force_parallel_mode = regress is causing a few more problems than I
thought.  It seems that both the leader and the single worker can
contribute to the execution. I had mistakenly thought that only the worker
process would do any work.  Since it's not deterministic as to which
of the two processes will get a chance to work on the plan, it seems just
better to disable force_parallel_mode for these tests.  At least doing
this seems better than changing to EXPLAIN only rather than EXPLAIN
ANALYZE.

Additionally, I overlooked the fact that the number of executions of the
sub-plan below a Result Cache will execute a varying number of times
depending on cache eviction.  32-bit machines will use less memory and
evict fewer tuples from the cache.  That results in the subnode being
executed fewer times on 32-bit machines.  Let's just blank out the number
of loops in each node.