Hi Tom! On Mon, 12 Oct 2015 18:56:29 +0200, Tom de Vries <[email protected]> wrote: > Handle original loop tree in expand_omp_for_generic > > 2015-09-12 Tom de Vries <[email protected]> > > PR tree-optimization/67476 > * omp-low.c (expand_omp_for_generic): Handle original loop tree.
Working on a merge from trunk into gomp-4_0-branch, I'm seeing your
change (trunk r228754) conflict with code Chung-Lin changed
(gomp-4_0-branch r224505). So, would you two please cherry-pick/merge
trunk r228754 into gomp-4_0-branch? Thanks! (I'm assuming you can
easily tell what needs to be done here; it's been a long time that
Chung-Lin touched this code, so CCing him just in case.) Thanks!
Chung-Lin's gomp-4_0-branch r224505:
commit 5f9849b7f0723d06fcd18a18e0880d4df75da92a
Author: cltang <cltang@138bc75d-0d04-0410-961f-82ee72b054a4>
Date: Tue Jun 16 08:59:01 2015 +0000
2015-06-16 Chung-Lin Tang <[email protected]>
* omp-low.c (struct omp_region): Add inside_kernels_p field.
(expand_omp_for_generic): Adjust to generate a 'sequential' loop
when GOMP builtin arguments are BUILT_IN_NONE.
(expand_omp_for): Use expand_omp_for_generic() to generate a
non-parallelized loop for OMP_FORs inside OpenACC kernels regions.
(expand_omp): Mark inside_kernels_p field true for regions
nested inside OpenACC kernels constructs.
git-svn-id: svn+ssh://gcc.gnu.org/svn/gcc/branches/gomp-4_0-branch@224505
138bc75d-0d04-0410-961f-82ee72b054a4
diff --git gcc/ChangeLog.gomp gcc/ChangeLog.gomp
index be09b0f..6fa08da 100644
--- gcc/ChangeLog.gomp
+++ gcc/ChangeLog.gomp
@@ -1,3 +1,13 @@
+2015-06-16 Chung-Lin Tang <[email protected]>
+
+ * omp-low.c (struct omp_region): Add inside_kernels_p field.
+ (expand_omp_for_generic): Adjust to generate a 'sequential' loop
+ when GOMP builtin arguments are BUILT_IN_NONE.
+ (expand_omp_for): Use expand_omp_for_generic() to generate a
+ non-parallelized loop for OMP_FORs inside OpenACC kernels regions.
+ (expand_omp): Mark inside_kernels_p field true for regions
+ nested inside OpenACC kernels constructs.
+
2015-06-15 Cesar Philippidis <[email protected]>
* omp-low.c (expand_omp_for_static_nochunk): Update entry_bb after
diff --git gcc/omp-low.c gcc/omp-low.c
index c7451c9..a3dab12 100644
--- gcc/omp-low.c
+++ gcc/omp-low.c
@@ -161,6 +161,9 @@ struct omp_region
/* True if this is a combined parallel+workshare region. */
bool is_combined_parallel;
+ /* True if this is nested inside an OpenACC kernels construct. */
+ bool inside_kernels_p;
+
/* For an OpenACC loop, the level of parallelism requested. */
int gwv_this;
@@ -6862,6 +6865,7 @@ expand_omp_for_generic (struct omp_region *region,
gassign *assign_stmt;
bool in_combined_parallel = is_combined_parallel (region);
bool broken_loop = region->cont == NULL;
+ bool seq_loop = (!start_fn || !next_fn);
edge e, ne;
tree *counts = NULL;
int i;
@@ -6949,7 +6953,20 @@ expand_omp_for_generic (struct omp_region *region,
zero_iter_bb));
}
}
- if (in_combined_parallel)
+ if (seq_loop)
+ {
