StarNEig published in Special Issue of CCPE
An extended paper describing the task-based StarNEig library for solving nonsymmetric standard and generalized eigenvalue problems has been published in a special issue of the international journal “Concurrency and Computation: Practice and Experience”. The publishers version can be found here. A post print can be found here.
New release of the StarNEig library
StarNEig is a new task-based parallel library for solving nonsymmetric standard and generalized eigenvalue problems. A new version (StarNEig 0.1 Beta 4) is now freely available for download from the dedicated website https://nlafet.github.io/StarNEig/ StarNEig is either comparable to LAPACK and ScaLAPACK or significantly faster depending on the computational step. Moreover, StarNEig realizes new parallel and blocked algorithms for computing eigenvectors… Read more »
Three new papers published
Three papers based on research completed at Umeå University during the NLAFET project were presented at the conference PPAM-2019 (Parallel Processing and Applied Mathematics) in Bialystok, Poland in September 2019. They now appear as part of the peer-reviewed conference proceedings published by Springer as LNCS volume 12043. Free preprints are also available through arXiv. 1: Carl Christian Kjelgaard Mikkelsen and… Read more »
Public deliverables (2.4, 3.7, 4.5) uploaded.
Public deliverables uploaded: D2.4 Batched BLAS 2018 Reference Implementation D3.7 Software for Hybrid Methods D4.5 Integration For the full list of released public deliverables, see this page: http://www.nlafet.eu/public-deliverables/
CCPE – Paper Accepted for special issue
Paper accepted to a special issue of Concurrency and Computation: Practice and Experience (CCPE). This special issue will consist of extended versions of the best papers accepted by PPAM 2017. The title of the paper is “Parallel robust solution of triangular linear systems” Robust algorithms do not suffer from overflow and always return a valid result. In LAPACK eigenvectors (standard… Read more »
Working Note 20 have been uploaded
Working Note 19 have been uploaded: WN20 – Parallelization of the solve phase in a task-based Cholesky solver using a sequential task flow model, Sébastien Cayrols, Iain Duff and Florent Lopez The full list of published Working Notes can be found on this page: http://www.nlafet.eu/working-notes/
Research poster award for Mawussi Zounon
Research poster award for Mawussi Zounon on exploiting the low precision floating-point arithmetic available on NVIDIA V100 GPU in solving linear system of equations. The title of the poster is “Using GPU’s FP16 Tensor Cores Arithmetic to Accelerate Mixed-Precision Iterative Refinement Solvers and Reduce Energy Consumption” with the authors Azzam Haidar, Stan Tomov, Ahmad Abdelfattah, Mawussi Zounon, Jack Dongarra
Public Deliverables uploaded
Several deliverables have been uploaded: D3.2, D3.6, D4.3, D6.2, and D6.6. A full list, including links to all the public deliverables that have been posted until now can be found here: http://www.nlafet.eu/public-deliverables/
SIAM PP18 – SIAM Conference on Parallel Processing for Scientific Computing
NLAFET sent several participants to SIAM PP18 (March 7-10, 2018) at Waseda University in Tokyo, Japan, where they presented some of their ongoing research. Persons in italic made the presentation at the conference. Talks Dense Linear Systems for Extreme Scale Jack J. Dongarra, University of Tennessee, ORNL, and University of Manchester, USA The Batched Blas abstract Sven J. Hammarling and… Read more »
Working Note 19 has been uploaded
Working Note 19 have been uploaded: WN19 – Solving linear equations with messenger-field and conjugate gradients techniques – an application to CMB data analysis, Jan Papez, Laura Grigori, Radoslav Stompor The full list of published Working Notes can be found on this page: http://www.nlafet.eu/working-notes/
Working Notes 17-18 published and available.
