Abstract
We have developed a scalable hierarchical parallelization scheme for molecular dynamics (MD) simulation on multicore clusters. The scheme explores multilevel parallelism combining: (1) Internode parallelism using spatial decomposition via message passing; (2) intercore parallelism using cellular decomposition via multithreading employing a master/worker model; (3) data-level optimization via single-instruction multiple-data (SIMD) parallelism with various code transformation techniques. By using a hierarchy of parallelisms, the scheme exposes very high concurrency and data locality, thereby achieving: (1) internode weak-scaling parallel efficiency 0.985 on 106,496 BlueGene/L nodes (0.975 on 32,768 BlueGene/P nodes), internode strong-scaling parallel efficiency 0.90 on 8,192 BlueGene/L nodes; (2) intercore multithread parallel efficiency 0.65 for eight threads on a dual quadcore Xeon platform; and (3) SIMD speedup around 2 for problem sizes ranging from 3,072 to 98,304 atoms. Furthermore, the effect of memory-access penalty on SIMD performance is analyzed, and an application-based SIMD analysis scheme is proposed to help programmers determine whether their applications are amenable to SIMDization.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Vashishta P, Bachlechner ME, Nakano A, Campbell TJ, Kalia RK, Kodiyalam S, Ogata S, Shimojo F, Walsh P (2001) Multimillion atom simulation of materials on parallel computers-nanopixel, interfacial fracture, nanoindentation, and oxidation. Appl Surface Sci 182:258–264
Nomura K et al (2009) A metascalable computing scheme for large spatiotemporal-scale atomistic simulations. In: Proceedings of the 2009 international parallel and distributed processing symposium. IEEE Press, New York
Dongarra J et al (2007) The impact of multicore on computational science software. In: CTWatch
Nakano A et al (2001) Scalable atomistic simulation algorithms for materials research. In: SuperComputing
Ohno Y (2007) A 128 Tflops calculation for x-ray protein structure analysis with special-purpose computers MD-GRAPE3. In: SuperComputing
Shaw DE (2007) Anton, a special-purpose machine for molecular dynamics simulation. In: ISCA
Scrofano R, Prasanna VK (2005) Preliminary investigation of advanced electrostatics in molecular dynamics on reconfigurable computers. In: SuperComputing, New York, NY
Erez M et al (2004) Analysis and performance results of a molecular modeling application on Merrimac. In: SuperComputing, Washington, DC
Erez M et al (2007) Executing irregular scientific applications on stream architectures. In: ICS, New York, NY
Dally WJ et al (2003) Merrimac: supercomputing with streams. In: SuperComputing, Washington, DC
Almasi GS et al (2001) Demonstrating the scalability of a molecular dynamics application on a petaflop computer. In: ICS, New York, NY, 2001
Phillips JC et al (2002) NAMD: Biomolecular simulations on thousands of processors. In: Proceedings of supercomputing (SC2002). IEEE/ACM, New York
Peng L et al (2009) High-order stencil computations on multicore clusters. In: Proceedings of the 2009 international parallel and distributed processing symposium
Chang H, Sung W (2008) Efficient vectorization of SIMD programs with non-aligned and irregular data access hardware. In: Proceedings of the 2008 international conference on compilers, architectures and synthesis for embedded systems, Atlanta, GA, USA
McKinley KS et al (1996) Improving data locality with loop transformations. ACM Trans Program Lang Syst 18:424–453
Darte A, Robert Y (1994) On the alignment problem. Parallel Process Lett 4:259–270
Eichenberger AE et al (2004) Vectorization for SIMD Architectures with alignment constraints. ACM SIGPLAN Not 39:82–93
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Peng, L., Kunaseth, M., Dursun, H. et al. Exploiting hierarchical parallelisms for molecular dynamics simulation on multicore clusters. J Supercomput 57, 20–33 (2011). https://doi.org/10.1007/s11227-011-0560-1
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11227-011-0560-1