skip to main content
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Sparse Data Acquisition on Emerging Memory Architectures

Abstract

Emerging memory devices, such as resistive crossbars, have the capacity to store large amounts of data in a single array. Acquiring the data stored in large-capacity crossbars in a sequential fashion can become a bottleneck. We present practical methods, based on sparse sampling, to quickly acquire sparse data stored on emerging memory devices that support the basic summation kernel, reducing the acquisition time from linear to sub-linear. The experimental results show that at least an order of magnitude improvement in acquisition time can be achieved when the data are sparse. Finally, in addition, we show that the energy cost associated with our approach is competitive to that of the sequential method.

Authors:
ORCiD logo [1];  [2];  [2];  [2];  [2]
  1. Sandia National Lab. (SNL-NM), Albuquerque, NM (United States). Threat Intelligence Center
  2. Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
Publication Date:
Research Org.:
Sandia National Lab. (SNL-NM), Albuquerque, NM (United States); Sandia National Laboratories, Livermore, CA (United States)
Sponsoring Org.:
USDOE National Nuclear Security Administration (NNSA)
OSTI Identifier:
1492354
Report Number(s):
SAND-2018-14005J
Journal ID: ISSN 2169-3536; 670902
Grant/Contract Number:  
AC04-94AL85000
Resource Type:
Accepted Manuscript
Journal Name:
IEEE Access
Additional Journal Information:
Journal Volume: 7; Journal ID: ISSN 2169-3536
Publisher:
IEEE
Country of Publication:
United States
Language:
English
Subject:
97 MATHEMATICS AND COMPUTING; Memory acquisition; crossbar; sparse sampling; sparsity estimation

Citation Formats

Quach, Tu-Thach, Agarwal, Sapan, James, Conrad D., Marinella, Matthew J., and Aimone, James B. Sparse Data Acquisition on Emerging Memory Architectures. United States: N. p., 2018. Web. doi:10.1109/ACCESS.2018.2886931.
Quach, Tu-Thach, Agarwal, Sapan, James, Conrad D., Marinella, Matthew J., & Aimone, James B. Sparse Data Acquisition on Emerging Memory Architectures. United States. doi:10.1109/ACCESS.2018.2886931.
Quach, Tu-Thach, Agarwal, Sapan, James, Conrad D., Marinella, Matthew J., and Aimone, James B. Fri . "Sparse Data Acquisition on Emerging Memory Architectures". United States. doi:10.1109/ACCESS.2018.2886931. https://www.osti.gov/servlets/purl/1492354.
@article{osti_1492354,
title = {Sparse Data Acquisition on Emerging Memory Architectures},
author = {Quach, Tu-Thach and Agarwal, Sapan and James, Conrad D. and Marinella, Matthew J. and Aimone, James B.},
abstractNote = {Emerging memory devices, such as resistive crossbars, have the capacity to store large amounts of data in a single array. Acquiring the data stored in large-capacity crossbars in a sequential fashion can become a bottleneck. We present practical methods, based on sparse sampling, to quickly acquire sparse data stored on emerging memory devices that support the basic summation kernel, reducing the acquisition time from linear to sub-linear. The experimental results show that at least an order of magnitude improvement in acquisition time can be achieved when the data are sparse. Finally, in addition, we show that the energy cost associated with our approach is competitive to that of the sequential method.},
doi = {10.1109/ACCESS.2018.2886931},
journal = {IEEE Access},
number = ,
volume = 7,
place = {United States},
year = {2018},
month = {12}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Figures / Tables:

Fig. 1 Fig. 1: Diagram of a 4-by-4 crossbar. Solid lines are active and dashed lines are inactive. In this illustration, we are reading rows 2 and 4 of column 2. The output value is x2 + x4. The summation is a native kernel operation of crossbars and is the core kernelmore » used in our sparse sampling approach.« less

Save / Share:
Figures/Tables have been extracted from DOE-funded journal article accepted manuscripts.