Paper Info
Title
Constructing a performance database for large-scale quantum chemistry packages
Abstract
When several large-scale quantum chemistry packages interoperate through components and some components provide similar functionality, we are faced with many challenges such as efficiently selecting the component with the best efficiency, finding compromises between efficiency and accuracy, or constructing new computations from available components with minimum overhead. These challenges are core questions in Computational Quality of Service (CQoS) research, and exploring robust methods for these questions requires a performance database as the foundation for referencing historical performance data. However, these large-scale packages have a long history of development, provide many complex computations, and involve a large number of chemists in the development process. Building a database for these packages is thus not as straightforward as simply selecting a database engine and uploading data. In this paper, we present our efforts in fast prototyping a system to construct a performance database for quantum chemistry packages. We discuss the requirements for such a system, delineate the tasks in each building stage, evaluate how current tool technologies can facilitate the building process, and discuss the support required from the performance tools development community for future CQoS research.
Year
Venue
Keywords
2008
SpringSim
historical performance data,large-scale quantum chemistry package,database engine,building stage,best efficiency,performance tools development community,building process,development process,performance database,large-scale package,future cqos research,common component architecture,quality of service,quantum chemistry
Field
DocType
ISBN
Systems engineering,Simulation,Computer science,Interoperability,Common Component Architecture,Upload,Quality of service,Database engine,Database,Computation
Conference
1-56555-319-5
Citations 
PageRank 
References 
0
0.34
11
Authors
7
Name
Order
Citations
PageRank
Meng-Shiou Wu1202.87
Hirotoshi Mori211.39
Jonathan L. Bentz3132.61
Theresa L. Windus422930.66
Heather Netzloff500.68
Masha Sosonkina627245.62
Mark S. Gordon728325.73