Hi
this patch turns final to use counts rather than frequencies when deciding
on alignments.
Honza
* final.c (compute_alignments): Use counts rather than frequencies.
Index: final.c
===================================================================
--- final.c (revision 254767)
+++ final.c (working copy)
@@ -661,16 +661,13 @@ insn_current_reference_address (rtx_insn
}
}
-/* Compute branch alignments based on frequency information in the
- CFG. */
+/* Compute branch alignments based on CFG profile. */
unsigned int
compute_alignments (void)
{
int log, max_skip, max_log;
basic_block bb;
- int freq_max = 0;
- int freq_threshold = 0;
if (label_align)
{
@@ -693,17 +690,19 @@ compute_alignments (void)
flow_loops_dump (dump_file, NULL, 1);
}
loop_optimizer_init (AVOID_CFG_MODIFICATIONS);
- FOR_EACH_BB_FN (bb, cfun)
- if (bb->count.to_frequency (cfun) > freq_max)
- freq_max = bb->count.to_frequency (cfun);
- freq_threshold = freq_max / PARAM_VALUE (PARAM_ALIGN_THRESHOLD);
+ profile_count count_threshold = cfun->cfg->count_max.apply_scale
+ (1, PARAM_VALUE (PARAM_ALIGN_THRESHOLD));
if (dump_file)
- fprintf (dump_file, "freq_max: %i\n",freq_max);
+ {
+ fprintf (dump_file, "count_max: ");
+ cfun->cfg->count_max.dump (dump_file);
+ fprintf (dump_file, "\n");
+ }
FOR_EACH_BB_FN (bb, cfun)
{
rtx_insn *label = BB_HEAD (bb);
- int fallthru_frequency = 0, branch_frequency = 0, has_fallthru = 0;
+ bool has_fallthru = 0;
edge e;
edge_iterator ei;
@@ -712,35 +711,41 @@ compute_alignments (void)
{
if (dump_file)
fprintf (dump_file,
- "BB %4i freq %4i loop %2i loop_depth %2i skipped.\n",
- bb->index, bb->count.to_frequency (cfun),
+ "BB %4i loop %2i loop_depth %2i skipped.\n",
+ bb->index,
bb->loop_father->num,
bb_loop_depth (bb));
continue;
}
max_log = LABEL_ALIGN (label);
max_skip = targetm.asm_out.label_align_max_skip (label);
+ profile_count fallthru_count = profile_count::zero ();
+ profile_count branch_count = profile_count::zero ();
FOR_EACH_EDGE (e, ei, bb->preds)
{
if (e->flags & EDGE_FALLTHRU)
- has_fallthru = 1, fallthru_frequency += EDGE_FREQUENCY (e);
+ has_fallthru = 1, fallthru_count += e->count ();
else
- branch_frequency += EDGE_FREQUENCY (e);
+ branch_count += e->count ();
}
if (dump_file)
{
- fprintf (dump_file, "BB %4i freq %4i loop %2i loop_depth"
- " %2i fall %4i branch %4i",
- bb->index, bb->count.to_frequency (cfun),
bb->loop_father->num,
- bb_loop_depth (bb),
- fallthru_frequency, branch_frequency);
+ fprintf (dump_file, "BB %4i loop %2i loop_depth"
+ " %2i fall ",
+ bb->index, bb->loop_father->num,
+ bb_loop_depth (bb));
+ fallthru_count.dump (dump_file);
+ fprintf (dump_file, " branch ");
+ branch_count.dump (dump_file);
if (!bb->loop_father->inner && bb->loop_father->num)
fprintf (dump_file, " inner_loop");
if (bb->loop_father->header == bb)
fprintf (dump_file, " loop_header");
fprintf (dump_file, "\n");
}
+ if (!fallthru_count.initialized_p () || !branch_count.initialized_p ())
+ continue;
/* There are two purposes to align block with no fallthru incoming edge:
1) to avoid fetch stalls when branch destination is near cache boundary
@@ -753,11 +758,11 @@ compute_alignments (void)
when function is called. */
if (!has_fallthru
- && (branch_frequency > freq_threshold
- || (bb->count.to_frequency (cfun)
- > bb->prev_bb->count.to_frequency (cfun) * 10
- && (bb->prev_bb->count.to_frequency (cfun)
- <= ENTRY_BLOCK_PTR_FOR_FN (cfun)->count.to_frequency
(cfun) / 2))))
+ && (branch_count > count_threshold
+ || (bb->count > bb->prev_bb->count.apply_scale (10, 1)
+ && (bb->prev_bb->count
+ <= ENTRY_BLOCK_PTR_FOR_FN (cfun)
+ ->count.apply_scale (1, 2)))))
{
log = JUMP_ALIGN (label);
if (dump_file)
@@ -774,9 +779,10 @@ compute_alignments (void)
&& !(single_succ_p (bb)
&& single_succ (bb) == EXIT_BLOCK_PTR_FOR_FN (cfun))
&& optimize_bb_for_speed_p (bb)
- && branch_frequency + fallthru_frequency > freq_threshold
- && (branch_frequency
- > fallthru_frequency * PARAM_VALUE (PARAM_ALIGN_LOOP_ITERATIONS)))
+ && branch_count + fallthru_count > count_threshold
+ && (branch_count
+ > fallthru_count.apply_scale
+ (PARAM_VALUE (PARAM_ALIGN_LOOP_ITERATIONS), 1)))
{
log = LOOP_ALIGN (label);
if (dump_file)
