@inbook{bb081f3bed8b4e618d5a3064baa1dbe8,
title = "Efficient execution of multi-query data analysis batches using compiler optimization strategies",
abstract = "This work investigates the leverage that can be obtained from compiler optimization techniques for efficient execution of multi-query workloads in data analysis applications. Our approach is to address multi-query optimization at the algorithmic level, by transforming a declarative specification of scientific data analysis queries into a high-level imperative program that can be made more efficient by applying compiler optimization techniques. These techniques - including loop fusion, common subexpression elimination and dead code elimination are employed to allow data and computation reuse across queries. We describe a preliminary experimental analysis on a real remote sensing application that analyzes very large quantities of satellite data. The results show our techniques achieve sizable reductions in the amount of computation and I/O necessary for executing query batches and in average execution times for the individual queries in a given batch.",
author = "Henrique Andrade and Suresh Aryangat and Tahsin Kurc and Joel Saltz and Alan Sussman",
year = "2004",
doi = "10.1007/978-3-540-24644-2\_33",
language = "English",
isbn = "9783540246442",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Verlag",
pages = "509--523",
editor = "Lawrence Rauchwerger",
booktitle = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
}