General atomic and molecular electronic structure system
Journal of Computational Chemistry
Proceedings of the 11 IPPS/SPDP'99 Workshops Held in Conjunction with the 13th International Parallel Processing Symposium and 10th Symposium on Parallel and Distributed Processing
Protocol-Dependent Message-Passing Performance on Linux Clusters
CLUSTER '02 Proceedings of the IEEE International Conference on Cluster Computing
Enabling the Efficient Use of SMP Clusters: The GAMESS/DDI Model
Proceedings of the 2003 ACM/IEEE conference on Supercomputing
Design and Implementation of a Parallel Performance Data Management Framework
ICPP '05 Proceedings of the 2005 International Conference on Parallel Processing
PerfExplorer: A Performance Data Mining Framework For Large-Scale Parallel Computing
SC '05 Proceedings of the 2005 ACM/IEEE conference on Supercomputing
Performance Modeling and Tuning Strategies of Mixed Mode Collective Communications
SC '05 Proceedings of the 2005 ACM/IEEE conference on Supercomputing
The Tau Parallel Performance System
International Journal of High Performance Computing Applications
Tackling component interoperability in quantum chemistry software
Proceedings of the 2007 symposium on Component and framework technology in high-performance and scientific computing
| Hi-index | 0.00 |
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.