hh.sePublikasjoner
Endre søk
Link to record
Permanent link

Direct link
BETA
Raase, Sebastian
Publikasjoner (3 av 3) Visa alla publikasjoner
Savas, S., Raase, S., Gebrewahid, E., Ul-Abdin, Z. & Nordström, T. (2016). Dataflow Implementation of QR Decomposition on a Manycore. In: MES '16: Proceedings of the Third ACM International Workshop on Many-core Embedded Systems. Paper presented at MES '16, International Workshop on Many-core Embedded Systems, Seoul, Republic of Korea, June 19, 2016 (pp. 26-30). New York, NY: ACM Press
Åpne denne publikasjonen i ny fane eller vindu >>Dataflow Implementation of QR Decomposition on a Manycore
Vise andre…
2016 (engelsk)Inngår i: MES '16: Proceedings of the Third ACM International Workshop on Many-core Embedded Systems, New York, NY: ACM Press, 2016, s. 26-30Konferansepaper, Publicerat paper (Fagfellevurdert)
Abstract [en]

While parallel computer architectures have become mainstream, application development on them is still challenging. There is a need for new tools, languages and programming models. Additionally, there is a lack of knowledge about the performance of parallel approaches of basic but important operations, such as the QR decomposition of a matrix, on current commercial manycore architectures.

This paper evaluates a high level dataflow language (CAL), a source-to-source compiler (Cal2Many) and three QR decomposition algorithms (Givens Rotations, Householder and Gram-Schmidt). The algorithms are implemented both in CAL and hand-optimized C languages, executed on Adapteva's Epiphany manycore architecture and evaluated with respect to performance, scalability and development effort.

The performance of the CAL (generated C) implementations gets as good as 2\% slower than the hand-written versions. They require an average of 25\% fewer lines of source code without significantly increasing the binary size. Development effort is reduced and debugging is significantly simplified. The implementations executed on Epiphany cores outperform the GNU scientific library on the host ARM processor of the Parallella board by up to 30x. © 2016 Copyright held by the owner/author(s).

sted, utgiver, år, opplag, sider
New York, NY: ACM Press, 2016
HSV kategori
Identifikatorer
urn:nbn:se:hh:diva-32371 (URN)10.1145/2934495.2934499 (DOI)2-s2.0-84991106778 (Scopus ID)978-1-4503-4262-9 (ISBN)
Konferanse
MES '16, International Workshop on Many-core Embedded Systems, Seoul, Republic of Korea, June 19, 2016
Prosjekter
ESCHERHiPEC
Forskningsfinansiär
Knowledge FoundationSwedish Foundation for Strategic Research ELLIIT - The Linköping‐Lund Initiative on IT and Mobile Communications
Tilgjengelig fra: 2016-11-04 Laget: 2016-11-04 Sist oppdatert: 2019-05-07bibliografisk kontrollert
Raase, S. (2015). A Dataflow Communications Library for Adapteva's Epiphany. Halmstad
Åpne denne publikasjonen i ny fane eller vindu >>A Dataflow Communications Library for Adapteva's Epiphany
2015 (engelsk)Rapport (Annet vitenskapelig)
Abstract [en]

Adapteva'€™s Epiphany platform is a scalable low-power manycore architecture. Even though Adapteva provides an ANSI C compatible compiler and runtime as well as a Software Development Kit (eSDK), developing for this platform is not particularly easy.

At Halmstad University, we are interested in dataflow applications and have developed a suitable communications library (e-commlib) for the Epiphany, which we would like to release under a permissive 2-clause BSD license. Given sufficiently aware compute kernels, e-commlib projects can also be compiled and run in a Linux-pthreads environment, which simplifies both development and (functional) debugging. This Technical Report shall document both e-commlib (version 3) and our surrounding infrastructure.

sted, utgiver, år, opplag, sider
Halmstad: , 2015. s. 17
Emneord
manycore, communications library, e-commlib, commlib
HSV kategori
Identifikatorer
urn:nbn:se:hh:diva-30187 (URN)
Merknad

Source code is BSD licensed.

Tilgjengelig fra: 2016-01-19 Laget: 2016-01-19 Sist oppdatert: 2018-03-22bibliografisk kontrollert
Raase, S. & Nordström, T. (2015). On the Use of a Many-core Processor for Computational Fluid Dynamics Simulations. Paper presented at International Conference On Computational Science, ICCS 2015 – Computational Science at the Gates of Nature, Reykjavík, Iceland, 1-3 June, 2015. Procedia Computer Science, 51, 1403-1412
Åpne denne publikasjonen i ny fane eller vindu >>On the Use of a Many-core Processor for Computational Fluid Dynamics Simulations
2015 (engelsk)Inngår i: Procedia Computer Science, ISSN 1877-0509, E-ISSN 1877-0509, Vol. 51, s. 1403-1412Artikkel i tidsskrift (Fagfellevurdert) Published
Abstract [en]

The increased availability of modern embedded many-core architectures supporting floating-point operations in hardware makes them interesting targets in traditional high performance computing areas as well. In this paper, the Lattice Boltzmann Method (LBM) from the domain of Computational Fluid Dynamics (CFD) is evaluated on Adapteva’s Epiphany many-core architecture. Although the LBM implementation shows very good scalability and high floating-point efficiency in the lattice computations, current Epiphany hardware does not provide adequate amounts of either local memory or external memory bandwidth to provide a good foundation for simulation of the large problems commonly encountered in real CFD applications.

sted, utgiver, år, opplag, sider
Amsterdam: Elsevier, 2015
Emneord
Many-core, Epiphany, Computational Fluid Dynamics, Lattice Boltzmann
HSV kategori
Identifikatorer
urn:nbn:se:hh:diva-29136 (URN)10.1016/j.procs.2015.05.348 (DOI)000373939100143 ()2-s2.0-84939142878 (Scopus ID)
Konferanse
International Conference On Computational Science, ICCS 2015 – Computational Science at the Gates of Nature, Reykjavík, Iceland, 1-3 June, 2015
Prosjekter
ESCHER
Forskningsfinansiär
Knowledge Foundation
Merknad

This work was supported by the ESCHER project funded by the Swedish Knowledge foundation, and Volvo Penta AB, Gothenburg, Sweden

Tilgjengelig fra: 2015-08-10 Laget: 2015-08-10 Sist oppdatert: 2018-03-22bibliografisk kontrollert
Organisasjoner