umu.sePublikasjoner
Endre søk
Begrens søket
3456789 251 - 300 of 840
RefereraExporteraLink til resultatlisten
Permanent link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Treff pr side
  • 5
  • 10
  • 20
  • 50
  • 100
  • 250
Sortering
  • Standard (Relevans)
  • Forfatter A-Ø
  • Forfatter Ø-A
  • Tittel A-Ø
  • Tittel Ø-A
  • Type publikasjon A-Ø
  • Type publikasjon Ø-A
  • Eldste først
  • Nyeste først
  • Skapad (Eldste først)
  • Skapad (Nyeste først)
  • Senast uppdaterad (Eldste først)
  • Senast uppdaterad (Nyeste først)
  • Disputationsdatum (tidligste først)
  • Disputationsdatum (siste først)
  • Standard (Relevans)
  • Forfatter A-Ø
  • Forfatter Ø-A
  • Tittel A-Ø
  • Tittel Ø-A
  • Type publikasjon A-Ø
  • Type publikasjon Ø-A
  • Eldste først
  • Nyeste først
  • Skapad (Eldste først)
  • Skapad (Nyeste først)
  • Senast uppdaterad (Eldste først)
  • Senast uppdaterad (Nyeste først)
  • Disputationsdatum (tidligste først)
  • Disputationsdatum (siste først)
Merk
Maxantalet träffar du kan exportera från sökgränssnittet är 250. Vid större uttag använd dig av utsökningar.
  • 251.
    Eklund, Patrik
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Helgesson, Robert
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Composing partially ordered monads2009Inngår i: Relations and Kleene Algebra in Computer Science: 11th International Conference on Relational Methods in Computer Science, RelMiCS 2009, and 6th International Conference on Applications of Kleene Algebra, AKA 2009, Doha, Qatar, November 1-5, 2009. Proceedings / [ed] Rudolf Berghammer, Ali Mohamed Jaoua, Bernhard Möller, Springer, 2009, Vol. 5827, s. 88-102Konferansepaper (Fagfellevurdert)
    Abstract [en]

    Composition of the many-valued powerset partially ordered monad with the term monad provides extensions to non-classical relations and also new examples for Kleene algebras.

  • 252.
    Eklund, Patrik
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Helgesson, Robert
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Monadic extensions of institutions2010Inngår i: Fuzzy sets and systems (Print), ISSN 0165-0114, E-ISSN 1872-6801, Vol. 161, nr 18 (Special issue), s. 2354-2368Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    In this paper we show how partially ordered monads can be used to provide a non-classical extension of institutions and entailment systems as appearing in the framework of general logics. General logics is an axiomatization of a general framework for logics. This framework builds upon traditional power sets of sentences as appearing in satisfaction relations and entailment. The underlying power set monad is implicit, and the utility of a monadic machinery was therefore not explored. Making the use of the power set monad more explicit in the satisfaction and entailment relations opens up possibilities to experiment with various non-classical representations of sentences as appearing in inference. These representations are enabled by partially ordered monads, where the partial order attached to the underlying set functor is essential for extending the axiomatization.

  • 253.
    Eklund, Patrik
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Helgesson, Robert
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Lindgren, Helena
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Towards refining clinical evidence using general logics2008Inngår i: Artificial Intelligence and Soft Computing – ICAISC 2008: 9th International Conference Zakopane, Poland, June 22-26, 2008, Proceedings, Springer , 2008, s. 1029-1040Konferansepaper (Fagfellevurdert)
    Abstract [en]

    Clinical knowledge building upon evidence-based medicine is typically represented in textual guidelines, thus providing a rather informal description from a logical point of view. Further, the context which provides utility of these guidelines is not specified in any detail with respect to workflow and underlying motivations for decision-making. In addition, the level of detail is mostly static in the sense that measurements and decision values are fixed and intended for specific user groups. There is thus a lack of flexibility which disables knowledge to be shifted coherently between user levels in the entire workflow and decision process. In this paper, we will discuss formalizations of the underlying logical structures of guidelines from the viewpoint of being represented appropriately at each user level. Further, to establish a formal correctness criterion, the shift from one level of representation to another is required to be morphic in the categorical sense. General logics [6] is the selected generalized, and categorical, framework for our approach to flexible guideline representation. Our medical scope is dementia differential diagnosis based on consensus guidelines [2], and we focus on types of cognitive disorders as a prerequisite for further diagnostic tasks.

  • 254.
    Eklund, Patrik
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Hoehle, Ulrich
    Kortelainen, Jari
    Modules in Health Classifications2017Inngår i: 2017 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), IEEE, 2017Konferansepaper (Fagfellevurdert)
    Abstract [en]

    In applications, for example in health care, many-valuedness modelled using quantales plays an important role. The paper presents variations of the three chain modules C-3 over unitalization of the three chain quantale (C-3 is the smallest possible quantale to model many-valuedness), thus, variations of right actions are given. From application point of view, it is then possible to choose suitable modules when modelling, for example, the causalities between disease, intervention and functioning. The effect of drug interaction in presence of multiple diseases, and as affecting functioning, adds to this complexity. Health care communities and professionals comply with a range classifications and terminologies, also including scales to qualify strength or hierarchies of evidence, in the sense of Evidence-Based Medicine (EBM), or interaction, or as related to levels of functioning. Such hierarchies adopted in health care are ad hoc as compared to the potentially algebraic and logical structures of terminologies used as part of clinical decision-making. The notion of 'evidence' in EBM would benefit from a logical enrichment. In this paper we show how these hierarchies canonically derive as actions where transitions appear as levels in hierarchies of evidence. In this sense, the Logic-Based Medicine (LBM) view is complementary to EBM, the latter indeed very well known and established, whereas LBM is yet to be recognized more broadly. We will also see how three-valuedness related to health conditions, rather than two-valuedness, is the generator of many-valuedness related to strength of evidence.

  • 255.
    Eklund, Patrik
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Hohle, Ulrich
    Kortelainen, Jari
    A survey on the categorical term construction with applications2016Inngår i: Fuzzy sets and systems (Print), ISSN 0165-0114, E-ISSN 1872-6801, Vol. 298, s. 128-157Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    This paper gives a survey on the categorical term construction based on the free algebra algorithm. In the framework of monoidal biclosed and cocomplete categories a possible concept of signature for finitary theories is introduced. Applications of these constructions are given in Goguen's category and in the category of complete lattices and join preserving maps.

