Granite: an effective tool to explore the concepts of high-performance data intensive scientific computation in java

Authors:
Baoqiang Yan;Philip J. Rhodes
Affiliations:
University of Mississippi, University, MS;University of Mississippi, University, MS
Venue:
Journal of Computing Sciences in Colleges
Year:
2008

Citing 8
Cited 1

Informed prefetching and caching

SOSP '95 Proceedings of the fifteenth ACM symposium on Operating systems principles
Storage-Aware Caching: Revisiting Caching for Heterogeneous Storage Systems

FAST '02 Proceedings of the Conference on File and Storage Technologies
Efficient Organization of Large Multidimensional Arrays

Proceedings of the Tenth International Conference on Data Engineering
I/O Requirements of Scientific Applications: An Evolutionary View

HPDC '96 Proceedings of the 5th IEEE International Symposium on High Performance Distributed Computing
Iteration aware prefetching for large multidimensional datasets

SSDBM'2005 Proceedings of the 17th international conference on Scientific and statistical database management
Why does file system prefetching work?

ATEC '99 Proceedings of the annual conference on USENIX Annual Technical Conference
Teaching high-performance computing in the undergraduate college CS curriculum

Journal of Computing Sciences in Colleges
Toward automatic parallelization of spatial computation for computing clusters

HPDC '08 Proceedings of the 17th international symposium on High performance distributed computing

Teaching parallel computing in a small college: meeting a renewed demand

Journal of Computing Sciences in Colleges

Quantified Score

Hi-index	0.00

Visualization

Abstract

Scientific computation on parallel architectures is a performance-oriented field with large multidimensional input datasets. Granite is a scientific database model developed to provide efficient I/O support for data intensive scientific applications by hiding or reducing disk and network latencies. Granite provides students with an easy-to-use toolkit for spatial computation, and a better understanding of how efficiency is achieved through different I/O optimization techniques. Knowledge of concepts that students learn from classes would be strengthened and extended. Also, student will be exposed to the performance issues in Java programming through live examples.