Working Notes 17 and 18 have been uploaded: WN17 – Sparse direct solution on parallel computers, Iain Duff, Florent Lopez, and Stojce Nakov WN18 – An Auto-Tuning Framework for a NUMA-Aware Hessenberg Reduction Algorithm, Mahmoud Eljammaly, Lars Karlsson, and Bo Kågström The full list of published Working Notes can be found on this page: http://www.nlafet.eu/working-notes/
Public Deliverables uploaded
During Q3-2017, several deliverables were uploaded. These belong to WP2 – WP7. A full list, including links to all the public deliverables that have been posted until now can be found here: http://www.nlafet.eu/public-deliverables/
Swedish e-Science Academy 2017
At the recent Swedish e-Science Academy 2017, held at Umeå University 11-12 October 2017, NLAFET members presented 3 posters: A Task-Based Algorithm for Reordering the Eigenvalues of a Matrix in Real Schur Form, Mirko Myllykoski Blocked and Robust solution of triangular systems, Carl Christian K. Mikkelsen and Lars Karlsson An Auto-tuning Framework for a NUMA-Aware Hessenberg Reduction Algorithm, Mahmoud Eljammaly,… Read more »
NLAFET sent several participants to PPAM 2017 (September 10-13, 2017), where they presented some of their ongoing research. Persons in bold made the presentation at the conference. On the Tunability of a New Hessenberg Reduction Algorithm Using Parallel Cache Assignment – Mahmoud Eljammaly, Lars Karlsson and Bo Kågström Blocked Algorithms for Robust Solution of Triangular Linear Systems – Carl Christian… Read more »
Working Notes 14-16 published and available!
WN14 – Experiments with sparse Cholesky using a parametrized task graph implementation, Iain Duff and Florent Lopez WN15 – PLASMA 17 Functionality Report Parallel BLAS and Norms, Linear Systems and Least Squares, Mixed Precision and Matrix Inversion, Maksims Abalenkovs, Jack Dongarra, Mark Gates, Azzam Haidar, Jakub Kurzak, Piotr Luszczek, Mawussi Zounon, Samuel Relton, Jakub Sistek, David Stevens, Ichitaro Yamazaki, Asim… Read more »
Working Note 11 posted
Working Note 11: Task-Based Parallel Algorithms for Eigenvalue Reordering of Matrices in Real Schur Form, Mirko Myllykoski, Carl Christian Kjelgaard Mikkelsen, Lars Karlsson, and Bo Kågström has been uploaded and can be found on the NLAFET Working Notes page.
Working Notes 12 and 13 uploaded
Working Note 12: Second Workshop on Batched, Reproducible, and Reduced Precision BLAS, Sven Hammarling and Working Note 13: Reducing the communication and computational costs of Enlarged Krylov subspaces Conjugate Gradient, Laura Grigori and Olivier Tissot, have been uploaded and can be found on the NLAFET Working Notes page.
Bo Kågström appointed SIAM Fellow 2016
The citation for his nomination reads; “Bo Kågström is Professor of Numerical Analysis and Parallel Computing and Director of High Performance Computing Center North (HPC2N) at Umeå University. Kågström has 25 publications in SIAM books and journals. He was a corresponding editor of the SIAM Journal on Matrix Analysis and Applications, was awarded the SIAM/SIAG Linear Algebra Prize in 2000,… Read more »
Postdoc and PhD positions in Parallel Computing for Extreme-Scale Systems, Umeå University
Department of Computing Science at Umea University, Sweden invites excellent candidates to apply for postdoctoral and PhD positions. The successful candidate(s) will join NLAFET, which is one of the high-profile extreme-scale computing projects funded by the European Commission within the recent FET-HPC call under Horizon 2020. NLAFET is coordinated by Umea University with international partners from INRIA (France), University of… Read more »
Postdoc position in Numerical Analysis, STFC, UK
We are looking for a talented and enthusiastic researcher to join our Numerical Analysis research team within the STFC’s Scientific Computing Department for a three year period. The team is internationally known for its research into numerical linear algebra and optimization. The role involves both algorithmic research and the translation of this research into software. You will be working in… Read more »
NLAFET kickoff 9-10 November 2015
The NLAFET kick-off was held at the MIT building, Umeå University, Sweden. There were participants from all four partners. The conference was organized jointly by the Department of Computing Science and the High Performance Computing Center North (HPC2N). At the conference, the research project and its various components were presented and discussed. A key challenge for NLAFET, and for all… Read more »