% 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”.

@ARTICLE{Muralikrishnan:1049166,
      author       = {Muralikrishnan, Sriramkrishnan and Speck, Robert},
      title        = {{E}rror {A}nalysis and {P}arallel {S}caling {S}tudy of a
                      {P}arareal {P}arallel-in-{T}ime {I}ntegration {A}lgorithm
                      for {P}article-in-{F}ourier {S}chemes},
      journal      = {SIAM journal on scientific computing},
      volume       = {n/a},
      issn         = {1064-8275},
      address      = {Philadelphia, Pa.},
      publisher    = {SIAM},
      reportid     = {FZJ-2025-05249},
      pages        = {311 - 336},
      year         = {2025},
      note         = {Bitte Post-print ergänzen},
      abstract     = {We propose a parareal based time parallelization scheme in
                      the phase-space for the particle-in-Fourier (PIF)
                      discretization of the Vlasov–Poisson system used in
                      kinetic plasma simulations. We use PIF with a coarse
                      tolerance for the nonuniform fast Fourier transforms, or the
                      standard particle-in-cell scheme, combined with temporal
                      coarsening, as coarse propagators. This is different from
                      the typical spatial coarsening of particles and/or Fourier
                      modes for parareal, which are not possible or effective for
                      PIF schemes. We perform an error analysis of the algorithm
                      and verify the results numerically with Landau damping,
                      two-stream instability, and Penning trap test cases in
                      3D-3V. We also implement the space-time parallelization of
                      the PIF schemes in the open-source, performance-portable
                      library IPPL and conduct scaling studies up to 1536 A100
                      GPUs on the JUWELS booster supercomputer. The space-time
                      parallelization utilizing the parareal algorithm for the
                      time parallelization provides up to 4–6 times speedup
                      compared to spatial parallelization alone and achieves a
                      push rate of around 1 billion particles per second for the
                      benchmark plasma mini-apps considered.},
      cin          = {JSC},
      ddc          = {510},
      cid          = {I:(DE-Juel1)JSC-20090406},
      pnm          = {5112 - Cross-Domain Algorithms, Tools, Methods Labs (ATMLs)
                      and Research Groups (POF4-511)},
      pid          = {G:(DE-HGF)POF4-5112},
      typ          = {PUB:(DE-HGF)16},
      doi          = {10.1137/24M1673097},
      url          = {https://juser.fz-juelich.de/record/1049166},
}