Transient Solid Dynamics Simulations on the Sandia/Intel Teraflop Computer

S. Attaway, T. Barragy, K. Brown, D. Gardner, B. Hendrickson, S. J. Plimpton, C. Vaughan, Gordon Bell finalist paper, in Proc of SuperComputing '97, San Jose, CA, November 1997.

Transient solid dynamics simulations are among the most widely used engineering calculations. Industrial applications include vehicle crashworthiness studies, metal forging, and powder compaction prior to sintering. These calculations are also critical to defense applications including safety studies and weapons simulations. The practical importance of these calculations and their computational intensiveness make them natural candidates for parallelization. This has proved to be difficult, and existing implementations fail to scale to more than a few dozen processors. In this paper we describe our parallelization of PRONTO, Sandia's transient solid dynamics code, via a novel algorithmic approach that utilizes multiple decompositions for different key segments of the computations, including the material contact calculation. This latter calculation is notoriously difficult to perform well in parallel, because it involves dynamically changing geometry, global searches for elements in contact, and unstructured communications among the compute nodes. Our approach scales to at least 3600 compute nodes of the Sandia/Intel Teraflop computer (the largest set of nodes to which we have had access to date) on problems involving millions of finite elements. On this machine we can simulate models using more than ten-million elements in a few tenths of a second per timestep, and solve problems more than 3000 times faster than a single processor Cray Jedi.

Return to Publications page