Research Field

Optimisation, compilation for parallel and high performance computing and interations with runtime systems.

Current Research Projects

I'm involved in the following projects:

ParMa: a European ITEA2 project on Parallel Programming for Multicore Architectures

Project supported by Aquitaine Region and INRIA: Performance Modeling for heterogeneous platforms. I'm participating to this project.

PetaQCD: ANR project for a sustained petaflops machine for Lattice QCD (jan. 2009 - dec 2012). I'm scientific coordinator for UVSQ of this project.

ProHMPT: ANR project on the programming heterogeneous multicore processor technologies. I'm scientific coordinator for UVSQ of this project (jan 2009 - dev 2011).

Publications

Book Chapters

[1] DSL Stream Programming on Multicore Architectures. Pablo de Oliveira Castro, Stephane Louise, and Denis Barthou. In Programming Multi-core and Many-core Computing Systems, Parallel and Distributed Computing. Wiley-Blackwell, 2011. To appear. [ bib ]
[2] Performance Tuning of x86 OpenMP Codes with MAQAO. Denis Barthou, Andres Charif Rubial, William Jalby, Souad Koliai, and Cédric Valensi. In Matthias S. Müller, Michael M. Resch, Alexander Schulz, and Wolfgang E. Nagel, editors, Tools for High Performance Computing 2009, pages 95-113. Springer Berlin Heidelberg, 2010. [ bib ]

Journals

[1] Compositional Approach applied to Loop Specialization. Lamia Djoudi, Jean-Thomas Acquaviva, and Denis Barthou. Concurrency and Computation: Practice and Experience, 21:71-84, 2008. [ bib | .pdf ]
[2] Improving Performance of Optimized Kernels Through Fast Instantiations of Templates. Minhaj Ahmad Khan, Henri-Pierre Charles, and Denis Barthou. Concurrency and Computation: Practice and Experience, 21:59-71, 2008. [ bib | .pdf ]
[3] Maximal Static Expansion. Denis Barthou, Albert Cohen, and Jean-François Collard. Intl. J. of Parallel Programming, 28(3):213-243, 2000. [ bib | .pdf ]
[4] Fuzzy Array Dataflow Analysis. Denis Barthou, Jean-François Collard, and Paul Feautrier. J. of Parallel and Distributed Computing, 40(2):210-226, 1997. [ bib | .pdf ]

