LS-DYNA is a general purpose transient dynamic finite element program capable of simulating complex real world problems.   It is optimized for distributed memory, high-performance clusters running the Unix, Linux, or Windows operating systems.

LINUX CLUSTERS SOLVE CRITICAL PROBLEMS

Users are increasingly moving to Linux clusters to solve two primary problems.

First:  lower overall computing costs for compute-intensive applications.

Second:  challenge is to achieve more meaningful results in less time.

When compared to traditional large symmetrical multiprocessing systems (SMPs), Linux clusters promise:

• the advantages of superior scalability,

• inherent reliability,

• significantly lower costs.

Cluster solutions, however, have not evolved to keep pace with the explosion of complexity in deploying large-scale applications. Procedures for compiling and debugging code, achieving low latency interconnections between nodes and maximizing the performance of parallel applications still rely on craftsmanship.

ACCELERATING CLUSTER PERFORMANCE

High performance computing is rapidly evolving. Clusters of low-cost 64-bit nodes are creating new economies of scale for computing resources and redefining how computing is done. 

Applications that benefit from using 64-bit clusters include:

• seismic processing,

• complex physical modeling,

• EDA simulation,

• molecular modeling,

• bioinformatics,

• computational chemistry,

• rendering,

• resource optimization,

• decision support,

• data mining.

Benchmark performance for HPC Linux Clusters running LS-DYNA can be located on TopCrunch.  The TopCrunch project was initiated to track the aggregate performance trends of high performance computer systems and engineering software. Instead of using a synthetic benchmark, actual engineering software applications are used with real data and are run on high performance computer systems.  TopCrunch is not owned or operated by FEA Information Inc. but supported by DARPA HPCS through a subcontract from the USC