% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@INPROCEEDINGS{DiNapoli:811971,
author = {Di Napoli, Edoardo},
title = {{T}he {C}h{ASE} library on distributed and heterogeneous
platforms},
reportid = {FZJ-2016-04275},
year = {2016},
abstract = {We propose to step away from the black-box approach and
allow the eigensolver to accept as much information as it is
available from the application. Such a strategy implies that
the resulting library is tailored to the specific
application, or class of applications, and loose generality
of usage. On the other hand, the resulting eigensolver
maximally exploits knowledge from the application and become
very efficient. With this general strategy in mind, we
present here a version of a Chebyshev Accelerated Subspace
iteration Eigensolver (ChASE) which targets extremal
eigenpairs of dense eigenproblems. In particular, ChASE
focuses of on a class of applications resulting in having to
solve sequences of eigenvalue problems where adjacent
problems possess a certain degree of correlation. A typical
example of such applications is Density Functional Theory
where the solution to a non-linear partial differential
equation is worked out by generating and solving dozens of
algebraic eigenvalue problems in a self- consistent fashion
over dozens of iterations. Similarly, any non-linear
eigenvalue problem, which can be solved by the method of
successive linearization, gives rise to sequences of
correlated algebraic eigenproblems that are the target of
ChASE. We re-design the eigensolver so as to minimize its
complexity and have better control of its numerical
features. Following the algorithm optimizations, we strive
to adopt a strategy leading to an implementation that would
lends itself to high-performance parallel computing and
avoid, at the same time, issues related to portability to
heterogeneous architectures. We achieve such a goal by
implementing parallel kernels for the modular tasks of the
eigensolver using programming strategies out of MPI, OpenMP,
and CUDA.},
month = {Jul},
date = {2016-07-06},
organization = {Parallel Matrix Algorithms and
Applications, Bordeaux (France), 6 Jul
2016 - 8 Jul 2016},
subtyp = {After Call},
cin = {JSC},
cid = {I:(DE-Juel1)JSC-20090406},
pnm = {511 - Computational Science and Mathematical Methods
(POF3-511) / Simulation and Data Laboratory Quantum
Materials (SDLQM) (SDLQM)},
pid = {G:(DE-HGF)POF3-511 / G:(DE-Juel1)SDLQM},
typ = {PUB:(DE-HGF)6},
url = {https://juser.fz-juelich.de/record/811971},
}