@InProceedings{riedel:active-mining,
  author = {Erik Riedel and Garth Gibson and Christos Faloutsos},
  title = {Active storage for large-scale data mining and multimedia.},
  booktitle = {24th Annual International Conference on Very Large Data Bases
  (VLDB'98)},
  editor = {A. Gupta and O. Shmuel and J. Widom},
  year = {1998},
  month = {August},
  pages = {62--73},
  publisher = {Morgan Kaufmann Publishers Inc},
  copyright = {(c)2004 IEE},
  address = {New York, NY},
  URL = {http://www.pdl.cmu.edu/PDL-FTP/Active/VLDB98.pdf},
  keywords = {active disks, active storage, application level code, database
  server, data mining, pario-bib},
  abstract = {The increasing performance and decreasing cost of processors and
  memory are causing system intelligence to move into peripherals from the CPU.
  Storage system designers are using this trend toward "excess" compute power
  to perform more complex processing and optimizations inside storage devices.
  To date, such optimizations have been at relatively low levels of the storage
  protocol. At the same time, trends in storage density, mechanics, and
  electronics are eliminating the bottleneck in moving data off the media and
  putting pressure on interconnects and host processors to move data more
  efficiently. We propose a system called Active Disks that takes advantage of
  processing power on individual disk drives to run application-level code.
  Moving portions of an application's processing to execute directly at disk
  drives can dramatically reduce data traffic and take advantage of the storage
  parallelism already present in large systems today. We discuss several types
  of applications that would benefit from this capability with a focus on the
  areas of database, data mining, and multimedia. We develop an analytical
  model of the speedups possible for scan-intensive applications in an Active
  Disk system. We also experiment with a prototype Active Disk system using
  relatively low-powered processors in comparison to a database server system
  with a single, fast processor. Our experiments validate the intuition in our
  model and demonstrate speedups of 2x on 10 disks across four scan-based
  applications. The model promises linear speedups in disk arrays of hundreds
  of disks, provided the application data is large enough. (57 refs.)}
}