Advanced search
1 file | 124.35 KB Add to list
Author
Organization
Abstract
To handle the stringent performance requirements of future exascale-class applications, High Performance Computing (HPC) systems need ultra-efficient heterogeneous compute nodes. To reduce power and increase performance, such compute nodes will require hardware accelerators with a high degree of specialization. Ideally, dynamic reconfiguration will be an intrinsic feature, so that specific HPC application features can be optimally accelerated, even if they regularly change over time. In the EXTRA project, we create a new and flexible exploration platform for developing reconfigurable architectures, design tools and HPC applications with run-time reconfiguration built-in as a core fundamental feature instead of an add-on. EXTRA covers the entire stack from architecture up to the application, focusing on the fundamental building blocks for run-time reconfigurable exascale HPC systems: new chip architectures with very low reconfiguration overhead, new tools that truly take reconfiguration as a central design concept, and applications that are tuned to maximally benefit from the proposed run-time reconfiguration techniques. Ultimately, this open platform will improve Europe's competitive advantage and leadership in the field.

Downloads

  • PID3907129.pdf
    • full text
    • |
    • open access
    • |
    • PDF
    • |
    • 124.35 KB

Citation

Please use this url to cite or link to this publication:

MLA
Ciobanu, Catalin Bogdan et al. “EXTRA : Towards an Efficient Open Platform for Reconfigurable High Performance Computing.” 2015 IEEE 18TH INTERNATIONAL CONFERENCE ON COMPUTATIONAL SCIENCE AND ENGINEERING (CSE). 2015. 339–342. Print.
APA
Ciobanu, C. B., Varbanescu, A. L., Pnevmatikatos, D., Charitopoulos, G., Niu, X., Luk, W., Santambrogio, M. D., et al. (2015). EXTRA : towards an efficient open platform for reconfigurable high performance computing. 2015 IEEE 18TH INTERNATIONAL CONFERENCE ON COMPUTATIONAL SCIENCE AND ENGINEERING (CSE) (pp. 339–342). Presented at the IEEE 18th International Conference on Computational Science and Engineering (CSE).
Chicago author-date
Ciobanu, Catalin Bogdan, Ana Lucia Varbanescu, Dionisios Pnevmatikatos, George Charitopoulos, Xinyu Niu, Wayne Luk, Marco D Santambrogio, et al. 2015. “EXTRA : Towards an Efficient Open Platform for Reconfigurable High Performance Computing.” In 2015 IEEE 18TH INTERNATIONAL CONFERENCE ON COMPUTATIONAL SCIENCE AND ENGINEERING (CSE), 339–342.
Chicago author-date (all authors)
Ciobanu, Catalin Bogdan, Ana Lucia Varbanescu, Dionisios Pnevmatikatos, George Charitopoulos, Xinyu Niu, Wayne Luk, Marco D Santambrogio, Donatella Sciuto, Muhammed Al Kadi, Michael Huebner, Tobias Becker, Georgi Gaydadjiev, Andreas Brokalakis, Antonis Nikitakis, Alex Thom, Elias Vansteenkiste, and Dirk Stroobandt. 2015. “EXTRA : Towards an Efficient Open Platform for Reconfigurable High Performance Computing.” In 2015 IEEE 18TH INTERNATIONAL CONFERENCE ON COMPUTATIONAL SCIENCE AND ENGINEERING (CSE), 339–342.
Vancouver
1.
Ciobanu CB, Varbanescu AL, Pnevmatikatos D, Charitopoulos G, Niu X, Luk W, et al. EXTRA : towards an efficient open platform for reconfigurable high performance computing. 2015 IEEE 18TH INTERNATIONAL CONFERENCE ON COMPUTATIONAL SCIENCE AND ENGINEERING (CSE). 2015. p. 339–42.
IEEE
[1]
C. B. Ciobanu et al., “EXTRA : towards an efficient open platform for reconfigurable high performance computing,” in 2015 IEEE 18TH INTERNATIONAL CONFERENCE ON COMPUTATIONAL SCIENCE AND ENGINEERING (CSE), Porto, PORTUGAL, 2015, pp. 339–342.
@inproceedings{8115259,
  abstract     = {To handle the stringent performance requirements of future exascale-class applications, High Performance Computing (HPC) systems need ultra-efficient heterogeneous compute nodes. To reduce power and increase performance, such compute nodes will require hardware accelerators with a high degree of specialization. Ideally, dynamic reconfiguration will be an intrinsic feature, so that specific HPC application features can be optimally accelerated, even if they regularly change over time. In the EXTRA project, we create a new and flexible exploration platform for developing reconfigurable architectures, design tools and HPC applications with run-time reconfiguration built-in as a core fundamental feature instead of an add-on. EXTRA covers the entire stack from architecture up to the application, focusing on the fundamental building blocks for run-time reconfigurable exascale HPC systems: new chip architectures with very low reconfiguration overhead, new tools that truly take reconfiguration as a central design concept, and applications that are tuned to maximally benefit from the proposed run-time reconfiguration techniques. Ultimately, this open platform will improve Europe's competitive advantage and leadership in the field.},
  author       = {Ciobanu, Catalin Bogdan and Varbanescu, Ana Lucia and Pnevmatikatos, Dionisios and Charitopoulos, George and Niu, Xinyu and Luk, Wayne and Santambrogio, Marco D and Sciuto, Donatella and Al Kadi, Muhammed and Huebner, Michael and Becker, Tobias and Gaydadjiev, Georgi and Brokalakis, Andreas and Nikitakis, Antonis and Thom, Alex and Vansteenkiste, Elias and Stroobandt, Dirk},
  booktitle    = {2015 IEEE 18TH INTERNATIONAL CONFERENCE ON COMPUTATIONAL SCIENCE AND ENGINEERING (CSE)},
  isbn         = {978-1-4673-8297-7},
  language     = {eng},
  location     = {Porto, PORTUGAL},
  pages        = {339--342},
  title        = {EXTRA : towards an efficient open platform for reconfigurable high performance computing},
  url          = {http://dx.doi.org/10.1109/CSE.2015.54},
  year         = {2015},
}

Altmetric
View in Altmetric
Web of Science
Times cited: