skip to main content

DOE PAGESDOE PAGES

Title: Damaris: Addressing performance variability in data management for post-petascale simulations

With exascale computing on the horizon, reducing performance variability in data management tasks (storage, visualization, analysis, etc.) is becoming a key challenge in sustaining high performance. Here, this variability significantly impacts the overall application performance at scale and its predictability over time. In this article, we present Damaris, a system that leverages dedicated cores in multicore nodes to offload data management tasks, including I/O, data compression, scheduling of data movements, in situ analysis, and visualization. We evaluate Damaris with the CM1 atmospheric simulation and the Nek5000 computational fluid dynamic simulation on four platforms, including NICS’s Kraken and NCSA’s Blue Waters. Our results show that (1) Damaris fully hides the I/O variability as well as all I/O-related costs, thus making simulation performance predictable; (2) it increases the sustained write throughput by a factor of up to 15 compared with standard I/O approaches; (3) it allows almost perfect scalability of the simulation up to over 9,000 cores, as opposed to state-of-the-art approaches that fail to scale; and (4) it enables a seamless connection to the VisIt visualization software to perform in situ analysis and visualization in a way that impacts neither the performance of the simulation nor its variability. In addition, wemore » extended our implementation of Damaris to also support the use of dedicated nodes and conducted a thorough comparison of the two approaches—dedicated cores and dedicated nodes—for I/O tasks with the aforementioned applications.« less
Authors:
 [1] ;  [2] ;  [1] ;  [1] ;  [3] ;  [2] ;  [2] ;  [1] ;  [4]
  1. Argonne National Lab. (ANL), Argonne, IL (United States)
  2. Inria, Rennes - Bretagne Atlantique Research Centre (France)
  3. Univ. of Illinois at Urbana-Champaign, Urbana, IL (United States)
  4. Univ. of Wisconsin, Madison, WI (United States)
Publication Date:
Grant/Contract Number:
AC02-06CH11357
Type:
Accepted Manuscript
Journal Name:
ACM Transactions on Parallel Computing
Additional Journal Information:
Journal Volume: 3; Journal Issue: 3; Journal ID: ISSN 2329-4949
Publisher:
Association for Computing Machinery
Research Org:
Argonne National Lab. (ANL), Argonne, IL (United States)
Sponsoring Org:
USDOE Office of Science (SC), Basic Energy Sciences (BES) (SC-22); Central Michigan University; National Center for Atmospheric Research
Country of Publication:
United States
Language:
English
Subject:
97 MATHEMATICS AND COMPUTING; Damaris; Dedicated Cores; Dedicated Nodes; Design; Exascale Computing; Experimentation; I/O; In Situ Visualization; Performance
OSTI Identifier:
1346736

Dorier, Matthieu, Antoniu, Gabriel, Cappello, Franck, Snir, Marc, Sisneros, Robert, Yildiz, Orcun, Ibrahim, Shadi, Peterka, Tom, and Orf, Leigh. Damaris: Addressing performance variability in data management for post-petascale simulations. United States: N. p., Web. doi:10.1145/2987371.
Dorier, Matthieu, Antoniu, Gabriel, Cappello, Franck, Snir, Marc, Sisneros, Robert, Yildiz, Orcun, Ibrahim, Shadi, Peterka, Tom, & Orf, Leigh. Damaris: Addressing performance variability in data management for post-petascale simulations. United States. doi:10.1145/2987371.
Dorier, Matthieu, Antoniu, Gabriel, Cappello, Franck, Snir, Marc, Sisneros, Robert, Yildiz, Orcun, Ibrahim, Shadi, Peterka, Tom, and Orf, Leigh. 2016. "Damaris: Addressing performance variability in data management for post-petascale simulations". United States. doi:10.1145/2987371. https://www.osti.gov/servlets/purl/1346736.
@article{osti_1346736,
title = {Damaris: Addressing performance variability in data management for post-petascale simulations},
author = {Dorier, Matthieu and Antoniu, Gabriel and Cappello, Franck and Snir, Marc and Sisneros, Robert and Yildiz, Orcun and Ibrahim, Shadi and Peterka, Tom and Orf, Leigh},
abstractNote = {With exascale computing on the horizon, reducing performance variability in data management tasks (storage, visualization, analysis, etc.) is becoming a key challenge in sustaining high performance. Here, this variability significantly impacts the overall application performance at scale and its predictability over time. In this article, we present Damaris, a system that leverages dedicated cores in multicore nodes to offload data management tasks, including I/O, data compression, scheduling of data movements, in situ analysis, and visualization. We evaluate Damaris with the CM1 atmospheric simulation and the Nek5000 computational fluid dynamic simulation on four platforms, including NICS’s Kraken and NCSA’s Blue Waters. Our results show that (1) Damaris fully hides the I/O variability as well as all I/O-related costs, thus making simulation performance predictable; (2) it increases the sustained write throughput by a factor of up to 15 compared with standard I/O approaches; (3) it allows almost perfect scalability of the simulation up to over 9,000 cores, as opposed to state-of-the-art approaches that fail to scale; and (4) it enables a seamless connection to the VisIt visualization software to perform in situ analysis and visualization in a way that impacts neither the performance of the simulation nor its variability. In addition, we extended our implementation of Damaris to also support the use of dedicated nodes and conducted a thorough comparison of the two approaches—dedicated cores and dedicated nodes—for I/O tasks with the aforementioned applications.},
doi = {10.1145/2987371},
journal = {ACM Transactions on Parallel Computing},
number = 3,
volume = 3,
place = {United States},
year = {2016},
month = {10}
}