  • 256.
    Eklund, Patrik
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Immonen, M.
    Petäkoski-Hult, T.
    Similä, H.
    The logic of geriatrics2013Inngår i: The Journal of Nutrition, Health & Aging, ISSN 1279-7707, E-ISSN 1760-4788, Vol. 17, nr 1, s. 305-306Artikkel i tidsskrift (Fagfellevurdert)
  • 257.
    Eklund, Patrik
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Johansson, Mats
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Karlsson, Johan
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Åström, Rickard
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    BPMN and its semantics for information management in emergency care2009Inngår i: ICCIT '09. Fourth International Conference on Computer Sciences and Convergence Information Technology, 2009, IEEE Computer Society, 2009, s. 273-278Konferansepaper (Fagfellevurdert)
    Abstract [en]

    Emergency and crisis response such as appearing in large traffic accident management involves coordination of emergency and rescue services and police. The management of information is a complex task where decision support on site and distance management requires a well-founded understanding of the underlying processes. The Business Process Modeling Notation (BPMN) is used for encoding processes related to emergency medical services. BPMN is basically a syntax where the semantic part is left to be specified by the applications. Our approach to semantics is drawn from categorical approaches to representing signatures and generalized terms. In particular, monads over Set, the category of sets, composed with the term monad (over Set) turn out to be useful for modeling uncertainties both with respect to representation of observations as well as time. BPMN Flow Objects, Connecting Objects as well as Artifacts are represented as suitable morphisms in the underlying categories enabled by the monadic instrumentation.

  • 258.
    Eklund, Patrik
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Kallin Westin, L.
    Preprocessing for informative, ecient andsmall networks2001Inngår i: Proceedings Joint 9th IFSA World Congress and 20th NAFIPS International Conference (Vol 3), IEEE Computer Society, 2001, s. 1776-1779Konferansepaper (Fagfellevurdert)
    Abstract [en]

    We demonstrate how sigmoidal fuzzification affects discriminant capacities. In particular, we study thepreprocessing perceptron and compare it with the multilayer perceptron. Case studies are selected from the medical domain, where output performance needs to be related to requirements for high sensitivities. These smaller and more informative networks tend also to be more robust with respect to accuracy with various requirements on sensitivities

  • 259.
    Eklund, Patrik
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Karlsson, Johan
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Näslund, Annica
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Mobile pharmacology2006Inngår i: Advances in hybrid information technology: First international conference, ICHIT 2006, Jeju Island, Korea, november 9-11, 2006 / [ed] Marcin S. Szczuka, Daniel Howard, Dominik Slezak, Haeng-Kon Kim, Tai-Hoon Kim, Il Seok Ko, Geuk Lee, and Peter M. A. Sloot, Berlin/Heidelberg: Springer , 2006, s. 522-533Konferansepaper (Fagfellevurdert)
    Abstract [en]

    In mobile usage scenarios, patient care involving point of care considerations build upon increasingly complex information and information structures. Furthermore, communication of information must be enabled regardless of space and time. Decision support and guidelines are expected to communicate with other subsystems, such as those provided by information sources and hardware devices. As also these subsystems may build upon intelligence and involve their own usage scenarios, this implies further complications also the knowledge representation and software engineering tasks. In these developments, public health problems provide case studies with potentially rather huge impacts. Examples are provided e.g. by guidelines involving pharmacological treatment. Knowledge and reasoning need to interact with information management, and often involves utility of various devices. Well organized databases for pharmacological information are necessary for successful engineering of mobile extensions in these case studies. The public is now also one of the driving forces in these developments. As electronic prescriptions and generic substitutes are appreciated by the public, we experience how knowledge in its various forms provide success stories in this field.

  • 260.
    Eklund, Patrik
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Karlsson, Johan
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Rauch, J.
    Simunek, M.
    Computational coronary artery bypass grafting2005Inngår i: Sixth International Conference on Computational Intelligence and Multimedia Applications, 2005. / [ed] Selvaraj, H; Verma, B; DeCarvalho, A, IEEE Computer Society, 2005, s. 138-144Konferansepaper (Fagfellevurdert)
    Abstract [en]

    Multimedia in health care is a topic of growing interest. Guideline presentation, utility and adherence require intelligence and multimedia to interact in decision support environments. In this paper we aim at identifying guideline logic during statistical analysis. The case study is drawn from a regional perspective on analysis and production of data, information and knowledge.

  • 261.
    Eklund, Patrik
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Karlsson, Johan
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Rauch, Jan
    University of Economics, Prague, Faculty of Informatics and Statistics, Czech Republic.
    Simunek, Milan
    Academy of Sciences of the Czech Republic, Institute of Computer Science.
    On the logic of medical decision support2006Inngår i: Theory and applications of relational structures as knowledge instruments II: international workshops of COST action 274, TARSKI, 2002-2005, selected revised papers / [ed] Harrie C. M. de Swart, Ewa Orlowska, Gunther Schmidt and Mark Roubens, Berlin: Springer Berlin/Heidelberg, 2006, s. 50-59Kapittel i bok, del av antologi (Annet vitenskapelig)
    Abstract [en]

    Guideline development, implementation, utility and adherence require intelligence and multimedia to interact in decision support environments. However, efforts to combine all these aspects and to connect solutions into a effective, efficient and productive environment are rare. In this paper we use a regional health care perspective on maintenance and analysis of data, information and knowledge. Examples are drawn from cardiac diseases. Analysis and development is viewed from by-pass surgery point of view. Association rules are used for analysis, and we show how these rules take logical forms so as to prepare for development of guidelines.

  • 262.
    Eklund, Patrik
    et al.
    Department of Computer Science, Åbo Akademi University, Åbo, Finland.
    Kaufmann, Michael
    Hierarchical Wiring in Multigrids1990Inngår i: CONPAR 90 — VAPP IV: Joint International Conference on Vector and Parallel Processing Zurich, Switzerland, September 10–13, 1990 Proceedings / [ed] Helmar Burkhart, Springer Berlin/Heidelberg, 1990, s. 423-434Konferansepaper (Fagfellevurdert)
  • 263.
    Eklund, Patrik
    et al.
    Department of Computer Science, Åbo Akademi, Åbo, Finland.
    Klawonn, Frank
    Neural fuzzy logic programming1992Inngår i: IEEE Transactions on Neural Networks, ISSN 1045-9227, E-ISSN 1941-0093, Vol. 3, nr 5, s. 815-818Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    A foundational development of propositional fuzzy logic programs is presented. Fuzzy logic programs are structured knowledge bases including uncertainties in rules and facts. The precise specifications of uncertainties has a great influence on the performance of the knowledge base. We show how fuzzy logic programs can be transformed to neural nets, where adaptations of uncertainties in the knowledge base increase the reliability of the program and are carried out automatically.

