% 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:825379,
author = {Di Napoli, Edoardo},
title = {{E}fficient parallel implementation of the {C}h{ASE}
library on distributed {CPU}-{GPU} architectures},
reportid = {FZJ-2016-07842},
year = {2016},
abstract = {The Chebyshev Accelerated Subspace iteration Eigensolver
(ChASE) is an iterative eigensolver developed at the JSC by
the SimLab ab initio. The solver target principally
sequences of dense eigenvalue problems as they arise in
Density functional Theory, but can also work on the single
eigenproblem. ChASE leverages on the preponderant use of
BLAS 3 subroutines to achieve close-to-peak performance.
Currently, the library can be executed in parallel on many-
and multi-core platforms. The latest development of this
project dealt with the extension of the CUDA build to
encompass multiple GPUs on distinct CPUs. As such this
hybrid parallelization will use MPI as well as CUDA
interfaces effectively exploiting heterogeneous multi-GPU
platforms. The extended library was tested on large and
dense eigenproblems extracted from excitonic Hamiltonian.
The ultimate goal is to integrate this new parallel
implementation of ChASE with the VASP-BSE code.},
month = {Nov},
date = {2016-11-30},
organization = {Joint Laboratory for Extreme Scale
Computing, Kobe (Japan), 30 Nov 2016 -
2 Dec 2016},
subtyp = {Invited},
cin = {JSC / JARA-HPC},
cid = {I:(DE-Juel1)JSC-20090406 / $I:(DE-82)080012_20140620$},
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/825379},
}