[ftracer] Add caching of can_duplicate_bb_p
The fix "[omp, ftracer] Don't duplicate blocks in SIMT region" adds iteration
over insns in ignore_bb_p, which makes it more expensive.
Counteract this by piggybacking the computation of can_duplicate_bb_p onto
count_insns, which is called at the start of ftracer.
Bootstrapped and reg-tested on x86_64-linux.
gcc/ChangeLog:
2020-10-05 Tom de Vries <tdevries@suse.de>
* tracer.c (count_insns): Rename to ...
(analyze_bb): ... this.
(cache_can_duplicate_bb_p, cached_can_duplicate_bb_p): New function.
(ignore_bb_p): Use cached_can_duplicate_bb_p.
(tail_duplicate): Call cache_can_duplicate_bb_p.
---
gcc/tracer.c | 47 +++++++++++++++++++++++++++++++++++++++++------
1 file changed, 41 insertions(+), 6 deletions(-)
@@ -53,7 +53,7 @@
#include "fibonacci_heap.h"
#include "tracer.h"
-static int count_insns (basic_block);
+static void analyze_bb (basic_block, int *);
static bool better_p (const_edge, const_edge);
static edge find_best_successor (basic_block);
static edge find_best_predecessor (basic_block);
@@ -143,6 +143,33 @@ can_duplicate_bb_p (const_basic_block bb)
return true;
}
+static sbitmap can_duplicate_bb;
+
+/* Cache VAL as value of can_duplicate_bb_p for BB. */
+static inline void
+cache_can_duplicate_bb_p (const_basic_block bb, bool val)
+{
+ if (val)
+ bitmap_set_bit (can_duplicate_bb, bb->index);
+}
+
+/* Return cached value of can_duplicate_bb_p for BB. */
+static bool
+cached_can_duplicate_bb_p (const_basic_block bb)
+{
+ if (can_duplicate_bb)
+ {
+ unsigned int size = SBITMAP_SIZE (can_duplicate_bb);
+ if ((unsigned int)bb->index < size)
+ return bitmap_bit_p (can_duplicate_bb, bb->index);
+
+ /* Assume added bb's should not be duplicated. */
+ return false;
+ }
+
+ return can_duplicate_bb_p (bb);
+}
+
/* Return true if we should ignore the basic block for purposes of tracing. */
bool
ignore_bb_p (const_basic_block bb)
@@ -152,24 +179,27 @@ ignore_bb_p (const_basic_block bb)
if (optimize_bb_for_size_p (bb))
return true;
- return !can_duplicate_bb_p (bb);
+ return !cached_can_duplicate_bb_p (bb);
}
/* Return number of instructions in the block. */
-static int
-count_insns (basic_block bb)
+static void
+analyze_bb (basic_block bb, int *count)
{
gimple_stmt_iterator gsi;
gimple *stmt;
int n = 0;
+ bool can_duplicate = can_duplicate_bb_no_insn_iter_p (bb);
for (gsi = gsi_start_bb (bb); !gsi_end_p (gsi); gsi_next (&gsi))
{
stmt = gsi_stmt (gsi);
n += estimate_num_insns (stmt, &eni_size_weights);
+ can_duplicate = can_duplicate && can_duplicate_insn_p (stmt);
}
- return n;
+ *count = n;
+ cache_can_duplicate_bb_p (bb, can_duplicate);
}
/* Return true if E1 is more frequent than E2. */
@@ -317,6 +347,8 @@ tail_duplicate (void)
resize it. */
bb_seen = sbitmap_alloc (last_basic_block_for_fn (cfun) * 2);
bitmap_clear (bb_seen);
+ can_duplicate_bb = sbitmap_alloc (last_basic_block_for_fn (cfun));
+ bitmap_clear (can_duplicate_bb);
initialize_original_copy_tables ();
if (profile_info && profile_status_for_fn (cfun) == PROFILE_READ)
@@ -330,7 +362,8 @@ tail_duplicate (void)
FOR_EACH_BB_FN (bb, cfun)
{
- int n = count_insns (bb);
+ int n;
+ analyze_bb (bb, &n);
if (!ignore_bb_p (bb))
blocks[bb->index] = heap.insert (-bb->count.to_frequency (cfun), bb);
@@ -420,6 +453,8 @@ tail_duplicate (void)
free_original_copy_tables ();
sbitmap_free (bb_seen);
+ sbitmap_free (can_duplicate_bb);
+ can_duplicate_bb = NULL;
free (trace);
free (counts);