% 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{Mittenbhler:1028652,
      author       = {Mittenbühler, Marcel and Zhang, Junjie and Benigni,
                      Andrea},
      title        = {{A}utomatically optimized component model computation for
                      power system simulation on {GPU}},
      journal      = {Electric power systems research},
      volume       = {235},
      issn         = {0378-7796},
      address      = {Amsterdam [u.a.]},
      publisher    = {Elsevier Science},
      reportid     = {FZJ-2024-04719},
      pages        = {110740 -},
      year         = {2024},
      abstract     = {This work provides an approach that automatically optimizes
                      the component computations on graphics processing unit (GPU)
                      devices from different vendors. The approach consists of a
                      two-level optimization, where the first level considers the
                      linear part of the computation for vectorization and applies
                      mixed matrix formats to increase computational throughput
                      further. Then, the second optimization level treats the
                      combination of linear and non-linear parts as a black box
                      and searches for the optimal configuration of parameters
                      such as the degree of vectorization, the combination of
                      matrix formats, and the group (of threads) sizes during
                      parallel execution on GPU. Moreover, we also introduce
                      constraints that reduce the optimization procedure’s
                      execution time. Finally, we select three different types of
                      components that could be representative to computational
                      tasks in power system and perform our optimization approach
                      on these kernels. The computational performance is compared
                      with unoptimized baseline and sparse linear algebra library
                      based implementations, result shows that our optimization
                      leads to better performance and more efficient memory
                      utilization.},
      cin          = {ICE-1},
      ddc          = {620},
      cid          = {I:(DE-Juel1)ICE-1-20170217},
      pnm          = {1122 - Design, Operation and Digitalization of the Future
                      Energy Grids (POF4-112) / DFG project G:(GEPRIS)450829162 -
                      Raum-Zeit-parallele Simulation multimodale Energiesystemen
                      (450829162)},
      pid          = {G:(DE-HGF)POF4-1122 / G:(GEPRIS)450829162},
      typ          = {PUB:(DE-HGF)16},
      UT           = {WOS:001262510800001},
      doi          = {10.1016/j.epsr.2024.110740},
      url          = {https://juser.fz-juelich.de/record/1028652},
}