RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación
Artículo científico (JournalArticle)
Hierarchical approach for deriving a reproducible unblocked LU factorization
[EN] We propose a reproducible variant of the unblocked LU factorization for graphics processor units (GPUs). For this purpose, we build upon Level-1/2 BLAS kernels that deliver correctly-rounded and reproducible results for the dot (inner) product, vector scaling, and the matrix-vector product. In addition, we draw a strategy to enhance the accuracy of the triangular solve via iterative refinement. Following a bottom-up approach, we finally construct a reproducible unblocked implementation of the LU factorization for GPUs, which accommodates partial pivoting for stability and can be eventually integrated in a high performance and stable algorithm for the (blocked) LU factorization., The author(s) disclosed receipt of the following financial support for the research, authorship, and/or publication of this article: The simulations were performed on resources provided by the Swed-ish National Infrastructure for Computing (SNIC) at PDC Centre for High Performance Computing (PDC-HPC). This work was also granted access to the HPC resources of The Institute for Scientific Computing and Simulation financed by Region Ile-de-France and the project Equip@Meso (reference ANR-10-EQPX-29-01) overseen by the French National Agency for Research (ANR) as part of the Investissements d Avenir pro-gram. This work was also partly supported by the FastRelax (ANR-14-CE25-0018-01) project of ANR.