[gcc r14-2400] Improve dumping of profile_count

[gcc r14-2400] Improve dumping of profile_count

[Jan Hubicka]

https://gcc.gnu.org/g:d6c1d7c4009bfe759719675ce3bc03ca503b9bf4

commit r14-2400-gd6c1d7c4009bfe759719675ce3bc03ca503b9bf4
Author: Jan Hubicka <jh@suse.cz>
Date:   Sun Jul 9 15:14:54 2023 +0200

    Improve dumping of profile_count
    
    Dumps of profile_counts are quite hard to interpret since they are 64bit fixed point
    values.  In many cases one looks at a single function and it is better to think of
    basic block frequency, that is how many times it is executed each invocatoin. This
    patch makes CFG dumps to also print this info.
    
    For example:
    main()
    {
            for (int i = 0; i < 10; i++)
                    t();
    }
    
    the -fdump-tree-optimized-blocks-details now prints:
    int main ()
    {
      unsigned int ivtmp_1;
      unsigned int ivtmp_2;
    
    ;;   basic block 2, loop depth 0, count 97603128 (estimated locally, freq 1.0000), maybe hot
    ;;    prev block 0, next block 3, flags: (NEW, VISITED)
    ;;    pred:       ENTRY [always]  count:97603128 (estimated locally, freq 1.0000) (FALLTHRU,EXECUTABLE)
    ;;    succ:       3 [always]  count:97603128 (estimated locally, freq 1.0000) (FALLTHRU,EXECUTABLE)
    
    ;;   basic block 3, loop depth 1, count 976138697 (estimated locally, freq 10.0011), maybe hot
    ;;    prev block 2, next block 4, flags: (NEW, VISITED)
    ;;    pred:       3 [90.0% (guessed)]  count:878535568 (estimated locally, freq 9.0011) (TRUE_VALUE,EXECUTABLE)
    ;;                2 [always]  count:97603128 (estimated locally, freq 1.0000) (FALLTHRU,EXECUTABLE)
      # ivtmp_2 = PHI <ivtmp_1(3), 10(2)>
      t ();
      ivtmp_1 = ivtmp_2 + 4294967295;
      if (ivtmp_1 != 0)
        goto <bb 3>; [90.00%]
      else
        goto <bb 4>; [10.00%]
    ;;    succ:       3 [90.0% (guessed)]  count:878535568 (estimated locally, freq 9.0011) (TRUE_VALUE,EXECUTABLE)
    ;;                4 [10.0% (guessed)]  count:97603129 (estimated locally, freq 1.0000) (FALSE_VALUE,EXECUTABLE)
    
    ;;   basic block 4, loop depth 0, count 97603128 (estimated locally, freq 1.0000), maybe hot
    ;;    prev block 3, next block 1, flags: (NEW, VISITED)
    ;;    pred:       3 [10.0% (guessed)]  count:97603129 (estimated locally, freq 1.0000) (FALSE_VALUE,EXECUTABLE)
      return 0;
    ;;    succ:       EXIT [always]  count:97603128 (estimated locally, freq 1.0000) (EXECUTABLE)
    
    }
    
    Which makes it easier to see that the inner bb is executed 10 times per invocation
    
    gcc/ChangeLog:
    
            * cfg.cc (check_bb_profile): Dump counts with relative frequency.
            (dump_edge_info): Likewise.
            (dump_bb_info): Likewise.
            * profile-count.cc (profile_count::dump): Add comma between quality and
            freq.
    
    gcc/testsuite/ChangeLog:
    
            * gcc.dg/predict-22.c: Update template.

Diff:
---
 gcc/cfg.cc                        | 8 ++++----
 gcc/profile-count.cc              | 2 +-
 gcc/testsuite/gcc.dg/predict-22.c | 2 +-
 3 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/gcc/cfg.cc b/gcc/cfg.cc
index 740d4f3581d..0de6d6b9e71 100644
--- a/gcc/cfg.cc
+++ b/gcc/cfg.cc
@@ -475,9 +475,9 @@ check_bb_profile (basic_block bb, FILE * file, int indent)
 	{
 	  fprintf (file, ";; %sInvalid sum of incoming counts ",
 		   s_indent);
-	  sum.dump (file);
+	  sum.dump (file, fun);
 	  fprintf (file, ", should be ");
-	  bb->count.dump (file);
+	  bb->count.dump (file, fun);
 	  fprintf (file, "\n");
 	}
     }
@@ -525,7 +525,7 @@ dump_edge_info (FILE *file, edge e, dump_flags_t flags, int do_succ)
   if (e->count ().initialized_p () && do_details)
     {
       fputs (" count:", file);
-      e->count ().dump (file);
+      e->count ().dump (file, cfun);
     }
 
   if (e->flags && do_details)
@@ -808,7 +808,7 @@ dump_bb_info (FILE *outf, basic_block bb, int indent, dump_flags_t flags,
 	  if (bb->count.initialized_p ())
 	    {
 	      fputs (", count ", outf);
-	      bb->count.dump (outf);
+	      bb->count.dump (outf, cfun);
 	    }
 	  if (maybe_hot_bb_p (fun, bb))
 	    fputs (", maybe hot", outf);
diff --git a/gcc/profile-count.cc b/gcc/profile-count.cc
index 6bf9700d8db..2c07ebc5942 100644
--- a/gcc/profile-count.cc
+++ b/gcc/profile-count.cc
@@ -94,7 +94,7 @@ profile_count::dump (char *buffer, struct function *fun) const
   else if (fun && initialized_p ()
 	   && fun->cfg
 	   && ENTRY_BLOCK_PTR_FOR_FN (fun)->count.initialized_p ())
-    sprintf (buffer, "%" PRId64 " (%s freq %.4f)", m_val,
+    sprintf (buffer, "%" PRId64 " (%s, freq %.4f)", m_val,
 	     profile_quality_display_names[m_quality],
 	     to_sreal_scale (ENTRY_BLOCK_PTR_FOR_FN (fun)->count).to_double ());
   else
diff --git a/gcc/testsuite/gcc.dg/predict-22.c b/gcc/testsuite/gcc.dg/predict-22.c
index f14c2b68861..1aed03fae79 100644
--- a/gcc/testsuite/gcc.dg/predict-22.c
+++ b/gcc/testsuite/gcc.dg/predict-22.c
@@ -55,5 +55,5 @@ foo (int x, int y, int z)
   baz (&f);
 }
 /* { dg-final { scan-tree-dump-times "Invalid sum" 0 "optimized"} } */
-/* { dg-final { scan-tree-dump-times "count 0 .precise.," 1 "optimized"} } */
+/* { dg-final { scan-tree-dump-times "count 0 .precise" 1 "optimized"} } */
 /* { dg-final { scan-rtl-dump-times "COLD_PARTITION" 1 "bbpart"} } */