Is automatic “folding” of programs efficient enough to displace manual?

The operation of “folding” a program into the available memory is discussed. Measurements by Brawn et al. and by Nelson on an automatic folding mechanism of simple design, a demand paging unit built at the IBM Research Center by Belady, Nelson, O'Neill, and others, permitting its quality to be compared with that of manual folding, are discussed, and it is shown that given some care in use the unit performs satisfactorily under the conditions tested, even though it is operating across a memory-to-storage interface with a very large speed difference. The disadvantages of prefolding, which is required when the folding is manual, are examined, and a number of the important troubles which beset computing today are shown to arise from, or be aggravated by, this source. It is concluded that a folding mechanism will probably become a normal part of most computing systems.