mirage

# Parcourir LIP - Laboratoire de l'Informatique du Parallélisme par titre

Tri par : Ordre : Résultats :

• (2002-10)
(eng) The ratio between processor speed and memory speed frequently makes efficient use of cache memory a very important element in performance of user's application. This is the case for many elementary function algorithms. ...
• (1999-11)
(eng) This paper presents a survey of the state-of-the-art techniques and prototypes for Web caches. The basic principles are presented, the most important hardwares and softwares approaches are described.
• (1995-12)
(eng) We present here the use, the implementation and the performances, of the usual message-passing libraries NX, PVM and MPI on the Capitan machine. In particular, the implementation of a multi-user environment is described.
• (1994-12-27)
(eng) We apply the theory of generalised concrete data structures (or gCDSs) to construct a cartesian closed category of concrete array structures with explicit data layout. The technical novelty is the array gCDS preserved ...
• (1998-06)
(eng) The Besicovitch and Weyl pseudometrics on the space $A^{\ZZ}$ of biinfinite sequences measure the density of differences in either the central or arbitrary segments of given sequences. The Besicovitch and Weyl spaces ...
• (LIP, 2008-10)
(ENG) In many numerical programs there is a need for a high-quality floating-point approximation of useful functions f, such as exp, sin, erf. In the actual implementation, the function is replaced by a polynomial p, ...
• (LIP, 2007-06)
(eng) The high-quality floating-point implementation of useful functions f : R → R, such as exp, sin, erf requires bounding the error ε = p−f f of an approximation p with regard to the function f. This involves bounding ...
• (2004-09)
(eng) A discretized rotation is the composition of an Euclidean rotation with the rounding operation. For $0 < \alpha < \pi/4$, we prove that the discretized rotation $\round{r_\alpha}$ is bijective if and only if there ...
• (1995-04)
(eng) In this paper, we deal with modular mappings as introduced by Lee and Fortes, and we build upon their results. Our main contribution is a characterization of one-to-one modular mappings that is valid even when the ...
• (2004-05)
(eng) We investigate some fundamental properties of the reduction relation in the untyped term calculus derived from Curien and Herbelin's lambda-mu-mu~. The original lambda-mu-mu~ has a system of simple types, based on ...
• (1999-02)
(eng) In the context of a video server project, we look at fault tolerant communication services. As the Myrinet network has been selected for this project, we focus on the GM system, which has the appropriate properties, ...
• (2002-12)
(eng) We aim at finding the best possible seed values when computing reciprocals, square-roots and square-root reciprocals in a given interval using Newton-Raphson iterations. A natural choice of the seed value would be ...
• (2001-11)
(eng) Robertson and Seymour conjectured that the treewidth of a planar graph and the treewidth of its geometric dual differ by at most one. Lapoire solved the conjecture in the affirmative, using algebraic techniques. We ...
• (1995-09)
(eng) This paper presents the proof of correctness of a multiplier circuit formalized in the calculus of inductive constructions. It uses a representation of the circuit as a function from the stream of inputs to the stream ...
• (1995-11)
(eng) Bouclettes is a source to source loop nest parallelizer. It takes as input Fortran uniform, perfectly nested loops and gives as output a HPF (High Performance Fortran) program with data distribution and parallel ...
• (2004-04)
(eng) We consider a distributed system where processes can only communicate by message passing and need a coherent view of the load (e.g., workload, memory) of others to take dynamic decisions (scheduling). We present ...
• (1996-11)
(eng) Tiling is a technique used for exploiting medium-grain parallelism in nested loops. It relies on a first step that detects sets of permutable nested loops. All algorithms developed so far consider the statements of ...
• (2007-02)
(eng) Min, Veeravalli, and Barlas proposed strategies to minimize the overall execution time of one or several divisible loads on a heterogeneous linear network, using one or more installments. We show on a very simple ...
• (LIP, 2007-05)
(eng) Today, clusters are often interconnected by long distance networks within grids to offer a huge number of available ressources to a range of users. MPI, the standard communication library used to write parallel ...
• (1995-05-24)
(eng) In this paper, we compare three nested loops parallelization algorithms (Allen and Kennedy's algorithm, Wolf and Lam's algorithm and Darte and Vivien's algorithm) that use different representations of distance vectors ...

# Recherche

Recherche avancée