+ tree n1 = fold_convert (fd->iter_type, fd->loop.n1);
+ tree n2 = fold_convert (fd->iter_type, fd->loop.n2);
+
+ assign_stmt = gimple_build_assign (istart0, n1);
+ gsi_insert_before (&gsi, assign_stmt, GSI_SAME_STMT);
+
+ assign_stmt = gimple_build_assign (iend0, n2);
+ gsi_insert_before (&gsi, assign_stmt, GSI_SAME_STMT);
+
+ t = fold_build2 (NE_EXPR, boolean_type_node, istart0, iend0);
+ }
+ else if (in_combined_parallel)
{
/* In a combined parallel loop, emit a call to
GOMP_loop_foo_next. */
@@ -7135,32 +7152,38 @@ expand_omp_for_generic (struct omp_region *region,
collapse_bb = extract_omp_for_update_vars (fd, cont_bb, l1_bb);
/* Emit code to get the next parallel iteration in L2_BB. */
- gsi = gsi_start_bb (l2_bb);
+ if (!seq_loop)
+ {
+ gsi = gsi_start_bb (l2_bb);
- t = build_call_expr (builtin_decl_explicit (next_fn), 2,
- build_fold_addr_expr (istart0),
- build_fold_addr_expr (iend0));
- t = force_gimple_operand_gsi (&gsi, t, true, NULL_TREE,
- false, GSI_CONTINUE_LINKING);
- if (TREE_TYPE (t) != boolean_type_node)
- t = fold_build2 (NE_EXPR, boolean_type_node,
- t, build_int_cst (TREE_TYPE (t), 0));
- gcond *cond_stmt = gimple_build_cond_empty (t);
- gsi_insert_after (&gsi, cond_stmt, GSI_CONTINUE_LINKING);
+ t = build_call_expr (builtin_decl_explicit (next_fn), 2,
+ build_fold_addr_expr (istart0),
+ build_fold_addr_expr (iend0));
+ t = force_gimple_operand_gsi (&gsi, t, true, NULL_TREE,
+ false, GSI_CONTINUE_LINKING);
+ if (TREE_TYPE (t) != boolean_type_node)
+ t = fold_build2 (NE_EXPR, boolean_type_node,
+ t, build_int_cst (TREE_TYPE (t), 0));
+ gcond *cond_stmt = gimple_build_cond_empty (t);
+ gsi_insert_after (&gsi, cond_stmt, GSI_CONTINUE_LINKING);
+ }
}
/* Add the loop cleanup function. */
gsi = gsi_last_bb (exit_bb);
- if (gimple_omp_return_nowait_p (gsi_stmt (gsi)))
- t = builtin_decl_explicit (BUILT_IN_GOMP_LOOP_END_NOWAIT);
- else if (gimple_omp_return_lhs (gsi_stmt (gsi)))
- t = builtin_decl_explicit (BUILT_IN_GOMP_LOOP_END_CANCEL);
- else
- t = builtin_decl_explicit (BUILT_IN_GOMP_LOOP_END);
- gcall *call_stmt = gimple_build_call (t, 0);
- if (gimple_omp_return_lhs (gsi_stmt (gsi)))
- gimple_call_set_lhs (call_stmt, gimple_omp_return_lhs (gsi_stmt (gsi)));
- gsi_insert_after (&gsi, call_stmt, GSI_SAME_STMT);
+ if (!seq_loop)
+ {
+ if (gimple_omp_return_nowait_p (gsi_stmt (gsi)))
+ t = builtin_decl_explicit (BUILT_IN_GOMP_LOOP_END_NOWAIT);
+ else if (gimple_omp_return_lhs (gsi_stmt (gsi)))
+ t = builtin_decl_explicit (BUILT_IN_GOMP_LOOP_END_CANCEL);
+ else
+ t = builtin_decl_explicit (BUILT_IN_GOMP_LOOP_END);
+ gcall *call_stmt = gimple_build_call (t, 0);
+ if (gimple_omp_return_lhs (gsi_stmt (gsi)))
+ gimple_call_set_lhs (call_stmt, gimple_omp_return_lhs (gsi_stmt (gsi)));
+ gsi_insert_after (&gsi, call_stmt, GSI_SAME_STMT);
+ }
gsi_remove (&gsi, true);
/* Connect the new blocks. */
@@ -7172,7 +7195,7 @@ expand_omp_for_generic (struct omp_region *region,
gimple_seq phis;
e = find_edge (cont_bb, l3_bb);
