% 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{Orland:1052361,
      author       = {Orland, Fabian and Hilgers, Tom and Hübenthal, Fabian and
                      Sarma, Rakesh and Lintermann, Andreas and Terboven,
                      Christian},
      title        = {{H}ybrid {I}nference {O}ptimization for {AI}-{E}nhanced
                      {T}urbulent {B}oundary {L}ayer {S}imulation on
                      {H}eterogeneous {S}ystems},
      address      = {New York, NY, USA},
      publisher    = {ACM},
      reportid     = {FZJ-2026-00960},
      pages        = {165-176},
      year         = {2026},
      comment      = {Proceedings of the Supercomputing Asia and International
                      Conference on High Performance Computing in Asia Pacific
                      Region Workshops},
      booktitle     = {Proceedings of the Supercomputing Asia
                       and International Conference on High
                       Performance Computing in Asia Pacific
                       Region Workshops},
      abstract     = {Active drag reduction (ADR) using spanwise traveling
                      surface waves is a promising approach to reduce drag of
                      airplanes by manipulating the turbulent boundary layer (TBL)
                      around an airfoil, which directly translates into power
                      savings and lower emission of greenhouse gases harming the
                      environment. However, no analytical solution is known to
                      determine the optimal actuation parameters of these surface
                      waves based on given flow conditions. Data-driven deep
                      learning (DL) techniques from artificial intelligence (AI)
                      area promising alterna tive approach, but their training
                      requires a huge amount of high-fidelity data from
                      computationally expensive computational fluid dynamics (CFD)
                      simulations. Previous works proposed a TBL-Transformer
                      architecture for the expensive time-marching of turbulent
                      flow fields and coupled it with a finite volume solver from
                      the multi-physics PDE solver framework m-AIA to accelerate
                      the generation of TBL data. To accelerate the
                      computationally expensive inference of the TBL-Transformer,
                      the AIxeleratorService library was used to offload the
                      inference task to GPUs. While this approach significantly
                      accelerates the inference task, it leaves the CPU resources
                      allocated by the solver unutilized during inference. To
                      fully exploit modern heterogeneous computer systems, we
                      introduce a hybrid inference method based on a hybrid work
                      distribution model and implement it into the
                      AIxeleratorService library. Moreover, we present a formal
                      model to derive the optimal hybrid work distribution. To
                      evaluate the computational performance and scalability of
                      hybrid inference, we benchmark the coupled m-AIA solver from
                      previous work on a heterogeneous HPC system comprising Intel
                      Sapphire Rapids CPUs and NVIDIA H100 GPUs. Our results show
                      that hybrid inference achieves a performance speedup, that
                      grows as the ratio of allocated CPU cores to GPU devices
                      increases. We further demonstrate that the runtime
                      improvement by hybrid inference also increases the energy
                      efficiency of the coupled solver application. Finally, we
                      highlight that the theoretical hybrid work distribution
                      derived from our formal model yields near optimal results in
                      practice.},
      month         = {Jan},
      date          = {2026-01-26},
      organization  = {SCA/HPCAsia 2026 Workshops:
                       Supercomputing Asia and International
                       Conference on High Performance
                       Computing in Asia Pacific Region
                       Workshops, Osaka (Japan), 26 Jan 2026 -
                       29 Jan 2026},
      cin          = {JSC},
      cid          = {I:(DE-Juel1)JSC-20090406},
      pnm          = {5111 - Domain-Specific Simulation $\&$ Data Life Cycle Labs
                      (SDLs) and Research Groups (POF4-511) / SDLFSE - SDL Fluids
                      $\&$ Solids Engineering (SDLFSE) / RAISE - Research on AI-
                      and Simulation-Based Engineering at Exascale (951733)},
      pid          = {G:(DE-HGF)POF4-5111 / G:(DE-Juel-1)SDLFSE /
                      G:(EU-Grant)951733},
      typ          = {PUB:(DE-HGF)8 / PUB:(DE-HGF)7},
      doi          = {10.1145/3784828.3785255},
      url          = {https://juser.fz-juelich.de/record/1052361},
}