% 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{Wu:907602,
      author       = {Wu, Xinzhe and Davidovic, Davor and Achilles, Sebastian and
                      Di Napoli, Edoardo},
      title        = {{C}h{ASE} - {A} {D}istributed {H}ybrid {CPU}-{GPU}
                      {E}igensolver for {L}arge-scale {H}ermitian {E}igenvalue
                      {P}roblems},
      publisher    = {ACM New York, NY, USA},
      reportid     = {FZJ-2022-02101},
      pages        = {Article No.: 9},
      year         = {2022},
      comment      = {Proceedings of the Platform for Advanced Scientific
                      Computing Conference - ACM New York, NY, USA, 2022. - ISBN
                      9781450394109 - doi:10.1145/3539781.3539792},
      booktitle     = {Proceedings of the Platform for
                       Advanced Scientific Computing
                       Conference - ACM New York, NY, USA,
                       2022. - ISBN 9781450394109 -
                       doi:10.1145/3539781.3539792},
      abstract     = {As modern massively parallel clusters are getting larger
                      with beefier compute nodes, traditional parallel
                      eigensolvers, such as direct solvers, struggle keeping the
                      pace with the hardware evolution and being able to scale
                      efficiently due to additional layers of communication and
                      synchronization. This difficulty is especially important
                      when porting traditional libraries to heterogeneous
                      computing architectures equipped with accelerators, such as
                      Graphics Processing Unit (GPU). Recently, there have been
                      significant scientific contributions to the development of
                      filter-based subspace eigensolver to compute partial
                      eigenspectrum. The simpler structure of these type of
                      algorithms makes for them easier to avoid the communication
                      and synchronization bottlenecks typical of direct solvers.
                      The Chebyshev Accelerated Subspace Eigensolver (ChASE) is a
                      modern subspace eigensolver to compute partial extremal
                      eigenpairs of large-scale Hermitian eigenproblems with the
                      acceleration of a filter based on Chebyshev polynomials. In
                      this work, we extend our previous work on ChASE by adding
                      support for distributed hybrid CPU-multi-GPU computing
                      architectures. Our tests show that ChASE achieves very good
                      scaling performance up to 144 nodes with 526 NVIDIA A100
                      GPUs in total on dense eigenproblems of size up to $360$k.},
      month         = {Jun},
      date          = {2022-06-27},
      organization  = {Platform for Advanced Scientific
                       Computing, Basel (Switzerland), 27 Jun
                       2022 - 29 Jun 2022},
      cin          = {JSC},
      cid          = {I:(DE-Juel1)JSC-20090406},
      pnm          = {5111 - Domain-Specific Simulation $\&$ Data Life Cycle Labs
                      (SDLs) and Research Groups (POF4-511) / PRACE-6IP - PRACE
                      6th Implementation Phase Project (823767) / Simulation and
                      Data Laboratory Quantum Materials (SDLQM) (SDLQM)},
      pid          = {G:(DE-HGF)POF4-5111 / G:(EU-Grant)823767 /
                      G:(DE-Juel1)SDLQM},
      typ          = {PUB:(DE-HGF)8 / PUB:(DE-HGF)7},
      eprint       = {2205.02491},
      howpublished = {arXiv:2205.02491},
      archivePrefix = {arXiv},
      SLACcitation = {$\%\%CITATION$ = $arXiv:2205.02491;\%\%$},
      doi          = {10.1145/3539781.3539792},
      url          = {https://juser.fz-juelich.de/record/907602},
}