- ne = make_edge (l2_bb, l3_bb, EDGE_FALSE_VALUE);
+ ne = make_edge (l2_bb, l3_bb, seq_loop ? EDGE_FALLTHRU :
EDGE_FALSE_VALUE);
phis = phi_nodes (l3_bb);
for (gsi = gsi_start (phis); !gsi_end_p (gsi); gsi_next (&gsi))
@@ -7208,7 +7231,8 @@ expand_omp_for_generic (struct omp_region *region,
e = find_edge (cont_bb, l2_bb);
e->flags = EDGE_FALLTHRU;
}
- make_edge (l2_bb, l0_bb, EDGE_TRUE_VALUE);
+ if (!seq_loop)
+ make_edge (l2_bb, l0_bb, EDGE_TRUE_VALUE);
set_immediate_dominator (CDI_DOMINATORS, l2_bb,
recompute_dominator (CDI_DOMINATORS, l2_bb));
@@ -7219,10 +7243,16 @@ expand_omp_for_generic (struct omp_region *region,
set_immediate_dominator (CDI_DOMINATORS, l1_bb,
recompute_dominator (CDI_DOMINATORS, l1_bb));
- struct loop *outer_loop = alloc_loop ();
- outer_loop->header = l0_bb;
- outer_loop->latch = l2_bb;
- add_loop (outer_loop, l0_bb->loop_father);
+ struct loop *outer_loop;
+ if (seq_loop)
+ outer_loop = l0_bb->loop_father;
+ else
+ {
+ outer_loop = alloc_loop ();
+ outer_loop->header = l0_bb;
+ outer_loop->latch = l2_bb;
+ add_loop (outer_loop, l0_bb->loop_father);
+ }
if (!gimple_omp_for_combined_p (fd->for_stmt))
{
@@ -8704,7 +8734,10 @@ expand_omp_for (struct omp_region *region, gimple
inner_stmt)
original loops from being detected. Fix that up. */
loops_state_set (LOOPS_NEED_FIXUP);
- if (gimple_omp_for_kind (fd.for_stmt) & GF_OMP_FOR_SIMD)
+ if (region->inside_kernels_p)
+ expand_omp_for_generic (region, &fd, BUILT_IN_NONE, BUILT_IN_NONE,
+ inner_stmt);
+ else if (gimple_omp_for_kind (fd.for_stmt) & GF_OMP_FOR_SIMD)
expand_omp_simd (region, &fd);
else if (gimple_omp_for_kind (fd.for_stmt) == GF_OMP_FOR_KIND_CILKFOR)
expand_cilk_for (region, &fd);
@@ -10296,6 +10329,14 @@ expand_omp (struct omp_region *region)
if (region->type == GIMPLE_OMP_PARALLEL)
determine_parallel_type (region);
+ if (region->type == GIMPLE_OMP_TARGET && region->inner)
+ {
+ gomp_target *entry = as_a <gomp_target *> (last_stmt (region->entry));
+ if (region->inside_kernels_p
+ || gimple_omp_target_kind (entry) ==
GF_OMP_TARGET_KIND_OACC_KERNELS)
+ region->inner->inside_kernels_p = true;
+ }
+
if (region->type == GIMPLE_OMP_FOR
&& gimple_omp_for_combined_p (last_stmt (region->entry)))
inner_stmt = last_stmt (region->inner->entry);
Tom's trunk r228754:
commit 1c6a437bd44020c37452b7fb4f565f7e7f94d56b
Author: vries <vries@138bc75d-0d04-0410-961f-82ee72b054a4>
Date: Tue Oct 13 10:08:40 2015 +0000
Handle original loop tree in expand_omp_for_generic
2015-10-13 Tom de Vries <[email protected]>
PR tree-optimization/67476
* omp-low.c (expand_omp_for_generic): Handle original loop tree.
git-svn-id: svn+ssh://gcc.gnu.org/svn/gcc/trunk@228754
138bc75d-0d04-0410-961f-82ee72b054a4
diff --git gcc/ChangeLog gcc/ChangeLog
index e5ede0b..4632387 100644
--- gcc/ChangeLog
+++ gcc/ChangeLog
@@ -1,3 +1,8 @@
+2015-10-13 Tom de Vries <[email protected]>
+
+ PR tree-optimization/67476
+ * omp-low.c (expand_omp_for_generic): Handle original loop tree.