Refereed conferences and workshops

[1] QIRAL: A High Level Language for Lattice QCD Code Generation. Denis Barthou, Gilbert Grosdidier, Michael Kruse, Olivier Pene, and Claude Tadonki. In Programming Language Approaches to Concurrency and Communication-centric Software Workshop, 2012. To appear. [ bib ]
[2] Performance modeling for power consumption reduction on SCC. Bertrand Putigny, Brice Goglin, and Denis Barthou. In Hasso Plattner Institute at University of Potsdam, editor, 4th Many-core Applications Research Community (MARC) Symposium, Potsdam, Germany, December 2011. [ bib ]
[3] Analysing the Variability of OpenMP Programs Performances on Multico re Architectures. Abdelhafid Mazouz, Sid-Ahmed-Ali Touati, and Denis Barthou. In Fourth Workshop on Programmability Issues for Heterogeneous Mult icores (MULTIPROG-2011), page 14, Heraklion, Greece, 2011. Held in conjunction with: the 6th International Conference on High-Performance and Embedded Architectures and Compilers (HiPEAC). [ bib | http ]
[4] Performance evaluation and analysis of thread pinning strategies on multi-core platforms: Case study of SPEC OMP applications on intel architectures. Abdelhafid Mazouz, Sid-Ahmed-Ali Touati, and Denis Barthou. In High Performance Computing and Simulation (HPCS), pages 273 -279, Istanbul, Turquie, 2011. IEEE. [ bib | DOI | http | .pdf ]
[5] Reducing Memory Requirements of Stream Programs by Graph Transformations. Pablo de Oliveira Castro, Stéphane Louise, and Denis Barthou. In IEEE Intl. Conf. on High Performance Computing and Simulation, pages 171-180, Caen, France, June 2010. IEEE Computer Society. [ bib ]
[6] FADAlib: an open source C++ library for fuzzy array dataflow analysis. Marouane Belaoucha, Denis Barthou, Adrien Eliche, and Sid-Ahmed-Ali Touati. In Intl. Workshop on Practical Aspects of High-Level Parallel Programming, volume 1, pages 2075-2084, Amsterdam, The Netherlands, May 2010. [ bib | DOI | http ]
[7] A multidimensional array slicing DSL for Stream Programming. Pablo de Oliveira Castro, Stéphane Louise, and Denis Barthou. In Intl. IEEE Workshop on Multi-Core Computing Systems, pages 913-918, Krakow, Poland, February 2010. IEEE Computer Society. [ bib ]
[8] Study of Variations of Native Program Execution Times on Multi-Core Architectures. Abdelhafid Mazouz, Sid-Ahmed-Ali Touati, and Denis Barthou. In Intl. IEEE Workshop on Multi-Core Computing Systems, pages 919-924, Krakow, Poland, February 2010. IEEE Computer Society. [ bib ]
[9] Computing the transitive closure of a union of affine integer tuple relations. Anna Beletska, Denis Barthou, Wlodziemierz Bielecki, and Albert Cohen. In Intl. Conference on Combinatorial Optimization and Applications, volume 5573 of Lect. Notes in Computer Science, pages 98-109, Yellow Mountains, China, June 2009. [ bib ]
[10] Towards the petaflop for Lattice QCD simulations the PetaQCD project. J.C. Angles D'Auriac, D. Barthou, D. Becirevic, R. Bilhaut, François Bodin, P. Boucaud, O. Brand Foissac, J. Carbonell, C. Eisenbeis, P. Gallard, G. Grosdidier, P. Guichon, P.F. Honore, G. Le Meur, P. Pene, L. Rilling, P. Roudeau, A. Seznec, A. Stocchi, and F. Touze. In J. Gruntorad ; M. Lokajicek, editor, Journal of Physics Conference Series 17th International Conference on Computing in High Energy and Nuclear Physics (CHEP'09), volume 219, page 052021, Prague Tchèque, République, March 2009. IOP Publishing. LAL 09-58, LPSC09233. [ bib | DOI | http ]
[11] Parallel Expression Template for Large Vectors. Laurent Plagne, Franck Hulsemann, Denis Barthou, and Julien Jaeger. In Workshop on Parallel/High-Performance Object-Oriented Scientific Computing, pages 1-8, Genova, Italy, 2009. ACM Press. [ bib ]
[12] Combining Experimental Search and Performance Model for Adaptive Optimization. Julien Jaeger and Denis Barthou. In Hipeac Workshop on Statistical and Machine Learning Approaches to Architectures and compilation, Paphos, Cyprus, January 2009. [ bib | .pdf ]
[13] Optimizing code through iterative specialization. Minhaj Ahmad Khan, Henri-Pierre Charles, and Denis Barthou. In ACM Symp. on Applied Computing, pages 206-210, New York, NY, 2008. ACM Press. [ bib | .pdf ]
[14] An Effective Automated Approach to Specialization of Code. Minhaj Ahmad Khan, Henri-Pierre Charles, and Denis Barthou. In Intl. Workshop on Languages and Compilers for Parallel Computing, Lect. Notes in Computer Science, pages 308-322, Chicago, Illinois, October 2007. Springer-Verlag. [ bib | .pdf ]
[15] Hybrid Specialization : A Trade-off Between Static and Dynamic Specialization. Minhaj Ahmad Khan, Henri-Pierre Charles, and Denis Barthou. In ACM/IEEE Intl. Conf. on Parallel Architectures and Compilation Techniques(Extended abstract), page 415, Phoenix, AZ, September 2007. IEEE Computer Society. [ bib | .pdf ]
[16] Compositional Approach applied to Loop Specialization. Lamia Djoudi, Jean-Thomas Acquaviva, and Denis Barthou. In Euro-Par Conference, volume 4641 of Lect. Notes in Computer Science, pages 268-279, Rennes, August 2007. Springer-Verlag. [ bib | .pdf ]
