If one of the to-be-converted SETs requires the original comparison
(i.e. in order to generate a min/max insn) but no other insn after it
does, we can omit creating temporaries, thus facilitating costing.
---
gcc/ifcvt.c | 33 +++++++++++++++++++++++++++++++--
1 file changed, 31 insertions(+), 2 deletions(-)
diff --git a/gcc/ifcvt.c b/gcc/ifcvt.c
index d1e7db1ee27..3be5bb131df 100644
--- a/gcc/ifcvt.c
+++ b/gcc/ifcvt.c
@@ -3262,6 +3262,11 @@ noce_convert_multiple_sets (struct noce_if_info *if_info)
need_cmov_or_rewire (then_bb, &need_no_cmov, &rewired_src);
+ int last_needs_comparison = -1;
+ bool second_try = false;
+
+restart:
+
FOR_BB_INSNS (then_bb, insn)
{
/* Skip over non-insns. */
@@ -3305,8 +3310,12 @@ noce_convert_multiple_sets (struct noce_if_info *if_info)
Therefore we introduce a temporary every time we are about to
overwrite a variable used in the check. Costing of a sequence with
these is going to be inaccurate so only use temporaries when
- needed. */
- if (reg_overlap_mentioned_p (target, cond))
+ needed.
+
+ If performing a second try, we know how many insns require a
+ temporary. For the last of these, we can omit creating one. */
+ if (reg_overlap_mentioned_p (target, cond)
+ && (!second_try || count < last_needs_comparison))
temp = gen_reg_rtx (GET_MODE (target));
else
temp = target;
@@ -3389,6 +3398,8 @@ noce_convert_multiple_sets (struct noce_if_info *if_info)
{
seq = seq1;
temp_dest = temp_dest1;
+ if (!second_try)
+ last_needs_comparison = count;
}
else if (seq2 != NULL_RTX)
{
@@ -3412,6 +3423,24 @@ noce_convert_multiple_sets (struct noce_if_info *if_info)
unmodified_insns.safe_push (insn);
}
+ /* If there are insns that overwrite part of the initial
+ comparison, we can still omit creating temporaries for
+ the last of them.
+ As the second try will always create a less expensive,
+ valid sequence, we do not need to compare and can discard
+ the first one. */
+ if (!second_try && last_needs_comparison >= 0)
+ {
+ end_sequence ();
+ start_sequence ();
+ count = 0;
+ targets.truncate (0);
+ temporaries.truncate (0);
+ unmodified_insns.truncate (0);
+ second_try = true;
+ goto restart;
+ }
+
/* We must have seen some sort of insn to insert, otherwise we were
given an empty BB to convert, and we can't handle that. */
gcc_assert (!unmodified_insns.is_empty ());
--
2.31.1
