Hierarchical treecodes have, to a large extent, converted the compute-bound N-body problem into a memory-bound problem. The large ratio of DRAM to disk pricing suggests use of out-of-core techniques to overcome memory capacity limitations. We will describe a parallel, out-of-core treecode library, targeted at machines with independent secondary storage associated with each processor. Borrowing the space-filling curve techniques from our in-core library, and ``manually'' paging, results in excellent spatial and temporal locality and very good performance.
Several formats for this paper are available. It was necessary to shrink the figures in order to stay within the page limit imposed by the proceedings. The versions here have identical content, but slightly different formatting in order to make the figures more legible.
The figures in this paper may cause trouble for older printers. Send email if you have trouble. I will break out the figures into separate files if necessary.