[17] The Design and Architecture of MAQAOProfile: an Instrumentation MAQAO Module. Lamia Djoudi, Denis Barthou, Olivier Tomaz, Andres Charif-Rubial, Jean-Thomas Acquaviva, and William Jalby. In Workshop on Explicitly Parallel Instruction Computing Techniques, San Jose, California, March 2007. [ bib | .pdf ]
[18] Loop Optimization using Adaptive Compilation and Kernel Decomposition. Denis Barthou, Sebastien Donadio, Alexandre Duchateau, Patrick Carribault, and William Jalby. In ACM/IEEE Intl. Symp. on Code Optimization and Generation, pages 170-184, San Jose, California, March 2007. IEEE Computer Society. [ bib | .pdf ]
[19] Improving Performance through Low-Overhead Specialization of Code. Minhaj Ahmad Khan, Henri-Pierre Charles, and Denis Barthou. In Intl. Workshop on Iteraction between Compilers and Computer Architectures, Phoenix, Arizona, February 2007. [ bib | .pdf ]
[20] Iterative Compilation with Kernel Exploration. Denis Barthou, Sebastien Donadio, Alexandre Duchateau, William Jalby, and Eric Courtois. In Intl. Workshop on Languages and Compilers for Parallel Computing, volume 4382 of Lect. Notes in Computer Science, pages 173-189, New Orleans, November 2006. Springer-Verlag. [ bib | .pdf ]
[21] On the decidability of phase ordering problem in optimizing compilation. Sid-Ahmed-Ali Touati and Denis Barthou. In ACM Computing Frontiers Conf., pages 147-156, Ischia, Italy, 2006. ACM Press. [ bib | .pdf ]
[22] Exploring Application Performance: a New Tool For a Static/Dynamic Approach. Lamia Djoudi, Denis Barthou, Patrick Carribault, Christophe Lemuet, Jean-Thomas Acquaviva, and William Jalby. In Los Alamos Computer Science Institute Symp., Santa Fe, NM, October 2005. [ bib | .pdf ]
[23] A Language for the Compact Representation of Multiple Program Versions. Sebastien Donadio, James Brodman, Thomas Roeder, Kamen Yotov, Denis Barthou, Albert Cohen, Maria Garzaran, David Padua, and Keshav Pingali. In Intl. Workshop on Languages and Compilers for Parallel Computing, volume 4339 of Lect. Notes in Computer Science, pages 136-151, Hawthorne, New York, October 2005. Springer-Verlag. [ bib | .pdf ]
[24] Deciding Where to Call Performance Libraries. Christophe Alias and Denis Barthou. In Euro-Par Conference, volume 3648 of Lect. Notes in Computer Science, pages 336-345, Lisboa, September 2005. Springer-Verlag. [ bib | .pdf ]
[25] On Domain Specific Languages Re-Engineering. Christophe Alias and Denis Barthou. In ACM Intl. Conf. on Generative Programming and Component Engineering, volume 3676 of Lect. Notes in Computer Science, pages 63-77, Tallinn, September 2005. Springer-Verlag. [ bib | .pdf ]
[26] MAQAO: Modular Assembler Quality Analyzer and Optimizer for Itanium 2. Lamia Djoudi, Denis Barthou, Patrick Carribault, Christophe Lemuet, Jean-Thomas Acquaviva, and William Jalby. In Workshop on Explicitly Parallel Instruction Computing Techniques, Santa Jose, California, March 2005. [ bib | .pdf ]
[27] Algorithm Recognition based on Demand-driven Data-flow Analysis. Christophe Alias and Denis Barthou. In IEEE Working Conf. on Reverse Engineering, pages 296-305, Victoria, November 2003. IEEE. [ bib | .pdf ]
[28] On the recognition of algorithm templates. Christophe Alias and Denis Barthou. In Intl. Workshop on Compilers Optimization Meets Compiler Verification, volume 82 of ENTCS, pages 395-409, Warsaw, April 2003. Elsevier Science. [ bib | .pdf ]
[29] On the Equivalence of Two Systems of Affine Recurrence Equations. Denis Barthou, Paul Feautrier, and Xavier Redon. In Euro-Par Conference, volume 2400 of Lect. Notes in Computer Science, pages 309-313, Paderborn, August 2002. Springer-Verlag. [ bib | .pdf ]
[30] Maximal Static Expansion. Denis Barthou, Albert Cohen, and Jean-François Collard. In ACM Symp. on Principles of Programming Languages, pages 98-106, San Diego, California, January 1998. ACM Press. [ bib | .pdf ]
[31] Automatic data mapping of signal processing applications. Corinne Ancourt, Denis Barthou, Christophe Guettier, François Irigoin, Bertrand Jeannet, Jean Jourdan, and Juliette Mattioli. In IEEE Intl. Conf. on Application-Specific Systems, Architectures and Processors, pages 350-362, Zurich, July 1997. IEEE Computer Society. [ bib | .pdf ]
[32] Applications of Fuzzy Array Dataflow Analysis. Denis Barthou, Jean-François Collard, and Paul Feautrier. In Euro-Par Conference, volume 1123 of Lect. Notes in Computer Science, pages 424-427, Lyon, August 1996. Springer-Verlag. [ bib | .pdf ]
[33] Fuzzy array dataflow analysis. Jean-François Collard, Denis Barthou, and Paul Feautrier. In ACM SIGPLAN Symp. on Principles and Practice of Parallel Programming, pages 92-101, Santa Barbara, California, 1995. ACM Press. [ bib | .pdf ]
[34] Allocating Communication Channels to Parallel Tasks. Denis Barthou, Franco Gasperoni, and Uwe Schwiegelshohn. In Intl. Workshop on Environments and Tools for Parallel Scientific Computing, volume 6, pages 275-291, St Hilaire du Touvet, September 1993. Advances in Parallel Computing. [ bib | .pdf ]

