Subversion Repositories scarts

/* Calculate branch probabilities, and basic block execution counts.

   Copyright (C) 1990, 1991, 1992, 1993, 1994, 1996, 1997, 1998, 1999,

   2000, 2001, 2002, 2003, 2004, 2005  Free Software Foundation, Inc.

   Contributed by James E. Wilson, UC Berkeley/Cygnus Support;

   based on some ideas from Dain Samples of UC Berkeley.

   Further mangling by Bob Manson, Cygnus Support.

This file is part of GCC.

GCC is free software; you can redistribute it and/or modify it under

the terms of the GNU General Public License as published by the Free

Software Foundation; either version 2, or (at your option) any later

version.

GCC is distributed in the hope that it will be useful, but WITHOUT ANY

WARRANTY; without even the implied warranty of MERCHANTABILITY or

FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License

for more details.

You should have received a copy of the GNU General Public License

along with GCC; see the file COPYING.  If not, write to the Free

Software Foundation, 51 Franklin Street, Fifth Floor, Boston, MA

02110-1301, USA.  */

/* Generate basic block profile instrumentation and auxiliary files.

   Profile generation is optimized, so that not all arcs in the basic

   block graph need instrumenting. First, the BB graph is closed with

   one entry (function start), and one exit (function exit).  Any

   ABNORMAL_EDGE cannot be instrumented (because there is no control

   path to place the code). We close the graph by inserting fake

   EDGE_FAKE edges to the EXIT_BLOCK, from the sources of abnormal

   edges that do not go to the exit_block. We ignore such abnormal

   edges.  Naturally these fake edges are never directly traversed,

   and so *cannot* be directly instrumented.  Some other graph

   massaging is done. To optimize the instrumentation we generate the

   BB minimal span tree, only edges that are not on the span tree

   (plus the entry point) need instrumenting. From that information

   all other edge counts can be deduced.  By construction all fake

   edges must be on the spanning tree. We also attempt to place

   EDGE_CRITICAL edges on the spanning tree.

   The auxiliary files generated are <dumpbase>.gcno (at compile time)

   and <dumpbase>.gcda (at run time).  The format is

   described in full in gcov-io.h.  */

/* ??? Register allocation should use basic block execution counts to

   give preference to the most commonly executed blocks.  */

/* ??? Should calculate branch probabilities before instrumenting code, since

   then we can use arc counts to help decide which arcs to instrument.  */

#include "config.h"

#include "system.h"

#include "coretypes.h"

#include "tm.h"

#include "rtl.h"

#include "flags.h"

#include "output.h"

#include "regs.h"

#include "expr.h"

#include "function.h"

#include "toplev.h"

#include "coverage.h"

#include "value-prof.h"

#include "tree.h"

#include "cfghooks.h"

#include "tree-flow.h"

#include "timevar.h"

#include "cfgloop.h"

#include "tree-pass.h"

/* Hooks for profiling.  */

static struct profile_hooks* profile_hooks;

/* File for profiling debug output.  */

static inline FILE*

profile_dump_file (void) {

  return profile_hooks->profile_dump_file ();

}

/* Additional information about the edges we need.  */

struct edge_info {

  unsigned int count_valid : 1;

  /* Is on the spanning tree.  */

  unsigned int on_tree : 1;

  /* Pretend this edge does not exist (it is abnormal and we've

     inserted a fake to compensate).  */

  unsigned int ignore : 1;

};

struct bb_info {

  unsigned int count_valid : 1;

  /* Number of successor and predecessor edges.  */

  gcov_type succ_count;

  gcov_type pred_count;

};

#define EDGE_INFO(e)  ((struct edge_info *) (e)->aux)

#define BB_INFO(b)  ((struct bb_info *) (b)->aux)

/* Counter summary from the last set of coverage counts read.  */

const struct gcov_ctr_summary *profile_info;

/* Collect statistics on the performance of this pass for the entire source

   file.  */

static int total_num_blocks;

static int total_num_edges;

static int total_num_edges_ignored;

static int total_num_edges_instrumented;

static int total_num_blocks_created;

static int total_num_passes;

static int total_num_times_called;

static int total_hist_br_prob[20];

static int total_num_never_executed;

static int total_num_branches;

/* Forward declarations.  */

static void find_spanning_tree (struct edge_list *);

static unsigned instrument_edges (struct edge_list *);

static void instrument_values (histogram_values);

static void compute_branch_probabilities (void);

static void compute_value_histograms (histogram_values);

static gcov_type * get_exec_counts (void);

static basic_block find_group (basic_block);

static void union_groups (basic_block, basic_block);

/* Add edge instrumentation code to the entire insn chain.

