The following fixes a latent issue in loop distribution catched by
the fake edge placement adjustment.
Bootstrapped and tested on x86_64-unknown-linux-gnu, applied.
Richard.
2016-05-17 Richard Biener <rguent...@suse.de>
PR tree-optimization/71132
* tree-loop-distribution.c (create_rdg_cd_edges): Pass in loop.
Only add control dependences for blocks in the loop.
(build_rdg): Adjust.
(generate_code_for_partition): Return whether loop should
be destroyed and delay that.
(distribute_loop): Likewise.
(pass_loop_distribution::execute): Record loops to be destroyed
and perform delayed destroying of loops.
* gcc.dg/torture/pr71132.c: New testcase.
Index: gcc/tree-loop-distribution.c
===================================================================
*** gcc/tree-loop-distribution.c (revision 236309)
--- gcc/tree-loop-distribution.c (working copy)
*************** create_rdg_flow_edges (struct graph *rdg
*** 312,318 ****
/* Creates the edges of the reduced dependence graph RDG. */
static void
! create_rdg_cd_edges (struct graph *rdg, control_dependences *cd)
{
int i;
--- 315,321 ----
/* Creates the edges of the reduced dependence graph RDG. */
static void
! create_rdg_cd_edges (struct graph *rdg, control_dependences *cd, loop_p loop)
{
int i;
*************** create_rdg_cd_edges (struct graph *rdg,
*** 324,329 ****
--- 327,333 ----
edge_iterator ei;
edge e;
FOR_EACH_EDGE (e, ei, gimple_bb (stmt)->preds)
+ if (flow_bb_inside_loop_p (loop, e->src))
create_edge_for_control_dependence (rdg, e->src, i, cd);
}
else
*************** build_rdg (vec<loop_p> loop_nest, contro
*** 455,461 ****
create_rdg_flow_edges (rdg);
if (cd)
! create_rdg_cd_edges (rdg, cd);
datarefs.release ();
--- 459,465 ----
create_rdg_flow_edges (rdg);
if (cd)
! create_rdg_cd_edges (rdg, cd, loop_nest[0]);
datarefs.release ();
*************** destroy_loop (struct loop *loop)
*** 917,925 ****
recompute_dominator (CDI_DOMINATORS, dest));
}
! /* Generates code for PARTITION. */
! static void
generate_code_for_partition (struct loop *loop,
partition *partition, bool copy_p)
{
--- 921,929 ----
recompute_dominator (CDI_DOMINATORS, dest));
}
! /* Generates code for PARTITION. Return whether LOOP needs to be destroyed.
*/
! static bool
generate_code_for_partition (struct loop *loop,
partition *partition, bool copy_p)
{
*************** generate_code_for_partition (struct loop
*** 930,936 ****
gcc_assert (!partition_reduction_p (partition)
|| !copy_p);
generate_loops_for_partition (loop, partition, copy_p);
! return;
case PKIND_MEMSET:
generate_memset_builtin (loop, partition);
--- 934,940 ----
gcc_assert (!partition_reduction_p (partition)
|| !copy_p);
generate_loops_for_partition (loop, partition, copy_p);
! return false;
case PKIND_MEMSET:
generate_memset_builtin (loop, partition);
*************** generate_code_for_partition (struct loop
*** 947,953 ****
/* Common tail for partitions we turn into a call. If this was the last
partition for which we generate code, we have to destroy the loop. */
if (!copy_p)
! destroy_loop (loop);
}
--- 951,958 ----
/* Common tail for partitions we turn into a call. If this was the last
partition for which we generate code, we have to destroy the loop. */
if (!copy_p)
! return true;
! return false;
}
*************** pgcmp (const void *v1_, const void *v2_)
*** 1397,1407 ****
/* Distributes the code from LOOP in such a way that producer
statements are placed before consumer statements. Tries to separate
only the statements from STMTS into separate loops.