  • 264.
    Eklund, Patrik
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Kortelainen, Jari
    Department of Information and Media Technology, Mikkeli University of Applied Sciences, Finland .
    Stout, Lawrence Neff
    Department of Mathematics and Computer Science, Illinois Wesleyan University, Illinois, USA .
    Adding fuzziness to terms and powerobjects using a monadic approach2012Inngår i: Fuzzy sets and systems (Print), ISSN 0165-0114, E-ISSN 1872-6801, Vol. 192, s. 104-122Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    Fuzzy mathematics often starts by taking a piece of classical mathematics and introducing fuzziness to existing mathematical concepts, and then proceeds to a more essential adoption of a fuzzy perspective. This paper explores this progression for two important monads: the powerset monad and its generalizations to fuzzy powerobjects, and the term monad and its generalization to using fuzzy sets of operators. This brings together two lines of research previously discussed at the Linz seminars. The powerset and its fuzzy analogs are important in the development of topology in a fuzzy world and the term monad and its fuzzy analogs are vital in understanding fuzzy computer science.

  • 265.
    Eklund, Patrik
    et al.
    Umeå universitet, Teknisk-naturvetenskaplig fakultet, Institutionen för datavetenskap.
    Lindgren, Helena
    Umeå universitet, Teknisk-naturvetenskaplig fakultet, Institutionen för datavetenskap.
    Towards Dementia Diagnosis Logic2006Inngår i: 11th Int. Conf. Information Processing and Management of Uncertainty in Knowledge-based Systems (IPMU'06), Paris: Editions EDK , 2006, s. 1251-1257Konferansepaper (Fagfellevurdert)
    Abstract [en]
    Historical motivations for classification systems in health care are requirements of data collections for statistics. Aims to unify data collections eventually becomes a starting point for nomenclature and ontology developments. Diagnosis encoding plays an important role in shifting the paradigm from providing statistics to making decisions. For logic and decision support the situation is non-trivial as nomenclatures continuously change and diagnostic categories are extended. Further, management of both phenomenology and etiology in differential diagnosis requires organisation and logical structure of information modalities and disease taxonomies. In this paper we provide a logical analysis of a diagnostic manual dividing mental disorders into disorder types. The subdivision is based on criteria (rule) sets and defining features (facts). Our focus is on dementia and we show and compare how particular underlying logic for encoding the dementia classifier can manage heterogeneity of individuals sharing a diagnosis and manyvaluedness of truth regarding diagnosis of boundary cases.
  • 266.
    Eklund, Patrik
    et al.
    Department of Computer Science, Åbo Akademi, Åbo, Finland.
    Malén, Tor-Erik
    Block Placement in Switching Networks1989Inngår i: Proceedings of the conference on CONPAR 88 / [ed] C.R. Jesshope, K.D. Reinartz, New York: Cambridge University Press, 1989, s. 299-305Konferansepaper (Fagfellevurdert)
  • 267.
    Eklund, Patrik
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Näslund, Annica
    Mobile guidelines for pharmacologic treatment of hypertension2004Inngår i: Studies in Health Technology and Informatics, ISSN 0926-9630, E-ISSN 1879-8365, Vol. 103, s. 58-60Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    Mobile health technologies provide case studies with potentially rather huge impacts. Examples are provided e.g. by guidelines involving pharmacologic treatment. Knowledge and reasoning need to interact with information management, and often involves utility of various devices. Well organised databases for pharmacological information are also necessary for successful engineering of mobile extensions in these case studies.

  • 268.
    Eklund, Patrik
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Rusinowska, Agnieszka
    de Swart, Harrie
    A consensus model of political decision-making2008Inngår i: Annals of Operations Research, ISSN 0254-5330, E-ISSN 1572-9338, Vol. 158, nr 1, s. 5-20Artikkel i tidsskrift (Annet vitenskapelig)
    Abstract [en]

    In this paper, a model of political consensus is introduced. Parties try to reach consensus in forming a government. A government is defined as a pair consisting of a winning coalition and a policy supported by this coalition, where a policy consists of policies on given issues. A party evaluates all governments the party belongs to with respect to some criteria. We allow the criteria to be of unequal importance to a party. These criteria concern winning coalitions and policy issues. Parties may be advised to adjust their preferences, i.e., to change their evaluation concerning some government(s) or/and the importance of the criteria, in order to obtain a better political consensus.

  • 269.
    Eklund, Patrik
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Rusinowska, Agnieszka
    Radboud University, Faculty of Management Science, Nijmegen, The Netherlands and Warsaw School of Economics, Department of Mathematical Economics, Warsaw, Poland.
    De Swart, Harrie
    Tilburg University, Faculty of Philosophy, Tilburg, The Netherlands.
    Consensus reaching in committees2007Inngår i: European Journal of Operational Research, ISSN 0377-2217, E-ISSN 1872-6860, Vol. 178, nr 1, s. 185-193Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    In this paper, we apply a consensus model to decision-making in committees that have to choose one or more alternatives from a set of alternatives. The model does not use a voting rule nor a set of winning coalitions. Every decision maker evaluates each alternative with respect to given criteria. The criteria may be of unequal importance to a decision maker. Decision makers may be advised by a chairman to adjust their preferences, i.e., to change their evaluation of some alternative(s) or/and the importance of the criteria, in order to obtain a better consensus. The consensus result should satisfy constraints concerning the consensus degree and the majority degree. A simple example is presented. (c) 2005 Elsevier B.V. All rights reserved.

