% 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{Muralikrishnan:1049565,
      author       = {Muralikrishnan, Sriramkrishnan and Speck, Robert},
      title        = {{A} {M}assive {S}pace-{T}ime {P}arallel
                      {P}article-{I}n-{F}ourier {F}ramework for {K}inetic {P}lasma
                      {S}imulations},
      reportid     = {FZJ-2025-05369},
      year         = {2025},
      abstract     = {Particle-In-Fourier (PIF) schemes are attractive for
                      long-time integration of kinetic plasma simulations as they
                      conserve charge, momentum and energy (up to time
                      discretization error), exhibit a variational structure, do
                      not have aliasing and have excellent stability properties.
                      However, they are typically more expensive than the commonly
                      used Particle-In-Cell (PIC) schemes due to the requirement
                      of non-uniform discrete Fourier transforms (DFT) or fast
                      Fourier transforms (FFT). In this talk, we propose a
                      Parareal-based parallel-in-time integration method for PIF
                      schemes by employing a PIF scheme of coarser tolerance for
                      nonuniform FFTs or the standard PIC scheme as coarse
                      propagators towards the goal of performing long-time
                      integration simulations. 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 "Independent Parallel Particle Layer" (IPPL) and
                      conduct massively parallel scaling studies on JUWELS and
                      JEDI supercomputers with A100 and GH200 GPUs. The space-time
                      parallelization provides up to $4-6$ times speedup compared
                      to spatial parallelization alone and achieves a push rate of
                      more than 1 billion particles per second for the benchmark
                      plasma mini-apps considered.},
      month         = {May},
      date          = {2025-05-25},
      organization  = {XI International Conference on Coupled
                       Problems in Science and Engineering,
                       Villasimius (Italy), 25 May 2025 - 28
                       May 2025},
      subtyp        = {After Call},
      cin          = {JSC},
      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)6},
      url          = {https://juser.fz-juelich.de/record/1049565},
}