Elide loops over ncopies.
* tree-vect-stmts.cc (vectorizable_load):
---
gcc/tree-vect-stmts.cc | 54 ++++++++++++++++--------------------------
1 file changed, 20 insertions(+), 34 deletions(-)
diff --git a/gcc/tree-vect-stmts.cc b/gcc/tree-vect-stmts.cc
index 2efa000034c..717d4694b88 100644
--- a/gcc/tree-vect-stmts.cc
+++ b/gcc/tree-vect-stmts.cc
@@ -11007,10 +11007,9 @@ vectorizable_load (vec_info *vinfo,
gcc_assert (!grouped_load && !slp_perm);
unsigned int inside_cost = 0, prologue_cost = 0;
- for (j = 0; j < 1; j++)
{
/* 1. Create the vector or array pointer update chain. */
- if (j == 0 && !costing_p)
+ if (!costing_p)
{
if (STMT_VINFO_GATHER_SCATTER_P (stmt_info))
vect_get_gather_scatter_ops (loop_vinfo, loop, stmt_info,
@@ -11022,13 +11021,6 @@ vectorizable_load (vec_info *vinfo,
at_loop, offset, &dummy, gsi,
&ptr_incr, false, bump);
}
- else if (!costing_p)
- {
- gcc_assert (!LOOP_VINFO_USING_SELECT_VL_P (loop_vinfo));
- if (!STMT_VINFO_GATHER_SCATTER_P (stmt_info))
- dataref_ptr = bump_vector_ptr (vinfo, dataref_ptr, ptr_incr,
- gsi, stmt_info, bump);
- }
gimple *new_stmt = NULL;
for (i = 0; i < vec_num; i++)
@@ -11039,12 +11031,11 @@ vectorizable_load (vec_info *vinfo,
if (!costing_p)
{
if (mask)
- vec_mask = vec_masks[vec_num * j + i];
+ vec_mask = vec_masks[i];
if (loop_masks)
final_mask
= vect_get_loop_mask (loop_vinfo, gsi, loop_masks,
- vec_num, vectype,
- vec_num * j + i);
+ vec_num, vectype, i);
if (vec_mask)
final_mask = prepare_vec_mask (loop_vinfo, mask_vectype,
final_mask, vec_mask, gsi);
@@ -11067,7 +11058,7 @@ vectorizable_load (vec_info *vinfo,
continue;
}
if (STMT_VINFO_GATHER_SCATTER_P (stmt_info))
- vec_offset = vec_offsets[vec_num * j + i];
+ vec_offset = vec_offsets[i];
tree zero = build_zero_cst (vectype);
tree scale = size_int (gs_info.scale);
@@ -11076,8 +11067,7 @@ vectorizable_load (vec_info *vinfo,
if (loop_lens)
final_len
= vect_get_loop_len (loop_vinfo, gsi, loop_lens,
- vec_num, vectype,
- vec_num * j + i, 1);
+ vec_num, vectype, i, 1);
else
final_len
= build_int_cst (sizetype,
@@ -11148,7 +11138,7 @@ vectorizable_load (vec_info *vinfo,
{
new_stmt = vect_build_one_gather_load_call
(vinfo, stmt_info, gsi, &gs_info,
- dataref_ptr, vec_offsets[vec_num * j + i],
+ dataref_ptr, vec_offsets[i],
final_mask);
data_ref = NULL_TREE;
}
@@ -11159,7 +11149,7 @@ vectorizable_load (vec_info *vinfo,
data with just the lower lanes filled. */
new_stmt = vect_build_one_gather_load_call
(vinfo, stmt_info, gsi, &gs_info,
- dataref_ptr, vec_offsets[2 * vec_num * j + 2 * i],
+ dataref_ptr, vec_offsets[2 * i],
final_mask);
tree low = make_ssa_name (vectype);
gimple_set_lhs (new_stmt, low);
@@ -11204,7 +11194,7 @@ vectorizable_load (vec_info *vinfo,
new_stmt = vect_build_one_gather_load_call
(vinfo, stmt_info, gsi, &gs_info,
dataref_ptr,
- vec_offsets[2 * vec_num * j + 2 * i + 1],
+ vec_offsets[2 * i + 1],
final_mask);
tree high = make_ssa_name (vectype);
gimple_set_lhs (new_stmt, high);
@@ -11229,8 +11219,8 @@ vectorizable_load (vec_info *vinfo,
{
/* We have a offset vector with double the number of
lanes. Select the low/high part accordingly. */
- vec_offset = vec_offsets[(vec_num * j + i) / 2];
- if ((vec_num * j + i) & 1)
+ vec_offset = vec_offsets[i / 2];
+ if (i & 1)
{
int count = offset_nunits.to_constant ();
vec_perm_builder sel (count, count, 1);
@@ -11290,9 +11280,8 @@ vectorizable_load (vec_info *vinfo,
than the data vector for now. */
unsigned HOST_WIDE_INT factor
= const_offset_nunits / const_nunits;
- vec_offset = vec_offsets[(vec_num * j + i) / factor];
- unsigned elt_offset
- = ((vec_num * j + i) % factor) * const_nunits;
+ vec_offset = vec_offsets[i / factor];
+ unsigned elt_offset = (i % factor) * const_nunits;
tree idx_type = TREE_TYPE (TREE_TYPE (vec_offset));
tree scale = size_int (gs_info.scale);
align = get_object_alignment (DR_REF (first_dr_info->dr));
@@ -11372,10 +11361,9 @@ 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 < 1; j++)
{
/* 1. Create the vector or array pointer update chain. */
- if (j == 0 && !costing_p)
+ if (!costing_p)
{
bool simd_lane_access_p
= STMT_VINFO_SIMD_LANE_ACCESS_P (stmt_info) != 0;
@@ -11450,11 +11438,10 @@ vectorizable_load (vec_info *vinfo,
if (!costing_p)
{
if (mask)
- vec_mask = vec_masks[vec_num * j + i];
+ vec_mask = vec_masks[i];
if (loop_masks)
final_mask = vect_get_loop_mask (loop_vinfo, gsi, loop_masks,
- vec_num, vectype,
- vec_num * j + i);
+ vec_num, vectype, i);
if (vec_mask)
final_mask = prepare_vec_mask (loop_vinfo, mask_vectype,
final_mask, vec_mask, gsi);
@@ -11504,8 +11491,7 @@ 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, vectype,
- vec_num * j + i, factor);
+ vec_num, vectype, i, factor);
}
else if (final_mask)
{
@@ -11612,12 +11598,12 @@ vectorizable_load (vec_info *vinfo,
/* Try to use a single smaller load when we are about
to load excess elements compared to the unrolled
scalar loop. */
- if (known_gt ((vec_num * j + i + 1) * nunits,
+ if (known_gt ((i + 1) * nunits,
(group_size * vf - gap)))
{
poly_uint64 remain = ((group_size * vf - gap)
- - (vec_num * j + i) * nunits);
- if (known_ge ((vec_num * j + i + 1) * nunits
+ - i * nunits);
+ if (known_ge ((i + 1) * nunits
- (group_size * vf - gap), nunits))
/* DR will be unused. */
ltype = NULL_TREE;
@@ -11920,7 +11906,7 @@ vectorizable_load (vec_info *vinfo,
if (alignment_support_scheme == dr_explicit_realign_optimized)
{
gcc_assert (phi);
- if (i == vec_num - 1 && j == 0)
+ if (i == vec_num - 1)
add_phi_arg (phi, lsq, loop_latch_edge (containing_loop),
UNKNOWN_LOCATION);
msq = lsq;
--
2.43.0