   F is the first insn of the chain.

   NUM_BLOCKS is the number of basic blocks found in F.  */

static unsigned

instrument_edges (struct edge_list *el)

{

  unsigned num_instr_edges = 0;

  int num_edges = NUM_EDGES (el);

  basic_block bb;

  FOR_BB_BETWEEN (bb, ENTRY_BLOCK_PTR, NULL, next_bb)

    {

      edge e;

      edge_iterator ei;

      FOR_EACH_EDGE (e, ei, bb->succs)

        {

          struct edge_info *inf = EDGE_INFO (e);

          if (!inf->ignore && !inf->on_tree)

            {

              gcc_assert (!(e->flags & EDGE_ABNORMAL));

              if (dump_file)

                fprintf (dump_file, "Edge %d to %d instrumented%s\n",

                         e->src->index, e->dest->index,

                         EDGE_CRITICAL_P (e) ? " (and split)" : "");

              (profile_hooks->gen_edge_profiler) (num_instr_edges++, e);

            }

        }

    }

  total_num_blocks_created += num_edges;

  if (dump_file)

    fprintf (dump_file, "%d edges instrumented\n", num_instr_edges);

  return num_instr_edges;

}

/* Add code to measure histograms for values in list VALUES.  */

static void

instrument_values (histogram_values values)

{

  unsigned i, t;

  /* Emit code to generate the histograms before the insns.  */

  for (i = 0; i < VEC_length (histogram_value, values); i++)

    {

      histogram_value hist = VEC_index (histogram_value, values, i);

      switch (hist->type)

        {

        case HIST_TYPE_INTERVAL:

          t = GCOV_COUNTER_V_INTERVAL;

          break;

        case HIST_TYPE_POW2:

          t = GCOV_COUNTER_V_POW2;

          break;

        case HIST_TYPE_SINGLE_VALUE:

          t = GCOV_COUNTER_V_SINGLE;

          break;

        case HIST_TYPE_CONST_DELTA:

          t = GCOV_COUNTER_V_DELTA;

          break;

        default:

          gcc_unreachable ();

        }

      if (!coverage_counter_alloc (t, hist->n_counters))

        continue;

      switch (hist->type)

        {

        case HIST_TYPE_INTERVAL:

          (profile_hooks->gen_interval_profiler) (hist, t, 0);

          break;

        case HIST_TYPE_POW2:

          (profile_hooks->gen_pow2_profiler) (hist, t, 0);

          break;

        case HIST_TYPE_SINGLE_VALUE:

          (profile_hooks->gen_one_value_profiler) (hist, t, 0);

          break;

        case HIST_TYPE_CONST_DELTA:

          (profile_hooks->gen_const_delta_profiler) (hist, t, 0);

          break;

        default:

          gcc_unreachable ();

        }

    }

  VEC_free (histogram_value, heap, values);

}

/* Computes hybrid profile for all matching entries in da_file.  */

static gcov_type *

get_exec_counts (void)

{

  unsigned num_edges = 0;

  basic_block bb;

  gcov_type *counts;

  /* Count the edges to be (possibly) instrumented.  */

  FOR_BB_BETWEEN (bb, ENTRY_BLOCK_PTR, NULL, next_bb)

    {

      edge e;

      edge_iterator ei;

      FOR_EACH_EDGE (e, ei, bb->succs)

        if (!EDGE_INFO (e)->ignore && !EDGE_INFO (e)->on_tree)

          num_edges++;

    }

  counts = get_coverage_counts (GCOV_COUNTER_ARCS, num_edges, &profile_info);

  if (!counts)

    return NULL;

  if (dump_file && profile_info)

    fprintf(dump_file, "Merged %u profiles with maximal count %u.\n",

            profile_info->runs, (unsigned) profile_info->sum_max);

  return counts;

}

/* Compute the branch probabilities for the various branches.

