diff options
author | Jan Hubicka <hubicka@ucw.cz> | 2017-06-04 20:55:08 +0200 |
---|---|---|
committer | Jan Hubicka <hubicka@gcc.gnu.org> | 2017-06-04 18:55:08 +0000 |
commit | 3995f3a2207fbde0c31341d79bf49563d681ca9a (patch) | |
tree | 51458cb1039eb15cb224e5b7de48d9e17703b737 /gcc/ipa-inline.c | |
parent | a7e8f816bd09adc24013b5fd3a43128778f6581b (diff) | |
download | gcc-3995f3a2207fbde0c31341d79bf49563d681ca9a.zip gcc-3995f3a2207fbde0c31341d79bf49563d681ca9a.tar.gz gcc-3995f3a2207fbde0c31341d79bf49563d681ca9a.tar.bz2 |
i386.c (make_resolver_func): Update.
2017-05-23 Jan Hubicka <hubicka@ucw.cz>
* config/i386/i386.c (make_resolver_func): Update.
* Makefile.in: Add profile-count.h and profile-count.o
* auto-profile.c (afdo_indirect_call): Update to new API.
(afdo_set_bb_count): Update.
(afdo_propagate_edge): Update.
(afdo_propagate_circuit): Update.
(afdo_calculate_branch_prob): Update.
(afdo_annotate_cfg): Update.
* basic-block.h: Include profile-count.h
(struct edge_def): Turn count to profile_count.
(struct basic_block_def): Likewie.
(REG_BR_PROB_BASE): Move to profile-count.h
(RDIV): Move to profile-count.h
* bb-reorder.c (max_entry_count): Turn to profile_count.
(find_traces): Update.
(rotate_loop):Update.
(connect_traces):Update.
(sanitize_hot_paths):Update.
* bt-load.c (migrate_btr_defs): Update.
* cfg.c (RDIV): Remove.
(init_flow): Use alloc_block.
(alloc_block): Uninitialize count.
(unchecked_make_edge): Uninitialize count.
(check_bb_profile): Update.
(dump_edge_info): Update.
(dump_bb_info): Update.
(update_bb_profile_for_threading): Update.
(scale_bbs_frequencies_int): Update.
(scale_bbs_frequencies_gcov_type): Update.
(scale_bbs_frequencies_profile_count): New.
* cfg.h (update_bb_profile_for_threading): Update.
(scale_bbs_frequencies_profile_count): Declare.
* cfgbuild.c (compute_outgoing_frequencies): Update.
(find_many_sub_basic_blocks): Update.
* cfgcleanup.c (try_forward_edges): Update.
(try_crossjump_to_edge): Update.
* cfgexpand.c (expand_gimple_tailcall): Update.
(construct_exit_block): Update.
* cfghooks.c (verify_flow_info): Update.
(dump_bb_for_graph): Update.
(split_edge): Update.
(make_forwarder_block): Update.
(duplicate_block): Update.
(account_profile_record): Update.
* cfgloop.c (find_subloop_latch_edge_by_profile): Update.
(get_estimated_loop_iterations): Update.
* cfgloopanal.c (expected_loop_iterations_unbounded): Update.
(single_likely_exit): Update.
* cfgloopmanip.c (scale_loop_profile): Update.
(loopify): Update.
(set_zero_probability): Update.
(lv_adjust_loop_entry_edge): Update.
* cfgrtl.c (force_nonfallthru_and_redirect): Update.
(purge_dead_edges): Update.
(rtl_account_profile_record): Update.
* cgraph.c (cgraph_node::create): Uninitialize count.
(symbol_table::create_edge): Uninitialize count.
(cgraph_update_edges_for_call_stmt_node): Update.
(cgraph_edge::dump_edge_flags): Update.
(cgraph_node::dump): Update.
(cgraph_edge::maybe_hot_p): Update.
* cgraph.h: Include profile-count.h
(create_clone), create_edge, create_indirect_edge): Update.
(cgraph_node): Turn count to profile_count.
