
   DO k=y_min,y_max
     DO j=x_min,x_max
       sum=sum*arr(j,k)
diff --git a/gcc/tree-core.h b/gcc/tree-core.h
index bd19c99..2389441 100644
--- a/gcc/tree-core.h
+++ b/gcc/tree-core.h
@@ -278,7 +278,9 @@ enum omp_clause_code {
                 placeholder used in OMP_CLAUSE_REDUCTION_{INIT,MERGE}.
      Operand 4: OMP_CLAUSE_REDUCTION_DECL_PLACEHOLDER: Another dummy
 		VAR_DECL placeholder, used like the above for C/C++ array
-		reductions.  */
+		reductions.
+     Operand 5: OMP_CLAUSE_REDUCTION_PRIVATE_DECL: A private VAR_DECL of
+		the original DECL associated with the reduction clause.  */
   OMP_CLAUSE_REDUCTION,
 
   /* OpenMP clause: task_reduction (operator:variable_list).  */
diff --git a/gcc/tree.cc b/gcc/tree.cc
index eccfcc8..3e71d8d 100644
--- a/gcc/tree.cc
+++ b/gcc/tree.cc
@@ -301,7 +301,7 @@ unsigned const char omp_clause_num_ops[] =
   1, /* OMP_CLAUSE_SHARED  */
   1, /* OMP_CLAUSE_FIRSTPRIVATE  */
   2, /* OMP_CLAUSE_LASTPRIVATE  */
-  5, /* OMP_CLAUSE_REDUCTION  */
+  6, /* OMP_CLAUSE_REDUCTION  */
   5, /* OMP_CLAUSE_TASK_REDUCTION  */
   5, /* OMP_CLAUSE_IN_REDUCTION  */
   1, /* OMP_CLAUSE_COPYIN  */
diff --git a/gcc/tree.h b/gcc/tree.h
index 99f2617..7f528f5 100644
--- a/gcc/tree.h
+++ b/gcc/tree.h
@@ -1962,6 +1962,8 @@ class auto_suppress_location_wrappers
 #define OMP_CLAUSE_REDUCTION_DECL_PLACEHOLDER(NODE) \
   OMP_CLAUSE_OPERAND (OMP_CLAUSE_RANGE_CHECK (NODE, OMP_CLAUSE_REDUCTION, \
 					      OMP_CLAUSE_IN_REDUCTION), 4)
+#define OMP_CLAUSE_REDUCTION_PRIVATE_DECL(NODE) \
+  OMP_CLAUSE_OPERAND (OMP_CLAUSE_SUBCODE_CHECK (NODE, OMP_CLAUSE_REDUCTION), 5)
 
 /* True if a REDUCTION clause may reference the original list item (omp_orig)
    in its OMP_CLAUSE_REDUCTION_{,GIMPLE_}INIT.  */