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:

2019-09-20  Andreas Krebbel  <krebbel@linux.ibm.com>

	Backport from mainline
	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: r275993

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index ad4384a37c3b29d818953476de8f266adac7249e..533ab1c3f13afda0c08709a2a32deda80945539f 100644 (file)
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,12 @@
+2019-09-20  Andreas Krebbel  <krebbel@linux.ibm.com>
+
+       Backport from mainline
+       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.
+
 2019-09-11  Eric Botcazou  <ebotcazou@adacore.com>
 
        PR rtl-optimization/89795

diff --git a/gcc/ira.c b/gcc/ira.c
index 5265ab1748803b40972888a7bc8b24faec4e264a..4925cc713b065a60686e782467df589f512d6cb4 100644 (file)
--- a/gcc/ira.c
+++ b/gcc/ira.c
@@ -5160,6 +5160,8 @@ 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 ();
 
@@ -5175,12 +5177,17 @@ 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.  */