Non-refereed communications

[1] Modélisation du coût de la cohérence de cache pour améliorer le tuilage de boucles. Bertrand Putigny, Denis Barthou, and Brice Goglin. Quatrième rencontres de la communauté française de compilation, Saint-Hippolyte, France, December 2011. [ bib ]
[2] Stencils sur CPU et GPU. Julien Jaeger and Denis Barthou. Quatrième rencontres de la communauté française de compilation, Saint-Hippolyte, France, December 2011. [ bib ]
[3] Simulation of the Lattice QCD and Technological Trends in Computation. Khaled Ibrahim, Julien Jaeger, Zhaofeng Liu, Louis-Noel Pouchet, Piotr Lesnicki, Lamia Djoudi, Denis Barthou, Francois Bodin, Christine Eisenbeis, Gilbert Grosdidier, Olivier Pene, and Patrick Roudeau. Workshop on Compilers for Parallel Computing, January 2009. arXiv:0808.0391v3. [ bib | .pdf ]
[4] A Global Approach for MPEG-4 AVC Encoder Optimization. Khawar Sajjad, Son-Minh Tran, Denis Barthou, Henri-Pierre Charles, Marius Preda, and Francoise Preteux. Workshop on Compilers for Parallel Computing, January 2009. [ bib | .pdf ]
[5] Kernel (De)composition, A compositional approach applied to linear algebra libraries. Denis Barthou. Dagstuhl workshop, Programming Models for Ubiquitous Parallelism, September 2007. [ bib | .pdf ]
[6] MAQAO: Optimization of low level code by static and dynamic analysis. Lamia Djoudi, Denis Barthou, and William Jalby. Conférence sur le Génie Electrique, Alger, 2007. [ bib ]
[7] ATLAST: A new tool chain for automatically generating high performance dense matrix kernels. Denis Barthou, Alexandre Duchateau, Sebastien Donadio, and William Jalby. FAME2 Workshop on High Performance Computing, 2006. [ bib ]
[8] Deciding where to call performance libraries. David Soguet, Christophe Alias, and Denis Barthou. Technical Report 65, Laboratoire PRiSM, 2004. [ bib ]
[9] Program Optimization by Algorithm Recognition and Replacement. Christophe Alias and Denis Barthou. Technical Report 66, Laboratoire PRiSM, 2004. [ bib ]
[10] On the Equivalence of Two Systems of Affine Recurrence Equations. Denis Barthou, Paul Feautrier, and Xavier Redon. Technical Report RR-4285, INRIA, October 2001. [ bib ]
[11] The Interplay of Expansion and Scheduling in PAF. Paul Feautrier, Jean-François Collard, Michel Barreteau, Denis Barthou, Albert Cohen, and Vincent Lefebvre. Technical Report 6, Laboratoire PRiSM, 1998. [ bib ]
[12] Fuzzy Array Dataflow Analysis. Denis Barthou, Jean-François Collard, and Paul Feautrier. Technical Report 95/33, Laboratoire PRiSM, 1995. [ bib ]

PhD and Habilitation thesis

[1] Contributions to code optimization and high performance library generation. Denis Barthou. Habilitation à diriger les recherches (HDR), Université de Versailles St-Quentin, Versailles, January 2008. [ bib | .pdf ]
[2] Array Dataflow Analysis in Presence of Non-affine Constraints. Denis Barthou. PhD thesis, Université de Versailles St-Quentin, Versailles, February 1998. [ bib | .pdf ]