mirage

Browsing by Title

DSpace/Manakin Repository

Browsing by Title

Sort by: Order: Results:

  • Laboratoire de l'informatique du parallélisme; Desprez, Frédéric; Domas, Stéphane; Dongarra, Jack; Petitet, Antoine; Randriamaro, Cyril; Robert, Yves (1998-03)
    (eng) This article is devoted to the run-time redistribution of one-dimensional arrays that are distributed in a block-cyclic fashion over a processor grid. In a previous paper, we have reported how to derive optimal ...
  • Laboratoire de l'informatique du parallélisme; Revol, Nathalie; Rouillier, Fabrice (2002-07)
    (eng) This paper explains why an arbitrary precision interval arithmetic is needed: to provide accurate results, an interval computation requires small input intervals; this explains why bisection is so often employed in ...
  • Laboratoire de l'informatique du parallélisme; Aumage, Olivier; Mercier, Guillaume; Namyst, Raymond (2000-10)
    (eng) This report introduces a version of MPICH handling efficiently different networks simultaneously. The core of the implementation relies on a device called ch_mad which is based on a generic multiprotocol communication ...
  • Benoit, Anne; Rehn-Sonigo, Veronika; Robert, Yves; Laboratoire de l'informatique du parallélisme (LIP, 2007-06)
    (ENG) Mapping workflow applications onto parallel platforms is a challenging problem, even for simple application patterns such as pipeline graphs. Several antagonist criteria should be optimized, such as throughput ...
  • Amestoy, Patrick R.; Duff, I.S.; L'Excellent, Jean-Yves; Koster, J.; Laboratoire de l'informatique du parallélisme (LIP, 2002-12)
    (eng) This document describes the Fortran 90 and C user interface to MUMPS Version 4.2 beta, a software package for the solution of sparse systems of linear equations. We describe in detail the data structures, parameters, ...
  • Laboratoire de l'informatique du parallélisme; Detrey, Jérémie; de Dinechin, Florent (2001-11)
    (eng) This paper presents a core generator for arbitrary numeric functions on Xilinx Virtex FPGAs. The cores use the state-of-the-art multipartite table method, which allows input and output precisions in the range of 8 ...
  • Laboratoire de l'informatique du parallélisme; Grimmer, Markus; Petras, Knut; Revol, Nathalie (2003-06)
    (eng) We give a survey on packages for multiple precision interval arithmetic, with the main focus on three specific packages. One is within a Maple environment, intpakX, and two are C/C++ libraries, GMP-XSC and MPFI. We ...
  • Centre national de la recherche scientifique, Institut de mathématiques économiques; Marchal, J.; Poulon, F. (IME, 1977-12)
    La théorie du multiplicateur est étroitement liée à l'analyse de circuit (et de ce fait à l'analyse macroéconomique). Le multiplicateur est défini à partir de la comparaison de deux situations d'équilibre de long terme ...
  • Laboratoire de l'informatique du parallélisme; Beuchat, Jean-Luc; Muller, Jean-Michel (2005-02)
    (eng) The RN-codings are particular cases of signed-digit representations, for which rounding to the nearest is always identical to truncation. In radix $2$, Booth recoding is an RN-coding. In this paper, we suggest several ...
  • Laboratoire de l'informatique du parallélisme; Lefevre, Vincent (1999-01)
    (eng) We present an algorithm allowing to perform integer multiplications by constants. This algorithm is compared to existing algorithms. Such algorithms are useful, as they occur in several problems, such as the ...
  • Centre national de la recherche scientifique, Laboratoire d'analyse et de techniques économiques; Baumont, Catherine; Bourdon, Françoise; Guillain, Rachel (LATEC, 2003-09)
    (FRE) L'objectif de cette recherche est d'étudier les mutations existant au sein de la configuration urbaine de la Communauté de l'Agglomération Dijonnaise, à travers notamment les nouvelles logiques de localisation des ...
  • BILLOT, Antoine-Bertrand; Université de Dijon, Institut de mathématiques économiques, Dijon, FRA; CNRS, Institut de mathématiques économiques, Dijon, FRA (1987)
    Développement d'un cadre dans lequel les agents n'expriment pas un jugement précis de booléen, mais classent l'objet de leur choix selon un préordre flou, et dans lequel l'intervention du planificateur est limitée au choix ...
  • Herbert, Marc; Laboratoire de l'informatique du parallélisme (LIP, 2002-03)
    (eng) This report describes the technical aspects of the developpement of a Myrinet LANAI code on a Linux platform. It contains information and references that can be useful to people wishing to develop in a similar context, ...
  • Louala, Christine; Vedovotto, Nathalie; Institut de l'information scientifique et technique (INIST-CNRS, 2004-06)
    Le développement des nanosciences et nanotechnologies entraîne des mutations conceptuelles qui intègrent les apports de la physique quantique. Ce tournant technologique aux enjeux multiples aura un impact incontestable sur ...
  • BALESTRA, Pietro; PICHERY, Marie-Claude; Université de Dijon, Institut de mathématiques économiques, Dijon, FRA; CNRS, Institut de mathématiques économiques, Dijon, FRA (1988)
    On analyse de manière systématique le rôle joué par les «contraintes naturelles» dans l'estimation d'un système d'équations simultanées
  • Laboratoire de l'informatique du parallélisme; Boldo, Sylvie; Daumas, Marc (2002-11)
    (eng) Studying floating point arithmetic, authors have shown that the implemented operations (addition, subtraction, multiplication, division and square root) can compute a result and an exact correcting term using the ...
  • Laboratoire de l'informatique du parallélisme; Darte, Alain; Schreiber, Robert (2004-12)
    (eng) We want to perform compile-time analysis of an SPMD program and place barriers in it to synchronize it correctly, minimizing the runtime cost of the synchronization. This is the barrier minimization problem. No full ...
  • Laboratoire de l'informatique du parallélisme; Silber, Georges-Andre; Darte, Alain (1998-09)
    (eng) We describe Nestor, a library to easily manipulate Fortran programs through a high level internal representation based on C++ classes. Nestor is a research tool that can be used to quickly implement source to source ...
  • Laboratoire de l'informatique du parallélisme; Casanova, Henri; Marchal, Loris (2002-10)
    (eng) In this work we investigate network models that can be potentiallyemployed in the simulation of scheduling algorithms for distributedcomputing applications. We seek to develop a model of TCP communicationwhich is ...
  • Laboratoire de l'informatique du parallélisme; Thierry, Eric (2003-10)
    (eng) This paper provides a new upper bound on the 2-dimension of partially ordered sets. The 2-dimension of an ordered set P is the smallest
Bookmark and Share