   Annotate them accordingly.  */

static void

compute_branch_probabilities (void)

{

  basic_block bb;

  int i;

  int num_edges = 0;

  int changes;

  int passes;

  int hist_br_prob[20];

  int num_never_executed;

  int num_branches;

  gcov_type *exec_counts = get_exec_counts ();

  int exec_counts_pos = 0;

  /* Very simple sanity checks so we catch bugs in our profiling code.  */

  if (profile_info)

    {

      if (profile_info->run_max * profile_info->runs < profile_info->sum_max)

        {

          error ("corrupted profile info: run_max * runs < sum_max");

          exec_counts = NULL;

        }

      if (profile_info->sum_all < profile_info->sum_max)

        {

          error ("corrupted profile info: sum_all is smaller than sum_max");

          exec_counts = NULL;

        }

    }

  /* Attach extra info block to each bb.  */

  alloc_aux_for_blocks (sizeof (struct bb_info));

  FOR_BB_BETWEEN (bb, ENTRY_BLOCK_PTR, NULL, next_bb)

    {

      edge e;

      edge_iterator ei;

      FOR_EACH_EDGE (e, ei, bb->succs)

        if (!EDGE_INFO (e)->ignore)

          BB_INFO (bb)->succ_count++;

      FOR_EACH_EDGE (e, ei, bb->preds)

        if (!EDGE_INFO (e)->ignore)

          BB_INFO (bb)->pred_count++;

    }

  /* Avoid predicting entry on exit nodes.  */

  BB_INFO (EXIT_BLOCK_PTR)->succ_count = 2;

  BB_INFO (ENTRY_BLOCK_PTR)->pred_count = 2;

  /* For each edge not on the spanning tree, set its execution count from

     the .da file.  */

  /* The first count in the .da file is the number of times that the function

     was entered.  This is the exec_count for block zero.  */

  FOR_BB_BETWEEN (bb, ENTRY_BLOCK_PTR, NULL, next_bb)

    {

      edge e;

      edge_iterator ei;

      FOR_EACH_EDGE (e, ei, bb->succs)

        if (!EDGE_INFO (e)->ignore && !EDGE_INFO (e)->on_tree)

          {

            num_edges++;

            if (exec_counts)

              {

                e->count = exec_counts[exec_counts_pos++];

                if (e->count > profile_info->sum_max)

                  {

                    error ("corrupted profile info: edge from %i to %i exceeds maximal count",

                           bb->index, e->dest->index);

                  }

              }

            else

              e->count = 0;

            EDGE_INFO (e)->count_valid = 1;

            BB_INFO (bb)->succ_count--;

            BB_INFO (e->dest)->pred_count--;

            if (dump_file)

              {

                fprintf (dump_file, "\nRead edge from %i to %i, count:",

                         bb->index, e->dest->index);

                fprintf (dump_file, HOST_WIDEST_INT_PRINT_DEC,

                         (HOST_WIDEST_INT) e->count);

              }

          }

    }

  if (dump_file)

    fprintf (dump_file, "\n%d edge counts read\n", num_edges);

  /* For every block in the file,

     - if every exit/entrance edge has a known count, then set the block count

     - if the block count is known, and every exit/entrance edge but one has

     a known execution count, then set the count of the remaining edge

     As edge counts are set, decrement the succ/pred count, but don't delete

     the edge, that way we can easily tell when all edges are known, or only

     one edge is unknown.  */

  /* The order that the basic blocks are iterated through is important.

     Since the code that finds spanning trees starts with block 0, low numbered

     edges are put on the spanning tree in preference to high numbered edges.

     Hence, most instrumented edges are at the end.  Graph solving works much

     faster if we propagate numbers from the end to the start.

     This takes an average of slightly more than 3 passes.  */

  changes = 1;

  passes = 0;

  while (changes)

    {

      passes++;

      changes = 0;

      FOR_BB_BETWEEN (bb, EXIT_BLOCK_PTR, NULL, prev_bb)

        {

          struct bb_info *bi = BB_INFO (bb);

          if (! bi->count_valid)

            {

              if (bi->succ_count == 0)

                {

                  edge e;

                  edge_iterator ei;

                  gcov_type total = 0;

                  FOR_EACH_EDGE (e, ei, bb->succs)

                    total += e->count;

                  bb->count = total;

                  bi->count_valid = 1;

                  changes = 1;

                }

              else if (bi->pred_count == 0)

                {

                  edge e;

                  edge_iterator ei;

                  gcov_type total = 0;

                  FOR_EACH_EDGE (e, ei, bb->preds)

                    total += e->count;

                  bb->count = total;

                  bi->count_valid = 1;

                  changes = 1;

                }

            }

          if (bi->count_valid)

            {

              if (bi->succ_count == 1)

                {

                  edge e;

                  edge_iterator ei;

                  gcov_type total = 0;

                  /* One of the counts will be invalid, but it is zero,

                     so adding it in also doesn't hurt.  */

                  FOR_EACH_EDGE (e, ei, bb->succs)

                    total += e->count;

