% 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{John:1032519,
      author       = {John, Chelsea Maria and Nassyr, Stepan and Herten, Andreas
                      and Penke, Carolin},
      title        = {{CARAML}: {S}ystematic {E}valuation of {AI} {W}orkloads on
                      {A}ccelerators},
      reportid     = {FZJ-2024-06308},
      year         = {2024},
      abstract     = {The rapid advancement of machine learning (ML) technologies
                      has driven the development of specialized hardware
                      accelerators designed to facilitate more efficient model
                      training. This paper introduces the CARAML benchmark suite,
                      which is employed to assess performance and energy
                      consumption during the training of transformer-based large
                      language models and computer vision models on a range of
                      hardware accelerators, including systems from NVIDIA, AMD,
                      and Graphcore. CARAML provides a compact, automated,
                      extensible, and reproducible framework for assessing the
                      performance and energy of ML workloads across various novel
                      hardware architectures. The design and implementation of
                      CARAML, along with a custom power measurement tool called
                      jpwr, are discussed in detail.},
      month         = {Nov},
      date          = {2024-11-05},
      organization  = {OpenGPT-X Forum, Berlin (Germany), 5
                       Nov 2024 - 5 Nov 2024},
      subtyp        = {Other},
      cin          = {JSC},
      cid          = {I:(DE-Juel1)JSC-20090406},
      pnm          = {5112 - Cross-Domain Algorithms, Tools, Methods Labs (ATMLs)
                      and Research Groups (POF4-511) / 5122 - Future Computing
                      $\&$ Big Data Systems (POF4-512) / OpenGPT-X - Aufbau eines
                      Gaia-X Knotens für große KI-Sprachmodelle und innovative
                      Sprachapplikations-Services; Teilvorhaben: Optimierung und
                      Skalierung auf großen HPC-Systemen (68GX21007F) / MAELSTROM
                      - MAchinE Learning for Scalable meTeoROlogy and cliMate
                      (955513) / Verbundprojekt: MAELSTROM - Skalierbarkeit von
                      Anwendungen des Maschinellen Lernens in den Bereichen Wetter
                      und Klimawissenschaften für das zukünftige Supercomputing
                      (16HPC029) / ATML-X-DEV - ATML Accelerating Devices
                      (ATML-X-DEV)},
      pid          = {G:(DE-HGF)POF4-5112 / G:(DE-HGF)POF4-5122 /
                      G:(DE-Juel-1)68GX21007F / G:(EU-Grant)955513 /
                      G:(BMBF)16HPC029 / G:(DE-Juel-1)ATML-X-DEV},
      typ          = {PUB:(DE-HGF)24},
      doi          = {10.34734/FZJ-2024-06308},
      url          = {https://juser.fz-juelich.de/record/1032519},
}