% 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{Oden:863837,
      author       = {Oden, Lena and Schiffer, Christian and Spitzer, Hannah and
                      Dickscheid, Timo and Pleiter, Dirk},
      title        = {{IO} {C}hallenges for {H}uman {B}rain {A}tlasing {U}sing
                      {D}eep {L}earning {M}ethods - {A}n {I}n-{D}epth {A}nalysis},
      publisher    = {IEEE},
      reportid     = {FZJ-2019-03816},
      pages        = {291-298},
      year         = {2019},
      abstract     = {The use of Deep Learning methods have been identified as a
                      key opportunity for enabling processing of extreme-scale
                      scientific datasets. Feeding data into compute nodes
                      equipped with several high-end GPUs at sufficiently high
                      rate is a known challenge. Facilitating processing of these
                      datasets thus requires the ability to store petabytes of
                      data as well as to access the data with very high bandwidth.
                      In this work, we look at two Deep Learning use cases for
                      cytoarchitectonic brain mapping. These applications are very
                      challenging for the underlying IO system. We present an in
                      depth analysis of their IO requirements and performance.
                      Both applications are limited by the IO performance, as the
                      training processes often have to wait several seconds for
                      new training data. Both applications read random patches
                      from a collection of large HDF5 datasets or TIFF files,
                      which result in many small non-consecutive accesses to the
                      parallel file systems. By using a chunked data format or
                      storing temporally copies of the required patches, the IO
                      performance can be improved significantly. These leads to a
                      decrease of the total runtime of up to $80\%.$},
      month         = {Feb},
      date          = {2019-02-13},
      organization  = {2019 27th Euromicro International
                       Conference on Parallel, Distributed and
                       Network-Based Processing (PDP), Pavia
                       (Italy), 13 Feb 2019 - 15 Feb 2019},
      cin          = {INM-1 / JSC},
      cid          = {I:(DE-Juel1)INM-1-20090406 / I:(DE-Juel1)JSC-20090406},
      pnm          = {511 - Computational Science and Mathematical Methods
                      (POF3-511) / 574 - Theory, modelling and simulation
                      (POF3-574) / HBP SGA2 - Human Brain Project Specific Grant
                      Agreement 2 (785907) / HBP SGA1 - Human Brain Project
                      Specific Grant Agreement 1 (720270)},
      pid          = {G:(DE-HGF)POF3-511 / G:(DE-HGF)POF3-574 /
                      G:(EU-Grant)785907 / G:(EU-Grant)720270},
      typ          = {PUB:(DE-HGF)8},
      UT           = {WOS:000467257000041},
      doi          = {10.1109/EMPDP.2019.8671630},
      url          = {https://juser.fz-juelich.de/record/863837},
}