Handle double reduction in parloops
2015-07-28 Tom de Vries <tom@codesourcery.com>
backport from trunk:
2015-07-28 Tom de Vries <tom@codesourcery.com>
* tree-parloops.c (reduc_stmt_res): New function.
(initialize_reductions, add_field_for_reduction)
(create_phi_for_local_result, create_loads_for_reductions)
(create_stores_for_reduction, build_new_reduction): Handle case that
reduc_stmt is a phi.
(gather_scalar_reductions): Allow double_reduc reductions.
* gcc.dg/autopar/uns-outer-4.c: Remove xfail on scan for parallelizing
outer loop.
* testsuite/libgomp.c/uns-outer-4.c: New test.
---
gcc/testsuite/gcc.dg/autopar/uns-outer-4.c | 6 +--
gcc/tree-parloops.c | 73 ++++++++++++++++++++++++++----
libgomp/testsuite/libgomp.c/uns-outer-4.c | 36 +++++++++++++++
3 files changed, 102 insertions(+), 13 deletions(-)
create mode 100644 libgomp/testsuite/libgomp.c/uns-outer-4.c
@@ -12,9 +12,7 @@ parloop (int N)
int i, j;
unsigned int sum;
- /* Double reduction is currently not supported, outer loop is not
- parallelized. Inner reduction is detected, inner loop is
- parallelized. */
+ /* Double reduction is detected, outer loop is parallelized. */
sum = 0;
for (i = 0; i < N; i++)
for (j = 0; j < N; j++)
@@ -23,5 +21,5 @@ parloop (int N)
g_sum = sum;
}
-/* { dg-final { scan-tree-dump-times "parallelizing outer loop" 1 "parloops" { xfail *-*-* } } } */
+/* { dg-final { scan-tree-dump-times "parallelizing outer loop" 1 "parloops" } } */
/* { dg-final { scan-tree-dump-times "loopfn" 4 "optimized" } } */
@@ -550,6 +550,14 @@ take_address_of (tree obj, tree type, edge entry,
return name;
}
+static tree
+reduc_stmt_res (gimple stmt)
+{
+ return (gimple_code (stmt) == GIMPLE_PHI
+ ? gimple_phi_result (stmt)
+ : gimple_assign_lhs (stmt));
+}
+
/* Callback for htab_traverse. Create the initialization statement
for reduction described in SLOT, and place it at the preheader of
the loop described in DATA. */
@@ -576,7 +584,7 @@ initialize_reductions (reduction_info **slot, struct loop *loop)
c = build_omp_clause (gimple_location (reduc->reduc_stmt),
OMP_CLAUSE_REDUCTION);
OMP_CLAUSE_REDUCTION_CODE (c) = reduc->reduction_code;
- OMP_CLAUSE_DECL (c) = SSA_NAME_VAR (gimple_assign_lhs (reduc->reduc_stmt));
+ OMP_CLAUSE_DECL (c) = SSA_NAME_VAR (reduc_stmt_res (reduc->reduc_stmt));
init = omp_reduction_init (c, TREE_TYPE (bvar));
reduc->init = init;
@@ -983,7 +991,7 @@ add_field_for_reduction (reduction_info **slot, tree type)
{
struct reduction_info *const red = *slot;
- tree var = gimple_assign_lhs (red->reduc_stmt);
+ tree var = reduc_stmt_res (red->reduc_stmt);
tree field = build_decl (gimple_location (red->reduc_stmt), FIELD_DECL,
SSA_NAME_IDENTIFIER (var), TREE_TYPE (var));
@@ -1043,12 +1051,12 @@ create_phi_for_local_result (reduction_info **slot, struct loop *loop)
e = EDGE_PRED (store_bb, 1);
else
e = EDGE_PRED (store_bb, 0);
- local_res = copy_ssa_name (gimple_assign_lhs (reduc->reduc_stmt));
+ tree lhs = reduc_stmt_res (reduc->reduc_stmt);
+ local_res = copy_ssa_name (lhs);
locus = gimple_location (reduc->reduc_stmt);
new_phi = create_phi_node (local_res, store_bb);
add_phi_arg (new_phi, reduc->init, e, locus);
- add_phi_arg (new_phi, gimple_assign_lhs (reduc->reduc_stmt),
- FALLTHRU_EDGE (loop->latch), locus);
+ add_phi_arg (new_phi, lhs, FALLTHRU_EDGE (loop->latch), locus);
reduc->new_phi = new_phi;
return 1;
@@ -1161,7 +1169,7 @@ create_loads_for_reductions (reduction_info **slot, struct clsn_data *clsn_data)
struct reduction_info *const red = *slot;
gimple stmt;
gimple_stmt_iterator gsi;
- tree type = TREE_TYPE (gimple_assign_lhs (red->reduc_stmt));
+ tree type = TREE_TYPE (reduc_stmt_res (red->reduc_stmt));
