http://developer.amd.com/tools-and-sdks/open-source/  

“Parallel Performance Study of Block-Preconditioned Iterative Methods on Multicore Computer Systems” Ali Dorostkar, Dimitar Lukarski, Björn Lund, Maya Neytcheva, Yvan Notay, Peter Schmidt http://www.it.uu.se/research/publications/reports/2014-007/  

“Multi-Elimination ILU Preconditioners on GPUs” Dimitar Lukarsk, Hartwig Anzt, Stanimire Tomov, Jack Dongarra    http://www.eecs.utk.edu/resources/library/581

We will present our current development in direction of MPI and multi-GPU support at the GTC conference in San Jose. http://registration.gputechconf.com/quicklink/gf0AvNc  

http://www.nvidia.com/content/events/sc13/pdf/SC13-theater-schedule-oct17.pdf The talk has been recorded and it is available on http://www.ustream.tv/recorded/40952552

https://developer.nvidia.com/gpu-accelerated-libraries https://developer.nvidia.com/paralution  

“Fine-grained parallel iterative solvers in OpenFOAM – utilizing multi-core and GPU devices with PARALUTION” More information on the OpenFOAM (NL) group page or Delft TU / Seminar

NVIDIA presented various GPU libraries at the GTC 2013  (San Jose) and PARALUTION is one of them! S3461A: CUDA Accelerated Compute Libraries http://nvidia.fullviewmedia.com/gtc2013/0318-210H-S3461A.html [44:40]

Tutorial about PARALUTION will be held at the pre-conference course “GPU-enabled numerical libraries” / 22nd International Conference on Domain Decomposition Methods (DD22). More information on http://dd22.ics.usi.ch/index.php/pre-conference-course

Lecture and tutorial about the PARALUTION project will be hold at the summer school “Heterogeneous computing – impact on algorithms”, Uppsala Sweden 3-7 June 2013. More information on the web site of the school http://www.it.uu.se/conf/complexhpc2013/