Fall back to elementwise access for too spaced SLP single element interleaving

gcc.dg/vect/vect-pr111779.c is a case where non-SLP manages to vectorize
using VMAT_ELEMENTWISE but SLP currently refuses because doing a regular
access with permutes would cause excess vector loads with at most one
element used.  The following makes us fall back to elementwise accesses
for that, too.

	* tree-vect-stmts.cc (get_group_load_store_type): Fall back
	to VMAT_ELEMENTWISE when single element interleaving of
	a too large group.
	(vectorizable_load): Do not try to verify load permutations
	when using VMAT_ELEMENTWISE for single-lane SLP and fix code
	generation for this case.

	* gfortran.dg/vect/vect-8.f90: Allow one more vectorized loop.

0 files changed, 0 insertions, 0 deletions