tree load_struct;
tree name;
tree x;
@@ -1226,7 +1234,7 @@ create_stores_for_reduction (reduction_info **slot, struct clsn_data *clsn_data)
tree t;
gimple stmt;
gimple_stmt_iterator gsi;
- tree type = TREE_TYPE (gimple_assign_lhs (red->reduc_stmt));
+ tree type = TREE_TYPE (reduc_stmt_res (red->reduc_stmt));
gsi = gsi_last_bb (clsn_data->store_bb);
t = build3 (COMPONENT_REF, type, clsn_data->store, red->field, NULL_TREE);
@@ -2473,6 +2481,7 @@ build_new_reduction (reduction_info_table_type *reduction_list,
{
reduction_info **slot;
struct reduction_info *new_reduction;
+ enum tree_code reduction_code;
gcc_assert (reduc_stmt);
@@ -2484,12 +2493,22 @@ build_new_reduction (reduction_info_table_type *reduction_list,
fprintf (dump_file, "\n");
}
+ if (gimple_code (reduc_stmt) == GIMPLE_PHI)
+ {
+ tree op1 = PHI_ARG_DEF (reduc_stmt, 0);
+ gimple def1 = SSA_NAME_DEF_STMT (op1);
+ reduction_code = gimple_assign_rhs_code (def1);
+ }
+
+ else
+ reduction_code = gimple_assign_rhs_code (reduc_stmt);
+
new_reduction = XCNEW (struct reduction_info);
new_reduction->reduc_stmt = reduc_stmt;
new_reduction->reduc_phi = phi;
new_reduction->reduc_version = SSA_NAME_VERSION (gimple_phi_result (phi));
- new_reduction->reduction_code = gimple_assign_rhs_code (reduc_stmt);
+ new_reduction->reduction_code = reduction_code;
slot = reduction_list->find_slot (new_reduction, INSERT);
*slot = new_reduction;
}
@@ -2511,6 +2530,8 @@ gather_scalar_reductions (loop_p loop, reduction_info_table_type *reduction_list
{
gphi_iterator gsi;
loop_vec_info simple_loop_info;
+ loop_vec_info simple_inner_loop_info = NULL;
+ bool allow_double_reduc = true;
simple_loop_info = vect_analyze_loop_form (loop);
if (simple_loop_info == NULL)
@@ -2532,12 +2553,46 @@ gather_scalar_reductions (loop_p loop, reduction_info_table_type *reduction_list
gimple reduc_stmt
= vect_force_simple_reduction (simple_loop_info, phi, true,
&double_reduc, true);
- if (!reduc_stmt || double_reduc)
+ if (!reduc_stmt)
continue;
+ if (double_reduc)
+ {
+ if (!allow_double_reduc
+ || loop->inner->inner != NULL)
+ continue;
+
+ if (!simple_inner_loop_info)
+ {
+ simple_inner_loop_info = vect_analyze_loop_form (loop->inner);
+ if (!simple_inner_loop_info)
+ {
+ allow_double_reduc = false;
+ continue;
+ }
+ }
+
+ use_operand_p use_p;
+ gimple inner_stmt;
+ bool single_use_p = single_imm_use (res, &use_p, &inner_stmt);
+ gcc_assert (single_use_p);
+ gphi *inner_phi = as_a <gphi *> (inner_stmt);
+ if (simple_iv (loop->inner, loop->inner, PHI_RESULT (inner_phi),
+ &iv, true))
+ continue;
+
+ gimple inner_reduc_stmt
+ = vect_force_simple_reduction (simple_inner_loop_info, inner_phi,
+ true, &double_reduc, true);
+ gcc_assert (!double_reduc);
+ if (inner_reduc_stmt == NULL)
+ continue;
+ }
+
build_new_reduction (reduction_list, reduc_stmt, phi);
}
destroy_loop_vec_info (simple_loop_info, true);
+ destroy_loop_vec_info (simple_inner_loop_info, true);
/* As gimple_uid is used by the vectorizer in between vect_analyze_loop_form
and destroy_loop_vec_info, we can set gimple_uid of reduc_phi stmts
new file mode 100644
@@ -0,0 +1,36 @@
+/* { dg-do run } */
+/* { dg-additional-options "-ftree-parallelize-loops=2" } */
+
+void abort (void);
+
+unsigned int g_sum = 1;
+
+unsigned int x[500][500];
+
+void __attribute__((noinline,noclone))
+parloop (int N)
+{
+ int i, j;
+ unsigned int sum;
+
+ /* Double reduction is detected, outer loop is parallelized. */
+ sum = 0;
+ for (i = 0; i < N; i++)
+ for (j = 0; j < N; j++)
+ sum += x[i][j];
+
+ g_sum = sum;
+}
+
+int
+main (void)
+{
+ x[234][432] = 2;
+
+ parloop (500);
+
+ if (g_sum != 2)
+ abort ();
+
+ return 0;
+}
--
1.9.1