Evolution of parallel machines (2008)
Yves Robert, École Normale, Supérieure Lyon, Larry Carter, Henri Casanova, Jeanne Ferrante, ...
Evolution of parallel machines... and soon to the Holy Grid? Parallel algorithm design and scheduling were already difficult tasks with homogeneous machines Yves Robert Scheduling for Heterogeneous...
Mapping and load-balancing iterative computations on heterogeneous clusters (2008)
Arnaud Legrand, Hélène Renard, Yves Robert, Frédéric Vivien
This paper is devoted to mapping iterative algorithms onto heterogeneous clusters. The application data is partitioned over the processors, which are arranged along a virtual ring. At each iteration,...
Alan Su, Frédéric Vivien, École Normale, Supérieure Lyon, École Normale, Supérieure Lyon, ...
when scheduling flows of divisible requests
École Normale, Supérieure Lyon, Loris Marchal, Frédéric Vivien, École Normale, Supérieure Lyon, ...
Offline and online scheduling of concurrent
encadré par Yves Robert, (2006)
École Normale, Supérieure Lyon, Veronika Rehn, Frédéric Vivien, Loris Marchal, École Normale, ...
Rapport de M2 N o DEA2006-05 Scheduling and data redistribution strategies on star platforms
Revisiting matrix product on master-worker platforms (2006)
Jean-françois Pineau, Yves Robert, Frédéric Vivien, Zhiao Shi, Jack Dongarra
This paper is aimed at designing efficient parallel matrix-product algorithms for heterogeneous master-worker platforms. While matrix-product is well-understood for homogeneous 2D-arrays of...
Data redistribution algorithms for heterogeneous processor rings (2004)
École Normale, Supérieure Lyon, Hélène Renard, Yves Robert, Frédéric Vivien, École Normale, ...
We consider the problem of redistributing data on homogeneous and heterogeneous ring of processors. The problem arises in several applications, each time after that a load-balancing mechanism is...
Mapping and Load-Balancing Iterative Computations (2004)
Arnaud Legr, Hélène Renard, Yves Robert, Senior Member, Frédéric Vivien
Abstract—This paper is devoted to mapping iterative algorithms onto heterogeneous clusters. The application data is partitioned over the processors, which are arranged along a virtual ring. At each...
École Normale, Supérieure Lyon, Unité Mixte, Hélène Renard, Yves Robert, ...
Load-balancing iterative computations in heterogeneous clusters with shared communication links
Load-Balancing Scatter Operations for Grid Computing (2003)
Stéphane Genaud, Arnaud Giersch, Frédéric Vivien
We present solutions to statically load-balance scatter operations in parallel codes run on Grids. Our loadbalancing strategy is based on the modification of the data distributions used in scatter...
Load-Balancing Scatter Operations for Grid Computing (2003)
Unit Mixte, Stéphane Genaud, Stphane Genaud, ...
We present solutions to statically load-balance scatter operations in parallel codes run on grids. Our load-balancing strategy is based on the modication of the data distributions used in scatter...
Loop parallelization algorithms: from parallelism extraction to code generation (2001)
Pierre Boulet, Alain Darte, Georges-André Silber, Frédéric Vivien
Incrementalized Pointer and Escape Analysis (2001)
We present a new pointer and escape analysis. Instead of analyzing the whole program, the algorithm incrementally analyzes only those parts of the program that may deliver useful results. An analysis...
Scheduling the Computations of a Loop Nest with Respect to a Given Mapping (2000)
Alain Darte, Claude Diderich, Marc Gengler, Frédéric Vivien
. When parallelizing loop nests for distributed memory parallel computers, we have to specify when the dierent computations are carried out (computation scheduling), where they are carried out...
A Constructive Solution to the Juggling Problem in Systolic Array Synthesis (1999)
Unit Mixte, Alain Darte, Alain Darte, Robert Schreiber, ...
We describe a new, practical, constructive method for solving the well-known conict-free scheduling problem for the locally sequential, globally parallel (LSGP) case of systolic array synthesis....
Static Tiling for Heterogeneous Computing Platforms (1999)
Pierre Boulet, Jack Dongarra, Yves Robert, Frédéric Vivien
In the framework of fully permutable loops, tiling has been extensively studied as a sourceto -source program transformation. However, little work has been devoted to the mapping and scheduling of...
Algorithmic Issues on Heterogeneous Computing Platforms (1998)
Pierre Boulet, Jack Dongarra, Fabrice Rastello, Yves Robert, Frédéric Vivien
This paper discusses some algorithmic issues when computing with a heterogeneous network of workstations (the typical poor man's parallel computer). Dealing with processors of dierent speeds...
Tiling for heterogeneous computing platforms (1997)
Pierre Boulet, Jack Dongarra, Yves Robert, Frédéric Vivien
In the framework of fully permutable loops, tiling has been extensively studied as a sourceto-source program transformation. However, little work has been devoted to the mapping and scheduling of the...
Plugging Anti and Output Dependence Removal Techniques Into Loop Parallelization Algorithms (1997)
Pierre-Yves Calland, Alain Darte, Yves Robert, Frédéric Vivien
In this paper we shortly survey some loop transformation techniques which break anti or output dependences, or artificial cycles involving such "false" dependences. These false dependences...
Combining Retiming and Scheduling Techniques for Loop Parallelization and Loop Tiling (1996)
Ecole Normale, Georges-André Silber, Frédéric Vivien, Suprieure Lyon, Alain Darte, Alain Darte
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...
On the Removal of Anti and Output Dependences (1996)
Ecole Normale, Suprieure Lyon, Pierre-yves Calland, Frédéric Vivien, Pierre-yves Calland, Alain Darte, ...
In this paper we build upon results of Padua and Wolfe [8], who introduce two graph transformations to eliminate anti and output dependences. We first give a unified framework for such...
Automatic Parallelization Based on Multi-Dimensional Scheduling (1994)
Ecole Normale, Frédéric Vivien, Suprieure Lyon, Alain Darte, Alain Darte
In the scope of uniform recurrence equations, we study an algorithm first proposed by Karp, Miller and Winograd for detecting cycles of null weight in cyclic graphs. We show how this algorithm can be...