Parallel Systems In The Data Warehouse

-- Focuses exclusively on UNIX-based parallel computing and relational databases in the data warehouse.
-- Tough questions for effective purchasing and decision-making.
-- Published in the Data Warehousing Institute Series.

The power of parallel computing systems is increasingly being brought to bear on enterprise-scale data warehouse applications. This is a complete technical introduction to the use of parallel computing in the data warehouse.

Learn how parallel computing systems offer an ideal foundation for data warehousing -- and learn how to make the right strategic and tactical decisions about these technologies. What are the right questions to ask? What aren't the hardware and software vendors telling you? How do benchmarks relate to real-world results? The book covers all three major parallel hardware architectures: symmetric multiprocessors (SMP); distributed memory (DM) or massively parallel machines; and distributed shared memory (DSM) systems. Understand how large queries are decomposed into hundreds of smaller instruction streams for execution by parallel systems; and how data can be sorted in parallel. Examine four real-world hardware/software combinations. Finally, review OLAP, data mining, universal database servers, and implementation considerations.