This fixes PR56270 - when two SLP instances share a load
we fail to properly initialize the vectorized SLP stmts.
In fact, there is no support in SLP to "share" vectorized
code between instances - the only support that's explicitely
wired in is to have different permutations of a load inside
a single SLP instance.
Without digging further into cross-instance SLP vectorized
code sharing (or even intra-instance sharing) the following
avoids the special early-out cross-instance by resetting
the instances loads vector-stmts after scheduling it.
Another fix would possibly to do
/* Check if the chain of loads is already vectorized. */
if (STMT_VINFO_VEC_STMT (vinfo_for_stmt (first_stmt)))
{
*vec_stmt = STMT_VINFO_VEC_STMT (stmt_info);
return true;
}
only for !slp and for SLP figure out an equivalent condition
using SLP_TREE_VEC_STMTS.
Jakub, do you have any insights into this code, especially
what kind of permutations we support?
Bootstrap and regtest running on x86_64-unknown-linux-gnu.
Thanks,
Richard.
2013-03-04 Richard Biener <rguent...@suse.de>
PR tree-optimization/56270
* tree-vect-slp.c (vect_schedule_slp): Clear vectorized stmts
of loads after scheduling an SLP instance.
* gcc.dg/vect/slp-38.c: New testcase.
Index: gcc/tree-vect-slp.c
===================================================================
*** gcc/tree-vect-slp.c (revision 196423)
--- gcc/tree-vect-slp.c (working copy)
*************** vect_schedule_slp (loop_vec_info loop_vi
*** 3138,3144 ****
{
vec<slp_instance> slp_instances;
slp_instance instance;
! unsigned int i, vf;
bool is_store = false;
if (loop_vinfo)
--- 3148,3155 ----
{
vec<slp_instance> slp_instances;
slp_instance instance;
! slp_tree loads_node;
! unsigned int i, j, vf;
bool is_store = false;
if (loop_vinfo)
*************** vect_schedule_slp (loop_vec_info loop_vi
*** 3157,3162 ****
--- 3168,3181 ----
/* Schedule the tree of INSTANCE. */
is_store = vect_schedule_slp_instance (SLP_INSTANCE_TREE (instance),
instance, vf);
+
+ /* Clear STMT_VINFO_VEC_STMT of all loads. With shared loads
+ between SLP instances we fail to properly initialize the
+ vectorized SLP stmts and confuse different load permutations. */
+ FOR_EACH_VEC_ELT (SLP_INSTANCE_LOADS (instance), j, loads_node)
+ STMT_VINFO_VEC_STMT
+ (vinfo_for_stmt (SLP_TREE_SCALAR_STMTS (loads_node)[0])) = NULL;
+
if (dump_enabled_p ())
dump_printf_loc (MSG_NOTE, vect_location,
"vectorizing stmts using SLP.");
Index: gcc/testsuite/gcc.dg/vect/slp-38.c
===================================================================
*** gcc/testsuite/gcc.dg/vect/slp-38.c (revision 0)
--- gcc/testsuite/gcc.dg/vect/slp-38.c (working copy)
***************
*** 0 ****
--- 1,24 ----
+ /* { dg-do compile } */
+
+ typedef struct {
+ float l, h;
+ } tFPinterval;
+
+ tFPinterval X[1024];
+ tFPinterval Y[1024];
+ tFPinterval Z[1024];
+
+ void Compute(void)
+ {
+ int d;
+ for (d= 0; d < 1024; d++)
+ {
+ Y[d].l= X[d].l + X[d].h;
+ Y[d].h= Y[d].l;
+ Z[d].l= X[d].l;
+ Z[d].h= X[d].h;
+ }
+ }
+
+ /* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 1
"vect" { target { vect_float && vect_perm } } } } */
+ /* { dg-final { cleanup-tree-dump "vect" } } */
