"False"
Umeå University
printicon
Main menu hidden.

Image: AdobeStock

High-Performance and Automatic Computing

Research group The research group Parallel and High-Performance Computing focuses on algorithms, tools, and applications for scalable high-performance computer systems.

Research topics include high-performance and portable linear algebra kernels and LAPACK- and ScaLAPACK-style algorithms for blocked and scalable matrix computations.

Projects
Hierarchically Blocked Algorithms and Optimized Low-Level Kernels for Dense Matrix Computations on Memory-Tiered High-Performance Computing Systems

Research leader

Bo Kågström Professor emeritus, professor
E-mail
Email
Phone
+46 90 786 54 19

Overview

Participating departments and units at Umeå University

Department of Computing Science

Research area

Computing science

Research projects

StratiGraph and MCS Toolbox
Research area: Computing science
Duration 1 January 1998
Type of project Research project

Latest publications

Geometry of Matrix Polynomial Spaces
Foundations of Computational Mathematics, Springer 2020, Vol. 20, (3) : 423-450
Dmytryshyn, Andrii; Johansson, Stefan; Kågström, Bo; et al.
D7.8 Release of the NLAFET library
NLAFET Consortium; Umeå University 2019
Kågström, Bo; Myllykoski, Mirko; Karlsson, Lars; et al.
D2.7 Eigenvalue solvers for nonsymmetric problems
NLAFET Consortium; Umeå University 2019
Myllykoski, Mirko; Kjelgaard Mikkelsen, Carl Christian; Schwarz, Angelika Beatrix; et al.
D2.6 Prototype Software for Eigenvalue Problem Solvers
NLAFET Consortium; Umeå University 2018
Myllykoski, Mirko; Karlsson, Lars; Kågström, Bo; et al.
On the Tunability of a New Hessenberg Reduction Algorithm Using Parallel Cache Assignment
Parallel Processing and Applied Mathematics. PPAM 2017: Part 1, Springer 2018 : 579-589
Eljammaly, Mahmoud; Karlsson, Lars; Kågström, Bo
Distributed one-stage Hessenberg-triangular reduction with wavefront scheduling
SIAM Journal on Scientific Computing, Society for Industrial and Applied Mathematics 2018, Vol. 40, (2) : C157-C180
Adlerborn, Björn; Karlsson, Lars; Kågström, Bo
An auto-tuning framework for a NUMA-aware Hessenberg reduction algorithm
ICPE '18 Companion of the 2018 ACM/SPEC International Conference on Performance Engineering, ACM Digital Library 2018 : 5-8
Eljammaly, Mahmoud; Karlsson, Lars; Kågström, Bo
An auto-tuning framework for a NUMA-aware Hessenberg reduction algorithm
Report / UMINF, 17.19
Eljammaly, Mahmoud; Karlsson, Lars; Kågström, Bo
Towards Highly Parallel and Compute-Bound Computation of Eigenvectors of Matrices in Schur Form
Report / UMINF, 17.10
Adlerborn, Björn; Kjelgaard Mikkelsen, Carl Christian; Karlsson, Lars; et al.
Task-Based Parallel Algorithms for Eigenvalue Reordering of Matrices in Real Schur Forms
Report / UMINF, 17.11
Myllykoski, Mirko; Kjelgaard Mikkelsen, Carl Christian; Karlsson, Lars; et al.
See more publications.
Latest update: 2022-03-23