SC14 New Orleans, LA

The International Conference for High Performance Computing, Networking, Storage and Analysis

Scalable Asynchronous Contact Mechanics with Charm++.


Student: Xiang Ni (University of Illinois at Urbana-Champaign)
Supervisor: Laxmikant Kale (University of Illinois at Urbana-Champaign)

Abstract: This poster presents a scalable implementation 
of the Asynchronous Contact Mechanics (ACM) algorithm, a
 reliable method to simulate flexible material subject to complex collisions and contact geometries, e.g. cloth simulation in animation. The parallelization of
ACM is challenging due to its highly irregular communication 
pattern, requirement for dynamic load balancing, and 
extremely fine-grained computations. We make use of Charm++, an adaptive parallel runtime system, to address these challenges and scale ACM to 384 cores for problems with less than 100k 
vertices. By comparison the previously published shared memory implementation only scales well to about 30 cores. We demonstrate the scalability of our implementation
 through a number of challenging examples. In particular, for a 
simulation of a cylindrical rod twisting within a cloth sheet, the 
simulation time is reduced by 12× from 9 hours on 30 cores to
 46 minutes using our implementation on 384 cores of a Cray
 XC30.

Poster: pdf
Two-page extended abstract: pdf


Poster Index