High Performance Computing Center North
Readings and Preparatory Work for the SeSE Course, March 2014. The readings and preparatory material listed below give a solid background to the main topics of the course and will prepare you for the week in Umeå. More information may be added during the course.
Students will be acquainted with some of the software listed below during the assignments and homework for the course. It will of course not be possible to cover all the material listed below during the course.
You should rehearse your MPI- and OpenMP-programming knowledge, either by repeating some of the excercises from the earlier SeSE course or by looking at the tutorials below.
Basics of parallel linear algebra
Data partitioning and data distribution
The following two articles give an overview of concepts, methods and algorithms for basic problems in parallel numerical linear algebra. To some extent they are overlapping with respect to content.
The following article gives an overview of recursive blocked algorithms and hybrid data structures for dense matrix computations, targeting HPC architectures with deep memory hierarchies.
Templates for the solution of linear systems
Templates for dense and sparse eigenvalue problems
The following article presents a parallel formulation of the multilevel graph
partitioning and sparse matrix ordering algorithm introduced by Karypis and Kumar.
Get acquainted with some libraries and tools that will be covered in the course.
Dense linear algebra
Sparse linear algebra
Parallel graph partitioning
Survey of tools for developing HPC applications