Towards distributed heterogenous high-performance computing with ViennaCL. One of the major drawbacks of computing with graphics adapters is the limited available memory for relevant problem sizes. To overcome this limitation for the ViennaCL library, we investigate a partitioning approach for one of the standard benchmark problems in High-Performance Computing (HPC), namely the dense matrix-matrix product. We apply this partitioning approach to problems exceeding the available memory on graphics adapters. Moreover, we investigate the applicability on distributed memory systems by facilitating the Message Passing Interface (MPI). Our approach is presented in detail and benchmark results are given.
Keywords for this software
References in zbMATH (referenced in 3 articles , 1 standard article )
Showing results 1 to 3 of 3.
- Rupp, Karl; Tillet, Philippe; Rudolf, Florian; Weinbub, Josef; Morhammer, Andreas; Grasser, Tibor; Jüngel, Ansgar; Selberherr, Siegfried: ViennaCL-linear algebra library for multi- and many-core architectures (2016)
- Demidov, Denis; Ahnert, Karsten; Rupp, Karl; Gottschling, Peter: Programming CUDA and OpenCL: a case study using modern C++ libraries (2013)
- Georgescu, Serban; Chow, Peter; Okuda, Hiroshi: GPU acceleration for FEM-based structural analysis (2013)
Further publications can be found at: http://viennacl.sourceforge.net/viennacl-publications.html