A data model for supporting on-line analytical processing
CIKM '96 Proceedings of the fifth international conference on Information and knowledge management
Disk-directed I/O for MIMD multiprocessors
ACM Transactions on Computer Systems (TOCS)
ESMDIS: Earth System Model Data Information System
SSDBM '97 Proceedings of the Ninth International Conference on Scientific and Statistical Database Management
Modeling and identifying bottlenecks in EOSDIS
FRONTIERS '96 Proceedings of the 6th Symposium on the Frontiers of Massively Parallel Computation
Hi-index | 0.00 |
Large multidimensional arrays are widely used in scientific and engineering database applications. In this paper, we present methods of organizing arrays to make their access on secondary and tertiary memory devices fast and efficient. We have developed four techniques for doing this: (1) storing the array in multidimensional "chunks" to minimize the number of blocks fetched, (2) reordering the chunked array to minimize seek distance between accessed blocks, (3) maintaining redundant copies of the array, each organized for a different chunk size and ordering and (4) partitioning the array onto platters of a tertiary memory device so as to minimize the number of platter switches. Our measurements on real data sets obtained from global change scientists demonstrate that accesses on arrays organized using the above techniques are often an order of magnitude faster than on the original unoptimized data.