onr:"swepub:oai:DiVA.org:hv-7664"
Search: onr:"swepub:oai:DiVA.org:hv-7664" > Addressing characte...
- 1 of 1
- Previous record
- Next record
- To hitlist
Addressing characterization methods for memory contention aware co-scheduling
-
- de Blanche, Andreas, 1975- (author)
- Högskolan Väst,Avd för data- och elektroteknik
-
- Lundqvist, Thomas, 1967- (author)
- Högskolan Väst,Avd för data- och elektroteknik
- (creator_code:org_t)
- 2015-01-18
- 2015
- English.
- In: Journal of Supercomputing. - : Springer Science and Business Media LLC. - 0920-8542 .- 1573-0484. ; 71:4, s. 1451-1483
- Journal article (peer-reviewed)
Abstract
Subject headings
Close
- The ability to precisely predict how memory contention degrades performance when co-scheduling programs is critical for reaching high performance levels in cluster, grid and cloud environments. In this paper we present an overview and compare the performance of state-of-the-art characterization methods for memory aware (co-)scheduling. We evaluate the prediction accuracy and co-scheduling performance of four methods: one slowdown-based, two cache-contention based and one based on memory bandwidth usage. Both our regression analysis and scheduling simulations find that the slowdown based method, represented by Memgen, performs better than the other methods. The linear correlation coefficient (Formula presented.) of Memgen's prediction is 0.890. Memgen's preferred schedules reached 99.53 % of the obtainable performance on average. Also, the memory bandwidth usage method performed almost as well as the slowdown based method. Furthermore, while most prior work promote characterization based on cache miss rate we found it to be on par with random scheduling of programs and highly unreliable.
Subject headings
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Sciences (hsv//eng)
Keyword
- Memory contention
- Memory subsystem
- Performance measurements
- Co-scheduling
- Slowdown based scheduling
- Datateknik
- Computer engineering
Publication and Content Type
- ref (subject category)
- art (subject category)
Find in a library
- Journal of Supercomputing (Search for host publication in LIBRIS)
To the university's database
- 1 of 1
- Previous record
- Next record
- To hitlist
Find more in SwePub
- By the author/editor
- de Blanche, Andr ...
- Lundqvist, Thoma ...
- About the subject
-
- NATURAL SCIENCES
- NATURAL SCIENCES
- and Computer and Inf ...
- and Computer Science ...
- Articles in the publication
- Journal of Super ...
- By the university
- University West
Search outside SwePub
- Extend your search to:
- Google Book Search
- Google Scholar
Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.
- Copyright © LIBRIS - National Library Systems
- LIBRIS.kb.se
