The following testcase FAILs with -fcompare-debug, because reassociate_bb
mishandles the case when the last stmt in a bb has zero uses.  In that case
reassoc_remove_stmt (like gsi_remove) moves the iterator to the next stmt,
i.e. gsi_end_p is true, which means the code sets the iterator back to
gsi_last_bb.  The problem is that the for loop does gsi_prev on that before
handling the next statement, which means the former penultimate stmt, now
last one, is not processed by reassociate_bb.
Now, with -g, if there is at least one debug stmt at the end of the bb,
reassoc_remove_stmt moves the iterator to that following debug stmt and we
just do gsi_prev and continue with the former penultimate non-debug stmt,
now last non-debug stmt.

The following patch fixes that by not doing the gsi_prev in this case; there
are too many continue; cases, so I didn't want to copy over the gsi_prev to
all of them, so this patch uses a bool for that instead.  The second
gsi_end_p check isn't needed anymore, because when we don't do the
undesirable gsi_prev after gsi = gsi_last_bb, the loop !gsi_end_p (gsi)
condition will catch the removal of the very last stmt from a bb.

2020-03-28  Jakub Jelinek  <jakub@redhat.com>

	PR tree-optimization/94329
	* tree-ssa-reassoc.c (reassociate_bb): When calling reassoc_remove_stmt
	on the last stmt in a bb, make sure gsi_prev isn't done immediately
	after gsi_last_bb.

	* gfortran.dg/pr94329.f90: New test.