Propagate out ncopies == 1.
* tree-vect-stmts.cc (vectorizable_load): Step 3.
---
gcc/tree-vect-stmts.cc | 46 +++++++++++-------------------------------
1 file changed, 12 insertions(+), 34 deletions(-)
diff --git a/gcc/tree-vect-stmts.cc b/gcc/tree-vect-stmts.cc
index eca7e70adf4..2efa000034c 100644
--- a/gcc/tree-vect-stmts.cc
+++ b/gcc/tree-vect-stmts.cc
@@ -9836,7 +9836,6 @@ vectorizable_load (vec_info *vinfo,
tree dataref_ptr = NULL_TREE;
tree dataref_offset = NULL_TREE;
gimple *ptr_incr = NULL;
- int ncopies;
int i, j;
unsigned int group_size;
poly_uint64 group_gap_adj;
@@ -9938,16 +9937,9 @@ vectorizable_load (vec_info *vinfo,
else
vf = 1;
- /* Multiple types in SLP are handled by creating the appropriate number of
- vectorized stmts for each SLP node. Hence, NCOPIES is always 1 in
- case of SLP. */
- ncopies = 1;
-
- gcc_assert (ncopies >= 1);
-
/* FORNOW. This restriction should be relaxed. */
if (nested_in_vect_loop
- && (ncopies > 1 || SLP_TREE_NUMBER_OF_VEC_STMTS (slp_node) > 1))
+ && SLP_TREE_NUMBER_OF_VEC_STMTS (slp_node) > 1)
{
if (dump_enabled_p ())
dump_printf_loc (MSG_MISSED_OPTIMIZATION, vect_location,
@@ -9955,20 +9947,6 @@ vectorizable_load (vec_info *vinfo,
return false;
}
- /* Invalidate assumptions made by dependence analysis when vectorization
- on the unrolled body effectively re-orders stmts. */
- if (ncopies > 1
- && STMT_VINFO_MIN_NEG_DIST (stmt_info) != 0
- && maybe_gt (LOOP_VINFO_VECT_FACTOR (loop_vinfo),
- STMT_VINFO_MIN_NEG_DIST (stmt_info)))
- {
- if (dump_enabled_p ())
- dump_printf_loc (MSG_MISSED_OPTIMIZATION, vect_location,
- "cannot perform implicit CSE when unrolling "
- "with negative dependence distance\n");
- return false;
- }
-
elem_type = TREE_TYPE (vectype);
mode = TYPE_MODE (vectype);
@@ -10018,7 +9996,7 @@ vectorizable_load (vec_info *vinfo,
int maskload_elsval = 0;
bool need_zeroing = false;
if (!get_load_store_type (vinfo, stmt_info, vectype, slp_node, mask,
VLS_LOAD,
- ncopies, &memory_access_type, &poffset,
+ 1, &memory_access_type, &poffset,
&alignment_support_scheme, &misalignment, &gs_info,
&lanes_ifn, &elsvals))
return false;
@@ -10194,8 +10172,7 @@ vectorizable_load (vec_info *vinfo,
gcc_assert (memory_access_type == SLP_TREE_MEMORY_ACCESS_TYPE (slp_node));
if (dump_enabled_p () && !costing_p)
- dump_printf_loc (MSG_NOTE, vect_location,
- "transform load. ncopies = %d\n", ncopies);
+ dump_printf_loc (MSG_NOTE, vect_location, "transform load.\n");
/* Transform. */
@@ -10443,6 +10420,7 @@ vectorizable_load (vec_info *vinfo,
/* For SLP permutation support we need to load the whole group,
not only the number of vector stmts the permutation result
fits in. */
+ int ncopies;
if (slp_perm)
{
/* We don't yet generate SLP_TREE_LOAD_PERMUTATIONs for
@@ -10869,7 +10847,7 @@ vectorizable_load (vec_info *vinfo,
/* For costing some adjacent vector loads, we'd like to cost with
the total number of them once instead of cost each one by one. */
unsigned int n_adjacent_loads = 0;
- ncopies = slp_node->vec_stmts_size / group_size;
+ int ncopies = slp_node->vec_stmts_size / group_size;
for (j = 0; j < ncopies; j++)
{
if (costing_p)
@@ -11029,7 +11007,7 @@ vectorizable_load (vec_info *vinfo,
gcc_assert (!grouped_load && !slp_perm);
unsigned int inside_cost = 0, prologue_cost = 0;
- for (j = 0; j < ncopies; j++)
+ for (j = 0; j < 1; j++)
{
/* 1. Create the vector or array pointer update chain. */
if (j == 0 && !costing_p)
@@ -11065,7 +11043,7 @@ vectorizable_load (vec_info *vinfo,
if (loop_masks)
final_mask
= vect_get_loop_mask (loop_vinfo, gsi, loop_masks,
- vec_num * ncopies, vectype,
+ vec_num, vectype,
vec_num * j + i);
if (vec_mask)
final_mask = prepare_vec_mask (loop_vinfo, mask_vectype,
@@ -11098,7 +11076,7 @@ vectorizable_load (vec_info *vinfo,
if (loop_lens)
final_len
= vect_get_loop_len (loop_vinfo, gsi, loop_lens,
- vec_num * ncopies, vectype,
+ vec_num, vectype,
vec_num * j + i, 1);
else
final_len
@@ -11394,7 +11372,7 @@ vectorizable_load (vec_info *vinfo,
/* For costing some adjacent vector loads, we'd like to cost with
the total number of them once instead of cost each one by one. */
unsigned int n_adjacent_loads = 0;
- for (j = 0; j < ncopies; j++)
+ for (j = 0; j < 1; j++)
{
/* 1. Create the vector or array pointer update chain. */
if (j == 0 && !costing_p)
@@ -11475,7 +11453,7 @@ vectorizable_load (vec_info *vinfo,
vec_mask = vec_masks[vec_num * j + i];
if (loop_masks)
final_mask = vect_get_loop_mask (loop_vinfo, gsi, loop_masks,
- vec_num * ncopies, vectype,
+ vec_num, vectype,
vec_num * j + i);
if (vec_mask)
final_mask = prepare_vec_mask (loop_vinfo, mask_vectype,
@@ -11526,7 +11504,7 @@ vectorizable_load (vec_info *vinfo,
unsigned factor
= (new_ovmode == vmode) ? 1 : GET_MODE_UNIT_SIZE (vmode);
final_len = vect_get_loop_len (loop_vinfo, gsi, loop_lens,
- vec_num * ncopies, vectype,
+ vec_num, vectype,
vec_num * j + i, factor);
}
else if (final_mask)
@@ -11942,7 +11920,7 @@ vectorizable_load (vec_info *vinfo,
if (alignment_support_scheme == dr_explicit_realign_optimized)
{
gcc_assert (phi);
- if (i == vec_num - 1 && j == ncopies - 1)
+ if (i == vec_num - 1 && j == 0)
add_phi_arg (phi, lsq, loop_latch_edge (containing_loop),
UNKNOWN_LOCATION);
msq = lsq;
--
2.43.0
