Patrick Carribault


Informations:
Postdoc Fellowship, Ph.D at the University of Texas.
Center for Grid and Distributed Computing

Contact me: email
Phone: (+1) 512-232-2568
Address: ICES Department, 1 University Station C0200, Austin, TX 78712, United States
Office: ACE 4.118



Outline:
moi

Research:

Lonestar Benchmark Suite

Ph.D Thesis:

Download the dissertation: PDF
(The dissertation is in english, but it provides a french summary as well)

Title: Contribution to the Compilation of Irregular Programs for Complex Architectures
Advisors: William Jalby and Albert Cohen

Defended on July 13th, 2007 at the University of Versailles (France).
Commitee members: Summary
Multicore architectures are ubiquitous in general purpose and embedded systems. Modern processors execute several instruction flows (threads) increasing the parallelism and accommodating for resource stalls. Both the execution of a thread and its interaction with the others shape the overall performance of an application. Thus, an accurate exploitation of a single core is mandatory: it leads to the necessity to discover the instruction-level parallelism (ILP) within an instruction flow.

This thesis focuses on the monocore optimization of irregular codes whose parallelism is hidden behind complex control flow. We designed transformations to increase their ILP: Deep Jam converting coarse-grain parallelism, decision tree reshaping and an instruction-scheduling framework unifying data dependences and complex resource constraints. Every transformation leads to significant speedups on a wide issue architecture (Itanium), compared to state-of-the-art techniques and compilers.

Keywords: High-Performance Computing, Optimizing Compiler, Irregular Codes, Instruction-Level Parallelism, Instruction Scheduling

Publications:

  1. Patrick Carribault, Stéphane Zuckerman, Albert Cohen and William Jalby. Deep Jam: Conversion of Coarse-Grain Parallelism to Instruction-Level and Vector Parallelism for Irregular Applications. The Journal of Instruction-Level Parallelism, vol 9, September 2007. pdf

  2. Denis Barthou, Sébastien Donadio, Patrick Carribault, Alexandre Duchateau and William Jalby, Loop Optimization using Hierarchical Compilation and Kernel Decomposition. In: Proceedings of ACM/IEEE Intl. Symposium on Code Optimization and Generation (CGO'07). San Jose, CA, March 2007. pdf

  3. Lamia Djoudi, Denis Barthou, Patrick Carribault, Christophe Lemuet, Jean-Thomas Acquaviva and William Jalby, Exploring Application Performance: a New Tool For a Static/Dynamic Approach. In: The Sixth Los Alamos Computer Science Institute Symposium (LACSI Symposium 2005). Santa Fe, NM, October 11-13. 2005. pdf

  4. Patrick Carribault, Albert Cohen and William Jalby. Deep Jam: Conversion of Coarse-Grain Parallelism to Instruction-Level and Vector Parallelism for Irregular Applications. In: The Fourteenth International Conference on Parallel Architectures and Compilation Techniques (PACT'05). Saint Louis, Missouri. September 17-21. 2005. pdf slides

  5. Eli Biham, Rafi Chen, Antoine Joux, Patrick Carribault, William Jalby and Christophe Lemuet. Collisions of SHA-0 and Reduced SHA-1. In: Advances in Cryptology - EUROCRYPT 2005: 24th Annual International Conference on the Theory and Applications of Cryptographic Techniques. Aarhus, Denmark. May 22-26. 2005. pdf

  6. Lamia Djoudi, Denis Barthou, Patrick Carribault, Christophe Lemuet, Jean-Thomas Acquaviva and William Jalby. MAQAO Modular Assembler Quality Analyzer, and Optimizer for Itanium 2. In: Workshop on Explicitly Parallel Instruction Computing Techniques (EPIC). San Jose, California. March 2005.

  7. Patrick Carribault, Christophe Lemuet, Jean-Thomas Acquaviva, Albert Cohen and William Jalby. Branch strategies to optimize decision trees for wide-issue architectures. In: Workshop on Languages and Compilers for Parallel Computing (LCPC'04). West Lafayette, Indiana, September 2004. pdf
    Springer Verlag: download

  8. Patrick Carribault and Albert Cohen. Application of storage mapping optimization to register promotion. In: ACM Int. Conf. on Supercomputing (ICS'04). St-Malo, France, June 2004. pdf

Teaching: