Logo des Repositoriums
 

Efficient memory allocations on a many-core accelerator

dc.contributor.authorKoutras, Ioannis
dc.contributor.authorBartzas, Alexandros
dc.contributor.authorSoudris, Dimitrios
dc.contributor.editorMühl, Gero
dc.contributor.editorRichling, Jan
dc.contributor.editorHerkersdorf, Andreas
dc.date.accessioned2019-10-30T12:50:17Z
dc.date.available2019-10-30T12:50:17Z
dc.date.issued2012
dc.description.abstractMemory management is one of the key challenges in the design of embedded systems where memory is a scarce resource. The problem scales disproportionally as new embedded systems incorporate many-core architectures where the cores have to struggle accessing an even more limited amount of resources. In this paper we present a way of creating custom memory allocators for many-core accelerators. We evaluated our approach in the P2012 platform, a many-core accelerator from ST. It is shown that a custom memory allocator created by our framework could save on average 62% of the total cycles spent on memory resource management when compared with the platform's current memory allocator without increasing the allocator's overhead.en
dc.identifier.isbn978-3-88579-294-9
dc.identifier.pissn1617-5468
dc.identifier.urihttps://dl.gi.de/handle/20.500.12116/29503
dc.language.isoen
dc.publisherGesellschaft für Informatik e.V.
dc.relation.ispartofARCS 2012 Workshops
dc.relation.ispartofseriesLecture Notes in Informatics (LNI) - Proceedings, Volume P-200
dc.titleEfficient memory allocations on a many-core acceleratoren
dc.typeText/Conference Paper
gi.citation.endPage338
gi.citation.publisherPlaceBonn
gi.citation.startPage327
gi.conference.date28. Februar-2. März 2012
gi.conference.locationMünchen
gi.conference.sessiontitleRegular Research Papers

Dateien

Originalbündel
1 - 1 von 1
Lade...
Vorschaubild
Name:
327.pdf
Größe:
416.7 KB
Format:
Adobe Portable Document Format