Lacoste, X., Ramet, P., Faverge, M., Ichitaro, I., Dongarra, J. "Sparse direct solvers with accelerators over DAG runtimes," Inria Technical Report RR-7972, December, 2012.

Agullo, E., Bramas, B., Coulaud, O., Darve, E., Messner, M., Takahashi, T. "Pipelining the Fast Multipole Method over a Runtime System," Inria Technical Report RR-7981, May, 2012.

Fully Empirical Autotuned QR Factorization For Multicore Architectures "http://hal.inria.fr/inria-00569514/en/," Rapport de recherche, Volume , Number INRIA, HiePACS - INRIA Bordeaux - Sud-Ouest - INRIA - Universit{é} de Bordeaux - CNRS : UMR5800 - CERFACS - Laboratoire Bordelais de Recherche en Informatique - LaBRI - CNRS : UMR5800 - Universit{é} Sciences et Technologies - Bordeaux I - Ecole Nat, RR-7526.

Faster, Cheaper, Better -- a Hybridization Methodology to Develop Linear Algebra Software for GPUs "http://hal.inria.fr/inria-00547847/en/," HiePACS - INRIA Bordeaux - Sud-Ouest - INRIA - Universit{é} de Bordeaux - CNRS : UMR5800 - CERFACS - Laboratoire Bordelais de Recherche en Informatique - LaBRI - CNRS : UMR5800 - Universit{é} Sciences et Technologies - Bordeaux I - Ecole Nat, 2 eds. GPU Computing Gems, Volume Morgan Kaufmann, Wen-mei W. Hwu .

Dynamically scheduled Cholesky factorization on multicore architectures with GPU accelerators. "http://hal.inria.fr/inria-00547616/en/," HiePACS - INRIA Bordeaux - Sud-Ouest - INRIA - Universit{é} de Bordeaux - CNRS : UMR5800 - CERFACS - Laboratoire Bordelais de Recherche en Informatique - LaBRI - CNRS : UMR5800 - Universit{é} Sciences et Technologies - Bordeaux I - Ecole Nat, internationale .

QR Factorization on a Multicore Node Enhanced with Multiple GPU Accelerators "http://hal.inria.fr/inria-00547614/en/," HiePACS - INRIA Bordeaux - Sud-Ouest - INRIA - Universit{é} de Bordeaux - CNRS : UMR5800 - CERFACS - Laboratoire Bordelais de Recherche en Informatique - LaBRI - CNRS : UMR5800 - Universit{é} Sciences et Technologies - Bordeaux I - Ecole Nat, internationale .