+
2015-10-13 Richard Biener <[email protected]>
* tree-vect-data-refs.c (vect_analyze_data_ref_dependences): Allocate
diff --git gcc/omp-low.c gcc/omp-low.c
index b2a93b9..7e894e4 100644
--- gcc/omp-low.c
+++ gcc/omp-low.c
@@ -6439,7 +6439,6 @@ expand_omp_for_generic (struct omp_region *region,
remove_edge (e);
make_edge (cont_bb, l2_bb, EDGE_FALSE_VALUE);
- add_bb_to_loop (l2_bb, cont_bb->loop_father);
e = find_edge (cont_bb, l1_bb);
if (e == NULL)
{
@@ -6516,17 +6515,30 @@ expand_omp_for_generic (struct omp_region *region,
set_immediate_dominator (CDI_DOMINATORS, l1_bb,
recompute_dominator (CDI_DOMINATORS, l1_bb));
- struct loop *outer_loop = alloc_loop ();
- outer_loop->header = l0_bb;
- outer_loop->latch = l2_bb;
- add_loop (outer_loop, l0_bb->loop_father);
+ /* We enter expand_omp_for_generic with a loop. This original loop may
+ have its own loop struct, or it may be part of an outer loop struct
+ (which may be the fake loop). */
+ struct loop *outer_loop = entry_bb->loop_father;
+ bool orig_loop_has_loop_struct = l1_bb->loop_father != outer_loop;
- if (!gimple_omp_for_combined_p (fd->for_stmt))
+ add_bb_to_loop (l2_bb, outer_loop);
+
+ /* We've added a new loop around the original loop. Allocate the
+ corresponding loop struct. */
+ struct loop *new_loop = alloc_loop ();
+ new_loop->header = l0_bb;
+ new_loop->latch = l2_bb;
+ add_loop (new_loop, outer_loop);
+
+ /* Allocate a loop structure for the original loop unless we already
+ had one. */
+ if (!orig_loop_has_loop_struct
+ && !gimple_omp_for_combined_p (fd->for_stmt))
{
- struct loop *loop = alloc_loop ();
- loop->header = l1_bb;
+ struct loop *orig_loop = alloc_loop ();
+ orig_loop->header = l1_bb;
/* The loop may have multiple latches. */
- add_loop (loop, outer_loop);
+ add_loop (orig_loop, new_loop);
}
}
}
The merge conflict looks as follows:
set_immediate_dominator (CDI_DOMINATORS, l1_bb,
recompute_dominator (CDI_DOMINATORS, l1_bb));
<<<<<<< HEAD
struct loop *outer_loop;
if (seq_loop)
outer_loop = l0_bb->loop_father;
else
{
outer_loop = alloc_loop ();
outer_loop->header = l0_bb;
outer_loop->latch = l2_bb;
add_loop (outer_loop, l0_bb->loop_father);
}
=======
/* We enter expand_omp_for_generic with a loop. This original loop may
have its own loop struct, or it may be part of an outer loop struct
(which may be the fake loop). */
struct loop *outer_loop = entry_bb->loop_father;
bool orig_loop_has_loop_struct = l1_bb->loop_father != outer_loop;
>>>>>>> e2c514f0507fb1864c4eed5d691e47156be57b5b
add_bb_to_loop (l2_bb, outer_loop);
/* We've added a new loop around the original loop. Allocate the
corresponding loop struct. */
struct loop *new_loop = alloc_loop ();
new_loop->header = l0_bb;
new_loop->latch = l2_bb;
add_loop (new_loop, outer_loop);
/* Allocate a loop structure for the original loop unless we already
had one. */
if (!orig_loop_has_loop_struct
&& !gimple_omp_for_combined_p (fd->for_stmt))
{
struct loop *orig_loop = alloc_loop ();
orig_loop->header = l1_bb;
/* The loop may have multiple latches. */
add_loop (orig_loop, new_loop);
}
}
}
Grüße,
Thomas
signature.asc
Description: PGP signature