  • 270.
    Eklund, Patrik
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Zhou, Jun
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Comparison of learning strategies for adaptation of fuzzy controller parameters1999Inngår i: Fuzzy sets and systems (Print), ISSN 0165-0114, E-ISSN 1872-6801, Vol. 106, nr 3, s. 321-333Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    For tuning fuzzy controllers, several parameter identification techniques are available, ranging from more robust descent methods to sophisticated optimisation. However, from an application point of view, it is not always clear that numerical sophistication wins over more pragmatic approaches to tuning. Obviously, the data sets play crucial roles in efforts to reach successful tuning. Especially data sets generated from real processes often contain not only noisy data and conflicting subsets, but also the connected problem of non-covering input spaces. In this paper we will compare several parameter identification techniques w.r.t. different data sets. We focus on selections of learning rates and on defining training sequences related to subclasses of parameters.

  • 271.
    Eklund, Patrik
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Ángeles Galán, M
    Department of Applied Mathematics, University of Málaga, Spain.
    Helgesson, Robert
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Kortelainen, Jari
    Department of Electrical Engineering and Information Technology, Mikkeli University of Applied Sciences, Finland.
    Fuzzy terms2014Inngår i: Fuzzy sets and systems (Print), ISSN 0165-0114, E-ISSN 1872-6801, Vol. 256, s. 211-235Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    In this paper we will show how purely categorical constructions of terms are advantageous when investigating situations concerning uncertainty; more specifically where uncertainty comes from and how uncertainty is integrated when dealing with terms over selected signatures. There are basically two ways of invoking uncertainty for terms. On one hand, we may proceed by building composed monads where uncertainty is provided by some suitable monad composed with the traditional term monad. On the other hand, we can provide a strictly formal basis for term monads being created over categories themselves carrying uncertainty. This is the distinction between 'computing with fuzzy' and 'fuzzy computing' and the fundamental question raised by these constructions is where uncertainty resides in language constructions for logic. This paper also shows how the notion of signature often needs to be expanded to levels of signatures, in particular when dealing with type constructors. Such levels allow us to strictly delineate, e.g., primitive operations, type terms, and value level terms. Levels of signature will in this paper be exemplified by the construction of the signature of simply typed lambda calculus.

  • 272.
    Eljammaly, Mahmoud
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Identification and tuning of algorithmic parameters in parallel matrix computations: Hessenberg reduction and tensor storage format conversion2018Licentiatavhandling, med artikler (Annet vitenskapelig)
    Abstract [en]

    This thesis considers two problems in numerical linear algebra and high performance computing (HPC): (i) the parallelization of a new blocked Hessenberg reduction algorithm using Parallel Cache Assignment (PCA) and the tunability of its algorithm parameters, and (ii) storing and manipulating dense tensors on shared memory HPC systems.

    The Hessenberg reduction appears in the Aggressive Early Deflation (AED) process for identifying converged eigenvalues in the distributed multishift QR algorithm (state-of-the-art algorithm for computing all eigenvalues for dense square matrices). Since the AED process becomes a parallel bottleneck it motivates a further study of AED components. We present a new Hessenberg reduction algorithm based on PCA which is NUMA-aware and targeting relatively small problem sizes on shared memory systems. The tunability of the algorithm parameters are investigated. A simple off-line tuning is presented and the performance of the new Hessenberg reduction algorithm is compared to its counterparts from LAPACK and ScaLAPACK. The new algorithm outperforms LAPACK in all tested cases and outperforms ScaLAPACK in problems smaller than order 1500, which are common problem sizes for AED in the context of the distributed multishift QR algorithm.

    We also investigate automatic tuning of the algorithm parameters. The parameters span a huge search space and it is impractical to tune them using standard auto-tuning and optimization techniques. We present a modular auto-tuning framework which applies: search space decomposition, binning, and multi-stage search to enable searching the huge search space efficiently. The framework using these techniques exposes the underlying subproblems which allows using standard auto-tuning methods to tune them. In addition, the framework defines an abstract interface, which combined with its modular design, allows testing various tuning algorithms.

    In the last part of the thesis, the focus is on the problem of storing and manipulating dense tensors. Developing open source tensor algorithms and applications is hard due to the lack of open source software for fundamental tensor operations. We present a software library dten, which includes tools for storing dense tensors in shared memory and converting a tensor storage format from one canonical form to another. The library provides two different ways to perform the conversion in parallel, in-place and out-of-place. The conversion involves moving blocks of contiguous data and are done to maximize the size of the blocks to move. In addition, the library supports tensor matricization for one or two tensors at the same time. The latter case is important in preparing tensors for contraction operations. The library is general purpose and highly flexible.

  • 273.
    Eljammaly, Mahmoud
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Karlsson, Lars
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    A library for storing and manipulating dense tensors2016Rapport (Annet vitenskapelig)
    Abstract [en]

    Aiming to build a layered infrastructure for high-performance dense tensor applications, we present a library, called dten, for storing and manipulating dense tensors. The library focuses on storing dense tensors in canonical storage formats and converting between storage formats in parallel. In addition, it supports tensor matricization in different ways. The library is general-purpose and provides a high degree of flexibility.

  • 274.
    Eljammaly, Mahmoud
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Karlsson, Lars
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Kågström, Bo
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap. Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Högpresterande beräkningscentrum norr (HPC2N).
    An auto-tuning framework for a NUMA-aware Hessenberg reduction algorithm2017Rapport (Annet vitenskapelig)
    Abstract [en]

    The performance of a recently developed Hessenberg reduction algorithm greatly depends on the values chosen for its tunable parameters. The search space is huge combined with other complications makes the problem hard to solve effectively with generic methods and tools. We describe a modular auto-tuning framework in which the underlying optimization algorithm is easy to substitute. The framework exposes sub-problems of standard auto-tuning type for which existing generic methods can be reused. The outputs of concurrently executing sub-tuners are assembled by the framework into a solution to the original problem.

