Application I/O and Data Management

Author

Dai, William W.

Author_Institution

Comput., Comput., & Stat. Sci. Div., Los Alamos Nat. Lab., Los Alamos, NM, USA

fYear

2011

fDate

26-30 Sept. 2011

Firstpage

446

Lastpage

454

Abstract

A library called HIO has been developed for large-scale multi-physics simulations, based on the UDM library [10]. The goal of the library is to provide sustainable, interoperable, efficient, scalable, and convenient tools for parallel IO and data management for high-level data structures in applications, and to provide tools for the connection between applications. The high-level data structures include one- and multi-dimensional arrays, structured meshes, unstructured meshes, and the meshes generated through adaptive mesh refinement. The IO mechanism can be collective and non-collective. The data objects suitable for the library could be either large or small data sets. Even for small data sets, the IO performance is close to one of MPI-IO performance.

Keywords

application program interfaces; data structures; input-output programs; libraries; message passing; parallel programming; MPI-IO performance; UDM library; application I/O; data management; high-level data structures; large-scale multi-physics simulations; parallel IO; Arrays; Computers; Libraries; Numerical models; Program processors; Writing; IO; data management; data structure; high performance;

fLanguage

English

Publisher

ieee

Conference_Titel

Cluster Computing (CLUSTER), 2011 IEEE International Conference on

Conference_Location

Austin, TX

Print_ISBN

978-1-4577-1355-2

Electronic_ISBN

978-0-7695-4516-5

Type

conf

DOI

10.1109/CLUSTER.2011.84

Filename

6061133