Index: doc/invoke.texi =================================================================== --- doc/invoke.texi (revision 191852) +++ doc/invoke.texi (working copy) @@ -386,7 +386,7 @@ Objective-C and Objective-C++ Dialects}. -fno-toplevel-reorder -fno-trapping-math -fno-zero-initialized-in-bss @gol -fomit-frame-pointer -foptimize-register-move -foptimize-sibling-calls @gol -fpartial-inlining -fpeel-loops -fpredictive-commoning @gol --fprefetch-loop-arrays @gol +-fprefetch-loop-arrays -fprofile-consistency-report @gol -fprofile-correction -fprofile-dir=@var{path} -fprofile-generate @gol -fprofile-generate=@var{path} @gol -fprofile-use -fprofile-use=@var{path} -fprofile-values @gol @@ -5149,6 +5149,11 @@ allocation for the WPA phase only. Makes the compiler print some statistics about permanent memory allocation before or after interprocedural optimization. +@item -fprofile-consistency-report +@opindex fprofile-consistency-report +Makes the compiler print some statistics about consistency of the +(estimated) profile. + @item -fstack-usage @opindex fstack-usage Makes the compiler output stack usage information for the program, on a Index: common.opt =================================================================== --- common.opt (revision 191852) +++ common.opt (working copy) @@ -1649,6 +1649,10 @@ fprofile-values Common Report Var(flag_profile_values) Insert code to profile values of expressions +fprofile-consistency-report +Common Report Var(profile_report) +Report on consistency of profile + frandom-seed Common Var(common_deferred_options) Defer Index: toplev.c =================================================================== --- toplev.c (revision 191852) +++ toplev.c (working copy) @@ -1815,6 +1815,9 @@ finalize (bool no_backend) if (mem_report) dump_memory_report (true); + if (profile_report) + dump_profile_consistency_report (); + /* Language-specific end of compilation actions. */ lang_hooks.finish (); } Index: passes.c =================================================================== --- passes.c (revision 191852) +++ passes.c (working copy) @@ -1782,6 +1784,108 @@ execute_function_dump (void *data ATTRIB } } +/* Hold statistic about profile consistency. */ + +struct profile_record +{ + int num_mismatched_freq_in[2]; + int num_mismatched_freq_out[2]; + int num_mismatched_count_in[2]; + int num_mismatched_count_out[2]; + bool tested; +}; + +static struct profile_record *profile_record; + +/* Account profile inconsistencies for pass INDEX. If SUBPASS is non-zero, the + accounting happens after TODO. */ + +static void +check_profile_consistency (int index, int subpass) +{ + basic_block bb; + edge_iterator ei; + edge e; + int sum; + gcov_type lsum; + + if (index == -1) + return; + if (!profile_record) + profile_record = XCNEWVEC (struct profile_record, + passes_by_id_size); + gcc_assert (index < passes_by_id_size && index >= 0); + gcc_assert (subpass < 2); + profile_record[index].tested = true; + + FOR_ALL_BB (bb) + { + if (bb != EXIT_BLOCK_PTR_FOR_FUNCTION (cfun)) + { + sum = 0; + FOR_EACH_EDGE (e, ei, bb->succs) + sum += e->probability; + if (EDGE_COUNT (bb->succs) && abs (sum - REG_BR_PROB_BASE) > 100) + profile_record[index].num_mismatched_freq_out[subpass]++; + lsum = 0; + FOR_EACH_EDGE (e, ei, bb->succs) + lsum += e->count; + if (EDGE_COUNT (bb->succs) + && (lsum - bb->count > 100 || lsum - bb->count < -100)) + profile_record[index].num_mismatched_count_out[subpass]++; + } + if (bb != ENTRY_BLOCK_PTR_FOR_FUNCTION (cfun)) + { + sum = 0; + FOR_EACH_EDGE (e, ei, bb->preds) + sum += EDGE_FREQUENCY (e); + if (abs (sum - bb->frequency) > 100 + || (MAX (sum, bb->frequency) > 10 + && abs ((sum - bb->frequency) * 100 / (MAX (sum, bb->frequency) + 1)) > 10)) + profile_record[index].num_mismatched_freq_in[subpass]++; + lsum = 0; + FOR_EACH_EDGE (e, ei, bb->preds) + lsum += e->count; + if (lsum - bb->count > 100 || lsum - bb->count < -100) + profile_record[index].num_mismatched_count_in[subpass]++; + } + } +} + +/* Output profile consistency. */ + +void +dump_profile_consistency_report (void) +{ + int i, j; + int last_freq_in = 0, last_count_in = 0, last_freq_out = 0, last_count_out = 0; + + if (!profile_record) + return; + fprintf (stderr, "\nProfile consistency report:\n"); + for (i = 0; i < passes_by_id_size; i++) + for (j = 0 ; j < 2; j++) + if ((profile_record[i].num_mismatched_freq_in[j] != last_freq_in + || profile_record[i].num_mismatched_freq_out[j] != last_freq_out + || profile_record[i].num_mismatched_count_in[j] != last_count_in + || profile_record[i].num_mismatched_count_out[j] != last_count_out) + && profile_record[i].tested) + { + fprintf (stderr," Pass: %-20s %s mismatched in: %+4i (freqs) %+4i (counts); " + "michmatched out: %+4i (freqs) %+4i (counts)\n", + passes_by_id [i]->name, + j ? "(after TODO)" : "(after pass)", + profile_record[i].num_mismatched_freq_in[j] - last_freq_in, + profile_record[i].num_mismatched_count_in[j] - last_count_in, + profile_record[i].num_mismatched_freq_out[j] - last_freq_out, + profile_record[i].num_mismatched_count_out[j] - last_count_out); + last_freq_in = profile_record[i].num_mismatched_freq_in[j]; + last_freq_out = profile_record[i].num_mismatched_freq_out[j]; + last_count_in = profile_record[i].num_mismatched_count_in[j]; + last_count_out = profile_record[i].num_mismatched_count_out[j]; + } +} + /* Perform all TODO actions that ought to be done on each function. */ static void @@ -2050,9 +2150,16 @@ execute_one_ipa_transform_pass (struct c if (pass->tv_id != TV_NONE) timevar_pop (pass->tv_id); + if (profile_report && cfun && (cfun->curr_properties & PROP_cfg) + && profile_status != PROFILE_ABSENT) + check_profile_consistency (pass->static_pass_number, 0); + /* Run post-pass cleanup and verification. */ execute_todo (todo_after); verify_interpass_invariants (); + if (profile_report && cfun && (cfun->curr_properties & PROP_cfg) + && profile_status != PROFILE_ABSENT) + check_profile_consistency (pass->static_pass_number, 1); do_per_function (execute_function_dump, NULL); pass_fini_dump_file (pass); @@ -2218,8 +2325,16 @@ execute_one_pass (struct opt_pass *pass) clean_graph_dump_file (dump_file_name); } + if (profile_report && cfun && (cfun->curr_properties & PROP_cfg) + && profile_status != PROFILE_ABSENT) + check_profile_consistency (pass->static_pass_number, 0); + /* Run post-pass cleanup and verification. */ execute_todo (todo_after | pass->todo_flags_finish); + if (profile_report && cfun && (cfun->curr_properties & PROP_cfg) + && profile_status != PROFILE_ABSENT) + check_profile_consistency (pass->static_pass_number, 1); + verify_interpass_invariants (); do_per_function (execute_function_dump, NULL); if (pass->type == IPA_PASS) Index: toplev.h =================================================================== --- toplev.h (revision 191852) +++ toplev.h (working copy) @@ -49,6 +49,7 @@ extern void emit_debug_global_declaratio extern void write_global_declarations (void); extern void dump_memory_report (bool); +extern void dump_profile_consistency_report (void); extern void target_reinit (void);