Pipelining Computational Stages of the Tomographic Reconstructor for Multi-Object Adaptive Optics on a Multi-GPU System

Handle URI:
http://hdl.handle.net/10754/575827
Title:
Pipelining Computational Stages of the Tomographic Reconstructor for Multi-Object Adaptive Optics on a Multi-GPU System
Authors:
Charara, Ali ( 0000-0002-9509-7794 ) ; Ltaief, Hatem ( 0000-0002-6897-1095 ) ; Gratadour, Damien; Keyes, David E. ( 0000-0002-4052-7224 ) ; Sevin, Arnaud; Abdelfattah, Ahmad ( 0000-0001-5054-4784 ) ; Gendron, Eric; Morel, Carine; Vidal, Fabrice
Abstract:
The European Extremely Large Telescope project (E-ELT) is one of Europe's highest priorities in ground-based astronomy. ELTs are built on top of a variety of highly sensitive and critical astronomical instruments. In particular, a new instrument called MOSAIC has been proposed to perform multi-object spectroscopy using the Multi-Object Adaptive Optics (MOAO) technique. The core implementation of the simulation lies in the intensive computation of a tomographic reconstruct or (TR), which is used to drive the deformable mirror in real time from the measurements. A new numerical algorithm is proposed (1) to capture the actual experimental noise and (2) to substantially speed up previous implementations by exposing more concurrency, while reducing the number of floating-point operations. Based on the Matrices Over Runtime System at Exascale numerical library (MORSE), a dynamic scheduler drives all computational stages of the tomographic reconstruct or simulation and allows to pipeline and to run tasks out-of order across different stages on heterogeneous systems, while ensuring data coherency and dependencies. The proposed TR simulation outperforms asymptotically previous state-of-the-art implementations up to 13-fold speedup. At more than 50000 unknowns, this appears to be the largest-scale AO problem submitted to computation, to date, and opens new research directions for extreme scale AO simulations. © 2014 IEEE.
KAUST Department:
Extreme Computing Research Center; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division; Applied Mathematics and Computational Science Program; Computer Science Program
Publisher:
Institute of Electrical and Electronics Engineers (IEEE)
Journal:
SC14: International Conference for High Performance Computing, Networking, Storage and Analysis
Conference/Event name:
International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2014
Issue Date:
Nov-2014
DOI:
10.1109/SC.2014.27
Type:
Conference Paper
Appears in Collections:
Conference Papers; Applied Mathematics and Computational Science Program; Applied Mathematics and Computational Science Program; Extreme Computing Research Center; Computer Science Program; Computer Science Program; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorCharara, Alien
dc.contributor.authorLtaief, Hatemen
dc.contributor.authorGratadour, Damienen
dc.contributor.authorKeyes, David E.en
dc.contributor.authorSevin, Arnauden
dc.contributor.authorAbdelfattah, Ahmaden
dc.contributor.authorGendron, Ericen
dc.contributor.authorMorel, Carineen
dc.contributor.authorVidal, Fabriceen
dc.date.accessioned2015-08-24T09:27:15Zen
dc.date.available2015-08-24T09:27:15Zen
dc.date.issued2014-11en
dc.identifier.doi10.1109/SC.2014.27en
dc.identifier.urihttp://hdl.handle.net/10754/575827en
dc.description.abstractThe European Extremely Large Telescope project (E-ELT) is one of Europe's highest priorities in ground-based astronomy. ELTs are built on top of a variety of highly sensitive and critical astronomical instruments. In particular, a new instrument called MOSAIC has been proposed to perform multi-object spectroscopy using the Multi-Object Adaptive Optics (MOAO) technique. The core implementation of the simulation lies in the intensive computation of a tomographic reconstruct or (TR), which is used to drive the deformable mirror in real time from the measurements. A new numerical algorithm is proposed (1) to capture the actual experimental noise and (2) to substantially speed up previous implementations by exposing more concurrency, while reducing the number of floating-point operations. Based on the Matrices Over Runtime System at Exascale numerical library (MORSE), a dynamic scheduler drives all computational stages of the tomographic reconstruct or simulation and allows to pipeline and to run tasks out-of order across different stages on heterogeneous systems, while ensuring data coherency and dependencies. The proposed TR simulation outperforms asymptotically previous state-of-the-art implementations up to 13-fold speedup. At more than 50000 unknowns, this appears to be the largest-scale AO problem submitted to computation, to date, and opens new research directions for extreme scale AO simulations. © 2014 IEEE.en
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)en
dc.subjectComputational Astronomyen
dc.subjectDense Linear Algebraen
dc.subjectDynamic Scheduleren
dc.subjectGPU Computingen
dc.subjectMulti-Objects Adaptive Opticsen
dc.titlePipelining Computational Stages of the Tomographic Reconstructor for Multi-Object Adaptive Optics on a Multi-GPU Systemen
dc.typeConference Paperen
dc.contributor.departmentExtreme Computing Research Centeren
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.contributor.departmentApplied Mathematics and Computational Science Programen
dc.contributor.departmentComputer Science Programen
dc.identifier.journalSC14: International Conference for High Performance Computing, Networking, Storage and Analysisen
dc.conference.date16 November 2014 through 21 November 2014en
dc.conference.nameInternational Conference for High Performance Computing, Networking, Storage and Analysis, SC 2014en
kaust.authorLtaief, Hatemen
kaust.authorKeyes, David E.en
kaust.authorAbdelfattah, Ahmaden
kaust.authorCharara, Alien
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.