  • 275.
    Eljammaly, Mahmoud
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Karlsson, Lars
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Kågström, Bo
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap. Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Högpresterande beräkningscentrum norr (HPC2N).
    An auto-tuning framework for a NUMA-aware Hessenberg reduction algorithm2018Inngår i: ICPE '18 Companion of the 2018 ACM/SPEC International Conference on Performance Engineering, ACM Digital Library, 2018, , s. 4s. 5-8Konferansepaper (Fagfellevurdert)
  • 276.
    Eljammaly, Mahmoud
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Karlsson, Lars
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap. Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Högpresterande beräkningscentrum norr (HPC2N).
    Kågström, Bo
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap. Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Högpresterande beräkningscentrum norr (HPC2N).
    Evaluation of the Tunability of a New NUMA-Aware Hessenberg Reduction Algorithm2016Rapport (Annet vitenskapelig)
  • 277.
    Eljammaly, Mahmoud
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Karlsson, Lars
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Kågström, Bo
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    On the Tunability of a New Hessenberg Reduction Algorithm Using Parallel Cache Assignment2018Inngår i: Parallel Processing and Applied Mathematics. PPAM 2017: Part 1 / [ed] Wyrzykowski R., Dongarra J., Deelman E., Karczewski K., Springer, 2018, s. 579-589Konferansepaper (Fagfellevurdert)
    Abstract [en]

    The reduction of a general dense square matrix to Hessenberg form is a well known first step in many standard eigenvalue solvers. Although parallel algorithms exist, the Hessenberg reduction is one of the bottlenecks in AED, a main part in state-of-the-art software for the distributed multishift QR algorithm. We propose a new NUMA-aware algorithm that fits the context of the QR algorithm and evaluate the sensitivity of its algorithmic parameters. The proposed algorithm is faster than LAPACK for all problem sizes and faster than ScaLAPACK for the relatively small problem sizes typical for AED.

  • 278.
    Elmroth, E.
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Gardfjall, P.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Tordsson, J.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Ali-Eldin, A.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    L., Larsson
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    METHOD, NODE AND COMPUTER PROGRAM FOR ENABLING AUTOMATIC ADAPTATION OF RESOURCE UNITS2015Patent (Annet (populærvitenskap, debatt, mm))
  • 279.
    Elmroth, Erik
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap. Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Högpresterande beräkningscentrum norr (HPC2N).
    Gardfjäll, Peter
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Design and Evaluation of a Decentralized System for Grid-wide Fairshare Scheduling2005Inngår i: Proceedings of the First International Conference on e-Science and Grid Computing (e-Science’05), USA, Los Alamitos: IEEE Computer Society Press , 2005, s. 221-229Konferansepaper (Fagfellevurdert)
    Abstract [en]

    This contribution presents a decentralized architecture for a grid-wide fairshare scheduling system and demonstrates its potential in a simulated environment. The system, which preserves local site autonomy, enforces locally and globally scoped share policies, allowing local resource capacity as well as global grid capacity to be logically divided across different groups of users. The policy model is hierarchical and subpolicy definition can be delegated so that, e.g., a VO that has been granted a resource share can partition its share across its projects, which in turn can divide their shares between project members. There is no need for a central coordinator as policies are enforced collectively by the resource schedulers. Each local scheduler adopts a grid-wide view on utilization in order to steer local resource utilization to not only maintain local resource shares but also to contribute to maintaining global shares across the entire set of grid resources. Share enforcement is addressed by an algorithm that calculates simple priority values, thus simplifying integration with local schedulers, which can remain unaware of the hierarchical share policy structure

  • 280.
    Elmroth, Erik
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap. Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Högpresterande beräkningscentrum norr (HPC2N).
    Gardfjäll, Peter
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Mulmo, Olle
    Sandholm, Thomas
    An OGSA-based Bank Service for Grid Accounting Systems2006Inngår i: State-of-the-art in Scientific Computing, Springer-Verlag , 2006, s. 1051-1060Konferansepaper (Fagfellevurdert)
    Abstract [en]

    This contribution presents the design and implementation of a bank service, constituting a key component in a recently developed Grid accounting system. The Grid accounting system maintains a Grid-wide view of the resources consumed by members of a virtual organization (VO). The bank is designed as an online service, managing the accounts of VO projects. Each service request is transparently intercepted by the accounting system, which acquires a reservation on a portion of the project’s bank account prior to servicing the request. Upon service completion, the account is charged for the consumed resources. We present the overall bank design and technical details of its major components, as well as some illustrative examples of relevant service interactions. The system, which has been implemented using the Globus Toolkit, is based on state-of-the-art Web and Grid services technology and complies with the Open Grid Services Architecture (OGSA).

  • 281.
    Elmroth, Erik
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Högpresterande beräkningscentrum norr (HPC2N). Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Gardfjäll, Peter
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Tordsson, Johan
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    An Advanced Grid Computing Course for Application and Infrastructure Developers2005Inngår i: 2005 IEEE International Symposium on Cluster Computing and the Grid, USA: IEEE Computer Society Press , 2005, s. 43-50Konferansepaper (Fagfellevurdert)
    Abstract [en]

    This contribution presents our experiences from developing an advanced course in grid computing, aimed at application and infrastructure developers. The course was intended for computer science students with extensive programming experience and previous knowledge of distributed systems, parallel computing, computer networking, and security. The presentation includes brief presentations of all topics covered in the course, a list of the literature used, and descriptions of the mandatory computer assignments performed using Globus Toolkit 2 and 3. A summary of our experiences from the course and some suggestions for future directions concludes the presentation.

  • 282.
    Elmroth, Erik
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Gustavson, F. G.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Applying recursion to serial and parallel QR factorization leads to better performance2000Inngår i: IBM Journal of Research and Development, ISSN 0018-8646, E-ISSN 2151-8556, Vol. 44, nr 4, s. 605-624Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    We present new recursive serial and parallel algorithms for QR factorization of an m by n matrix. They improve performance. The recursion leads to an automatic variable blocking, and it also replaces a Level 2 part in a standard block algorithm with Level 3 operations. However, there are significant additional costs for creating and performing the updates, which prohibit the efficient use of the recursion for large n. We present a quantitative analysis of these extra costs. This analysis leads us to introduce a hybrid recursive algorithm that outperforms the LAPACK algorithm DGEQRF by about 20% for large square matrices and up to almost a factor of 3 for tall thin matrices. Uniprocessor performance results are presented for two IBM RS/6000(R) SP nodes-a 120-MHz IBM POWER2 node and one processor of a four-way 332-MHz IBM PowerPC(R) 604e SMP node. The hybrid recursive algorithm reaches more than 90% of the theoretical peak performance of the POWER2 node, Compared to standard block algorithms, the recursive approach also shows a significant advantage in the automatic tuning obtained from its automatic variable blocking. A successful parallel implementation on a four-way 332-MHz IBM PPC604e SMP node based on dynamic load balancing is presented. For two, three, and four processors it shows speedups of up to 1.97, 2.99, and 3.97.

