In this paper, we describe an implementation of the Barnes–Hut treecode on a cluster of PCs (Beowulf-class machines) equipped with GRAPE hardware. Our implementation is designed to achieve good performance on clusters of GRAPE with a relatively slow network, such as the standard Gigabit Ethernet. With 12 processors, the speedup over single-processor code reaches around 10. Our code is available on the web.
No takes yet. Share an insight, caveat, or question.
Junichiro Makino (2004) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: