#include "expr.h"
#include "params.h"
#include "toplev.h"
+#include "tree-pass.h"
+
+#ifndef HAVE_conditional_execution
+#define HAVE_conditional_execution 0
+#endif
/* The number of rounds. In most cases there will only be 4 rounds, but
when partitioning hot and cold basic blocks into separate sections of
{
basic_block new_bb;
- new_bb = duplicate_block (old_bb, e);
+ new_bb = duplicate_block (old_bb, e, bb);
BB_COPY_PARTITION (new_bb, old_bb);
gcc_assert (e->dest == new_bb);
else
count_threshold = max_entry_count / 1000 * DUPLICATION_THRESHOLD;
- connected = xcalloc (n_traces, sizeof (bool));
+ connected = XCNEWVEC (bool, n_traces);
last_trace = -1;
current_pass = 1;
current_partition = BB_PARTITION (traces[0].first);
return false;
if (code_may_grow && maybe_hot_bb_p (bb))
- max_size *= 8;
+ max_size *= PARAM_VALUE (PARAM_MAX_GROW_COPY_BB_INSNS);
FOR_BB_INSNS (bb, insn)
{
if (INSN_P (insn))
- size += get_attr_length (insn);
+ size += get_attr_min_length (insn);
}
if (size <= max_size)
label = emit_label_before (gen_label_rtx (), get_insns ());
jump = emit_jump_insn (gen_jump (label));
- length = get_attr_length (jump);
+ length = get_attr_min_length (jump);
delete_insn (jump);
delete_insn (label);
for (cur_insn = indirect_jump_sequence; cur_insn;
cur_insn = NEXT_INSN (cur_insn))
{
- BLOCK_FOR_INSN (cur_insn) = cur_bb;
+ if (!BARRIER_P (cur_insn))
+ BLOCK_FOR_INSN (cur_insn) = cur_bb;
if (JUMP_P (cur_insn))
jump_insn = cur_insn;
}
{
if (switched_sections)
{
- error ("Multiple hot/cold transitions found (bb %i)",
+ error ("multiple hot/cold transitions found (bb %i)",
bb->index);
err = 1;
}
int i;
struct trace *traces;
- if (n_basic_blocks <= 1)
+ if (n_basic_blocks <= NUM_FIXED_BLOCKS + 1)
return;
if (targetm.cannot_modify_jumps_p ())
return;
- timevar_push (TV_REORDER_BLOCKS);
-
cfg_layout_initialize (flags);
set_edge_can_fallthru_flag ();
/* We need to know some information for each basic block. */
array_size = GET_ARRAY_SIZE (last_basic_block);
- bbd = xmalloc (array_size * sizeof (bbro_basic_block_data));
+ bbd = XNEWVEC (bbro_basic_block_data, array_size);
for (i = 0; i < array_size; i++)
{
bbd[i].start_of_trace = -1;
bbd[i].node = NULL;
}
- traces = xmalloc (n_basic_blocks * sizeof (struct trace));
+ traces = XNEWVEC (struct trace, n_basic_blocks);
n_traces = 0;
find_traces (&n_traces, traces);
connect_traces (n_traces, traces);
FREE (bbd);
if (dump_file)
- dump_flow_info (dump_file);
+ dump_flow_info (dump_file, dump_flags);
cfg_layout_finalize ();
if (flag_reorder_blocks_and_partition)
verify_hot_cold_block_grouping ();
-
- timevar_pop (TV_REORDER_BLOCKS);
}
/* Determine which partition the first basic block in the function
encountering this note will make the compiler switch between the
hot and cold text sections. */
-void
+static void
insert_section_boundary_note (void)
{
basic_block bb;
which can seriously pessimize code with many computed jumps in the source
code, such as interpreters. See e.g. PR15242. */
-void
+static bool
+gate_duplicate_computed_gotos (void)
+{
+ return (optimize > 0 && flag_expensive_optimizations && !optimize_size);
+}
+
+
+static unsigned int
duplicate_computed_gotos (void)
{
basic_block bb, new_bb;
bitmap candidates;
int max_size;
- if (n_basic_blocks <= 1)
- return;
+ if (n_basic_blocks <= NUM_FIXED_BLOCKS + 1)
+ return 0;
if (targetm.cannot_modify_jumps_p ())
- return;
-
- timevar_push (TV_REORDER_BLOCKS);
+ return 0;
cfg_layout_initialize (0);
FOR_BB_INSNS (bb, insn)
if (INSN_P (insn))
{
- size += get_attr_length (insn);
+ size += get_attr_min_length (insn);
if (size > max_size)
break;
}
if (!bitmap_bit_p (candidates, single_succ (bb)->index))
continue;
- new_bb = duplicate_block (single_succ (bb), single_succ_edge (bb));
+ new_bb = duplicate_block (single_succ (bb), single_succ_edge (bb), bb);
new_bb->aux = bb->aux;
bb->aux = new_bb;
new_bb->il.rtl->visited = 1;
cfg_layout_finalize ();
BITMAP_FREE (candidates);
-
- timevar_pop (TV_REORDER_BLOCKS);
+ return 0;
}
+struct tree_opt_pass pass_duplicate_computed_gotos =
+{
+ "compgotos", /* name */
+ gate_duplicate_computed_gotos, /* gate */
+ duplicate_computed_gotos, /* execute */
+ NULL, /* sub */
+ NULL, /* next */