  • 283.
    Elmroth, Erik
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Henriksson, Daniel
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Distributed usage logging for federated grids2010Inngår i: Future generations computer systems, ISSN 0167-739X, E-ISSN 1872-7115, Vol. 26, nr 8, s. 1215-1225Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    We present a non-intrusive solution to the increasingly important problem of shared logging for overlapping and federated Grid environments. The solution addresses three usage scenarios of hierarchical Grids, mutual cross-Grid resource utilization, and federated Cloud computing infrastructures. The approach is evaluated by extending the existing SweGrid Accounting System (SGAS) with a light-weight component that makes the system applicable to a wide range of usage scenarios. The proposed architecture is characterized by its simplicity, flexibility, and generality, and the new key component by its non-intrusiveness, flexibility, and ability to manage high load. We present requirements derived from three usage scenarios, and also include an in-depth description of the architecture and design, as well as the implementation and performance evaluation of a new component written for use with SGAS. We conclude from a performance evaluation that the sharing of usage data is not likely to be a limiting performance factor even in large-scale Grid scenarios.

  • 284.
    Elmroth, Erik
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Högpresterande beräkningscentrum norr (HPC2N). Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Hernández, Francisco
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Tordsson, Johan
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    A light-weight Grid workflow execution service enabling client and middleware independence2008Inngår i: Parallel Processing and Applied Mathematics: 7th International Conference on Parallel Processing and Applied Mathematics (PPAM 2007), Springer-Verlag , 2008, s. 754-761Konferansepaper (Fagfellevurdert)
    Abstract [en]

    We present a generic and light-weight Grid workflow execution engine made available as a Grid service. A long-term goal is to facilitate the rapid development of application-oriented end-user workflow tools, while providing a high degree of Grid middleware-independence. The workflow engine is designed for workflow execution, independent of client tools for workflow definition. A flexible plugin-structure for middleware-integration provides a strict separation of the workflow execution and the processing of individual tasks, such as computational jobs or file transfers. The light-weight design is achieved by focusing on the generic workflow execution components and by leveraging state-of-the art Grid technology, e.g., for state management. The current prototype is implemented using the Globus Toolkit 4 (GT4) Java WS Core and has support for executing workflows produced by Karajan. It also includes plugins for task execution with GT4 as well as a high-level Grid job management framework.

  • 285.
    Elmroth, Erik
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Hernández, Francisco
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Tordsson, Johan
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Three fundamental dimensions of scientific workflow interoperability: model of computation, language, and execution environment2010Inngår i: Future generations computer systems, ISSN 0167-739X, E-ISSN 1872-7115, Vol. 26, nr 2, s. 245-256Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    We investigate interoperability aspects of scientific workflow systems and argue that the workflow execution environment, the model of computation (MoC), and the workflow language form three dimensions that must be considered depending on the type of interoperability sought: at the activity, sub-workflow, or workflow levels. With a focus on the problems that affect interoperability, we illustrate how these issues are tackled by current scientific workflows as well as how similar problems have been addressed in related areas. Our long-term objective is to achieve (logical) interoperability between workflow systems operating under different MoCs, using distinct language features, and sharing activities running on different execution environments.

  • 286.
    Elmroth, Erik
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Högpresterande beräkningscentrum norr (HPC2N). Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Hernández, Francisco
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Tordsson, Johan
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Östberg, Per-Olov
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Designing service-based resource management tools for a healthy grid ecosystem2008Inngår i: Parallel processing and applied mathematics: 7th International Conference on Parallel Processing and Applied Mathematics, Springer-Verlag , 2008, s. 259-270Konferansepaper (Fagfellevurdert)
    Abstract [en]

    We present an approach for development of Grid resource management tools, where we put into practice internationally established high-level views of future Grid architectures. The approach addresses fundamental Grid challenges and strives towards a future vision of the Grid where capabilities are made available as independent and dynamically assembled utilities, enabling run-time changes in the structure, behavior, and location of software. The presentation is made in terms of design heuristics, design patterns, and quality attributes, and is centered around the key concepts of co-existence, composability, adoptability, adaptability, changeability, and interoperability. The practical realization of the approach is illustrated by five case studies (recently developed Grid tools) high-lighting the most distinct aspects of these key concepts for each tool. The approach contributes to a healthy Grid ecosystem that promotes a natural selection of “surviving” components through competition, innovation, evolution, and diversity. In conclusion, this environment facilitates the use and composition of components on a per-component basis.

  • 287.
    Elmroth, Erik
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Holmgren, S.
    Lindemann, J.
    Toor, S.
    Östberg, Per-Olov
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Empowering a flexible application portal with a SOA-based Grid job management framework2009Inngår i: Applied Parallel Computing (PARA 08): State of art in scientific computing / [ed] A.C. Elster et al., Springer , 2009Konferansepaper (Fagfellevurdert)
  • 288.
    Elmroth, Erik
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Johansson, Pedher
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Kreßner, Daniel
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Kågström, Bo
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap. Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Högpresterande beräkningscentrum norr (HPC2N).
    A Web Computing Environment for the SLICOT Library2001Inngår i: The Third NICONET Workshop on Numerical Control Software, s. 53-61Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    A prototype web computing environment for computations related to the design and analysis of control systems using the SLICOT software library is presented. The web interface can be accessed from a standard world wide web browser with no need for additional software installations on the local machine. The environment provides user-friendly access to SLICOT routines where run-time options are specified by mouse clicks on appropriate buttons. Input data can be entered directly into the web interface by the user or uploaded from a local computer in a standard text format or in Matlab binary format. Output data is presented in the web browser window and possible to download in a number of different formats, including Matlab binary. The environment is ideal for testing the SLICOT software before performing a software installation or for performing a limited number of computations. It is also highly recommended for education as it is easy to use, and basically self-explanatory, with the users' guide integrated in the user interface.

  • 289.
    Elmroth, Erik
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Johansson, Pedher
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Kågström, Bo
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap. Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Högpresterande beräkningscentrum norr (HPC2N).
    Computation and presentation of graphs displaying closure hierarchies of Jordan and Kronecker structures2001Inngår i: Numerical Linear Algebra with Applications, ISSN 1070-5325, E-ISSN 1099-1506, Vol. 8, nr 6-7, s. 381-399Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    StratiGraph, a Java-based tool for computation and presentation of closure hierarchies of Jordan and Kronecker structures is presented. The tool is based on recent theoretical results on stratifications of orbits and bundles of matrices and matrix pencils. A stratification reveals the complete hierarchy of nearby structures. information critical for explaining the qualitative behaviour of linear systems under perturbations. StratiGraph facilitates the application of these theories and visualizes the resulting hierarchy as a graph. Nodes in the graph represent orbits or bundles of matrices or matrix pencils. Edges represent covering relations in the closure hierarchy. Given a Jordan or Kronecker structure, a user can obtain the complete information of nearby structures simply by mouse clicks on nodes of interest. This contribution gives an overview of the StratiGraph tool, presents its main functionalities and other features, and illustrates its use by sample applications.

