@Article{chiu:smart-disks,
  author = {Steve Chiu and Wei-keng Liao and Mahmut Kandemir},
  title = {Processor-embedded distributed smart disks for I/O-intensive
  workloads: architectures, performance models and evaluation},
  journal = {Journal of Parallel and Distributed Computing},
  year = {2004},
  month = {March},
  volume = {64},
  number = {3},
  pages = {427--445},
  institution = {Northwestern Univ, Dept Elect \& Comp Engn, Evanston, IL 60208
  USA; Northwestern Univ, Dept Elect \& Comp Engn, Evanston, IL 60208 USA; Penn
  State Univ, Dept Comp Sci \& Engn, University Pk, PA 16802 USA},
  publisher = {Academic Press},
  copyright = {(c)2004 Institute for Scientific Information, Inc.},
  URL =
  {http://www.sciencedirect.com/science?_ob=ArticleURL&_udi=B6WKJ-4C2NCJB-2&_user=10&_handle=B-WA-A-A-AW-MsSAYVW-UUA-AUYDWYAVCD-AUYVYZWWCD-VAZYCWZWZ-AW-U&_f%
mt=summary&_coverDate=03%2F31%2F2004&_rdoc=10&_orig=browse&_srch=%23toc%236908%232004%23999359996%23491486!&_cdi=6908&view=c&_acct=C000050221&_version=1&_ur%
lVersion=0&_userid=10&md5=1e1c7dff847a1da714e396fcd2a3d908},
  keywords = {smart disks, active disks, I/O performance evaluation, analytic
  performance models, infiniband, data mining, data clustering, I/O
  architecture, pario-bib},
  abstract = {Processor-embedded disks, or smart disks, with their network
  interface controller, can in effect be viewed as processing elements with
  on-disk memory and secondary storage. The data sizes and access patterns of
  today's large I/O-intensive workloads require architectures whose processing
  power scales with increased storage capacity. To address this concern, we
  propose and evaluate disk-based distributed smart storage architectures.
  Based on analytically derived performance models, our evaluation with
  representative workloads show that offloading processing and performing
  point-to-point data communication improve performance over centralized
  architectures. Our results also demonstrate that distributed smart disk
  systems exhibit desirable scalability and can efficiently handle
  I/O-intensive workloads, such as commercial decision support database
  (ITPC-H) queries, association rules mining, data clustering, and
  two-dimensional fast Fourier transform, among others.}
}