(cgraph_edge0: Likewise.
(make_speculative, clone): Update.
(create_edge): Update.
(init_lowered_empty_function): Update.
* cgraphclones.c (cgraph_edge::clone): Update.
(duplicate_thunk_for_node): Update.
(cgraph_node::create_clone): Update.
* cgraphunit.c (cgraph_node::analyze): Update.
(cgraph_node::expand_thunk): Update.
* final.c (dump_basic_block_info): Update.
* gimple-streamer-in.c (input_bb): Update.
* gimple-streamer-out.c (output_bb): Update.
* graphite.c (print_global_statistics): Update.
(print_graphite_scop_statistics): Update.
* hsa-brig.c: Include basic-block.h.
* hsa-dump.c: Include basic-block.h.
* hsa-gen.c (T sum_slice): Update.
(convert_switch_statements):Update.
* hsa-regalloc.c: Include basic-block.h.
* ipa-chkp.c (chkp_produce_thunks): Update.
* ipa-cp.c (struct caller_statistics): Update.
(init_caller_stats): Update.
(gather_caller_stats): Update.
(ipcp_cloning_candidate_p): Update.
(good_cloning_opportunity_p): Update.
(get_info_about_necessary_edges): Update.
(dump_profile_updates): Update.
(update_profiling_info): Update.
(update_specialized_profile): Update.
(perhaps_add_new_callers): Update.
(decide_about_value): Update.
(ipa_cp_c_finalize): Update.
* ipa-devirt.c (struct odr_type_warn_count): Update.
(struct decl_warn_count): Update.
(struct final_warning_record): Update.
(possible_polymorphic_call_targets): Update.
(ipa_devirt): Update.
* ipa-fnsummary.c (redirect_to_unreachable): Update.
* ipa-icf.c (sem_function::merge): Update.
* ipa-inline-analysis.c (do_estimate_edge_time): Update.
* ipa-inline.c (compute_uninlined_call_time): Update.
(compute_inlined_call_time): Update.
(want_inline_small_function_p): Update.
(want_inline_self_recursive_call_p): Update.
(edge_badness): Update.
(lookup_recursive_calls): Update.
(recursive_inlining): Update.
(inline_small_functions): Update.
(dump_overall_stats): Update.
(dump_inline_stats): Update.
* ipa-profile.c (ipa_profile_generate_summary): Update.
(ipa_propagate_frequency): Update.
(ipa_profile): Update.
* ipa-prop.c (ipa_make_edge_direct_to_target): Update.
* ipa-utils.c (ipa_merge_profiles): Update.
* loop-doloop.c (doloop_modify): Update.
* loop-unroll.c (report_unroll): Update.
(unroll_loop_runtime_iterations): Update.
* lto-cgraph.c (lto_output_edge): Update.
(lto_output_node): Update.
(input_node): Update.
(input_edge): Update.
(merge_profile_summaries): Update.
* lto-streamer-in.c (input_cfg): Update.
* lto-streamer-out.c (output_cfg): Update.
* mcf.c (create_fixup_graph): Update.
(adjust_cfg_counts): Update.
(sum_edge_counts): Update.
* modulo-sched.c (sms_schedule): Update.
* postreload-gcse.c (eliminate_partially_redundant_load): Update.
* predict.c (maybe_hot_count_p): Update.
(probably_never_executed): Update.
(dump_prediction): Update.
(combine_predictions_for_bb): Update.
(propagate_freq): Update.
(handle_missing_profiles): Update.
(counts_to_freqs): Update.
(rebuild_frequencies): Update.
(force_edge_cold): Update.
* predict.h: Include profile-count.h
(maybe_hot_count_p, counts_to_freqs): UPdate.
* print-rtl-function.c: Do not include cfg.h
* print-rtl.c: Include basic-block.h
* profile-count.c: New file.
* profile-count.h: New file.
* profile.c (is_edge_inconsistent): Update.
(correct_negative_edge_counts): Update.
(is_inconsistent): Update.
(set_bb_counts): Update.