                  /* Seedgeh for the invalid edge, and set its count.  */

                  FOR_EACH_EDGE (e, ei, bb->succs)

                    if (! EDGE_INFO (e)->count_valid && ! EDGE_INFO (e)->ignore)

                      break;

                  /* Calculate count for remaining edge by conservation.  */

                  total = bb->count - total;

                  gcc_assert (e);

                  EDGE_INFO (e)->count_valid = 1;

                  e->count = total;

                  bi->succ_count--;

                  BB_INFO (e->dest)->pred_count--;

                  changes = 1;

                }

              if (bi->pred_count == 1)

                {

                  edge e;

                  edge_iterator ei;

                  gcov_type total = 0;

                  /* One of the counts will be invalid, but it is zero,

                     so adding it in also doesn't hurt.  */

                  FOR_EACH_EDGE (e, ei, bb->preds)

                    total += e->count;

                  /* Search for the invalid edge, and set its count.  */

                  FOR_EACH_EDGE (e, ei, bb->preds)

                    if (!EDGE_INFO (e)->count_valid && !EDGE_INFO (e)->ignore)

                      break;

                  /* Calculate count for remaining edge by conservation.  */

                  total = bb->count - total + e->count;

                  gcc_assert (e);

                  EDGE_INFO (e)->count_valid = 1;

                  e->count = total;

                  bi->pred_count--;

                  BB_INFO (e->src)->succ_count--;

                  changes = 1;

                }

            }

        }

    }

  if (dump_file)

    dump_flow_info (dump_file);

  total_num_passes += passes;

  if (dump_file)

    fprintf (dump_file, "Graph solving took %d passes.\n\n", passes);

  /* If the graph has been correctly solved, every block will have a

     succ and pred count of zero.  */

  FOR_EACH_BB (bb)

    {

      gcc_assert (!BB_INFO (bb)->succ_count && !BB_INFO (bb)->pred_count);

    }

  /* For every edge, calculate its branch probability and add a reg_note

     to the branch insn to indicate this.  */

  for (i = 0; i < 20; i++)

    hist_br_prob[i] = 0;

  num_never_executed = 0;

  num_branches = 0;

  FOR_BB_BETWEEN (bb, ENTRY_BLOCK_PTR, NULL, next_bb)

    {

      edge e;

      edge_iterator ei;

      rtx note;

      if (bb->count < 0)

        {

          error ("corrupted profile info: number of iterations for basic block %d thought to be %i",

                 bb->index, (int)bb->count);

          bb->count = 0;

        }

      FOR_EACH_EDGE (e, ei, bb->succs)

        {

          /* Function may return twice in the cased the called function is

             setjmp or calls fork, but we can't represent this by extra

             edge from the entry, since extra edge from the exit is

             already present.  We get negative frequency from the entry

             point.  */

          if ((e->count < 0

               && e->dest == EXIT_BLOCK_PTR)

              || (e->count > bb->count

                  && e->dest != EXIT_BLOCK_PTR))

            {

              if (block_ends_with_call_p (bb))

                e->count = e->count < 0 ? 0 : bb->count;

            }

          if (e->count < 0 || e->count > bb->count)

            {

              error ("corrupted profile info: number of executions for edge %d-%d thought to be %i",

                     e->src->index, e->dest->index,

                     (int)e->count);

              e->count = bb->count / 2;

            }

        }

      if (bb->count)

        {

          FOR_EACH_EDGE (e, ei, bb->succs)

            e->probability = (e->count * REG_BR_PROB_BASE + bb->count / 2) / bb->count;

          if (bb->index >= 0

              && block_ends_with_condjump_p (bb)

              && EDGE_COUNT (bb->succs) >= 2)

            {

              int prob;

              edge e;

              int index;

              /* Find the branch edge.  It is possible that we do have fake

                 edges here.  */

              FOR_EACH_EDGE (e, ei, bb->succs)

                if (!(e->flags & (EDGE_FAKE | EDGE_FALLTHRU)))

                  break;

              prob = e->probability;

              index = prob * 20 / REG_BR_PROB_BASE;

              if (index == 20)

                index = 19;

              hist_br_prob[index]++;

              /* Do this for RTL only.  */

              if (!ir_type ())

                {

                  note = find_reg_note (BB_END (bb), REG_BR_PROB, 0);

                  /* There may be already note put by some other pass, such

                     as builtin_expect expander.  */

                  if (note)

                    XEXP (note, 0) = GEN_INT (prob);

                  else

                    REG_NOTES (BB_END (bb))

                      = gen_rtx_EXPR_LIST (REG_BR_PROB, GEN_INT (prob),

                                           REG_NOTES (BB_END (bb)));

