re PR rtl-optimization/88751 (Performance regression reload vs lra)

Fix PR88751

This patch implements a small improvement for the heuristic in lra
which decides when it has to activate the simpler register allocation
algorithm.

gcc/ChangeLog:

2019-06-06  Andreas Krebbel  <krebbel@linux.ibm.com>

	PR rtl-optimization/88751
	* ira.c (ira): Use the number of the actually referenced registers
	when calculating the threshold.

From-SVN: r271996

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 9dbe57a131ae1ef9c4741245a3e84864dacea134..012af38d631863087f1ea33c942fbfd723c8fcd6 100644 (file)
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,9 @@
+2019-06-06  Andreas Krebbel  <krebbel@linux.ibm.com>
+
+       PR rtl-optimization/88751
+       * ira.c (ira): Use the number of the actually referenced registers
+       when calculating the threshold.
+
 2019-06-06  Jakub Jelinek  <jakub@redhat.com>
 
        * configure: Regenerate.

diff --git a/gcc/ira.c b/gcc/ira.c
index 4a14fb315833ab36829516f5624e1da3fc6d6f5c..725636d8dc5429f362fb666a2a84acae8766a314 100644 (file)
--- a/gcc/ira.c
+++ b/gcc/ira.c
@@ -5198,6 +5198,8 @@ ira (FILE *f)
   int ira_max_point_before_emit;
   bool saved_flag_caller_saves = flag_caller_saves;
   enum ira_region saved_flag_ira_region = flag_ira_region;
+  unsigned int i;
+  int num_used_regs = 0;
 
   clear_bb_flags ();
 
@@ -5213,12 +5215,17 @@ ira (FILE *f)
 
   ira_conflicts_p = optimize > 0;
 
+  /* Determine the number of pseudos actually requiring coloring.  */
+  for (i = FIRST_PSEUDO_REGISTER; i < DF_REG_SIZE (df); i++)
+    num_used_regs += !!(DF_REG_USE_COUNT (i) + DF_REG_DEF_COUNT (i));
+
   /* If there are too many pseudos and/or basic blocks (e.g. 10K
      pseudos and 10K blocks or 100K pseudos and 1K blocks), we will
      use simplified and faster algorithms in LRA.  */
   lra_simple_p
     = (ira_use_lra_p
-       && max_reg_num () >= (1 << 26) / last_basic_block_for_fn (cfun));
+       && num_used_regs >= (1 << 26) / last_basic_block_for_fn (cfun));
+
   if (lra_simple_p)
     {
       /* It permits to skip live range splitting in LRA.  */