(read_profile_edge_counts): Update.
(compute_frequency_overlap): Update.
(compute_branch_probabilities): Update; Initialize and deinitialize
gcov_count tables.
(branch_prob): Update.
* profile.h (bb_gcov_counts, edge_gcov_counts): New.
(edge_gcov_count): New.
(bb_gcov_count): New.
* shrink-wrap.c (try_shrink_wrapping): Update.
* tracer.c (better_p): Update.
* trans-mem.c (expand_transaction): Update.
(ipa_tm_insert_irr_call): Update.
(ipa_tm_insert_gettmclone_call): Update.
* tree-call-cdce.c: Update.
* tree-cfg.c (gimple_duplicate_sese_region): Update.
(gimple_duplicate_sese_tail): Update.
(gimple_account_profile_record): Update.
(execute_fixup_cfg): Update.
* tree-inline.c (copy_bb): Update.
(copy_edges_for_bb): Update.
(initialize_cfun): Update.
(freqs_to_counts): Update.
(copy_cfg_body): Update.
(expand_call_inline): Update.
* tree-ssa-ifcombine.c (update_profile_after_ifcombine): Update.
* tree-ssa-loop-ivcanon.c (unloop_loops): Update.
(try_unroll_loop_completely): Update.
(try_peel_loop): Update.
* tree-ssa-loop-manip.c (tree_transform_and_unroll_loop): Update.
* tree-ssa-loop-niter.c (estimate_numbers_of_iterations_loop): Update.
* tree-ssa-loop-split.c (connect_loops): Update.
* tree-ssa-loop-unswitch.c (hoist_guard): Update.
* tree-ssa-reassoc.c (branch_fixup): Update.
* tree-ssa-tail-merge.c (replace_block_by): Update.
* tree-ssa-threadupdate.c (create_block_for_threading): Update.
(compute_path_counts): Update.
(update_profile): Update.
(recompute_probabilities): Update.
(update_joiner_offpath_counts): Update.
(estimated_freqs_path): Update.
(freqs_to_counts_path): Update.
(clear_counts_path): Update.
(ssa_fix_duplicate_block_edges): Update.
(duplicate_thread_path): Update.
* tree-switch-conversion.c (case_bit_test_cmp): Update.
(struct switch_conv_info): Update.
* tree-tailcall.c (decrease_profile): Update.
* tree-vect-loop-manip.c (slpeel_add_loop_guard): Update.
* tree-vect-loop.c (scale_profile_for_vect_loop): Update.
* value-prof.c (check_counter): Update.
(gimple_divmod_fixed_value): Update.
(gimple_mod_pow2): Update.
(gimple_mod_subtract): Update.
(gimple_ic_transform): Update.
(gimple_stringop_fixed_value): Update.
* value-prof.h (gimple_ic): Update.
* gcc.dg/tree-ssa/attr-hotcold-2.c: Update template.