                }

              num_branches++;

            }

        }

      /* Otherwise try to preserve the existing REG_BR_PROB probabilities

         tree based profile guessing put into code.  BB can be the

         ENTRY_BLOCK, and it can have multiple (fake) successors in

         EH cases, but it still has no code; don't crash in this case.  */

      else if (profile_status == PROFILE_ABSENT

               && !ir_type ()

               && EDGE_COUNT (bb->succs) > 1

               && BB_END (bb)

               && (note = find_reg_note (BB_END (bb), REG_BR_PROB, 0)))

        {

          int prob = INTVAL (XEXP (note, 0));

          BRANCH_EDGE (bb)->probability = prob;

          FALLTHRU_EDGE (bb)->probability = REG_BR_PROB_BASE - prob;

        }

      /* As a last resort, distribute the probabilities evenly.

         Use simple heuristics that if there are normal edges,

         give all abnormals frequency of 0, otherwise distribute the

         frequency over abnormals (this is the case of noreturn

         calls).  */

      else if (profile_status == PROFILE_ABSENT)

        {

          int total = 0;

          FOR_EACH_EDGE (e, ei, bb->succs)

            if (!(e->flags & (EDGE_COMPLEX | EDGE_FAKE)))

              total ++;

          if (total)

            {

              FOR_EACH_EDGE (e, ei, bb->succs)

                if (!(e->flags & (EDGE_COMPLEX | EDGE_FAKE)))

                  e->probability = REG_BR_PROB_BASE / total;

                else

                  e->probability = 0;

            }

          else

            {

              total += EDGE_COUNT (bb->succs);

              FOR_EACH_EDGE (e, ei, bb->succs)

                e->probability = REG_BR_PROB_BASE / total;

            }

          if (bb->index >= 0

              && block_ends_with_condjump_p (bb)

              && EDGE_COUNT (bb->succs) >= 2)

            num_branches++, num_never_executed;

        }

    }

  counts_to_freqs ();

  if (dump_file)

    {

      fprintf (dump_file, "%d branches\n", num_branches);

      fprintf (dump_file, "%d branches never executed\n",

               num_never_executed);

      if (num_branches)

        for (i = 0; i < 10; i++)

          fprintf (dump_file, "%d%% branches in range %d-%d%%\n",

                   (hist_br_prob[i] + hist_br_prob[19-i]) * 100 / num_branches,

                   5 * i, 5 * i + 5);

      total_num_branches += num_branches;

      total_num_never_executed += num_never_executed;

      for (i = 0; i < 20; i++)

        total_hist_br_prob[i] += hist_br_prob[i];

      fputc ('\n', dump_file);

      fputc ('\n', dump_file);

    }

  free_aux_for_blocks ();

}

/* Load value histograms values whose description is stored in VALUES array

   from .gcda file.  */

static void

compute_value_histograms (histogram_values values)

{

  unsigned i, j, t, any;

  unsigned n_histogram_counters[GCOV_N_VALUE_COUNTERS];

  gcov_type *histogram_counts[GCOV_N_VALUE_COUNTERS];

  gcov_type *act_count[GCOV_N_VALUE_COUNTERS];

  gcov_type *aact_count;

  for (t = 0; t < GCOV_N_VALUE_COUNTERS; t++)

    n_histogram_counters[t] = 0;

  for (i = 0; i < VEC_length (histogram_value, values); i++)

    {

      histogram_value hist = VEC_index (histogram_value, values, i);

      n_histogram_counters[(int) hist->type] += hist->n_counters;

    }

  any = 0;

  for (t = 0; t < GCOV_N_VALUE_COUNTERS; t++)

    {

      if (!n_histogram_counters[t])

        {

          histogram_counts[t] = NULL;

          continue;

        }

      histogram_counts[t] =

        get_coverage_counts (COUNTER_FOR_HIST_TYPE (t),

                             n_histogram_counters[t], NULL);

      if (histogram_counts[t])

        any = 1;

      act_count[t] = histogram_counts[t];

    }

  if (!any)

    return;

  for (i = 0; i < VEC_length (histogram_value, values); i++)

    {

      histogram_value hist = VEC_index (histogram_value, values, i);

      tree stmt = hist->hvalue.stmt;

      stmt_ann_t ann = get_stmt_ann (stmt);

      t = (int) hist->type;

      aact_count = act_count[t];

      act_count[t] += hist->n_counters;

      hist->hvalue.next = ann->histograms;

      ann->histograms = hist;