Don't think it makes any difference, but:
Richard Biener <[email protected]> writes:
> @@ -2151,7 +2151,16 @@ get_group_load_store_type (vec_info *vinfo,
> stmt_vec_info stmt_info,
> access excess elements.
> ??? Enhancements include peeling multiple iterations
> or using masked loads with a static mask. */
> - || (group_size * cvf) % cnunits + group_size - gap < cnunits))
> + || ((group_size * cvf) % cnunits + group_size - gap < cnunits
> + /* But peeling a single scalar iteration is enough if
> + we can use the next power-of-two sized partial
> + access. */
> + && ((cremain = (group_size * cvf - gap) % cnunits), true
...this might be less surprising as:
&& ((cremain = (group_size * cvf - gap) % cnunits, true)
in terms of how the &&s line up.
Thanks,
Richard
> + && ((cpart_size = (1 << ceil_log2 (cremain)))
> + != cnunits)
> + && vector_vector_composition_type
> + (vectype, cnunits / cpart_size,
> + &half_vtype) == NULL_TREE))))
> {
> if (dump_enabled_p ())
> dump_printf_loc (MSG_MISSED_OPTIMIZATION, vect_location,
> @@ -11599,6 +11608,27 @@ vectorizable_load (vec_info *vinfo,
> gcc_assert (new_vtype
> || LOOP_VINFO_PEELING_FOR_GAPS
> (loop_vinfo));
> + /* But still reduce the access size to the next
> + required power-of-two so peeling a single
> + scalar iteration is sufficient. */
> + unsigned HOST_WIDE_INT cremain;
> + if (remain.is_constant (&cremain))
> + {
> + unsigned HOST_WIDE_INT cpart_size
> + = 1 << ceil_log2 (cremain);
> + if (known_gt (nunits, cpart_size)
> + && constant_multiple_p (nunits, cpart_size,
> + &num))
> + {
> + tree ptype;
> + new_vtype
> + = vector_vector_composition_type (vectype,
> + num,
> + &ptype);
> + if (new_vtype)
> + ltype = ptype;
> + }
> + }
> }
> }
> tree offset