From-SVN: r248863
Diffstat (limited to 'gcc/ipa-inline.c')
-rw-r--r-- | gcc/ipa-inline.c | 128 |
1 files changed, 72 insertions, 56 deletions
diff --git a/gcc/ipa-inline.c b/gcc/ipa-inline.c index 0ebe147..8900556 100644 --- a/gcc/ipa-inline.c +++ b/gcc/ipa-inline.c @@ -123,8 +123,8 @@ typedef fibonacci_node <sreal, cgraph_edge> edge_heap_node_t; /* Statistics we collect about inlining algorithm. */ static int overall_size; -static gcov_type max_count; -static gcov_type spec_rem; +static profile_count max_count; +static profile_count spec_rem; /* Pre-computed constants 1/CGRAPH_FREQ_BASE and 1/100. */ static sreal cgraph_freq_base_rec, percent_rec; @@ -637,8 +637,10 @@ compute_uninlined_call_time (struct cgraph_edge *edge, ? edge->caller->global.inlined_to : edge->caller); - if (edge->count && caller->count) - uninlined_call_time *= (sreal)edge->count / caller->count; + if (edge->count > profile_count::zero () + && caller->count > profile_count::zero ()) + uninlined_call_time *= (sreal)edge->count.to_gcov_type () + / caller->count.to_gcov_type (); if (edge->frequency) uninlined_call_time *= cgraph_freq_base_rec * edge->frequency; else @@ -660,8 +662,9 @@ compute_inlined_call_time (struct cgraph_edge *edge, : edge->caller); sreal caller_time = ipa_fn_summaries->get (caller)->time; - if (edge->count && caller->count) - time *= (sreal)edge->count / caller->count; + if (edge->count > profile_count::zero () + && caller->count > profile_count::zero ()) + time *= (sreal)edge->count.to_gcov_type () / caller->count.to_gcov_type (); if (edge->frequency) time *= cgraph_freq_base_rec * edge->frequency; else @@ -718,7 +721,7 @@ want_inline_small_function_p (struct cgraph_edge *e, bool report) promote non-inline functions to inline and we increase MAX_INLINE_INSNS_SINGLE 16-fold for inline functions. */ else if ((!DECL_DECLARED_INLINE_P (callee->decl) - && (!e->count || !e->maybe_hot_p ())) + && (!e->count.initialized_p () || !e->maybe_hot_p ())) && ipa_fn_summaries->get (callee)->min_size - ipa_call_summaries->get (e)->call_stmt_size > MAX (MAX_INLINE_INSNS_SINGLE, MAX_INLINE_INSNS_AUTO)) @@ -726,7 +729,8 @@ want_inline_small_function_p (struct cgraph_edge *e, bool report) e->inline_failed = CIF_MAX_INLINE_INSNS_AUTO_LIMIT; want_inline = false; } - else if ((DECL_DECLARED_INLINE_P (callee->decl) || e->count) + else if ((DECL_DECLARED_INLINE_P (callee->decl) + || e->count > profile_count::zero ()) && ipa_fn_summaries->get (callee)->min_size - ipa_call_summaries->get (e)->call_stmt_size > 16 * MAX_INLINE_INSNS_SINGLE) @@ -836,7 +840,7 @@ want_inline_self_recursive_call_p (struct cgraph_edge *edge, reason = "recursive call is cold"; want_inline = false; } - else if (max_count && !outer_node->count) + else if (outer_node->count == profile_count::zero ()) { reason = "not executed in profile"; want_inline = false; @@ -874,14 +878,15 @@ want_inline_self_recursive_call_p (struct cgraph_edge *edge, int i; for (i = 1; i < depth; i++) max_prob = max_prob * max_prob / CGRAPH_FREQ_BASE; - if (max_count - && (edge->count * CGRAPH_FREQ_BASE / outer_node->count + if (max_count > profile_count::zero () && edge->count > profile_count::zero () + && (edge->count.to_gcov_type () * CGRAPH_FREQ_BASE + / outer_node->count.to_gcov_type () >= max_prob)) { reason = "profile of recursive call is too large"; want_inline = false; } - if (!max_count + if (max_count == profile_count::zero () && (edge->frequency * CGRAPH_FREQ_BASE / caller_freq >= max_prob)) { @@ -907,14 +912,15 @@ want_inline_self_recursive_call_p (struct cgraph_edge *edge, methods. */ else { - if (max_count - && (edge->count * 100 / outer_node->count + if (max_count > profile_count::zero () + && (edge->count.to_gcov_type () * 100 + / outer_node->count.to_gcov_type () <= PARAM_VALUE (PARAM_MIN_INLINE_RECURSIVE_PROBABILITY))) { reason = "profile of recursive call is too small"; want_inline = false; } - else if (!max_count + else if (max_count == profile_count::zero () && (edge->frequency * 100 / caller_freq <= PARAM_VALUE (PARAM_MIN_INLINE_RECURSIVE_PROBABILITY))) { @@ -1058,7 +1064,8 @@ edge_badness (struct cgraph_edge *edge, bool dump) Again use negative value to make calls with profile appear hotter then calls without. */ - else if (opt_for_fn (caller->decl, flag_guess_branch_prob) || caller->count) + else if (opt_for_fn (caller->decl, flag_guess_branch_prob) + || caller->count > profile_count::zero ()) { sreal numerator, denominator; int overall_growth; @@ -1068,8 +1075,8 @@ edge_badness (struct cgraph_edge *edge, bool dump) - inlined_time); if (numerator == 0) numerator = ((sreal) 1 >> 8); - if (caller->count) - numerator *= caller->count; + if (caller->count > profile_count::zero ()) + numerator *= caller->count.to_gcov_type (); else if (opt_for_fn (caller->decl, flag_branch_probabilities)) numerator = numerator >> 11; denominator = growth; @@ -1155,7 +1162,8 @@ edge_badness (struct cgraph_edge *edge, bool dump) " %i (compensated)\n", badness.to_double (), (double)edge->frequency / CGRAPH_FREQ_BASE, - edge->count, caller->count, + edge->count.initialized_p () ? edge->count.to_gcov_type () : -1, + caller->count.initialized_p () ? caller->count.to_gcov_type () : -1, compute_uninlined_call_time (edge, unspec_edge_time).to_double (), compute_inlined_call_time (edge, edge_time).to_double (), @@ -1417,8 +1425,10 @@ lookup_recursive_calls (struct cgraph_node *node, struct cgraph_node *where, { /* When profile feedback is available, prioritize by expected number of calls. */ - heap->insert (!max_count ? -e->frequency - : -(e->count / ((max_count + (1<<24) - 1) / (1<<24))), + heap->insert (!(max_count > 0) || !e->count.initialized_p () ? -e->frequency + : -(e->count.to_gcov_type () + / ((max_count.to_gcov_type () + (1<<24) - 1) + / (1<<24))), e); } for (e = where->callees; e; e = e->next_callee) @@ -1506,10 +1516,11 @@ recursive_inlining (struct cgraph_edge *edge, { fprintf (dump_file, " Inlining call of depth %i", depth); - if (node->count) + if (node->count > profile_count::zero ()) { fprintf (dump_file, " called approx. %.2f times per call", - (double)curr->count / node->count); + (double)curr->count.to_gcov_type () + / node->count.to_gcov_type ()); } fprintf (dump_file, "\n"); } @@ -1731,7 +1742,7 @@ inline_small_functions (void) /* Compute overall unit size and other global parameters used by badness metrics. */ - max_count = 0; + max_count = profile_count::uninitialized (); ipa_reduced_postorder (order, true, true, NULL); free (order); @@ -1771,7 +1782,7 @@ inline_small_functions (void) } for (edge = node->callers; edge; edge = edge->next_caller) - if (max_count < edge->count) + if (!(max_count >= edge->count)) max_count = edge->count; } ipa_free_postorder_info (); @@ -1835,7 +1846,7 @@ inline_small_functions (void) } gcc_assert (in_lto_p - || !max_count + || !(max_count > 0) || (profile_info && flag_branch_probabilities)); while (!edge_heap.empty ()) @@ -1880,9 +1891,7 @@ inline_small_functions (void) Increases of badness are handled lazilly; when we see key with out of date value on it, we re-insert it now. */ current_badness = edge_badness (edge, false); - /* Disable checking for profile because roundoff errors may cause slight - deviations in the order. */ - gcc_assert (max_count || cached_badness == current_badness); + gcc_assert (cached_badness == current_badness); gcc_assert (current_badness >= badness); #else current_badness = edge_badness (edge, false); @@ -1927,9 +1936,12 @@ inline_small_functions (void) : -1, badness.to_double (), edge->frequency / (double)CGRAPH_FREQ_BASE); - if (edge->count) - fprintf (dump_file," Called %" PRId64"x\n", - edge->count); + if (edge->count.initialized_p ()) + { + fprintf (dump_file, " Called "); + edge->count.dump (dump_file); + fprintf (dump_file, "times\n"); + } if (dump_flags & TDF_DETAILS) edge_badness (edge, true); } @@ -2027,7 +2039,7 @@ inline_small_functions (void) update_caller_keys (&edge_heap, where, updated_nodes, NULL); /* Offline copy count has possibly changed, recompute if profile is available. */ - if (max_count) + if (max_count > profile_count::zero ()) { struct cgraph_node *n = cgraph_node::get (edge->callee->decl); if (n != edge->callee && n->analyzed) @@ -2233,7 +2245,8 @@ dump_overall_stats (void) { sreal time = ipa_fn_summaries->get (node)->time; sum += time; - sum_weighted += time * node->count; + if (node->count.initialized_p ()) + sum_weighted += time * node->count.to_gcov_type (); } fprintf (dump_file, "Overall time estimate: " "%f weighted by profile: " @@ -2263,56 +2276,59 @@ dump_inline_stats (void) { if (e->inline_failed) { - reason[(int) e->inline_failed][0] += e->count; + if (e->count.initialized_p ()) + reason[(int) e->inline_failed][0] += e->count.to_gcov_type (); reason[(int) e->inline_failed][1] += e->frequency; reason[(int) e->inline_failed][2] ++; - if (DECL_VIRTUAL_P (e->callee->decl)) + if (DECL_VIRTUAL_P (e->callee->decl) + && e->count.initialized_p ()) { if (e->indirect_inlining_edge) - noninlined_virt_indir_cnt += e->count; + noninlined_virt_indir_cnt += e->count.to_gcov_type (); else - noninlined_virt_cnt += e->count; + noninlined_virt_cnt += e->count.to_gcov_type (); } - else + else if (e->count.initialized_p ()) { if (e->indirect_inlining_edge) - noninlined_indir_cnt += e->count; + noninlined_indir_cnt += e->count.to_gcov_type (); else - noninlined_cnt += e->count; + noninlined_cnt += e->count.to_gcov_type (); } } - else + else if (e->count.initialized_p ()) { if (e->speculative) { if (DECL_VIRTUAL_P (e->callee->decl)) - inlined_speculative_ply += e->count; + inlined_speculative_ply += e->count.to_gcov_type (); else - inlined_speculative += e->count; + inlined_speculative += e->count.to_gcov_type (); } else if (DECL_VIRTUAL_P (e->callee->decl)) { if (e->indirect_inlining_edge) - inlined_virt_indir_cnt += e->count; + inlined_virt_indir_cnt += e->count.to_gcov_type (); else - inlined_virt_cnt += e->count; + inlined_virt_cnt += e->count.to_gcov_type (); } else { if (e->indirect_inlining_edge) - inlined_indir_cnt += e->count; + inlined_indir_cnt += e->count.to_gcov_type (); else - inlined_cnt += e->count; + inlined_cnt += e->count.to_gcov_type (); } } } for (e = node->indirect_calls; e; e = e->next_callee) - if (e->indirect_info->polymorphic) - indirect_poly_cnt += e->count; - else - indirect_cnt += e->count; + if (e->indirect_info->polymorphic + & e->count.initialized_p ()) + indirect_poly_cnt += e->count.to_gcov_type (); + else if (e->count.initialized_p ()) + indirect_cnt += e->count.to_gcov_type (); } - if (max_count) + if (max_count.initialized_p ()) { fprintf (dump_file, "Inlined %" PRId64 " + speculative " @@ -2331,9 +2347,9 @@ dump_inline_stats (void) inlined_indir_cnt, inlined_virt_cnt, inlined_virt_indir_cnt, noninlined_cnt, noninlined_indir_cnt, noninlined_virt_cnt, noninlined_virt_indir_cnt, indirect_cnt, indirect_poly_cnt); - fprintf (dump_file, - "Removed speculations %" PRId64 "\n", - spec_rem); + fprintf (dump_file, "Removed speculations "); + spec_rem.dump (dump_file); + fprintf (dump_file, "\n"); } dump_overall_stats (); fprintf (dump_file, "\nWhy inlining failed?\n"); |