Rethinking database algorithms for phase change memory

  • Chen S
  • Gibbons P
  • Nath S
  • 89

    Readers

    Mendeley users who have this article in their library.
  • 0

    Citations

    Citations of this article.

Abstract

Phase change memory (PCM) is an emerging memory tech- nology with many attractive features: it is non-volatile, byte-addressable, 2–4X denser than DRAM, and orders of magnitude better than NAND Flash in read latency, write latency, and write endurance. In the near future, PCM is expected to become a common component of the mem- ory/storage hierarchy for a wide range of computer systems. In this paper, we describe the unique characteristics of PCM, and their potential impact on database system design. In particular, we present analytic metrics for PCM endurance, energy, and latency, and illustrate that current approaches for common database algorithms such as B+ -trees and Hash Joins are suboptimal for PCM. We present improved algo- rithms that reduce both execution time and energy on PCM while increasing write endurance.

Get free article suggestions today

Mendeley saves you time finding and organizing research

Sign up here
Already have an account ?Sign in

Find this document

  • PUI: 362685865
  • SGR: 80053533280
  • SCOPUS: 2-s2.0-80053533280

Authors

  • Shimin Chen

  • Pb Gibbons

  • S Nath

Cite this document

Choose a citation style from the tabs below

Save time finding and organizing research with Mendeley

Sign up for free