! Returns the number of distributed loops. */
static int
distribute_loop (struct loop *loop, vec<gimple *> stmts,
! control_dependences *cd, int *nb_calls)
{
struct graph *rdg;
partition *partition;
--- 1412,1423 ----
/* Distributes the code from LOOP in such a way that producer
statements are placed before consumer statements. Tries to separate
only the statements from STMTS into separate loops.
! Returns the number of distributed loops. Set *DESTROY_P to whether
! LOOP needs to be destroyed. */
static int
distribute_loop (struct loop *loop, vec<gimple *> stmts,
! control_dependences *cd, int *nb_calls, bool *destroy_p)
{
struct graph *rdg;
partition *partition;
*************** distribute_loop (struct loop *loop, vec<
*** 1644,1654 ****
if (dump_file && (dump_flags & TDF_DETAILS))
dump_rdg_partitions (dump_file, partitions);
FOR_EACH_VEC_ELT (partitions, i, partition)
{
if (partition_builtin_p (partition))
(*nb_calls)++;
! generate_code_for_partition (loop, partition, i < nbp - 1);
}
ldist_done:
--- 1660,1671 ----
if (dump_file && (dump_flags & TDF_DETAILS))
dump_rdg_partitions (dump_file, partitions);
+ *destroy_p = false;
FOR_EACH_VEC_ELT (partitions, i, partition)
{
if (partition_builtin_p (partition))
(*nb_calls)++;
! *destroy_p |= generate_code_for_partition (loop, partition, i < nbp -
1);
}
ldist_done:
*************** pass_loop_distribution::execute (functio
*** 1702,1707 ****
--- 1719,1725 ----
bool changed = false;
basic_block bb;
control_dependences *cd = NULL;
+ auto_vec<loop_p> loops_to_be_destroyed;
FOR_ALL_BB_FN (bb, fun)
{
*************** out:
*** 1787,1794 ****
cd = new control_dependences (create_edge_list ());
free_dominance_info (CDI_POST_DOMINATORS);
}
nb_generated_loops = distribute_loop (loop, work_list, cd,
! &nb_generated_calls);
}
if (nb_generated_loops + nb_generated_calls > 0)
--- 1805,1816 ----
cd = new control_dependences (create_edge_list ());
free_dominance_info (CDI_POST_DOMINATORS);
}
+ bool destroy_p;
nb_generated_loops = distribute_loop (loop, work_list, cd,
! &nb_generated_calls,
! &destroy_p);
! if (destroy_p)
! loops_to_be_destroyed.safe_push (loop);
}
if (nb_generated_loops + nb_generated_calls > 0)
*************** out:
*** 1806,1811 ****
--- 1828,1839 ----
if (cd)
delete cd;
+ /* Destroy loop bodies that could not be reused. Do this late as we
+ otherwise can end up refering to stale data in control dependences. */
+ unsigned i;
+ FOR_EACH_VEC_ELT (loops_to_be_destroyed, i, loop)
+ destroy_loop (loop);
+
if (changed)
{
/* Cached scalar evolutions now may refer to wrong or non-existing
Index: gcc/testsuite/gcc.dg/torture/pr71132.c
===================================================================
*** gcc/testsuite/gcc.dg/torture/pr71132.c (revision 0)
--- gcc/testsuite/gcc.dg/torture/pr71132.c (working copy)
***************
*** 0 ****
--- 1,24 ----
+ /* { dg-do compile } */
+
+ typedef unsigned size_t;
+ struct {
+ unsigned char buf[sizeof(long)];
+ } a;
+ size_t b;
+ int main()
+ {
+ size_t c, i;
+ unsigned char *d;
+ for (; c < sizeof(long);)
+ {
+ d = a.buf;
+ b = 0;
+ for (; b < i; b++)
+ *d++ = '\0';
+ for (; c < b; c++)
+ *d++ = 'a';
+ c = 0;
+ for (; i < sizeof(long); i++)
+ ;
+ }
+ }