    Copyright (C) 2001 John Wiley & Sons, Ltd.

  • 290.
    Elmroth, Erik
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Johansson, Stefan
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Kågström, Bo
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap. Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Högpresterande beräkningscentrum norr (HPC2N).
    Stratification of controllability and observability pairs: theory and use in applications2009Inngår i: SIAM Journal on Matrix Analysis and Applications, ISSN 0895-4798, E-ISSN 1095-7162, Vol. 31, nr 2, s. 203-226Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    Cover relations for orbits and bundles of controllability and observability pairs associated with linear time-invariant systems are derived. The cover relations are combinatorial rules acting on integer sequences, each representing a subset of the Jordan and singular Kronecker structures of the corresponding system pencil. By representing these integer sequences as coin piles, the derived stratification rules are expressed as minimal coin moves between and within these piles, which satisfy and preserve certain monotonicity properties. The stratification theory is illustrated with two examples from systems and control applications, a mechanical system consisting of a thin uniform platform supported at both ends by springs, and a linearized Boeing 747 model. For both examples, nearby uncontrollable systems are identified as subsets of the complete closure hierarchy for the associated system pencils.

  • 291.
    Elmroth, Erik
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Larsson, Lars
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Interfaces for Placement, Migration, and Monitoring of Virtual Machines in Federated Clouds2009Inngår i: Proceedings of the Eighth International Conference on Grid and Cooperative Computing (GCC 2009) / [ed] Juan. E. Guerrero, IEEE Computer Society Press , 2009, s. 253-260Konferansepaper (Fagfellevurdert)
    Abstract [en]

    Current cloud computing infrastructure offerings are lacking in interoperability, which is a hindrance to the advancement and adoption of the cloud computing paradigm. As clouds are made interoperable, federations of clouds may be formed. Such federations are from the point of view of the user not burdened by vendor lock-in, and opens for business possibilities where a market place of cloud computing infrastructure can be formed. Federated clouds require unified management interfaces regarding the virtual machines (VMs) that comprise the services running in the cloud federation. Standardization efforts for the required management interfaces have so far focused on definition of description formats regarding VMs, and the control of already deployed VMs. We propose technology neutral interfaces and architectural additions for handling placement, migration, and monitoring of VMs in federated cloud environments, the latter as an extension of current monitoring architectures used in grid computing. The interfaces presented adhere to the general requirements of scalability, efficiency, and security in addition to specific requirements related to the particular issues of interoperability and business relationships between competing cloud computing infrastructure providers. In addition, they may be used equally well locally and remotely, creating a layer of abstraction that simplifies management of virtualized service components.

  • 292.
    Elmroth, Erik
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Leitner, Philipp
    Schulte, Stefan
    Venugopal, Srikumar
    Connecting Fog and Cloud Computing2017Inngår i: IEEE Cloud Computing, ISSN 2325-6095, Vol. 4, nr 2, s. 22-25Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    Fog computing provides a conceptual approach for virtualizing and orchestrating computing, networking, and storage resources to process data. This issue helps to progress the fog computing research field and offer solutions.

  • 293.
    Elmroth, Erik
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Marquez, Fermin Galan
    Telef´onica Investigaci´on y Desarrollo, Spain.
    Henriksson, Daniel
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Ferrera, David Perales
    Telef´onica Investigaci´on y Desarrollo, Spain.
    Accounting and Billing for Federated Cloud Infrastructures2009Inngår i: Proceedings of the Eighth International Conference on Grid and Cooperative Computing (GCC 2009) / [ed] Juan. E. Guerrero, IEEE Computer Society Press , 2009, s. 268-275Konferansepaper (Fagfellevurdert)
    Abstract [en]

    Emerging Cloud computing infrastructures provide computing resources on demand based on postpaid principles. For example, the RESERVOIR project develops an infrastructure capable of delivering elastic capacity that can automatically be increased or decreased in order to cost-efficiently fulfill established Service Level Agreements. This infrastructure also makes it possible for a data center to extend its total capacity by subcontracting additional resources from collaborating data centers, making the infrastructure a federation of Clouds. For accounting and billing, such infrastructures call for novel approaches to perform accounting for capacity that varies over time and for services (or more precisely virtual machines) that migrate between physical machines or even between data centers. For billing, needs arise for new approaches to simultaneously manage postpaid and prepaid payment schemes for capacity that varies over time in response to user needs. In this paper, we outline usage scenarios and a set of requirements for such infrastructures, and propose an accounting and billing architecture to be used within RESERVOIR. Even though the primary focus for this architecture is accounting and billing between resource consumers and infrastructure provides, future support for inter-site billing is also taken into account.

  • 294.
    Elmroth, Erik
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Nylén, Mats
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för fysik. Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Högpresterande beräkningscentrum norr (HPC2N).
    Oscarsson, Roger
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Högpresterande beräkningscentrum norr (HPC2N).
    A User-Centric Cluster and Grid Computing Portal2009Inngår i: International Journal of Computational Science and Engineering (IJCSE), ISSN 1742-7185, E-ISSN 1742-7193, Vol. 4, nr 2, s. 127-134Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    The HPC2N Grid portal is a user-centric environment that provides a homogeneous interface to a set of heterogeneous High-Performance Computing (HPC) resources from standard web-browsers. The interface includes support for most everyday activities, such as to submit, manipulate and delete jobs, monitor queues and job status, obtain user-, project-, and resource information, view job output, etc. This contribution reviews the portal functionalities and presents the design and implementation of the underlying system architecture. Some major design considerations, features and limitations are discussed. The portal currently gives access to all major resources at HPC2N, in total comprising over 700 CPUs.

