On Tue, 28 Oct 2025, Christopher Bazley wrote:
+/* Materialize length number INDEX for a group of scalar stmts in SLP_NODE
that
+ operate on NVECTORS vectors of type VECTYPE, where 0 <= INDEX <
NVECTORS. A
+ length limit is only required for the tail, therefore NULL_TREE is
returned
+ for every value of INDEX except that last; otherwise, return a value
that
+ contains FACTOR multiplied by the number of elements that should be
+ processed. */
+
+tree
+vect_slp_get_bb_len (slp_tree slp_node, unsigned int nvectors, tree
vectype,
+ unsigned int index, unsigned int factor)
+{
+ gcc_checking_assert (SLP_TREE_CAN_USE_LEN_P (slp_node));
+
+ /* Only the last vector can be a partial vector. */
+ if (index < nvectors - 1)
+ return NULL_TREE;
+
+ /* vect_get_num_copies only allows a partial vector if it is the only
+ vector. */
+ if (nvectors > 1)
+ return NULL_TREE;
+
+ gcc_checking_assert (nvectors == 1);
+
+ poly_uint64 nunits = TYPE_VECTOR_SUBPARTS (vectype);
+ unsigned int group_size = SLP_TREE_LANES (slp_node);
+
+ /* A single vector can be a full vector, in which case no length limit is
+ * needed. */
+ if (known_eq (nunits, group_size))
+ return NULL_TREE;
+
+ /* Return the scaled length of a single partial vector. */
+ gcc_checking_assert (known_lt (group_size, nunits));
+ return size_int (group_size * factor);
+}
diff --git a/gcc/tree-vect-stmts.cc b/gcc/tree-vect-stmts.cc
index 3115c610736..5ec65b2b2de 100644
--- a/gcc/tree-vect-stmts.cc
+++ b/gcc/tree-vect-stmts.cc
@@ -1408,7 +1408,9 @@ vectorizable_internal_function (combined_fn cfn, tree
fndecl,
/* Record that a complete set of masks associated with VINFO would need to
contain a sequence of NVECTORS masks that each control a vector of type
VECTYPE. If SCALAR_MASK is nonnull, the fully-masked loop would AND
- these vector masks with the vector version of SCALAR_MASK. */
+ these vector masks with the vector version of SCALAR_MASK.
Alternatively,
+ if doing basic block vectorization, record that an equivalent mask would
be
+ required to vectorize SLP_NODE. */
static void
vect_record_mask (vec_info *vinfo, slp_tree slp_node, unsigned int
nvectors,
tree vectype, tree scalar_mask)
@@ -1418,7 +1420,10 @@ vect_record_mask (vec_info *vinfo, slp_tree slp_node,
unsigned int nvectors,
vect_record_loop_mask (loop_vinfo, &LOOP_VINFO_MASKS (loop_vinfo),
nvectors,
vectype, scalar_mask);
else
- (void) slp_node; // FORNOW
+ {
+ gcc_checking_assert (!SLP_TREE_CAN_USE_LEN_P (slp_node));
+ SLP_TREE_CAN_USE_MASK_P (slp_node) = true;
+ }
}
/* Given a complete set of masks associated with VINFO, extract mask
number
@@ -1436,16 +1441,15 @@ vect_get_mask (vec_info *vinfo, slp_tree slp_node,
gimple_stmt_iterator *gsi,
return vect_get_loop_mask (loop_vinfo, gsi, &LOOP_VINFO_MASKS
(loop_vinfo),
nvectors, vectype, index);
else
- {
- (void) slp_node; // FORNOW
- return NULL_TREE;
- }
+ return vect_slp_get_bb_mask (slp_node, gsi, nvectors, vectype, index);
}
/* Record that a complete set of lengths associated with VINFO would need
to
contain a sequence of NVECTORS lengths for controlling an operation on
VECTYPE. The operation splits each element of VECTYPE into FACTOR
separate
- subelements, measuring the length as a number of these subelements. */
+ subelements, measuring the length as a number of these subelements.
+ Alternatively, if doing basic block vectorization, record that an
equivalent
+ length would be required to vectorize SLP_NODE. */
static void
vect_record_len (vec_info *vinfo, slp_tree slp_node, unsigned int
nvectors,
tree vectype, unsigned int factor)
@@ -1455,7 +1459,10 @@ vect_record_len (vec_info *vinfo, slp_tree slp_node,
unsigned int nvectors,
vect_record_loop_len (loop_vinfo, &LOOP_VINFO_LENS (loop_vinfo),
nvectors,
vectype, factor);
else
- (void) slp_node; // FORNOW
+ {
+ gcc_checking_assert (!SLP_TREE_CAN_USE_MASK_P (slp_node));
+ SLP_TREE_CAN_USE_LEN_P (slp_node) = true;
+ }
}
/* Given a complete set of lengths associated with VINFO, extract length
number
@@ -1476,10 +1483,7 @@ vect_get_len (vec_info *vinfo, slp_tree slp_node,
gimple_stmt_iterator *gsi,
return vect_get_loop_len (loop_vinfo, gsi, &LOOP_VINFO_LENS
(loop_vinfo),
nvectors, vectype, index, factor);
else
- {
- (void) slp_node; // FORNOW
- return NULL_TREE;
- }
+ return vect_slp_get_bb_len (slp_node, nvectors, vectype, index,
factor);
}
static tree permute_vec_elements (vec_info *, tree, tree, tree,
stmt_vec_info,
@@ -14252,24 +14256,35 @@ supportable_indirect_convert_operation
(code_helper code,
mask[I] is true iff J + START_INDEX < END_INDEX for all J <= I.
Add the statements to SEQ. */
+void
+vect_gen_while_ssa_name (gimple_seq *seq, tree mask_type, tree start_index,
+ tree end_index, tree ssa_name)
+{
+ tree cmp_type = TREE_TYPE (start_index);
+ gcc_checking_assert (direct_internal_fn_supported_p (IFN_WHILE_ULT,
cmp_type,
+ mask_type,
+ OPTIMIZE_FOR_SPEED));
+ gcall *call
+ = gimple_build_call_internal (IFN_WHILE_ULT, 3, start_index, end_index,
+ build_zero_cst (mask_type));
That's quite restrictive, for constant_p nunits you should be able to
create a VECTOR_CST. How do you ensure that the actual vector length
is big enough btw?