+ 0, /* static_pass_number */
+ TV_REORDER_BLOCKS, /* tv_id */
+ 0, /* properties_required */
+ 0, /* properties_provided */
+ 0, /* properties_destroyed */
+ 0, /* todo_flags_start */
+ TODO_dump_func, /* todo_flags_finish */
+ 0 /* letter */
+};
+
+
/* This function is the main 'entrance' for the optimization that
partitions hot and cold basic blocks into separate sections of the
.o file (to improve performance and cache locality). Ideally it
(through registers) requires that this optimization be performed
before register allocation. */
-void
+static void
partition_hot_cold_basic_blocks (void)
{
basic_block cur_bb;
int n_crossing_edges;
int max_edges = 2 * last_basic_block;
- if (n_basic_blocks <= 1)
+ if (n_basic_blocks <= NUM_FIXED_BLOCKS + 1)
return;
- crossing_edges = xcalloc (max_edges, sizeof (edge));
+ crossing_edges = XCNEWVEC (edge, max_edges);
cfg_layout_initialize (0);
FOR_EACH_BB (cur_bb)
- if (cur_bb->index >= 0
- && cur_bb->next_bb->index >= 0)
+ if (cur_bb->index >= NUM_FIXED_BLOCKS
+ && cur_bb->next_bb->index >= NUM_FIXED_BLOCKS)
cur_bb->aux = cur_bb->next_bb;
find_rarely_executed_basic_blocks_and_crossing_edges (crossing_edges,
cfg_layout_finalize();
}
+\f
+static bool
+gate_handle_reorder_blocks (void)
+{
+ return (optimize > 0);
+}
+
+
+/* Reorder basic blocks. */
+static unsigned int
+rest_of_handle_reorder_blocks (void)
+{
+ bool changed;
+ unsigned int liveness_flags;
+
+ /* Last attempt to optimize CFG, as scheduling, peepholing and insn
+ splitting possibly introduced more crossjumping opportunities. */
+ liveness_flags = (!HAVE_conditional_execution ? CLEANUP_UPDATE_LIFE : 0);
+ changed = cleanup_cfg (CLEANUP_EXPENSIVE | liveness_flags);
+
+ if (flag_sched2_use_traces && flag_schedule_insns_after_reload)
+ {
+ timevar_push (TV_TRACER);
+ tracer (liveness_flags);
+ timevar_pop (TV_TRACER);
+ }
+
+ if (flag_reorder_blocks || flag_reorder_blocks_and_partition)
+ reorder_basic_blocks (liveness_flags);
+ if (flag_reorder_blocks || flag_reorder_blocks_and_partition
+ || (flag_sched2_use_traces && flag_schedule_insns_after_reload))
+ changed |= cleanup_cfg (CLEANUP_EXPENSIVE | liveness_flags);
+
+ /* On conditional execution targets we can not update the life cheaply, so
+ we deffer the updating to after both cleanups. This may lose some cases
+ but should not be terribly bad. */
+ if (changed && HAVE_conditional_execution)
+ update_life_info (NULL, UPDATE_LIFE_GLOBAL_RM_NOTES,
+ PROP_DEATH_NOTES);
+
+ /* Add NOTE_INSN_SWITCH_TEXT_SECTIONS notes. */
+ insert_section_boundary_note ();
+ return 0;
+}
+
+struct tree_opt_pass pass_reorder_blocks =
+{
+ "bbro", /* name */
+ gate_handle_reorder_blocks, /* gate */
+ rest_of_handle_reorder_blocks, /* execute */
+ NULL, /* sub */
+ NULL, /* next */
+ 0, /* static_pass_number */
+ TV_REORDER_BLOCKS, /* tv_id */
+ 0, /* properties_required */
+ 0, /* properties_provided */
+ 0, /* properties_destroyed */
+ 0, /* todo_flags_start */
+ TODO_dump_func, /* todo_flags_finish */
+ 'B' /* letter */
+};
+
+static bool
+gate_handle_partition_blocks (void)
+{
+ /* The optimization to partition hot/cold basic blocks into separate
+ sections of the .o file does not work well with linkonce or with
+ user defined section attributes. Don't call it if either case
+ arises. */
+
+ return (flag_reorder_blocks_and_partition
+ && !DECL_ONE_ONLY (current_function_decl)
+ && !user_defined_section_attribute);
+}
+
+/* Partition hot and cold basic blocks. */
+static unsigned int
+rest_of_handle_partition_blocks (void)
+{
+ no_new_pseudos = 0;
+ partition_hot_cold_basic_blocks ();
+ allocate_reg_life_data ();
+ update_life_info (NULL, UPDATE_LIFE_GLOBAL_RM_NOTES,
+ PROP_LOG_LINKS | PROP_REG_INFO | PROP_DEATH_NOTES);
+ no_new_pseudos = 1;
+ return 0;
+}
+
+struct tree_opt_pass pass_partition_blocks =
+{
+ "bbpart", /* name */
+ gate_handle_partition_blocks, /* gate */
+ rest_of_handle_partition_blocks, /* execute */
+ NULL, /* sub */
+ NULL, /* next */
+ 0, /* static_pass_number */
+ TV_REORDER_BLOCKS, /* tv_id */
+ 0, /* properties_required */
+ 0, /* properties_provided */
+ 0, /* properties_destroyed */
+ 0, /* todo_flags_start */
+ TODO_dump_func, /* todo_flags_finish */
+ 0 /* letter */
+};
+
+