  • 295.
    Elmroth, Erik
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Sandgren, Åke
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Högpresterande beräkningscentrum norr (HPC2N).
    Tordsson, Johan
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Resource Management for Early Production Grids2003Rapport (Annet (populærvitenskap, debatt, mm))
    Abstract [en]

    This contribution presents the ongoing development of a resource managerfor use in early production grids. Even though our main focus is todevelop a stable brokering facility for current production grids, we alsoaddress features needed in further improved resource managers for futureenhanced grid infrastructures. The primary target environment is theNorduGrid platform, comprising around 20 parallel systems in 5 countries,available for production grid jobs 24 hours a day. Application characteristicsconsidered include serial, parallel, and coordinated multi-resourcejobs running in sequence or in parallel, all types in either interactive ornon-interactive mode. The brokering process aims to minimize the timeto delivery for each individual job and is based on a number of new featuresincluding reservation capability, information about currently usedor reserved capacity, benchmark-scaled time predictions, and queue adaptationcapability. We present the basic motivations for all these featuresand discuss various issues regarding their implementations in the currentgrid environment.

  • 296.
    Elmroth, Erik
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap. Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Högpresterande beräkningscentrum norr (HPC2N).
    Skelander, Rikard
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Semi-automatic generation of Grid computing interfaces for numerical software libraries2006Inngår i: State-of-the-art in Scientific Computing, Springer-Verlag , 2006, s. 404-412Konferansepaper (Fagfellevurdert)
    Abstract [en]

    There is an immediate need to develop Grid interfaces for a large set of numerical software libraries, in order to make popular software of today available in the computing infrastructure of tomorrow. As this development work tend to be both tedious and error-prone, this contribution presents a semi-automatic process for generating the interfaces. The underlying principle is to use a front-end tuned for each numerical library and a back-end for each Grid environment considered. Then all library—Grid environment combinations can be generated with a small amount of manual work. The presentation of the main ideas is followed by a proof-of-concept implementation that generates NetSolve interfaces for the complete SLICOT software library, a numerical library comprising nearly 400 Fortran subroutines for numerical computations in the design and analysis of control systems.

  • 297.
    Elmroth, Erik
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap. Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Högpresterande beräkningscentrum norr (HPC2N).
    Tordsson, Johan
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    A Grid Resource Broker Supporting Advance Reservations and Benchmark-based Resource Selection2006Inngår i: Applied Parallel Computing: State-of-the-art in Scientific Computing, Springer Verlag , 2006, s. 1061-1070Konferansepaper (Fagfellevurdert)
    Abstract [en]

    This contribution presents algorithms, methods, and software for a Grid resource manager, responsible for resource brokering and scheduling in early production Grids. The broker selects computing resources based on actual job requirements and a number of criteria identifying the available resources, with the aim to minimize the total time to delivery for the individual application. The total time to delivery includes the time for program execution, batch queue waiting, input/output data transfer, and executable staging. Main features of the resource manager include advance reservations, resource selection based on computer benchmark results and network performance predictions, and a basic adaptation facility.

  • 298.
    Elmroth, Erik
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Tordsson, Johan
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    A standards-based Grid resource brokering service supporting advance reservations, coallocation and cross-Grid interoperability2009Inngår i: Concurrency and Computation, ISSN 1532-0626, E-ISSN 1532-0634, Vol. 21, nr 18, s. 2298-2335Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    The problem of Grid-middleware interoperability is addressed by the design and analysis of a feature-rich, standards-based framework for all-to-all cross-middleware job submission.The architecture is designed with focus on generality and flexibility and builds on extensive use, internally and externally, of (proposed) Web and Grid services standards such asWSRF, JSDL, GLUE, and WS-Agreement. The external use providesthe foundation for easy integration into specific middlewares,which is performed by the design of a small set of plugins for each middleware. Currently, plugins are provided for integrationinto Globus Toolkit 4 and NorduGrid/ARC. The internal use of standard formats facilitates customizationof the job submission service by replacement of custom components for performing specific well-defined tasks.Most importantly, this enables the easy replacement of resource selection algorithms by algorithms that addresses the specific needs of a particular Grid environment and job submission scenario.By default, the service implements a decentralized brokering policy, strivingto optimize the performance for the individual user by minimizing the response time for each job submitted. The algorithms in our implementation perform resource selectionbased on performance predictions, and provide support for advance reservations as well as coallocation of multiple resources for coordinated use.The performance of the system is analyzed with focuson overall service throughput (up to over 250 jobs per minute)and individual job submission response time (down to under one second).

  • 299.
    Elmroth, Erik
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap. Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Högpresterande beräkningscentrum norr (HPC2N).
    Tordsson, Johan
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    An Interoperable, Standards-Based Grid Resource Broker and Job Submission Service2005Inngår i: First International Conference on e-Science and Grid Computing, 2005, s. 212-220Konferansepaper (Fagfellevurdert)
    Abstract [en]

    We present the architecture and implementation of a grid resource broker and job submission service, designed to be as independent as possible of the grid middleware used on the resources. The overall architecture comprises seven general components and a few conversion and integration points where all middleware-specific issues are handled. The implementation is based on state-of-the-art grid and Web services technology as well as existing and emerging standards (WSRF, JSDL, GLUE, WS-Agreement). Features provided by the service include advance reservations and a resource selection process based on a priori estimations of the total time to delivery for the application, including a benchmark-based prediction of the execution time. The general service implementation is based on the Globus Toolkit 4. For test and evaluation, plugins and format converters are provided for use with the NorduGrid ARC middleware

  • 300.
    Elmroth, Erik
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Högpresterande beräkningscentrum norr (HPC2N). Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Tordsson, Johan
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Grid resource brokering algorithms enabling advance reservations and resource selection based on performance predictions2008Inngår i: Future generations computer systems, ISSN 0167-739X, E-ISSN 1872-7115, Vol. 24, nr 6, s. 585-593Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    We present algorithms, methods, and software for a Grid resource manager, that performs resource brokering and job scheduling in production Grids. This decentralized broker selects computational resources based on actual job requirements, job characteristics, and information provided by the resources, with the aim to minimize the total time to delivery for the individual application. The total time to delivery includes the time for program execution, batch queue waiting, and transfer of executable and input/output data to and from the resource. The main features of the resource broker include two alternative approaches to advance reservations, resource selection algorithms based on computer benchmark results and network performance predictions, and a basic adaptation facility. The broker is implemented as a built-in component of a job submission client for the NorduGrid/ARC middleware.

3456789 251 - 300 of 840
RefereraExporteraLink til resultatlisten
Permanent link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf