Two years ago, I've added support for up to 2 simple preparation statements
in value_replacement, but the
-      && estimate_num_insns (assign, &eni_time_weights)
+      && estimate_num_insns (bb_seq (middle_bb), &eni_time_weights)
change, meant that we compute the cost of all those statements rather than
just the single assign that has been the single supported non-debug
statement in the bb before, doesn't do what I thought would do, gimple_seq
is just gimple * and thus it can't be really overloaded depending on whether
we pass a single gimple * or a whole sequence.  Which means in the last
two years it doesn't count all the statements, but only the first one.
With -g that happens to be a DEBUG_STMT, or it could be e.g. the first
preparation statement which could be much cheaper than the actual assign.

2020-03-19  Jakub Jelinek  <jakub@redhat.com>

	PR tree-optimization/94211
	* tree-ssa-phiopt.c (value_replacement): Use estimate_num_insns_seq
	instead of estimate_num_insns for bb_seq (middle_bb).  Rename
	emtpy_or_with_defined_p variable to empty_or_with_defined_p, adjust
	all uses.

	* gcc.dg/pr94211.c: New test.